Method, device, equipment and storage medium for determining the validity of remote sensing monitoring data

Through computer equipment and storage media, motor vehicle exhaust monitoring data is obtained and processed, and the calculation of excessive multiple quantile values ​​is calculated, which solves the problem of inaccurate data in the existing technology, improves the accuracy and reliability of judgments of excessive vehicles, and provides for punishment Reliable basis.

CN114757261BActive Publication Date: 2024-11-26PINGAN INT SMART CITY TECH CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202210259424.4
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2022-03-16
Publication Date
2024-11-26
Estimated Expiration
2042-03-16

AI Technical Summary

Technical Problem

The data obtained by existing motor vehicle exhaust remote sensing monitoring equipment is inaccurate, resulting in the inability to effectively screen vehicles exceeding the standard and cannot be supported as evidence for punishment.

Method used

By obtaining vehicle monitoring data at different time periods at the same monitoring point, calculating the excessive multiple quantile value, and determining the standard value of the excessive multiple, it is used to judge the effectiveness of the monitoring data of the to be determined, and improving the accuracy and reliability of the judgment of the excessive vehicle.

Benefits of technology

It improves the accuracy and reliability of motor vehicle exhaust monitoring data, provides a reliable basis for subsequent penalties for vehicles exceeding the standard, and enhances the effectiveness of monitoring data.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN114757261B_ABST
    Figure CN114757261B_ABST
Patent Text Reader

Abstract

The present application proposes a method, device, equipment and storage medium for judging the validity of remote sensing monitoring data, the method comprising: obtaining the first monitoring data of each passing vehicle in each different monitoring time period at the same monitoring point; determining the vehicles exceeding the standard according to the first monitoring data, and calculating the excess multiples of the vehicles exceeding the standard in the excess dimension; performing quantile calculation on the excess multiples, and determining the target excess multiple quantile value of each monitoring dimension in each monitoring time period according to the obtained excess multiple quantile value distribution and the number of vehicles exceeding the standard in each monitoring dimension in each monitoring time period; determining the excess multiple standard value of each monitoring dimension according to the target excess multiple quantile value; and judging the validity of the monitoring data to be estimated for the vehicles to be determined to be exceeding the standard according to the excess multiple standard value. The present application judges the validity of the vehicle monitoring data of the vehicles to be determined to be exceeding the standard according to the obtained excess multiple standard value, and provides a reliable basis for screening the vehicles exceeding the standard.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the technical field of motor vehicle exhaust monitoring, and in particular to a method, device, equipment and storage medium for determining the validity of remote sensing monitoring data. Background Art

[0002] As air pollution becomes increasingly severe, motor vehicle emission regulation will become increasingly important. In order to monitor motor vehicle exhaust emissions, many regions will install motor vehicle exhaust remote sensing monitoring equipment on the road. However, due to the high precision of the equipment and the many factors that affect it, a large amount of monitoring data is inaccurate and cannot be used as a basis for screening vehicles that exceed the standard, nor can it provide evidence to support the subsequent punishment of vehicles that exceed the standard. Summary of the invention

[0003] In order to solve the technical problem of inaccurate vehicle exhaust monitoring data in the prior art, this application provides a method, device, equipment and storage medium for judging the validity of remote sensing monitoring data, the main purpose of which is to judge the validity of vehicle exhaust monitoring data and improve the accuracy and reliability of judging vehicles that exceed the standard.

[0004] To achieve the above purpose, the present application provides a method for determining the validity of remote sensing monitoring data, the method comprising:

[0005] Acquire first monitoring data of each passing vehicle monitored in different monitoring time periods at the same monitoring point, wherein the first monitoring data is acquired by remote sensing monitoring equipment at the monitoring point, and the first monitoring data includes second monitoring data corresponding to the passing vehicle in each monitoring dimension;

[0006] Performing an excess check on the second monitoring data of each passing vehicle, and determining a passing vehicle with at least one second monitoring data exceeding the standard as an excess vehicle;

[0007] Calculate the excess multiple of each over-standard vehicle in the corresponding over-standard dimension, wherein the over-standard dimension is the monitoring dimension corresponding to the second monitoring data of the over-standard vehicle;

[0008] Calculate the quantile value of the excess multiples in the same monitoring dimension within the same monitoring time period to obtain the quantile value distribution of the excess multiples corresponding to each monitoring dimension of the monitoring point in each monitoring time period, wherein the quantile value distribution of the excess multiples includes the quantile value of the excess multiples corresponding to each percentile of the corresponding monitoring dimension;

[0009] Obtain the number of vehicles exceeding the standard detected by synchronous monitoring equipment at the monitoring point during each monitoring time period;

[0010] According to the number of vehicles exceeding the standard in the same monitoring period and the distribution of the excess multiple quantile values ​​corresponding to each monitoring dimension, the target excess multiple quantile value of each monitoring dimension in the corresponding monitoring period is determined;

[0011] According to the target excess multiple quantile value of the same monitoring dimension in all monitoring time periods, the excess multiple standard value of the monitoring point in the corresponding monitoring dimension is obtained;

[0012] According to the standard value of the excess multiples at each monitoring point in each monitoring dimension, the validity of the monitoring data to be estimated for vehicles that are expected to exceed the standard is judged.

[0013] In addition, to achieve the above purpose, the present application also provides a device for determining the validity of remote sensing monitoring data, the device comprising:

[0014] A first data acquisition module is used to acquire first monitoring data of each passing vehicle monitored in different monitoring time periods at the same monitoring point, wherein the first monitoring data is acquired by remote sensing monitoring equipment at the monitoring point, and the first monitoring data includes second monitoring data corresponding to the passing vehicle in each monitoring dimension;

[0015] An over-standard checking module, used for checking the over-standard of the second monitoring data of each passing vehicle, and determining a passing vehicle with at least one second monitoring data exceeding the standard as an over-standard vehicle;

[0016] A first calculation module is used to calculate the excess multiple of each over-standard vehicle in a corresponding over-standard dimension, wherein the over-standard dimension is a monitoring dimension corresponding to the second monitoring data of the over-standard vehicle;

[0017] The second calculation module is used to calculate the quantile value of the excess multiples of the same monitoring dimension in the same monitoring time period, and obtain the quantile value distribution of the excess multiples corresponding to each monitoring dimension of the monitoring point in each monitoring time period, wherein the excess multiple quantile value distribution includes the excess multiple quantile values ​​corresponding to each percentile of the corresponding monitoring dimension;

[0018] The second data acquisition module is used to obtain the number of vehicles exceeding the standard monitored by the synchronous monitoring equipment at the monitoring point in each monitoring time period;

[0019] A reverse determination module is used to determine the target excess multiple quantile value for each monitoring dimension in the corresponding monitoring time period according to the number of vehicles exceeding the standard in the same monitoring time period and the excess multiple quantile value distribution corresponding to each monitoring dimension;

[0020] The standard value determination module is used to obtain the standard value of the excess multiple of the monitoring point in the corresponding monitoring dimension according to the target excess multiple quantile value of the same monitoring dimension in all monitoring time periods;

[0021] The validity judgment module is used to judge the validity of the monitoring data to be estimated for vehicles that exceed the standard according to the standard values ​​of the excess multiples of the monitoring points in each monitoring dimension.

[0022] To achieve the above-mentioned purpose, the present application also provides a computer device, including a memory, a processor, and computer-readable instructions stored in the memory and executable on the processor. When the processor executes the computer-readable instructions, the steps of the method for determining the validity of remote sensing monitoring data as described in any of the preceding items are performed.

[0023] To achieve the above-mentioned purpose, the present application also provides a computer-readable storage medium, on which computer-readable instructions are stored. When the computer-readable instructions are executed by a processor, the processor executes the steps of the method for determining the validity of remote sensing monitoring data as described in any of the preceding items.

[0024] The method, device, equipment and storage medium for judging the validity of remote sensing monitoring data proposed in the present application compile the first monitoring data of passing vehicles at the same monitoring point in different monitoring time periods to obtain the standard value T of the exceeding multiples of the standard at the monitoring point in different monitoring dimensions, and use the standard value T of the exceeding multiples to check the accuracy or validity of the vehicle monitoring data of any vehicle to be determined as exceeding the standard, or make a judgment on the accuracy and validity, which provides a reliable basis for further checking and screening vehicles exceeding the standard. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] Figure 1 This is an application scenario diagram of a method for determining the validity of remote sensing monitoring data in an embodiment of the present application;

[0026] Figure 2 A flowchart of a method for determining the validity of remote sensing monitoring data in an embodiment of the present application;

[0027] Figure 3 This is a structural block diagram of a device for determining the validity of remote sensing monitoring data in one embodiment of the present application;

[0028] Figure 4 This is a block diagram of the internal structure of a computer device in one embodiment of the present application.

[0029] The realization of the purpose, functional features and advantages of this application will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0030] In order to make the purpose, technical scheme and advantages of the embodiments of the present application clearer, the technical scheme in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, rather than all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work belong to the scope of protection of this application. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0031] The method for judging the validity of remote sensing monitoring data provided in this application can be applied in Figure 1 In the application environment, the terminal device can be but not limited to various personal computers, laptops, smart phones, tablet computers and portable wearable devices.

[0032] Figure 2 Schematic diagram of a flow chart of a method for determining the validity of remote sensing monitoring data in an embodiment of the present application. Figure 2 , this method is applied in Figure 1 The method for determining the validity of remote sensing monitoring data includes the following steps S100-S800.

[0033] S100: Obtain first monitoring data of each passing vehicle monitored in different monitoring time periods at the same monitoring point, wherein the first monitoring data is obtained by remote sensing monitoring equipment at the monitoring point, and the first monitoring data includes second monitoring data corresponding to the passing vehicle in each monitoring dimension.

[0034] Specifically, a monitoring point is arranged on each section of the monitored road, and a remote sensing monitoring device and a synchronous monitoring device are arranged at the monitoring point. The monitoring point is specifically a monitoring point position, which corresponds to a monitored section of the road.

[0035] The first monitoring data of each passing vehicle monitored and collected by the remote sensing monitoring equipment at the same monitoring point in different monitoring time periods are obtained. The data of different monitoring time periods are collected in different time periods, and there are passing vehicles in each monitoring time period.

[0036] Different monitoring time periods can be, for example, 12 months in a year, and each month is a monitoring time period. The same monitoring point has 12 sets of monitoring data sets corresponding to 12 months. Each set of monitoring data sets is a data set of the first monitoring data of some passing vehicles or all passing vehicles collected during the corresponding monitoring time period. For example, the first monitoring data of the molecular time period within the monitoring time period is selected to form the monitoring data set of the monitoring time period. The first monitoring data includes the exhaust gas monitoring data of the corresponding passing vehicle. If it is a diesel vehicle, the first monitoring data, i.e., the exhaust gas monitoring data, includes: NO concentration and opacity, etc.; if it is a gasoline vehicle, the first monitoring data, i.e., the exhaust gas monitoring data, includes CO concentration and HC concentration (hydrocarbon concentration). NO concentration, opacity, CO concentration and HC concentration are the second monitoring data corresponding to four different monitoring dimensions or monitoring indicators.

[0037] S200: Perform an excess check on the second monitoring data of each passing vehicle, and determine a passing vehicle with at least one second monitoring data exceeding the standard as an excess vehicle.

[0038] Specifically, the monitoring data set of each monitoring time period includes a large amount of first monitoring data of passing vehicles. If any one or more second monitoring data of a passing vehicle in its corresponding second monitoring data exceeds the standard, the passing vehicle is determined to be an exceeding-standard vehicle.

[0039] For example, if a passing vehicle is a diesel vehicle, then if its first monitoring data satisfies at least one of the two conditions that the NO concentration value exceeds the first threshold and the opacity exceeds the second threshold, then the passing vehicle is determined to be an over-standard vehicle.

[0040] If a passing vehicle is a gasoline vehicle, then if its first monitoring data satisfies at least one of the conditions that the CO concentration value exceeds the third threshold and the HC concentration exceeds the fourth threshold, the passing vehicle is determined to be an over-standard vehicle.

[0041] In addition, some vehicles that exceed the standard in multiple monitoring dimensions may have the second monitoring data exceeding the standard only in some of the monitoring dimensions, while the second monitoring data in other monitoring dimensions do not exceed the standard; it is also possible that the second monitoring data in all monitoring dimensions exceed the standard.

[0042] S300: Calculate the excess multiple of each over-standard vehicle in the corresponding over-standard dimension, wherein the over-standard dimension is the monitoring dimension corresponding to the second monitoring data of the over-standard vehicle.

[0043] Specifically, if a gasoline vehicle exceeds the standard in the monitoring dimension or monitoring indicator of CO concentration, the excess multiple of the vehicle in the exceeding dimension of CO concentration is calculated.

[0044] If a gasoline vehicle exceeds the standard in the monitoring dimension or monitoring indicator of HC concentration, the excess multiple of the vehicle in the exceeding dimension of HC concentration is calculated.

[0045] If a diesel vehicle exceeds the standard in the monitoring dimension or monitoring indicator of NO concentration, the excess multiple of the vehicle in the NO concentration dimension will be calculated.

[0046] If a diesel vehicle exceeds the standard in the monitoring dimension or monitoring indicator of opacity, the multiple of the excess in the dimension of opacity shall be calculated.

[0047] The same vehicle that exceeds the standard has multiples of exceeding the standard in at least one exceeding dimension.

[0048] S400: Calculate the quantile value of the excess multiples in the same monitoring dimension within the same monitoring time period to obtain the quantile value distribution of the excess multiples corresponding to each monitoring dimension of the monitoring point in each monitoring time period, wherein the quantile value distribution of the excess multiples includes the quantile value of the excess multiples corresponding to each percentile in the corresponding monitoring dimension.

[0049] Specifically, in the same monitoring time period, some vehicles that exceeded the standard had excessive NO concentration, some vehicles that exceeded the standard had excessive CO concentration, some vehicles that exceeded the standard had excessive opacity, some vehicles that exceeded the standard had excessive HC concentration, some vehicles that exceeded the standard had excessive HC concentration and excessive CO concentration, and some vehicles that exceeded the standard had excessive NO concentration and excessive opacity. Each vehicle that exceeded the standard corresponds to at least one excess multiple of at least one excess dimension. Therefore, in the same monitoring time period, the same monitoring dimension or the same excess dimension corresponds to multiple excess multiples, and the multiple excess multiples are composed of the excess multiples of multiple different vehicles that exceeded the standard in the same excess dimension.

[0050] In the same monitoring period, all the excess multiples of the same monitoring dimension are clustered and summarized. Then, the excess multiple quantile values ​​at each percentile of the corresponding excess dimension are calculated based on the summary data obtained by clustering. The excess multiple quantile value counts the number of vehicles that exceed the standard at a certain percentile.

[0051] In each monitoring time period, each monitoring dimension corresponds to an excess multiple quantile value distribution, and the excess multiple quantile value distribution includes: the excess multiple quantile value of the 10th percentile, the excess multiple quantile value of the 20th percentile, the excess multiple quantile value of the 30th percentile, the excess multiple quantile value of the 40th percentile, the excess multiple quantile value of the 50th percentile, the excess multiple quantile value of the 60th percentile, the excess multiple quantile value of the 70th percentile, the excess multiple quantile value of the 80th percentile and the excess multiple quantile value of the 90th percentile.

[0052] S500: Obtain the number of vehicles exceeding the standard detected by the synchronous monitoring device at the monitoring point in each monitoring time period.

[0053] Specifically, the synchronous monitoring device can be a black smoke monitoring device. The same monitoring point is provided with two independent monitoring devices, namely a black smoke monitoring device and a remote sensing monitoring device. Both the remote sensing monitoring device and the black smoke monitoring device are used to monitor the relevant data of vehicles passing through the monitoring point. The black smoke monitoring device can identify and count the number of vehicles exceeding the standard in each monitoring time period at the monitoring point.

[0054] S600: Determine the target excess multiple quantile value for each monitoring dimension in the corresponding monitoring time period according to the number of vehicles exceeding the standard and the excess multiple quantile value distribution corresponding to each monitoring dimension in the same monitoring time period.

[0055] Specifically, based on the consistency between the number of vehicles exceeding the standard identified by the black smoke monitoring equipment and the number of vehicles exceeding the standard identified by the remote sensing monitoring equipment within the same monitoring time period, the target excess multiple quantile value of each monitoring dimension within the same monitoring time period is reversely determined.

[0056] For example, the black smoke monitoring equipment detected that the number of vehicles exceeding the standard in January was 100. Then, the excess multiple quantile values ​​corresponding to 100 vehicles were reversely found from the excess multiple quantile value distribution corresponding to the NO concentration in January as the first target excess multiple quantile value of the monitoring dimension of NO concentration in January.

[0057] From the distribution of the excess multiples percentiles corresponding to the opacity in January, reversely find the excess multiples percentiles corresponding to 100 vehicles as the second target excess multiples percentile of the opacity monitoring dimension in January.

[0058] From the distribution of the excess multiples percentiles corresponding to the CO concentration in January, we can reversely find the excess multiples percentiles corresponding to 100 vehicles as the third target excess multiples percentile of the CO concentration monitoring dimension in January.

[0059] From the distribution of the excess multiples percentiles corresponding to the HC concentration in January, reversely find the excess multiples percentiles corresponding to 100 vehicles as the fourth target excess multiples percentile of the monitoring dimension of HC concentration in January.

[0060] The target excess multiple percentile values ​​for each monitoring dimension from February to December are determined by analogy.

[0061] S700: Obtain the standard value of the excess multiple of the monitoring point in the corresponding monitoring dimension according to the target excess multiple quantile value of the same monitoring dimension in all monitoring time periods.

[0062] Specifically, each monitoring dimension in each monitoring time period corresponds to a target excess multiple quantile value, so the same monitoring dimension in all monitoring time periods corresponds to a corresponding number of target excess multiple quantile values. For example, within one year, the NO concentration monitoring dimension corresponds to 12 first target excess multiple quantile values. The opacity monitoring dimension corresponds to 12 second target excess multiple quantile values. The CO concentration monitoring dimension corresponds to 12 third target excess multiple quantile values. The HC concentration monitoring dimension corresponds to 12 fourth target excess multiple quantile values.

[0063] For diesel vehicles, the 12 first target multiples quantile values ​​corresponding to NO concentration and the 12 second target multiples quantile values ​​corresponding to opacity are combined to form 12 two-dimensional first sample points. The coordinates (abscissa and ordinate) of any first sample point are the first target multiples quantile value and the second target multiples quantile value of the same monitoring time period.

[0064] Similarly, for gasoline vehicles, the 12 third target multiples quantile values ​​corresponding to CO concentration and the 12 fourth target multiples quantile values ​​corresponding to HC concentration are combined into 12 two-dimensional second sample points, and the coordinates (abscissa and ordinate) of any second sample point are the third target multiples quantile value and the fourth target multiples quantile value of the same monitoring time period.

[0065] The first sample point and the second sample point are both sample points of a feature space. The center point of all the first sample points and the center point of all the second sample points are found through clustering respectively, and the percentile value of the excess multiples corresponding to the coordinates (horizontal coordinate and vertical coordinate) of the center point is used as the standard value of the excess multiples corresponding to the monitoring point in the corresponding two monitoring dimensions.

[0066] Of course, it is also possible to calculate the mean of all target excess multiples quantile values ​​corresponding to the same monitoring dimension, and use the obtained mean as the excess multiple standard value corresponding to the monitoring point in the monitoring dimension.

[0067] S800: According to the standard value of the excess multiples at the monitoring point in each monitoring dimension, the validity of the monitoring data to be estimated of the vehicle to be determined to exceed the standard is judged.

[0068] Specifically, determine the second monitoring data that exceeds the standard in the monitoring data to be estimated of the vehicle to be determined to have exceeded the standard, determine the corresponding target exceedance multiple standard value based on the target exceedance dimension corresponding to the second monitoring data that exceeds the standard, calculate the target exceedance multiple of the vehicle to be determined to have exceeded the standard in the target exceedance dimension, if the target exceedance multiple is not less than the target exceedance multiple standard value, then the monitoring data to be estimated is determined to be valid; if the target exceedance multiple is less than the target exceedance multiple standard value, then the monitoring data to be estimated is determined to be invalid.

[0069] This embodiment analyzes and organizes the first monitoring data of passing vehicles at the same monitoring point in different monitoring time periods to derive the standard value T of the excess multiples at the monitoring point in different monitoring dimensions, and uses the standard value T to check the accuracy or validity of the vehicle monitoring data of any vehicle to be determined to exceed the standard, or to make a judgment on the accuracy and validity, thereby providing a reliable basis for further inspection and screening of vehicles exceeding the standard.

[0070] In one embodiment, step S100 specifically includes:

[0071] The remote sensing monitoring equipment is calibrated at each monitoring moment corresponding to each monitoring time period, and vehicle monitoring data in the corresponding sub-monitoring time period after the data calibration is completed is obtained, wherein the vehicle monitoring data includes the first monitoring data of each passing vehicle in the corresponding sub-monitoring time period.

[0072] Specifically, a monitoring time period includes the vehicle monitoring data of all its sub-monitoring time periods. A monitoring time period can be divided into multiple sub-monitoring time periods. For example, if a monitoring time period is 1 month, and each day of the month is divided into 3 sub-monitoring time periods, the number of sub-monitoring time periods contained in that month is 3*the number of days in that month.

[0073] In a specific embodiment, each time data calibration is completed, vehicle monitoring data within a preset time period in the corresponding sub-monitoring time period is obtained. The preset time period is not longer than the total time period of the corresponding sub-monitoring time period, for example, it can be within one hour, two hours, etc., but is not limited thereto.

[0074] For example, there are 24 hours in a day. If divided evenly, one day corresponds to three sub-monitoring time periods, and each sub-monitoring time period corresponds to 8 hours. Data calibration is performed every 8 hours. The vehicle monitoring data within 1 hour after the statistical data calibration is completed is used as the vehicle monitoring data of the sub-monitoring time period obtained after this data calibration. Three sets of vehicle monitoring data will be obtained in one day. Each set of vehicle monitoring data contains the first monitoring data of all passing vehicles within 1 hour after the data calibration. The vehicle monitoring data is also the benchmark data, which is a data set. If there are 30 days in a month, the monitoring point can obtain 90 sets of vehicle monitoring data in one month, and these 90 sets of vehicle monitoring data are the monitoring data set corresponding to that month.

[0075] Data calibration is a device calibration operation (calibration with standard gas) to make the data obtained by the monitoring equipment more accurate. Calibration is performed on each monitoring point and each sub-monitoring time period (different time periods). The monitoring data obtained within the preset time period after calibration will be more accurate. Therefore, the data after calibration of each point, for example, 1 hour (1 hour of data may contain thousands of vehicle monitoring data) is used as the benchmark data.

[0076] In one embodiment, step S200 specifically includes:

[0077] Performing Mahalanobis distance calculation on the first monitoring data of each passing vehicle in the same sub-monitoring time period;

[0078] Eliminate the first monitoring data whose Mahalanobis distance is greater than a first preset value;

[0079] comparing the retained second monitoring data of the first monitoring data with a corresponding threshold value;

[0080] A passing vehicle having at least one second monitoring data exceeding the standard is marked as an exceeding-standard vehicle, wherein the exceeding second monitoring data exceeds a corresponding threshold value.

[0081] Specifically, each monitoring time period includes multiple sub-monitoring time periods, each sub-monitoring time period corresponds to a set of vehicle monitoring data, and all vehicle monitoring data corresponding to all sub-monitoring time periods constitute a monitoring data set of the monitoring time period.

[0082] Each set of vehicle monitoring data includes first monitoring data corresponding to a passing vehicle, and the first monitoring data of each passing vehicle includes second monitoring data corresponding to each monitoring dimension.

[0083] Before determining which passing vehicles are exceeding the standard, the first monitoring data that does not meet the conditions needs to be eliminated.

[0084] In this embodiment, the vehicle monitoring data of a sub-monitoring time period is used as a whole to calculate the Mahalanobis distance, and the second monitoring data of each dimension in the first monitoring data corresponding to each passing vehicle in the same vehicle monitoring data can obtain a Mahalanobis distance. The first preset value includes the sub-preset values ​​corresponding to each dimension. If the Mahalanobis distance of a passing vehicle in at least one dimension is greater than the corresponding sub-preset value, the first monitoring data corresponding to the Mahalanobis distance is determined to be an outlier, and the first monitoring data that is an outlier is removed from the corresponding vehicle monitoring data.

[0085] The calculation of Mahalanobis distance is shown in formula (1):

[0086]

[0087] Among them, μ is the sample mean of all data points in the vehicle monitoring data of the corresponding sub-monitoring time period in the same monitoring dimension, x is the second monitoring data of a passing vehicle in the corresponding sub-monitoring time period in the same monitoring dimension, and Σ is the covariance matrix of the multidimensional random variable composed of all the second monitoring data corresponding to the same monitoring dimension in the corresponding sub-monitoring time period. The second monitoring data in the first monitoring data of a passing vehicle constitutes a data point.

[0088] According to formula (1), the Mahalanobis distance corresponding to the first monitoring data of each passing vehicle in each monitoring dimension in the same sub-monitoring time period can be calculated. If the Mahalanobis distance of any passing vehicle in at least one monitoring dimension is greater than the corresponding sub-preset value, the first monitoring data corresponding to the passing vehicle is determined to be an outlier.

[0089] The sub-preset values ​​in the first preset value can be determined by chi-square distribution. The critical value is determined according to the given test level and degree of freedom, and the critical value is the first preset value. If the Mahalanobis distance of an individual is greater than the critical value, it is determined that the data corresponding to the outlier under the test level should be eliminated, otherwise it is retained. The commonly used test level α = 0.005 or 0.001 is the standard for judging multivariate outliers.

[0090] After eliminating the vehicle monitoring data that are outliers, the first monitoring data of each passing vehicle in the remaining vehicle monitoring data is checked for excess values. If any one or more second monitoring data in the first monitoring data of a passing vehicle exceeds the corresponding threshold, the passing vehicle is determined to be an excess vehicle.

[0091] In another embodiment, step S200 specifically includes:

[0092] The vehicle monitoring data of each sub-monitoring time period corresponding to each monitoring time period is divided into first vehicle monitoring data corresponding to diesel vehicles and second vehicle monitoring data corresponding to gasoline vehicles according to vehicle types;

[0093] Performing Mahalanobis distance calculation on the first monitoring data of each passing vehicle in the first vehicle monitoring data of the same sub-monitoring time period respectively;

[0094] Performing Mahalanobis distance calculation on the first monitoring data of each passing vehicle in the second vehicle monitoring data of the same sub-monitoring time period;

[0095] Eliminate the first monitoring data whose Mahalanobis distance is greater than the first sub-preset value in the first vehicle monitoring data, and eliminate the first monitoring data whose Mahalanobis distance is greater than the second sub-preset value in the second vehicle monitoring data;

[0096] comparing the second monitoring data of the first monitoring data retained in the first vehicle monitoring data and the second vehicle monitoring data with the corresponding threshold value;

[0097] A passing vehicle having at least one second monitoring data exceeding the standard is marked as an exceeding-standard vehicle, wherein the exceeding second monitoring data exceeds a corresponding threshold value.

[0098] In one embodiment, step S300 specifically includes:

[0099] Determine a first number of non-exceeding vehicles that are in close proximity to the exceeding vehicles at the time of driving, wherein the exceeding vehicles and the corresponding non-exceeding vehicles use the same vehicle driving energy;

[0100] The second monitoring data corresponding to the same exceeding dimension in the first monitoring data of the non-exceeding vehicle are averaged to obtain a first average of the corresponding exceeding dimension, wherein the exceeding dimension is the monitoring dimension corresponding to the second monitoring data of the exceeding vehicle;

[0101] According to the second monitoring data corresponding to the same exceeding dimension of the exceeding vehicle and the first mean value, the exceeding multiple of the exceeding vehicle in the corresponding exceeding dimension is calculated;

[0102] The quantile values ​​of all the excess multiples corresponding to each monitoring dimension in the same monitoring time period are calculated respectively to obtain the percentile quantile value distribution corresponding to each monitoring dimension of the monitoring point in each monitoring time period, where the percentile quantile value distribution includes the excess multiple quantile values ​​corresponding to each percentile.

[0103] Specifically, the non-exceeding vehicles whose driving time is immediately adjacent to the over-standard vehicle are the first number of normal vehicles whose driving time is before and / or after the driving time of the over-standard vehicle, and the over-standard vehicle and the corresponding normal vehicle both use the same vehicle driving energy. For example, the over-standard vehicle and the corresponding non-exceeding vehicle both use gasoline to drive, that is, both are gasoline vehicles; for another example, the over-standard vehicle and the corresponding non-exceeding vehicle both use diesel to drive, that is, both are diesel vehicles.

[0104] If only one of the second monitoring data corresponding to one monitoring dimension of an over-standard vehicle exceeds the standard, only the over-standard multiple corresponding to the dimension of the over-standard vehicle is calculated. If the second monitoring data corresponding to both monitoring dimensions of the over-standard vehicle exceeds the standard, the over-standard multiple corresponding to each over-standard dimension of the over-standard vehicle needs to be calculated.

[0105] The first mean value of the non-exceeding vehicles corresponding to any one of the exceeding vehicles in a certain exceeding dimension is the mean value of the second monitoring data of all the corresponding non-exceeding vehicles in the exceeding dimension.

[0106] If only one of the second monitoring data corresponding to one monitoring dimension of an over-standard vehicle exceeds the standard, the over-standard vehicle will correspond to an over-standard multiple in that monitoring dimension. If the second monitoring data corresponding to two monitoring dimensions of the over-standard vehicle exceed the standard, the over-standard vehicle will correspond to an over-standard multiple in each over-standard dimension.

[0107] The excess multiple of an over-standard vehicle in any over-standard dimension is the ratio of the absolute value of the difference between the second monitoring data of the over-standard vehicle in the over-standard dimension and the first mean value corresponding to the same over-standard dimension to the first mean value.

[0108] The calculation formula for the excess multiple of any vehicle in any corresponding excess dimension is shown in formula (2):

[0109] Qi=|Wi-Ai| / Ai Formula (2)

[0110] Among them, Qi is the excess multiple of the over-standard vehicle in a certain over-standard dimension, Ai is the average of the second monitoring data of the first number of non-over-standard vehicles corresponding to the over-standard vehicle in the over-standard dimension, and Wi is the second monitoring data of the over-standard vehicle in the over-standard dimension.

[0111] Based on the above, it is possible to determine which vehicles exceed the standard in each monitoring time period, as well as the excess multiples corresponding to each vehicle that exceeds the standard.

[0112] The first number may be 10, 20, etc., but is not limited thereto.

[0113] In one embodiment, the specific implementation steps of step S400 are:

[0114] Cluster all the excess multiples corresponding to all vehicles exceeding the standard in the same monitoring period.

[0115] Cluster the excess multiples of the same monitoring dimension in the same monitoring time period according to the excess dimension of the excess multiples.

[0116] The quantile value of the excess multiples corresponding to the same excess dimension in the same monitoring time period is calculated to obtain the quantile value distribution of the excess multiples of the excess dimension in the monitoring time period.

[0117] Specifically, the excess multiples corresponding to the same excess dimension in the same monitoring period are classified into one category. The calculation method for the excess multiple quantile value of the pth percentile of any excess dimension in the same monitoring period is as follows:

[0118] The pollutant concentration sequence corresponding to a certain exceeding dimension or monitoring dimension is sorted from small to large in numerical value. The sorted concentration sequence is {X(i), i=1,2,…n}.

[0119] Calculate the pth percentile m p The ordinal number k of is calculated according to formula (3):

[0120] k=1+(n-1)·p% Formula (3)

[0121] In formula (3):

[0122] k——the ordinal number corresponding to the p% position.

[0123] n – the number of concentration values ​​in the pollutant concentration series.

[0124] The pth percentile mp Calculate according to formula (4):

[0125] m p =X (s) +(X (s+1) -X (s) )×(ks) Formula (4)

[0126] In formula (4):

[0127] S--the integer part of k. When k is an integer, s is equal to k.

[0128] The distribution of the excess multiple quantile values ​​corresponding to the same excess dimension in the same monitoring period is shown below:

[0129] Exceeding the standard by tens of percentiles: Q10

[0130] Exceeding the standard multiple 20th percentile: Q20

[0131] Thirty percentile of excess multiples: Q30

[0132] Exceeding the standard multiple forty percentile: Q40

[0133] Exceeding the standard multiple 50th percentile: Q50

[0134] Exceeding the standard multiple sixty percentile: Q60

[0135] Exceeding the standard multiple seventy percentile: Q70

[0136] Exceeding the standard multiple 80th percentile: Q80

[0137] Exceeding the standard multiple ninety percentile: Q90

[0138] Percentile is also called quantile value or percentile value. In statistics, if a set of data is sorted from small to large and the corresponding cumulative percentile is calculated, the value of the data corresponding to a certain percentile is called the percentile of this percentile. It can be expressed as: a set of n observations are arranged according to the numerical value, for example, the value at the p% position is called the pth percentile.

[0139] In one embodiment, the synchronous monitoring device includes a black smoke monitoring device, and step S500 specifically includes:

[0140] Obtain the Ringelmann blackness of each passing vehicle monitored by the black smoke monitoring equipment at the monitoring point during each monitoring time period;

[0141] According to the Ringelmann blackness, it is determined whether the corresponding passing vehicle is an over-standard vehicle, and the number of over-standard vehicles in the corresponding monitoring time period is obtained by counting.

[0142] Specifically, the black smoke monitoring equipment identifies vehicles that exceed the standard by monitoring the Ringelmann blackness of the exhaust gas of passing vehicles. Vehicles with a Ringelmann blackness greater than or equal to 1 are identified as vehicles that exceed the standard. Both remote sensing monitoring equipment and black smoke monitoring equipment monitor the exhaust data of passing vehicles. Remote sensing monitoring equipment can analyze data from different monitoring dimensions to determine vehicles that exceed the standard, and specifically determine which dimensions of data exceed the standard. The black smoke monitoring equipment determines whether a passing vehicle is an over-standard vehicle from an overall perspective.

[0143] In one embodiment, step S600 specifically includes:

[0144] Among all the excess multiples quantiles corresponding to the same monitoring dimension in the same monitoring time period, the excess multiples quantile that is the same as or closest to the corresponding number of exceeding vehicles shall be used as the target excess multiples quantile of the corresponding monitoring dimension in the monitoring time period.

[0145] Specifically, for example, in the monitoring period of January, among the 9 excess multiples percentile values ​​corresponding to the NO concentration monitoring dimension, the excess multiples percentile value that is the same as or closest to the number of vehicles exceeding the standard in January is the excess multiples percentile value Q20 corresponding to the 20th percentile of the excess multiples. Then, the excess multiples percentile value Q20 corresponding to the 20th percentile of the excess multiples will be used as the target excess multiples percentile value for the NO concentration monitoring dimension in January.

[0146] For another example, in the monitoring period of January, among the 9 excess multiples percentile values ​​corresponding to the CO concentration monitoring dimension, the excess multiples percentile value that is the same as or closest to the number of vehicles exceeding the standard in January is the excess multiples percentile value Q30 corresponding to the 30th percentile of the excess multiples. Then the excess multiples percentile value Q30 corresponding to the 30th percentile of the excess multiples will be used as the target excess multiples percentile value for the CO concentration monitoring dimension in January.

[0147] In one embodiment, step S700 specifically includes:

[0148] The corresponding sample points are constructed using the excess multiple quantile value pairs as sample point coordinates, wherein the excess multiple quantile value pairs include the target excess multiple quantile values ​​of the monitoring dimension corresponding to the same type of vehicles in the same monitoring time period;

[0149] According to the mean shift algorithm, all sample points corresponding to the same type of vehicles in all monitoring time periods are clustered to obtain the corresponding center points;

[0150] The coordinates of the calculated center point are used as the standard values ​​of the excess multiples of the monitoring point in the corresponding monitoring dimensions.

[0151] Specifically, vehicles of the same type refer to vehicles that use the same vehicle driving energy. For example, if they are all powered by gasoline, they are all gasoline vehicles; for another example, if they are all powered by diesel, they are all diesel vehicles. The target excess multiple quantile values ​​of the monitoring dimension corresponding to the same type of vehicles in the same monitoring time period of the monitoring point are used as the sample point coordinates to construct the corresponding sample points.

[0152] For example, from January to December, there are 12 first target excess multiple quantiles corresponding to the NO concentration monitoring dimension, and 12 second target excess multiple quantiles corresponding to the opacity monitoring dimension. Take the first target excess multiple quantile corresponding to the NO concentration in January and the second target excess multiple quantile corresponding to the opacity as the horizontal and vertical coordinates of a first sample point to construct a first sample point. Take the first target excess multiple quantile corresponding to the NO concentration in February and the second target excess multiple quantile corresponding to the opacity as the horizontal and vertical coordinates of another first sample point to construct another first sample point. And so on, 12 first sample points can be constructed.

[0153] For another example, from January to December, there are 12 third target excess multiple quantiles corresponding to the CO concentration monitoring dimension, and 12 fourth target excess multiple quantiles corresponding to the HC concentration monitoring dimension. The third target excess multiple quantile corresponding to the CO concentration in January and the fourth target excess multiple quantile corresponding to the HC concentration are used as the horizontal and vertical coordinates of a second sample point to construct a second sample point. The third target excess multiple quantile corresponding to the CO concentration in February and the fourth target excess multiple quantile corresponding to the HC concentration are used as the horizontal and vertical coordinates of another second sample point to construct another second sample point. By analogy, 12 second sample points can be constructed.

[0154] The first center points of the 12 first sample points and the second center points of the 12 second sample points are obtained by the mean shift method. The coordinates of the first center point are calculated, and the value of the coordinates of the first center point is the standard value of the excess multiple of the monitoring point in the corresponding monitoring dimension. For example, the horizontal and vertical coordinates of the first center point are the standard values ​​T1 and T2 of the excess multiple of the two monitoring dimensions of NO concentration and opacity, respectively. The coordinates of the second center point are calculated, and the value of the coordinates of the second center point is the standard value of the excess multiple of the monitoring point in the corresponding monitoring dimension. For example, the horizontal and vertical coordinates of the second center point are the standard values ​​T3 and T4 of the excess multiple of the two monitoring dimensions of CO concentration and HC concentration, respectively.

[0155] The mean shift algorithm is as follows:

[0156] Imagine that in a feature space with N sample points, a center point x is initially determined, and the vectors of all sample points (xi) and the center point x in a circular space with a set radius of D are calculated. The average value of all vectors in the entire circular space is calculated to obtain an offset mean. The offset mean formula is shown in formula (5):

[0157]

[0158] S h : A high-dimensional sphere region with x as the center and radius h; k: contained in S h The number of sample points within the range; xi: included in S h Any sample point within the range.

[0159] The initial center point x is moved by the offset mean to obtain the current center point, and it is determined whether the current center point meets the end condition. If it does not meet the end condition, the next offset mean is recalculated based on the vector of the current center point x and the sample point xi, and the current center point is moved by the next offset mean to obtain the next center point, and it is determined again whether the next center point meets the end condition. The movement is repeated in this way until a certain end condition is met and the movement is stopped. The center point coordinate update formula is shown in formula (6):

[0160] x t+1 =M t +x t Formula (6)

[0161] M t is the mean offset value obtained at state t or node t; x t The coordinates of the center point under the t state or t node.

[0162] The specific idea of ​​the mean shift algorithm is to find an area with the highest density (a circular area in two-dimensional space), so the end condition is that the circular space with a radius of D contains the most points or the number of points contained no longer increases.

[0163] The coordinates of the center point on each axis finally obtained are the standard values ​​of the excess multiples of the corresponding monitoring dimensions.

[0164] In one embodiment, step S800 specifically includes:

[0165] Acquire the monitoring data to be estimated of the pending over-standard vehicle determined as the over-standard vehicle, wherein the monitoring data to be estimated includes the second monitoring data of the pending over-standard vehicle in each monitoring dimension;

[0166] According to the exceeding dimension corresponding to the second monitoring data exceeding the standard in the monitoring data to be estimated, the corresponding exceeding multiple standard value is obtained as the target exceeding multiple standard value;

[0167] Calculate the excess multiple of the vehicle to be determined to have exceeded the standard in the corresponding excess dimension as the target excess multiple;

[0168] If the target exceedance multiple is not less than the target exceedance multiple standard value corresponding to the same exceedance dimension, the monitoring data to be estimated is determined to be valid.

[0169] Specifically, this embodiment matches and compares data of the same monitoring dimension.

[0170] If the vehicle to be determined to have exceeded standards has two exceeding standards dimensions, and the target exceeding standards multiples of the two exceeding standards dimensions are not less than the target exceeding standards multiples standard values ​​corresponding to the same exceeding standards dimensions, then the monitoring data to be estimated for the vehicle to be determined to have exceeded standards is determined to be valid.

[0171] If the vehicle to be determined to have exceeded standards has two exceeding dimensions, and at least one of the two exceeding dimensions has a target exceeding multiple corresponding to it that is smaller than the target exceeding multiple standard value corresponding to the same exceeding dimension, then the monitoring data to be estimated for the vehicle to be determined to have exceeded standards is determined to be invalid.

[0172] The present application compiles the first monitoring data of passing vehicles at the same monitoring point in different monitoring time periods to obtain the standard value T of the excess multiples at the monitoring point in different monitoring dimensions, and uses the standard value T to check the accuracy or validity of the vehicle monitoring data of any vehicle to be determined to exceed the standard, or to make a judgment on the accuracy and validity, which provides a reliable basis for further checking and screening vehicles that exceed the standard.

[0173] It should be understood that the size of the serial numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0174] Figure 3 This is a structural block diagram of a device for determining the validity of remote sensing monitoring data in an embodiment of the present application. Figure 3 , the remote sensing monitoring data validity judgment device includes:

[0175] The first data acquisition module 100 is used to acquire first monitoring data of each passing vehicle monitored in different monitoring time periods at the same monitoring point, wherein the first monitoring data is acquired by remote sensing monitoring equipment at the monitoring point, and the first monitoring data includes second monitoring data corresponding to the passing vehicle in each monitoring dimension;

[0176] The excess checking module 200 is used to check the excess of the second monitoring data of each passing vehicle, and determine the passing vehicle with at least one second monitoring data exceeding the standard as an excess vehicle;

[0177] The first calculation module 300 is used to calculate the excess multiple of each over-standard vehicle in the corresponding over-standard dimension, wherein the over-standard dimension is the monitoring dimension corresponding to the second monitoring data of the over-standard vehicle;

[0178] The second calculation module 400 is used to calculate the quantile value of the excess multiples of the same monitoring dimension in the same monitoring time period, and obtain the quantile value distribution of the excess multiples corresponding to each monitoring dimension of the monitoring point in each monitoring time period, wherein the excess multiple quantile value distribution includes the excess multiple quantile value corresponding to each percentile of the corresponding monitoring dimension;

[0179] The second data acquisition module 500 is used to obtain the number of vehicles exceeding the standard monitored by the synchronous monitoring device at the monitoring point in each monitoring time period;

[0180] A reverse determination module 600 is used to determine the target excess multiple quantile value of each monitoring dimension in the corresponding monitoring time period according to the number of vehicles exceeding the standard in the same monitoring time period and the excess multiple quantile value distribution corresponding to each monitoring dimension;

[0181] The standard value determination module 700 is used to obtain the standard value of the excess multiple of the monitoring point in the corresponding monitoring dimension according to the target excess multiple quantile value of the same monitoring dimension in all monitoring time periods;

[0182] The validity judgment module 800 is used to judge the validity of the monitoring data to be estimated of the vehicle that is to be determined to exceed the standard according to the standard value of the excess multiples of the monitoring point in each monitoring dimension.

[0183] The device for determining the validity of remote sensing monitoring data is generally set in the server / terminal device.

[0184] In one embodiment, the first data acquisition module 100 specifically includes:

[0185] A data calibration and acquisition module is used to perform data calibration on the remote sensing monitoring equipment at each monitoring moment corresponding to each monitoring time period, and obtain vehicle monitoring data in the corresponding sub-monitoring time period after the data calibration is completed, wherein the vehicle monitoring data includes the first monitoring data of each passing vehicle in the corresponding sub-monitoring time period;

[0186] The data statistics module is used to use the vehicle monitoring data in all sub-monitoring time periods in the corresponding monitoring time period as the first monitoring data in the corresponding monitoring time period.

[0187] In one embodiment, the over-standard verification module 200 specifically includes:

[0188] A first sub-calculation module, used for calculating the Mahalanobis distance of the first monitoring data of each passing vehicle in the same sub-monitoring time period;

[0189] A data elimination module, used to eliminate first monitoring data whose Mahalanobis distance is greater than a first preset value;

[0190] A numerical comparison module, used for comparing the second monitoring data of the retained first monitoring data with a corresponding threshold value;

[0191] The exceeding standard determination module is used to mark a passing vehicle with at least one second monitoring data exceeding the standard as an exceeding standard vehicle, wherein the second monitoring data exceeding the standard exceeds a corresponding threshold value.

[0192] In one embodiment, the first calculation module 300 specifically includes:

[0193] a non-exceeding-standard vehicle determination module, configured to determine a first number of non-exceeding-standard vehicles that are adjacent to the exceeding-standard vehicles at a driving time, wherein the exceeding-standard vehicles and the corresponding non-exceeding-standard vehicles use the same vehicle driving energy;

[0194] The second sub-calculation module is used to average the second monitoring data corresponding to the same exceeding dimension in the first monitoring data of the non-exceeding vehicle to obtain a first average of the corresponding exceeding dimension, wherein the exceeding dimension is the monitoring dimension corresponding to the second monitoring data of the exceeding vehicle;

[0195] The third sub-calculation module is used to calculate the excess multiple of the over-standard vehicle in the corresponding excess dimension according to the second monitoring data corresponding to the over-standard vehicle in the same excess dimension and the first mean value;

[0196] The fourth sub-calculation module is used to calculate the percentile values ​​of all the excess multiples corresponding to each monitoring dimension in the same monitoring time period, and obtain the percentile quantile value distribution corresponding to each monitoring dimension of the monitoring point in each monitoring time period, wherein the percentile quantile value distribution includes the excess multiples quantile value corresponding to each percentile.

[0197] In one embodiment, the synchronous monitoring device includes a black smoke monitoring device, and the second data acquisition module 500 specifically includes:

[0198] The black smoke data collection module is used to obtain the Ringelmann blackness of each passing vehicle monitored by the black smoke monitoring equipment at the monitoring point during each monitoring time period;

[0199] The over-standard vehicle statistics module is used to determine whether the corresponding passing vehicle is an over-standard vehicle according to the Ringelmann blackness, and to obtain the number of over-standard vehicles in the corresponding monitoring time period.

[0200] In one embodiment, the reverse determination module 600 is specifically used to use the excess multiple quantile value that is the same as or closest to the corresponding number of exceeding vehicles among all the excess multiple quantile values ​​corresponding to the same monitoring dimension in the same monitoring time period as the target excess multiple quantile value of the monitoring dimension corresponding to the monitoring time period.

[0201] In one embodiment, the standard value determination module 700 specifically includes:

[0202] A sample point establishment module is used to construct corresponding sample points using the excess multiple quantile value pairs as sample point coordinates, wherein the excess multiple quantile value pairs include target excess multiple quantile values ​​of the monitoring dimension corresponding to the same type of vehicles in the same monitoring time period;

[0203] The center point determination module is used to cluster all sample points corresponding to the same type of vehicles in all monitoring time periods according to the mean shift algorithm to obtain the corresponding center point;

[0204] The standard value calculation module is used to calculate the coordinates of the center point as the standard value of the excess multiple of the monitoring point in the corresponding monitoring dimension.

[0205] In one embodiment, the validity determination module 800 specifically includes:

[0206] A third data acquisition module is used to acquire the monitoring data to be estimated of the pending over-standard vehicle determined as the over-standard vehicle, wherein the monitoring data to be estimated includes the second monitoring data of the pending over-standard vehicle in each monitoring dimension;

[0207] A standard value matching module, used for obtaining a corresponding standard value of the excess multiple according to the excess dimension corresponding to the second monitoring data exceeding the standard in the monitoring data to be estimated as a target standard value of the excess multiple;

[0208] The third calculation module is used to calculate the excess multiple of the vehicle to be determined to be over-standard in the corresponding excess dimension as the target excess multiple;

[0209] The validity determination module is used to determine that the monitoring data to be estimated is valid if the target exceedance multiple is not less than the target exceedance multiple standard value corresponding to the same exceedance dimension.

[0210] The meaning of "first" and "second" in the above modules / units is only to distinguish different modules / units, and is not used to define which module / unit has a higher priority or other limiting meanings. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or modules is not necessarily limited to those steps or modules clearly listed, but may include other steps or modules that are not clearly listed or inherent to these processes, methods, products or devices. The division of modules in this application is only a logical division, and there may be other division methods when implemented in actual applications.

[0211] The specific definition of the remote sensing monitoring data validity judgment device can refer to the definition of the remote sensing monitoring data validity judgment method mentioned above, which will not be repeated here. Each module in the above remote sensing monitoring data validity judgment device can be implemented in whole or in part by software, hardware and a combination thereof. The above modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

[0212] Figure 4 This is a block diagram of the internal structure of a computer device in one embodiment of the present application. The computer device may specifically be Figure 1 The terminal device in. Figure 4 As shown, the computer device includes a processor, a memory, a network interface, an input device and a display screen connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory includes a storage medium and an internal memory. The storage medium can be a non-volatile storage medium or a volatile storage medium. The storage medium stores an operating system and can also store computer-readable instructions. When the computer-readable instructions are executed by the processor, the processor can implement a method for determining the validity of remote sensing monitoring data. The internal memory provides an environment for the operation of the operating system and computer-readable instructions in the storage medium. The internal memory can also store computer-readable instructions. When the computer-readable instructions are executed by the processor, the processor can execute a method for determining the validity of remote sensing monitoring data. The network interface of the computer device is used to communicate with an external server through a network connection. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covered on the display screen, or a key, trackball or touchpad set on the shell of the computer device, or an external keyboard, touchpad or mouse.

[0213] In one embodiment, a computer device is provided, including a memory, a processor, and computer-readable instructions (such as a computer program) stored in the memory and executable on the processor. When the processor executes the computer-readable instructions, the steps of the method for determining the validity of remote sensing monitoring data in the above embodiment are implemented, such as Figure 2 Alternatively, when the processor executes the computer-readable instructions, the functions of each module / unit of the device for determining the validity of remote sensing monitoring data in the above embodiment are realized, for example Figure 3 The functions of the modules 100 to 800 are shown in detail and will not be described again to avoid repetition.

[0214] The processor may be a central processing unit (CPU), other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc. The processor is the control center of a computer device, and uses various interfaces and lines to connect various parts of the entire computer device.

[0215] The memory can be used to store computer-readable instructions and / or modules. The processor implements various functions of the computer device by running or executing the computer-readable instructions and / or modules stored in the memory and calling the data stored in the memory. The memory can mainly include a program storage area and a data storage area. The program storage area can store an operating system, an application required for at least one function (such as a sound playback function, an image playback function, etc.), etc.; the data storage area can store data created according to the use of the mobile phone (such as audio data, video data, etc.), etc.

[0216] The memory may be integrated into the processor or provided separately from the processor.

[0217] Those skilled in the art will understand that Figure 4 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0218] In one embodiment, a computer-readable storage medium is provided, on which computer-readable instructions are stored. When the computer-readable instructions are executed by a processor, the steps of the method for determining the validity of remote sensing monitoring data in the above embodiment are implemented, such as Figure 2 Alternatively, when the computer-readable instructions are executed by the processor, the functions of each module / unit of the device for determining the validity of remote sensing monitoring data in the above embodiment are realized, for example Figure 3 The functions of the modules 100 to 800 are shown in detail and will not be described again to avoid repetition.

[0219] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through computer-readable instructions, and the computer-readable instructions can be stored in a computer-readable storage medium. When the computer-readable instructions are executed, they can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in the present application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0220] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, device, article or method including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, device, article or method. In the absence of further restrictions, an element defined by the sentence "includes a ..." does not exclude the existence of other identical elements in the process, device, article or method including the element.

[0221] The serial numbers of the embodiments of the present application are for description only and do not represent the advantages and disadvantages of the embodiments. Through the description of the above implementation modes, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course, by hardware, but in many cases the former is a better implementation mode. Based on such an understanding, the technical solution of the present application is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) as described above, including a number of instructions to enable a terminal device (which can be a mobile phone, a computer, a server, or a network device, etc.) to execute the methods described in each embodiment of the present application.

[0222] The above are only preferred embodiments of the present application, and are not intended to limit the patent scope of the present application. Any equivalent structure or equivalent process transformation made using the contents of the present application specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present application.

Claims

1. A method for determining the validity of remote sensing monitoring data, characterized in that: The method comprises: Acquire first monitoring data of each passing vehicle monitored in different monitoring time periods at the same monitoring point, wherein the first monitoring data is acquired by remote sensing monitoring equipment at the monitoring point, and the first monitoring data includes second monitoring data corresponding to the passing vehicle in each monitoring dimension; Performing an excess check on the second monitoring data of each of the passing vehicles, and determining a passing vehicle having at least one second monitoring data exceeding the standard as an excess vehicle; Calculate the excess multiples of each of the exceeded vehicles in the corresponding exceeded dimension, wherein the exceeded dimension is the monitoring dimension corresponding to the second monitoring data of the exceeded vehicle; the calculation of the excess multiples of each of the exceeded vehicles in the corresponding exceeded dimension includes: determining a first number of non-exceeded vehicles that are adjacent to the exceeded vehicle at the time of driving, wherein the exceeded vehicle and the corresponding non-exceeded vehicle use the same vehicle driving energy; average the second monitoring data corresponding to the same exceeded dimension in the first monitoring data of the non-exceeded vehicles, and obtain the first average value of the corresponding exceeded dimension. value, wherein the exceeding dimension is the monitoring dimension corresponding to the second monitoring data of the exceeding vehicle; according to the second monitoring data corresponding to the exceeding vehicle in the same exceeding dimension and the first mean value, the exceeding multiple of the exceeding vehicle in the corresponding exceeding dimension is calculated; the quantile values ​​of all the exceeding multiples corresponding to each monitoring dimension in the same monitoring time period are calculated respectively, and the percentile quantile value distribution corresponding to each monitoring dimension of the monitoring point in each monitoring time period is obtained, wherein the percentile quantile value distribution includes the exceeding multiple quantile values ​​corresponding to each percentile; Calculate the quantile value of the excess multiples of the same monitoring dimension in the same monitoring time period to obtain the quantile value distribution of the excess multiples corresponding to each monitoring dimension of the monitoring point in each monitoring time period, wherein the quantile value distribution of the excess multiples includes the quantile value of the excess multiples corresponding to each percentile of the corresponding monitoring dimension; Obtaining the number of vehicles exceeding the standard monitored by the synchronous monitoring equipment at the monitoring point in each monitoring time period; According to the number of vehicles exceeding the standard in the same monitoring time period and the distribution of the excess multiple quantile values ​​corresponding to each monitoring dimension, determine the target excess multiple quantile value for each monitoring dimension in the corresponding monitoring time period; According to the target excess multiple quantile value of the same monitoring dimension in all monitoring time periods, the excess multiple standard value of the monitoring point in the corresponding monitoring dimension is obtained; According to the standard value of the excess multiples at the monitoring point in each monitoring dimension, the validity of the monitoring data to be estimated of the vehicle to be determined to exceed the standard is judged.

2. The method according to claim 1, characterized in that The obtaining of first monitoring data of each passing vehicle monitored in different monitoring time periods at the same monitoring point includes: The remote sensing monitoring device is calibrated at each monitoring moment corresponding to each monitoring time period, and vehicle monitoring data in the corresponding sub-monitoring time period after the data calibration is completed is obtained, wherein the vehicle monitoring data includes the first monitoring data of each passing vehicle in the corresponding sub-monitoring time period.

3. The method according to claim 2, characterized in that The step of checking the second monitoring data of each passing vehicle for exceeding the standard and determining a passing vehicle having at least one second monitoring data exceeding the standard as an exceeding-standard vehicle comprises: Performing Mahalanobis distance calculation on the first monitoring data of each passing vehicle in the same sub-monitoring time period; Eliminate the first monitoring data whose Mahalanobis distance is greater than a first preset value; comparing the retained second monitoring data of the first monitoring data with a corresponding threshold value; A passing vehicle having at least one second monitoring data exceeding the standard is marked as an exceeding-standard vehicle, wherein the second monitoring data exceeding the standard exceeds a corresponding threshold value.

4. The method according to claim 1, characterized in that: The synchronous monitoring device includes a black smoke monitoring device, and obtaining the number of vehicles exceeding the standard monitored by the synchronous monitoring device at the monitoring point in each monitoring time period includes: Obtaining the Ringelmann blackness of each passing vehicle monitored by the black smoke monitoring device at the monitoring point in each monitoring time period; Whether the corresponding passing vehicle is an over-standard vehicle is determined according to the Ringelmann blackness, and the number of over-standard vehicles in the corresponding monitoring time period is obtained by counting.

5. The method according to claim 1, characterized in that Determining the target excess multiple quantile value of each monitoring dimension in the corresponding monitoring time period according to the number of vehicles exceeding the standard in the same monitoring time period and the excess multiple quantile value distribution corresponding to each monitoring dimension includes: Among all the excess multiples quantile values ​​corresponding to the same monitoring dimension in the same monitoring time period, the excess multiples quantile value that is the same as or closest to the corresponding number of exceeding vehicles is used as the target excess multiples quantile value of the monitoring dimension corresponding to the monitoring time period.

6. The method according to claim 1 or 5, characterized in that: The method of obtaining the standard value of the excess multiple of the monitoring point in the corresponding monitoring dimension according to the target excess multiple quantile value of the same monitoring dimension in all monitoring time periods includes: The corresponding sample points are constructed using the excess multiple quantile value pairs as sample point coordinates, wherein the excess multiple quantile value pairs include the target excess multiple quantile values ​​of the monitoring dimension corresponding to the same type of vehicles in the same monitoring time period; According to the mean shift algorithm, all sample points corresponding to the same type of vehicles in all monitoring time periods are clustered to obtain the corresponding center points; The coordinates of the center point are calculated as the standard values ​​of the excess multiples of the monitoring point in the corresponding monitoring dimension.

7. The method according to claim 6, characterized in that The validity judgment of the monitoring data to be estimated for the vehicle to be determined to exceed the standard according to the standard value of the excess multiples of the monitoring point in each monitoring dimension includes: Acquire the monitoring data to be estimated of the pending over-standard vehicle determined as the over-standard vehicle, wherein the monitoring data to be estimated includes the second monitoring data of the pending over-standard vehicle in each monitoring dimension; According to the exceeding dimension corresponding to the second monitoring data exceeding the standard in the monitoring data to be estimated, the corresponding exceeding multiple standard value is obtained as the target exceeding multiple standard value; Calculate the excess multiple of the to-be-determined excess vehicle in the corresponding excess dimension as the target excess multiple; If the target excess multiple is not less than the target excess multiple standard value corresponding to the same excess dimension, it is determined that the monitoring data to be estimated is valid.

8. A device for determining the validity of remote sensing monitoring data, characterized in that: The device comprises: A first data acquisition module is used to acquire first monitoring data of each passing vehicle monitored in different monitoring time periods at the same monitoring point, wherein the first monitoring data is acquired by remote sensing monitoring equipment at the monitoring point, and the first monitoring data includes second monitoring data corresponding to the passing vehicle in each monitoring dimension; An over-standard checking module, used for checking the over-standard of the second monitoring data of each of the passing vehicles, and determining a passing vehicle with at least one over-standard second monitoring data as an over-standard vehicle; A first calculation module is used to calculate the excess multiple of each of the over-standard vehicles in the corresponding excess dimension, wherein the excess dimension is the monitoring dimension corresponding to the second monitoring data of the over-standard vehicle; the first calculation module specifically includes a non-over-standard vehicle determination module, a second sub-calculation module, a third sub-calculation module and a fourth sub-calculation module; The non-exceeding vehicle determination module is used to determine a first number of non-exceeding vehicles that are adjacent to the exceeding vehicle at a driving time, wherein the exceeding vehicle and the corresponding non-exceeding vehicle use the same vehicle driving energy; A second sub-calculation module is used to average the second monitoring data corresponding to the same exceeding dimension in the first monitoring data of the non-exceeding vehicle to obtain a first average of the corresponding exceeding dimension, wherein the exceeding dimension is the monitoring dimension corresponding to the second monitoring data of the exceeding vehicle; A third sub-calculation module is used to calculate the excess multiple of the over-standard vehicle in the corresponding excess dimension according to the second monitoring data corresponding to the same excess dimension of the over-standard vehicle and the first mean value; The fourth sub-calculation module is used to calculate the quantile values ​​of all the excess multiples corresponding to each monitoring dimension in the same monitoring time period, and obtain the percentile quantile value distribution corresponding to each monitoring dimension of the monitoring point in each monitoring time period, wherein the percentile quantile value distribution includes the excess multiple quantile values ​​corresponding to each percentile; The second calculation module is used to calculate the quantile value of the excess multiples of the same monitoring dimension in the same monitoring time period, and obtain the quantile value distribution of the excess multiples corresponding to each monitoring dimension of the monitoring point in each monitoring time period, wherein the excess multiple quantile value distribution includes the excess multiple quantile values ​​corresponding to each percentile of the corresponding monitoring dimension; A second data acquisition module is used to obtain the number of vehicles exceeding the standard monitored by the synchronous monitoring device at the monitoring point in each monitoring time period; A reverse determination module is used to determine the target excess multiple quantile value of each monitoring dimension in the corresponding monitoring time period according to the number of vehicles exceeding the standard in the same monitoring time period and the excess multiple quantile value distribution corresponding to each monitoring dimension; A standard value determination module is used to obtain the standard value of the excess multiple of the monitoring point in the corresponding monitoring dimension according to the target excess multiple quantile value of the same monitoring dimension in all monitoring time periods; The validity judgment module is used to judge the validity of the monitoring data to be estimated of the vehicle to be determined to exceed the standard according to the standard value of the excess multiples of the monitoring point in each monitoring dimension.

9. A computer device comprising a memory, a processor, and computer-readable instructions stored in the memory and executable on the processor, characterized in that: When the processor executes the computer-readable instructions, the processor performs the steps of the method for determining the validity of remote sensing monitoring data as described in any one of claims 1-7.

10. A computer-readable storage medium having computer-readable instructions stored thereon, characterized in that: When the computer-readable instructions are executed by a processor, the processor executes the steps of the method for determining the validity of remote sensing monitoring data as described in any one of claims 1 to 7.