Road dust condition monitoring method, system, device and medium

Abstract

The application provides a road dust condition monitoring method, system, device and medium, relates to the technical field of road dust monitoring, and comprises the following steps: dividing each original GPS point data to different monitoring road sections based on a road information library; for each monitoring road section, determining a dust characteristic value based on the original road dust data corresponding to each original GPS point data in the monitoring road section; determining an adaptive threshold based on the dust characteristic value; filtering key GPS point data from each original GPS point data based on the adaptive threshold by using a Douglas-Pok algorithm; and displaying the road dust condition based on the original road dust data corresponding to the key GPS point data. By filtering the key GPS point data based on the adaptive threshold determined based on the dust characteristic value, the adaptive threshold can be adapted to the dust characteristics of the monitoring road section, so that accurate key point filtering can be realized, the calculation amount is reduced, and the filtering efficiency is improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of road dust monitoring, in particular to a road dust condition monitoring method, system, device and medium. BACKGROUND

[0002] Road dust refers to a series of services and technical measures for monitoring, analyzing and managing dust on urban or highway roads. The main purpose of this business is to reduce environmental pollution caused by road dust, improve air quality, and provide a cleaner living environment for residents.

[0003] Currently, the matching of road dust and road information mainly relies on road dust condition monitoring systems integrated with online monitoring, data calculation, map matching, video monitoring, data transmission and automatic statistics and other functions. Such systems are usually installed on vehicles, and during vehicle driving, real-time collection of road dust data and original trajectory data is performed for analysis to match road dust conditions with road location information, thereby realizing dynamic monitoring of the dust conditions of the monitored road section.

[0004] However, in the prior art, the original trajectory data often contains a large number of redundant points, and dynamic monitoring of the dust conditions of the monitored road section based on the original trajectory data not only consumes resources, but also may affect the accuracy and efficiency of data analysis, thereby leading to poor matching effect of road dust conditions and road location information, and further affecting the accuracy of dust condition monitoring. SUMMARY

[0005] The present application aims to provide a road dust condition monitoring method, system, device and medium to alleviate the above technical problems in the prior art. The technical solution provided by the present application is as follows:

[0006] In a first aspect, the present application provides a road dust condition monitoring method, comprising:

[0007] receiving each original GPS point data collected by a road dust monitoring device and original road dust data corresponding to each original GPS point data;

[0008] based on a road information library, dividing each original GPS point data into different monitoring road sections; wherein the road information library comprises GPS point data corresponding to each road section;

[0009] for each monitoring road section, determining a dust feature value of the monitoring road section based on the original road dust data corresponding to each original GPS point data included in the monitoring road section; determining an adaptive threshold of the monitoring road section based on the dust feature value; using the Douglas-Poke algorithm, based on the adaptive threshold, screening out key GPS point data from each original GPS point data included in the monitoring road section;

[0010] determine the road dust condition corresponding to each monitoring road section based on the original road dust data corresponding to the key GPS point data contained in each monitoring road section;

[0011] visualize the road dust condition corresponding to each monitoring road section in a map.

[0012] Optionally, the dust feature value of the monitoring road section is determined based on the original road dust data corresponding to each original GPS point data contained in the monitoring road section, including:

[0013] extract the dust feature value corresponding to each original GPS point data contained in the monitoring road section from the original road dust data corresponding to each original GPS point data contained in the monitoring road section; wherein the dust feature value includes at least one of dust thickness, dust rate, dust thickness gradient, dust composition, and particle size distribution;

[0014] determine the dust feature value of the monitoring road section based on the average value of the dust feature value corresponding to each original GPS point data contained in the monitoring road section.

[0015] Optionally, the adaptive threshold of the monitoring road section is determined based on the dust feature value, including:

[0016] input the dust feature value into a threshold prediction model to obtain the adaptive threshold of the monitoring road section; wherein the threshold prediction model is obtained by training based on historical dust feature data and historical adaptive thresholds of different road sections, and is a machine learning model satisfying a selection effect index of the key GPS point data.

[0017] Optionally, in the process of screening the key GPS point data from the original GPS point data contained in the monitoring road section based on the adaptive threshold using the Douglas-Pok algorithm, further including:

[0018] based on the dust feature value corresponding to each original GPS point data contained in the monitoring road section, divide the original GPS point data with similar dust feature values into the same monitoring area;

[0019] determine the dust feature value of each monitoring area based on the average value of the dust feature value of each original GPS point data contained in each monitoring area;

[0020] based on the dust feature value of each monitoring area, determine the monitoring area in which dust mutation occurs from each monitoring area as a key monitoring area;

[0021] preferentially screen the key GPS point data from each original GPS point data contained in the key monitoring area.

[0022] Optionally, the road dust condition monitoring method provided in the application further comprises:

[0023] Based on the dust feature value of the key monitoring area, a local threshold value of the key monitoring area is determined, the adaptive threshold value is updated as the local threshold value, and based on the updated adaptive threshold value, key GPS point data is screened from each original GPS point data included in the key monitoring area.

[0024] Optionally, in the process of screening the key GPS point data from each original GPS point data included in the monitoring road section based on the adaptive threshold value by using the Douglas-Pike algorithm, the process further comprises:

[0025] Based on the dust center migration trajectory, a high complexity area in the monitoring road section is determined, and the key GPS point data is preferentially screened from each original GPS point data included in the high complexity area.

[0026] Optionally, in the process of screening the key GPS point data from each original GPS point data included in the monitoring road section based on the adaptive threshold value by using the Douglas-Pike algorithm, the process further comprises:

[0027] When any original GPS point data included in the monitoring road section is determined to be a common GPS point data of other monitoring road sections, the original GPS point data is determined as the key GPS point data.

[0028] In the second aspect, the application provides a road dust condition monitoring system, comprising:

[0029] A data receiving unit is configured to receive each original GPS point data and original road dust data corresponding to each original GPS point data collected by a road dust monitoring device.

[0030] A road section dividing unit is configured to divide each original GPS point data to different monitoring road sections based on a road information library; wherein the road information library comprises GPS point data corresponding to each road section.

[0031] A data thinning unit is configured to, for each monitoring road section, determine a dust feature value of the monitoring road section based on original road dust data corresponding to each original GPS point data included in the monitoring road section, determine an adaptive threshold value of the monitoring road section based on the dust feature value, and screen key GPS point data from each original GPS point data included in the monitoring road section based on the adaptive threshold value by using a Douglas-Pike algorithm.

[0032] A dust analysis unit is configured to determine a road dust condition corresponding to each monitoring road section based on original road dust data corresponding to the key GPS point data included in each monitoring road section.

[0033] A visualization unit is configured to visualize the road dust condition of each monitoring section on a map.

[0034] In a third aspect, the present application provides an electronic device, comprising a processor and a memory, the memory storing computer executable instructions executable by the processor, and the processor executes the computer executable instructions to implement the road dust condition monitoring method.

[0035] In a fourth aspect, the present application provides a computer readable storage medium, the computer readable storage medium storing computer executable instructions, and the computer executable instructions are executed by a processor to implement the road dust condition monitoring method.

[0036] The beneficial effects of the present application are as follows:

[0037] The present application can adapt the adaptive threshold to the dust characteristics of the monitoring section by using the adaptive threshold determined based on the dust characteristic value to filter the key GPS point data, so as to realize accurate key point filtering, reduce the calculation amount, improve the filtering efficiency, and further improve the matching effect of the road dust condition and the road position information and the accuracy of the dust condition monitoring. BRIEF DESCRIPTION OF DRAWINGS

[0038] In order to more clearly illustrate the technical solutions in the specific embodiments or prior art of the present application, the drawings needed in the specific embodiments or prior art description will be briefly introduced below. Obviously, the drawings in the following description are some embodiments of the present application, and those skilled in the art can also obtain other drawings according to these drawings without creative labor.

[0039] Figure 1 A general flowchart of a road dust condition monitoring method in an embodiment of the present application;

[0040] Figure 2 A general flowchart of another road dust condition monitoring method in an embodiment of the present application;

[0041] Figure 3 A schematic diagram of a dust level configuration in an embodiment of the present application;

[0042] Figure 4 A functional structure schematic diagram of a road dust condition monitoring system in an embodiment of the present application;

[0043] Figure 5 A hardware structure schematic diagram of an electronic device in an embodiment of the present application. DETAILED DESCRIPTION

[0044] To make the objects, technical solutions and advantages of the embodiments of the present application clearer, the following will be combined with the accompanying drawings for the embodiments of the present application to make a clear and complete description of the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only some of the embodiments of the present application, rather than all the embodiments. The components of the embodiments of the present application described and shown in the accompanying drawings can be arranged and designed in various different configurations.

[0045] Therefore, the following detailed description of the embodiments of the present application provided in the accompanying drawings is not intended to limit the scope of the claimed present application, but only represents selected embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without making creative efforts belong to the scope of protection of the present application.

[0046] It should be noted that: similar reference numerals and letters represent similar items in the following drawings, therefore, once an item is defined in one drawing, it does not need to be further defined and explained in the subsequent drawings.

[0047] The embodiments of the present application provide a road dust condition monitoring method, applied to a road dust condition monitoring system, which can be installed on a computer, a tablet computer, a mobile phone or other electronic devices, as shown in Figure 1 The road dust condition monitoring method provided by the embodiments of the present application mainly includes the following steps:

[0048] Step 110: receiving each original GPS point data collected by the road dust monitoring device and the original road dust data corresponding to each original GPS point data.

[0049] The road dust monitoring device is used to collect road dust data on the road and record GPS point data through a GPS positioning system. In an implementation manner, the original road dust data on the road can be collected through a dust collection device such as a dust sensor, a camera, a laser range finder, a laser radar (LiDAR), an ultrasonic sensor, an X-ray fluorescence spectrometer (XRF) and a portable gas chromatograph (GC) arranged on the road dust monitoring device, and the original GPS point data can be collected through a GPS positioning device arranged on the road dust monitoring device. The dust collection device and the GPS positioning device are synchronously collected, that is, the original GPS point data and the original road dust data are one-to-one associated through time information such as a time stamp. In addition, the original GPS point data and the original road dust data can also be indicated by the time information such as the time stamp. When the original GPS point data has supplementary transmission and repetition, the data with the repeated time stamp can be deleted according to the time stamp sorting.

[0050] Step 120: Based on the road information library, each original GPS point data is divided into different monitoring road sections; wherein the road information library includes GPS point data corresponding to each road section.

[0051] In the embodiment of the present application, the road information library contains basic information of each road section such as the home province, city, district, street, road grade, and GPS point data of multiple key positions (i.e. positions that can uniquely identify the road section) contained in each road section. By matching each original GPS point data with the GPS point data of multiple key positions of different road sections, the road section to which each original GPS point data belongs can be determined as a monitoring road section.

[0052] Step 130: For each monitoring road section, based on the original road dust data corresponding to each original GPS point data contained in the monitoring road section, the dust characteristic value of the monitoring road section is determined; based on the dust characteristic value, the adaptive threshold of the monitoring road section is determined; using the Douglas-Pike algorithm, based on the adaptive threshold, the key GPS point data is screened out from each original GPS point data contained in the monitoring road section.

[0053] In the embodiment of the present application, for each monitoring road section, when determining the dust characteristic value of the monitoring road section based on the original road dust data corresponding to each original GPS point data contained in the monitoring road section, the following methods can be used but are not limited to:

[0054] First, from the original road dust data corresponding to each original GPS point data contained in the monitoring road section, the dust characteristic value corresponding to each original GPS point data contained in the monitoring road section is extracted; wherein the dust characteristic value includes at least one of dust thickness, dust rate, dust thickness gradient, dust composition, and particle size distribution. In specific implementation, the road dust monitoring device is provided with a camera, a laser range finder, a laser radar (LiDAR), an ultrasonic sensor, an X-ray fluorescence spectrometer (XRF), a portable gas chromatograph (GC), and other dust collection devices. Based on this, for each original GPS point data contained in the monitoring road section, the following methods can be used to extract the dust characteristic values such as dust thickness, dust rate, dust thickness gradient, dust composition, and particle size distribution from the original road dust data corresponding to the original GPS point data:

[0055] 1. Dust thickness:

[0056] Direct measurement: select several points on the road and use a laser range finder or an ultrasonic sensor to measure the distance from the dust surface to the road surface.

[0057] Image analysis: take a photo of the road surface, identify the dust covered area through image processing technology and quantify its thickness.

[0058] 2. Dust deposition rate:

[0059] Periodic monitoring: Measure dust thickness periodically (e.g., weekly or monthly) at the same location, calculate the thickness difference between two time points to get the dust deposition rate.

[0060] Model prediction: Combine meteorological data (e.g., wind speed, precipitation), traffic flow data (e.g., vehicle flow, vehicle type), use statistical models or machine learning algorithms to predict dust deposition rate.

[0061] 3. Dust thickness gradient:

[0062] Direct measurement: Select multiple locations on the same road segment for measurement, generate a spatial distribution map of dust thickness, analyze its gradient change.

[0063] Mobile monitoring: Use LiDAR or ultrasonic sensors to drive along the road, record dust thickness data in real time, generate a continuous thickness gradient map.

[0064] 4. Dust composition:

[0065] Use X-ray fluorescence spectrometer (XRF), portable gas chromatograph (GC) to quickly detect the main components in dust, such as heavy metals, organic pollutants, etc.

[0066] 5. Particle size distribution:

[0067] Use a microscope to take micrographs of dust particles, analyze the size of each particle through image processing technology, and summarize the particle size distribution.

[0068] Then, based on the average value of the dust characteristic value corresponding to each original GPS point data included in the monitoring road segment, the dust characteristic value of the monitoring road segment is determined. In an optional implementation, the dust characteristic value of the monitoring road segment can be a weighted sum of the average values of different dust characteristic values corresponding to each original GPS point data, and the weights of different dust characteristic values can be determined according to the importance of the dust characteristic value to the monitoring road segment, and the importance of the dust characteristic value to the monitoring road segment can be determined according to the IV value. In another optional implementation, the dust characteristic value of the monitoring road segment can also be the average value of different dust characteristic values, that is, the dust characteristic value of the monitoring road segment includes at least one of the dust thickness, the dust deposition rate, the dust thickness gradient, the dust composition, and the particle size distribution corresponding to the original GPS point data.

[0069] Further, for each monitoring road segment, based on the original road dust data corresponding to each original GPS point data included in the monitoring road segment, the dust characteristic value of the monitoring road segment is determined, and then the adaptive threshold of the monitoring road segment can be determined based on the dust characteristic value. Specifically, the following methods can be used, but are not limited to:

[0070] The dust accumulation feature value is input into a threshold prediction model to obtain an adaptive threshold for the monitored road section; wherein the threshold prediction model is obtained by training based on historical dust accumulation feature data and historical adaptive thresholds of different road sections, and is a machine learning model meeting a screening effect index of key GPS point data.

[0071] In the embodiments of the present application, the threshold prediction model is trained and obtained in the following manner:

[0072] 1. Data collection and preprocessing:

[0073] Historical dust accumulation feature data: including information such as dust thickness, particle size distribution, and component analysis of different road sections at different time periods.

[0074] Historical adaptive thresholds: including thresholds corresponding to different road sections that are dynamically adjusted according to local dust accumulation features (such as dust mutation, public points, dust center migration, etc.).

[0075] Key GPS point data: including pre-calibrated specific GPS point data contained in different road sections, used to verify and evaluate the accuracy of the model.

[0076] 2. Feature engineering:

[0077] Extract features: extract useful features from historical data, such as average dust thickness, maximum-minimum value difference, seasonal variation trend, etc.

[0078] Weighted calculation: assign weights to each feature based on the importance of local dust accumulation features to ensure that the model can capture key information.

[0079] Data standardization: normalize or standardize all features to eliminate dimensional differences and improve model performance.

[0080] 3. Model selection and training:

[0081] Select a model: select a suitable model from linear regression, decision tree, random forest, support vector machine (SVM), neural network, etc.

[0082] Train the model: use the historical data set to train the selected model and adjust the hyperparameters to optimize the model performance.

[0083] Cross-validation: evaluate the generalization ability of the model through K-fold cross-validation to prevent overfitting.

[0084] 4. Model evaluation:

[0085] Set evaluation indicators: define the criteria for model success, such as accuracy, recall rate, F1 score, etc., especially the screening effect of key GPS point data.

[0086] Test Model: Evaluate the model's performance with an independent test set to ensure its reliability on new data.

[0087] 5. Application and Optimization:

[0088] Real-time Updates: Regularly retrain the model as new observational data is added, keeping it up-to-date.

[0089] Feedback Mechanism: Establish a feedback system to adjust model parameters based on real-world application performance, further improving prediction accuracy.

[0090] Furthermore, based on the dust characteristic value, after determining the adaptive threshold of the monitoring road section, the Douglas-Pike algorithm can be used to select key GPS point data from each original GPS point data contained in the monitoring road section based on the adaptive threshold. Specifically, the following methods can be used, but are not limited to:

[0091] Step 1, Select the starting point and the ending point: Select the starting point and the ending point from the original curve represented by the monitoring road section.

[0092] Step 2, Calculate the distance: Calculate the perpendicular distance from all other points on the original curve to the straight line segment determined by the starting point and the ending point.

[0093] Step 3, Determine and simplify: Find the point corresponding to the maximum distance. If the distance is greater than the adaptive threshold, keep the point and divide the original curve into two parts, and recursively execute the above process on these two parts; otherwise, remove all intermediate points and only keep the starting point and the ending point.

[0094] Step 4, Recursively execute: Repeat the above process for each sub-curve until all points are processed.

[0095] It is worth mentioning that in the embodiments of the present application, in order to improve the screening efficiency of key GPS point data and avoid the loss of key data, in the process of using the Douglas-Pike algorithm to select key GPS point data from each original GPS point data contained in the monitoring road section based on the adaptive threshold, the following steps are also included:

[0096] Based on the dust characteristic value corresponding to each original GPS point data contained in the monitoring road section, the original GPS point data pairs with similar dust characteristic values are divided into the same monitoring area;

[0097] Based on the average value of the dust characteristic values of each original GPS point data contained in each monitoring area, determine the dust characteristic value of each monitoring area;

[0098] Based on the dust characteristic value of each monitoring area, determine the monitoring area where the dust mutation occurs as the key monitoring area from each monitoring area.

[0099] The key GPS point data is screened from the various original GPS point data contained in the key monitoring area.

[0100] Further, in order to further strengthen the screening effect of the key GPS point data of the key monitoring area where the dust accumulation mutation occurs, the local threshold of the key monitoring area can be determined based on the dust accumulation characteristic value of the key monitoring area, the adaptive threshold is updated to the local threshold, and the key GPS point data is screened from the various original GPS point data contained in the key monitoring area based on the updated adaptive threshold. Wherein, when determining the local threshold of the key monitoring area based on the dust accumulation characteristic value of the key monitoring area, the threshold prediction model can be used to determine.

[0101] In addition, in order to further improve the screening efficiency and screening accuracy of the key GPS point data, in the process of using the Douglas-Pok algorithm to screen the key GPS point data from the various original GPS point data contained in the monitoring road section based on the adaptive threshold, the high complexity area in the monitoring road section can be determined based on the dust center migration trajectory, and the key GPS point data is screened from the various original GPS point data contained in the high complexity area. Wherein, according to the various historical GPS point data and the historical road dust data corresponding to each historical GPS point data contained in the monitoring road section within a set time range (such as a week, half a month, a month, etc.) between the current time, the dust center of the monitoring road section and the migration trajectory of the dust center can be analyzed, and the area passed by the migration trajectory of the dust center is determined as the high complexity area.

[0102] In addition, in order to further improve the screening efficiency and screening accuracy of the key GPS point data, in the process of using the Douglas-Pok algorithm to screen the key GPS point data from the various original GPS point data contained in the monitoring road section based on the adaptive threshold, it can also be determined that any original GPS point data contained in the monitoring road section is a common GPS point data with other monitoring road sections, and the original GPS point data is determined as the key GPS point data. By preferentially retaining the common GPS point data, the loss of key road boundary points can be effectively avoided, and the retention rate of key dust points can be improved.

[0103] Step 140: based on the original road dust data corresponding to the key GPS point data contained in each monitoring road section, determine the road dust condition corresponding to each monitoring road section.

[0104] In the embodiments of the present application, based on the original road dust data corresponding to the key GPS point data included in each monitoring road section, the dust characteristic value corresponding to the key GPS point data included in each monitoring road section is determined, and based on the dust characteristic value corresponding to the key GPS point data included in each monitoring road section, the road dust condition corresponding to each monitoring road section is determined. The road dust condition can be a quantitative data such as dust level and dust amount determined based on the weighted results after the dust characteristic values corresponding to each key GPS point data included in the monitoring road section are weighted.

[0105] Step 150: visualizing the road dust condition corresponding to each monitoring road section in the map.

[0106] In the embodiments of the present application, different road dust conditions correspond to visualized colors, for example, the visualized color corresponding to the monitoring road section with high dust level is red, the visualized color corresponding to the monitoring road section with medium dust level is yellow, and the visualized color corresponding to the monitoring road section with low dust level is green. By rendering each monitoring road section into the visualized color corresponding to its road dust condition in the map, the road dust condition corresponding to each monitoring road section is visualized. In this way, by using the adaptive threshold value determined based on the dust characteristic value to filter the key GPS point data, the adaptive threshold value can be adapted to the dust characteristics of the monitoring road section, so that accurate key point filtering can be realized while reducing the calculation amount, improving the filtering efficiency, and further improving the matching effect of the road dust condition and the road location information and the accuracy of the dust condition monitoring. In addition, in the key GPS point data filtering process, by locally dynamically adjusting and optimizing the adaptive threshold value, the filtering accuracy and efficiency of the key GPS point data can be further improved, so that the matching effect of the road dust condition and the road location information and the accuracy of the dust condition monitoring can be further improved.

[0107] Based on the above embodiments, another road dust condition monitoring method is provided in the embodiments of the present application, which is applied to a road dust condition monitoring system that can be installed on a computer, a tablet computer, a mobile phone or other electronic devices. As shown in Figure 2 The road dust condition monitoring method mainly includes the following steps:

[0108] Step 210: obtaining the GPS point latitude and longitude information and the dust value of the road dust monitoring device.

[0109] Step 220: matching the processed GPS point latitude and longitude information with the road information and matching the dust value with the dust rule information; wherein the GPS is respectively assigned to the road information and the dust rule information.

[0110] In an embodiment, the GPS point latitude and longitude information and the road information can be pre-processed, that is, the GPS point latitude and longitude information can be cleaned according to the road trajectory information, and abnormal points and / or error data points can be removed. In addition, the drawn road is stored in a database, and the drawn road is assigned to determine the attribution information and the road level information of the road.

[0111] In addition, in order to facilitate subsequent matching processing, the dust level can also be configured. Specifically, the road dust rule can be configured according to the dust requirement, and the dust rule includes a dust value range field, a color field, and a level (excellent, pass, and difference) field.

[0112] After the above-mentioned preprocessing and configuration processing are implemented, the matching processing can be performed. Specifically, the corresponding matching processing can be performed according to the business requirements. For example, the business requirements can include viewing all collected data, viewing only the data of the road segment responsible by oneself, and viewing only the road segment responsible by oneself to reduce the data amount, and the detailed information such as the name of the road segment responsible by oneself needs to be seen on the map.

[0113] In an embodiment, when the processed GPS point latitude and longitude information is matched with the road information, the GPS point latitude and longitude information of the matched road information carries the ID of the road information, the dust value of the collected GPS point latitude and longitude information is compared with the dust rule to obtain the excellent, pass, and difference evaluation, and different evaluations are displayed in different colors on the map.

[0114] In actual application, the above-mentioned GPS respectively assigns the road information and the dust rule information, that is, the road information is a multi-fold line drawn by several latitude and longitude points, when the distance from the GPS point to the straight line of the road point satisfies the preset threshold (for example, 50 meters), the GPS point is determined to belong to the road. Then the next GPS point will preferentially match the previously matched road, so that the matching probability is increased. Similarly, the dust value of the GPS is matched with the dust rule. Next time, the rule matched last time will be preferentially matched. The dust rule information corresponding to the road dust rule at least includes a dust value range field, a color field, and a level field.

[0115] Step 230: The cut GPS point is thinned by Douglas-Pike, and the point information, the dust rule information, and the road information corresponding to each cut GPS sub-point are calculated respectively.

[0116] In an embodiment, the cut GPS points are processed by Douglas-Pok thinning, which can be a set sorted according to GPS timestamps, setting a threshold, recursive segmentation, and obtaining an approximate curve straight line, thereby obtaining the thinning result. The size of the threshold and the matching similarity and deviation of the original all GPS lines are modified according to the user's acceptance, and the threshold of special roads can be customized. The depth of recursive segmentation is also a factor affecting performance, and a reasonable depth is set to increase performance.

[0117] Further, the point information, dust rule information and road information corresponding to each cut GPS sub-point are calculated respectively, which can be calculated by grouping the same dust level and the GPS of the corresponding road, and calculating the maximum value, minimum value, average value and number of each segment.

[0118] Step 240: Visualize each segment of the thinned GPS sub-track on the map.

[0119] After thinning, each line segment can be displayed on the map. The user can see the color, level, maximum value, minimum value, average value, number of device uploaded data and road information of each line segment. When visualizing, the thickness of the line on the map is used to distinguish whether the road is a working area. For example, the thickness of the line can be used to distinguish whether the road is a working area, to realize the visualization of the GPS sub-track on the map.

[0120] In summary, by Douglas-Pok thinning of GPS points and calculating corresponding point information, dust rule information and road information, the accuracy of processing original GPS data can be improved, and the accuracy and processing efficiency of road information matching can be improved.

[0121] For ease of understanding, the road dust condition monitoring method is described in detail as follows.

[0122] In an example, the GPS point latitude and longitude information is preliminarily cleaned to remove abnormal or incorrect data points, which can include the following processing steps:

[0123] 1. Data range check

[0124] Geographical boundary filtering: set a reasonable latitude and longitude range according to the actual working area, and exclude points obviously outside this range.

[0125] Reasonable value verification: ensure that the latitude is between [-90, 90] and the longitude is between [-180, 180].

[0126] 2. Time consistency check

[0127] Timestamp Check: Verify that each GPS record has a correct timestamp and is in chronological order. If time jumps or unreasonable time intervals are found, it may indicate problematic data.

[0128] Continuity Analysis: For data collected in time series, check if the time difference between adjacent points is reasonable, avoiding cases of excessively short (possibly duplicate points) or excessively long (possibly signal loss followed by reacquisition).

[0129] 3. Spatial Reasonability Assessment

[0130] Distance Threshold Filtering: Calculate the straight-line distance between adjacent GPS points and set a maximum allowed movement distance. If the distance between two points exceeds the maximum value that can be achieved by the vehicle's normal driving speed, consider that point as an abnormal point.

[0131] Speed Limit: Based on vehicle type and road conditions, set a reasonable maximum speed limit. Identify overspeed situations by calculating the speed between two points, marking potential problem points.

[0132] 4. Application of Clustering Algorithms

[0133] Using density clustering algorithms such as DBSCAN can automatically find isolated points far from the majority of points as abnormal points. This method is particularly suitable for dealing with distribution patterns without clear boundaries.

[0134] 5. Comparison with Historical Trajectory

[0135] For repeated paths, such as bus routes or fixed route cleaning vehicles, comparison with historical trajectories can detect deviations from the regular route in newly collected data.

[0136] 6. Data Smoothing

[0137] Applying low-pass filters or other forms of data smoothing techniques can help eliminate small fluctuations caused by unstable satellite signals, but care must be taken not to over-smooth and mask real motion characteristics.

[0138] 7. Map Matching

[0139] Project the original GPS points onto the nearest road network to correct the deviation caused by positioning errors. This requires the use of geographic information system (GIS) software and detailed map databases.

[0140] 8. Rule Engine

[0141] Develop a set of rules to define when a data point should be marked as abnormal. For example, when the GPS accuracy indicators (HDOP, VDOP, etc.) are too high, indicating poor positioning quality, the related records should be marked for further review.

[0142] 9. Automation tools and scripts

[0143] Write automation scripts using programming languages (Python, R, etc.) to perform the above cleaning processes, improve efficiency, and reduce the possibility of human error.

[0144] After completing the above steps, the cleaned data set should be reviewed again to ensure that all operations are reasonable and do not mistakenly delete valid data. In addition, in practical applications, it is best to combine domain knowledge and specific business logic to customize the cleaning strategy.

[0145] In another example, the road drawing is stored in the database, and the road can be assigned the attribution of the province, city, district, street, and road level information. In specific implementation, a multi-table structure can be designed to achieve this. For example, it can be built based on a relational database (such as MySQL, PostgreSQL):

[0146] 1. Design the database schema

[0147] Table One: provinces (Province Table)

[0148] id: INT, primary key

[0149] name: VARCHAR, province name

[0150] Table Two: cities (City Table)

[0151] id: INT, primary key

[0152] province_id: INT, foreign key, associated to provinces.id

[0153] name: VARCHAR, city name

[0154] Table Three: districts (District Table)

[0155] id: INT, primary key

[0156] city_id: INT, foreign key, associated to cities.id

[0157] name: VARCHAR, district name

[0158] Table Four: streets (Street Table)

[0159] id: INT, primary key

[0160] district_id: INT, foreign key, links to districts.id

[0161] name: VARCHAR, street name

[0162] Table Five: roads (Roads Table)

[0163] id: INT, primary key

[0164] street_id: INT, foreign key, links to streets.id

[0165] name: VARCHAR, road name

[0166] grade: ENUM or VARCHAR, road grade (e.g., 'expressway', 'arterial', 'collector', 'local').

[0167] 2. Drawing Roads and Storing Geographic Information

[0168] To support spatial queries and visualization, you can use GIS (Geographic Information System) features such as the PostGIS extension for PostgreSQL, which allows you to store and manipulate geometric objects like points, lines, and polygons.

[0169] For each road, you need to record its geometric shape (usually a line string). This can be achieved by:

[0170] Adding a field in the roads table to store the geometry data type (e.g., GEOMETRY(LINESTRING) in PostGIS).

[0171] Using GIS tools or libraries (such as QGIS, ArcGIS, GeoPandas, Shapely, etc.) to draw the roads and convert them into WKT (Well-Known Text) format or other compatible formats, then insert them into the corresponding field.

[0172] 3. Data Input and Maintenance

[0173] Manual Input: Manually input new roads and their attributes through a user interface.

[0174] Bulk Import: Bulk import road data from existing GIS files (such as Shapefile, GeoJSON, etc.).

[0175] API Interface: Develop an API interface to allow external systems to submit new road information or update existing information.

[0176] 4. Query and analysis

[0177] Once the data is properly stored in the database, you can perform various types of queries to retrieve all roads within a certain area, filter roads by rank, calculate the shortest path between two locations, etc. This usually involves spatial indexing and complex SQL query statements, and sometimes requires the use of more advanced spatial analysis provided by GIS servers.

[0178] In an optional embodiment, in order to realize subsequent application of Douglas-Pok for thinning, the GPS continuous point data corresponding to the GPS latitude and longitude information can be segmented and cut in advance, and the GPS continuous point data with the same dust accumulation level and the same road belonging to the same set; if there is GPS continuous point data that cannot be matched to the corresponding road, it is matched after increasing the attribute.

[0179] After segmentation and cutting, the point information, dust accumulation rule information and road information corresponding to each segment of the GPS sub-point are calculated respectively. In specific implementation, the GPS sub-point can be segmented and divided according to the dust accumulation level and the road belonging to it; the same dust accumulation level and the road belonging to it are determined as a segment of GPS, and the point information, dust accumulation rule information and road information corresponding to each segment of the GPS sub-point after cutting are calculated respectively.

[0180] Figure 3 An execution flow of a specific road dust condition monitoring method is shown, which can mainly include the following steps:

[0181] 1. Receive GPS point latitude and longitude information, timestamp, and dust accumulation value of the dust accumulation device.

[0182] 2. Preliminary cleaning of trajectory data to remove abnormal or incorrect data points.

[0183] 3. Road management: draw the road (polyline of multiple points) stored in the database, and the road can be assigned with the attribution of the road belonging to the province, city, district, and street, and the road rank information.

[0184] 4. Dust level configuration: according to the dust accumulation requirements, road dust rules can be formulated, which can be divided by fields, such as dust accumulation value range field, color field, and level (excellent, pass, difference, etc.) field, as shown in Figure 3 .

[0185] 5. Match the GPS point latitude and longitude information and the road information by setting the threshold, and match the GPS point dust accumulation value with the road segment level and the dust accumulation level configuration of the matched road.

[0186] 6. Continuous GPS point data is segmented and cut into sections. Continuous points with the same dust accumulation level and the same road are grouped together. Points that cannot be matched to a road will be distinguished by attributes (distinguished by thin lines on the map).

[0187] 7. Use Douglas-Peucker to perform thinning and optimize the Douglas-Peucker on the GPS points after cutting. Combining the segmented cutting of the business will increase the calculation efficiency and calculate the maximum, minimum, average, number and color and grade information of dust accumulation rules and road information of each segment.

[0188] 8. Each line segment after thinning is displayed on the map. Users can see the color, level, maximum, minimum, average value, number of device uploaded data and road information of each line segment. The thickness of the line can be used to distinguish whether the road is a work area.

[0189] Based on the above method embodiment, the present application embodiment also provides a road dust condition monitoring system, see Figure 4 As shown in the figure, the road dust condition monitoring system mainly includes the following parts:

[0190] The data receiving unit 401 is configured to receive each original GPS point data collected by the road dust monitoring device and the original road dust data corresponding to each original GPS point data;

[0191] The road segment division unit 402 is used to divide each original GPS point data into different monitoring sections based on the road information database; wherein the road information database includes the GPS point data corresponding to each road section;

[0192] The data thinning unit 403 is configured to determine, for each monitored road section, a dust accumulation characteristic value of the monitored road section based on the original road dust accumulation data corresponding to each original GPS point data contained in the monitored road section; determine an adaptive threshold value for the monitored road section based on the dust accumulation characteristic value; and use the Douglas-Peucker algorithm to filter out key GPS point data from each original GPS point data contained in the monitored road section based on the adaptive threshold value;

[0193] The dust accumulation analysis unit 404 is configured to determine the road dust accumulation condition corresponding to each monitored road section based on the original road dust accumulation data corresponding to the key GPS point data included in each monitored road section;

[0194] The visualization unit 405 is used to visualize the road dust conditions corresponding to each monitored road section on a map.

[0195] In a possible implementation, the data thinning unit 403 is configured to extract, from the original road dust data corresponding to each original GPS point data included in the monitoring road section, a dust feature value corresponding to each original GPS point data included in the monitoring road section; the dust feature value includes at least one of dust thickness, dust rate, dust thickness gradient, dust composition, and particle size distribution; and determine the dust feature value of the monitoring road section based on an average value of the dust feature values corresponding to each original GPS point data included in the monitoring road section.

[0196] In a possible implementation, the data thinning unit 403 is configured to input the dust feature value into a threshold prediction model to obtain an adaptive threshold of the monitoring road section; the threshold prediction model is obtained by training a machine learning model based on historical dust feature data and historical adaptive thresholds of different road sections, and the machine learning model meets a screening effect indicator of the key GPS point data.

[0197] In a possible implementation, the data thinning unit 403 is further configured to divide original GPS point data with similar dust feature values into the same monitoring area based on the dust feature values corresponding to each original GPS point data included in the monitoring road section; determine a dust feature value of each monitoring area based on an average value of the dust feature values of each original GPS point data included in each monitoring area; determine a monitoring area in which dust mutation occurs as a key monitoring area from each monitoring area based on the dust feature values of each monitoring area; and preferentially screen the key GPS point data from each original GPS point data included in the key monitoring area.

[0198] In a possible implementation, the data thinning unit 403 is further configured to determine a local threshold of the key monitoring area based on the dust feature value of the key monitoring area, update the adaptive threshold to the local threshold, and screen the key GPS point data from each original GPS point data included in the key monitoring area based on the updated adaptive threshold.

[0199] In a possible implementation, the data thinning unit 403 is further configured to determine a high complexity area in the monitoring road section based on the dust center migration trajectory, and preferentially screen the key GPS point data from each original GPS point data included in the high complexity area.

[0200] In a possible implementation, the data thinning unit 403 is further configured to determine, when any original GPS point data included in the monitoring road section is a common GPS point data of other monitoring road sections, the original GPS point data as the key GPS point data.

[0201] The road dust condition monitoring system provided by the embodiments of the present application has the same implementation principle and technical effects as the method embodiments, and for brevity, the embodiments of the road dust condition monitoring system are not mentioned in the following description, and the corresponding content can be referred to the method embodiments.

[0202] The embodiments of the present application further provide an electronic device, as shown in the accompanying drawings, which is a structural schematic diagram of the electronic device, wherein the electronic device 100 comprises a processor 51 and a memory 50, the memory 50 stores computer executable instructions capable of being executed by the processor 51, and the processor 51 executes the computer executable instructions to implement the road dust condition monitoring method. Figure 5 The embodiments of the present application further provide an electronic device, as shown in the accompanying drawings, which is a structural schematic diagram of the electronic device, wherein the electronic device 100 comprises a processor 51 and a memory 50, the memory 50 stores computer executable instructions capable of being executed by the processor 51, and the processor 51 executes the computer executable instructions to implement the road dust condition monitoring method.

[0203] In the embodiments shown in the accompanying drawings, the electronic device further comprises a bus 52 and a communication interface 53, wherein the processor 51, the communication interface 53 and the memory 50 are connected through the bus 52. Figure 5 In the embodiments shown in the accompanying drawings, the electronic device further comprises a bus 52 and a communication interface 53, wherein the processor 51, the communication interface 53 and the memory 50 are connected through the bus 52.

[0204] The memory 50 can include a high-speed random access memory (RAM) and can also include a non-volatile memory, such as at least one disk memory. The communication connection between the system network element and at least one other network element is realized through at least one communication interface 53 (which can be wired or wireless), and the Internet, a wide area network, a local area network, a metropolitan area network, etc. can be used. The bus 52 can be an ISA (Industry Standard Architecture) bus, a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus, etc. The bus 52 can be divided into an address bus, a data bus, a control bus, etc. For brevity, Figure 5 In the embodiments shown in the accompanying drawings, only one bidirectional arrow is used to represent the bus, but it does not mean that there is only one bus or only one type of bus.

[0205] The processor 51 can be an integrated circuit chip with processing capability. In the implementation process, the steps of the above method can be completed by integrated logic circuits or instructions in the form of software in the processor 51. The processor 51 described above can be a general processor, including a central processing unit (CPU), a network processor (NP), etc.; can also be a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components. The general processor can be a microprocessor or the processor can also be any conventional processor. The steps of the method disclosed in combination with the embodiments of the present application can be directly embodied as a hardware decoding processor for execution, or a combination of hardware and software modules in the decoding processor for execution. The software module can be located in a random access memory, a flash memory, a read only memory, a programmable read only memory or an electrically erasable programmable memory, a register, etc. The storage medium in the storage is read by the processor 51, and the hardware thereof is combined to complete the steps of the above road dust condition monitoring method.

[0206] The embodiments of the present application also provide a computer readable storage medium, which stores computer executable instructions. The computer executable instructions, when executed by a processor, implement the above road dust condition monitoring method. For details, refer to the foregoing method embodiments, which will not be described here.

[0207] The above road dust condition monitoring method provided by the embodiments of the present application can also be implemented as a computer program product. The program product includes program codes. The program codes, when executed by a processor, implement the above road dust condition monitoring method provided by the embodiments of the present application. For details, refer to the method embodiments, which will not be described here.

[0208] Unless otherwise specifically stated, the relative steps, numerical expressions and numerical values of the components and steps set forth in these embodiments do not limit the scope of the present application.

[0209] If the functions are implemented in the form of software function units and sold or used as independent products, they can be stored in a nonvolatile computer readable storage medium executable by a processor. Based on this understanding, the technical solutions of the present application or the part of the present application that essentially contributes to the prior art or the part of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes a plurality of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the embodiments of the present application. The aforementioned storage medium includes a U disk, a mobile hard disk, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), a magnetic disk or an optical disk, and various media that can store program codes.

[0210] In the description of the present application, it should be further pointed out that unless otherwise explicitly specified and limited, the terms "connected", "connected" should be understood broadly, for example, it can be fixedly connected, or it can be detachably connected, or integrally connected; it can be mechanically connected, or it can be electrically connected; it can be directly connected, or it can be indirectly connected through an intermediate medium; it can be the communication inside two elements. For those skilled in the art, the specific meaning of the above terms in the present application can be understood according to the specific circumstances.

[0211] Finally, it should be pointed out that: the above embodiments are only used to illustrate the technical solutions of the present application, and not to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments, or make equivalent replacement for part or all of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the scope of the technical solutions of the embodiments of the present application.

Claims

1. A road dust condition monitoring method characterized by, The method comprises the following steps: receiving each original GPS point data collected by a road dust monitoring device and original road dust data corresponding to each original GPS point data; dividing each original GPS point data into different monitoring road sections based on a road information database, wherein the road information database comprises GPS point data corresponding to each road section; for each monitoring road section, determining a dust characteristic value of the monitoring road section based on the original road dust data corresponding to each original GPS point data included in the monitoring road section, determining an adaptive threshold value of the monitoring road section based on the dust characteristic value, and using the Douglas-Pike algorithm to filter out key GPS point data from each original GPS point data included in the monitoring road section based on the adaptive threshold value; determining the road dust condition corresponding to each monitoring road section based on the original road dust data corresponding to the key GPS point data included in each monitoring road section; visually displaying the road dust condition corresponding to each monitoring road section in a map; in the process of filtering out key GPS point data from each original GPS point data included in the monitoring road section based on the adaptive threshold value using the Douglas-Pike algorithm, the method further comprises the following steps: dividing original GPS point data with similar dust characteristic values into the same monitoring area based on the dust characteristic values corresponding to each original GPS point data included in the monitoring road section; determining a dust characteristic value of each monitoring area based on the average value of the dust characteristic values of each original GPS point data included in each monitoring area; determining a key monitoring area from each monitoring area based on the dust characteristic value of each monitoring area, wherein the key monitoring area is a monitoring area where a dust mutation occurs; filtering out the key GPS point data from each original GPS point data included in the key monitoring area.

2. The road dust condition monitoring method according to claim 1, characterized by, determining a dust characteristic value of the monitoring road section based on the original road dust data corresponding to each original GPS point data included in the monitoring road section comprises the following steps: extracting a dust characteristic value corresponding to each original GPS point data included in the monitoring road section from the original road dust data corresponding to each original GPS point data included in the monitoring road section, wherein the dust characteristic value comprises at least one of dust thickness, dust rate, dust thickness gradient, dust composition, and particle size distribution; determining the dust characteristic value of the monitoring road section based on the average value of the dust characteristic values corresponding to each original GPS point data included in the monitoring road section.

3. The road dust condition monitoring method according to claim 1, characterized by, determining an adaptive threshold value of the monitoring road section based on the dust characteristic value comprises the following steps: inputting the dust characteristic value into a threshold prediction model to obtain the adaptive threshold value of the monitoring road section, wherein the threshold prediction model is obtained by training different road sections based on historical dust characteristic data and historical adaptive threshold values, and is a machine learning model satisfying a key GPS point data filtering effect index.

4. The road dust condition monitoring method according to claim 1, characterized by, The method further comprises the following steps: Determine a local threshold value of the key monitoring area based on the dust characteristic value of the key monitoring area, update the adaptive threshold value to the local threshold value, and filter the key GPS point data from each of the original GPS point data included in the key monitoring area based on the updated adaptive threshold value.

5. The road dust condition monitoring method according to claim 1, wherein In the process of filtering the key GPS point data from each of the original GPS point data included in the monitoring road section based on the adaptive threshold value by using the Douglas-Peucker algorithm, the method further includes: Determine a high complexity area in the monitoring road section based on the dust center migration trajectory, and filter the key GPS point data from each of the original GPS point data included in the high complexity area.

6. The road dust condition monitoring method according to claim 1, wherein In the process of filtering the key GPS point data from each of the original GPS point data included in the monitoring road section based on the adaptive threshold value by using the Douglas-Peucker algorithm, the method further includes: Determine that any original GPS point data included in the monitoring road section is a common GPS point data of other monitoring road sections, and determine the original GPS point data as the key GPS point data.

7. A road dust condition monitoring system characterized by, The method further includes: A data receiving unit configured to receive each original GPS point data and original road dust data corresponding to each original GPS point data collected by a road dust monitoring device; A road section dividing unit configured to divide each original GPS point data to different monitoring road sections based on a road information database, wherein the road information database includes GPS point data corresponding to each road section; A data thinning unit configured to, for each monitoring road section, determine a dust characteristic value of the monitoring road section based on original road dust data corresponding to each original GPS point data included in the monitoring road section, determine an adaptive threshold value of the monitoring road section based on the dust characteristic value, and filter key GPS point data from each original GPS point data included in the monitoring road section based on the adaptive threshold value by using a Douglas-Peucker algorithm; A dust analysis unit configured to determine a road dust condition corresponding to each monitoring road section based on original road dust data corresponding to the key GPS point data included in each monitoring road section; A visualization unit configured to visually display the road dust condition corresponding to each monitoring road section in a map; The data thinning unit is further configured to: Divide original GPS point data with similar dust characteristic values to the same monitoring area based on the dust characteristic values corresponding to each original GPS point data included in the monitoring road section; Determine a dust characteristic value of each monitoring area based on an average value of the dust characteristic values of each original GPS point data included in each monitoring area; Determine a key monitoring area from each monitoring area based on the dust characteristic value of each monitoring area, wherein the key monitoring area is a monitoring area in which dust mutation occurs; Filter the key GPS point data from each original GPS point data included in the key monitoring area.

8. An electronic device, comprising: A computer readable storage medium storing computer executable instructions that, when executed by a processor, perform the road dust accumulation condition monitoring method according to any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that, The computer readable storage medium stores computer executable instructions that, when executed by a processor, perform the road dust accumulation condition monitoring method according to any one of claims 1 to 6.

Images