Traffic engineering environment intelligent detection method and system

Abstract

The invention relates to the technical field of traffic supervision, and discloses a traffic engineering environment intelligent detection method and system, through high-precision data acquisition and dimensionless processing, the system can ensure that comprehensive and accurate traffic and environment data can be obtained from multiple dimensions, and through accurate calculation and analysis, the traffic engineering environment intelligent detection method and system can realize intelligent detection of traffic engineering environment. And effective correction and anomaly detection are carried out on the data. Especially in the aspect of coping with complex environmental conditions and multi-source data fusion, the system can effectively avoid errors and inaccuracy caused by a single data source in a traditional system, and under real-time monitoring of traffic flow, vehicle speed, environmental factors and potential safety hazards, the system can provide more accurate traffic prediction and safety early warning. The risk of traffic accidents is reduced, the traffic management efficiency is improved, and finally more intelligent and accurate urban traffic management and scheduling are realized.

Description

Technical Field

[0001] The present invention relates to the technical field of traffic supervision, and in particular to an intelligent detection method and system for a traffic engineering environment. Background Art

[0002] The intelligent detection system for traffic engineering environment monitors the impact of various types of traffic flow, vehicle speed, traffic density and environmental factors on traffic conditions on the road in real time. By accurately collecting this data, the intelligent detection system can provide real-time feedback to regulate traffic flow and provide traffic safety warnings.

[0003] Although the existing intelligent detection system for traffic environment can collect data such as traffic flow, speed, and traffic density in real time through various sensor devices, there are still several shortcomings in practical applications. First, the performance of existing equipment is often disturbed when facing severe weather conditions, resulting in inaccurate or lost data. Secondly, most existing systems rely on a single sensor or monitoring device and lack the ability to fuse multi-source data, which makes it difficult for the system to ensure the integrity and reliability of the data in the event of sensor failure or data anomalies. In addition, although the existing monitoring system can collect a large amount of data in real time, in the data optimization and analysis stage, the existing technology fails to give full play to the complementarity of multi-source data, making it difficult to accurately predict and optimize traffic conditions, limiting the system's ability to respond to complex traffic situations.

[0004] Therefore, we proposed an intelligent detection system for traffic engineering environment to solve the above problems. Summary of the invention

[0005] The purpose of the present invention is to provide an intelligent detection system for traffic engineering environment, so as to solve the problem proposed in the above background technology that the performance of existing equipment is often disturbed when facing severe weather conditions, resulting in inaccurate or lost data. Secondly, most of the existing systems rely on a single sensor or monitoring device and lack the ability to fuse multi-source data, which makes it difficult for the system to ensure the integrity and reliability of the data in the event of sensor failure or data anomalies. In addition, although the existing monitoring system can collect a large amount of data in real time, in the data optimization and analysis stage, the existing technology fails to give full play to the complementarity of multi-source data, making it difficult to accurately predict and optimize traffic conditions, limiting the system's ability to respond to complex traffic situations.

[0006] To achieve the above object, the present invention provides the following technical solutions: an intelligent detection system for a traffic engineering environment, comprising a data acquisition module, a data preprocessing module, a first data calculation module, a first data analysis module, a second data calculation module, a second data analysis module and a feedback module; The data acquisition module is used to collect traffic engineering environment data and vehicle data, and form a first data set and a second data set; The data preprocessing module is used to preprocess and dimensionlessly transform the first data set and the second data set; The first data calculation module is used to perform integrated calculation on the first data set, thereby generating a modified determination coefficient XZX and the first data calculation module is used to perform integrated calculation on the first data set, thereby generating a modified determination coefficient XZX and a first modified intervention coefficient S1, a second modified intervention coefficient S2 and a third modified intervention coefficient S3; The first data analysis module is used to compare the modified determination coefficient XZX with a preset first threshold value Y, thereby generating a first comparison result, and judging whether it is necessary to use the first data calculation module in subsequent calculations to perform integrated calculations on the first data set, thereby generating the modified determination coefficient XZX and the first modified intervention coefficient S1, the second modified intervention coefficient S2, and the third modified intervention coefficient S3; The second data calculation module is used to perform integrated calculation on the second data set, so as to generate a first abnormality determination coefficient YYC and a second abnormality determination coefficient RYC; The second data analysis module is used to compare the first abnormality determination coefficient YYC and the second abnormality determination coefficient RYC with the preset first abnormality threshold R1 and the second abnormality threshold R2, respectively, so as to generate a second comparison result, and determine whether the current vehicle has a traffic engineering safety problem according to the second comparison result, and classify the abnormality magnitude; The feedback module is used to feed back the first comparison result and the second comparison result to the terminal for data display.

[0007] Preferably, the data acquisition module includes a first data acquisition unit and a second data acquisition unit, and divides the data into time stamps, wherein the time stamps are recorded as: 1, 2, 3, ..., n; The first data collection unit is used to collect interference information of traffic engineering, including ambient temperature, ambient humidity, precipitation, road surface temperature and road damage index; The ambient temperatures are recorded as A1, A2, A3, ..., An respectively according to the timestamps; The environmental humidity is recorded as B1, B2, B3, ..., Bn according to the timestamp; The precipitation amounts are recorded as C1, C2, C3, ..., Cn according to the timestamps; The road surface temperatures are recorded as D1, D2, D3, ..., Dn according to the timestamps; The road damage indexes are recorded as E1, E2, E3, ..., En according to the timestamps; The second data collection unit is used to collect basic information of traffic engineering, including vehicle flow, vehicle speed, traffic density and road friction coefficient; The vehicle flows are recorded as F1, F2, F3, ..., Fn according to the timestamps; The vehicle speeds are recorded as G1, G2, G3, ..., Gn according to the timestamps; The traffic densities are recorded as H1, H2, H3, ..., Hn respectively according to the timestamps; The road friction coefficients are recorded as I1, I2, I3, ..., In according to the timestamps.

[0008] Preferably, the data preprocessing module preprocesses the first data set and the second data set, including data cleaning, noise removal, outlier processing, and dimensionless conversion.

[0009] Preferably, the first data calculation module plans the window size for each parameter in the processed first data set, and records it as m, selects the maximum value of each parameter in the first data set in window m, and records them as the maximum value Amax of the ambient temperature window, the maximum value Bmax of the ambient humidity window, the maximum value Cmax of the precipitation window, the maximum value Dmax of the road surface temperature window, and the maximum value Emax of the road damage index window; The parameters in the first data set in window m are calculated to generate the window means of each parameter, which are recorded as the ambient temperature window mean PA, the ambient humidity window mean PB, the precipitation window mean PC, the road surface temperature window mean PD and the road damage index window mean PE.

[0010] Preferably, the first data calculation module integrates and calculates the maximum value Amax of the ambient temperature window, the maximum value Bmax of the ambient humidity window, the maximum value Cmax of the precipitation window, the maximum value Dmax of the road surface temperature window, and the maximum value Emax of the road damage index window with the corresponding average values ​​PA of the ambient temperature window, the average values ​​PB of the ambient humidity window, the average values ​​PC of the precipitation window, the average values ​​PD of the road surface temperature window, and the average values ​​PE of the road damage index window, as well as a preset weight value, so as to generate a modified determination coefficient XZX; The first data calculation module integrates and calculates the ambient temperature An, ambient humidity Bn, precipitation Cn, road surface temperature Dn and road damage index En at the nth timestamp with the corresponding ambient temperature window mean PA, ambient humidity window mean PB, precipitation window mean PC, road surface temperature window mean PD and road damage index window mean PE, thereby generating a first corrected intervention coefficient S1, a second corrected intervention coefficient S2 and a third corrected intervention coefficient S3.

[0011] Preferably, the first comparison result generated by the first data analysis module is specifically as follows: when When , it means that the first correction intervention coefficient S1, the second correction intervention coefficient S2 and the third correction intervention coefficient S3 are not needed in the subsequent calculation. When , it means that the first corrected intervention coefficient S1, the second corrected intervention coefficient S2 and the third corrected intervention coefficient S3 need to be used in the subsequent calculation.

[0012] Preferably, the second data calculation module performs window value planning on the parameters in the processed second data set, and records the window value as m, selects the maximum values ​​of the parameters in the window m, and records them as the maximum value of the vehicle flow window Fmax, the maximum value of the vehicle speed window Gmax, the maximum value of the traffic density window Hmax, and the maximum value of the road friction coefficient window Imax respectively; The parameters in the second data set in window m are calculated to generate window means of various parameters, which are recorded as the vehicle flow window mean PF, the vehicle speed window mean PG, the traffic density window mean PH and the road friction coefficient window mean PI respectively.

[0013] Preferably, the second data calculation module integrates and calculates the maximum value Fmax of the traffic flow window, the maximum value Gmax of the vehicle speed window, the maximum value Hmax of the traffic density window, the maximum value Imax of the road friction coefficient window, the traffic flow Fn, the vehicle speed Gn, the traffic density Hn, the road friction coefficient In, the traffic flow window mean PF, the speed window mean PG, the traffic density window mean PH and the road friction coefficient window mean PI according to the first comparison result, so as to generate the first abnormality determination coefficient YYC; the second data calculation module integrates and calculates the maximum value Fmax of the traffic flow window, the maximum value Gmax of the speed window, the maximum value Hmax of the traffic density window, the maximum value Imax of the road friction coefficient window, the traffic flow Fn, the vehicle speed Gn, the traffic density Hn, the road friction coefficient In, the traffic flow window mean PF, the speed window mean PG, the traffic density window mean PH, the road friction coefficient window mean PI, the first corrected intervention coefficient S1, the second corrected intervention coefficient S2 and the third corrected intervention coefficient S3 according to the first comparison result, so as to generate the second abnormality determination coefficient RYC.

[0014] Preferably, the second comparison result generated by the second data analysis module is specifically as follows: When using the first abnormality determination coefficient YYC: If , which means that there is no traffic engineering safety problem for the current vehicle. , indicating that the current vehicle has traffic engineering safety issues; When using the second abnormality determination coefficient RYC: If , which means that there is no traffic engineering safety problem for the current vehicle. , indicating that the current vehicle has traffic engineering safety issues; The magnitude division generated by the second data analysis module is specifically as follows: When using the first abnormality determination coefficient YYC: If , which means that the current vehicle has a first-level traffic engineering safety problem, and the current vehicle is marked for key observation; like , indicating that the current vehicle has a secondary traffic engineering safety problem, the current vehicle is marked, and a text message notification is sent to remind the driver or owner to pay attention to the current road conditions; like , indicating that the current vehicle has a third-level traffic engineering safety problem, the current vehicle will be marked and a phone notification will be made to remind the driver or owner to pay attention to the current road conditions and notify nearby traffic police to pay attention to the vehicle; When using the second abnormality determination coefficient RYC: If , which means that the current vehicle has a first-level traffic engineering safety problem, and the current vehicle is marked for key observation; like , indicating that the current vehicle has a secondary traffic engineering safety problem, the current vehicle is marked, and a text message notification is sent to remind the driver or owner to pay attention to the current road conditions; like , indicating that the current vehicle has a third-level traffic engineering safety problem, the current vehicle will be marked and a phone notification will be made to remind the driver or owner to pay attention to the current road conditions and notify nearby traffic police to pay attention to the vehicle.

[0015] This application also includes a method for intelligent detection of traffic engineering environment, the specific steps are as follows: S1. Collecting traffic engineering environment data and vehicle data through a data acquisition module to generate a first data set and a second data set; S2. Preprocess the first data set and the second data set using a data preprocessing module, including data cleaning, denoising, outlier processing and dimensionless conversion, to ensure data quality and consistency; S3, using the first data calculation module to integrate and calculate the first data set, generate a correction determination coefficient XZX and a first correction intervention coefficient S1, a second correction intervention coefficient S2 and a third correction intervention coefficient S3, and use them for subsequent environmental correction analysis; S4. By using the first data analysis module, the generated correction determination coefficient XZX is compared with the preset first threshold value Y to generate a first comparison result, and it is determined whether a correction intervention coefficient needs to be introduced so as to effectively correct the environmental impact in subsequent calculations; S5, the second data calculation module integrates and calculates the second data set to generate a first abnormality determination coefficient YYC and a second abnormality determination coefficient RYC, which are used to identify abnormalities in traffic flow and road conditions; S6. The second data analysis module compares the first abnormality determination coefficient YYC and the second abnormality determination coefficient RYC with the preset first abnormality threshold R1 and the second abnormality threshold to generate a second comparison result, determine whether the current vehicle has a traffic engineering safety problem, and classify the problem according to the magnitude of the abnormality. The feedback module feeds back the result to the terminal for relevant personnel to issue a safety warning or response.

[0016] Compared with the prior art, the present invention has the following beneficial effects: 1. Through high-precision data collection and dimensionless processing, this system can ensure the acquisition of comprehensive and accurate traffic and environmental data from multiple dimensions, and through precise calculation and analysis, effectively correct the data and detect anomalies. Especially in dealing with complex environmental conditions and multi-source data fusion, this system can effectively avoid the errors and inaccuracies caused by a single data source in traditional systems. Under the real-time monitoring of traffic flow, vehicle speed, environmental factors and safety hazards, the system can provide more accurate traffic forecasts and safety warnings, reduce the risk of traffic accidents, improve traffic management efficiency, and ultimately achieve more intelligent and accurate urban traffic management and dispatch.

[0017] 2. This system integrates the maximum value of the window with the corresponding mean and the preset weight value to generate the correction determination coefficient XZX, which realizes the accurate correction of environmental factors on traffic flow. The introduction of weight values ​​allows the relative importance of various factors to be dynamically adjusted according to actual conditions, thereby improving the analysis accuracy of the system in different situations. The calculation of multiple correction intervention coefficients combines the real-time data at each timestamp with the mean data in the window. By analyzing the difference between the current environmental state and the historical average level, it realizes flexible response to sudden environmental changes. This design enables the system to make adjustments and interventions quickly, thereby improving the accuracy of traffic flow prediction and the response speed of safety warnings.

[0018] 3. The second data analysis module significantly improves the judgment accuracy and response capability of traffic engineering safety issues by generating the second comparison results and magnitude division. The module intelligently judges whether the vehicle has traffic engineering safety issues based on the comparison results of the first abnormal determination coefficient YYC and the second abnormal determination coefficient RYC, and takes corresponding early warning and response measures according to different safety problem levels. This design can flexibly adjust the threshold according to the actual situation, and accurately identify potential safety hazards by combining environmental factors and traffic data, greatly improving the real-time and accuracy of traffic safety management. Through the dynamic judgment of the first constant determination coefficient and the second abnormal determination coefficient RYC, the module can accurately distinguish different levels of traffic engineering safety issues. When the first constant determination coefficient or the second abnormal determination coefficient RYC exceeds the preset first abnormal threshold R or second abnormal threshold R, the system will divide the vehicle into different safety levels according to the specific values, and take different response measures for each level. Through this multi-level and hierarchical safety warning mechanism, the system can timely and effectively prevent traffic accidents and reduce major risks caused by traffic safety issues. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 It is a system flow chart of the present invention.

[0020] Figure 2 It is a diagram of the method steps of the present invention.

[0021] In the figure: 1. data acquisition module; 11. first data acquisition unit; 12. second data acquisition unit; 2. data preprocessing module; 3. first data calculation module; 4. first data analysis module; 5. second data calculation module; 6. second data analysis module; 7. feedback module. DETAILED DESCRIPTION

[0022] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0023] Example 1: Please refer to Figure 1 , a traffic engineering environment intelligent detection system, comprising a data acquisition module 1, a data preprocessing module 2, a first data calculation module 3, a first data analysis module 4, a second data calculation module 5, a second data analysis module 6 and a feedback module 7; The data collection module 1 is used to collect traffic engineering environment data and vehicle data, and form a first data set and a second data set; The data preprocessing module 2 is used to preprocess the first data set and the second data set and make them dimensionless; The first data calculation module 3 is used to perform integrated calculation on the first data set, so as to generate a modified determination coefficient XZX and a first modified intervention coefficient S1, a second modified intervention coefficient S2 and a third modified intervention coefficient S3; The first data analysis module 4 is used to compare the modified determination coefficient XZX with the preset first threshold value Y, so as to generate a first comparison result, and judge whether it is necessary to use the first data calculation module 3 in subsequent calculations to perform integrated calculations on the first data set, so as to generate the modified determination coefficient XZX and the first modified intervention coefficient S1, the second modified intervention coefficient S2 and the third modified intervention coefficient S3; The second data calculation module 5 is used to perform integrated calculation on the second data set, so as to generate a first abnormality determination coefficient YYC and a second abnormality determination coefficient RYC; The second data analysis module 6 is used to compare the first abnormality determination coefficient YYC and the second abnormality determination coefficient RYC with the preset first abnormality threshold R1 and the second abnormality threshold R2, respectively, so as to generate a second comparison result, and determine whether the current vehicle has a traffic engineering safety problem according to the second comparison result, and classify the abnormality magnitude; The feedback module 7 is used to feed back the first comparison result and the second comparison result to the terminal for data display.

[0024] In this embodiment: Data acquisition module 1 is the basic component of the intelligent detection system for traffic engineering environment, which is responsible for real-time collection of traffic environment data and vehicle data, and forms two data sets with the collected information - the first data set and the second data set. The first data set mainly includes traffic flow parameters such as vehicle volume, vehicle speed, and traffic density, while the second data set involves environmental data, such as environmental condition data such as temperature, humidity, precipitation, and visibility. Through high-precision sensors and monitoring equipment, the data acquisition module can comprehensively and timely obtain multi-dimensional traffic and environmental data, providing an accurate source of information for subsequent analysis and optimization. The role of this module is to ensure that the data foundation of the system is rich and accurate enough to support subsequent data processing and decision-making processes.

[0025] Data preprocessing module 2 is responsible for preprocessing the first data set and the second data set, and non-dimensionalizing the data. Dimensionless processing refers to normalizing data units and dimensions so that data from different sources can be compared and integrated to avoid data errors caused by dimensional differences. The task of this module is to standardize the data obtained from different sensors and monitoring equipment, remove interference factors such as noise and outliers, and ensure that the data quality meets certain standards. The pre-processed data can improve the accuracy of subsequent analysis and calculations, and avoid adverse effects caused by inconsistent or non-standard data.

[0026] The first data calculation module 3 integrates and calculates the preprocessed first data set to generate a modified determination coefficient XZX and a modified intervention coefficient. These coefficients are used to reflect the relationship between traffic flow data and environmental factors, and to correct the calculation results of the data. The modified determination coefficient XZX is mainly used to determine whether there are abnormal conditions or potential problems, while the modified intervention coefficient is used to adjust the calculation model when necessary to ensure higher accuracy. The role of this module is to provide a more accurate correction plan for subsequent decision-making by systematically calculating and analyzing traffic flow and environmental data, thereby improving the reliability and predictive ability of the overall data.

[0027] The first data analysis module 4 compares the generated correction determination coefficient XZX with the preset first threshold value Y, and generates a first comparison result based on the comparison result. If the correction determination coefficient XZX exceeds the preset threshold range, the module will determine whether it is necessary to use the correction intervention coefficient in subsequent calculations. This analysis process can monitor in real time whether the traffic data meets the expected normal range. When an abnormality occurs, the system will automatically adjust the calculation method to avoid the influence of erroneous data. Through this module, the system can flexibly respond to complex traffic conditions, automatically adjust and optimize the calculation method, and improve the adaptability and flexibility of the system.

[0028] The second data calculation module 5 mainly integrates and calculates the second data set to generate the first abnormality determination coefficient YYC and the second abnormality determination coefficient RYC. These coefficients are used to evaluate whether the environmental data is normal and to determine whether environmental factors may affect traffic safety or the smoothness of traffic flow. The first abnormality determination coefficient YYC is mainly used to identify abnormal points in environmental data, while the second abnormality determination coefficient RYC further classifies and processes abnormal data. The role of this module is to predict and identify possible risk factors in advance by analyzing the potential impact of environmental factors on traffic, and provide basic data for system optimization and safety prediction.

[0029] The second data analysis module 6 compares the generated first abnormality determination coefficient YYC and the second abnormality determination coefficient RYC with the preset abnormality threshold, thereby generating a second comparison result. Through the comparison results, the system can determine whether the current vehicle has a traffic engineering safety problem and classify the abnormal magnitude. The function of this module is to analyze the safety of the traffic environment in real time, identify potential traffic safety hazards, and help traffic management personnel make effective decisions and dispatch through classification. This module can provide timely warning information to avoid traffic accidents caused by environmental factors or equipment failures and ensure road safety.

[0030] Feedback module 7 is the output link of the system, which feeds back the first comparison result and the second comparison result to the terminal for data display. Through the visual interface, traffic management personnel can clearly understand the current traffic conditions and environmental conditions, and view information such as traffic flow, vehicle speed, traffic density, and traffic safety warnings and environmental data in real time. The feedback module enables all calculation and analysis results to be delivered to decision makers in a timely manner, ensuring that the system can reflect traffic changes in real time and make adjustments. This module greatly improves the efficiency and accuracy of traffic management, and facilitates managers to respond quickly to emergencies.

[0031] Through high-precision data collection and dimensionless processing, this system can ensure the acquisition of comprehensive and accurate traffic and environmental data from multiple dimensions, and through precise calculation and analysis, effectively correct the data and detect anomalies. Especially in dealing with complex environmental conditions and multi-source data fusion, this system can effectively avoid the errors and inaccuracies caused by a single data source in traditional systems. Under the real-time monitoring of traffic flow, vehicle speed, environmental factors and safety hazards, the system can provide more accurate traffic forecasts and safety warnings, reduce the risk of traffic accidents, improve traffic management efficiency, and ultimately achieve more intelligent and accurate urban traffic management and dispatch.

[0032] Example 2: Please refer to Figure 1 The data acquisition module 1 includes a first data acquisition unit 11 and a second data acquisition unit 12, and divides the data into time stamps, wherein the time stamps are recorded as: 1, 2, 3, ..., n; The first data collection unit 11 is used to collect interference information of traffic engineering, including ambient temperature, ambient humidity, precipitation, road surface temperature and road damage index; The ambient temperatures are recorded as A1, A2, A3, ..., An according to the timestamps; The ambient humidity is recorded as B1, B2, B3, ..., Bn according to the timestamp; The precipitation amounts are recorded as C1, C2, C3, ..., Cn according to the timestamps; The road surface temperatures are recorded as D1, D2, D3, ..., Dn according to the timestamps; The road damage index is recorded as E1, E2, E3, ..., En according to the timestamp; The second data collection unit 12 is used to collect basic information of traffic engineering, including vehicle flow, vehicle speed, traffic density and road friction coefficient; The traffic flow is recorded as F1, F2, F3, ..., Fn according to the timestamp; The vehicle speeds are recorded as G1, G2, G3, ..., Gn according to the timestamps; Traffic densities are recorded as H1, H2, H3, ..., Hn according to the timestamps; The road friction coefficients are recorded as I1, I2, I3, ..., In according to the timestamps.

[0033] In this embodiment: the data collection module 1 significantly improves the accuracy and detail of data recording by subdividing the data collection units and marking the collected data with timestamps. Each data item corresponds to a specific time point, and the timestamp is used to clearly identify the data collection time, thereby effectively avoiding the risk of data confusion, loss or misanalysis. This precise time record provides a solid foundation for subsequent data processing, analysis and optimization, especially when facing high-frequency, dynamically changing traffic flows and environmental conditions, it can track, monitor and respond in a timely manner more efficiently.

[0034] The first data collection unit 11 focuses on collecting interference information related to the traffic environment, including ambient temperature, humidity, precipitation, road surface temperature, and road damage index, while the second data collection unit 12 focuses on collecting traffic flow and road performance data. Through such division of labor, different types of data can be collected independently and accurately, avoiding the problem of information overload or confusion, and ensuring the independence and accuracy of various types of data. This design allows environmental data and traffic flow data to be clearly distinguished to avoid mutual interference, and can help the system accurately identify the specific impact of environmental factors on traffic flow, providing more accurate data support for traffic safety warnings.

[0035] Through the above design, this system can capture various changes in the traffic environment in more detail and conduct targeted analysis according to different types of data. When facing bad weather, road damage or emergencies, the system can adjust traffic management strategies in real time, optimize the prediction accuracy of traffic flow, vehicle speed, density, etc., and the impact on traffic flow can be identified in advance through precise data analysis, so that timely adjustment measures can be taken to reduce the risk of accidents. In particular, real-time monitoring of special parameters such as road damage index can provide data support for road maintenance and safety management, help traffic management departments to promptly discover potential safety hazards, deploy corresponding repair measures in advance, and reduce the probability of traffic accidents.

[0036] Example 3: Please refer to Figure 1 The data preprocessing module 2 preprocesses the first data set and the second data set, including data cleaning, noise removal, outlier processing, and dimensionless conversion.

[0037] In this embodiment: the data preprocessing module 2 significantly improves the quality of the data and the accuracy of subsequent analysis by comprehensively preprocessing the first data set and the second data set. First, the data cleaning step helps to eliminate redundant, repeated or invalid information in the original data, ensuring that the system only processes valid data that meets the analysis requirements. This process ensures the accuracy and integrity of the data and provides a reliable basis for subsequent analysis. Secondly, the noise removal operation can effectively eliminate inaccurate data introduced during the acquisition process due to equipment errors or external environmental factors, reduce the interference of noise on the analysis results, and further improve the stability and reliability of the data. Outlier processing avoids the impact of erroneous data on subsequent calculation results by timely identifying and correcting abnormal points in the data, ensuring the rationality and consistency of the data.

[0038] Dimensionless processing standardizes the dimensional differences between different data sets, allowing data from different sensors and monitoring equipment to be compared and fused on a unified scale. Dimensionless processing effectively solves the data compatibility issues that may be caused by inconsistent dimensions, allowing heterogeneous data such as environmental data and traffic flow data to be analyzed under the same framework. This processing not only improves the consistency and comparability of data, but also provides more accurate and efficient support for subsequent calculations, modeling, and data fusion, and enhances the system's adaptability to dynamically changing traffic environments and complex and changing external conditions.

[0039] Example 4: Please refer to Figure 1, the first data calculation module 3 plans the window size for each parameter in the processed first data set, and records it as m, selects the maximum value of each parameter in the first data set in window m, and records them as the maximum value Amax of the ambient temperature window, the maximum value Bmax of the ambient humidity window, the maximum value Cmax of the precipitation window, the maximum value Dmax of the road surface temperature window, and the maximum value Emax of the road damage index window; The parameters in the first data set in window m are calculated to generate the window means of each parameter, which are recorded as the ambient temperature window mean PA, the ambient humidity window mean PB, the precipitation window mean PC, the road surface temperature window mean PD and the road damage index window mean PE.

[0040] The first data calculation module 3 integrates and calculates the maximum value Amax of the ambient temperature window, the maximum value Bmax of the ambient humidity window, the maximum value Cmax of the precipitation window, the maximum value Dmax of the road surface temperature window, and the maximum value Emax of the road damage index window with the corresponding average values ​​PA of the ambient temperature window, the average values ​​PB of the ambient humidity window, the average values ​​PC of the precipitation window, the average values ​​PD of the road surface temperature window, and the average values ​​PE of the road damage index window, as well as the preset weight values, so as to generate the modified determination coefficient XZX; The first data calculation module 3 integrates and calculates the ambient temperature An, ambient humidity Bn, precipitation Cn, road surface temperature Dn and road damage index En at the nth timestamp with the corresponding ambient temperature window mean PA, ambient humidity window mean PB, precipitation window mean PC, road surface temperature window mean PD and road damage index window mean PE, thereby generating the first corrected intervention coefficient S1, the second corrected intervention coefficient S2 and the third corrected intervention coefficient S3.

[0041] In this embodiment: the first data calculation module 3 significantly improves the data analysis capability and correction accuracy of the traffic engineering environment monitoring system by performing in-depth calculations on the preprocessed first data set. First, the design of the planning window size m enables the system to flexibly divide the data window on the time axis and provide local context for the data in each window. This can effectively avoid calculation errors caused by data fluctuations or short-term anomalies, thereby ensuring the stability and accuracy of the analysis. The maximum value calculation in each window helps the system identify the extreme values ​​of each parameter in a specific time window, providing an important basis for subsequent correction calculations.

[0042] By calculating the mean of the data in each window, the module can effectively mitigate the impact of data fluctuations at a single moment. Mean processing ensures that the system will not overreact to extreme changes in the short term, thereby increasing sensitivity to long-term trends and average changes. In this way, the system can better reflect long-term environmental change trends and reduce the interference of accidental factors on the analysis results.

[0043] This system integrates the maximum value of the window with the corresponding mean and the preset weight value to generate a corrected determination coefficient XZX, which achieves accurate correction of environmental factors on traffic flow. The introduction of weight values ​​allows the relative importance of various factors to be dynamically adjusted according to actual conditions, thereby improving the analysis accuracy of the system in different scenarios.

[0044] The calculation of multiple modified intervention coefficients combines the real-time data at each timestamp with the mean data within the window, and analyzes the difference between the current environmental state and the historical average level to achieve flexible response to sudden environmental changes. This design enables the system to make adjustments and interventions quickly, thereby improving the accuracy of traffic flow prediction and the response speed of safety warnings.

[0045] The specific calculation formulas are as follows: Where: n is the total number of timestamps, m is the window value, i is the i-th timestamp, a1, a2, a3, a4 and a5 are weight values, and the values ​​of a1, a2, a3, a4 and a5 are adjusted and set by the user; Ai, Bi, Ci, Di and Ei are the ambient temperature, ambient humidity, precipitation, road surface temperature and road damage index at the i-th time stamp respectively; An, Bn, Cn, Dn and En are the ambient temperature, ambient humidity, precipitation, road surface temperature and road damage index at the nth time stamp, respectively; PA is the mean value of the ambient temperature window, PB is the mean value of the ambient humidity window, PC is the mean value of the precipitation window, PD is the mean value of the pavement temperature window, PE is the mean value of the road damage index window, Amax is the maximum value of the ambient temperature window, Bmax is the maximum value of the ambient humidity window, Cmax is the maximum value of the precipitation window, Dmax is the maximum value of the pavement temperature window, and Emax is the maximum value of the road damage index window.

[0046] Example 5: Please refer to Figure 1 The first comparison result generated by the first data analysis module 4 is as follows: when When , it means that the first correction intervention coefficient S1, the second correction intervention coefficient S2 and the third correction intervention coefficient S3 are not needed in the subsequent calculation. When , it means that the first corrected intervention coefficient S1, the second corrected intervention coefficient S2 and the third corrected intervention coefficient S3 need to be used in the subsequent calculation.

[0047] In this embodiment: the first data analysis module 4 significantly improves the system's dynamic adaptability to environmental changes and improves the accuracy and efficiency of calculations by generating the first comparison result. When XZX ≤ Y, it means that the first correction intervention coefficient S1, the second correction intervention coefficient S2 and the third correction intervention coefficient S3 are not needed in subsequent calculations, which means that the current environmental changes have little impact on traffic flow. The system can maintain the original calculation model for analysis to avoid introducing unnecessary complex calculations, thereby improving calculation efficiency and speeding up response speed. On the contrary, when XZX > Y, it means that the correction intervention coefficient needs to be introduced in subsequent calculations, indicating that the environmental changes at this time are more significant. The system should dynamically adjust the calculation method according to this change to more accurately reflect the impact of environmental factors on parameters such as traffic flow, vehicle speed and traffic density.

[0048] This design optimizes the flexibility and adaptability of the system. By dynamically determining whether multiple correction intervention coefficients need to be introduced, the system can intelligently adjust the calculation strategy according to real-time environmental changes, avoiding invalid or excessive calculation interventions, thereby ensuring that computing resources are effectively used. Especially when dealing with complex traffic environments and sudden weather changes, the system can flexibly adjust the calculation method to provide more accurate analysis and prediction results, and improve the system's real-time response capabilities.

[0049] Example 6: Please refer to Figure 1 , the second data calculation module 5 performs window value planning on the parameters in the processed second data set, and records the window value as m, selects the maximum values ​​of the parameters in the window m, and records them as the maximum value of the vehicle flow window Fmax, the maximum value of the vehicle speed window Gmax, the maximum value of the traffic density window Hmax, and the maximum value of the road friction coefficient window Imax; The parameters in the second data set in window m are calculated to generate window means of various parameters, which are recorded as the vehicle flow window mean PF, the vehicle speed window mean PG, the traffic density window mean PH and the road friction coefficient window mean PI respectively.

[0050] According to the first comparison result, the second data calculation module 5 integrates and calculates the maximum value Fmax of the traffic flow window, the maximum value Gmax of the vehicle speed window, the maximum value Hmax of the traffic density window, the maximum value Imax of the road friction coefficient window, the traffic flow Fn, the vehicle speed Gn, the traffic density Hn, the road friction coefficient In, the traffic flow window mean PF, the speed window mean PG, the traffic density window mean PH and the road friction coefficient window mean PI, so as to generate the first abnormality determination coefficient YYC. According to the first comparison result, the second data calculation module 5 integrates and calculates the maximum value Fmax of the traffic flow window, the maximum value Gmax of the speed window, the maximum value Hmax of the traffic density window, the maximum value Imax of the road friction coefficient window, the traffic flow Fn, the vehicle speed Gn, the traffic density Hn, the road friction coefficient In, the traffic flow window mean PF, the speed window mean PG, the traffic density window mean PH, the road friction coefficient window mean PI, the first corrected intervention coefficient S1, the second corrected intervention coefficient S2 and the third corrected intervention coefficient S3, so as to generate the second abnormality determination coefficient RYC.

[0051] In this embodiment: the second data calculation module 5 significantly improves the abnormal detection capability and correction accuracy of key parameters such as traffic flow, vehicle speed, traffic density and road friction coefficient by performing comprehensive calculation and analysis on the pre-processed second data set. The second data calculation module 5 first divides the data into windows, defines the window value as m, and calculates the maximum value of each parameter in the window, such as the maximum value Fmax of the traffic flow window, the maximum value Gmax of the speed window, the maximum value Hmax of the traffic density window, and the maximum value Imax of the road friction coefficient window. In addition, the module also calculates the mean of each parameter in the window, such as the mean value PF of the traffic flow window, the mean value PG of the speed window, the mean value PH of the traffic density window, and the mean value PI of the road friction coefficient window. This window design provides a solid foundation for subsequent data analysis and ensures the validity and representativeness of the data in each time window.

[0052] By calculating the maximum and mean values ​​of the window, the second data calculation module 5 can accurately identify potential abnormal data based on the parameter fluctuation range within the time period, avoiding interference with the overall calculation results due to short-term fluctuations or extreme situations. This design can accurately capture abnormal changes in the traffic environment and provide more reliable support for subsequent analysis and decision-making.

[0053] After calculating the maximum and mean values ​​of the window, the second data calculation module 5 intelligently adjusts the calculation process according to the first comparison result. When XZX ≤ Y, the module can perform analysis according to the conventional calculation process; when XZX > Y, a correction coefficient needs to be introduced to reflect the significant impact of environmental changes on parameters such as traffic flow, vehicle speed and density. The module combines real-time data such as vehicle flow, vehicle speed, traffic density, and road friction coefficient with the corresponding window mean to generate the first abnormality determination coefficient YYC and the second abnormality determination coefficient RYC, thereby providing a basis for early warning of traffic flow safety and road conditions. This design can dynamically adjust the threshold according to different scenarios, thereby improving the accuracy of anomaly detection.

[0054] By integrating the first correction intervention coefficient S1, the second correction intervention coefficient S2 and other key parameters, the second data calculation module 5 further enhances the system's ability to respond to sudden changes in the traffic environment. For example, when complex or sudden traffic conditions occur, the system can adjust the calculation strategy in a timely manner according to the real-time situation and generate an accurate abnormality determination coefficient, thereby effectively avoiding the impact of environmental changes or system errors on traffic safety management decisions.

[0055] The specific calculation formulas are as follows: Where: n is the total number of timestamps, m is the window value, and i is the i-th timestamp; Fi, Gi, Hi and Ii are the traffic volume, vehicle speed, traffic density and road friction coefficient at the i-th time stamp respectively; Fn, Gn, Hn and In are the traffic volume, vehicle speed, traffic density and road friction coefficient at the nth time stamp respectively; PF is the mean of the traffic flow window, PG is the mean of the vehicle speed window, PH is the mean of the traffic density window, PI is the mean of the road friction coefficient window, Fmax is the maximum value of the traffic flow window, Gmax is the maximum value of the vehicle speed window, Hmax is the maximum value of the traffic density window, and Imax is the maximum value of the road friction coefficient window.

[0056] Example 7: Please refer to Figure 1 The second comparison result generated by the second data analysis module 6 is as follows: When using the first abnormality determination coefficient YYC: If , which means that there is no traffic engineering safety problem for the current vehicle. , indicating that the current vehicle has traffic engineering safety issues; When using the second abnormality determination coefficient RYC: If , which means that there is no traffic engineering safety problem for the current vehicle. , indicating that the current vehicle has traffic engineering safety issues; The magnitude division generated by the second data analysis module 6 is as follows: When using the first abnormality determination coefficient YYC: If , which means that the current vehicle has a first-level traffic engineering safety problem, and the current vehicle is marked for key observation; like , indicating that the current vehicle has a secondary traffic engineering safety problem, the current vehicle is marked, and a text message notification is sent to remind the driver or owner to pay attention to the current road conditions; like , indicating that the current vehicle has a third-level traffic engineering safety problem, the current vehicle will be marked and a phone notification will be made to remind the driver or owner to pay attention to the current road conditions and notify nearby traffic police to pay attention to the vehicle; When using the second abnormality determination coefficient RYC: If , which means that the current vehicle has a first-level traffic engineering safety problem, and the current vehicle is marked for key observation; like , indicating that the current vehicle has a secondary traffic engineering safety problem, the current vehicle is marked, and a text message notification is sent to remind the driver or owner to pay attention to the current road conditions; like , indicating that the current vehicle has a third-level traffic engineering safety problem, the current vehicle will be marked and a phone notification will be made to remind the driver or owner to pay attention to the current road conditions and notify nearby traffic police to pay attention to the vehicle.

[0057] In this embodiment: the second data analysis module 6 significantly improves the judgment accuracy and response capability of traffic engineering safety issues by generating the second comparison result and magnitude division. The module intelligently judges whether the vehicle has a traffic engineering safety issue based on the comparison result of the first abnormality determination coefficient YYC and the second abnormality determination coefficient RYC, and takes corresponding early warning and response measures according to different safety problem levels. This design can flexibly adjust the threshold according to the actual situation, and combine environmental factors with traffic data to accurately identify potential safety hazards, greatly improving the real-time and accuracy of traffic safety management.

[0058] Through dynamic judgment of the first constant determination coefficient and the second abnormal determination coefficient RYC, the module can accurately distinguish different levels of traffic engineering safety issues. When the first constant determination coefficient or the second abnormal determination coefficient RYC exceeds the preset first abnormal threshold R1 or the second abnormal threshold R2, the system will divide the vehicle into different safety levels according to the specific values, and take different response measures for each level. Through this multi-level and graded safety warning mechanism, the system can timely and effectively prevent traffic accidents and reduce major risks caused by traffic safety issues.

[0059] The introduction of the magnitude classification scheme further refines the classification of safety issues and provides targeted response measures. This step-by-step response approach can flexibly adjust the intensity and speed of emergency response according to the severity of the problem, ensuring that the system handles traffic safety hazards more accurately and efficiently.

[0060] This application also includes a method for intelligent detection of traffic engineering environment, see Figure 2 , the specific steps are as follows: S1, collecting traffic engineering environment data and vehicle data through data collection module 1 to generate a first data set and a second data set; S2, using the data preprocessing module 2 to preprocess the first data set and the second data set, including data cleaning, denoising, outlier processing and dimensionless conversion, to ensure the quality and consistency of the data; S3, using the first data calculation module 3 to integrate and calculate the first data set, generate the correction determination coefficient XZX and the first correction intervention coefficient S1, the second correction intervention coefficient S2 and the third correction intervention coefficient S3, and use them for subsequent environmental correction analysis; S4, by means of the first data analysis module 4, the generated correction determination coefficient XZX is compared with the preset first threshold value Y to generate a first comparison result, and it is determined whether a correction intervention coefficient needs to be introduced so as to effectively correct the environmental impact in subsequent calculations; S5, the second data calculation module 5 integrates and calculates the second data set to generate a first abnormality determination coefficient YYC and a second abnormality determination coefficient RYC, which are used to identify abnormalities in traffic flow and road conditions; S6. The second data analysis module 6 compares the first abnormality determination coefficient YYC and the second abnormality determination coefficient RYC with the preset first abnormality threshold R1 and the second abnormality threshold to generate a second comparison result, determine whether the current vehicle has a traffic engineering safety problem, and classify the problem according to the magnitude of the abnormality. The feedback module 7 feeds back the result to the terminal for relevant personnel to issue a safety warning or response.

[0061] The contents not described in detail in this specification belong to the prior art known to professional and technical personnel in this field.

[0062] Although the present invention has been described in detail with reference to the aforementioned embodiments, it is still possible for those skilled in the art to modify the technical solutions described in the aforementioned embodiments, or to make equivalent substitutions for some of the technical features therein. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. An intelligent detection system for traffic engineering environment, characterized by: It comprises a data acquisition module (1), a data preprocessing module (2), a first data calculation module (3), a first data analysis module (4), a second data calculation module (5), a second data analysis module (6) and a feedback module (7); The data collection module (1) is used to collect traffic engineering environment data and vehicle data, and form a first data set and a second data set; The data preprocessing module (2) is used to preprocess the first data set and the second data set and make them dimensionless; The first data calculation module (3) is used to perform integrated calculation on the first data set, thereby generating a modified determination coefficient XZX and the first data calculation module (3) is used to perform integrated calculation on the first data set, thereby generating a modified determination coefficient XZX and a first modified intervention coefficient S1, a second modified intervention coefficient S2 and a third modified intervention coefficient S3; The first data analysis module (4) is used to compare the modified determination coefficient XZX with a preset first threshold value Y, thereby generating a first comparison result, and judging whether it is necessary to use the first data calculation module (3) in subsequent calculations to perform integrated calculations on the first data set, thereby generating the modified determination coefficient XZX and the first modified intervention coefficient S1, the second modified intervention coefficient S2, and the third modified intervention coefficient S3; The second data calculation module (5) is used to perform integrated calculation on the second data set, thereby generating a first abnormality determination coefficient YYC and a second abnormality determination coefficient RYC; The second data analysis module (6) is used to compare the first abnormality determination coefficient YYC and the second abnormality determination coefficient RYC with the preset first abnormality threshold R1 and the second abnormality threshold R2 respectively, so as to generate a second comparison result, and determine whether the current vehicle has a traffic engineering safety problem according to the second comparison result, and classify the abnormality magnitude; The feedback module (7) is used to feed back the first comparison result and the second comparison result to the terminal for data display.

2. The intelligent detection system for traffic engineering environment according to claim 1 is characterized by: The data acquisition module (1) comprises a first data acquisition unit (11) and a second data acquisition unit (12), and divides the data into time stamps, wherein the time stamps are recorded as: 1, 2, 3, ..., n; The first data collection unit (11) is used to collect interference information of traffic engineering, including ambient temperature, ambient humidity, precipitation, road surface temperature and road damage index; The ambient temperatures are recorded as A1, A2, A3, ..., An respectively according to the timestamps; The environmental humidity is recorded as B1, B2, B3, ..., Bn according to the timestamp; The precipitation amounts are recorded as C1, C2, C3, ..., Cn according to the timestamps; The road surface temperatures are recorded as D1, D2, D3, ..., Dn according to the timestamps; The road damage indexes are recorded as E1, E2, E3, ..., En according to the timestamps; The second data collection unit (12) is used to collect basic information of traffic engineering, including vehicle flow, vehicle speed, traffic density and road friction coefficient; The vehicle flows are recorded as F1, F2, F3, ..., Fn according to the timestamps; The vehicle speeds are recorded as G1, G2, G3, ..., Gn according to the timestamps; The traffic densities are recorded as H1, H2, H3, ..., Hn respectively according to the timestamps; The road friction coefficients are recorded as I1, I2, I3, ..., In according to the timestamps.

3. The intelligent detection system for traffic engineering environment according to claim 2 is characterized in that: The data preprocessing module (2) preprocesses the first data set and the second data set, including data cleaning, noise removal, outlier processing, and dimensionless conversion.

4. The intelligent detection system for traffic engineering environment according to claim 3 is characterized by: The first data calculation module (3) plans a window size for each parameter in the processed first data set, and records it as m, selects the maximum value of each parameter in the first data set in window m, and records them as the maximum value Amax of the ambient temperature window, the maximum value Bmax of the ambient humidity window, the maximum value Cmax of the precipitation window, the maximum value Dmax of the road surface temperature window, and the maximum value Emax of the road damage index window; The parameters in the first data set in window m are calculated to generate the window means of each parameter, which are recorded as the ambient temperature window mean PA, the ambient humidity window mean PB, the precipitation window mean PC, the road surface temperature window mean PD and the road damage index window mean PE.

5. The intelligent detection system for traffic engineering environment according to claim 4 is characterized by: The first data calculation module (3) integrates and calculates the maximum value Amax of the ambient temperature window, the maximum value Bmax of the ambient humidity window, the maximum value Cmax of the precipitation window, the maximum value Dmax of the road surface temperature window, and the maximum value Emax of the road damage index window with the corresponding average values ​​PA of the ambient temperature window, the average values ​​PB of the ambient humidity window, the average values ​​PC of the precipitation window, the average values ​​PD of the road surface temperature window, and the average values ​​PE of the road damage index window, as well as a preset weight value, thereby generating a modified determination coefficient XZX; The first data calculation module (3) integrates and calculates the ambient temperature An, ambient humidity Bn, precipitation Cn, road surface temperature Dn and road damage index En at the nth timestamp with the corresponding ambient temperature window average PA, ambient humidity window average PB, precipitation window average PC, road surface temperature window average PD and road damage index window average PE, thereby generating a first corrected intervention coefficient S1, a second corrected intervention coefficient S2 and a third corrected intervention coefficient S3.

6. The intelligent detection system for traffic engineering environment according to claim 5 is characterized by: The first comparison result generated by the first data analysis module (4) is specifically as follows: when When , it means that the first correction intervention coefficient S1, the second correction intervention coefficient S2 and the third correction intervention coefficient S3 are not needed in the subsequent calculation. When , it means that the first corrected intervention coefficient S1, the second corrected intervention coefficient S2 and the third corrected intervention coefficient S3 need to be used in the subsequent calculation.

7. The intelligent detection system for traffic engineering environment according to claim 6 is characterized by: The second data calculation module (5) performs window value planning on the parameters in the processed second data set, and records the window value as m, selects the maximum values ​​of the parameters in the window m, and records them as the maximum value of the vehicle flow window Fmax, the maximum value of the vehicle speed window Gmax, the maximum value of the traffic density window Hmax, and the maximum value of the road friction coefficient window Imax respectively; The parameters in the second data set in window m are calculated to generate window means of various parameters, which are recorded as the vehicle flow window mean PF, the vehicle speed window mean PG, the traffic density window mean PH and the road friction coefficient window mean PI respectively.

8. The intelligent detection system for traffic engineering environment according to claim 7 is characterized by: The second data calculation module (5) integrates and calculates the maximum value Fmax of the traffic flow window, the maximum value Gmax of the vehicle speed window, the maximum value Hmax of the traffic density window, the maximum value Imax of the road friction coefficient window, the traffic flow Fn, the vehicle speed Gn, the traffic density Hn, the road friction coefficient In, the traffic flow window mean PF, the vehicle speed window mean PG, the traffic density window mean PH and the road friction coefficient window mean PI according to the first comparison result, so as to generate a first abnormality determination coefficient YYC. The second data calculation module (5) integrates and calculates the maximum value Fmax of the traffic flow window, the maximum value Gmax of the vehicle speed window, the maximum value Hmax of the traffic density window, the maximum value Imax of the road friction coefficient window, the traffic flow Fn, the vehicle speed Gn, the traffic density Hn, the road friction coefficient In, the traffic flow window mean PF, the vehicle speed window mean PG, the traffic density window mean PH, the road friction coefficient window mean PI, the first corrected intervention coefficient S1, the second corrected intervention coefficient S2 and the third corrected intervention coefficient S3 according to the first comparison result, so as to generate a second abnormality determination coefficient RYC.

9. The intelligent detection system for traffic engineering environment according to claim 8 is characterized by: The second comparison result generated by the second data analysis module (6) is specifically as follows: When using the first abnormality determination coefficient YYC: If , which means that there is no traffic engineering safety problem for the current vehicle. , indicating that the current vehicle has traffic engineering safety issues; When using the second abnormality determination coefficient RYC: If , which means that there is no traffic engineering safety problem for the current vehicle. , indicating that the current vehicle has traffic engineering safety issues; The magnitude division generated by the second data analysis module (6) is specifically as follows: When using the first abnormality determination coefficient YYC: If , which means that the current vehicle has a first-level traffic engineering safety problem, and the current vehicle is marked for key observation; like , indicating that the current vehicle has a secondary traffic engineering safety problem, the current vehicle is marked, and a text message notification is sent to remind the driver or owner to pay attention to the current road conditions; like , indicating that the current vehicle has a third-level traffic engineering safety problem, the current vehicle will be marked and a phone notification will be made to remind the driver or owner to pay attention to the current road conditions and notify nearby traffic police to pay attention to the vehicle; When using the second abnormality determination coefficient RYC: If , which means that the current vehicle has a first-level traffic engineering safety problem, and the current vehicle is marked for key observation; like , indicating that the current vehicle has a secondary traffic engineering safety problem, the current vehicle is marked, and a text message notification is sent to remind the driver or owner to pay attention to the current road conditions; like , indicating that the current vehicle has a third-level traffic engineering safety problem, the current vehicle will be marked and a phone notification will be made to remind the driver or owner to pay attention to the current road conditions and notify nearby traffic police to pay attention to the vehicle.

10. A method for intelligent detection of traffic engineering environment, used to execute a system for intelligent detection of traffic engineering environment as claimed in any one of claims 1 to 9, characterized in that: The specific steps are as follows: S1. Collecting traffic engineering environment data and vehicle data through a data collection module (1) to generate a first data set and a second data set; S2, using the data preprocessing module (2) to preprocess the first data set and the second data set, including data cleaning, denoising, outlier processing and dimensionless conversion, to ensure data quality and consistency; S3, using the first data calculation module (3) to perform integrated calculation on the first data set, generate a correction determination coefficient XZX and a first correction intervention coefficient S1, a second correction intervention coefficient S2 and a third correction intervention coefficient S3, and use them for subsequent environmental correction analysis; S4, comparing the generated correction determination coefficient XZX with a preset first threshold value Y through the first data analysis module (4), generating a first comparison result, and judging whether it is necessary to introduce a correction intervention coefficient, so as to effectively correct the environmental impact in subsequent calculations; S5, the second data calculation module (5) integrates and calculates the second data set to generate a first abnormality determination coefficient YYC and a second abnormality determination coefficient RYC, which are used to identify abnormalities in traffic flow and road conditions; S6. The second data analysis module (6) compares the first abnormality determination coefficient YYC and the second abnormality determination coefficient RYC with the preset first abnormality threshold R1 and the second abnormality threshold, generates a second comparison result, determines whether the current vehicle has a traffic engineering safety problem, and classifies the problem according to the abnormality magnitude. The feedback module (7) feeds back the result to the terminal for relevant personnel to issue a safety warning or response.

Images