Mobile monitoring early warning method and system based on expressway operation safety

Abstract

The invention discloses a mobile monitoring and early warning method and system based on expressway operation safety, which are used in the field of monitoring and early warning, and the mobile monitoring and early warning method comprises the following steps: collecting operation data of an expressway in real time by using a pre-deployed mobile monitoring unit; analyzing the operation data by using the operation data analysis model; evaluating the security risk by using a random forest algorithm; and according to a risk assessment result, generating early warning information, and starting a preset emergency response mechanism. According to the method, the current safety risk can be identified, and risk points possibly appearing in the future can be analyzed and predicted through historical data, so that preparation is made in advance, the capability of dealing with emergencies is enhanced, and the method is of great importance for improving the overall safety level of the expressway.

Description

Technical Field

[0001] The present invention relates to the field of monitoring and early warning, and in particular to a mobile monitoring and early warning method and system based on highway operation safety. Background Art

[0002] Highway operation safety refers to ensuring the smooth and safe flow of traffic, preventing and reducing traffic accidents, and protecting the safety of people and vehicles during the daily operation of highways. It involves many aspects, including but not limited to: the integrity and functional maintenance of infrastructure, such as the repair and maintenance of bridges, tunnels, road surfaces, etc.; traffic management, through real-time monitoring of traffic flow, vehicle speed, etc., rational allocation of traffic resources, and taking necessary traffic control measures (such as speed limit, diversion, etc.); emergency response, for traffic accidents, natural disasters (such as mudslides, floods), severe weather (such as haze, heavy snow), etc., rapid response measures are taken, including rescue, road condition information release, traffic guidance, etc.

[0003] Mobile monitoring and early warning refers to real-time monitoring and early warning using mobile devices (such as patrol vehicles, drones, etc.). Compared with traditional fixed monitoring systems, mobile monitoring and early warning systems have higher flexibility and coverage, and can respond quickly to various emergencies.

[0004] In the operational safety management of highways, the application of mobile monitoring and early warning methods can greatly improve the response speed and processing capabilities to various emergencies, especially in the blind spots of fixed monitoring equipment or in rapid response to sudden and local events. Through real-time monitoring and data analysis, potential safety risks can be discovered and warned in a timely manner, such as traffic congestion, accidents, severe weather conditions, etc., thereby effectively avoiding or reducing the impact of accidents and ensuring the safe and smooth operation of highways.

[0005] Traditional safety monitoring relies on manual observation and analysis, which is not only time-consuming but also inefficient. When discovering and responding to potential risks, the best time for intervention may be missed due to slow response. It is difficult for manual analysis to accurately identify all types of traffic conditions and abnormal events, especially in complex or ambiguous situations, which are prone to false alarms and missed alarms. In the absence of in-depth analysis of operational data, traffic management and resource allocation strategies may not be optimized, resulting in waste of resources or low efficiency. Previous safety risk assessment methods may not be able to accurately assess the severity and urgency of various risks, affecting the effectiveness of safety management.

[0006] Currently, no effective solution has been proposed for the problems in the related technologies. Summary of the invention

[0007] In order to overcome the above problems, the present invention aims to propose a mobile monitoring and early warning method and system based on highway operation safety, with the aim of solving the problem that in the absence of in-depth analysis of operation data, traffic management and resource allocation strategies may not be optimized, resulting in waste of resources or low efficiency, and previous safety risk assessment methods may not be able to accurately assess the severity and urgency of various risks, affecting the effectiveness of safety management.

[0008] To this end, the specific technical solution adopted by the present invention is as follows: According to one aspect of the present invention, a mobile monitoring and early warning method based on highway operation safety is provided, and the mobile monitoring and early warning method comprises the following steps: S1. Use pre-deployed mobile monitoring units to collect highway operation data in real time; S2. Analyze operational data using operational data analysis models; S3. Based on the analysis results of operational data, the random forest algorithm is used to evaluate safety risks; S4. Generate early warning information based on risk assessment results and initiate a pre-set emergency response mechanism to monitor and warn of highway operation safety.

[0009] Optionally, analyzing the operation data using the operation data analysis model includes the following steps: S21, acquiring and collecting operation data from a pre-deployed mobile monitoring unit, and pre-processing the operation data; S22, extracting feature data from the pre-processed operation data and integrating the operation data; S23. Construct the architecture of the operation data analysis model according to the characteristics of the operation data and the analysis objectives, and train the model using the extracted feature data; S24. Use the trained operational data analysis model to analyze the integrated operational data and identify security risks.

[0010] Optionally, constructing the architecture of the operation data analysis model according to the characteristics of the operation data and the analysis objectives, and training the model using the extracted feature data includes the following steps: S231. Evaluate and select a model structure that meets the characteristics of operational data and analysis objectives; S232, dividing the feature data into a training set, a validation set, and a test set; S233, using the training set to train the operation data analysis model; S234. Use the validation set to evaluate the performance of the operational data analysis model; S235. Use the test set to test the performance of the operational data analysis model.

[0011] Optionally, analyzing the integrated operational data using a trained operational data analysis model to identify security risks includes the following steps: S241. Obtain integrated operational data; S242. Use the trained model to analyze the integrated operational data to identify security risks and abnormal situations; S243. Use multi-criteria decision analysis to evaluate, classify and prioritize identified security risks and anomalies.

[0012] Optionally, evaluating, classifying, and prioritizing the identified security risks and anomalies using multi-criteria decision analysis includes the following steps: S2431. Evaluate each identified risk and anomaly and determine the criteria for evaluating risk; S2432, assigning a weight to each evaluation criterion; S2433. Score each identified risk according to the criteria after assigning weights; S2434. Use multi-criteria decision-making methods to comprehensively evaluate each risk and classify it; S2435. Prioritize risks according to their comprehensive evaluation values.

[0013] Optionally, a multi-criteria decision-making method is used to comprehensively evaluate each risk and classify it, including the following steps: S24341. Determine the objectives and criteria for risk assessment and construct the framework of the multi-criteria decision-making model; S24342. Construct an evaluation index system for risk dimensions; S24343. Calculate the weight of each evaluation criterion; S24344. For each evaluation criterion, score each risk data under each evaluation criterion; S24345. Input the risk data score and the weight of each evaluation criterion into the multi-criteria decision-making model to calculate the comprehensive score of each risk data; S24346. Based on the comprehensive score and the set classification threshold, the risk data is classified into corresponding categories.

[0014] Optionally, the comprehensive score formula for calculating each risk data is: ; In the formula, represents the weight of evaluation criterion j; represents the score of risk item i under evaluation criterion j; n represents the total number of evaluation criteria; Indicates the comprehensive score of each risk data.

[0015] Optionally, based on the analysis results of the operational data, the safety risk assessment using the random forest algorithm includes the following steps: S31. Obtain security risks and select characteristic data for evaluation in the security risks; S32, using the extracted feature data, dividing the operation data into a training set, a validation set, and a test set; S33, using the training set to train the random forest model, and optimizing the parameters of the random forest model; S34. Use the validation set to evaluate the optimized random forest model; S35. Use the test set to perform final performance evaluation on the optimized random forest model S36. Determine the type of risk based on the evaluation results of the operational data using the random forest model.

[0016] Optionally, according to the evaluation result of the random forest model on the operational data, determining the type of risk includes the following steps: S361. Use the trained random forest model to predict the operational data in the test set; S362. Analyze the risk prediction of each feature data in the category label according to the category label output by the model; S363, mapping the risk type output by the model to a specific risk name; S364. Determine the risk to which each feature data belongs according to the mapped risk type; S365. Summarize and count the risk types of all characteristic data to obtain the distribution of different risk types.

[0017] According to another aspect of the present invention, there is also provided a mobile monitoring and early warning system based on highway operation safety, the system comprising: a data acquisition module, a data analysis module, a risk assessment module and an early warning and response module; A data collection module for collecting highway operation data in real time using pre-deployed mobile monitoring units; A data analysis module, used to analyze operational data using an operational data analysis model; The risk assessment module is used to assess safety risks using the random forest algorithm based on the analysis results of operational data; The early warning and response module is used to generate early warning information based on risk assessment results and initiate pre-set emergency response mechanisms to achieve monitoring and early warning of highway operation safety.

[0018] Compared with the prior art, this application has the following beneficial effects: 1. The present invention can identify and evaluate potential safety risks in real time by automatically analyzing a large amount of operational data collected from mobile monitoring units, including videos, pictures, speeds and locations, greatly improving the efficiency of highway safety monitoring. Compared with traditional methods that rely on manual monitoring and analysis, problems can be discovered and measures can be taken more quickly; the deep convolutional neural network model has excellent performance in image recognition and processing tasks. The CNN model is used to analyze image or video data, accurately identify various traffic conditions and abnormal events, optimize traffic management strategies and resource allocation, and improve overall operational efficiency.

[0019] 2. The present invention can not only identify current safety risks, but also predict possible risk points in the future through historical data analysis, so as to prepare in advance and enhance the ability to respond to emergencies, which is crucial to improving the overall safety level of highways.

[0020] 3. The random forest of the present invention determines the final result by constructing multiple decision trees and taking the average or majority vote at the output. This integrated learning method greatly improves the accuracy of risk assessment. In operational data analysis, the data of security events are often unbalanced. Random forests naturally have the ability to handle such unbalanced data and can maintain a high overall prediction accuracy without sacrificing the ability to identify minority classes. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] The above characteristics, features and advantages of the present invention and their implementation methods and methods will become more clearly understood in conjunction with the following description of the embodiments, which are described in detail in conjunction with the accompanying drawings. Herein, a schematic diagram is shown: Figure 1 is a flow chart of a mobile monitoring and early warning method based on highway operation safety according to an embodiment of the present invention; Figure 2 The present invention is a block diagram of a mobile monitoring and early warning system based on highway operation safety according to an embodiment of the present invention.

[0022] In the figure: 1. Data collection module; 2. Data analysis module; 3. Risk assessment module; 4. Early warning and response module. DETAILED DESCRIPTION

[0023] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0024] According to an embodiment of the present invention, a mobile monitoring and early warning method and system based on highway operation safety are provided.

[0025] The present invention is further described with reference to the accompanying drawings and specific embodiments. Figure 1 As shown, according to one embodiment of the present invention, a mobile monitoring and early warning method based on highway operation safety is provided, and the mobile monitoring and early warning method comprises the following steps: S1. Use pre-deployed mobile monitoring units to collect highway operation data in real time.

[0026] It should be explained that the deployment of mobile monitoring units includes core steps and implementation methods. The core step is to pre-deploy mobile monitoring units on highways. Mobile monitoring units are vehicles equipped with cameras, radars, GPS and other sensors, or drones carrying corresponding sensor equipment.

[0027] This is achieved by selecting key deployment points based on the geographic characteristics of the highway, traffic volume, and accident frequency. For example, monitoring units can be deployed in areas where traffic accidents frequently occur, near large transportation hubs, or in curved areas with limited vision.

[0028] S2. Analyze operational data using operational data analysis models.

[0029] Preferably, analyzing the operation data using the operation data analysis model comprises the following steps: S21, acquiring and collecting operation data from a pre-deployed mobile monitoring unit, and pre-processing the operation data; S22, extracting feature data from the pre-processed operation data and integrating the operation data; S23. Construct the architecture of the operation data analysis model according to the characteristics of the operation data and the analysis objectives, and train the model using the extracted feature data; S24. Use the trained operational data analysis model to analyze the integrated operational data and identify security risks.

[0030] In addition, it should be explained that the data collected by the mobile monitoring unit mentioned in step S1 may include videos, pictures, speed, location, etc.

[0031] Preprocessing includes data cleaning (removing erroneous or incomplete records), standardization (ensuring that all data is in the same measure and format), denoising (reducing random variation in the data), and handling missing values.

[0032] According to the analysis objectives, relevant data attributes are selected or algorithms are used to extract information from the data, such as extracting traffic density and average speed from video data, and merging data from different sources into a unified data set for unified analysis. For example, GPS data can be combined with speed data to provide a complete operational situation at each time point.

[0033] The operational data analysis model is a deep convolutional neural network model (CNN). CNN is a deep learning model that is particularly suitable for image recognition and processing tasks. It automatically extracts important features from images through convolutional layers, avoiding complex feature engineering. When the operational data analysis model is based on a deep convolutional neural network, its powerful automatic feature extraction and learning capabilities are particularly suitable for processing image or video operational data to identify and assess potential security risks.

[0034] Preferably, constructing the architecture of the operation data analysis model according to the characteristics of the operation data and the analysis objectives, and training the model using the extracted feature data includes the following steps: S231. Evaluate and select a model structure that meets the characteristics of operational data and analysis objectives; S232, dividing the feature data into a training set, a validation set, and a test set; S233, using the training set to train the operation data analysis model; S234. Use the validation set to evaluate the performance of the operational data analysis model; S235. Use the test set to test the performance of the operational data analysis model.

[0035] Preferably, analyzing the integrated operational data using the trained operational data analysis model to identify security risks includes the following steps: S241. Obtain integrated operational data; S242. Use the trained model to analyze the integrated operational data to identify security risks and abnormal situations; S243. Use multi-criteria decision analysis to evaluate, classify and prioritize identified security risks and anomalies.

[0036] Preferably, evaluating, classifying and prioritizing the identified security risks and anomalies using multi-criteria decision analysis includes the following steps: S2431. Evaluate each identified risk and anomaly and determine the criteria for evaluating risk; S2432, assigning a weight to each evaluation criterion; S2433. Score each identified risk according to the criteria after assigning weights; S2434. Use multi-criteria decision-making methods to comprehensively evaluate each risk and classify it; S2435. Prioritize risks according to their comprehensive evaluation values.

[0037] Preferably, the multi-criteria decision-making method is used to comprehensively evaluate each risk and classify it, including the following steps: S24341. Determine the objectives and criteria for risk assessment and construct the framework of the multi-criteria decision-making model; S24342. Construct an evaluation index system for risk dimensions; S24343. Calculate the weight of each evaluation criterion; S24344. For each evaluation criterion, score each risk data under each evaluation criterion; S24345. Input the risk data score and the weight of each evaluation criterion into the multi-criteria decision-making model to calculate the comprehensive score of each risk data; S24346. Based on the comprehensive score and the set classification threshold, the risk data is classified into corresponding categories.

[0038] Preferably, the comprehensive scoring formula for calculating each risk data is: ; In the formula, represents the weight of evaluation criterion j; represents the score of risk item i under evaluation criterion j; n represents the total number of evaluation criteria; Indicates the comprehensive score of each risk data.

[0039] S3. Based on the analysis results of operational data, the random forest algorithm is used to evaluate safety risks.

[0040] Preferably, based on the analysis results of the operational data, the safety risk assessment using the random forest algorithm includes the following steps: S31. Obtain security risks and select characteristic data for evaluation in the security risks; S32, using the extracted feature data, dividing the operation data into a training set, a validation set, and a test set; S33, using the training set to train the random forest model, and optimizing the parameters of the random forest model; S34. Use the validation set to evaluate the optimized random forest model; S35. Use the test set to perform final performance evaluation on the optimized random forest model S36. Determine the type of risk based on the evaluation results of the operational data using the random forest model.

[0041] In addition, it should be explained that identifying data points related to safety risks from previously collected and pre-processed operational data involves analyzing past accident reports, fault records or traffic violations, and based on this information, selecting features that are highly correlated with safety risks, such as vehicle speed, traffic density, weather conditions, etc.

[0042] Common data partitioning methods, such as random allocation, are used to ensure the distribution consistency of the training set, validation set, and test set. Usually, the data set is divided into 70% training set, 15% validation set, and 15% test set. The training set data is used to train the random forest model by selecting appropriate parameters such as the number of trees, the depth of the tree, and the minimum number of samples required for node splitting. The parameters are optimized through methods such as cross-validation. The validation set data is input into the trained random forest model. The model's accuracy, recall rate, F1 score and other indicators are evaluated to determine the generalization ability of the model. The output of the random forest model is analyzed and the output results are mapped to specific risk types, such as speeding, traffic congestion, etc. This involves collaboration with industry experts to ensure the accuracy and practicality of risk classification. The random forest algorithm is an integrated learning method that improves the accuracy and stability of the model by building multiple decision trees and summarizing them at the output. It is robust to noise and outliers in the data set and is particularly suitable for handling complex classification tasks.

[0043] Preferably, according to the evaluation result of the random forest model on the operational data, determining the type of risk includes the following steps: S361. Use the trained random forest model to predict the operational data in the test set; S362. Analyze the risk prediction of each feature data in the category label according to the category label output by the model; S363, mapping the risk type output by the model to a specific risk name; S364. Determine the risk to which each feature data belongs according to the mapped risk type; S365. Summarize and count the risk types of all characteristic data to obtain the distribution of different risk types.

[0044] S4. Generate early warning information based on risk assessment results and initiate a pre-set emergency response mechanism to monitor and warn of highway operation safety.

[0045] According to another embodiment of the present invention, Figure 2As shown, a mobile monitoring and early warning system based on highway operation safety is also proposed, the system includes: a data acquisition module 1, a data analysis module 2, a risk assessment module 3 and an early warning and response module 4; The data collection module 1 is used to collect the operation data of the expressway in real time using the pre-deployed mobile monitoring unit; Data analysis module 2, used for analyzing operation data using an operation data analysis model; Risk assessment module 3, used to assess safety risks using the random forest algorithm based on the analysis results of operational data; The early warning and response module 4 is used to generate early warning information according to the risk assessment results and start the pre-set emergency response mechanism to achieve monitoring and early warning of highway operation safety.

[0046] In summary, with the help of the above-mentioned technical scheme of the present invention, the present invention can identify and evaluate potential safety risks in real time by automatically analyzing a large amount of operational data collected from mobile monitoring units, including videos, pictures, speeds and locations, etc., thereby greatly improving the efficiency of highway safety monitoring. Compared with the traditional method of relying on manual monitoring and analysis, problems can be discovered and measures can be taken more quickly; the deep convolutional neural network model has excellent performance in image recognition and processing tasks. The CNN model is used to analyze image or video data to accurately identify various traffic conditions and abnormal events, such as traffic congestion, accidents, etc., which helps to ensure the accuracy of safety risk assessment and reduce false positives and negative positives. By deeply analyzing the operational data, more insights and patterns can be mined to provide data-driven decision support for the operation and management of highways, optimize traffic management strategies and resource allocation, and improve overall operational efficiency; the present invention can not only identify current safety risks, but also predict possible risk points in the future through historical data analysis, so as to prepare in advance and enhance the ability to respond to emergencies, which is crucial to improving the overall safety level of highways.

[0047] Although the present invention has been disclosed as above with preferred embodiments, the embodiments are merely examples for the convenience of description and are not intended to limit the present invention. Those skilled in the art may make several changes and modifications without departing from the spirit and scope of the present invention. The scope of protection claimed by the present invention shall be based on the claims.

Claims

1. A mobile monitoring and early warning method based on highway operation safety, characterized in that: The mobile monitoring early warning method comprises the following steps: S1. Use pre-deployed mobile monitoring units to collect highway operation data in real time; S2. Analyze operational data using operational data analysis models; S3. Based on the analysis results of operational data, the random forest algorithm is used to evaluate safety risks; S4. Generate early warning information based on risk assessment results and initiate a pre-set emergency response mechanism to monitor and warn of highway operation safety.

2. A mobile monitoring and early warning method based on highway operation safety according to claim 1, characterized in that: Analyzing the operation data using the operation data analysis model includes the following steps: S21, acquiring and collecting operation data from a pre-deployed mobile monitoring unit, and pre-processing the operation data; S22, extracting feature data from the pre-processed operation data and integrating the operation data; S23. Construct the architecture of the operation data analysis model according to the characteristics of the operation data and the analysis objectives, and train the model using the extracted feature data; S24. Use the trained operational data analysis model to analyze the integrated operational data and identify security risks.

3. A mobile monitoring and early warning method based on highway operation safety according to claim 2, characterized in that: The step of constructing the architecture of the operation data analysis model according to the characteristics of the operation data and the analysis objectives, and training the model using the extracted feature data includes the following steps: S231. Evaluate and select a model structure that meets the characteristics of operational data and analysis objectives; S232, dividing the feature data into a training set, a validation set, and a test set; S233, using the training set to train the operation data analysis model; S234. Use the validation set to evaluate the performance of the operational data analysis model; S235. Use the test set to test the performance of the operational data analysis model.

4. The mobile monitoring and early warning method based on highway operation safety according to claim 3 is characterized in that: Analyzing the integrated operation data using the trained operation data analysis model to identify security risks includes the following steps: S241. Obtain integrated operational data; S242. Use the trained model to analyze the integrated operational data to identify security risks and abnormal situations; S243. Use multi-criteria decision analysis to evaluate, classify and prioritize identified security risks and anomalies.

5. The mobile monitoring and early warning method based on highway operation safety according to claim 4 is characterized in that: The use of multi-criteria decision analysis to evaluate, classify and prioritize identified security risks and abnormal situations includes the following steps: S2431. Evaluate each identified risk and anomaly and determine the criteria for evaluating risk; S2432, assigning a weight to each evaluation criterion; S2433. Score each identified risk according to the criteria after assigning weights; S2434. Use multi-criteria decision-making methods to comprehensively evaluate each risk and classify it; S2435. Prioritize risks according to their comprehensive evaluation values.

6. A mobile monitoring and early warning method based on highway operation safety according to claim 5, characterized in that: The use of the multi-criteria decision-making method to comprehensively evaluate each risk and classify it includes the following steps: S24341. Determine the objectives and criteria for risk assessment and construct the framework of the multi-criteria decision-making model; S24342. Construct an evaluation index system for risk dimensions; S24343. Calculate the weight of each evaluation criterion; S24344. For each evaluation criterion, score each risk data under each evaluation criterion; S24345. Input the risk data score and the weight of each evaluation criterion into the multi-criteria decision-making model to calculate the comprehensive score of each risk data; S24346. Based on the comprehensive score and the set classification threshold, the risk data is classified into corresponding categories.

7. A mobile monitoring and early warning method based on highway operation safety according to claim 6, characterized in that: The formula for calculating the comprehensive score of each risk data is: ； In the formula, represents the weight of evaluation criterion j; represents the score of risk item i under evaluation criterion j; n represents the total number of evaluation criteria; Indicates the comprehensive score of each risk data.

8. The mobile monitoring and early warning method based on highway operation safety according to claim 1 is characterized in that: The method of evaluating safety risks using the random forest algorithm based on the analysis results of the operational data includes the following steps: S31. Obtain security risks and select characteristic data for evaluation in the security risks; S32, using the extracted feature data, dividing the operation data into a training set, a validation set, and a test set; S33, using the training set to train the random forest model, and optimizing the parameters of the random forest model; S34. Use the validation set to evaluate the optimized random forest model; S35. Use the test set to perform final performance evaluation on the optimized random forest model S36. Determine the type of risk based on the evaluation results of the operational data using the random forest model.

9. A mobile monitoring and early warning method based on highway operation safety according to claim 8, characterized in that: Determining the type of risk based on the evaluation results of the operation data by the random forest model includes the following steps: S361. Use the trained random forest model to predict the operational data in the test set; S362. Analyze the risk prediction of each feature data in the category label according to the category label output by the model; S363, mapping the risk type output by the model to a specific risk name; S364. Determine the risk to which each feature data belongs according to the mapped risk type; S365. Summarize and count the risk types of all characteristic data to obtain the distribution of different risk types.

10. A mobile monitoring and early warning system based on highway operation safety, used to implement the mobile monitoring and early warning method based on highway operation safety according to any one of claims 1 to 9, characterized in that: The system includes: data collection module, data analysis module, risk assessment module and early warning and response module; The data collection module is used to collect the operation data of the expressway in real time using the pre-deployed mobile monitoring unit; The data analysis module is used to analyze the operation data using the operation data analysis model; The risk assessment module is used to assess the safety risk using a random forest algorithm based on the analysis results of the operation data; The early warning and response module is used to generate early warning information according to the risk assessment results, and start the pre-set emergency response mechanism to achieve monitoring and early warning of highway operation safety.

Images