Road traffic safety intelligent early warning system and method based on artificial intelligence

Abstract

The invention relates to the technical field of traffic safety, in particular to a highway traffic safety intelligent early warning system and method based on artificial intelligence. The system is composed of a data acquisition module, a data preprocessing module, an intelligent analysis module, an early warning decision module and an interactive early warning interface, and the data acquisition module collects multi-parameter data through three ways of a sensor, a monitoring system and a meteorological station; the data preprocessing module cleans, standardizes, normalizes and supplements missing values for the collected multi-parameter data, trains the extracted features through the intelligent analysis module by using a feedforward neural network FFNN + self-attention mechanism, constructs a multi-dimensional risk prediction model, automatically identifies the change of a traffic mode, predicts potential dangerous events, and improves the risk prediction efficiency. The interactive response interface displays the early warning information and the multi-parameter data collected in real time. According to the invention, road conditions and traffic risk conditions can be more comprehensively known, powerful data support is provided for decision making of an early warning system, and the early warning accuracy and intelligent level are significantly improved.

Description

Technical Field

[0001] The present invention relates to the field of traffic safety technology, and in particular to an artificial intelligence-based intelligent early warning system and method for highway traffic safety. Background Art

[0002] The traffic safety warning systems based on traditional algorithms currently available on the market mainly rely on vehicle driving data and road conditions to predict safety risks. These systems use simple threshold judgment methods, which can improve the safety of highway traffic to a certain extent, but have obvious shortcomings and are difficult to adapt to complex and changing traffic environments, especially when dealing with atypical or emergency situations. In addition, due to the lack of support for deep learning and big data analysis, the accuracy of warnings is limited, the false alarm and missed alarm rates are high, and it is difficult to accurately identify and analyze potential traffic risk patterns. In addition, these systems fail to fully consider the behavioral habits and risk preferences of different drivers, and the warning information lacks pertinence and practicality, making it difficult to meet personalized service needs. Therefore, the present invention provides an intelligent highway traffic safety warning system and method based on artificial intelligence to overcome the shortcomings of the existing technology and improve the safety of highway traffic. Summary of the Invention

[0003] The present invention provides an artificial intelligence-based highway traffic safety intelligent early warning system and method, which are used to solve the technical problems that existing traffic safety intelligent early warning systems are difficult to adapt to complex and changeable traffic environments and have low early warning accuracy.

[0004] In order to achieve the above-mentioned purpose, the technical solution adopted by the present invention is as follows: an artificial intelligence-based intelligent warning system for highway traffic safety, consisting of a data acquisition module, a data preprocessing module, an intelligent analysis module, a warning decision module and an interactive warning interface. The data acquisition module collects multi-parameter data through three channels: sensors, monitoring systems, and weather stations. The data preprocessing module cleans, standardizes, normalizes and supplements missing values ​​for the collected multi-parameter data. After feature extraction of the preprocessed multi-parameter data, the intelligent analysis module uses the feedforward neural network FFNN+self-attention mechanism to train the extracted features, construct a multi-dimensional risk prediction model, automatically identify changes in traffic patterns, predict potential dangerous events, and the interactive response interface displays warning information and real-time collected multi-parameter data.

[0005] Furthermore, the multi-parameter data includes historical accident records, real-time traffic flow, weather conditions, road conditions, driver behavior data, and random data.

[0006] Furthermore, the multi-parameter data cleaning uses a standard deviation method to identify and process outliers.

[0007] Furthermore, the multi-parameter data were normalized using improved Z-score normalization to enable comparison and analysis on the same scale.

[0008] Furthermore, the standardized multi-parameter data are converted into dimensionless values ​​between 0 and 1 using minimum-maximum normalization.

[0009] Furthermore, the intelligent analysis module also includes a self-attention mechanism layer to capture the correlation between different positions in multi-parameter data. By calculating the query, key and value vectors of each element in the sequence, and assigning weights to each element through similarity calculation, the value vectors are weighted summed according to the weights to obtain the contextual representation of each element. The contextual representation is input into the subsequent layers of the feed-forward neural network FFNN model to further enhance the model's early warning capabilities.

[0010] Furthermore, the intelligent analysis module constructs a driver profile based on the driver behavior data. The profile includes the driver's driving habits, reaction speed, and risk preference, and then sets personalized warning thresholds for each driver based on the driver profile.

[0011] Furthermore, the warning decision module issues warning information in a timely manner based on the prediction results of the model, including warning type, warning level and recommended measures, and issues warning information to drivers and traffic management departments through roadside display screens, vehicle-mounted terminals and mobile phone APPs.

[0012] A method for an intelligent early warning system for highway traffic safety based on artificial intelligence comprises the following steps: S01. Data Collection: Collect multi-parameter data through sensors, monitoring systems, and weather stations; S02. Data preprocessing: cleaning, standardization, normalization and missing value supplementation of multi-parameter data; S03. Intelligent Analysis: Use a feedforward neural network (FFNN) with a self-attention mechanism to train extracted features and construct a multi-dimensional risk prediction model to automatically identify changes in traffic patterns and predict potential dangerous events. S04. Early Warning Decision-Making: Based on the results of predictive analysis, early warning signals are automatically generated, and diagnostic reports and recommended measures are provided based on the warning level. S05. Interactive response: Display warning information and multi-parameter data collected in real time.

[0013] Compared with the prior art, the present invention has the following beneficial effects: (1) By integrating and analyzing multi-parameter data and utilizing the feedforward neural network (FFNN) + self-attention mechanism, the present invention can more comprehensively understand road conditions and traffic risks, providing strong data support for the decision-making of the early warning system, thereby achieving adaptive learning of complex traffic environments and significantly improving the accuracy and intelligence level of early warnings; (2) The present invention constructs an accurate driver profile by analyzing and mining a large amount of driver information, and customizes personalized warning thresholds and reminder methods for each driver based on the profile, thereby significantly improving the pertinence and effectiveness of warning information and reducing false alarm and missed alarm rates. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] Figure 1 This is a structural diagram of the artificial intelligence highway traffic safety intelligent early warning system of the present invention. DETAILED DESCRIPTION

[0015] The present invention will be described in detail below with reference to specific embodiments. The following examples will help those skilled in the art to further understand the present invention, but are not intended to limit the present invention in any form. It should be noted that, for those skilled in the art, several changes and improvements can be made without departing from the scope of the present invention. These all fall within the scope of protection of the present invention.

[0016] like Figure 1 As shown, an artificial intelligence-based intelligent early warning system for highway traffic safety consists of a data acquisition module, a data preprocessing module, an intelligent analysis module, an early warning decision module and an interactive early warning interface. The data acquisition module collects multi-parameter data through three channels: sensors, monitoring systems and weather stations. The data preprocessing module cleans, standardizes, normalizes and supplements missing values ​​for the collected multi-parameter data. After feature extraction from the preprocessed multi-parameter data, the intelligent analysis module uses a feedforward neural network FFNN+self-attention mechanism to train the extracted features, construct a multi-dimensional risk prediction model, automatically identify changes in traffic patterns, predict potential dangerous events, and display early warning information and real-time collected multi-parameter data on the interactive response interface.

[0017] Specifically, the data acquisition module collects massive traffic data including historical accident records, real-time traffic flow, and weather conditions. These multi-parameter data are obtained through various channels such as sensors, monitoring systems, and weather stations.

[0018] The main data includes historical accident records , real-time traffic flow , weather conditions , road conditions , driver behavior data , random data (holidays, special events, traffic policies and regulations) .

[0019] Specifically, the data preprocessing module performs preprocessing operations such as cleaning, missing value supplementation, normalization, and standardization on the collected data to improve the quality and usability of the data.

[0020] Data cleaning: Use the standard deviation method to identify and handle outliers. For each data point (Historical accident records , real-time traffic flow , weather conditions , road conditions , driver behavior data , random data (holidays, special events, traffic policies and regulations) , ),in is the normalized weight value. Calculate its average value The difference and with the standard deviation Compare. If the difference Exceeding the threshold (3 times the standard deviation), the data point is considered an outlier and is removed or replaced.

[0021] Data standardization: Standardize data from different sources and units so that they can be compared and analyzed on the same scale.

[0022] Improve Z-score normalization,

[0023] Where x is the multi-parameter data after data cleaning, μ is the mean of the data, and σ is the standard deviation of the data. After standardization, the mean of the data is 0 and the standard deviation is 1.

[0024] Data normalization: Convert data into dimensionless values ​​between 0 and 1 to facilitate subsequent algorithm processing and analysis.

[0025] Minimum-maximum normalization formula:

[0026] Among them, x is the multi-parameter data after data cleaning, x min and x max are the minimum and maximum values ​​in the data respectively. After normalization, the data value range is between 0 and 1.

[0027] Missing value filling: using linear interpolation, for missing values , the two non-missing values ​​before and after are and ,and ,but .

[0028] Features related to traffic safety are extracted from the preprocessed data, which will serve as input to the deep learning model.

[0029] Specifically, the intelligent analysis module uses a deep learning algorithm (feed-forward neural network (FFNN) combined with a self-attention mechanism) to train extracted features and construct a multi-dimensional risk prediction model. This model can automatically identify changes in traffic patterns and predict potential dangerous events, such as vehicle collisions and road congestion.

[0030] Set network input For M dimension: The hidden layer has a total of K nodes, and the output The dimension is L, the length of the input and output sample pairs is N, and the action function of the hidden layer node of the radial basis network is the Gaussian basis function:

[0031] The input data vector is mapped to the hidden layer, and the hidden layer nodes The output is:

[0032] Where: is the normalization constant of the hidden layer nodes, is the Gaussian function center vector of the hidden layer node, The hidden layer to output layer of the RBF network realizes a linear mapping of the conversion dimension, that is, the output of the output layer node k is:

[0033] Where: is the adjustment weight from the hidden layer to the output layer; is the bias of output layer node k. As a response to the corresponding input signal, it is output to the workspace as an important regulatory variable according to different backgrounds.

[0034] The feature data extracted from the preprocessed input x is output as potential dangerous state data. An attention mechanism module is added after the output feature data to capture the global dependencies between the input data.

[0035] Specifically, the attention mechanism module calculates the query, key, and value vectors of each element in the sequence, assigns a weight to each element through similarity calculation, and performs weighted summation on the value vectors according to the weight to obtain the contextual representation of each element. The contextual representation is input into the subsequent layers of the FFNN model to further enhance the model's early warning capability.

[0036] Specifically, by querying and key The attention weight , the weight is a scalar that is obtained by adding the attention score function Maps two vectors into a scalar , and then obtained through softmax operation: .

[0037] Additive Attention:

[0038] Scaled Dot Product Attention:

[0039] By introducing an attention mechanism, weights and biases are linearly transformed and nonlinearly activated. Each layer of neurons receives the outputs of neurons in the previous layer as input and calculates its own output values. These output values ​​are then passed to the next layer until they reach the output layer. The self-attention mechanism generates a context-sensitive representation for each input element based on the entire input sequence. This representation incorporates not only the element itself but also its relationships with other elements, thereby enhancing the model's representational capabilities and generalization performance. The model is then evaluated using metrics such as cross-validation, accuracy, and recall, and optimized based on the evaluation results to improve prediction accuracy.

[0040] The intelligent analysis module can also customize individual warning thresholds and reminder methods for each driver by analyzing their driving habits, reaction speed, historical violation records, and other information. The specific implementation process is as follows: (1) Driver information collection: collecting driver behavior data; (2) Driver profile construction: The profile includes the driver's driving habits, reaction speed, and risk preference; (3) Based on the driver profile, set a personalized warning threshold for each driver. For example, for drivers with more aggressive driving habits, set a lower warning threshold; for drivers with more conservative driving habits, set a higher warning threshold; (4) Select the appropriate reminder method based on the driver’s preference and actual situation. For example, for drivers who prefer visual reminders, the warning information can be displayed on the vehicle display screen.

[0041] By analyzing and mining a large amount of driver information, we build accurate driver profiles and customize warning thresholds and reminder methods for each driver based on their profiles. This personalized warning strategy can significantly improve the relevance and effectiveness of warning information and reduce false alarms and missed alarms.

[0042] The interactive warning interface is the user interface of the system of the present invention. It conveys warning information to the driver through various means such as voice prompts and visual warnings. Specifically, the interactive warning interface includes the following: (1) Warning information display: Warning information is displayed through various means such as visual warnings (such as red warning lights, flashing icons, etc.) and voice prompts (such as voice broadcast of warning information). The combination of visual warnings and voice prompts can convey warning information more intuitively and improve the driver's attention; (2) User interaction: Allows the driver to confirm, ignore, or take corresponding measures for the warning information. At the same time, a setting function is provided to allow the driver to adjust the reminder method and content of the warning information according to his or her preferences.

[0043] Through reasonable interface layout and diversified information display methods, the readability and comprehensibility of warning information can be significantly improved, reducing the cognitive burden on drivers.

[0044] A method for an intelligent early warning system for highway traffic safety based on artificial intelligence comprises the following steps: S01. Data Collection: Collect multi-parameter data through sensors, monitoring systems, and weather stations. Collect road traffic data, including key information such as vehicle type, speed, direction of travel, traffic flow, and weather conditions. S02. Data preprocessing: Clean, standardize, normalize, and fill in missing values ​​for multi-parameter data to ensure data quality and consistency; S03. Intelligent Analysis: Use a feedforward neural network (FFNN) and self-attention mechanism to train extracted features, build a multi-dimensional risk prediction model, automatically identify changes in traffic patterns, and predict potential dangerous events.

[0045] A feedforward neural network model was constructed to initially extract features from traffic data. An input layer, hidden layer, and output layer were configured. The input layer received preprocessed traffic data, and the output layer outputted warning results. The FFNN model was trained using a backpropagation algorithm to accurately identify potential risks in traffic data. A self-attention mechanism layer was introduced to the FFNN model to capture correlations between different locations in the traffic data.

[0046] S04. Warning Decision-Making: Based on the predictive analysis results, a warning signal is automatically generated, and a diagnostic report and recommended measures are provided based on the warning level. The trained model is deployed in the highway traffic safety warning system. Traffic data is collected in real time and input into the model for prediction. Based on the model's prediction results, warning information is promptly issued, including the warning type, warning level, and recommended measures. Warning information is disseminated to drivers and traffic management authorities through various channels, including roadside displays, on-board terminals, and mobile apps, ensuring the timeliness and effectiveness of the information.

[0047] S05. Interactive response: Display warning information and multi-parameter data collected in real time.

[0048] The above describes specific embodiments of the present invention. It should be understood that the present invention is not limited to the specific embodiments described above, and those skilled in the art may make various changes or modifications within the scope of the claims, which do not affect the essence of the present invention. The embodiments of this application and the features in the embodiments may be combined with each other in any manner unless there is a conflict.

Claims

1. An intelligent early warning system for highway traffic safety based on artificial intelligence, characterized in that: It consists of a data acquisition module, a data preprocessing module, an intelligent analysis module, an early warning decision module and an interactive early warning interface. The data acquisition module collects multi-parameter data through three channels: sensors, monitoring systems and weather stations. The data preprocessing module cleans, standardizes, normalizes and supplements missing values ​​for the collected multi-parameter data. After feature extraction from the preprocessed multi-parameter data, the intelligent analysis module uses the feedforward neural network FFNN+ self-attention mechanism to train the extracted features, build a multi-dimensional risk prediction model, automatically identify changes in traffic patterns, predict potential dangerous events, and use an interactive response interface to display early warning information and real-time collected multi-parameter data.

2. According to claim 1, an artificial intelligence-based intelligent early warning system for highway traffic safety is characterized in that: The multi-parameter data includes historical accident records, real-time traffic flow, weather conditions, road conditions, driver behavior data, and random data.

3. The highway traffic safety intelligent early warning system based on artificial intelligence according to claim 1 is characterized in that: The multi-parameter data cleaning adopts the standard deviation method to identify and process outliers.

4. The intelligent early warning management method for a data center computer room according to claim 1 is characterized in that: The multi-parameter data were normalized using improved Z-score normalization to enable comparison and analysis on the same scale.

5. The highway traffic safety intelligent early warning system based on artificial intelligence according to claim 1 is characterized in that: The standardized multi-parameter data were converted into dimensionless values ​​between 0 and 1 using minimum-maximum normalization.

6. The highway traffic safety intelligent early warning system based on artificial intelligence according to claim 1 is characterized in that: The intelligent analysis module also includes a self-attention mechanism layer to capture the correlation between different positions in multi-parameter data. It calculates the query, key and value vectors of each element in the sequence, assigns weights to each element through similarity calculation, and performs weighted summation on the value vectors according to the weights to obtain the context representation of each element. The context representation is input into the subsequent layers of the feedforward neural network FFNN model to further enhance the model's early warning capability.

7. The intelligent early warning management method for a data center computer room according to claim 1 is characterized in that: The intelligent analysis module builds a driver profile based on driver behavior data, which includes the driver's driving habits, reaction speed, and risk preference, and then sets personalized warning thresholds for each driver based on the driver profile.

8. The intelligent early warning management method for a data center computer room according to claim 1 is characterized in that: The warning decision module releases warning information in a timely manner according to the prediction results of the model, including warning type, warning level and recommended measures, and releases warning information to drivers and traffic management departments through roadside display screens, vehicle-mounted terminals and mobile phone APPs.

9. A method for a highway traffic safety intelligent early warning system based on artificial intelligence, the method is implemented based on the system as claimed in claim 1, comprising the following steps: S01. Data collection: Collect multi-parameter data through sensors, monitoring systems, and weather stations; S02. Data preprocessing: cleaning, standardization, normalization and missing value supplement of multi-parameter data; S03. Intelligent analysis: Use the feedforward neural network FFNN + self-attention mechanism to train the extracted features, build a multi-dimensional risk prediction model, automatically identify changes in traffic patterns, and predict potential dangerous events; S04. Early warning decision: Based on the prediction and analysis results, early warning signals are automatically generated, and diagnostic reports and recommended measures are provided according to the warning level; S05. Interactive response: Display warning information and multi-parameter data collected in real time.

Images