A statistical analysis method for a comprehensive traffic index system based on mobile terminals

Abstract

The present invention relates to the technical field of comprehensive traffic index analysis, and discloses a statistical analysis method for a comprehensive traffic index system based on a mobile terminal, comprising the following steps: Step 1: Data collection, using the GPS and acceleration sensors built into a smart phone to collect vehicle position, speed, and acceleration data in real time; Step 2: Data preprocessing, cleaning the collected raw data to remove outliers and duplicate data; Step 3: Feature extraction, using data mining technology to extract key features in traffic data, such as traffic flow, speed distribution, and congestion periods. The present invention proposes a statistical analysis method for a comprehensive traffic index system based on a mobile terminal, which solves the problem that traditional methods rely heavily on fixed monitoring equipment, such as cameras and sensors, and are difficult to achieve comprehensive coverage and real-time collection of traffic data.

Description

Technical Field

[0001] The present invention relates to the technical field of comprehensive traffic index analysis, and in particular to a statistical analysis method of a comprehensive traffic index system based on a mobile terminal. Background Art

[0002] Transportation, as the lifeblood of modern social and economic activities, bears the heavy responsibility of the flow of people and materials. It covers multiple modes of transportation, including roads, railways, aviation, and waterways. Each mode has its unique advantages and applicable scenarios. With the acceleration of urbanization and the development of intelligent transportation systems, traffic management is becoming increasingly complex, and the dependence on data and real-time requirements are becoming increasingly high. The comprehensive transportation indicator system, as an important tool for evaluating traffic conditions and guiding traffic planning and management, covers multiple dimensions such as traffic flow, speed, congestion, safety, and public transportation service quality. The statistical analysis method of the comprehensive transportation indicator system based on the mobile terminal mainly uses the mobile devices of smartphones as the medium for data collection and transmission to achieve real-time, comprehensive, and accurate collection of traffic data, and through data analysis technology, dig out the deep-seated laws behind the traffic conditions to provide a scientific basis for traffic management. However, there are still some problems in the application of existing technologies in this field: 1. Traditional methods mostly rely on fixed monitoring equipment, such as cameras and sensors, which makes it difficult to achieve comprehensive coverage and real-time collection of traffic data; 2. Traffic data is massive, multi-dimensional and dynamic, and traditional data processing methods are difficult to accurately mine valuable information; 3. The data sharing mechanism between departments is not sound, resulting in serious data silos, which affects the overall efficiency of traffic management.

[0003] In order to solve the above problems, this application proposes a statistical analysis method of a comprehensive traffic indicator system based on a mobile terminal. Summary of the invention

[0004] Based on the technical problems existing in the background technology, the present invention proposes a statistical analysis method of a comprehensive traffic indicator system based on a mobile terminal.

[0005] The present invention proposes a statistical analysis method for a comprehensive traffic indicator system based on a mobile terminal, comprising the following steps: Step 1: Data collection, using the GPS and acceleration sensors built into the smartphone to collect vehicle location, speed, and acceleration data in real time; Step 2: Data preprocessing: cleaning the collected raw data to remove outliers and duplicate data; Step 3: Feature extraction, using data mining technology to extract key features from traffic data, such as traffic flow, speed distribution, and congestion periods; Step 4: Traffic index calculation: Based on the extracted features, the comprehensive traffic indexes of traffic congestion index TCI and traffic smoothness index TSI are calculated; Step 5: Spatiotemporal analysis: Use geographic information system (GIS) technology to conduct spatiotemporal analysis of traffic data to reveal the changing patterns of traffic conditions over time and space. Step 6: Prediction and warning: Use machine learning algorithms to predict traffic data and detect potential traffic congestion risks in advance; Step 7: Information integration and release, establish a traffic information sharing platform, and realize data sharing and exchange among various departments; Step 8: Feedback and optimization, collect user feedback on the use of the traffic information service platform, and continuously optimize platform functions and user experience.

[0006] Preferably, the data collection comprises the following steps: Step 1: GPS data collection: S1. Start the GPS function of the smartphone and set the sampling frequency; S2. Real-time recording of vehicle longitude, latitude, and altitude location information; S3, calculating the vehicle speed and acceleration according to the position change; Step 2: Sensor data collection: S1. Use the built-in acceleration sensor of the smartphone to collect the acceleration data of the vehicle in real time; S2. Collecting other possible sensor data, such as direction sensor data, to assist in analyzing the vehicle's driving status; Step 3: User Questionnaire Design: S1. Design a questionnaire containing subjective evaluation questions on traffic congestion level, safety, and driving comfort; S2. Determine the channels and frequency of questionnaire release, such as push notifications through APP and social media; S3. Collect user feedback and organize it into structured data.

[0007] Preferably, the data preprocessing comprises the following steps: Step 1: Data cleaning: S1. Identify and delete missing values, duplicate values, or data records that are obviously abnormal; S2, smoothing or interpolating outliers to reduce data errors; Step 2: Data standardization: S1. Unify the formats of data from different sources and in different formats, such as converting time data into a unified time format; S2. Normalize the data so that data of different dimensions can be compared and analyzed.

[0008] Preferably, the feature extraction comprises the following steps: Step 1: Traffic flow extraction: S1. Count the number of vehicles passing a certain road section within a specific time period based on vehicle location data; S2. Calculate average traffic flow and peak traffic flow indicators; Step 2: Extract velocity distribution: S1. Statistically analyze vehicle speed data and calculate average speed and speed standard deviation indicators; S2. Draw the speed distribution curve and analyze the law of speed change; Step 3: Extraction of congestion period: S1. Identify traffic congestion periods based on vehicle travel time and speed data; S2. Count the average waiting time and driving speed of vehicles during congestion periods; Step 4: Application of clustering algorithm: S1. Select the appropriate clustering algorithm K-means and set the number of clusters K; S2. Perform cluster analysis on traffic data to identify different traffic conditions, such as smooth traffic, slight congestion, and severe congestion.

[0009] Preferably, the traffic index calculation comprises the following steps: Step 1: Calculation of Traffic Congestion Index (TCI): S1. Calculate the congestion index of each road section according to the congested road section length and congestion time data; S2. Traffic congestion index calculation formula: TCI = Σ (congested road section length × congestion time) / total road section length, to obtain the traffic congestion index of the entire area; Step 2: Calculation of Traffic Fluency Index (TSI): S1. Collect the total distance and total time data of vehicle travel; S2. Calculate the traffic flow index using the formula TSI = total driving distance / total driving time.

[0010] Preferably, the spatiotemporal analysis comprises the following steps: Step 1: GIS technology application: S1. Import traffic data into the GIS system for visualization; S2. Use the spatial analysis function of GIS to analyze the spatial distribution of traffic conditions; Step 2: Application of spatiotemporal clustering algorithm: S1. Select a suitable spatiotemporal clustering algorithm, such as ST-DBSCAN, and set the algorithm parameters; S2. Perform spatiotemporal clustering analysis on traffic data to identify traffic hotspots and congested periods.

[0011] Preferably, the prediction and early warning comprises the following steps: Step 1: Machine Learning Algorithm Selection: S1. Select appropriate machine learning algorithms, such as support vector machines (SVM) and neural networks (NN), based on data characteristics and prediction requirements. S2. Optimize algorithm parameters to improve prediction accuracy; Step 2: Data preprocessing and feature engineering: S1. Preprocess historical traffic data to extract features related to prediction; S2, construct feature engineering to convert raw data into feature vectors that can be used for prediction; Step 3: Model training and verification: S1. Train the model using the training data set; S2. Use the validation data set to validate the model and evaluate the prediction accuracy. Step 4: Early warning system design: S1. Set the warning threshold according to the prediction results; S2. When the risk of traffic congestion is predicted, the early warning mechanism is triggered and early warning information is issued in a timely manner.

[0012] Preferably, the information integration and publishing includes the following steps: Step 1: Construction of traffic information sharing platform: S1. Design and develop a traffic information sharing platform to achieve data sharing and exchange among various departments; S2. Develop data sharing standards and protocols to ensure data security and consistency; Step 2: Design of traffic information service platform: S1. Design a user-friendly traffic information service platform interface; S2. Integrate traffic conditions and warning information data resources to realize real-time publishing and query functions.

[0013] Preferably, the feedback and optimization comprises the following steps: Step 1: Collect user feedback: S1. Collect user feedback on the traffic information service platform through user surveys and feedback; S2. Organize and analyze feedback to identify problems and areas for improvement; Step 2: Platform function optimization: S1. Optimize platform functions and user experience based on user feedback and analysis results; S2. Regularly update and maintain the platform to ensure the accuracy and timeliness of data; Step 3: Traffic management measures adjustment: S1. Adjust traffic management measures based on analysis results and feedback; S2. Optimize traffic signal control and road planning schemes to improve the traffic environment.

[0014] The above technical solution of the present invention has the following beneficial technical effects: 1. Improve the efficiency and accuracy of traffic data collection and provide more reliable data support for traffic management; 2. Through data mining and machine learning technology, valuable information in traffic data is deeply excavated, providing a scientific basis for traffic planning and management; 3. A traffic information sharing platform has been established to break the information island phenomenon and improve the overall efficiency of traffic management; 4. Real-time prediction and early warning of traffic conditions are realized, providing more timely and accurate traffic information for traffic managers and the public. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 This is a flow chart of a statistical analysis method for a comprehensive traffic indicator system based on a mobile terminal proposed by the present invention. DETAILED DESCRIPTION

[0016] In order to make the purpose, technical scheme and advantages of the present invention clearer, the present invention is further described in detail below in conjunction with specific embodiments and with reference to the accompanying drawings. It should be understood that these descriptions are only exemplary and are not intended to limit the scope of the present invention. In addition, in the following description, the description of well-known structures and technologies is omitted to avoid unnecessary confusion of the concept of the present invention.

[0017] like Figure 1 As shown, the present invention proposes a statistical analysis method of a comprehensive traffic indicator system based on a mobile terminal, comprising the following steps: Step 1: Data collection, using the GPS and acceleration sensors built into the smartphone to collect vehicle location, speed, and acceleration data in real time; Step 2: Data preprocessing: cleaning the collected raw data to remove outliers and duplicate data; Step 3: Feature extraction, using data mining technology to extract key features from traffic data, such as traffic flow, speed distribution, and congestion periods; Step 4: Traffic index calculation: Based on the extracted features, the comprehensive traffic indexes of traffic congestion index TCI and traffic smoothness index TSI are calculated; Step 5: Spatiotemporal analysis: Use geographic information system (GIS) technology to conduct spatiotemporal analysis of traffic data to reveal the changing patterns of traffic conditions over time and space. Step 6: Prediction and warning: Use machine learning algorithms to predict traffic data and detect potential traffic congestion risks in advance; Step 7: Information integration and release, establish a traffic information sharing platform, and realize data sharing and exchange among various departments; Step 8: Feedback and optimization, collect user feedback on the use of the traffic information service platform, and continuously optimize platform functions and user experience.

[0018] In a specific embodiment, data collection includes the following steps: Step 1: GPS data collection: S1. Start the GPS function of the smartphone and set the sampling frequency; S2. Real-time recording of vehicle longitude, latitude, and altitude location information; S3, calculating the vehicle speed and acceleration according to the position change; Step 2: Sensor data collection: S1. Use the built-in acceleration sensor of the smartphone to collect the acceleration data of the vehicle in real time; S2. Collecting other possible sensor data, such as direction sensor data, to assist in analyzing the vehicle's driving status; Step 3: User Questionnaire Design: S1. Design a questionnaire containing subjective evaluation questions on traffic congestion level, safety, and driving comfort; S2. Determine the channels and frequency of questionnaire release, such as push notifications through APP and social media; S3. Collect user feedback and organize it into structured data.

[0019] It should be noted that a user questionnaire was designed to collect users' subjective evaluation of traffic conditions, such as congestion level and safety.

[0020] In a specific embodiment, data preprocessing includes the following steps: Step 1: Data cleaning: S1. Identify and delete missing values, duplicate values, or data records that are obviously abnormal; S2, smoothing or interpolating outliers to reduce data errors; Step 2: Data standardization: S1. Unify the formats of data from different sources and in different formats, such as converting time data into a unified time format; S2. Normalize the data so that data of different dimensions can be compared and analyzed.

[0021] It should be noted that data should be standardized to ensure that data from different sources and in different formats can be analyzed and compared in a unified manner.

[0022] In a specific embodiment, feature extraction includes the following steps: Step 1: Traffic flow extraction: S1. Count the number of vehicles passing a certain road section within a specific time period based on vehicle location data; S2. Calculate average traffic flow and peak traffic flow indicators; Step 2: Extract velocity distribution: S1. Statistically analyze vehicle speed data and calculate average speed and speed standard deviation indicators; S2. Draw the speed distribution curve and analyze the law of speed change; Step 3: Extraction of congestion period: S1. Identify traffic congestion periods based on vehicle travel time and speed data; S2. Count the average waiting time and driving speed of vehicles during congestion periods; Step 4: Application of clustering algorithm: S1. Select the appropriate clustering algorithm K-means and set the number of clusters K; S2. Perform cluster analysis on traffic data to identify different traffic conditions, such as smooth traffic, slight congestion, and severe congestion.

[0023] It should be noted that: clustering algorithms, such as K-means, are used to classify traffic data and identify different traffic states; K-means clustering algorithm: used to divide traffic data into K clusters, each cluster represents a traffic state.

[0024] In a specific embodiment, the traffic index calculation includes the following steps: Step 1: Calculation of Traffic Congestion Index (TCI): S1. Calculate the congestion index of each road section according to the congested road section length and congestion time data; S2. Traffic congestion index calculation formula: TCI = Σ (congested road section length × congestion time) / total road section length, to obtain the traffic congestion index of the entire area; Step 2: Calculation of Traffic Fluency Index (TSI): S1. Collect the total distance and total time data of vehicle travel; S2. Calculate the traffic flow index using the formula TSI = total driving distance / total driving time.

[0025] In a specific embodiment, the spatiotemporal analysis includes the following steps: Step 1: GIS technology application: S1. Import traffic data into the GIS system for visualization; S2. Use the spatial analysis function of GIS to analyze the spatial distribution of traffic conditions; Step 2: Application of spatiotemporal clustering algorithm: S1. Select a suitable spatiotemporal clustering algorithm, such as ST-DBSCAN, and set the algorithm parameters; S2. Perform spatiotemporal clustering analysis on traffic data to identify traffic hotspots and congested periods.

[0026] It should be noted that the ST-DBSCAN spatiotemporal clustering algorithm is used to identify traffic hotspots and congested periods, where DBSCAN is a density clustering algorithm and ST represents the spatiotemporal dimension.

[0027] In a specific embodiment, prediction and early warning include the following steps: Step 1: Machine Learning Algorithm Selection: S1. Select appropriate machine learning algorithms, such as support vector machines (SVM) and neural networks (NN), based on data characteristics and prediction requirements. S2. Optimize algorithm parameters to improve prediction accuracy; Step 2: Data preprocessing and feature engineering: S1. Preprocess historical traffic data to extract features related to prediction; S2, construct feature engineering to convert raw data into feature vectors that can be used for prediction; Step 3: Model training and verification: S1. Train the model using the training data set; S2. Use the validation data set to validate the model and evaluate the prediction accuracy. Step 4: Early warning system design: S1. Set the warning threshold according to the prediction results; S2. When the risk of traffic congestion is predicted, the early warning mechanism is triggered and early warning information is issued in a timely manner.

[0028] It should be noted that: the early warning system is designed to issue early warning information in a timely manner when the risk of traffic congestion is predicted; Support vector machine (SVM): used for traffic data prediction, which divides the data into two categories, such as congestion and non-congestion, by finding the optimal hyperplane; Neural network NN: used for more complex traffic data prediction, simulating the nonlinear relationship between data through a multi-layer neural network.

[0029] In a specific embodiment, information integration and publishing includes the following steps: Step 1: Construction of traffic information sharing platform: S1. Design and develop a traffic information sharing platform to achieve data sharing and exchange among various departments; S2. Develop data sharing standards and protocols to ensure data security and consistency; Step 2: Design of traffic information service platform: S1. Design a user-friendly traffic information service platform interface; S2. Integrate traffic conditions and warning information data resources to realize real-time publishing and query functions.

[0030] In a specific embodiment, feedback and optimization include the following steps: Step 1: Collect user feedback: S1. Collect user feedback on the traffic information service platform through user surveys and feedback; S2. Organize and analyze feedback to identify problems and areas for improvement; Step 2: Platform function optimization: S1. Optimize platform functions and user experience based on user feedback and analysis results; S2. Regularly update and maintain the platform to ensure the accuracy and timeliness of data; Step 3: Traffic management measures adjustment: S1. Adjust traffic management measures based on analysis results and feedback; S2. Optimize traffic signal control and road planning schemes to improve the traffic environment.

[0031] It should be understood that the above specific embodiments of the present invention are only used to illustrate or explain the principles of the present invention, and do not constitute a limitation of the present invention. Therefore, any modifications, equivalent substitutions, improvements, etc. made without departing from the spirit and scope of the present invention should be included in the protection scope of the present invention. In addition, the appended claims of the present invention are intended to cover all changes and modifications that fall within the scope and boundaries of the appended claims, or the equivalent forms of such scope and boundaries.

Claims

1. A statistical analysis method for a comprehensive traffic index system based on a mobile terminal, characterized in that: The following steps are involved: Step 1: Data collection, using the GPS and acceleration sensors built into the smartphone to collect vehicle location, speed, and acceleration data in real time; Step 2: Data preprocessing: cleaning the collected raw data to remove outliers and duplicate data; Step 3: Feature extraction, using data mining technology to extract key features from traffic data, such as traffic flow, speed distribution, and congestion periods; Step 4: Traffic index calculation: Based on the extracted features, the comprehensive traffic indexes of traffic congestion index TCI and traffic smoothness index TSI are calculated; Step 5: Spatiotemporal analysis: Use geographic information system (GIS) technology to conduct spatiotemporal analysis of traffic data to reveal the changing patterns of traffic conditions over time and space. Step 6: Prediction and warning: Use machine learning algorithms to predict traffic data and detect potential traffic congestion risks in advance; Step 7: Information integration and release, establish a traffic information sharing platform, and realize data sharing and exchange among various departments; Step 8: Feedback and optimization, collect user feedback on the use of the traffic information service platform, and continuously optimize platform functions and user experience.

2. According to claim 1, a statistical analysis method of a comprehensive traffic index system based on a mobile terminal is characterized in that: The data collection comprises the following steps: Step 1: GPS data collection: S1. Start the GPS function of the smartphone and set the sampling frequency; S2. Real-time recording of vehicle longitude, latitude, and altitude location information; S3, calculating the vehicle speed and acceleration according to the position change; Step 2: Sensor data collection: S1. Use the built-in acceleration sensor of the smartphone to collect the acceleration data of the vehicle in real time; S2. Collecting other possible sensor data, such as direction sensor data, to assist in analyzing the vehicle's driving status; Step 3: User Questionnaire Design: S1. Design a questionnaire containing subjective evaluation questions on traffic congestion level, safety, and driving comfort; S2. Determine the channels and frequency of questionnaire release, such as push notifications through APP and social media; S3. Collect user feedback and organize it into structured data.

3. The statistical analysis method of the comprehensive traffic index system based on the mobile terminal according to claim 2 is characterized in that: The data preprocessing comprises the following steps: Step 1: Data cleaning: S1. Identify and delete missing values, duplicate values, or data records that are obviously abnormal; S2, smoothing or interpolating outliers to reduce data errors; Step 2: Data standardization: S1. Unify the formats of data from different sources and in different formats, such as converting time data into a unified time format; S2. Normalize the data so that data of different dimensions can be compared and analyzed.

4. The statistical analysis method of the comprehensive traffic index system based on the mobile terminal according to claim 3 is characterized in that: The feature extraction comprises the following steps: Step 1: Traffic flow extraction: S1. Count the number of vehicles passing a certain road section within a specific time period based on vehicle location data; S2. Calculate average traffic flow and peak traffic flow indicators; Step 2: Extract velocity distribution: S1. Statistically analyze vehicle speed data and calculate average speed and speed standard deviation indicators; S2. Draw the speed distribution curve and analyze the law of speed change; Step 3: Extraction of congestion period: S1. Identify traffic congestion periods based on vehicle travel time and speed data; S2. Count the average waiting time and driving speed of vehicles during congestion periods; Step 4: Application of clustering algorithm: S1. Select the appropriate clustering algorithm K-means and set the number of clusters K; S2. Perform cluster analysis on traffic data to identify different traffic conditions, such as smooth traffic, slight congestion, and severe congestion.

5. The statistical analysis method of the comprehensive traffic index system based on the mobile terminal according to claim 4 is characterized in that: The traffic index calculation includes the following steps: Step 1: Calculation of Traffic Congestion Index (TCI): S1. Calculate the congestion index of each road section according to the congested road section length and congestion time data; S2. Traffic congestion index calculation formula: TCI = Σ (congested road section length × congestion time) / total road section length, to obtain the traffic congestion index of the entire area; Step 2: Calculation of Traffic Fluency Index (TSI): S1. Collect the total distance and total time data of vehicle travel; S2. Calculate the traffic flow index using the formula TSI = total driving distance / total driving time.

6. The statistical analysis method of the comprehensive traffic index system based on the mobile terminal according to claim 5 is characterized in that: The spatiotemporal analysis comprises the following steps: Step 1: GIS technology application: S1. Import traffic data into the GIS system for visualization; S2. Use the spatial analysis function of GIS to analyze the spatial distribution of traffic conditions; Step 2: Application of spatiotemporal clustering algorithm: S1. Select a suitable spatiotemporal clustering algorithm, such as ST-DBSCAN, and set the algorithm parameters; S2. Perform spatiotemporal clustering analysis on traffic data to identify traffic hotspots and congested periods.

7. The statistical analysis method of the comprehensive traffic index system based on the mobile terminal according to claim 6 is characterized in that: The prediction and early warning comprises the following steps: Step 1: Machine Learning Algorithm Selection: S1. Select appropriate machine learning algorithms, such as support vector machines (SVM) and neural networks (NN), based on data characteristics and prediction requirements. S2. Optimize algorithm parameters to improve prediction accuracy; Step 2: Data preprocessing and feature engineering: S1. Preprocess historical traffic data to extract features related to prediction; S2, construct feature engineering to convert raw data into feature vectors that can be used for prediction; Step 3: Model training and verification: S1. Train the model using the training data set; S2. Use the validation data set to validate the model and evaluate the prediction accuracy. Step 4: Early warning system design: S1. Set the warning threshold according to the prediction results; S2. When the risk of traffic congestion is predicted, the early warning mechanism is triggered and early warning information is issued in a timely manner.

8. The statistical analysis method of the comprehensive traffic index system based on the mobile terminal according to claim 7 is characterized in that: The information integration and release includes the following steps: Step 1: Construction of traffic information sharing platform: S1. Design and develop a traffic information sharing platform to achieve data sharing and exchange among various departments; S2. Develop data sharing standards and protocols to ensure data security and consistency; Step 2: Design of traffic information service platform: S1. Design a user-friendly traffic information service platform interface; S2. Integrate traffic conditions and warning information data resources to realize real-time publishing and query functions.

9. The statistical analysis method of the comprehensive traffic index system based on the mobile terminal according to claim 8 is characterized in that: The feedback and optimization include the following steps: Step 1: Collect user feedback: S1. Collect user feedback on the traffic information service platform through user surveys and feedback; S2. Organize and analyze feedback to identify problems and areas for improvement; Step 2: Platform function optimization: S1. Optimize platform functions and user experience based on user feedback and analysis results; S2. Regularly update and maintain the platform to ensure the accuracy and timeliness of data; Step 3: Traffic management measures adjustment: S1. Adjust traffic management measures based on analysis results and feedback; S2. Optimize traffic signal control and road planning schemes to improve the traffic environment.

Images