TW201719541A - Method and system of analyzing and predicting high-risk road section by means of driving behavior utilizing an on-board unit to collect a driver's driving trajectory for analyzing bad driving behaviors and therefore learn a high-risk road section - Google Patents

Abstract

The present invention discloses a method and a system of analyzing and predicting a high-risk road section by means of driving behaviors. The present invention utilizes an on-board unit to collect a driver's driving trajectory so as to analyze bad driving behaviors such as speeding, emergency brake, and sharp turn according to the driving trajectory, and to correspond occurrence frequencies of the bad driving behaviors to a road network to learn a potential high-risk road section that would easily cause the driver to conduct a dangerous driving behavior. An on-board warning device can immediately remind the driver to drive carefully while approaches the high-risk road section, thereby preventing accidents from happening.

Description

Method and system for estimating high-risk road sections by using driving behavior analysis

The present invention relates to a method and system for estimating a high-risk road section by using driving behavior analysis, and in particular to a method and system for collecting a traveling trajectory of a passerby using a vehicle device.

Due to poor design of road junctions, lack of warning signs, poor driving planning and other factors, many road sections are prone to bad driving behavior and increase the risk of accidents.

In view of the shortcomings derived from the above-mentioned conventional methods, the inventor of the present invention has improved and innovated, and after years of painstaking research, he finally succeeded in researching and developing the method and system for estimating high-risk sections using driving behavior analysis.

It is an object of the present invention to provide a method for estimating a high risk road section using driving behavior analysis. Through the collection and analysis, the driver often has dangerous driving behaviors on the road sections, including rapid acceleration, sharp turns, speeding, etc., and with the information of the accident sections disclosed by the public department, to calculate the high risk of potentially driving the driver to dangerous driving behavior. Road section. The driver can receive an early warning notice when approaching the risk section through the car device, so that the driver can be careful Drive to avoid dangerous driving behavior and reduce the risk of accidents.

A system for estimating a high-risk road section by using driving behavior analysis, which mainly comprises: a positioning information receiving module, which is capable of simultaneously receiving positioning information of a plurality of front-end vehicle equipment devices, and storing the original positioning information in a background system. The GPS filtering processing module removes the original GPS point data through the GPS two-point spacing judgment and removes the GPS point that has drifted too far, and corrects the offset GPS point to the road segment with the road network data to increase The correctness of the subsequent analysis, and the processed GPS point data is stored in the driving track database, wherein the driving behavior analysis module uses the processed GPS point data to calculate the driver's rush in the driving section and time. The dangerous driving behavior of braking, sharp turning and overspeed, and the driving behavior analysis module calculates the intensity and frequency of driving behavior; the latitude and longitude transit section information module is a module that converts the processed GPS point data into a road network segment. The road section risk calculation module is the intensity and frequency of dangerous driving behavior caused by sudden braking, sharp turns and overspeed on the road section. Standard arithmetic unit section of the strength of the risk, this degree of risk of an accident on a road quantitative indicators to assess, according to the degree of risk and the risk related information stored in the database section.

The road section risk calculation module is composed of sudden braking intensity and frequency, sharp turning intensity and frequency, overspeed intensity and frequency, and public sector dangerous road section information. The risk index calculation unit is composed of frequency and risk correlation analysis and driving behavior. Correlation analysis with risk, its driving behavior and risk correlation analysis, different driving behavior indicators are given different weights through the training algorithm, wherein the training algorithm refers to different risk levels of the road segments according to the risk value R. , θ _M is the moderate risk threshold, and θ _L is the high risk threshold. If R < θ _M, it is classified as a low-risk road. If θ _M < R < θ _L, it is classified as a moderate risk section. If R > θ _L, it is classified as a high-risk section.

A method for estimating a high-risk road section by using driving behavior analysis, the flow is as follows: transmitting GPS position information; road section comparison; judging the risk of approaching a high road section; if not, there is no early warning event; if so, the vehicle device actively driving Human warning.

The invention provides a method and a system for estimating a high-risk road section by using driving behavior analysis, and has the following advantages when compared with other conventional technologies:

1. The platform of the present invention proposes a positioning information collecting module to receive the GPS driving track of the vehicle device, and the data is processed by the GPS filtering processing module, and then sent to the driving behavior analysis module for processing by the analyzed driving track. .

2. The platform of the invention proposes a driving behavior analysis module to analyze whether there is dangerous driving behavior in each driving track, and combines the latitude and longitude transit segment information module to calculate the intensity and frequency of dangerous driving behaviors of each road segment.

3. The platform of the present invention proposes a road segment risk calculation module, which is the frequency of dangerous driving behaviors such as sudden braking, sharp turn, and overspeed that occur in a single road segment, and different risk weights are given according to different risk behaviors, and the road segment is calculated. The level of danger.

4. The mobile device of the present invention proposes a high-risk road section early warning device, obtains risk road section information according to the road section risk level database, compares the distance between the driver's travel section and the risk section, and issues an early warning to remind the driving when the driving route approaches the risk section. People pay attention to the road segment The degree of risk informs the possible risks of the roads in front of the passers-by, allowing the driver to be alert and reduce the chance of an accident.

111‧‧‧ Front-end car machine

112‧‧‧Mobile communication network

120‧‧‧Backstage system

121‧‧‧Location Information Receiver Module

122‧‧‧GPS Filter Processing Module

123‧‧‧ Driving track database

124‧‧‧ Driving Behavior Analysis Module

125‧‧‧Longitude and latitude transit section information module

126‧‧‧ Public Sector Dangerous Roads Database

127‧‧‧ Road Section Risk Calculation Module

128‧‧‧Road risk level database

130‧‧‧In-vehicle devices

131‧‧‧ display

132‧‧‧Speakers

210‧‧‧ Road section risk calculation module

211‧‧‧Emergency vehicle strength and frequency

212‧‧‧ sharp turn intensity and frequency

213‧‧‧Overspeed intensity and frequency

214‧‧‧ Public Sector Dangerous Road Information

220‧‧‧ risk indicator arithmetic unit

221‧‧‧Affinity and risk correlation analysis

222‧‧‧Analysis of the relationship between driving behavior and risk

230‧‧‧ training algorithm

231‧‧‧Low risk section R <

232‧‧‧Moderate risk section < R <

233‧‧‧High risk section R >

The detailed description of the present invention and its accompanying drawings will be further understood, and the technical contents of the present invention and the functions thereof can be further understood. The related drawings are: FIG. 1 is a method and system for estimating a high-risk road section by using driving behavior analysis. System architecture diagram; FIG. 2 is a flowchart of operation of a road section risk calculation module for a method and system for estimating a high-risk road section by using driving behavior analysis; FIG. 3 is a method for estimating a high-risk road section by using driving behavior analysis according to the present invention; System car engine early warning device flow chart.

The present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It is understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.

The following is a further description of the present invention with reference to the accompanying drawings: Referring to FIG. 1 , a system architecture diagram of a method and system for estimating a high-risk road section using driving behavior analysis according to the present invention, including a positioning information receiving module 121, can simultaneously Receiving the positioning information returned by the plurality of front-end vehicle equipment 111 devices, the receiving manner is received by the mobile communication network 112 as a medium, and the original positioning information is stored in the background system 120; the GPS filtering processing module 122 is original The GPS point data is used to remove the GPS points that have drifted too far through the GPS two-point spacing judgment, and the GPS data points are corrected to the road segments with the road network data to increase the correctness of the subsequent analysis, and will be The GPS location data is stored in the driving track database 123. The driving behavior analysis module 124 uses the processed GPS point data to calculate the risk of the driver braking, sharp turning, and overspeed in the driving section and time. Driving behavior, and the driving behavior analysis module 124 calculates the intensity and frequency of the driving behavior; the latitude and longitude transit segment information module 125 is a module for converting the processed GPS point data into a road network segment; the road segment risk calculation module 127, including the intensity and frequency of sudden braking, sharp turn strength and frequency, overspeed strength and frequency, information on dangerous sections of the public sector, the intensity and frequency of dangerous driving behavior caused by sudden braking, sharp turns and overspeed on the road section. The index computing unit generates the risk intensity of the road segment, and the quantified index evaluates the risk level of the accident on the road segment, and stores the relevant information according to the degree of danger in the road segment risk database 128.

The risk index calculation unit is an analysis of the correlation between frequency and risk, and the correlation analysis between driving behavior and risk. The driving behavior and risk correlation analysis is to give different driving behavior indicators different weights through training algorithms, among which training The algorithm means that different risk levels can be given to the road segment according to the risk value R , θ _M is the moderate risk threshold value, and θ _L is the high risk threshold value. If R < θ _M, it is classified as a low-risk road. If θ _M < R < θ _L, it is classified as a moderate risk section. If R > θ _L, it is classified as a high-risk section.

In summary, it can be divided into two parts: the front end vehicle device 111 and the background system 120. The front-end vehicle device 111 is a device having position information for receiving a global satellite positioning system or a wireless communication base station for recording position information of the driver's travel, and the front-end vehicle device 111 periodically transmits the vehicle travel position via the mobile communication network 112. Return to the background system 120. The background system receives the location information returned by the front-end vehicle device 111 by the positioning information receiving module 121, and uses the GPS filtering processing module 122 to remove the noise and make up for the shortage. The missing coordinate point, the processed coordinate track will be stored in the travel track database 123. The driving behavior analysis module 124 obtains the filtered driving position information from the driving trajectory database, and calculates the intensity and frequency of the dangerous driving behavior such as sudden braking, sharp turning, and overspeed of the driver in each section by using the latitude and longitude traverse section information module 125. . The road section risk calculation module 127 calculates the risk level of each road section by the dangerous driving behavior intensity and frequency of each road section, and matches the public department dangerous road section database 126 collected by the public department announcement information, and stores the operation result to the road section. Risk Level Database 128. The instant alarm device mounted on the vehicle-mounted device 130 can read the risk road segment data from the road segment risk level database 128, and display the dangerous road segment information on the display 131 of the vehicle device immediately when the driver approaches the high-risk road segment, and broadcast it by the speaker 132. The alarm content reminds the driver.

Please refer to FIG. 2, which is a flowchart of operation of a road section risk calculation module for a method and system for estimating a high-risk road section by using driving behavior analysis. The road section risk calculation module 210 calculates each section of the driving behavior analysis module. Driving behavior statistics include sudden braking intensity and frequency 211, sharp turn intensity and frequency 212, overspeed strength and frequency 213, and public sector dangerous road information 214. The operation module uses the operation algorithm of the risk index operation unit 220 to calculate the risk value, and the frequency and risk correlation analysis 221 processes the frequency of the driving behavior for the risk intensity image, and the driving behavior and risk correlation analysis 222 will drive different driving behaviors. The indicator gives different weights through the training algorithm 230 and calculates a risk value R. According to the risk value R , different risk levels can be given to the road segment, θ _M is the moderate risk threshold value, and θ _L is the high risk threshold value. If R <θ _M is classified as low risk link 231, if θ _M <R <θ _L is classified as intermediate risk sections 232, if R> θ _L 233 is classified as highly Risk section.

Please refer to FIG. 3, which is a flow chart of a method and system for estimating a high-risk road section using a driving behavior analysis according to the present invention. The flow is as follows: S310 transmits GPS position information; S320 road section comparison; determines S330 is high Road section risk; if not, then S331 has no warning event; if so, S340 is actively alerted to the driver by the vehicle equipment.

It can be known from the above process that the vehicle equipment continuously transmits GPS position information during the vehicle traveling process, and the background system compares with the road section risk database to determine whether the current road section is close to the high risk section, and if not, does not issue If the warning event is close to the high-risk road section, the vehicle equipment will take the initiative to warn the driver.

The instant alarm function of the front-end vehicle equipment, such as the vehicle equipment device, is informed by the road section risk level database that the front road section is a high-risk road section, and the vehicle immediately displays <the front intersection is a high-risk road section, please drive carefully> information. A warning tone is issued to remind the driver to take special precautions against the road ahead.

The detailed description of the present invention is intended to be illustrative of a preferred embodiment of the invention, and is not intended to limit the scope of the invention. The patent scope of this case.

To sum up, this case is not only innovative in terms of technical thinking, but also has many of the above-mentioned functions that are not in the traditional methods of the past. It has fully complied with the statutory invention patent requirements of novelty and progressiveness, and applied for it according to law. Approved this invention patent application, in order to invent invention, to the sense of virtue.

111‧‧‧ Front-end car machine

112‧‧‧Mobile communication network

120‧‧‧Backstage system

121‧‧‧Location Information Receiver Module

122‧‧‧GPS Filter Processing Module

123‧‧‧ Driving track database

124‧‧‧ Driving Behavior Analysis Module

125‧‧‧Longitude and latitude transit section information module

126‧‧‧ Public Sector Dangerous Roads Database

127‧‧‧ Road Section Risk Calculation Module

128‧‧‧Road risk level database

130‧‧‧In-vehicle devices

131‧‧‧ display

132‧‧‧Speakers

Claims (6)

A system for estimating a high-risk road section by using driving behavior analysis, which mainly comprises: a positioning information receiving module, which is capable of simultaneously receiving positioning information of a plurality of front-end vehicle equipment devices, and storing the original positioning information in the background. In the system; the GPS filtering processing module removes the GPS points that have drifted too far through the GPS two-point spacing judgment, and corrects the offset GPS points to the road segments with the road network data. The correctness of the subsequent analysis is increased, and the processed GPS point data is stored in the driving track database; the driving behavior analysis module uses the processed GPS point data to calculate the driver's rush in the driving section and time. Braking, sharp turn, overspeed dangerous driving behavior, and the driving behavior analysis module calculates the intensity and frequency of driving behavior; the latitude and longitude transit segment information module converts the processed GPS point data into a network segment Module; section risk calculation module, which is the intensity and frequency of dangerous driving behavior caused by sudden braking, sharp turns and overspeed on the road section. Strength index calculation means the risk of road, this a quantitative indicators to assess the degree of risk of accidents on the road, and in accordance with the degree of risk of the relevant information stored in the database section risk. For example, the system for estimating high-risk road sections by using driving behavior analysis as described in claim 1 of the patent application scope, wherein the road section risk calculation module includes sudden braking strength and frequency, sharp turning strength and frequency, overspeed strength and frequency, and Departmental dangerous section information. The system for estimating a high-risk road section using driving behavior analysis as described in claim 1 of the patent application scope, wherein the risk index computing unit includes frequency and risk correlation analysis, and driving behavior and risk correlation analysis. For example, the system for estimating high-risk road sections using driving behavior analysis as described in claim 3 of the patent application, wherein the driving behavior and risk correlation analysis, different driving behavior indicators are given different weights through the training algorithm. A system for estimating a high-risk road section using driving behavior analysis as described in claim 4 of the patent application scope, wherein the training algorithm refers to a different risk level according to the risk value R , and θ _M is a medium risk Threshold value, θ _L is the high risk threshold. If R < θ _M, it is classified as a low-risk road. If θ _M < R < θ _L, it is classified as a moderate risk section. If R > θ _L, it is classified as a high-risk section. A method for estimating a high-risk road section by using driving behavior analysis, the flow is as follows: transmitting GPS position information; road section comparison; judging the risk of approaching a high road section; if not, there is no early warning event; if so, the vehicle device actively driving Human warning.