CN115871682A - Method and system for monitoring, evaluating and early warning safe driving behavior of driver - Google Patents
Method and system for monitoring, evaluating and early warning safe driving behavior of driver Download PDFInfo
- Publication number
- CN115871682A CN115871682A CN202310019360.5A CN202310019360A CN115871682A CN 115871682 A CN115871682 A CN 115871682A CN 202310019360 A CN202310019360 A CN 202310019360A CN 115871682 A CN115871682 A CN 115871682A
- Authority
- CN
- China
- Prior art keywords
- driving
- driver
- hundred
- driving behavior
- data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/80—Technologies aiming to reduce greenhouse gasses emissions common to all road transportation technologies
- Y02T10/84—Data processing systems or methods, management, administration
Landscapes
- Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)
Abstract
The invention provides a method and a system for monitoring, evaluating and early warning safe driving behaviors of a driver, which relate to the technical field of network appointment and comprise the following steps: step S1: collecting driving data and processing the driving data; step S2: establishing a model, wherein the model comprises driving behavior grading and driving result grading, and the comprehensive driving grading of a driver is obtained after the driving behavior grading and the driving result grading are combined; and step S3: and according to the comprehensive driving rating of the driver, different safety assistance and prompt are adopted for the driver. The invention can effectively identify the personnel with potential driving risks and implement targeted safety prompt and education, thereby reducing the occurrence of traffic accidents.
Description
Technical Field
The invention relates to the technical field of network appointment vehicles, in particular to a method for monitoring, evaluating and early warning safe driving behaviors of a driver based on the network appointment vehicle, and particularly relates to a method and a system for monitoring, evaluating and early warning the safe driving behaviors of the driver.
Background
The network taxi booking, namely the short name of the network taxi booking operation service, refers to the operation activities of booking taxi service for non-tour by establishing a service platform based on the internet technology, accessing vehicles and drivers meeting the conditions and integrating supply and demand information.
The invention patent with publication number CN113395394A discloses an early warning method for detecting safety of a network taxi appointment journey, which comprises the steps of (1) calculating a linear distance between a place for finishing an order and a place for reserving a taxi-off, and judging whether the linear distance is greater than a first threshold value; (2) returning the travel record; (3) Inquiring whether a safety problem is generated, if normal operation is selected to be finished, if abnormal order is selected, skipping to an online customer service dialogue page, if abnormal operation is selected to be finished, alarming 110, entering the step (4), and if abnormal operation is selected to be finished, informing an emergency contact person to enter the step (5); (4) Inquiring whether to dial 110, if not, returning the order to a normal state and ending the operation; if the order enters the alarm interface, returning the order to a normal state after the alarm is finished and finishing the operation; (5) Judging whether the passenger sets an emergency contact person or not, if not, enabling the user to input a mobile phone number of the emergency contact person, and sending an abnormal information short message to the mobile phone number; otherwise, entering a dialing interface to enable the passenger to communicate with the emergency contact.
The core of the patent is to judge the safety of a single journey through the behavior of the taxi booking user and the order per se. However, the above patent only uses a single trip to make safety precaution, and cannot judge the driving behavior and safety consciousness of the net appointment driver in a time period, so that the accuracy and continuity of evaluation are limited, and the evaluation effect is further influenced.
Disclosure of Invention
Aiming at the defects in the prior art, the invention provides a method and a system for monitoring, evaluating and early warning the safe driving behavior of a driver.
According to the monitoring, evaluating and early warning method and system for the safe driving behavior of the driver, the scheme is as follows:
in a first aspect, a method for monitoring, evaluating and warning safe driving behavior of a driver is provided, the method comprising:
step S1: collecting driving data and processing the driving data;
step S2: establishing a model, wherein the model comprises driving behavior scoring and driving result scoring, and the driving behavior scoring and the driving result scoring are combined to obtain a comprehensive driving rating of a driver;
and step S3: and according to the comprehensive driving rating of the driver, different safety assistance and prompt are adopted for the driver.
Preferably, the driving data includes: real-time vehicle data in the driving process comprises basic information of an OBD high-frequency dotting position and alarm information; the driving result data includes violation conditions and insurance claim data during the observation period.
Preferably, the processing the driving data includes: and carrying out edge calculation on the driving condition of the driver every second by the OBD equipment, and transmitting the processed alarm result back to the cloud.
Preferably, the driving behavior score comprises: and performing linear regression training on a large amount of network contracted vehicle travel data acquired by OBD by using a supervised learning algorithm, constructing a model for accident overview of each 10 kilometers of a single vehicle by combining travel key characteristics, and depicting the driving behavior and trip risk probability of each driver.
Preferably, the driving result scoring comprises: the final judgment is carried out by hundred-kilometer quick acceleration, hundred-kilometer quick deceleration, hundred-kilometer quick turning, hundred-kilometer overspeed, fatigue driving time ratio and daily average driving mileage, and the formula is as follows:
R＝a*p
p＝s1 x1 *2 x2 *3 x3 *4 x4 *5 x5 * 6 logx6
wherein, R represents the driving behavior score of a certain trolley; p represents the probability of a possible accident every 10 kilometres; a represents a coefficient based on the probability mapping score of the accident; for the probabilities p, s1, s2, s3, s4, s5, s6, coefficients based on historical vehicle operation and risk occurrence fit are represented; x1 represents the number of hundred kilometers speeding; x2 represents the number of rapid acceleration times of hundred kilometers; x3 represents the number of rapid decelerations in hundred kilometers; x4 represents the number of sharp turns of one hundred kilometers; x5 represents a fatigue driving time period ratio; x6 represents the daily average mileage.
Preferably, the statistical period of the comprehensive driving rating of the driver is a time period required by evaluation, and by combining with the driving insurance and violation condition marking of the network car booking driver, the driving behavior of the driver is classified by the Bayesian network through semi-supervised learning, so that high-risk, medium-risk, low-risk and normal vehicles are obtained.
In a second aspect, there is provided a system for monitoring, evaluating and warning of safe driving behavior of a driver, the system comprising:
a module M1: collecting driving data and processing the driving data;
a module M2: establishing a model, wherein the model comprises driving behavior grading and driving result grading, and the comprehensive driving grading of a driver is obtained after the driving behavior grading and the driving result grading are combined;
a module M3: and according to the comprehensive driving rating of the driver, different safety assistance and prompt are adopted for the driver.
Preferably, the driving data includes: real-time vehicle data in the driving process comprises basic information of an OBD high-frequency dotting position and alarm information; the driving result data includes violation conditions and insurance claim data during the observation period.
Preferably, the processing the driving data includes: and carrying out edge calculation on the driving condition of the driver every second by the OBD equipment, and transmitting the processed alarm result back to the cloud.
Preferably, the driving behavior score comprises: carrying out linear regression training on a large amount of network contracted vehicle travel data acquired by OBD (on-board diagnostics), constructing a model for accident overview of each 10 kilometers of a single vehicle by combining travel key characteristics, and depicting the driving behavior and trip risk probability of each driver;
the driving result scoring comprises: the final judgment is carried out by hundred-kilometer quick acceleration, hundred-kilometer quick deceleration, hundred-kilometer quick turning, hundred-kilometer overspeed, fatigue driving time ratio and daily average driving mileage, and the formula is as follows:
R＝a*p
p＝s1 x1 *2 x2 *3 x3 *4 x4 *5 x5 * 6 logx6
wherein, R represents the driving behavior score of a certain trolley; p represents the probability of a possible accident every 10 kilometres; a represents a coefficient based on the probability mapping score of the accident; for the probabilities p, s1, s2, s3, s4, s5, s6, coefficients based on historical vehicle operation and risk occurrence fit are represented; x1 represents the number of hundred kilometers speeding; x2 represents the number of rapid acceleration times of hundred kilometers; x3 represents the number of rapid decelerations in hundred kilometers; x4 represents the number of sharp turns of one hundred kilometers; x5 represents a fatigue driving time period ratio; x6 represents the average daily mileage.
The statistical cycle of the comprehensive driving rating of the driver is a time period required by evaluation, the driving insurance and violation condition marking of the network car booking driver are combined, and Bayesian network classification is carried out on the driving behavior of the driver through semi-supervised learning, so that high-risk, medium-risk, low-risk and normal vehicles are obtained.
Compared with the prior art, the invention has the following beneficial effects:
the invention analyzes and evaluates the safe driving level of various drivers based on the user data acquisition, effectively identifies the personnel with potential driving risk, and implements targeted safety prompt and education, thereby reducing the occurrence of traffic accidents.
Other advantages of the present invention will be described in the detailed description, which is provided by the technical features and technical solutions.
Drawings
Other features, objects and advantages of the invention will become more apparent upon reading of the detailed description of non-limiting embodiments with reference to the following drawings:
FIG. 1 is a flow chart of the present invention.
Detailed Description
The present invention will be described in detail with reference to specific examples. The following examples will assist those skilled in the art in further understanding the invention, but are not intended to limit the invention in any way. It should be noted that it would be obvious to those skilled in the art that various changes and modifications can be made without departing from the spirit of the invention. All falling within the scope of the present invention.
The embodiment of the invention provides a method for monitoring, evaluating and early warning safe driving behaviors of a driver, which is shown in figure 1 and specifically comprises the following steps:
step S1: and collecting driving data and processing the driving data.
Data range:
1) Real-time vehicle data in the driving process mainly comprises basic information of an OBD high-frequency dotting position and alarm information. OBD refers to on-vehicle self-diagnosis system in this embodiment for car networking driving behavior data acquisition.
2) The driving result data consists of violation conditions in the observation period and insurance claim settlement data.
The collection mode is as follows:
1) Dotting position basic information: the device number, longitude and latitude, device reporting time, analysis time, processing time, GPS speed (km/h), satellite number, signal strength, altitude (m), direction (0-359, north is 0, clockwise), total mileage (km), power-on flag bit and whether to supplement transmission.
2) Alarm information: alarm zone bits (including equipment power-down alarm, collision alarm, overspeed alarm, low-voltage alarm, flameout alarm, ignition alarm, insertion alarm, pull-out alarm, rapid acceleration alarm, rapid deceleration alarm and rapid turning alarm).
3) Violation condition: violation time, violation type, violation content, violation location, violation amount, score value and annual inspection time.
4) Insurance claim data: insurance policy number, dangerous type, accident number, case time, case type, case state, case channel, loss amount, vehicle price, vehicle type, responsibility type, whether injury occurs, danger place and accident passing.
Data processing: and carrying out edge calculation on the driving condition of the driver every second by the OBD equipment, wherein the result of the edge calculation is the vehicle driving behavior alarming result, transmitting the result and other equipment data to the database, and jointly predicting and evaluating the driving behavior by combining the existing vehicle, the emergence data and the violation data in the database.
Step S2: establishing a model:
the model is divided into two parts, wherein the first part is used for scoring the driving behavior process, the second part is used for scoring the driving result, and finally the comprehensive driving rating of the driver is obtained after the first part and the second part are combined.
(1) And (3) scoring the driving behavior:
the partial grading utilizes a supervised learning algorithm to perform linear regression training on a large amount of label-free desensitized existing ten-thousand-network contracted vehicle travel data acquired by OBD equipment, and combines travel key characteristics of hundred-kilometer quick acceleration, hundred-kilometer quick deceleration, hundred-kilometer quick braking, hundred-kilometer quick turning, hundred-kilometer overspeed, fatigue driving, daily average driving duration and daily average driving mileage to construct a model for accident overview of each 10 ten thousand kilometers of a single vehicle, and accurately depict driving behaviors and trip risk probability of each driver.
(2) And (3) scoring a driving result:
the part of scores are finally judged by hundred-kilometer quick acceleration, hundred-kilometer quick deceleration, hundred-kilometer quick turning, hundred-kilometer overspeed, fatigue driving time ratio and daily average driving mileage, and the formula is as follows:
R＝a*p
p＝s1 x1 *2 x2 *3 x3 *4 x4 *5 x5 * 6 logx6
wherein, R represents the driving behavior score of a certain trolley; p represents the probability of a possible accident every 10 kilometres; a represents a score coefficient mapped based on the probability of occurrence of the accident. For the probabilities p, s1, s2, s3, s4, s5, s6, coefficients based on historical vehicle operation and risk occurrence fit are represented; x1 represents the number of overspeed times of hundred kilometers (total number of overspeed alarms/total mileage); x2 represents the number of times of emergency acceleration (total number of times of emergency acceleration alarm/total mileage); x3 represents the number of times of sudden deceleration (total number of times of sudden deceleration alarm/total mileage); x4 represents the number of sharp turns (total number of sharp turn alarms/total mileage); x5 represents a fatigue driving time period ratio (total fatigue driving time period/total driving time period); x6 represents the daily average mileage.
(3) And (3) comprehensive rating of the driver:
the statistical cycle of the partial evaluation is a time period (generally one year) required by evaluation, the driving danger occurrence and violation condition marking of the network car booking driver are combined, a prior probability matrix is calculated according to the historical dangerous driver behaviors, a Bayesian network DAG (DAG, directed acyclic graph) is constructed according to the matrix, the weight of each variable x is calculated until convergence to obtain the probabilities of high risk (easy danger/violation) of each car, medium risk (easy danger), low risk (easy violation) and normal cars. Wherein the highest probability value is output as the classification rating.
And step S3: according to the comprehensive driving rating of the driver, different safety assistance and prompt are adopted for the driver, and the following table specifically shows that:
grading effect:
the model adopts a quantification means to comprehensively evaluate the driving behavior of the network car booking driver, combines the management difficulty of fatigue driving and the management appeal of daily mileage in the actual operation process of the network car booking, and can objectively show the driving risk of the driver. The motorcade manager has the functions of regular education, in-vehicle safety electronic sound prompt, prompt sound when the vehicle speed is higher than 80km/h, remote power failure and the like, and plays a role in prompting, supervising, educating and forcing safe driving protection in one body, so that the accident probability is reduced.
The invention also provides a system for monitoring, evaluating and early warning the safe driving behavior of the driver, which can be realized by executing the flow steps of the method for monitoring, evaluating and early warning the safe driving behavior of the driver, namely, the method for monitoring, evaluating and early warning the safe driving behavior of the driver can be understood as the preferred implementation mode of the system for monitoring, evaluating and early warning the safe driving behavior of the driver by technicians in the field. The system specifically comprises the following contents:
a module M1: and collecting driving data and processing the driving data.
Data range:
1) Real-time vehicle data in the driving process mainly comprises basic information of OBD high-frequency dotting positions and alarm information.
2) The driving result data consists of violation conditions in the observation period and insurance claim settlement data.
The collection mode is as follows:
1) Dotting position basic information: the method comprises the steps of equipment number, longitude and latitude, equipment reporting time, analysis time, processing time, GPS speed (km/h), satellite number, signal strength, altitude (m), direction (0-359, north and north is 0, clockwise), total mileage (km), power-on flag bit and whether to supplement transmission.
2) Alarm information: alarm zone bits (including equipment power-down alarm, collision alarm, overspeed alarm, low-voltage alarm, flameout alarm, ignition alarm, insertion alarm, pull-out alarm, rapid acceleration alarm, rapid deceleration alarm and rapid turning alarm).
3) Violation condition: violation time, violation type, violation content, violation location, violation amount, score value and annual inspection time.
4) Insurance claim data: insurance policy number, dangerous type, accident number, case time, case type, case state, case channel, loss amount, vehicle price, vehicle type, responsibility type, whether injury occurs, danger place and accident passing.
Data processing: and carrying out edge calculation on the driving condition of the driver every second by the OBD equipment, and transmitting the processed alarm result back to the cloud.
A module M2: establishing a model:
the model is divided into two parts, wherein the first part is used for scoring the driving behavior process, the second part is used for scoring the driving result, and finally the comprehensive driving rating of the driver is obtained after the first part and the second part are combined.
(1) And (3) scoring the driving behavior:
the partial grading utilizes a supervised learning algorithm to perform linear regression training on a large amount of label-free desensitized existing ten thousand network contracted vehicle travel data acquired by OBD, and combines travel key characteristics of hundred kilometers of rapid acceleration, hundred kilometers of rapid deceleration, hundred kilometers of rapid braking, hundred kilometers of rapid turning, hundred kilometers of over-speed, fatigue driving, daily average driving duration and daily average driving mileage to construct a model for accident overview of each 10 ten thousand kilometers of a single vehicle, and accurately depict driving behaviors and trip risk probability of each driver.
(2) And (3) scoring a driving result:
the part of scores are finally judged by hundred-kilometer quick acceleration, hundred-kilometer quick deceleration, hundred-kilometer quick turning, hundred-kilometer overspeed, fatigue driving time ratio and daily average driving mileage, and the formula is as follows:
R＝a*p
p＝s1 x1 *2 x2 *3 x3 *4 x4 *5 x5 * 6 logx6
wherein, R represents the driving behavior score of a certain trolley; p represents the probability of a possible accident every 10 kilometres; a represents a score coefficient mapped based on the probability of occurrence of the accident. For the probabilities p, s1, s2, s3, s4, s5, s6, coefficients based on historical vehicle operation and the fitting of the out-of-danger situation are represented; x1 represents the number of hundreds of kilometers speeding (total speeding alarm number/total mileage); x2 represents the number of times of emergency acceleration (total number of times of emergency acceleration alarm/total mileage); x3 represents the number of times of sudden deceleration (total number of times of sudden deceleration alarm/total mileage); x4 represents the number of sharp turns (total number of sharp turn alarms/total mileage); x5 represents a fatigue driving time period ratio (total fatigue driving time period/total driving time period); x6 represents the daily average mileage.
(3) And (3) comprehensive rating of the driver:
the statistical cycle of the partial evaluation is a time period (generally one year) required by evaluation, and by combining with the marking of the driving insurance and the violation condition of the network car booking driver, the Bayesian network classification is carried out on the driving behavior of the driver through semi-supervised learning, so that high-risk (easy insurance/violation), medium-risk (easy insurance), low-risk (easy violation) and normal vehicles are obtained.
A module M3: according to the comprehensive driving rating of the driver, different safety assistance and prompt are adopted for the driver, and the following table specifically shows that:
the embodiment of the invention provides a method and a system for monitoring, evaluating and early warning safe driving behaviors of drivers, wherein the types of car renters in a moving trip are complicated, and specific differences are reflected in the aspects of driving level, character characteristics, physiological characteristics and the like, so that the driving behaviors are finally acted. The invention analyzes and evaluates the safe driving level of various drivers based on the user data acquisition, effectively identifies the personnel with potential driving risk, and implements targeted safety prompt and education, thereby reducing the occurrence of traffic accidents.
According to the online car appointment driving behavior evaluation method, online car appointment driving behavior data obtained through high-frequency acquisition and edge calculation of OBD equipment are adopted, insurance claim settlement and violation data are fused, and a driving behavior evaluation model of the online car appointment based on the supervised/semi-supervised risk probability + scoring labels is established by combining integral data of multiple sections of travel within a certain time period. The driving behavior of the driver is evaluated by combining the driving process and the driving result, and the driving behavior file of the driver is established.
Those skilled in the art will appreciate that, in addition to implementing the system and its various devices, modules, units provided by the present invention as pure computer readable program code, the system and its various devices, modules, units provided by the present invention can be fully implemented by logically programming method steps in the form of logic gates, switches, application specific integrated circuits, programmable logic controllers, embedded microcontrollers and the like. Therefore, the system and various devices, modules and units thereof provided by the present invention can be regarded as a hardware component, and the devices, modules and units included therein for implementing various functions can also be regarded as structures within the hardware component; means, modules, units for performing the various functions may also be regarded as structures within both software modules and hardware components for performing the method.
The foregoing description of specific embodiments of the present invention has been presented. It is to be understood that the present invention is not limited to the specific embodiments described above, and that various changes or modifications may be made by one skilled in the art within the scope of the appended claims without departing from the spirit of the invention. The embodiments and features of the embodiments of the present application may be combined with each other arbitrarily without conflict.
Claims (10)
1. A method for monitoring, evaluating and early warning safe driving behaviors of a driver is characterized by comprising the following steps:
step S1: collecting driving data and processing the driving data;
step S2: establishing a model, wherein the model comprises driving behavior grading and driving result grading, and the comprehensive driving grading of a driver is obtained after the driving behavior grading and the driving result grading are combined;
and step S3: and according to the comprehensive driving rating of the driver, different safety assistance and prompt are adopted for the driver.
2. The method for monitoring, assessing and warning of safe driving behavior of a driver as claimed in claim 1, wherein the driving data includes: real-time vehicle data in the driving process comprises basic information of an OBD high-frequency dotting position and alarm information; the driving result data includes violation conditions and insurance claim data during the observation period.
3. The method for monitoring, evaluating and warning of safe driving behavior of a driver as claimed in claim 1, wherein the processing of the driving data comprises: and carrying out edge calculation on the driving condition of the driver every second by the OBD equipment, and transmitting the processed alarm result back to the cloud.
4. The method for monitoring, evaluating and warning of safe driving behavior of a driver as claimed in claim 1, wherein the driving behavior scoring comprises: and performing linear regression training on a large amount of network-constrained vehicle travel data acquired by OBD (on-board diagnostics) by using a supervised learning algorithm, constructing a model for accident overview every 10 kilometers of a single vehicle by combining travel key characteristics, and depicting the driving behavior and trip risk probability of each driver.
5. The method for monitoring, evaluating and warning the safe driving behavior of the driver as claimed in claim 1, wherein the scoring the driving results comprises: the final judgment is carried out by hundred-kilometer quick acceleration, hundred-kilometer quick deceleration, hundred-kilometer quick turning, hundred-kilometer overspeed, fatigue driving time ratio and daily average driving mileage, and the formula is as follows:
R＝a*p
p＝s1 x1 *s2 x2 *s3 x3 *s4 x4 *s5 x5 *s 6 log x6
wherein, R represents the driving behavior score of a certain trolley; p represents the probability of a possible accident every 10 kilometres; a represents a coefficient based on the probability mapping score of the accident; for the probabilities p, s1, s2, s3, s4, s5, s6, coefficients based on historical vehicle operation and risk occurrence fit are represented; x1 represents the number of hundred kilometers speeding; x2 represents the number of rapid acceleration times of hundred kilometers; x3 represents the number of rapid decelerations in hundred kilometers; x4 represents the number of sharp turns of hundred kilometers; x5 represents the fatigue driving time ratio; x6 represents the daily average mileage.
6. The method for monitoring, evaluating and early warning safe driving behaviors of drivers according to claim 1, wherein the statistical period of the comprehensive driving rating of the drivers is a time period required for evaluation, and Bayesian network classification is performed on the driving behaviors of the drivers by semi-supervised learning in combination with the marking of the driving insurance and the violation conditions of the network car appointment drivers to obtain high-risk, medium-risk, low-risk and normal vehicles.
7. A system for monitoring, evaluating and early warning of safe driving behavior of a driver, comprising:
a module M1: collecting driving data and processing the driving data;
a module M2: establishing a model, wherein the model comprises driving behavior grading and driving result grading, and the comprehensive driving grading of a driver is obtained after the driving behavior grading and the driving result grading are combined;
a module M3: and according to the comprehensive driving rating of the driver, different safety assistance and prompt are adopted for the driver.
8. The system for monitoring, assessing and warning of safe driving behavior of a driver as claimed in claim 7, wherein the driving data includes: real-time vehicle data in the driving process comprises basic information of an OBD high-frequency dotting position and alarm information; the driving result data includes violation conditions and insurance claim data during the observation period.
9. The system for monitoring, assessing and warning of safe driving behavior of a driver as claimed in claim 7, wherein said processing of driving data comprises: and carrying out edge calculation on the driving condition of the driver every second by the OBD equipment, and transmitting the processed alarm result back to the cloud.
10. The system for monitoring, assessing and warning of safe driving behavior of a driver as claimed in claim 7, wherein said driving behavior scoring comprises: carrying out linear regression training on a large amount of network contracted vehicle travel data acquired by OBD (on-board diagnostics), constructing a model for accident overview of each 10 kilometers of a single vehicle by combining travel key characteristics, and depicting the driving behavior and trip risk probability of each driver;
the driving result scoring comprises: the final judgment is carried out by hundred-kilometer quick acceleration, hundred-kilometer quick deceleration, hundred-kilometer quick turning, hundred-kilometer overspeed, fatigue driving time ratio and daily average driving mileage, and the formula is as follows:
R＝a*p
p＝s1 x1 *s2 x2 *s3 x3 *s4 x4 *s5 x5 *s 6 log x6
wherein, R represents the driving behavior score of a certain trolley; p represents the probability of a possible accident every 10 kilometres; a represents a coefficient based on the probability mapping score of the accident; for the probabilities p, s1, s2, s3, s4, s5, s6, coefficients based on historical vehicle operation and the fitting of the out-of-danger situation are represented; x1 represents the number of hundred kilometers speeding; x2 represents the number of rapid acceleration times of hundred kilometers; x3 represents the number of rapid decelerations in hundred kilometers; x4 represents the number of sharp turns of one hundred kilometers; x5 represents a fatigue driving time period ratio; x6 represents the average daily mileage;
the statistical cycle of the comprehensive driving rating of the driver is a time period required by evaluation, the driving insurance and violation condition marking of the network car booking driver are combined, and Bayesian network classification is carried out on the driving behavior of the driver through semi-supervised learning, so that high-risk, medium-risk, low-risk and normal vehicles are obtained.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310019360.5A CN115871682A (en) | 2023-01-06 | 2023-01-06 | Method and system for monitoring, evaluating and early warning safe driving behavior of driver |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310019360.5A CN115871682A (en) | 2023-01-06 | 2023-01-06 | Method and system for monitoring, evaluating and early warning safe driving behavior of driver |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115871682A true CN115871682A (en) | 2023-03-31 |
Family
ID=85758184
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310019360.5A Pending CN115871682A (en) | 2023-01-06 | 2023-01-06 | Method and system for monitoring, evaluating and early warning safe driving behavior of driver |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115871682A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116665342A (en) * | 2023-08-01 | 2023-08-29 | 北京简精科技有限公司 | New energy automobile driving behavior analysis method, system and equipment |
-
2023
- 2023-01-06 CN CN202310019360.5A patent/CN115871682A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116665342A (en) * | 2023-08-01 | 2023-08-29 | 北京简精科技有限公司 | New energy automobile driving behavior analysis method, system and equipment |
| CN116665342B (en) * | 2023-08-01 | 2023-10-03 | 北京简精科技有限公司 | New energy automobile driving behavior analysis method, system and equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11891071B2 (en) | Vehicle to vehicle telematics | |
| CN111860561B (en) | Abnormal stay behavior identification method, device and equipment of network appointment vehicle and storage medium | |
| CN109493566B (en) | Fatigue driving prediction method based on GPS data | |
| CN104268701B (en) | A kind of commerial vehicle drive safety evaluation system and evaluation method | |
| CN102136190B (en) | Dispatching management system and method for event emergency response of urban bus passenger transport | |
| CN108475362A (en) | Vehicle appraisal procedure, device and equipment | |
| CN106651602A (en) | ADAS intelligent vehicle-mounted terminal-based vehicle insurance management service system | |
| CN103871122A (en) | Driving behavior analysis method and driving behavior analysis system | |
| CN102044095A (en) | Personal driving behaviour analysis management control system | |
| US20180114377A1 (en) | Method for digital processing of automotive data and a system for implementing the same | |
| CN111511622A (en) | Programmatically identifying personality of autonomous vehicle | |
| CN109242227A (en) | The driving risk and assessment models of car steering behavior | |
| CN106781442B (en) | A kind of vehicle behavior early warning system | |
| CN114821968B (en) | Intervention method, device and equipment for fatigue driving of motor car driver and readable storage medium | |
| El Masri et al. | Toward self-policing: Detecting drunk driving behaviors through sampling CAN bus data | |
| CN106657244A (en) | Intelligently prompting method and system for vehicle state information | |
| CN115871682A (en) | Method and system for monitoring, evaluating and early warning safe driving behavior of driver | |
| TW202101344A (en) | Systems And Method For Calculating Liability Of A Driver Of A Vehicle | |
| Wu et al. | Clustering of several typical behavioral characteristics of commercial vehicle drivers based on GPS data mining: Case study of highways in China | |
| CN116911610A (en) | Method and system for monitoring, evaluating and early warning of driving safety risk of transport vehicle | |
| CN114511178A (en) | Monitoring method and system for safe driving behaviors of shared trip users | |
| CN117087674A (en) | Early warning method and system based on road risk and driver behavior | |
| DE102022111037A1 (en) | METHODS AND SYSTEMS FOR OPTIMIZING VEHICLE EVENT PROCESSES | |
| Kim et al. | Use of digital tachograph data to provide traffic safety education and evaluate effects on bus driver behavior | |
| CN116453345B (en) | Bus driving safety early warning method and system based on driving risk feedback |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |