CN105730450A - Driving behavior analyzing method and evaluation system based on vehicle-mounted data - Google Patents

Driving behavior analyzing method and evaluation system based on vehicle-mounted data Download PDF

Info

Publication number
CN105730450A
CN105730450A CN201610066136.1A CN201610066136A CN105730450A CN 105730450 A CN105730450 A CN 105730450A CN 201610066136 A CN201610066136 A CN 201610066136A CN 105730450 A CN105730450 A CN 105730450A
Authority
CN
China
Prior art keywords
stroke
amp
data
scoring
duration
Prior art date
Application number
CN201610066136.1A
Other languages
Chinese (zh)
Other versions
CN105730450B (en
Inventor
侯志伟
李旭
吴烜
Original Assignee
北京荣之联科技股份有限公司
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by 北京荣之联科技股份有限公司 filed Critical 北京荣之联科技股份有限公司
Priority to CN201610066136.1A priority Critical patent/CN105730450B/en
Publication of CN105730450A publication Critical patent/CN105730450A/en
Application granted granted Critical
Publication of CN105730450B publication Critical patent/CN105730450B/en

Links

Classifications

    • BPERFORMING OPERATIONS; TRANSPORTING
    • B60VEHICLES IN GENERAL
    • B60WCONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W40/00Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models
    • B60W40/08Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models related to drivers or passengers
    • B60W40/09Driving style or behaviour

Abstract

The invention discloses a driving behavior analyzing method based on vehicle-mounted data. The driving behavior analyzing method comprises the following steps of collecting driving data of automobiles in a real time manner; deleting invalid driving data according to bit mask; performing deletion or modification on exceptional data; performing descriptive statistic on the driving data so as to obtain statistic driving data; through an analytic hierarchy process of group decision, obtaining the weight distribution of evaluating indicators; through a method for scoring by an expert, obtaining scores during a stroke period; through a conformability principle, obtaining the duration of the stroke, the average velocity of the stroke, and the ride comfort scores of the stroke; and according to the weight distribution of the evaluating indicators and the score, obtaining a scoring matrix of the driving data. The invention further discloses a driving behavior evaluation system based on the vehicle-mounted data. According to the driving behavior analyzing method and evaluation system based on the vehicle-mounted data, through the level analysis method of the group decision, the weight of the driving data is obtained, and through the conformability principle, the score of the driving data is obtained, so that the driving behavior of a user can be accurately analyzed and evaluated.

Description

Driving behavior analysis method and the system of evaluation based on vehicle-mounted data

Technical field

The present invention relates to vehicle drive assay technical field, particularly relate to a kind of driving behavior analysis method based on vehicle-mounted data and evaluation system.

Background technology

Development along with mobile Internet and technology of Internet of things, increasing vehicle adds the camp of car networking by the mode of front dress or rear dress, and create the substantial amounts of related data based on the information such as vehicle location, performance, by observing and analyze these data, the driving behavior of user can be made concrete evaluation by us, so, can not only vehicle be used, the driving of user provides rational standard or suggestion, and is conducive to the differential management of related industry.Such as: car insurance industry, the related data of these vehicles brings new opportunity to keeping reforming of fixing a price of vehicle insurance.Particularly as follows: these data reasonably analyzed, and studying the dependency of itself and the information of being in danger, finally can providing the rational driving behavior evaluation factor for vehicle insurance price, thus more reasonably formulating the price of the vehicle insurance based on user's driving behavior.

At present, domestic correlational study focuses primarily upon identification and the early warning of the bad steering behavior based on car networking data and the economy research of driving behavior.Such as: patent documentation 201220002851.6 discloses a kind of driver driving economy evaluation system, the document is the information by the fuel consumption values obtained, MAP etc. is utilized to calculate most economical instantaneous fuel consumption values, and compare, with the instantaneous fuel consumption values of reality, the economy grade obtaining driving behavior, and inverse goes out the advisory information characterizing most economical driving behavior.But, lack of the evaluation methodology of driving behavior itself at present.

Summary of the invention

In view of this, it is an object of the invention to propose a kind of driving behavior analysis method based on vehicle-mounted data and evaluation system, it is possible to carry out analyzing accurately and evaluating to the driving behavior of user by the driving information of vehicle.

Based on the above-mentioned purpose driving behavior analysis method based on vehicle-mounted data provided by the invention, including:

The driving data of Real-time Collection vehicle, meanwhile, duty when each driving data can be gathered by the OBD box in vehicle generates a bitmask;

According to the bitmask that OBD box generates, it is judged that whether the driving data of collection is effective, and deletes invalid driving data;

Search and analyze abnormal data, according to the regularity that abnormal data occurs, carrying out deleting or revising for abnormal data;

Being described property of driving data is added up, obtain statistics driving data, wherein, described statistics driving data is divided into stroke statistical data and user's statistical data, and stroke statistical data includes: the duration of stroke, the period of stroke, the average speed of stroke, travel speed variance and stroke acceleration variance;User's statistical data includes: go on a journey number of times, user of user on average travels duration and user's average travel;

By the analytic hierarchy process (AHP) of group decision, it is thus achieved that the weight distribution of evaluation index, wherein, described evaluation index is respectively added up in driving data: the ride comfort of the period of stroke, the duration of stroke, the average speed of stroke and stroke;

By the method for expert estimation, it is thus achieved that trip times is marked;By principle of comforming, it is thus achieved that the scoring of stroke duration, the average speed scoring of stroke and the ride comfort of stroke are marked;

Weight distribution according to the trip times scoring obtained, the scoring of stroke duration, the average speed scoring of stroke and the ride comfort scoring of stroke and corresponding evaluation index, calculates the rating matrix obtaining driving data.

Preferably, the step of the driving data of described Real-time Collection vehicle includes:

Set frequency acquisition threshold value, it is judged that whether the frequency of driving data collection exceedes described frequency acquisition threshold value;

If so, frequency acquisition is then reduced, until lower than described frequency acquisition threshold value;

If it is not, then keep frequency acquisition constant.

Preferably, also include after the described step to being described property of driving data statistics:

According to user's statistical data, set user and go on a journey frequency threshold value and user travels duration threshold value, it is judged that whether vehicle is the vehicle of automatic start-stop;

If user on average travels duration and travels duration threshold value less than user, and user's number of times of going on a journey is gone on a journey frequency threshold value more than user, then filter out the relevant driving data of these vehicles, and be individually analyzed and calculate;

Otherwise, all data are retained constant.

Further, the step of described acquisition evaluation criterion weight distribution includes:

Having m policymaker that the weight of described 4 evaluation indexes is evaluated, wherein, the evaluation vector of 4 evaluation index importances is by kth policymaker:

ωk=(ω1 k2 k3 k4 k), (k=1,2 ... m)

Use again dstRepresent the degree of closeness of s policymaker and t policymaker, and

d s t = d { ω s , ω t } = Σ i = 1 4 ( ω i s - ω i t ) 2 , ( s , t = 1 , 2 ... m )

Thus, the degree of closeness obtaining kth policymaker and residue policymaker is dk, and

d k = Σ i = 1 m d k i , ( k = 1 , 2 ... m )

Further, the decision weights σ of kth policymaker is obtainedk, and

σ k = ( Σ i = 1 m d i ) / d k , ( k = 1 , 2 ... m )

Finally, the weight distribution obtaining described 4 evaluation indexes is ω, and

ω = ( Σ k = 1 m σ k ω 1 k , Σ k = 1 m σ k ω 2 k , Σ k = 1 m σ k ω 3 k , Σ k = 1 m σ k ω 4 k ) .

Further, the step of the scoring of described acquisition evaluation index includes:

The method adopting expert estimation, it is thus achieved that the scoring P of trip timesi,tf(i=1,2 ... n), wherein, n is the quantity of stroke;

From 0-120min, stroke duration being divided into multiple duration interval, the scoring more than 120min of the stroke duration is 0;The duration finding maximum frequency place is interval, and to arrange scoring be 100 points, and the interval scoring of all the other durations is Pi,time, and

Pi,time=fi,time/max(fi,time) × 100, wherein, Pi,timeFor the scoring in i-th duration interval of the stroke duration, fi,timeFor stroke duration frequency in i-th duration interval;

From 0-120km/h, the average speed of stroke is divided into multiple speed interval, and the scoring more than 120km/h of the average speed of stroke is 0;Finding the speed interval at maximum frequency place, and to arrange scoring be 100 points, the scoring of all the other speed intervals is Pi,speed, and

Pi,speed=fi,speed/max(fi,speed) × 100, wherein, Pi,speedFor the scoring in i-th speed interval of the average speed of stroke, fi,speedFor frequency in i-th speed interval of the average speed of stroke;

With the acceleration standard deviation of stroke for reference, the acceleration standard deviation of stroke is set to multiple standard deviation interval, obtains the scoring P of stroke ride comforti,smooth, and

P i , s m o o t h = ( 1 - Σ 0 i f i , s m o o t h / Σ 0 m a x ( i ) f i , s m o o t h ) × 100 , Wherein, Pi,smoothFor the scoring in i-th standard deviation interval of the stroke ride comfort, fi,smoothFor standard deviation frequency in i-th standard deviation interval.

Present invention also offers a kind of driving behavior based on vehicle-mounted data and evaluate system, including:

Data acquisition module, for the driving data of Real-time Collection vehicle, and obtains the bitmask that duty when each driving data is gathered by the OBD box in vehicle generates;

Data cleansing module, for the bitmask generated according to OBD box, it is judged that whether the driving data of collection is effective, and deletes invalid driving data;It is additionally operable to search and analyze abnormal data, according to the regularity that abnormal data occurs, carries out deleting or revising for abnormal data;

Data statistics module, for being described property of driving data is added up, obtain statistics driving data, wherein, described statistics driving data is divided into stroke statistical data and user's statistical data, wherein, stroke statistical data includes: the duration of stroke, the period of stroke, the average speed of stroke, travel speed variance and stroke acceleration variance;User's statistical data includes: go on a journey number of times, user of user on average travels duration and user's average travel;

Weight evaluation module, for by the analytic hierarchy process (AHP) of group decision, it is thus achieved that the weight distribution of evaluation index, wherein, evaluation index be add up in driving data: the ride comfort of the period of stroke, the duration of stroke, the average speed of stroke and stroke;

Data grading module, for by the method for comform principle and expert estimation, it is thus achieved that the scoring of evaluation index;

Computing module, for the weight distribution according to evaluation index and scoring, calculates the rating matrix obtaining driving data.

Preferably, described data acquisition module is additionally operable to set frequency acquisition threshold value, it is judged that whether the frequency of driving data collection exceedes described frequency acquisition threshold value;

If so, frequency acquisition is then reduced, until lower than described frequency acquisition threshold value;

If it is not, then keep frequency acquisition constant.

Preferably, described data cleansing module is additionally operable to according to user's statistical data, sets user and goes on a journey frequency threshold value and user travels duration threshold value, it is judged that whether vehicle is the vehicle of automatic start-stop;

If user on average travels duration and travels duration threshold value less than user, and user's number of times of going on a journey is gone on a journey frequency threshold value more than user, then filter out the relevant driving data of these vehicles, and carry out individually analyzing and calculating;

Otherwise, all data are retained constant.

Further, the analytic hierarchy process (AHP) of described group decision has m policymaker the weight of described 4 evaluation indexes is evaluated, described weight evaluation module be additionally operable to by calculate kth policymaker to the evaluation vector of 4 evaluation index importances be:

ωk=(ω1 k2 k3 k4 k), (k=1,2 ... m)

Use again dstRepresent the degree of closeness of s policymaker and t policymaker, and

d s t = d { ω s , ω t } = Σ i = 1 4 ( ω i s - ω i t ) 2 , ( s , t = 1 , 2 ... m )

Thus, the degree of closeness obtaining kth policymaker and residue policymaker is dk, and

d k = Σ i = 1 m d k i , ( k = 1 , 2 ... m )

Further, the decision weights σ of kth policymaker is obtainedk, and

σ k = ( Σ i = 1 m d i ) / d k , ( k = 1 , 2 ... m )

Finally, the weight obtaining described 4 evaluation indexes is ω, and

ω = ( Σ k = 1 m σ k ω 1 k , Σ k = 1 m σ k ω 2 k , Σ k = 1 m σ k ω 3 k , Σ k = 1 m σ k ω 4 k ) .

Further, described data grading module is additionally operable to:

The method adopting expert estimation, it is thus achieved that the scoring P of trip timesi,tf(i=1,2 ... n), wherein, n is the quantity of stroke;

From 0-120min, stroke duration being divided into multiple duration interval, the scoring more than 120min of the stroke duration is 0;The duration finding maximum frequency place is interval, and to arrange scoring be 100 points, and the interval scoring of all the other durations is Pi,time, and

Pi,time=fi,time/max(fi,time) × 100, wherein, Pi,timeFor the scoring in i-th duration interval of the stroke duration, fi,timeFor stroke duration frequency in i-th duration interval;

From 0-120km/h, the average speed of stroke is divided into multiple speed interval, and the scoring more than 120km/h of the average speed of stroke is 0;Finding the speed interval at maximum frequency place, and to arrange scoring be 100 points, the scoring of all the other speed intervals is Pi,speed, and

Pi,speed=fi,speed/max(fi,speed) × 100, wherein, Pi,speedFor the scoring in i-th speed interval of the average speed of stroke, fi,speedFor frequency in i-th speed interval of the average speed of stroke;

With the acceleration standard deviation of stroke for reference, the acceleration standard deviation of stroke is set to multiple standard deviation interval, obtains the scoring P of stroke ride comforti,smooth, and

P i , s m o o t h = ( 1 - Σ 0 i f i , s m o o t h / Σ 0 m a x ( i ) f i , s m o o t h ) × 100 , Wherein, Pi,smoothFor the scoring in i-th standard deviation interval of the stroke ride comfort, fi,smoothFor standard deviation frequency in i-th standard deviation interval.

As can be seen from above, driving behavior analysis method based on vehicle-mounted data provided by the invention and evaluation system are by obtaining effective driving data to the cleaning of driving data, then pass through the weight distribution adopting the analytic hierarchy process (AHP) of group decision to obtain driving data, and adopt the method for comform principle and expert estimation to obtain the scoring of driving data, the analysis accurately to driving behavior and evaluation can be obtained by the weight distribution of driving data and scoring.

Accompanying drawing explanation

Fig. 1 is the flow chart of the embodiment of the driving behavior analysis method based on vehicle-mounted data provided by the invention;

Fig. 2 is the structure chart that the embodiment of system is evaluated in the driving behavior based on vehicle-mounted data provided by the invention.

Detailed description of the invention

For making the object, technical solutions and advantages of the present invention clearly understand, below in conjunction with specific embodiment, and with reference to accompanying drawing, the present invention is described in more detail.

With reference to shown in Fig. 1, for the flow chart of the embodiment of the driving behavior analysis method based on vehicle-mounted data provided by the invention.The described driving behavior analysis method based on vehicle-mounted data, including:

Step 101, the driving data of Real-time Collection vehicle, meanwhile, duty when each driving data can be gathered by the OBD box in vehicle generates a bitmask.

Wherein, described driving data is to be obtained by the data acquisition relevant with traveling in the vehicles such as the gps data on automobile, electromotor related data and G-sensor data.Described driving data comprises the Various types of data related in driving process, for instance: time residing for the distance of each run, travel speed, acceleration and stroke etc..Described OBD box refers to onboard diagnostic system, and it can monitor the duty of automobile engine and automobilism at any time, and collects the information that storage is relevant.When OBD box gathers each driving data, all can judge the whether effective bitmask of these data to these data duty at that time generation one is preliminary.

Step 102, according to the bitmask that OBD box generates, it is judged that whether the driving data of collection is effective, and deletes invalid driving data.

For each driving data, read the bitmask corresponding with this driving data, the judgment principle according to bitmask, directly judging whether this driving data is valid data, if finding, this driving data is invalid, then delete this driving data, if finding, this driving data is effective, then retain this driving data.

Step 103, searches and analyzes abnormal data, according to the regularity that abnormal data occurs, carries out deleting or revising for abnormal data.

Wherein, described abnormal data refers to the data judging substantially not meet practical situation according to convention.Such as: in one section of run-length data collected, it has been found that speed is a certain proportion threshold value that the quantity of the data of 0 has exceeded total data, namely the ratio occupied has reached higher degree, then it is believed that these data do not have statistical significance, it should delete.Described proportion threshold value can according to the practical situation respective settings of different pieces of information.And for example: in another stroke gps data collected, find that gps data is continuous print, but the speed of certain position is suddenly 0, and it is promptly restored to original velocity amplitude, namely, the rate of change of this speed is beyond the urgent threshold value accelerated with emergency deceleration, so can be determined that, these data are likely due to the interference data that hardware reason causes, at this moment, hop region in these data adopts the method for slip mean filter to make it smooth, so, it becomes possible to make abnormal data be changed into effective driving data.

Step 104, being described property of driving data is added up, obtain statistics driving data, wherein, described statistics driving data is divided into stroke statistical data and user's statistical data, wherein, stroke statistical data includes: the duration of stroke, the period of stroke, the average speed of stroke, travel speed variance and stroke acceleration variance;User's statistical data includes: go on a journey number of times, user of user on average travels duration and user's average travel.

Wherein, descriptive statistic refers to and is concluded respectively in corresponding statistical table according to different mode classifications by driving data.Described stroke statistical data refers to adds up the data such as the duration of corresponding stroke, the period of stroke, the average speed of stroke, travel speed variance and stroke acceleration variance respectively to every section of stroke.Described user's statistical data is based on the basis of stroke statistical data, and for the driving behavior of same user, the trip of corresponding counting user number of times, user on average travel the data such as duration and user's average travel respectively.

Step 105, by the analytic hierarchy process (AHP) of group decision, it is thus achieved that the weight distribution of evaluation index, and wherein, described evaluation index is respectively added up in driving data: the ride comfort of the period of stroke, the duration of stroke, the average speed of stroke and stroke.

Wherein, the analytic hierarchy process (AHP) of described group decision is that one passes through multiple policymaker, adopts the method that a certain target is evaluated by different levels, and the method is by the overall merit then passing through multiple policymaker, it is possible to obtain comparatively reliable, stable evaluation result.Concrete flow process is that each policymaker is respectively provided with different weights, then each policymaker is all to all targets, the i.e. ride comfort of the period of stroke, the duration of stroke, the average speed of stroke and stroke, it is evaluated respectively, so, each target can obtain the different evaluation of the policymaker of different weight, finally evaluation result is accumulated, just can obtain relatively reliable evaluation, or become the weight of different target.

Step 106, by the method for expert estimation, it is thus achieved that trip times is marked;By principle of comforming, it is thus achieved that the duration of stroke is marked, the average speed of stroke is marked and the scoring of the ride comfort of stroke.

Method according to comform principle and expert estimation, by adding up the feature of driving data, gives a mark to respectively different evaluation indexes, finally obtains the scoring of all evaluation indexes.

Step 107, the weight distribution according to the trip times scoring obtained, the scoring of stroke duration, the average speed scoring of stroke and the ride comfort scoring of stroke and corresponding evaluation index, calculate the rating matrix obtaining driving data.

The weight distribution of evaluation index is listed weight vectors according to a definite sequence, then the scoring of evaluation index is also listed scoring vector according to same order, make weight vectors and scoring multiplication of vectors, finally obtain the rating matrix of evaluation index, namely to the concrete analysis result of different evaluation index in driving data.

By above-described embodiment it can be seen that first pass through screening and the process of data based on the driving behavior analysis method of vehicle-mounted data, obtain driving data accurately and effectively.The evaluation index of selected driving data, then weight distribution and the scoring of evaluation index are obtained respectively, finally can calculate the accurate evaluation obtained user's driving behavior, and this is evaluated as the concrete data of quantization, is conducive to driving behavior being analyzed and record.

Further, the described driving behavior analysis method based on vehicle-mounted data is not limited to the enforcement step of above-described embodiment, it is possible to be adjusted correspondingly according to the actual needs, for instance: the order of step 105 and step 106 can arbitrarily be exchanged.

In some preferred embodiments, in described step 101, the step of the driving data of Real-time Collection vehicle includes:

For the respective feature of different vehicle, set corresponding frequency acquisition threshold value respectively, when the driving data of Real-time Collection vehicle, it is judged that whether the frequency of driving data collection exceedes described frequency acquisition threshold value;

If so, frequency acquisition is then reduced, until lower than described frequency acquisition threshold value;

If it is not, then keep frequency acquisition constant.

When vehicle is in driving process, if the collection of the driving data of vehicle being exceeded certain frequency possibility the normal driving of user will be caused certain interference, and this is definitely unallowed, it is necessary to first ensure the driving safety of user.It is necessary to set the frequency acquisition threshold value of a safety so that the normal use of user will not be had any impact by the collection of driving data.So, the present invention is exactly based on and arranges a frequency acquisition limited, namely frequency acquisition threshold value, it is possible to the frequency of driving data collection is limited in safe and reliable scope, has ensured the normal driving of user.

As a preferred embodiment of the present invention, also include after the described step to being described property of driving data statistics:

According to user's statistical data, set user and go on a journey frequency threshold value and user travels duration threshold value, it is judged that whether vehicle is the vehicle of automatic start-stop;

If user on average travels duration and travels duration threshold value less than user, and user's number of times of going on a journey is gone on a journey frequency threshold value more than user, then filter out the relevant driving data of these vehicles, and carry out individually analyzing and calculating;

Otherwise, all data are retained constant.

Owing to a lot of high-end vehicles have employed the correlation technique of electromotor automatic start-stop, and the driving data of the driving data that the automatic start-stop of electromotor produces and non-automatic start and stop has bigger difference, therefore, if they being processed together and analyze and will producing bigger interference and error so that analyze result inaccurate.Accordingly, it would be desirable to the vehicle of this class is distinguished.The vehicle adopting electromotor automatic start-stop technology has that stroke duration is shorter and feature that the frequency is more, the therefore characteristic according to this feature first class vehicle, sets user respectively and goes on a journey frequency threshold value and user travels duration threshold value.According to the user's statistical data obtained in step 104, the user of statistics is on average travelled duration and user's number of times of going on a journey compares with corresponding threshold value.If user on average travels duration and travels duration threshold value less than user, and user's number of times of going on a journey goes on a journey frequency threshold value more than user, so representing, this vehicle have employed electromotor automatic start-stop technology, is distinguished by driving data corresponding for the vehicle of this class and individually analyzes and process.In such manner, it is possible to be greatly improved accuracy and the reliability of driving behavior analysis.

Further, the described analytic hierarchy process (AHP) by group decision, it is thus achieved that the step 105 of the weight distribution of evaluation index includes:

It is assumed that there be m policymaker that the weight of described 4 evaluation indexes is evaluated, wherein, the evaluation vector of 4 evaluation index importances is by kth policymaker:

ωk=(ω1 k2 k3 k4 k), (k=1,2 ... m), wherein, ω1、ω2、ω3、ω4The weighted value of corresponding 4 evaluation indexes respectively.

Use again dstRepresent the degree of closeness of s policymaker and t policymaker, and

d s t = d { ω s , ω t } = Σ i = 1 4 ( ω i s - ω i t ) 2 , ( s , t = 1 , 2 ... m )

Thus, the degree of closeness obtaining kth policymaker and residue policymaker is dk, and

d k = Σ i = 1 m d k i , ( k = 1 , 2 ... m )

Further, the decision weights σ of kth policymaker is obtainedk, and

σ k = ( Σ i = 1 m d i ) / d k , ( k = 1 , 2 ... m )

The weight distribution finally giving described 4 evaluation indexes is ω, and

ω = ( Σ k = 1 m σ k ω 1 k , Σ k = 1 m σ k ω 2 k , Σ k = 1 m σ k ω 3 k , Σ k = 1 m σ k ω 4 k ) .

Here, the present invention, when adopting the analytic hierarchy process (AHP) based on group decision, comes the weight of respective settings policymaker namely the significance level of policymaker self by calculating the degree of closeness between different decision-making.Specifically, kth policymaker and the degree of closeness d remaining policymakerkValue more little, then it represents that the decision-making of this policymaker is more big close to the degree of group decision, therefore, in colony obtain significance level also more high, that is, the weight of this policymaker is also more big.In such manner, it is possible to obtain, by the analysis method of group decision, the weight that 4 evaluation index decision-makings are gone out by all policymaker more accurately, namely obtain the weight distribution of evaluation index.

Further, described step 106 includes:

The method adopting expert estimation, it is thus achieved that the scoring P of trip timesi,tf(i=1,2 ... n), wherein, n is the quantity of stroke.

Wherein, the method for expert estimation is existing method, it is possible to by the rule of data with existing, corresponding available data is given a mark.

From 0-120min, stroke duration being divided into multiple duration interval, the scoring more than 120min of the stroke duration is 0;The duration finding maximum frequency place is interval, and to arrange scoring be 100 points, and the interval scoring of all the other durations is Pi,time, and

Pi,time=fi,time/max(fi,time) × 100, wherein, Pi,timeFor the scoring in i-th duration interval of the stroke duration, fi,timeFor stroke duration frequency in i-th duration interval.

Wherein, the relevant regulations according to traffic law, the time that single is driven is fatigue driving more than 120min, therefore, the scoring more than 120min of the stroke duration is set as 0.Described frequency refers to after the driving stroke duration gathered is divided different duration interval, in different intervals, checks the number of the interval driving data of this duration namely the number of times occurred.During the multiple duration interval of described division, it is possible to the needs according to analyzing divide accordingly, namely, when needs Accurate Analysis, it is possible to make duration interval shorter, when exact requirements is relatively low, duration interval can be made accordingly elongated, it is possible to increase the speed of data analysis.

From 0-120km/h, the average speed of stroke is divided into multiple speed interval, and the scoring more than 120km/h of the average speed of stroke is 0;Finding the speed interval at maximum frequency place, and to arrange scoring be 100 points, the scoring of all the other speed intervals is Pi,speed, and

Pi,speed=fi,speed/max(fi,speed) × 100, wherein, Pi,speedFor the scoring in i-th speed interval of the average speed of stroke, fi,speedFor frequency in i-th speed interval of the average speed of stroke.

Similar with stroke duration, when travel speed is more than 120km/h for hypervelocity, now scoring is 0.

With the acceleration standard deviation of stroke for reference, the acceleration standard deviation of stroke is set to multiple standard deviation interval, obtains the scoring P of stroke ride comforti,smooth, and

P i , s m o o t h = ( 1 - Σ 0 i f i , s m o o t h / Σ 0 m a x ( i ) f i , s m o o t h ) × 100 , Wherein, Pi,smoothFor the scoring in i-th standard deviation interval of the stroke ride comfort, fi,smoothFor standard deviation frequency in i-th standard deviation interval.

Wherein, the acceleration standard deviation of described stroke is to calculate according to the travel speed variance in statistical data and acceleration variance to obtain.Described stroke ride comfort refers to the change frequency of automobile running status in the process of moving namely the stability travelled.When vehicle stationary or when at the uniform velocity travelling, stroke ride comfort is best, on the contrary, anxious accelerates, anxious slows down and zig zag all can reduce stroke ride comfort.

The final scoring of each evaluation index both can by having obtained the scoring addition calculation in all intervals, it can also be carried out percentage, such as, the evaluation of stroke duration is divided into 10 different durations interval, the full marks that so stroke duration is total should be 1000 points, so, last calculated appraisal result is divided by 10, then the total score of stroke duration is converted into full marks 100, namely scoring is carried out percentage.So, achieved the scoring forming the period by the method for expert estimation, calculated the scoring of the ride comfort obtaining the duration of stroke, the average speed of stroke and stroke by principle of comforming respectively.Make it possible to the feature according to different driving data, obtain the accurate scoring of corresponding evaluation index.

Preferably, in vehicle insurance industry, also include after obtaining rating matrix: undertaken contrasting and analyzing by the history Claims Resolution data of evaluation result with vehicle, according to history Claims Resolution data, evaluation methodology is optimized further, finally obtain the evaluation methodology more meeting actual Claims Resolution so that the described driving behavior analysis method based on vehicle-mounted data is more accurate.

With reference to, shown in Fig. 2, evaluating the structure chart of the embodiment of system for the driving behavior based on vehicle-mounted data provided by the invention.The shown driving behavior based on vehicle-mounted data is evaluated system and is included:

Data acquisition module 201, for the driving data of Real-time Collection vehicle, and obtains the bitmask that duty when each driving data is gathered by the OBD box in vehicle generates.

Data cleansing module 202, for the bitmask generated according to OBD box, it is judged that whether the driving data of collection is effective, and deletes invalid driving data;It is additionally operable to search and analyze abnormal data, according to the regularity that abnormal data occurs, carries out deleting or revising for abnormal data.

Data statistics module 203, for being described property of driving data is added up, obtain statistics driving data, wherein, described statistics driving data is divided into stroke statistical data and user's statistical data, wherein, stroke statistical data includes: the duration of stroke, the period of stroke, the average speed of stroke, travel speed variance and stroke acceleration variance;User's statistical data includes: go on a journey number of times, user of user on average travels duration and user's average travel.

Weight evaluation module 204, for by the analytic hierarchy process (AHP) of group decision, it is thus achieved that the weight distribution of evaluation index, wherein, evaluation index be add up in driving data: the ride comfort of the period of stroke, the duration of stroke, the average speed of stroke and stroke.

Data grading module 205, for by the method for comform principle and expert estimation, it is thus achieved that the scoring of evaluation index.

Computing module 206, for the weight distribution according to evaluation index and scoring, calculates the rating matrix obtaining driving data.

From above-described embodiment, the described driving behavior based on vehicle-mounted data is evaluated system and is realized the collection of driving data by described data acquisition module 201, screening and the removing of driving data is realized by data cleansing module 202, then pass through described weight evaluation module 204 and described data grading module 205 obtains weight distribution and the scoring of driving data respectively, finally, can calculate, by described computing module 206, the rating matrix obtaining driving data.By evaluation index as driving data of the period of selected stroke, the duration of stroke, the average speed of stroke and the ride comfort of stroke, and analyze and process accordingly, make it possible to the driving behavior to user carry out analyzing accurately and evaluating, and finally give the evaluation result quantified.

In some preferred embodiments, described data acquisition module 201 is additionally operable to set frequency acquisition threshold value, it is judged that whether the frequency of driving data collection exceedes described frequency acquisition threshold value;

If so, frequency acquisition is then reduced, until lower than described frequency acquisition threshold value;

If it is not, then keep frequency acquisition constant.

Described data acquisition module 201 ensure that the normal driving without influence on user of the collection to driving data, and then brings potential safety hazard to driving.So, improve the described driving behavior based on vehicle-mounted data and evaluate the security reliability of system.

In presently preferred embodiment, described data cleansing module 202 is additionally operable to according to user's statistical data, sets user and goes on a journey frequency threshold value and user travels duration threshold value, it is judged that whether vehicle is the vehicle of automatic start-stop;

If user on average travels duration and travels duration threshold value less than user, and user's number of times of going on a journey is gone on a journey frequency threshold value more than user, then filter out the relevant driving data of these vehicles, and carry out individually analyzing and calculating;

Otherwise, all data are retained constant.

So, the vehicle of the vehicle of automatic start-stop Yu non-automatic start and stop is made a distinction by described data cleansing module 202 further mutually so that the evaluation of driving data is more accurate.

Further, the evaluation procedure of described weight evaluation module 204 is:

Having m policymaker that the weight of described 4 evaluation indexes is evaluated, wherein, the evaluation vector of 4 evaluation index importances is by kth policymaker:

ωk=(ω1 k2 k3 k4 k), (k=1,2 ... m)

Use again dstRepresent the degree of closeness of s policymaker and t policymaker, and

d s t = d { ω s , ω t } = Σ i = 1 4 ( ω i s - ω i t ) 2 , ( s , t = 1 , 2 ... m )

Thus, the degree of closeness obtaining kth policymaker and residue policymaker is dk, and

d k = Σ i = 1 m d k i , ( k = 1 , 2 ... m )

Further, the decision weights σ of kth policymaker is obtainedk, and

σ k = ( Σ i = 1 m d i ) / d k , ( k = 1 , 2 ... m )

The weight finally giving described 4 evaluation indexes is ω, and

ω = ( Σ k = 1 m σ k ω 1 k , Σ k = 1 m σ k ω 2 k , Σ k = 1 m σ k ω 3 k , Σ k = 1 m σ k ω 4 k ) .

So, by judging that the degree of closeness of different policymaker carrys out the weight of respective settings difference policymaker, it is possible to greatly improve the accuracy of group decision.It is of course also possible to the masses of all policymaker are set to identical.

Further, the scoring step of described data grading module 205 is:

The method adopting expert estimation, it is thus achieved that the scoring P of trip timesi,tf(i=1,2 ... n), wherein, n is the quantity of stroke;

From 0-120min, stroke duration being divided into multiple duration interval, the scoring more than 120min of the stroke duration is 0;The duration finding maximum frequency place is interval, and to arrange scoring be 100 points, and the interval scoring of all the other durations is Pi,time, and

Pi,time=fi,time/max(fi,time) × 100, wherein, Pi,timeFor the scoring in i-th duration interval of the stroke duration, fi,timeFor stroke duration frequency in i-th duration interval;

From 0-120km/h, the average speed of stroke is divided into multiple speed interval, and the scoring more than 120km/h of the average speed of stroke is 0;Finding the speed interval at maximum frequency place, and to arrange scoring be 100 points, the scoring of all the other speed intervals is Pi,speed, and

Pi,speed=fi,speed/max(fi,speed) × 100, wherein, Pi,speedFor the scoring in i-th speed interval of the average speed of stroke, fi,speedFor frequency in i-th speed interval of the average speed of stroke;

With the acceleration standard deviation of stroke for reference, the acceleration standard deviation of stroke is set to multiple standard deviation interval, obtains the scoring P of stroke ride comforti,smooth, and

P i , s m o o t h = ( 1 - Σ 0 i f i , s m o o t h / Σ 0 m a x ( i ) f i , s m o o t h ) × 100 , Wherein, Pi,smoothFor the scoring in i-th standard deviation interval of the stroke ride comfort, fi,smoothFor standard deviation frequency in i-th standard deviation interval.

Data characteristics according to different evaluation index, by comforming, it is marked by principle respectively, due to trip times only with time correlation and unrelated with driving data, therefore, trip times adopts the method for expert estimation to be evaluated, the main impact considering the different periods physiologic factor on human body and social environmental factor (such as traffic environment etc.).And all the other evaluation indexes are all relevant with driving data, therefore adopt principle of comforming to give a mark, and carry out corresponding score calculation according to different interval different frequencies.So so that the driving behavior evaluation system based on vehicle-mounted data can obtain marking more accurately, finally improves the accuracy that user's driving behavior is evaluated.

Those of ordinary skill in the field are it is understood that the discussion of any of the above embodiment is exemplary only, it is not intended that hint the scope of the present disclosure (including claim) is limited to these examples;Under the thinking of the present invention, can also be combined between technical characteristic in above example or different embodiment, step can realize with random order, and there are other changes many of the different aspect of the present invention as above, for they not offers in details simple and clear.Therefore, all within the spirit and principles in the present invention, any omission of making, amendment, equivalent replacement, improvement etc., should be included within protection scope of the present invention.

Claims (10)

1. the driving behavior analysis method based on vehicle-mounted data, it is characterised in that including:
The driving data of Real-time Collection vehicle, meanwhile, duty when each driving data can be gathered by the OBD box in vehicle generates a bitmask;
According to the bitmask that OBD box generates, it is judged that whether the driving data of collection is effective, and deletes invalid driving data;
Search and analyze abnormal data, according to the regularity that abnormal data occurs, carrying out deleting or revising for abnormal data;
Being described property of driving data is added up, obtain statistics driving data, wherein, described statistics driving data is divided into stroke statistical data and user's statistical data, and stroke statistical data includes: the duration of stroke, the period of stroke, the average speed of stroke, travel speed variance and stroke acceleration variance;User's statistical data includes: go on a journey number of times, user of user on average travels duration and user's average travel;
By the analytic hierarchy process (AHP) of group decision, it is thus achieved that the weight distribution of evaluation index, wherein, described evaluation index is respectively added up in driving data: the ride comfort of the period of stroke, the duration of stroke, the average speed of stroke and stroke;
By the method for expert estimation, it is thus achieved that trip times is marked;By principle of comforming, it is thus achieved that the scoring of stroke duration, the average speed scoring of stroke and the ride comfort of stroke are marked;
Weight distribution according to the trip times scoring obtained, the scoring of stroke duration, the average speed scoring of stroke and the ride comfort scoring of stroke and corresponding evaluation index, calculates the rating matrix obtaining driving data.
2. method according to claim 1, it is characterised in that the step of the driving data of described Real-time Collection vehicle includes:
Set frequency acquisition threshold value, it is judged that whether the frequency of driving data collection exceedes described frequency acquisition threshold value;
If so, frequency acquisition is then reduced, until lower than described frequency acquisition threshold value;
If it is not, then keep frequency acquisition constant.
3. method according to claim 1, it is characterised in that also include after the described step to being described property of driving data statistics:
According to user's statistical data, set user and go on a journey frequency threshold value and user travels duration threshold value, it is judged that whether vehicle is the vehicle of automatic start-stop;
If user on average travels duration and travels duration threshold value less than user, and user's number of times of going on a journey is gone on a journey frequency threshold value more than user, then filter out the relevant driving data of these vehicles, and be individually analyzed and calculate;
Otherwise, all data are retained constant.
4. method according to claim 1, it is characterised in that the step of described acquisition evaluation criterion weight distribution includes:
Having m policymaker that the weight of described 4 evaluation indexes is evaluated, wherein, the evaluation vector of 4 evaluation index importances is by kth policymaker:
ωk=(ω1 k2 k3 k4 k), (k=1,2 ... m)
Use again dstRepresent the degree of closeness of s policymaker and t policymaker, and
d s t = d { ω s , ω t } = Σ i = 1 4 ( ω i s - ω i t ) 2 , ( s , t = 1 , 2 ... m )
Thus, the degree of closeness obtaining kth policymaker and residue policymaker is dk, and
d k = Σ i = 1 m d k i , ( k = 1 , 2 ... m )
Further, the decision weights σ of kth policymaker is obtainedk, and
σ k = ( Σ i = 1 m d i ) / d k , ( k = 1 , 2 ... m )
Finally, the weight distribution obtaining described 4 evaluation indexes is ω, and
ω = ( Σ k = 1 m σ k ω 1 k , Σ k = 1 m σ k ω 2 k , Σ k = 1 m σ k ω 3 k , Σ k = 1 m σ k ω 4 k ) .
5. method according to claim 1, it is characterised in that the step of the scoring of described acquisition evaluation index includes:
The method adopting expert estimation, it is thus achieved that the scoring P of trip timesi,tf(i=1,2 ... n), wherein, n is the quantity of stroke;
From 0-120min, stroke duration being divided into multiple duration interval, the scoring more than 120min of the stroke duration is 0;The duration finding maximum frequency place is interval, and to arrange scoring be 100 points, and the interval scoring of all the other durations is Pi,time, and
Pi,time=fi,time/max(fi,time) × 100, wherein, Pi,timeFor stroke durationiScoring in individual duration interval, fi,timeFor stroke duration frequency in i-th duration interval;
From 0-120km/h, the average speed of stroke is divided into multiple speed interval, and the scoring more than 120km/h of the average speed of stroke is 0;Finding the speed interval at maximum frequency place, and to arrange scoring be 100 points, the scoring of all the other speed intervals is Pi,speed, and
Pi,speed=fi,speed/max(fi,speed) × 100, wherein, Pi,speedFor the average speed of strokeiScoring in individual speed interval, fi,speedFor frequency in i-th speed interval of the average speed of stroke;
With the acceleration standard deviation of stroke for reference, the acceleration standard deviation of stroke is set to multiple standard deviation interval, obtains the scoring P of stroke ride comforti,smooth, and
P i , s m o o t h = ( 1 - Σ 0 i f i , s m o o t h / Σ 0 m a x ( i ) f i , s m o o t h ) × 100 , Wherein, Pi,smoothFor the scoring in i-th standard deviation interval of the stroke ride comfort, fi,smoothFor standard deviation frequency in i-th standard deviation interval.
6. system is evaluated in the driving behavior based on vehicle-mounted data, it is characterised in that including:
Data acquisition module, for the driving data of Real-time Collection vehicle, and obtains the bitmask that duty when each driving data is gathered by the OBD box in vehicle generates;
Data cleansing module, for the bitmask generated according to OBD box, it is judged that whether the driving data of collection is effective, and deletes invalid driving data;It is additionally operable to search and analyze abnormal data, according to the regularity that abnormal data occurs, carries out deleting or revising for abnormal data;
Data statistics module, for being described property of driving data is added up, obtain statistics driving data, wherein, described statistics driving data is divided into stroke statistical data and user's statistical data, wherein, stroke statistical data includes: the duration of stroke, the period of stroke, the average speed of stroke, travel speed variance and stroke acceleration variance;User's statistical data includes: go on a journey number of times, user of user on average travels duration and user's average travel;
Weight evaluation module, for by the analytic hierarchy process (AHP) of group decision, it is thus achieved that the weight distribution of evaluation index, wherein, evaluation index be add up in driving data: the ride comfort of the period of stroke, the duration of stroke, the average speed of stroke and stroke;
Data grading module, for by the method for comform principle and expert estimation, it is thus achieved that the scoring of evaluation index;
Computing module, for the weight distribution according to evaluation index and scoring, calculates the rating matrix obtaining driving data.
7. system according to claim 6, it is characterised in that described data acquisition module is additionally operable to set frequency acquisition threshold value, it is judged that whether the frequency of driving data collection exceedes described frequency acquisition threshold value;
If so, frequency acquisition is then reduced, until lower than described frequency acquisition threshold value;
If it is not, then keep frequency acquisition constant.
8. system according to claim 6, it is characterised in that described data cleansing module is additionally operable to according to user's statistical data, sets user and goes on a journey frequency threshold value and user travels duration threshold value, it is judged that whether vehicle is the vehicle of automatic start-stop;
If user on average travels duration and travels duration threshold value less than user, and user's number of times of going on a journey is gone on a journey frequency threshold value more than user, then filter out the relevant driving data of these vehicles, and carry out individually analyzing and calculating;
Otherwise, all data are retained constant.
9. system according to claim 6, it is characterised in that
The analytic hierarchy process (AHP) of described group decision has m policymaker the weight of described 4 evaluation indexes is evaluated, described weight evaluation module be additionally operable to by calculate kth policymaker to the evaluation vector of 4 evaluation index importances be:
ωk=(ω1 k2 k3 k4 k), (k=1,2 ... m)
Use again dstRepresent the degree of closeness of s policymaker and t policymaker, and
d s t = d { ω s , ω t } = Σ i = 1 4 ( ω i s - ω i t ) 2 , ( s , t = 1 , 2 ... m )
Thus, the degree of closeness obtaining kth policymaker and residue policymaker is dk, and
d k = Σ i = 1 m d k i , ( k = 1 , 2 ... m )
Further, the decision weights σ of kth policymaker is obtainedk, and
σ k = ( Σ i = 1 m d i ) / d k , ( k = 1 , 2 ... m )
Finally, the weight obtaining described 4 evaluation indexes is ω, and
ω = ( Σ k = 1 m σ k ω 1 k , Σ k = 1 m σ k ω 2 k , Σ k = 1 m σ k ω 3 k , Σ k = 1 m σ k ω 4 k ) .
10. system according to claim 6, it is characterised in that described data grading module is additionally operable to:
The method adopting expert estimation, it is thus achieved that the scoring P of trip timesi,tf(i=1,2 ... n), wherein, n is the quantity of stroke;
From 0-120min, stroke duration being divided into multiple duration interval, the scoring more than 120min of the stroke duration is 0;The duration finding maximum frequency place is interval, and to arrange scoring be 100 points, and the interval scoring of all the other durations is Pi,time, and
Pi,time=fi,time/max(fi,time) × 100, wherein, Pi,timeFor stroke durationiScoring in individual duration interval, fi,timeFor stroke duration frequency in i-th duration interval;
From 0-120km/h, the average speed of stroke is divided into multiple speed interval, and the scoring more than 120km/h of the average speed of stroke is 0;Finding the speed interval at maximum frequency place, and to arrange scoring be 100 points, the scoring of all the other speed intervals is Pi,speed, and
Pi,speed=fi,speed/max(fi,speed) × 100, wherein, Pi,speedFor the average speed of strokeiScoring in individual speed interval, fi,speedFor frequency in i-th speed interval of the average speed of stroke;
With the acceleration standard deviation of stroke for reference, the acceleration standard deviation of stroke is set to multiple standard deviation interval, obtains the scoring P of stroke ride comforti,smooth, and
P i , s m o o t h = ( 1 - Σ 0 i f i , s m o o t h / Σ 0 m a x ( i ) f i , s m o o t h ) × 100 , Wherein, Pi,smoothFor the scoring in i-th standard deviation interval of the stroke ride comfort, fi,smoothFor standard deviation frequency in i-th standard deviation interval.
CN201610066136.1A 2016-01-29 2016-01-29 Driving behavior analysis method and evaluation system based on vehicle-mounted data CN105730450B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201610066136.1A CN105730450B (en) 2016-01-29 2016-01-29 Driving behavior analysis method and evaluation system based on vehicle-mounted data

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201610066136.1A CN105730450B (en) 2016-01-29 2016-01-29 Driving behavior analysis method and evaluation system based on vehicle-mounted data

Publications (2)

Publication Number Publication Date
CN105730450A true CN105730450A (en) 2016-07-06
CN105730450B CN105730450B (en) 2018-01-02

Family

ID=56248049

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201610066136.1A CN105730450B (en) 2016-01-29 2016-01-29 Driving behavior analysis method and evaluation system based on vehicle-mounted data

Country Status (1)

Country Link
CN (1) CN105730450B (en)

Cited By (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106240571A (en) * 2016-08-03 2016-12-21 东软集团股份有限公司 Driving behavior analysis method and apparatus
CN106314438A (en) * 2016-08-15 2017-01-11 西北工业大学 Method and system for detecting abnormal track in driver driving track
CN106564503A (en) * 2016-11-08 2017-04-19 交通运输部公路科学研究所 Method and device for determining behavior information of generation of abnormal driving behaviors
CN106585635A (en) * 2016-11-25 2017-04-26 东软集团股份有限公司 Driving behavior scoring method and device
CN107123173A (en) * 2017-04-25 2017-09-01 百度在线网络技术(北京)有限公司 For the method and apparatus for the transport condition for monitoring unmanned vehicle
CN107161153A (en) * 2017-06-16 2017-09-15 北京车薄荷科技有限公司 A kind of driving behavior methods of marking and device
CN107341864A (en) * 2017-06-07 2017-11-10 华东师范大学 The evaluation system of driver's driving behavior is analyzed by vehicle bus recording equipment
CN109034589A (en) * 2018-07-18 2018-12-18 南斗六星系统集成有限公司 A kind of driving behavior evaluation method and system based on big data analysis
CN109229108A (en) * 2018-08-07 2019-01-18 武汉理工大学 A kind of driving behavior safe evaluation method based on driving fingerprint

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20040153362A1 (en) * 1996-01-29 2004-08-05 Progressive Casualty Insurance Company Monitoring system for determining and communicating a cost of insurance
JP2004234260A (en) * 2003-01-29 2004-08-19 Hitachi Ltd Method for diagnosing safe driving, method and device for diagnosing fuel saving driving, safe driving diagnosis program, and fuel saving driving diagnosis program
JP2006243856A (en) * 2005-03-01 2006-09-14 Hitachi Ltd Operation diagnosis method and its device
CN101870293A (en) * 2009-04-24 2010-10-27 南京理工大学 Vehicle driving state evaluating method based on road-switching behavior detection
CN102044095A (en) * 2010-09-10 2011-05-04 深圳市航天星网通讯有限公司 Personal driving behaviour analysis management control system
CN102428504A (en) * 2009-05-20 2012-04-25 欧宝士株式会社 Driving assistance method and device
CN104802737A (en) * 2015-03-25 2015-07-29 清华大学 Mobile phone based vehicle abnormality driving behavior detection method

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20040153362A1 (en) * 1996-01-29 2004-08-05 Progressive Casualty Insurance Company Monitoring system for determining and communicating a cost of insurance
JP2004234260A (en) * 2003-01-29 2004-08-19 Hitachi Ltd Method for diagnosing safe driving, method and device for diagnosing fuel saving driving, safe driving diagnosis program, and fuel saving driving diagnosis program
JP2006243856A (en) * 2005-03-01 2006-09-14 Hitachi Ltd Operation diagnosis method and its device
CN101870293A (en) * 2009-04-24 2010-10-27 南京理工大学 Vehicle driving state evaluating method based on road-switching behavior detection
CN102428504A (en) * 2009-05-20 2012-04-25 欧宝士株式会社 Driving assistance method and device
CN102044095A (en) * 2010-09-10 2011-05-04 深圳市航天星网通讯有限公司 Personal driving behaviour analysis management control system
CN104802737A (en) * 2015-03-25 2015-07-29 清华大学 Mobile phone based vehicle abnormality driving behavior detection method

Cited By (14)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106240571A (en) * 2016-08-03 2016-12-21 东软集团股份有限公司 Driving behavior analysis method and apparatus
CN106240571B (en) * 2016-08-03 2019-01-25 东软集团股份有限公司 Driving behavior analysis method and apparatus
CN106314438A (en) * 2016-08-15 2017-01-11 西北工业大学 Method and system for detecting abnormal track in driver driving track
CN106314438B (en) * 2016-08-15 2018-09-25 西北工业大学 The detection method and system of abnormal track in a kind of driver driving track
CN106564503A (en) * 2016-11-08 2017-04-19 交通运输部公路科学研究所 Method and device for determining behavior information of generation of abnormal driving behaviors
CN106564503B (en) * 2016-11-08 2019-03-08 交通运输部公路科学研究所 The behavioural information for generating abnormal driving behavior determines method and device
CN106585635B (en) * 2016-11-25 2019-05-10 东软集团股份有限公司 Driving behavior methods of marking and device
CN106585635A (en) * 2016-11-25 2017-04-26 东软集团股份有限公司 Driving behavior scoring method and device
CN107123173A (en) * 2017-04-25 2017-09-01 百度在线网络技术(北京)有限公司 For the method and apparatus for the transport condition for monitoring unmanned vehicle
CN107341864A (en) * 2017-06-07 2017-11-10 华东师范大学 The evaluation system of driver's driving behavior is analyzed by vehicle bus recording equipment
CN107161153A (en) * 2017-06-16 2017-09-15 北京车薄荷科技有限公司 A kind of driving behavior methods of marking and device
CN107161153B (en) * 2017-06-16 2019-11-29 重庆途安信息科技有限公司 A kind of driving behavior methods of marking and device
CN109034589A (en) * 2018-07-18 2018-12-18 南斗六星系统集成有限公司 A kind of driving behavior evaluation method and system based on big data analysis
CN109229108A (en) * 2018-08-07 2019-01-18 武汉理工大学 A kind of driving behavior safe evaluation method based on driving fingerprint

Also Published As

Publication number Publication date
CN105730450B (en) 2018-01-02

Similar Documents

Publication Publication Date Title
Kamble et al. Development of real-world driving cycle: Case study of Pune, India
Thiemann et al. Estimating acceleration and lane-changing dynamics from next generation simulation trajectory data
Toledo et al. Modeling duration of lane changes
JP3044025B1 (en) That the analysis of driving tendency operation management system and its constituent devices
Moritz Adult bicyclists in the United States: characteristics and riding experience in 1996
US8706416B2 (en) System and method for determining a vehicle route
Martinez et al. Driving style recognition for intelligent vehicle control and advanced driver assistance: A survey
Davis Relating severity of pedestrian injury to impact speed in vehicle-pedestrian crashes: Simple threshold model
Coelho et al. Effect of roundabout operations on pollutant emissions
Araújo et al. Driving coach: A smartphone application to evaluate driving efficient patterns
Engel et al. Comparing benchmark methodologies for police-citizen contacts: Traffic stop data collection for the Pennsylvania State Police
Samuel et al. Automotive test drive cycles for emission measurement and real-world emission levels-a review
JP4469297B2 (en) Driving diagnosis method and apparatus
Ericsson Independent driving pattern factors and their influence on fuel-use and exhaust emission factors
BRPI0520270B1 (en) Evaluation method of at least one individual
CN103234763B (en) System and method for quantitatively evaluating unmanned vehicles
DE112010003678T5 (en) Traffic evaluation system, vehicle mounted machine and information processing center
Treiber et al. How much does traffic congestion increase fuel consumption and emissions? Applying a fuel consumption model to the NGSIM trajectory data
Lin et al. Regional driving characteristics, regional driving cycles
CN104732785A (en) Driving behavior analyzing and reminding method and system
Esteves-Booth et al. A review of vehicular emission models and driving cycles
US10467824B2 (en) Method for determining driving characteristics of a vehicle and vehicle analyzing system
CN103531042A (en) Rear-end collision pre-warning method based on driver types
Hallmark et al. Characterizing on-road variables that affect passenger vehicle modal operation
Zhao et al. An investigation of the relationship between the driving behavior questionnaire and objective measures of highway driving behavior

Legal Events

Date Code Title Description
C06 Publication
PB01 Publication
C10 Entry into substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant