CN105730450B - Driving behavior analysis method and evaluation system based on vehicle-mounted data - Google Patents
Driving behavior analysis method and evaluation system based on vehicle-mounted data Download PDFInfo
- Publication number
- CN105730450B CN105730450B CN201610066136.1A CN201610066136A CN105730450B CN 105730450 B CN105730450 B CN 105730450B CN 201610066136 A CN201610066136 A CN 201610066136A CN 105730450 B CN105730450 B CN 105730450B
- Authority
- CN
- China
- Prior art keywords
- stroke
- scoring
- data
- duration
- speed
- 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.)
- Active
Links
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT 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
- B60W40/00—Estimation 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
- B60W40/08—Estimation 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
- B60W40/09—Driving style or behaviour
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Mathematical Physics (AREA)
- Transportation (AREA)
- Mechanical Engineering (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention discloses a kind of driving behavior analysis method based on vehicle-mounted data, including:The driving data of real-time collection vehicle;Invalid driving data is deleted according to bitmask;It is deleted or modified for abnormal data;Being described property of driving data is counted, obtains statistics driving data;By the analytic hierarchy process (AHP) of group decision, the weight distribution of evaluation index is obtained;By the method for expert estimation, trip times scoring is obtained;By principle of comforming, the scoring of the ride comfort of the duration of stroke, the average speed of stroke and stroke is obtained;According to the weight distribution of evaluation index and scoring, the rating matrix of driving data is obtained.The invention also discloses a kind of driving behavior evaluation system based on vehicle-mounted data.The driving behavior analysis method and evaluation system based on vehicle-mounted data obtain the weight of driving data by the analytic hierarchy process (AHP) of group decision, and the scoring of driving data is obtained by principle of comforming, and driving behavior that can be to user accurately analyze and evaluate.
Description
Technical field
The present invention relates to vehicle drive assay technical field, particularly relates to a kind of driving behavior based on vehicle-mounted data
Analysis method and evaluation system.
Background technology
With the continuous development of mobile Internet and technology of Internet of things, increasing vehicle passes through preceding dress or the side filled afterwards
Formula adds the camp of car networking, and generates the related data largely based on information such as vehicle location, performances, passes through observation
And these data are analyzed, we can make specific evaluation to the driving behavior of user, and so, vehicle can not only be made
Rational standard or suggestion are provided with the driving of, user, and is advantageous to the differential management of related industry.Such as:Automobile is protected
Dangerous industry, the related datas of these vehicles bring new opportunity to keeping reforming of fixing a price of vehicle insurance.Specially:By these data
Reasonably analyzed, and study its correlation with information of being in danger, can be finally that vehicle insurance price provides rational driving row
To evaluate the factor, so as to more reasonably formulate the price of the vehicle insurance based on user's driving behavior.
At present, domestic correlative study focuses primarily upon the identification of the bad steering behavior based on car networking data and pre-
It is alert, and the economic Journal of Sex Research of driving behavior.Such as:Patent document 201220002851.6 discloses a kind of driver and drives warp
Ji property evaluation system, the document is by the information of the fuel consumption values of acquisition, and most economical instantaneous oil consumption is calculated using MAP etc.
Value, and the economy grade of driving behavior is obtained compared with actual instantaneous fuel consumption values, and inverse goes out to characterize most economical drive
Sail the advisory information of behavior.But lack be directed to the evaluation method of driving behavior in itself at present.
The content 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 can carry out accurately analyzing and evaluating by driving behavior of the driving information of vehicle to user.
Based on the above-mentioned purpose driving behavior analysis method provided by the invention based on vehicle-mounted data, including:
The driving data of real-time collection vehicle, meanwhile, the work when OBD boxes in vehicle can gather to each driving data
Make state and generate a bitmask;
The bitmask generated according to OBD boxes, judge whether the driving data of collection is effective, and delete invalid driving number
According to;
Search and analyze abnormal data, the regularity occurred according to abnormal data, deleted or repaiied for abnormal data
Change;
Being described property of driving data is counted, obtains statistics driving data, wherein, the statistics driving data is divided into row
Journey statistics and user's statistics, and stroke statistics includes:The duration of stroke, the period of stroke, stroke are averaged
Speed, travel speed variance and stroke acceleration variance;User's statistics includes:User's trip number, user averagely travel
Duration and user's average travel;
By the analytic hierarchy process (AHP) of group decision, the weight distribution of evaluation index is obtained, wherein, the evaluation index is respectively
Count in driving data:The period of stroke, the duration of stroke, the ride comfort of the average speed of stroke and stroke;
By the method for expert estimation, trip times scoring is obtained;By principle of comforming, obtain stroke duration and score, OK
The average speed scoring of journey and the ride comfort of stroke score;
According to the scoring of the trip times of acquisition, the scoring of stroke duration, the average speed scoring of stroke and the ride comfort of stroke
Scoring and the weight distribution of corresponding evaluation index, the rating matrix of driving data is calculated.
Preferably, the step of driving data of collection vehicle in real time includes:
Frequency acquisition threshold value is set, judges whether the frequency of driving data collection exceedes the frequency acquisition threshold value;
If so, frequency acquisition is then reduced, until being less than the frequency acquisition threshold value;
If it is not, then keep frequency acquisition constant.
Preferably, also include after described the step of being counted to being described property of driving data:
According to user's statistics, setting user trip frequency threshold value and user travel duration threshold value, whether judge vehicle
For the vehicle of automatic start-stop;
If user averagely travels duration and travels duration threshold value less than user, and user goes on a journey number more than user's trip number
Threshold value, then the relevant driving data of these vehicles is filtered out, and individually analyzed and calculated;
Otherwise, it is constant to retain all data.
Further, the step of acquisition evaluation criterion weight distribution includes:
There is m policymaker to evaluate the weight of 4 evaluation indexes, wherein, k-th of policymaker is evaluated 4
The evaluation vector of index importance is:
ωk=(ω1 k,ω2 k,ω3 k,ω4 k), (k=1,2 ... m)
D is used againstTo represent the degree of closeness of s-th of policymaker and t-th of policymaker, and
Thus, the degree of closeness for obtaining k-th of policymaker and remaining policymaker is dk, and
Further, the decision weights σ of k-th of policymaker is obtainedk, and
Finally, the weight distribution for obtaining 4 evaluation indexes is ω, and
Further, the step of scoring of the acquisition evaluation index includes:
Using the method for expert estimation, the scoring P of trip times is obtainedi,tf(i=1,2 ... n), wherein, n is the number of stroke
Amount;
Stroke duration is divided into multiple duration sections from 0-120min, scoring of the stroke duration more than 120min is 0;
The duration section where maximum frequency is found, and it is 100 points to set scoring, the scoring in remaining duration section is Pi,time, and
Pi,time=fi,time/max(fi,time) × 100, wherein, Pi,timeIt is stroke duration in i-th of duration section
Scoring, fi,timeFor frequency of the stroke duration in i-th of duration section;
The average speed of stroke is divided into multiple speed intervals from 0-120km/h, the average speed of stroke exceedes
120km/h scoring is 0;The speed interval where maximum frequency is found, and it is 100 points to set scoring, remaining speed interval
Scoring be Pi,speed, and
Pi,speed=fi,speed/max(fi,speed) × 100, wherein, Pi,speedFor stroke average speed in i-th of speed
Scoring in section, fi,speedFor frequency of the average speed in i-th of speed interval of stroke;
Using the acceleration standard deviation of stroke as reference, the acceleration standard deviation of stroke is arranged to multiple standard deviation sections,
Obtain the scoring P of stroke ride comforti,smooth, and
Wherein, Pi,smoothFor scoring of the stroke ride comfort in i-th of standard deviation section, fi,smoothIt is that standard deviation is marked at i-th
Frequency in accurate poor section.
Present invention also offers a kind of driving behavior evaluation system based on vehicle-mounted data, including:
Data acquisition module, for the driving data of real-time collection vehicle, and obtain the OBD boxes in vehicle and driven to each
The bitmask that working condition when sailing data acquisition generates;
Data cleansing module, for the bitmask generated according to OBD boxes, judge whether the driving data of collection is effective,
And delete invalid driving data;It is additionally operable to search and analyze abnormal data, the regularity occurred according to abnormal data, for different
Regular data is deleted or modified;
Data statistics module, for being counted to being described property of driving data, statistics driving data is obtained, wherein, it is described
Statistics driving data is divided into stroke statistics and user's statistics, wherein, stroke statistics includes:The duration of stroke,
The period of stroke, the average speed of stroke, travel speed variance and stroke acceleration variance;User's statistics includes:User
Trip number, user averagely travel duration and user's average travel;
Weight evaluation module, for the analytic hierarchy process (AHP) by group decision, the weight distribution of evaluation index is obtained, wherein,
Evaluation index is in statistics driving data:The period of stroke, the duration of stroke, the ride comfort of the average speed of stroke and stroke;
Data grading module, for the method by comform principle and expert estimation, obtain the scoring of evaluation index;
Computing module, for the weight distribution according to evaluation index and scoring, the rating matrix of driving data is calculated.
Preferably, the data acquisition module is additionally operable to set frequency acquisition threshold value, judges the frequency of driving data collection
Whether the frequency acquisition threshold value is exceeded;
If so, frequency acquisition is then reduced, until being less than the frequency acquisition threshold value;
If it is not, then keep frequency acquisition constant.
Preferably, the data cleansing module is additionally operable to according to user's statistics, setting user go on a journey frequency threshold value and
User travel duration threshold value, judge vehicle whether be automatic start-stop vehicle;
If user averagely travels duration and travels duration threshold value less than user, and user goes on a journey number more than user's trip number
Threshold value, then the relevant driving data of these vehicles is filtered out, and individually analyze and calculate;
Otherwise, it is constant to retain all data.
Further, m policymaker carries out the weight of 4 evaluation indexes in the analytic hierarchy process (AHP) of the group decision
Evaluation, the weight evaluation module are additionally operable to by calculating evaluation vector of k-th of policymaker to 4 evaluation index importance
For:
ωk=(ω1 k,ω2 k,ω3 k,ω4 k), (k=1,2 ... m)
D is used againstTo represent the degree of closeness of s-th of policymaker and t-th of policymaker, and
Thus, the degree of closeness for obtaining k-th of policymaker and remaining policymaker is dk, and
Further, the decision weights σ of k-th of policymaker is obtainedk, and
Finally, the weight for obtaining 4 evaluation indexes is ω, and
Further, the data grading module is additionally operable to:
Using the method for expert estimation, the scoring P of trip times is obtainedi,tf(i=1,2 ... n), wherein, n is the number of stroke
Amount;
Stroke duration is divided into multiple duration sections from 0-120min, scoring of the stroke duration more than 120min is 0;
The duration section where maximum frequency is found, and it is 100 points to set scoring, the scoring in remaining duration section is Pi,time, and
Pi,time=fi,time/max(fi,time) × 100, wherein, Pi,timeIt is stroke duration in i-th of duration section
Scoring, fi,timeFor frequency of the stroke duration in i-th of duration section;
The average speed of stroke is divided into multiple speed intervals from 0-120km/h, the average speed of stroke exceedes
120km/h scoring is 0;The speed interval where maximum frequency is found, and it is 100 points to set scoring, remaining speed interval
Scoring be Pi,speed, and
Pi,speed=fi,speed/max(fi,speed) × 100, wherein, Pi,speedFor stroke average speed in i-th of speed
Scoring in section, fi,speedFor frequency of the average speed in i-th of speed interval of stroke;
Using the acceleration standard deviation of stroke as reference, the acceleration standard deviation of stroke is arranged to multiple standard deviation sections,
Obtain the scoring P of stroke ride comforti,smooth, and
Wherein, Pi,smoothFor scoring of the stroke ride comfort in i-th of standard deviation section, fi,smoothIt is that standard deviation is marked at i-th
Frequency in accurate poor section.
From the above it can be seen that driving behavior analysis method and evaluation system provided by the invention based on vehicle-mounted data
System obtains effective driving data by the cleaning to driving data, is then driven by using the analytic hierarchy process (AHP) of group decision
The weight distribution of data is sailed, and the scoring of driving data is obtained using the method for comform principle and expert estimation, by driving number
According to weight distribution and scoring can obtain accurate analysis and evaluation to driving behavior.
Brief description of the drawings
Fig. 1 is the flow chart of the embodiment of the driving behavior analysis method provided by the invention based on vehicle-mounted data;
Fig. 2 is the structure chart of the embodiment of the driving behavior evaluation system provided by the invention based on vehicle-mounted data.
Embodiment
For the object, technical solutions and advantages of the present invention are more clearly understood, below in conjunction with specific embodiment, and reference
Accompanying drawing, the present invention is described in more detail.
It is the stream of the embodiment of the driving behavior analysis method provided by the invention based on vehicle-mounted data shown in reference picture 1
Cheng Tu.The driving behavior analysis method based on vehicle-mounted data, including:
Step 101, the driving data of real-time collection vehicle, meanwhile, the OBD boxes in vehicle can be adopted to each driving data
Working condition during collection generates a bitmask.
Wherein, the driving data is by the gps data on automobile, engine related data and G-sensor data etc.
The data acquisition relevant with traveling obtains in vehicle.The driving data includes the Various types of data being related to during traveling, example
Such as:Time residing for the distance of each run, travel speed, acceleration and stroke etc..The OBD boxes refer to vehicle-mounted examine
Disconnected system, it can monitor automobile engine and the working condition of automobilism at any time, and collect the related information of storage.OBD
When box gathers each driving data, can one be generated to the working condition of the data at that time and tentatively judge whether the data have
The bitmask of effect.
Step 102, according to OBD boxes generate bitmask, judge collection driving data it is whether effective, and delete it is invalid
Driving data.
For each driving data, bitmask corresponding with the driving data is read, according to the judgment principle of bitmask, directly
Connect and judge whether the driving data is valid data, the driving data is invalid, deletes the driving data if finding, should if finding
Driving data is effective, then retains the driving data.
Step 103, search and analyze abnormal data, the regularity occurred according to abnormal data, carried out for abnormal data
It is deleted or modified.
Wherein, the abnormal data refers to judge the obvious data for not meeting actual conditions according to convention.Such as:At one section
In the run-length data collected, it is found that the quantity for the data that speed is 0 has exceeded a certain proportion threshold value of total data, namely occupy
Ratio reached higher degree, then it is considered that the data do not have statistical significance, should delete.The proportion threshold value
Can be according to the actual conditions respective settings of different pieces of information.And for example:In another stroke gps data collected, GPS numbers are found
According to being continuous, but the speed of some position is suddenly 0, and is promptly restored to original velocity amplitude, that is, the change of the speed
Speed is beyond the urgent threshold value accelerated with emergency deceleration, then can be determined that, the data are probably because hardware reason causes
Interference data, at this moment, make it smooth using the method for sliding mean filter in the hop region of the data, in this way, it is possible to
So that abnormal data is changed into effective driving data.
Step 104, being described property of driving data is counted, obtains statistics driving data, wherein, the statistics drives number
According to being divided into stroke statistics and user's statistics, wherein, stroke statistics includes:The duration of stroke, the period of stroke,
Average speed, travel speed variance and the stroke acceleration variance of stroke;User's statistics includes:User's trip number, use
Family averagely travels duration and user's average travel.
Wherein, descriptive statistic refers to driving data concluding corresponding statistical form respectively according to different mode classifications
In.The stroke statistics refers to respectively to count every section of stroke the duration of corresponding stroke, the period of stroke, stroke
The data such as average speed, travel speed variance and stroke acceleration variance.User's statistics is to be based on stroke statistical number
On the basis of, for the driving behavior of same user, respectively corresponding counting user trip number, user averagely travel duration and
The data such as user's average travel.
Step 105, by the analytic hierarchy process (AHP) of group decision, the weight distribution of evaluation index is obtained, wherein, the evaluation refers to
Mark is respectively in statistics driving data:The period of stroke, the duration of stroke, the ride comfort of the average speed of stroke and stroke.
Wherein, the analytic hierarchy process (AHP) of the group decision is a kind of by multiple policymaker, using different levels to a certain
The method that target is evaluated, this method can be obtained more reliable, stably by then passing through the overall merit of multiple policymaker
Evaluation result.Specific flow is that each policymaker has different weights respectively, and then each policymaker is to all mesh
Mark, the i.e. ride comfort of the period of stroke, the duration of stroke, the average speed of stroke and stroke, are evaluated, so, often respectively
One target can obtain the different evaluation of the policymaker of different weights, finally accumulate evaluation result, it becomes possible to obtain relative
Reliable evaluation, or the weight as different target.
Step 106, by the method for expert estimation, trip times scoring is obtained;By principle of comforming, obtain stroke when
The scoring of the ride comfort of long scoring, the average speed scoring of stroke and stroke.
According to the method for comform principle and expert estimation, by counting the feature of driving data, respectively to different evaluations
Index is given a mark, and finally obtains the scoring of all evaluation indexes.
Step 107, according to the scoring of the trip times of acquisition, the scoring of stroke duration, the average speed scoring of stroke and stroke
Ride comfort scoring and corresponding evaluation index weight distribution, the rating matrix of driving data is calculated.
The weight distribution of evaluation index is included into weight vectors according to certain order, then by the scoring of evaluation index
Scoring vector is included according to same order, weight vectors and scoring multiplication of vectors is made, finally obtains the scoring of evaluation index
Matrix, namely the specific analysis result to different evaluation index in driving data.
From above-described embodiment, screening and place of the driving behavior analysis method based on vehicle-mounted data first by data
Reason, has obtained accurately and effectively driving data.The evaluation index of selected driving data, the weight of evaluation index is then obtained respectively
Distribution and scoring, the accurate evaluation to user's driving behavior can finally be calculated, and this is evaluated as the specific data of quantization,
Be advantageous to that driving behavior is analyzed and records.
Further, the driving behavior analysis method based on vehicle-mounted data is not limited to the implementation step of above-described embodiment
Suddenly, can be adjusted correspondingly according to the actual needs, such as:The order of step 105 and step 106 can be exchanged arbitrarily.
In some preferred embodiments, include in the step 101 the step of the driving data of real-time collection vehicle:
For the respective feature of different vehicle, corresponding frequency acquisition threshold value is set respectively, when driving for real-time collection vehicle
When sailing data, judge whether the frequency of driving data collection exceedes the frequency acquisition threshold value;
If so, frequency acquisition is then reduced, until being less than the frequency acquisition threshold value;
If it is not, then keep frequency acquisition constant.
When vehicle is in during traveling, if the collection to the driving data of vehicle may incite somebody to action more than certain frequency
Certain interference can be caused to the normal driving of user, and this absolutely not allows, it is necessary to ensure the driving peace of user first
Entirely.It is necessary to set the frequency acquisition threshold value of a safety so that the collection of driving data will not be to the normal use of user
Have any impact.So, the present invention is exactly based on the frequency acquisition for setting a restriction, namely frequency acquisition threshold value, can
The frequency that driving data gathers is limited in safe and reliable scope, has ensured the normal driving of user.
As the preferred embodiment of the present invention, gone back after described the step of being counted to being described property of driving data
Including:
According to user's statistics, setting user trip frequency threshold value and user travel duration threshold value, whether judge vehicle
For the vehicle of automatic start-stop;
If user averagely travels duration and travels duration threshold value less than user, and user goes on a journey number more than user's trip number
Threshold value, then the relevant driving data of these vehicles is filtered out, and individually analyze and calculate;
Otherwise, it is constant to retain all data.
Due to employing the correlation technique of engine automatic start-stop in many high-end vehicles, and the automatic start-stop of engine produces
Raw driving data and the driving data of non-automatic start and stop have larger difference, therefore, will if they are handled and analyzed together
Larger interference and error can be produced so that analysis result is inaccurate.Therefore, it is necessary to which this kind of vehicle is distinguished.Adopt
Have stroke duration shorter with the vehicle of engine automatic start-stop technology and the characteristics of the frequency is more, therefore according to this feature
The characteristic of first class vehicle, sets user's trip frequency threshold value respectively and user travels duration threshold value.According to what is obtained in step 104
User's statistics, the user of statistics is averagely travelled into duration and user goes on a journey number compared with corresponding threshold value.If
User averagely travels duration and travels duration threshold value less than user, and user goes on a journey number more than user's trip frequency threshold value, then
Represent, the vehicle employs engine automatic start-stop technology, driving data corresponding to this kind of vehicle is distinguished and
Individually analysis and processing.In such manner, it is possible to greatly improve the accuracy and reliability of driving behavior analysis.
Further, the analytic hierarchy process (AHP) by group decision, the step 105 for obtaining the weight distribution of evaluation index are wrapped
Include:
It is assumed that there is m policymaker to evaluate the weight of 4 evaluation indexes, wherein, k-th of policymaker is to 4
The evaluation vector of evaluation index importance is:
ωk=(ω1 k,ω2 k,ω3 k,ω4 k), (k=1,2 ... m), wherein, ω1、ω2、ω3、ω4Respectively 4 are corresponded to comment
The weighted value of valency index.
D is used againstTo represent the degree of closeness of s-th of policymaker and t-th of policymaker, and
Thus, the degree of closeness for obtaining k-th of policymaker and remaining policymaker is dk, and
Further, the decision weights σ of k-th of policymaker is obtainedk, and
The weight distribution for finally giving 4 evaluation indexes is ω, and
Here, the present invention is when using analytic hierarchy process (AHP) based on group decision, close between different decision-makings by calculating
Degree comes the weight of respective settings policymaker, namely the significance level of policymaker itself.Specifically, k-th of policymaker and residue
The degree of closeness d of policymakerkValue it is smaller, then it represents that the degree of the decision-making of the policymaker close to group decision-making is bigger, therefore,
The significance level obtained in colony is also higher, that is, the weight of the policymaker is also bigger.In such manner, it is possible to point for passing through group decision
Analysis method obtains the weight that more accurately all policymaker go out to 4 evaluation index decision-makings, namely obtains the power of evaluation index
Redistribution.
Further, the step 106 includes:
Using the method for expert estimation, the scoring P of trip times is obtainedi,tf(i=1,2 ... n), wherein, n is the number of stroke
Amount.
Wherein, the method for expert estimation is existing method, can be by the rule of data with existing to corresponding existing number
According to being given a mark.
Stroke duration is divided into multiple duration sections from 0-120min, scoring of the stroke duration more than 120min is 0;
The duration section where maximum frequency is found, and it is 100 points to set scoring, the scoring in remaining duration section is Pi,time, and
Pi,time=fi,time/max(fi,time) × 100, wherein, Pi,timeIt is stroke duration in i-th of duration section
Scoring, fi,timeFor frequency of the stroke duration in i-th of duration section.
Wherein, according to the relevant regulations of traffic law, the time that single drives is fatigue driving more than 120min, because
This, is set as 0 by scoring of the stroke duration more than 120min.The frequency refers to the driving stroke duration of collection dividing difference
Behind duration section, in different sections, the number of the driving data in the duration section, namely the number occurred are checked.Described stroke
During point multiple duration sections, it can be divided accordingly according to the needs of analysis, can be with that is, when needing Accurate Analysis
So that duration section is shorter, when exact requirements are relatively low, it can accordingly cause that duration section is elongated, it is possible to increase data analysis
Speed.
The average speed of stroke is divided into multiple speed intervals from 0-120km/h, the average speed of stroke exceedes
120km/h scoring is 0;The speed interval where maximum frequency is found, and it is 100 points to set scoring, remaining speed interval
Scoring be Pi,speed, and
Pi,speed=fi,speed/max(fi,speed) × 100, wherein, Pi,speedFor stroke average speed in i-th of speed
Scoring in section, fi,speedFor frequency of the average speed in i-th of speed interval of stroke.
It is similar with stroke duration, it is hypervelocity when travel speed is more than 120km/h, now scoring is 0.
Using the acceleration standard deviation of stroke as reference, the acceleration standard deviation of stroke is arranged to multiple standard deviation sections,
Obtain the scoring P of stroke ride comforti,smooth, and
Wherein, Pi,smoothFor scoring of the stroke ride comfort in i-th of standard deviation section, fi,smoothIt is that standard deviation is marked at i-th
Frequency in accurate poor section.
Wherein, the acceleration standard deviation of the stroke is travel speed variance and acceleration variance in statistics
Calculate what is obtained.The stroke ride comfort refers to the change frequency of automobile running status in the process of moving, namely traveling is steady
It is qualitative.When vehicle stationary or when at the uniform velocity travelling, stroke ride comfort is best, on the contrary, anxious accelerate, anxious slow down and zig zag can all drop
Low row journey ride comfort.
The final scoring of each evaluation index both can be by the way that the scoring addition calculation in all sections be obtained, can also be right
It carries out percentage, for example, the evaluation of stroke duration is divided into 10 different duration sections, then the total full marks of stroke duration should
It is 1000 points, so, the appraisal result being finally calculated divided by 10, then the total score of stroke duration is converted into full marks 100,
Percentage is carried out to scoring.So, the scoring to forming the period is realized by the method for expert estimation, passes through principle of comforming
The scoring of the ride comfort of the duration of stroke, the average speed of stroke and stroke is calculated respectively.Make it possible to be driven according to difference
The characteristics of sailing data, obtain the accurate scoring of corresponding evaluation index.
Preferably, in vehicle insurance industry, also include after obtaining rating matrix:By evaluation result and the history of vehicle Claims Resolution data
Contrasted and analyzed, evaluation method is further optimized according to history Claims Resolution data, finally obtains and more meets reality
The evaluation method of Claims Resolution so that the driving behavior analysis method based on vehicle-mounted data is more accurate.
It is the knot of the embodiment of the driving behavior evaluation system provided by the invention based on vehicle-mounted data shown in reference picture 2
Composition.The shown driving behavior evaluation system based on vehicle-mounted data includes:
Data acquisition module 201, for the driving data of real-time collection vehicle, and the OBD boxes in vehicle is obtained to every
The bitmask of working condition generation during individual driving data collection.
Data cleansing module 202, whether for the bitmask generated according to OBD boxes, judging the driving data of collection has
Effect, and delete invalid driving data;It is additionally operable to search and analyze abnormal data, the regularity occurred according to abnormal data, pin
Abnormal data is deleted or modified.
Data statistics module 203, for being counted to being described property of driving data, statistics driving data is obtained, wherein, institute
State statistics driving data and be divided into stroke statistics and user's statistics, wherein, stroke statistics includes:Stroke when
Length, the period of stroke, the average speed of stroke, travel speed variance and stroke acceleration variance;User's statistics includes:With
Family trip number, user averagely travel duration and user's average travel.
Weight evaluation module 204, for the analytic hierarchy process (AHP) by group decision, the weight distribution of evaluation index is obtained, its
In, evaluation index is in statistics driving data:The period of stroke, the smooth-going of the duration of stroke, the average speed of stroke and stroke
Property.
Data grading module 205, for the method by comform principle and expert estimation, obtain the scoring of evaluation index.
Computing module 206, for the weight distribution according to evaluation index and scoring, the scoring square of driving data is calculated
Battle array.
From above-described embodiment, the driving behavior evaluation system based on vehicle-mounted data passes through the data acquisition module
Block 201 realizes the collection of driving data, and the screening and removing of driving data are realized by data cleansing module 202, is then passed through
The weight evaluation module 204 and the data grading module 205 obtain weight distribution and the scoring of driving data respectively, most
Afterwards, the rating matrix of driving data can be calculated by the computing module 206.By period, the stroke of selecting stroke
Evaluation index as driving data of duration, the average speed of stroke and the ride comfort of stroke, and corresponding analyzing and processing,
Make it possible to the driving behavior to user accurately analyze and evaluate, and finally give the evaluation result quantified.
In some preferred embodiments, the data acquisition module 201 is additionally operable to set frequency acquisition threshold value, judges to drive
Whether the frequency for sailing data acquisition exceedes the frequency acquisition threshold value;
If so, frequency acquisition is then reduced, until being less than the frequency acquisition threshold value;
If it is not, then keep frequency acquisition constant.
The data acquisition module 201 can ensure that the collection to driving data does not interfere with the normal driving of user, enter
And bring potential safety hazard to driving.So, the safe and reliable of the driving behavior evaluation system based on vehicle-mounted data is improved
Property.
In presently preferred embodiment, the data cleansing module 202 is additionally operable to according to user's statistical number
Travel duration threshold value according to go on a journey frequency threshold value and user of, setting user, judge vehicle whether be automatic start-stop vehicle;
If user averagely travels duration and travels duration threshold value less than user, and user goes on a journey number more than user's trip number
Threshold value, then the relevant driving data of these vehicles is filtered out, and individually analyze and calculate;
Otherwise, it is constant to retain all data.
So, the data cleansing module 202 is further mutual by the vehicle of automatic start-stop and the vehicle of non-automatic start and stop
Make a distinction so that the evaluation to driving data is more accurate.
Further, the evaluation procedure of the weight evaluation module 204 is:
There is m policymaker to evaluate the weight of 4 evaluation indexes, wherein, k-th of policymaker is evaluated 4
The evaluation vector of index importance is:
ωk=(ω1 k,ω2 k,ω3 k,ω4 k), (k=1,2 ... m)
D is used againstTo represent the degree of closeness of s-th of policymaker and t-th of policymaker, and
Thus, the degree of closeness for obtaining k-th of policymaker and remaining policymaker is dk, and
Further, the decision weights σ of k-th of policymaker is obtainedk, and
The weight for finally giving 4 evaluation indexes is ω, and
So, can be very big by judging the degree of closeness of different policymaker come the weight of respective settings difference policymaker
Improve the accuracy of group decision.It is of course also possible to the masses of all policymaker are arranged to identical.
Further, the scoring step of the data grading module 205 is:
Using the method for expert estimation, the scoring P of trip times is obtainedi,tf(i=1,2 ... n), wherein, n is the number of stroke
Amount;
Stroke duration is divided into multiple duration sections from 0-120min, scoring of the stroke duration more than 120min is 0;
The duration section where maximum frequency is found, and it is 100 points to set scoring, the scoring in remaining duration section is Pi,time, and
Pi,time=fi,time/max(fi,time) × 100, wherein, Pi,timeIt is stroke duration in i-th of duration section
Scoring, fi,timeFor frequency of the stroke duration in i-th of duration section;
The average speed of stroke is divided into multiple speed intervals from 0-120km/h, the average speed of stroke exceedes
120km/h scoring is 0;The speed interval where maximum frequency is found, and it is 100 points to set scoring, remaining speed interval
Scoring be Pi,speed, and
Pi,speed=fi,speed/max(fi,speed) × 100, wherein, Pi,speedFor stroke average speed in i-th of speed
Scoring in section, fi,speedFor frequency of the average speed in i-th of speed interval of stroke;
Using the acceleration standard deviation of stroke as reference, the acceleration standard deviation of stroke is arranged to multiple standard deviation sections,
Obtain the scoring P of stroke ride comforti,smooth, and
Wherein, Pi,smoothFor scoring of the stroke ride comfort in i-th of standard deviation section, fi,smoothIt is that standard deviation is marked at i-th
Frequency in accurate poor section.
According to the data characteristicses of different evaluation index, by comforming, principle scores it respectively, due to trip times
Only with time correlation and it is unrelated with driving data, therefore, trip times are evaluated using the method for expert estimation, main to consider
Influence of the different periods to the physiologic factor and social environmental factor (such as traffic environment etc.) of human body.And remaining evaluation index
It is relevant with driving data, therefore given a mark using principle of comforming, and it is corresponding to carry out according to the different frequencies in different sections
Score calculation.So so that the driving behavior evaluation system based on vehicle-mounted data can obtain more accurately scoring, finally
Improve the accuracy to user's driving behavior evaluation.
Those of ordinary skills in the art should understand that:The discussion of any of the above embodiment is exemplary only, not
It is intended to imply that the scope of the present disclosure (including claim) is limited to these examples;Under the thinking of the present invention, above example
Or can also be combined between the technical characteristic in different embodiments, step can be realized with random order, and exist such as
Many other changes of upper described different aspect of the invention, for simplicity, they are not provided in details.Therefore, it is all
Within the spirit and principles in the present invention, any omission for being made, modification, equivalent substitution, improvement etc., it should be included in the present invention's
Within protection domain.
Claims (8)
- A kind of 1. driving behavior analysis method based on vehicle-mounted data, it is characterised in that including:The driving data of real-time collection vehicle, meanwhile, the work shape when OBD boxes in vehicle can gather to each driving data State generates a bitmask;The bitmask generated according to OBD boxes, judge whether the driving data of collection is effective, and delete invalid driving data;Search and analyze abnormal data, the regularity occurred according to abnormal data, be deleted or modified for abnormal data;Being described property of driving data is counted, obtains statistics driving data, wherein, the statistics driving data is divided into stroke system Count with user's statistics, and stroke statistics includes:The duration of stroke, the period of stroke, stroke average speed, Travel speed variance and stroke acceleration variance;User's statistics includes:User go on a journey number, user averagely travel duration and User's average travel;By the analytic hierarchy process (AHP) of group decision, the weight distribution of evaluation index is obtained, wherein, the evaluation index is respectively to count In driving data:The period of stroke, the duration of stroke, the ride comfort of the average speed of stroke and stroke;By the method for expert estimation, trip times scoring is obtained;By principle of comforming, stroke duration scoring, stroke are obtained Average speed scores and the ride comfort of stroke scores;Scored according to the ride comfort of the scoring of the trip times of acquisition, the scoring of stroke duration, the average speed scoring of stroke and stroke And the weight distribution of corresponding evaluation index, the rating matrix of driving data is calculated;The step of acquisition evaluation criterion weight distribution, includes:There is m policymaker to evaluate the weight of 4 evaluation indexes, wherein, k-th of policymaker is to 4 evaluation indexes The evaluation vector of importance is:ωk=(ω1 k,ω2 k,ω3 k,ω4 k), (k=1,2L m)D is used againstTo represent the degree of closeness of s-th of policymaker and t-th of policymaker, andThus, the degree of closeness for obtaining k-th of policymaker and remaining policymaker is dk, andFurther, the decision weights σ of k-th of policymaker is obtainedk, andFinally, the weight distribution for obtaining 4 evaluation indexes is ω, and
- 2. according to the method for claim 1, it is characterised in that it is described in real time collection vehicle driving data the step of wrap Include:Frequency acquisition threshold value is set, judges whether the frequency of driving data collection exceedes the frequency acquisition threshold value;If so, frequency acquisition is then reduced, until being less than the frequency acquisition threshold value;If it is not, then keep frequency acquisition constant.
- 3. according to the method for claim 1, it is characterised in that described the step of being counted to being described property of driving data it Also include afterwards:According to user's statistics, setting user trip frequency threshold value and user travel duration threshold value, judge whether vehicle is certainly The vehicle of dynamic start and stop;If user averagely travels duration and travels duration threshold value less than user, and user goes on a journey number more than user's trip number threshold Value, then filter out the relevant driving data of these vehicles, and individually analyzed and calculated;Otherwise, it is constant to retain all data.
- 4. according to the method for claim 1, it is characterised in that it is described obtain evaluation index scoring the step of include:Using the method for expert estimation, the scoring P of trip times is obtainedi,tf(i=1,2 ... n), wherein, n is the quantity of stroke;Stroke duration is divided into multiple duration sections from 0-120min, scoring of the stroke duration more than 120min is 0;Find Duration section where maximum frequency, and it is 100 points to set scoring, the scoring in remaining duration section is Pi,time, andPi,time=fi,time/max(fi,time) × 100, wherein, Pi,timeFor scoring of the stroke duration in i-th of duration section, fi,timeFor frequency of the stroke duration in i-th of duration section;The average speed of stroke is divided into multiple speed intervals from 0-120km/h, the average speed of stroke is more than 120km/h's Scoring is 0;The speed interval where maximum frequency is found, and it is 100 points to set scoring, the scoring of remaining speed interval is Pi,speed, andPi,speed=fi,speed/max(fi,speed) × 100, wherein, Pi,speedFor stroke average speed in i-th of speed interval Interior scoring, fi,speedFor frequency of the average speed in i-th of speed interval of stroke;Using the acceleration standard deviation of stroke as reference, the acceleration standard deviation of stroke is arranged to multiple standard deviation sections, obtained The scoring P of stroke ride comforti,smooth, andWherein, Pi,smoothFor scoring of the stroke ride comfort in i-th of standard deviation section, fi,smoothIt is that standard deviation is marked at i-th Frequency in accurate poor section.
- A kind of 5. driving behavior evaluation system based on vehicle-mounted data, it is characterised in that including:Data acquisition module, for the driving data of real-time collection vehicle, and the OBD boxes in vehicle is obtained to each driving number The bitmask generated according to working condition during collection;Data cleansing module, for the bitmask generated according to OBD boxes, judge whether the driving data of collection is effective, and delete Except invalid driving data;It is additionally operable to search and analyze abnormal data, the regularity occurred according to abnormal data, for abnormal number According to being deleted or modified;Data statistics module, for being counted to being described property of driving data, statistics driving data is obtained, wherein, the statistics Driving data is divided into stroke statistics and user's statistics, wherein, stroke statistics includes:Duration, the stroke of stroke Period, average speed, travel speed variance and the stroke acceleration variance of stroke;User's statistics includes:User goes on a journey Number, user averagely travel duration and user's average travel;Weight evaluation module, for the analytic hierarchy process (AHP) by group decision, the weight distribution of evaluation index is obtained, wherein, evaluation Index is in statistics driving data:The period of stroke, the duration of stroke, the ride comfort of the average speed of stroke and stroke;Data grading module, for the method by comform principle and expert estimation, obtain the scoring of evaluation index;Computing module, for the weight distribution according to evaluation index and scoring, the rating matrix of driving data is calculated;There is m policymaker to evaluate the weight of 4 evaluation indexes in the analytic hierarchy process (AHP) of the group decision, the power Weight evaluation module is additionally operable to:ωk=(ω1 k,ω2 k,ω3 k,ω4 k), (k=1,2L m)D is used againstTo represent the degree of closeness of s-th of policymaker and t-th of policymaker, andThus, the degree of closeness for obtaining k-th of policymaker and remaining policymaker is dk, andFurther, the decision weights σ of k-th of policymaker is obtainedk, andFinally, the weight for obtaining 4 evaluation indexes is ω, and
- 6. system according to claim 5, it is characterised in that the data acquisition module is additionally operable to set frequency acquisition threshold Value, judges whether the frequency of driving data collection exceedes the frequency acquisition threshold value;If so, frequency acquisition is then reduced, until being less than the frequency acquisition threshold value;If it is not, then keep frequency acquisition constant.
- 7. system according to claim 5, it is characterised in that the data cleansing module is additionally operable to according to user's statistical number Travel duration threshold value according to go on a journey frequency threshold value and user of, setting user, judge vehicle whether be automatic start-stop vehicle;If user averagely travels duration and travels duration threshold value less than user, and user goes on a journey number more than user's trip number threshold Value, then the relevant driving data of these vehicles is filtered out, and individually analyze and calculate;Otherwise, it is constant to retain all data.
- 8. system according to claim 5, it is characterised in that the data grading module is additionally operable to:Using the method for expert estimation, the scoring P of trip times is obtainedi,tf(i=1,2 ... n), wherein, n is the quantity of stroke;Stroke duration is divided into multiple duration sections from 0-120min, scoring of the stroke duration more than 120min is 0;Find Duration section where maximum frequency, and it is 100 points to set scoring, the scoring in remaining duration section is Pi,time, andPi,time=fi,time/max(fi,time) × 100, wherein, Pi,timeFor scoring of the stroke duration in i-th of duration section, fi,timeFor frequency of the stroke duration in i-th of duration section;The average speed of stroke is divided into multiple speed intervals from 0-120km/h, the average speed of stroke is more than 120km/h's Scoring is 0;The speed interval where maximum frequency is found, and it is 100 points to set scoring, the scoring of remaining speed interval is Pi,speed, andPi,speed=fi,speed/max(fi,speed) × 100, wherein, Pi,speedFor stroke average speed in i-th of speed interval Interior scoring, fi,speedFor frequency of the average speed in i-th of speed interval of stroke;Using the acceleration standard deviation of stroke as reference, the acceleration standard deviation of stroke is arranged to multiple standard deviation sections, obtained The scoring P of stroke ride comforti,smooth, andWherein, Pi,smoothFor scoring of the stroke ride comfort in i-th of standard deviation section, fi,smoothIt is that standard deviation is marked at i-th Frequency in accurate poor section.
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 CN105730450A (en) | 2016-07-06 |
CN105730450B true CN105730450B (en) | 2018-01-02 |
Family
ID=56248049
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610066136.1A Active 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) |
Families Citing this family (24)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106240571B (en) * | 2016-08-03 | 2019-01-25 | 东软集团股份有限公司 | Driving behavior analysis method and apparatus |
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 |
CN107066458A (en) * | 2016-08-26 | 2017-08-18 | 北京车网互联科技有限公司 | A kind of Spatial dimensionality user portrait analysis method based on car networking data |
US10049328B2 (en) * | 2016-10-13 | 2018-08-14 | Baidu Usa Llc | Group driving style learning framework for autonomous vehicles |
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 |
CN108694486A (en) * | 2017-04-07 | 2018-10-23 | 深圳市体数科科技有限公司 | A kind of driving behavior intelligent Evaluation method and apparatus based on cloud model |
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 |
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 |
CN107992579A (en) * | 2017-12-06 | 2018-05-04 | 上海评驾科技有限公司 | A kind of filter method of car networking data |
CN110070245A (en) * | 2018-01-23 | 2019-07-30 | 吉旗物联科技(上海)有限公司 | A kind of driver's scoring arrangement method based on driving data |
CN108765627A (en) * | 2018-04-12 | 2018-11-06 | 深圳市拓保软件有限公司 | A kind of method of driving data risk quantification |
CN108876165B (en) * | 2018-06-27 | 2021-08-27 | 上海天方夜谭网络科技有限公司 | Driver safety monitoring learning system |
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 |
CN109229108B (en) * | 2018-08-07 | 2020-05-05 | 武汉理工大学 | Driving behavior safety evaluation method based on driving fingerprints |
CN111461568B (en) * | 2020-04-14 | 2023-05-02 | 西安热工研究院有限公司 | Method for evaluating performances of strip mine trucks |
CN111724599B (en) * | 2020-06-30 | 2021-07-16 | 暨南大学 | Method, device, equipment and medium for acquiring safe driving behavior evaluation data |
CN111814904B (en) * | 2020-07-22 | 2021-05-28 | 同济大学 | Method and system for distinguishing test driving mode of automatic driving road |
CN112422656A (en) * | 2020-11-06 | 2021-02-26 | 杭州图软科技有限公司 | Driving behavior analysis method and system based on big data |
CN114842571A (en) * | 2021-02-02 | 2022-08-02 | 深圳市易流科技股份有限公司 | Method and device for determining driving behavior data |
CN112926142B (en) * | 2021-04-09 | 2023-04-07 | 厦门金龙联合汽车工业有限公司 | Linear control chassis overall performance evaluation method, terminal device and storage medium |
CN113470214A (en) * | 2021-06-11 | 2021-10-01 | 深圳市前海链科信息技术有限公司 | Vehicle-mounted information processing system based on block chain |
CN114627654B (en) * | 2022-03-21 | 2023-10-20 | 吉林大学 | Bus-mounted passenger quantity quantification method based on space-time characteristics |
Family Cites Families (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US8090598B2 (en) * | 1996-01-29 | 2012-01-03 | Progressive Casualty Insurance Company | Monitoring system for determining and communicating a cost of insurance |
JP4153798B2 (en) * | 2003-01-29 | 2008-09-24 | 株式会社日立製作所 | Safe driving diagnosis method and safe driving diagnosis device |
JP4469297B2 (en) * | 2005-03-01 | 2010-05-26 | 日立オートモティブシステムズ株式会社 | Driving diagnosis method and apparatus |
CN101870293B (en) * | 2009-04-24 | 2013-06-05 | 南京理工大学 | Vehicle driving state evaluating method based on road-switching behavior detection |
CN102428504B (en) * | 2009-05-20 | 2014-04-23 | 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 |
CN104802737B (en) * | 2015-03-25 | 2017-05-10 | 清华大学 | Mobile phone based vehicle abnormality driving behavior detection method |
-
2016
- 2016-01-29 CN CN201610066136.1A patent/CN105730450B/en active Active
Also Published As
Publication number | Publication date |
---|---|
CN105730450A (en) | 2016-07-06 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN105730450B (en) | Driving behavior analysis method and evaluation system based on vehicle-mounted data | |
WO2020244288A1 (en) | Method and apparatus for evaluating truck driving behaviour based on gps trajectory data | |
CN109448369B (en) | Real-time operation risk calculation method for expressway | |
JP6502148B2 (en) | Driving diagnosis method and driving diagnosis apparatus | |
CN110796859A (en) | Real-time traffic state identification and accident risk early warning method based on traffic flow | |
CN111210165B (en) | Vehicle operation risk assessment system based on risk conduction coupling | |
Andrieu et al. | Using statistical models to characterize eco-driving style with an aggregated indicator | |
Abas et al. | Development of Malaysian urban drive cycle using vehicle and engine parameters | |
AU2020103488A4 (en) | Method and device for evaluating driving behaviour of truck based on gps trajectory data | |
CN106022846A (en) | Automobile insurance pricing method, second-hand automobile pricing method and corresponding devices | |
CN109034589A (en) | A kind of driving behavior evaluation method and system based on big data analysis | |
CN104807640A (en) | Method of detecting life state of spatial rolling bearing based on vibration-sensitive time-frequency characteristics | |
Zeng et al. | Identifying deficient pavement sections by means of an improved acceleration-based metric | |
CN102789690A (en) | Illegal vehicle identifying method and system | |
CN109405962B (en) | Road traffic noise frequency spectrum calculation method | |
CN117171921B (en) | Method and device for evaluating and processing health state of diesel particulate tail gas purification device | |
Liu et al. | Construction of driving behavior scoring model based on obd terminal data analysis | |
Rozenshtein et al. | Models for estimating drivers following on two-lane rural highways | |
Reddy | Driving behaviour classification: An eco-driving approach | |
Agnoor et al. | Analysis of driving behaviour through instrumented vehicles | |
Cen et al. | A system design for driving behavior analysis and assessment | |
Ping et al. | Spectral clustering based approach for evaluating the effect of driving behavior on fuel economy | |
Le et al. | Condition monitoring of engine lubrication oil of military vehicles: A machine learning approach | |
CN108694486A (en) | A kind of driving behavior intelligent Evaluation method and apparatus based on cloud model | |
Xu et al. | Investigating contributing factors on aggressive driving based on a structural equation model |
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 | ||
CP03 | Change of name, title or address |
Address after: 1002-1, 10th floor, No.56, Beisihuan West Road, Haidian District, Beijing 100080 Patentee after: Ronglian Technology Group Co., Ltd Address before: 100080, Beijing, Haidian District, No. 56 West Fourth Ring Road, glorious Times Building, 10, 1002-1 Patentee before: UNITED ELECTRONICS Co.,Ltd. |
|
CP03 | Change of name, title or address |