CN106781454A - The appraisal procedure and device of driving behavior - Google Patents
The appraisal procedure and device of driving behavior Download PDFInfo
- Publication number
- CN106781454A CN106781454A CN201611060709.6A CN201611060709A CN106781454A CN 106781454 A CN106781454 A CN 106781454A CN 201611060709 A CN201611060709 A CN 201611060709A CN 106781454 A CN106781454 A CN 106781454A
- Authority
- CN
- China
- Prior art keywords
- stroke
- assessed
- fragment
- event
- time interval
- 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.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
- G08G1/0125—Traffic data processing
Abstract
The present invention proposes the appraisal procedure and device of a kind of driving behavior, wherein, the appraisal procedure of the driving behavior, including：The vehicle operation data of stroke to be assessed is obtained, wherein, the vehicle operation data includes the alert data of multiple traveling index item；The stroke to be assessed is split according to prefixed time interval, obtains the corresponding at least one stroke fragment of the stroke to be assessed；Based on default assessment models, the alert data of the multiple traveling index item included according to each stroke fragment determines the safety trend numerical value of corresponding stroke fragment；The assessment result of stroke to be assessed described in safety trend numerical generation according at least one stroke fragment.Embodiments of the invention, make assessment result more accurate, improve the reasonability and referring to property of assessment.
Description
Technical field
The present invention relates to vehicle drive behavioral analysis technology field, the appraisal procedure and dress of more particularly to a kind of driving behavior
Put.
Background technology
With the increasingly raising of living standard, the quantity of motor vehicles is also more and more.Meanwhile, the generation of traffic accident is frequently
Rate is also continuously increased.In vehicle processes are driven, unsafe driving behavior brings many potential safety hazards, causes huge
Property and the loss of personnel, therefore, the driving behavior for how improving driver has become a very important problem.
At present, generally threshold is carried out by longitudinal acceleration, transverse acceleration, three parameters of normal acceleration in correlation technique
Value judges, to provide the gross score of driving behavior, or, there is provided safe or unsafe judged result.However, current comments
Valency method, there is a problem of to the assessment result of driving behavior not precisely, reference value it is low.
The content of the invention
It is contemplated that at least solving above-mentioned technical problem to a certain extent.
Therefore, first purpose of the invention is to propose a kind of appraisal procedure of driving behavior, make assessment result more smart
Standard, improves the reasonability and referring to property of assessment.
Second object of the present invention is to propose a kind of apparatus for evaluating of driving behavior.
It is that up to above-mentioned purpose, embodiment proposes a kind of appraisal procedure of driving behavior according to a first aspect of the present invention, wraps
Include following steps：
The vehicle operation data of stroke to be assessed is obtained, wherein, the vehicle operation data includes multiple traveling index item
Alert data；
The stroke to be assessed is split according to prefixed time interval, obtains the stroke to be assessed corresponding at least
One stroke fragment；
Based on default assessment models, the alert data of the multiple traveling index item included according to each stroke fragment is true
The safety trend numerical value of fixed corresponding stroke fragment；
The assessment result of stroke to be assessed described in safety trend numerical generation according at least one stroke fragment.
It is in one embodiment of the invention, described the stroke to be assessed is split according to prefixed time interval,
The corresponding at least one stroke fragment of the stroke to be assessed is obtained, including：
Judge whether the stroke to be assessed collides event according to the vehicle operation data；
In the event of collision accident, it is determined that the time point of the event that collides, and by the stroke, with the time
Point is terminal, the time period that length is the prefixed time interval, used as the corresponding stroke fragment of the stroke to be assessed；Or
If not colliding event, the stroke to be assessed is split according to the prefixed time interval, obtain
To multiple stroke fragments.
In one embodiment of the invention, the stroke to be assessed is divided according to prefixed time interval described
Cut, before obtaining the corresponding at least one stroke fragment of the stroke to be assessed, also include：
The quantity of the |input paramete according to the default assessment models determines the length of the prefixed time interval.
In one embodiment of the invention, also include：
The vehicle operation data of multiple sample strokes is obtained, wherein, the vehicle operation data includes multiple traveling indexs
The sample alert data of item；
The multiple stroke is divided according to the stroke event that whether collides, obtains the first of the event of colliding
The Equations of The Second Kind stroke of class stroke and the event that do not collide；
For each first kind stroke, the time point of the event that determines to collide in the first kind stroke, and will be described
In first kind stroke, with the time point as terminal, time period of the length as prefixed time interval, as the first kind stroke
Corresponding stroke fragment；
For each Equations of The Second Kind stroke, the Equations of The Second Kind stroke is split according to the prefixed time interval, obtain
Multiple stroke fragments of the Equations of The Second Kind stroke；
The sample alert data of the multiple traveling index item included according to the corresponding stroke fragment of the multiple sample stroke
Model training is carried out, the assessment models are set up.
In one embodiment of the invention, it is described to be given birth to according to the safety trend numerical value of at least one stroke fragment
Into the assessment result of the stroke to be assessed, including：
Count at least one stroke fragment, the safety trend numerical value is the first segments of the first numerical value
Amount, and count at least one stroke fragment, the safety trend numerical value is the second number of fragments of second value；
The assessment score of the stroke to be assessed is calculated according to first number of fragments and second number of fragments.
Second aspect present invention embodiment proposes a kind of apparatus for evaluating of driving behavior, it is characterised in that including：
Acquisition module, the vehicle operation data for obtaining stroke to be assessed, wherein, the vehicle operation data includes many
The alert data of individual traveling index item；
Segmentation module, for splitting to the stroke to be assessed according to prefixed time interval, obtains described to be assessed
The corresponding at least one stroke fragment of stroke；
First determining module, for based on default assessment models, according to multiple travelings that each stroke fragment includes
The alert data of index item determines the safety trend numerical value of corresponding stroke fragment；
Generation module, for row to be assessed described in the safety trend numerical generation according at least one stroke fragment
The assessment result of journey.
In one embodiment of the invention, the segmentation module is used for：
Judge whether the stroke to be assessed collides event according to the vehicle operation data；
In the event of collision accident, it is determined that the time point of the event that collides, and by the stroke, with the time
Point is terminal, the time period that length is the prefixed time interval, used as the corresponding stroke fragment of the stroke to be assessed；Or
If not colliding event, the stroke to be assessed is split according to the prefixed time interval, obtain
To multiple stroke fragments.
In one embodiment of the invention, also include：
Second determining module, when the quantity for the |input paramete according to the default assessment models determines described default
Between be spaced length.
In one embodiment of the invention, module also is set up including assessment models, is used for：
The vehicle operation data of multiple sample strokes is obtained, wherein, the vehicle operation data includes multiple traveling indexs
The sample alert data of item；
The multiple stroke is divided according to the stroke event that whether collides, obtains the first of the event of colliding
The Equations of The Second Kind stroke of class stroke and the event that do not collide；
For each first kind stroke, the time point of the event that determines to collide in the first kind stroke, and will be described
In first kind stroke, with the time point as terminal, time period of the length as prefixed time interval, as the first kind stroke
Corresponding stroke fragment；
For each Equations of The Second Kind stroke, the Equations of The Second Kind stroke is split according to the prefixed time interval, obtain
Multiple stroke fragments of the Equations of The Second Kind stroke；
The sample alert data of the multiple traveling index item included according to the corresponding stroke fragment of the multiple sample stroke
Model training is carried out, the assessment models are set up.
In one embodiment of the invention, the generation module is used for：
Count at least one stroke fragment, the safety trend numerical value is the first segments of the first numerical value
Amount, and count at least one stroke fragment, the safety trend numerical value is the second number of fragments of second value；
The assessment score of the stroke to be assessed is calculated according to first number of fragments and second number of fragments.
The appraisal procedure and device of the driving behavior of the embodiment of the present invention, number is travelled by the vehicle for obtaining stroke to be assessed
According to, stroke to be assessed is then divided into by least one stroke fragment according to prefixed time interval, and based on default assessment mould
Type determines the safety trend numerical value of each stroke fragment, the safety trend numerical value of the stroke fragment in stroke to be assessed
The assessment result of the stroke to be assessed is generated, more index item can be combined, make assessment result more accurate, and by row
The alert data of the traveling index item of journey is temporally segmented cutting analysis, can accurately flutter and catch the reason for causing dangerous generation and mistake
Journey, vehicle operation data is estimated in real time with prompting, improve assessment reasonability and referring to property, reduce traffic thing
Therefore generation, improve drive safety.
Additional aspect of the invention and advantage will be set forth in part in the description, and will partly become from the following description
Obtain substantially, or recognized by practice of the invention.
Brief description of the drawings
Of the invention above-mentioned and/or additional aspect and advantage will become from description of the accompanying drawings below to embodiment is combined
Substantially and be readily appreciated that, wherein：
Fig. 1 is the flow chart of the appraisal procedure of the driving behavior according to one embodiment of the invention；
Fig. 2 is the flow chart of the appraisal procedure of the driving behavior according to another embodiment of the present invention；
Fig. 3 is the flow chart of the appraisal procedure of the driving behavior according to another embodiment of the present invention；
Fig. 4 is the structural representation of the apparatus for evaluating of the driving behavior according to one embodiment of the invention；
Fig. 5 is the structural representation of the apparatus for evaluating of the driving behavior according to another embodiment of the present invention.
Specific embodiment
Embodiments of the invention are described below in detail, the example of the embodiment is shown in the drawings, wherein from start to finish
Same or similar label represents same or similar element or the element with same or like function.Below with reference to attached
It is exemplary to scheme the embodiment of description, is only used for explaining the present invention, and is not considered as limiting the invention.
In the description of the invention, it is to be understood that term " multiple " refers to two or more；Term " first ",
" second " is only used for describing purpose, and it is not intended that indicating or implying relative importance.
Below with reference to the accompanying drawings the appraisal procedure and device of driving behavior according to embodiments of the present invention described.
Fig. 1 is the flow chart of the appraisal procedure of the driving behavior according to one embodiment of the invention.
As shown in figure 1, the appraisal procedure of driving behavior according to embodiments of the present invention, including：
S101, obtains the vehicle operation data of stroke to be assessed.
Specifically, the appraisal procedure of driving behavior provided in an embodiment of the present invention, executive agent is carried for the embodiment of the present invention
The apparatus for evaluating of the driving behavior of confession, the device can be configured in any motor vehicles, to realize commenting vehicle travel
Point.
Wherein, vehicle operation data may include the alert data of multiple index item.
For example, the alert data of multiple index item can be alarmed including collision warning, zig zag, anxious deceleration is alarmed,
It is anxious to accelerate alarm, anxious lane change alert, overspeed alarming, fatigue driving alarm, the alarm of long-time idling, frequent lane change alert, rotating speed
The information such as too high alarm, water temperature over-high alarm, neutral position sliding alarm.
Further, above-mentioned warning message can be opened by vehicle single stroke distance travelled, main furnace building light switch, dipped headlight
Pass, side-marker lamp switch, fog lamp switch, left steering lamp switch, right turn lamp switch, dangerous lamp switch, door contact interrupter, car door lock are opened
Pass, car window switch, ECM (control unit of engine)/ECU (engine control module), ABS (anti-blocking brake system), SRS
The alarm of (electronic security(ELSEC) air bag), machine oil (pressure, temperature), maintenance alarm, wheel tyre pressure alarm, parking brake state, brake pedal, stop
Car pedal relative position, gas pedal, gas pedal relative position, clutch state, seat belt status, ACC signals, key shape
The information of vehicles such as state, wiper status, air-conditioning switch gear, Engine Inlet Temperature, air-conditioning vehicle interior temperature determine.
In some embodiments of the invention, data when each index item can be alarmed are designated as 1, alarm
When data be designated as 0.
When implementing, can be by mobile device, OBD (On-Board Diagnostics, letter
Claim OBD), or standby, etc. any equipment that can obtain vehicle operation data is installed before vehicle, obtain the car of branch's journey to be evaluated
Running data.
S102, splits according to prefixed time interval to the stroke to be assessed, obtains the stroke correspondence to be assessed
At least one stroke fragment.
Wherein, prefixed time interval can be 10 seconds (s), 15s, 20s, etc..
Specifically, can be configured according to the type of OBD equipment, or the change of other factorses.
Or, in one embodiment of the invention, for the ease of subsequently determining the peace of stroke fragment according to assessment models
During full tendentiousness numerical value, between can also determining the Preset Time according to the quantity of the |input paramete of the default assessment models
Every length.For example, if the quantity of the |input paramete of assessment models is 15, above-mentioned prefixed time interval can be 15 seconds,
So as to, it is per second under the alert data of multiple index item can be used as default assessment models |input paramete.
Assessment models are the vehicle drive data foundation previously according to great amount of samples stroke.Specifically setting up process can pass through
The process of embodiment illustrated in fig. 3 is set up.Wherein, the quantity of the |input paramete of assessment models, is split by sample stroke
When the length of prefixed time interval that is used determine.
When implementing, as shown in Fig. 2 step 102 can include step S201-S203.
S201, judges whether the stroke to be assessed collides event according to the vehicle operation data.
S202, in the event of collision accident, it is determined that the time point of the event that collides, and by the stroke, with institute
Time point is stated for terminal, the time period that length is the prefixed time interval, as the corresponding stroke piece of the stroke to be assessed
Section.
That is, for the stroke for colliding, the data of 15s are used as the trip pair before being collided in stroke
The stroke fragment answered.
As an example it is assumed that preset time period is 15s, in a stroke to be assessed of 2min, collide event
Time point be the 1st point 30 seconds, then can be corresponding as stroke to be assessed using 1 point of time period between 30 seconds 15 seconds to 1 point
Stroke fragment.
S203, if not colliding event, is divided the stroke to be assessed according to the prefixed time interval
Cut, obtain multiple stroke fragments.
That is, for the stroke not collided, it is prefixed time interval length that stroke can be divided into length
Multiple fragments.
As an example it is assumed that preset time period is 15s, in a stroke to be assessed of 2min, split with 15s,
Obtain 8 stroke fragments.
In one embodiment of the invention, for the ease of carrying out the purposes such as data preservation and calculating, can be based on default rule
Then, the corresponding alert data of each stroke fragment after segmentation is stored as the tables of data of preset format.
Specifically, the tables of data is arranged including M × N+1, Q+2 rows, wherein, M is the duration of prefixed time interval, and N is car
The item number of the index item included in running data, Q is the number of the corresponding stroke fragment of stroke to be assessed.That is, in tables of data
An often capable corresponding stroke fragment.
As an example it is assumed that the index item in a vehicle operation data for the stroke to be assessed of 1min includes " anxious to accelerate "
" hypervelocity " 2, prefixed time interval is 15s.So, the event if stroke to be assessed does not collide, after its segmentation
Storable tables of data can be as shown in table 1, comprising 60/15+2=6 rows, 15 × 2+1=31 row.If the stroke to be assessed occurs
Collision accident, then storable tables of data can be as shown in table 2 after its segmentation, comprising 1+2=3 rows, 15 × 2+1=31 row.
Table 1
Table 2
S103, based on default assessment models, the alarm of the multiple traveling index item included according to each stroke fragment
Data determine the safety trend numerical value of corresponding stroke fragment.
Specifically, for each stroke fragment, can be by the report of corresponding each traveling index item per second in stroke fragment
Alert data are input into the |input paramete of assessment models as |input paramete, by exportable the trip fragment after the calculating of assessment models
Safety trend numerical value.Thus, can enter to obtain the safety trend numerical value of each stroke fragment in stroke to be assessed.
Wherein, safety trend numerical value may include to represent first numerical value (for example, can be represented with 0) of safety and represent dangerous
Second value (for example, can be represented with 1).
S104, the assessment of stroke to be assessed described in the safety trend numerical generation according at least one stroke fragment
As a result.
Specifically, can be counted according to the safety trend numerical value of each stroke fragment in stroke to be assessed.Obtain
Wherein safety trend PTS and dangerous tendency PTS, and then, according to safety trend PTS and dangerous tendency PTS meter
Calculate the assessment score of whole stroke to be assessed.
In one embodiment of the invention, for first numerical value (for example, can be represented with 0) and table of above-mentioned expression safety
Show the second value (for example, can be represented with 1) of danger, in can counting at least one stroke fragment, the safety trend
Numerical value is the first number of fragments of the first numerical value, and counts at least one stroke fragment, the safety trend numerical value
It is the second number of fragments of second value；Calculate described to be assessed according to first number of fragments and second number of fragments
The assessment score of stroke.
As an example it is assumed that the first number of fragments is S, the second number of fragments is D, then,
The assessment score of stroke to be assessed=S/ (S+D) × 100.
Thus, split by stroke, each stroke fragment in stroke is carried out by being converted to the assessment of stroke
Whether safety classification problem, then by the scoring that the classification results of each stroke fragment are converted to whole stroke cause scoring tie
Fruit is more accurate.
The appraisal procedure of the driving behavior of the embodiment of the present invention, by obtaining the vehicle operation data of stroke to be assessed, so
Stroke to be assessed is divided into by least one stroke fragment according to prefixed time interval afterwards, and is determined based on default assessment models
The safety trend numerical value of each stroke fragment, the safety trend numerical generation institute of the stroke fragment in stroke to be assessed
The assessment result of stroke to be assessed is stated, more index item can be combined, make assessment result more accurate, and by the row to stroke
The alert data for sailing index item is temporally segmented cutting analysis, can accurately flutter the reason for causing dangerous generation and the process of catching, real
When vehicle operation data is estimated with prompting, improve assessment reasonability and referring to property, reduce traffic accident
Occur, improve drive safety.
In another embodiment of this hair invention, the appraisal procedure of above-mentioned driving behavior may also include as shown in Figure 3
Set up the process of above-mentioned assessment models.Specifically, as shown in Figure 3, it may include following steps：
S301, obtains the vehicle operation data of multiple sample strokes.
Wherein, the vehicle operation data includes the sample alert data of multiple traveling index item.
The vehicle operation data of sample stroke can be the mass data during vehicle history traveling.
Whether S302, divides according to the stroke event that collides to the multiple stroke, obtains the event of colliding
First kind stroke and the event that do not collide Equations of The Second Kind stroke.
In order that the assessment models that must be trained are more accurate, sample stroke may include the first kind row of the time of colliding
The Equations of The Second Kind stroke of journey and the event that do not collide.Therefore, after the vehicle operation data for obtaining sample stroke, can root first
According to the event that whether collided in stroke, the sample stroke of acquisition is divided into the first kind stroke of the event of colliding and is not sent out
The Equations of The Second Kind stroke of raw collision accident.
S303, for each first kind stroke, the time point of the event that determines to collide in the first kind stroke, and will
In the first kind stroke, with the time point as terminal, time period of the length as prefixed time interval, as the first kind
The corresponding stroke fragment of stroke.
Wherein, determine that the specific implementation of the corresponding stroke fragment of first kind stroke can refer to Fig. 2 institutes in step S303
That states step S202 in embodiment implements process.
Thus, analyzed by the way that accident into preceding alert data (data of 15 seconds before as collided) fine cut occurs, Neng Gouzhun
Really flutter and catch the reason for causing dangerous generation and process, thus train the assessment accuracy of the assessment models for obtaining higher.
S304, for each Equations of The Second Kind stroke, splits according to the prefixed time interval to the Equations of The Second Kind stroke,
Obtain multiple stroke fragments of the Equations of The Second Kind stroke.
Wherein, determine that the specific implementation of the corresponding stroke fragment of Equations of The Second Kind stroke can refer to Fig. 1 institutes in step S304
That states step S203 in embodiment implements process.
Thus, by the way that data to be temporally segmented cutting, and for Training valuation model, the assessment mould for obtaining thus is trained
Type can carry out behavior evaluation and prompting at regular intervals to vehicle operation data in real time, can in time avoid accident from sending out
It is raw.
Further, can be according to the mode that stroke fragment is stored in embodiment illustrated in fig. 2, by first kind stroke and Equations of The Second Kind
The corresponding fragment unification storage of stroke is in a tables of data.For example, can be as shown in table 3.
Table 3
S305, the sample alarm of the multiple traveling index item included according to the corresponding stroke fragment of the multiple sample stroke
Data carry out model training, set up the assessment models.
In an embodiment of the present invention, various machine learning algorithms, the traveling index in above-mentioned packet can be based on
The sample alert data Training valuation model of item.For example, by taking neural network algorithm as an example, an initial nerve net can be set up
Network, wherein, the input layer quantity in the initial neutral net is 15 × index number, and hidden layer neuron quantity isOutput layer neuronal quantity is 2.
Then, the data in table 3 are pressed into bar input neutral net, wherein each achievement data is used as independent variable in 1 to 15 second
Input layer is sequentially input, the achievement data of the row that " collided " in table is used as dependent variable input and output layer neuron.
Thus, above-mentioned neutral net is trained by the vehicle drive data of the sample stroke of the magnanimity for obtaining, most
The neural network model for assessing is obtained eventually.
Further it will be understood that in a kind of possible way of realization, vehicle operation data be not it is changeless,
Over time or other factorses change, vehicle operation data can also produce change.Corresponding, default characteristic model can also be produced
Change, therefore, in embodiments of the present invention, after assessment models are set up, can also include：
The vehicle operation data of the sample stroke is gathered every predetermined period；
Vehicle operation data according to the sample stroke for collecting updates the assessment models.
Wherein, predetermined period, can be 1 hour, 2 hours, 1 day, 2 days, etc..It is updated by assessment models,
Assessment result can be made more accurate.
Determine after assessment models, current stroke to be assessed can be determined according to the assessment models in vehicle operation
In each stroke fragment safety trend numerical value.
It should be noted that in actual applications, layer number and each layer neuron number can be hidden according to actual conditions adjustment
Amount.
Thus the assessment models for obtaining are trained, alert data before accident is occurred (data of 15 seconds before as collided) is crossed fine
Cutting analysis, can accurately flutter catch cause it is dangerous the reason for occur and process, vehicle operation data can be carried out in real time every
The behavior evaluation of a period of time and prompting, can in time avoid accident from occurring, and assessment accuracy is higher.
In order to realize above-described embodiment, the present invention also proposes a kind of apparatus for evaluating of driving behavior.
Fig. 4 is the structural representation of the apparatus for evaluating of the driving behavior according to one embodiment of the invention.
As shown in figure 4, the apparatus for evaluating of driving behavior according to embodiments of the present invention, including：Acquisition module 10, segmentation mould
Block 20, the first determining module 30 and generation module 40.
Specifically, acquisition module 10 is used to obtain the vehicle operation data of stroke to be assessed, wherein, the vehicle travels number
According to the alert data including multiple traveling index item.
Specifically, the appraisal procedure of driving behavior provided in an embodiment of the present invention, executive agent is carried for the embodiment of the present invention
The apparatus for evaluating of the driving behavior of confession, the device can be configured in any motor vehicles, to realize commenting vehicle travel
Point.
Wherein, vehicle operation data may include the alert data of multiple index item.
For example, the alert data of multiple index item can be alarmed including collision warning, zig zag, anxious deceleration is alarmed,
It is anxious to accelerate alarm, anxious lane change alert, overspeed alarming, fatigue driving alarm, the alarm of long-time idling, frequent lane change alert, rotating speed
The information such as too high alarm, water temperature over-high alarm, neutral position sliding alarm.
Further, above-mentioned warning message can be opened by vehicle single stroke distance travelled, main furnace building light switch, dipped headlight
Pass, side-marker lamp switch, fog lamp switch, left steering lamp switch, right turn lamp switch, dangerous lamp switch, door contact interrupter, car door lock are opened
Pass, car window switch, ECM (control unit of engine)/ECU (engine control module), ABS (anti-blocking brake system), SRS
The alarm of (electronic security(ELSEC) air bag), machine oil (pressure, temperature), maintenance alarm, wheel tyre pressure alarm, parking brake state, brake pedal, stop
Car pedal relative position, gas pedal, gas pedal relative position, clutch state, seat belt status, ACC signals, key shape
The information of vehicles such as state, wiper status, air-conditioning switch gear, Engine Inlet Temperature, air-conditioning vehicle interior temperature determine.
In some embodiments of the invention, data when each index item can be alarmed are designated as 1, alarm
When data be designated as 0.
When implementing, can be by mobile device, OBD (On-Board Diagnostics, letter
Claim OBD), or standby, etc. any equipment that can obtain vehicle operation data is installed before vehicle, obtain the car of branch's journey to be evaluated
Running data.
Segmentation module 20 is used to split the stroke to be assessed according to prefixed time interval, obtains described to be assessed
The corresponding at least one stroke fragment of stroke.
Wherein, prefixed time interval can be 10 seconds (s), 15s, 20s, etc..
Specifically, can be configured according to the type of OBD equipment, or the change of other factorses.
Or, in one embodiment of the invention, for the ease of subsequently determining the peace of stroke fragment according to assessment models
During full tendentiousness numerical value, between can also determining the Preset Time according to the quantity of the |input paramete of the default assessment models
Every length.For example, if the quantity of the |input paramete of assessment models is 15, above-mentioned prefixed time interval can be 15 seconds,
So as to, it is per second under the alert data of multiple index item can be used as default assessment models |input paramete.
In one embodiment of the invention, segmentation module 20 can be used for：
Judge whether the stroke to be assessed collides event according to the vehicle operation data；
In the event of collision accident, it is determined that the time point of the event that collides, and by the stroke, with the time
Point is terminal, the time period that length is the prefixed time interval, used as the corresponding stroke fragment of the stroke to be assessed；
If not colliding event, the stroke to be assessed is split according to the prefixed time interval, obtain
To multiple stroke fragments.
That is, for the stroke for colliding, the data of 15s are used as the trip pair before being collided in stroke
The stroke fragment answered.
As an example it is assumed that preset time period is 15s, in a stroke to be assessed of 2min, collide event
Time point be the 1st point 30 seconds, then can be corresponding as stroke to be assessed using 1 point of time period between 30 seconds 15 seconds to 1 point
Stroke fragment.
For the stroke not collided, stroke can be divided into multiple fragments that length is prefixed time interval length.
As an example it is assumed that preset time period is 15s, in a stroke to be assessed of 2min, split with 15s,
Obtain 8 stroke fragments.
In one embodiment of the invention, for the ease of carrying out the purposes such as data preservation and calculating, can be based on default rule
Then, the corresponding alert data of each stroke fragment after segmentation is stored as the tables of data of preset format.
Specifically, the tables of data is arranged including M × N+1, Q+2 rows, wherein, M is the duration of prefixed time interval, and N is car
The item number of the index item included in running data, Q is the number of the corresponding stroke fragment of stroke to be assessed.That is, in tables of data
An often capable corresponding stroke fragment.
As an example it is assumed that the index item in a vehicle operation data for the stroke to be assessed of 1min includes " anxious to accelerate "
" hypervelocity " 2, prefixed time interval is 15s.So, the event if stroke to be assessed does not collide, after its segmentation
Storable tables of data can be as shown in table 1, comprising 60/15+2=6 rows, 15 × 2+1=31 row.If the stroke to be assessed occurs
Collision accident, then storable tables of data can be as shown in table 2 after its segmentation, comprising 1+2=3 rows, 15 × 2+1=31 row.
First determining module 30 is used to be based on default assessment models, according to multiple travelings that each stroke fragment includes
The alert data of index item determines the safety trend numerical value of corresponding stroke fragment.
Specifically, for each stroke fragment, the first determining module 30 can by stroke fragment it is per second it is corresponding each
The alert data for travelling index item is input into the |input paramete of assessment models as |input paramete, by can after the calculating of assessment models
Export the safety trend numerical value of the trip fragment.Thus, the safety that can enter to obtain each stroke fragment in stroke to be assessed is inclined
Tropism numerical value.
Wherein, safety trend numerical value may include to represent first numerical value (for example, can be represented with 0) of safety and represent dangerous
Second value (for example, can be represented with 1).
Generation module 40 is used for be assessed according to the safety trend numerical generation of at least one stroke fragment
The assessment result of stroke.
Specifically, generation module 40 can be carried out according to the safety trend numerical value of each stroke fragment in stroke to be assessed
Statistics.Wherein safety trend PTS and dangerous tendency PTS are obtained, and then, according to safety trend PTS and dangerous tendency
PTS calculates the assessment score of whole stroke to be assessed.
In one embodiment of the invention, for first numerical value (for example, can be represented with 0) and table of above-mentioned expression safety
Show the second value (for example, can be represented with 1) of danger, generation module 40 can be used for：In counting at least one stroke fragment,
The safety trend numerical value is the first number of fragments of the first numerical value, and counts at least one stroke fragment, described
Safety trend numerical value is the second number of fragments of second value；According to first number of fragments and second number of fragments
Calculate the assessment score of the stroke to be assessed.
As an example it is assumed that the first number of fragments is S, the second number of fragments is D, then,
The assessment score of stroke to be assessed=S/ (S+D) × 100.
Thus, split by stroke, each stroke fragment in stroke is carried out by being converted to the assessment of stroke
Whether safety classification problem, then by the scoring that the classification results of each stroke fragment are converted to whole stroke cause scoring tie
Fruit is more accurate.
The apparatus for evaluating of the driving behavior of the embodiment of the present invention, by obtaining the vehicle operation data of stroke to be assessed, so
Stroke to be assessed is divided into by least one stroke fragment according to prefixed time interval afterwards, and is determined based on default assessment models
The safety trend numerical value of each stroke fragment, the safety trend numerical generation institute of the stroke fragment in stroke to be assessed
The assessment result of stroke to be assessed is stated, more index item can be combined, make assessment result more accurate, and by the row to stroke
The alert data for sailing index item is temporally segmented cutting analysis, can accurately flutter the reason for causing dangerous generation and the process of catching, real
When vehicle operation data is estimated with prompting, improve assessment reasonability and referring to property, reduce traffic accident
Occur, improve drive safety.
Fig. 5 is the structural representation of the apparatus for evaluating of the driving behavior according to another embodiment of the present invention.
As shown in figure 5, the apparatus for evaluating of driving behavior according to embodiments of the present invention, including：Acquisition module 10, segmentation mould
Block 20, the first determining module 30, generation module 40, the second determining module 50, assessment models set up module 60.
Wherein, acquisition module 10, segmentation module 20, the first determining module 30 and generation module 40 can refer to real shown in Fig. 4
Apply example.
The quantity that second determining module 50 is used for the |input paramete according to the default assessment models determines described default
The length of time interval.
Assessment models in the embodiment of the present invention can be the vehicle drive data foundation previously according to great amount of samples stroke.
Specifically set up process and can set up module 60 by assessment models and set up.Wherein, the quantity of the |input paramete of assessment models, is by right
What the length of the prefixed time interval that sample stroke is used when being split determined.
Assessment models set up module 60 to be used for：
The vehicle operation data of multiple sample strokes is obtained, wherein, the vehicle operation data includes multiple traveling indexs
The sample alert data of item；The multiple stroke is divided according to the stroke event that whether collides, is collided
The first kind stroke of event and the Equations of The Second Kind stroke of the event that do not collide；For each first kind stroke, described first is determined
Time point of the event that collided in class stroke, and by the first kind stroke, with the time point as terminal, length be pre-
If the time period of time interval, as the corresponding stroke fragment of the first kind stroke；For each Equations of The Second Kind stroke, according to institute
State prefixed time interval to split the Equations of The Second Kind stroke, obtain multiple stroke fragments of the Equations of The Second Kind stroke；According to
The sample alert datas of multiple traveling index item that the corresponding stroke fragment of the multiple sample stroke includes carry out model training,
Set up the assessment models.
Wherein, the vehicle operation data includes the sample alert data of multiple traveling index item.
The vehicle operation data of sample stroke can be the mass data during vehicle history traveling.
In order that the assessment models that must be trained are more accurate, sample stroke may include the first kind row of the time of colliding
The Equations of The Second Kind stroke of journey and the event that do not collide.Therefore, after the vehicle operation data for obtaining sample stroke, can root first
According to the event that whether collided in stroke, the sample stroke of acquisition is divided into the first kind stroke of the event of colliding and is not sent out
The Equations of The Second Kind stroke of raw collision accident.
In an embodiment of the present invention, various machine learning algorithms, the traveling index in above-mentioned packet can be based on
The sample alert data Training valuation model of item.For example, by taking neural network algorithm as an example, an initial nerve net can be set up
Network, wherein, the input layer quantity in the initial neutral net is 15 × index number, and hidden layer neuron quantity isOutput layer neuronal quantity is 2.
Then, the data in table 3 are pressed into bar input neutral net, wherein each achievement data is used as independent variable in 1 to 15 second
Input layer is sequentially input, the achievement data of the row that " collided " in table is used as dependent variable input and output layer neuron.
Thus, above-mentioned neutral net is trained by the vehicle drive data of the sample stroke of the magnanimity for obtaining, most
The neural network model for assessing is obtained eventually.
Determine after assessment models, current stroke to be assessed can be determined according to the assessment models in vehicle operation
In each stroke fragment safety trend numerical value.
It should be noted that in actual applications, layer number and each layer neuron number can be hidden according to actual conditions adjustment
Amount.
Thus the assessment models for obtaining are trained, alert data before accident is occurred (data of 15 seconds before as collided) is crossed fine
Cutting analysis, can accurately flutter catch cause it is dangerous the reason for occur and process, vehicle operation data can be carried out in real time every
The behavior evaluation of a period of time and prompting, can in time avoid accident from occurring, and assessment accuracy is higher.
Further it will be understood that in a kind of possible way of realization, vehicle operation data be not it is changeless,
Over time or other factorses change, vehicle operation data can also produce change.Corresponding, default characteristic model can also be produced
Change, therefore, in embodiments of the present invention, after assessment models are set up, the sample stroke can be gathered every predetermined period
Vehicle operation data, and the assessment models are updated according to the vehicle operation data of the sample stroke for collecting.
Wherein, predetermined period, can be 1 hour, 2 hours, 1 day, 2 days, etc..It is updated by assessment models,
Assessment result can be made more accurate.
In the description of this specification, reference term " one embodiment ", " some embodiments ", " example ", " specifically show
The description of example " or " some examples " etc. means to combine specific features, structure, material or spy that the embodiment or example are described
Point is contained at least one embodiment of the invention or example.In this manual, to the schematic representation of above-mentioned term not
Identical embodiment or example must be directed to.And, the specific features of description, structure, material or feature can be with office
Combined in an appropriate manner in one or more embodiments or example.Additionally, in the case of not conflicting, the skill of this area
Art personnel can be tied the feature of the different embodiments or example described in this specification and different embodiments or example
Close and combine.
Additionally, term " first ", " second " are only used for describing purpose, and it is not intended that indicating or implying relative importance
Or the implicit quantity for indicating indicated technical characteristic.Thus, define " first ", the feature of " second " can express or
Implicitly include at least one this feature.In the description of the invention, " multiple " is meant that two or more, unless separately
There is clearly specific restriction.
Any process described otherwise above or method description in flow chart or herein is construed as, and expression includes
It is one or more for realizing specific logical function or process the step of the module of code of executable instruction, fragment or portion
Point, and the scope of the preferred embodiment of the present invention includes other realization, wherein can not press shown or discussion suitable
Sequence, including function involved by basis by it is basic simultaneously in the way of or in the opposite order, carry out perform function, this should be of the invention
Embodiment person of ordinary skill in the field understood.
Represent in flow charts or logic and/or step described otherwise above herein, for example, being considered use
In the order list of the executable instruction for realizing logic function, in may be embodied in any computer-readable medium, for
Instruction execution system, device or equipment (such as computer based system, including the system of processor or other can be held from instruction
The system of row system, device or equipment instruction fetch and execute instruction) use, or with reference to these instruction execution systems, device or set
It is standby and use.For the purpose of this specification, " computer-readable medium " can any can be included, store, communicate, propagate or pass
The dress that defeated program is used for instruction execution system, device or equipment or with reference to these instruction execution systems, device or equipment
Put.The more specifically example (non-exhaustive list) of computer-readable medium includes following：With the electricity that one or more are connected up
Connecting portion (electronic installation), portable computer diskette box (magnetic device), random access memory (RAM), read-only storage
(ROM), erasable edit read-only storage (EPROM or flash memory), fiber device, and portable optic disk is read-only deposits
Reservoir (CDROM).In addition, computer-readable medium can even is that the paper that can thereon print described program or other are suitable
Medium, because optical scanner for example can be carried out by paper or other media, then enters edlin, interpretation or if necessary with it
His suitable method is processed electronically to obtain described program, is then stored in computer storage.
Those skilled in the art are appreciated that to realize all or part of step that above-described embodiment method is carried
The rapid hardware that can be by program to instruct correlation is completed, and described program can be stored in a kind of computer-readable storage medium
In matter, the program upon execution, including one or a combination set of the step of embodiment of the method.
Additionally, during each functional unit in each embodiment of the invention can be integrated in a processing module, it is also possible to
It is that unit is individually physically present, it is also possible to which two or more units are integrated in a module.Above-mentioned integrated mould
Block can both be realized in the form of hardware, it would however also be possible to employ the form of software function module is realized.The integrated module is such as
Fruit is to realize in the form of software function module and as independent production marketing or when using, it is also possible to which storage is in a computer
In read/write memory medium.
Storage medium mentioned above can be read-only storage, disk or CD etc..Although having been shown above and retouching
Embodiments of the invention are stated, it is to be understood that above-described embodiment is exemplary, it is impossible to be interpreted as to limit of the invention
System, one of ordinary skill in the art can be changed to above-described embodiment, change, replace and become within the scope of the invention
Type.
Claims (10)
1. a kind of appraisal procedure of driving behavior, it is characterised in that comprise the following steps：
The vehicle operation data of stroke to be assessed is obtained, wherein, the vehicle operation data includes the report of multiple traveling index item
Alert data；
The stroke to be assessed is split according to prefixed time interval, obtains the stroke to be assessed corresponding at least one
Stroke fragment；
Based on default assessment models, the alert data of the multiple traveling index item included according to each stroke fragment determines phase
Answer the safety trend numerical value of stroke fragment；
The assessment result of stroke to be assessed described in safety trend numerical generation according at least one stroke fragment.
2. the method for claim 1, it is characterised in that described to be entered to the stroke to be assessed according to prefixed time interval
Row segmentation, obtains the corresponding at least one stroke fragment of the stroke to be assessed, including：
Judge whether the stroke to be assessed collides event according to the vehicle operation data；
In the event of collision accident, it is determined that the time point of the event that collides, and by the stroke, it is with the time point
Terminal, length are the time period of the prefixed time interval, used as the corresponding stroke fragment of the stroke to be assessed；Or
If not colliding event, the stroke to be assessed is split according to the prefixed time interval, obtain many
Individual stroke fragment.
3. the method for claim 1, it is characterised in that it is described according to prefixed time interval to the stroke to be assessed
Split, before obtaining the corresponding at least one stroke fragment of the stroke to be assessed, also included：
The quantity of the |input paramete according to the default assessment models determines the length of the prefixed time interval.
4. the method for claim 1, it is characterised in that also include：
The vehicle operation data of multiple sample strokes is obtained, wherein, the vehicle operation data includes multiple traveling index item
Sample alert data；
The multiple stroke is divided according to the stroke event that whether collides, obtains the first kind row of the event of colliding
The Equations of The Second Kind stroke of journey and the event that do not collide；
For each first kind stroke, the time point of the event that determines to collide in the first kind stroke, and by described first
In class stroke, with the time point as terminal, time period of the length as prefixed time interval, as first kind stroke correspondence
Stroke fragment；
For each Equations of The Second Kind stroke, the Equations of The Second Kind stroke is split according to the prefixed time interval, obtain described
Multiple stroke fragments of Equations of The Second Kind stroke；
The sample alert data of the multiple traveling index item included according to the corresponding stroke fragment of the multiple sample stroke is carried out
Model training, sets up the assessment models.
5. the method as described in claim any one of 1-4, it is characterised in that described according at least one stroke fragment
The assessment result of stroke to be assessed described in safety trend numerical generation, including：
Count at least one stroke fragment, the safety trend numerical value is the first number of fragments of the first numerical value, and
Count at least one stroke fragment, the safety trend numerical value is the second number of fragments of second value；
The assessment score of the stroke to be assessed is calculated according to first number of fragments and second number of fragments.
6. a kind of apparatus for evaluating of driving behavior, it is characterised in that including：
Acquisition module, the vehicle operation data for obtaining stroke to be assessed, wherein, the vehicle operation data includes multiple rows
Sail the alert data of index item；
Segmentation module, for splitting to the stroke to be assessed according to prefixed time interval, obtains the stroke to be assessed
Corresponding at least one stroke fragment；
First determining module, for based on default assessment models, according to multiple traveling indexs that each stroke fragment includes
The alert data of item determines the safety trend numerical value of corresponding stroke fragment；
Generation module, for stroke to be assessed described in the safety trend numerical generation according at least one stroke fragment
Assessment result.
7. device as claimed in claim 6, it is characterised in that the segmentation module is used for：
Judge whether the stroke to be assessed collides event according to the vehicle operation data；
In the event of collision accident, it is determined that the time point of the event that collides, and by the stroke, it is with the time point
Terminal, length are the time period of the prefixed time interval, used as the corresponding stroke fragment of the stroke to be assessed；Or
If not colliding event, the stroke to be assessed is split according to the prefixed time interval, obtain many
Individual stroke fragment.
8. device as claimed in claim 6, it is characterised in that also include：
Second determining module, for the |input paramete according to the default assessment models quantity determine the Preset Time between
Every length.
9. device as claimed in claim 6, it is characterised in that also set up module including assessment models, be used for：
The vehicle operation data of multiple sample strokes is obtained, wherein, the vehicle operation data includes multiple traveling index item
Sample alert data；
The multiple stroke is divided according to the stroke event that whether collides, obtains the first kind row of the event of colliding
The Equations of The Second Kind stroke of journey and the event that do not collide；
For each first kind stroke, the time point of the event that determines to collide in the first kind stroke, and by described first
In class stroke, with the time point as terminal, time period of the length as prefixed time interval, as first kind stroke correspondence
Stroke fragment；
For each Equations of The Second Kind stroke, the Equations of The Second Kind stroke is split according to the prefixed time interval, obtain described
Multiple stroke fragments of Equations of The Second Kind stroke；
The sample alert data of the multiple traveling index item included according to the corresponding stroke fragment of the multiple sample stroke is carried out
Model training, sets up the assessment models.
10. the device as described in claim any one of 6-9, it is characterised in that the generation module is used for：
Count at least one stroke fragment, the safety trend numerical value is the first number of fragments of the first numerical value, and
Count at least one stroke fragment, the safety trend numerical value is the second number of fragments of second value；
The assessment score of the stroke to be assessed is calculated according to first number of fragments and second number of fragments.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611060709.6A CN106781454B (en) | 2016-11-25 | 2016-11-25 | The appraisal procedure and device of driving behavior |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611060709.6A CN106781454B (en) | 2016-11-25 | 2016-11-25 | The appraisal procedure and device of driving behavior |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106781454A true CN106781454A (en) | 2017-05-31 |
| CN106781454B CN106781454B (en) | 2019-07-19 |
Family
ID=58913224
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201611060709.6A Active CN106781454B (en) | 2016-11-25 | 2016-11-25 | The appraisal procedure and device of driving behavior |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106781454B (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107730028A (en) * | 2017-09-18 | 2018-02-23 | 广东翼卡车联网服务有限公司 | A kind of car accident recognition methods, car-mounted terminal and storage medium |
| CN108389072A (en) * | 2018-01-23 | 2018-08-10 | 武汉康慧然信息技术咨询有限公司 | Cost management method during p2p vehicles are rented |
| WO2019056498A1 (en) * | 2017-09-19 | 2019-03-28 | 平安科技（深圳）有限公司 | Driving model training method, driver recognition method, device, apparatus and medium |
| WO2019056470A1 (en) * | 2017-09-19 | 2019-03-28 | 平安科技（深圳）有限公司 | Driving model training method, driver recognition method and apparatus, device, and medium |
| CN110210980A (en) * | 2018-06-15 | 2019-09-06 | 腾讯科技（深圳）有限公司 | A kind of driving behavior appraisal procedure, device and storage medium |
| CN111833480A (en) * | 2019-04-12 | 2020-10-27 | 比亚迪股份有限公司 | Driving behavior detection method and device and vehicle |
| CN112734147A (en) * | 2019-10-28 | 2021-04-30 | 北京京东乾石科技有限公司 | Method and device for equipment evaluation management |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103198685A (en) * | 2013-03-15 | 2013-07-10 | Tcl集团股份有限公司 | Method and system for achieving driving safety early warning |
| WO2014076841A1 (en) * | 2012-11-19 | 2014-05-22 | パイオニア株式会社 | Display apparatus, control method, program, and recording medium |
| CN103871242A (en) * | 2014-04-01 | 2014-06-18 | 北京工业大学 | Driving behavior comprehensive evaluation system and method |
| US20140309881A1 (en) * | 2011-02-18 | 2014-10-16 | Honda Motor Co., Ltd. | System and method for responding to driver behavior |
| CN105593095A (en) * | 2013-10-02 | 2016-05-18 | 雅马哈发动机株式会社 | Driving skill evaluation method, driving skill evaluation program, driving skill evaluation device, and vehicle equipped therewith |
| CN105761002A (en) * | 2016-02-22 | 2016-07-13 | 上汽通用汽车有限公司 | Driving behavior evaluation method and driving behavior evaluation system |
-
2016
- 2016-11-25 CN CN201611060709.6A patent/CN106781454B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140309881A1 (en) * | 2011-02-18 | 2014-10-16 | Honda Motor Co., Ltd. | System and method for responding to driver behavior |
| WO2014076841A1 (en) * | 2012-11-19 | 2014-05-22 | パイオニア株式会社 | Display apparatus, control method, program, and recording medium |
| CN103198685A (en) * | 2013-03-15 | 2013-07-10 | Tcl集团股份有限公司 | Method and system for achieving driving safety early warning |
| CN105593095A (en) * | 2013-10-02 | 2016-05-18 | 雅马哈发动机株式会社 | Driving skill evaluation method, driving skill evaluation program, driving skill evaluation device, and vehicle equipped therewith |
| CN103871242A (en) * | 2014-04-01 | 2014-06-18 | 北京工业大学 | Driving behavior comprehensive evaluation system and method |
| CN105761002A (en) * | 2016-02-22 | 2016-07-13 | 上汽通用汽车有限公司 | Driving behavior evaluation method and driving behavior evaluation system |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107730028A (en) * | 2017-09-18 | 2018-02-23 | 广东翼卡车联网服务有限公司 | A kind of car accident recognition methods, car-mounted terminal and storage medium |
| WO2019056498A1 (en) * | 2017-09-19 | 2019-03-28 | 平安科技（深圳）有限公司 | Driving model training method, driver recognition method, device, apparatus and medium |
| WO2019056470A1 (en) * | 2017-09-19 | 2019-03-28 | 平安科技（深圳）有限公司 | Driving model training method, driver recognition method and apparatus, device, and medium |
| CN108389072A (en) * | 2018-01-23 | 2018-08-10 | 武汉康慧然信息技术咨询有限公司 | Cost management method during p2p vehicles are rented |
| CN108389072B (en) * | 2018-01-23 | 2020-12-22 | 深圳市至尊汽车服务有限公司 | Method for managing fees in p2p vehicle renting process |
| CN110210980A (en) * | 2018-06-15 | 2019-09-06 | 腾讯科技（深圳）有限公司 | A kind of driving behavior appraisal procedure, device and storage medium |
| CN111833480A (en) * | 2019-04-12 | 2020-10-27 | 比亚迪股份有限公司 | Driving behavior detection method and device and vehicle |
| CN112734147A (en) * | 2019-10-28 | 2021-04-30 | 北京京东乾石科技有限公司 | Method and device for equipment evaluation management |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106781454B (en) | 2019-07-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106781454B (en) | The appraisal procedure and device of driving behavior | |
| CN106585635B (en) | Driving behavior methods of marking and device | |
| CN106240571B (en) | Driving behavior analysis method and apparatus | |
| CN105427606B (en) | Road condition information gathers and dissemination method | |
| CN109242251A (en) | Vehicular behavior safety detecting method, device, equipment and storage medium | |
| CN107066787B (en) | The methods of marking and device of vehicle travel | |
| DE102013222634B4 (en) | A method of predicting a road friction coefficient and method of operating a motor vehicle | |
| CN106740864A (en) | A kind of driving behavior is intended to judge and Forecasting Methodology | |
| CN106777907A (en) | Driving behavior methods of marking and device | |
| WO2020229116A1 (en) | Method for training at least one algorithm for a control unit of a motor vehicle, computer program product, motor vehicle and system | |
| CN105501220A (en) | Vehicle collision warning method and device and vehicle | |
| CN108447308A (en) | A kind of intersection vehicles risk of collision prediction technique and system based on bus or train route collaboration | |
| CN106557663A (en) | Driving behavior methods of marking and device | |
| CN106448265A (en) | Collecting method and device of driver's driving behavior data | |
| CN106570560B (en) | Driving style quantitative evaluation method based on standardization driving behavior and phase space reconfiguration | |
| CN106097709A (en) | Driving behavior recognition methods based on intelligent vehicle mounted terminal | |
| Tenbrock et al. | The conscend dataset: Concrete scenarios from the highd dataset according to alks regulation unece r157 in openx | |
| CN106777776A (en) | A kind of vehicle lane-changing decision-making technique based on supporting vector machine model | |
| CN110239556B (en) | Driver instant control ability sensing method | |
| CN116466644B (en) | Vehicle performance supervision system and method based on PLC control | |
| CN116034345A (en) | Method and system for testing a driver assistance system | |
| JP6694995B1 (en) | Lane change evaluation device and lane change evaluation method | |
| Huber et al. | Evaluation of virtual traffic situations for testing automated driving functions based on multidimensional criticality analysis | |
| CN115576224A (en) | Simulation test and evaluation method for adaptive cruise control system | |
| TWI496709B (en) | Car driving behavior analysis system and its device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |