CN107585164B - A kind of method and device for the driver that classifies - Google Patents
A kind of method and device for the driver that classifies Download PDFInfo
- Publication number
- CN107585164B CN107585164B CN201710784429.8A CN201710784429A CN107585164B CN 107585164 B CN107585164 B CN 107585164B CN 201710784429 A CN201710784429 A CN 201710784429A CN 107585164 B CN107585164 B CN 107585164B
- Authority
- CN
- China
- Prior art keywords
- driver
- sample data
- driving behavior
- ratio
- behavior sample
- 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
Landscapes
- Traffic Control Systems (AREA)
- Control Of Driving Devices And Active Controlling Of Vehicle (AREA)
Abstract
The invention discloses the method and devices of driver that classifies a kind of, belong to driving behavior analysis technical field.The described method includes: obtaining the sample data sets of M driver;According to the sample data sets of each driver in the M driver, the Euclidean distance matrix between the driving behavior sample data of any two driver in the M driver is calculated;According to the Euclidean distance matrix between the driving behavior sample data of any two driver in the M driver, the M driver is clustered at least one driver cluster.Described device includes: to obtain module, computing module and determining module.The present invention may be implemented to classify to driver.
Description
Technical field
The present invention relates to driving behavior analysis technical field, in particular to a kind of method and device for the driver that classifies.
Background technique
Large number of (China's automobile driver sum is more than 200,000,000 people) of automobile driver, due to each driver
The education of receiving, the makings of locating environment and individual, individual character, health degree are different, and the driving of each driver is practised
It is used to be all different.Therefore in driving behavior data analysis process, the driving behavior habit distinguished between different drivers is
It is no similar, and a large amount of driver is accurately carried out sorting out to be very important.However, at present but not to driver into
The method of row classification, therefore how to classify to driver, it is current urgent problem.
Summary of the invention
In order to solve relevant issues, the present invention provides the method and devices of driver that classifies a kind of.The technical solution
It is as follows:
In a first aspect, the present invention provides the methods of driver that classifies a kind of, which comprises
The sample data sets of M driver are obtained, the sample data sets of driver include acquisition in N number of unit time
Driving behavior sample data, the driving behavior sample data includes the travel speed of the driver-operated vehicle, vehicle
Transversal displacement in road, operating range in the unit time, gas pedal depth in the unit time, in the unit time brake pedal into
Depth, steering wheel angle angular speed, transverse acceleration, vehicle angular speed, running distance and leading vehicle distance in the unit time, before described
Vehicle distance is the distance between the vehicle and front truck, and the front truck is traveling in same lane before the vehicle and from institute
The nearest automobile of vehicle is stated, M and N are respectively the integer of size 1;
According to the sample data sets of each driver in the M driver, appointing in the M driver is calculated
Euclidean distance between the driving behavior sample data of two drivers of anticipating, the Euclidean distance is for reflecting described two driving
The similar degree of driving habit of member;
According to the Euclidean distance between the driving behavior sample data of any two driver in the M driver,
The M driver is clustered at least one driver cluster.
Optionally, the sample data sets according to each driver in the M driver calculate the M
Euclidean distance between the driving behavior sample data of any two driver in driver, comprising:
Travel speed, acceleration and the leading vehicle distance that driving behavior sample data according to each driver includes,
The sample data sets of each driver are divided into multiple first sets respectively;
According to the corresponding first set of each driver, the eigenmatrix of each driver, driver are calculated
Eigenmatrix be used to react the driving habit of the driver;
According to the eigenmatrix of each driver, between the driving behavior sample data for calculating any two driver
Euclidean distance.
Optionally, the driving behavior sample data according to each driver includes travel speed and front truck away from
From the sample data sets of each driver are divided into multiple first sets respectively, comprising:
The travel speed that each driving behavior sample data that sample data sets according to the first driver include includes
Running time needed for calculating the complete leading vehicle distance of the vehicle driving with leading vehicle distance obtains each driving behavior sample
The corresponding running time of notebook data, the first driver are any driver in the M driver;
The driving behavior sample data that running time is less than or equal to default first time threshold is divided into and follows driving
Set, is greater than default first time threshold for running time and the driving behavior sample data for being less than default second time threshold is drawn
It assigns to limited drive to gather, the driving behavior sample data that running time is greater than or equal to default third time threshold is divided into
Freely drive set.
Optionally, described according to the corresponding first set of each driver, calculate the feature of each driver
Matrix, comprising:
According to the travel speed that each driving behavior sample data that the corresponding first set of kid includes includes,
The driving behavior sample data that the corresponding first set of the kid includes is divided into multiple second sets, is located at same
The travel speed in each driving behavior sample data in one second set is located at same speed interval, the kid
For any driver in the M driver;
According to the driving behavior sample data in each second set, calculate that each second set is corresponding multiple to drive
Sail behavioural characteristic value;
By the corresponding driving behavior value of each second set, the corresponding feature square of the kid is formed
Battle array.
Optionally, the driving behavior sample data according in each second set calculates each second set
Corresponding multiple driving behavior values, comprising:
Transversal displacement in the lane for including according to any driving behavior sample data in second set, in the unit time
Operating range, gas pedal depth, brake pedal depth, steering wheel angle angular speed, transverse direction in the unit time in the unit time
Acceleration and vehicle angular speed calculate the corresponding multiple characteristic values of the driving behavior sample data, the multiple characteristic value packet
Include the lane lateral shift value and the first ratio in the unit time between operating range, brake in the unit time
The second ratio between pedal depth and the unit time length, gas pedal depth and the unit in the unit time
The 4th ratio between third ratio, the transverse acceleration and the vehicle angular speed and the direction between time span
Disk corner angular speed;
Corresponding first ratio of each driving behavior sample data that the second set includes is ranked up, from sequence
Select the first ratio for coming target position as a driving behavior value in the first sequence of ratio values afterwards;
Corresponding second ratio of each driving behavior sample data that the second set includes is ranked up, from sequence
Select the second ratio for coming target position as a driving behavior value in the second sequence of ratio values afterwards;
The corresponding third ratio of each driving behavior sample data that the second set includes is ranked up, from sequence
Select the third ratio for coming target position as a driving behavior value in third sequence of ratio values afterwards;
Corresponding 4th ratio of each driving behavior sample data that the second set includes is ranked up, from sequence
Select to come the 4th ratio of target position in the 4th sequence of ratio values afterwards as a driving behavior value;
The corresponding steering wheel angle angular speed of each driving behavior sample data that the second set includes is arranged
Sequence selects the steering wheel angle angular speed for coming target position as one from the steering wheel angle angular speed sequence after sequence
Driving behavior value.
Second aspect, the present invention provides the device of driver that classifies a kind of, described device includes:
Module is obtained, for obtaining the sample data sets of M driver, the sample data sets of driver include N number of
The driving behavior sample data acquired in unit time, the driving behavior sample data includes the driver-operated vehicle
Travel speed, transversal displacement in lane, operating range in the unit time, in the unit time when gas pedal depth, unit
Interior brake pedal depth, steering wheel angle angular speed, transverse acceleration, vehicle angular speed, in the unit time running distance and
Leading vehicle distance, the leading vehicle distance are the distance between the vehicle and front truck, and the front truck is traveling in same lane in institute
It states before vehicle and the automobile nearest from the vehicle, M and N are respectively the integer of size 1;
Computing module calculates the M for the sample data sets according to each driver in the M driver
Euclidean distance between the driving behavior sample data of any two driver in a driver, the Euclidean distance is for anti-
Reflect the similar degree of driving habit of described two drivers;
Determining module, for according to the driving behavior sample data of any two driver in the M driver it
Between Euclidean distance, by the M driver be clustered at least one driver cluster.
Optionally, the computing module includes:
Division unit, travel speed, acceleration for including according to the driving behavior sample data of each driver
The sample data sets of each driver are divided into multiple first sets respectively by degree and leading vehicle distance;
First computing unit, for calculating each driver according to the corresponding first set of each driver
Eigenmatrix, the eigenmatrix of driver is used to react the driving habit of the driver;
Second computing unit calculates between any two driver for the eigenmatrix according to each driver
Euclidean distance.
Optionally, the division unit includes:
First computation subunit, each driving behavior sample for including according to the sample data sets of the first driver
Running time needed for the travel speed and leading vehicle distance that data include calculate the complete leading vehicle distance of the vehicle driving, obtains
The corresponding running time of each driving behavior sample data, the first driver are any driving in the M driver
Member;
First divides subelement, for running time to be less than or equal to the driving behavior sample of default first time threshold
Data, which are divided into, follows driving to gather, and running time is greater than default first time threshold and is less than default second time threshold
Driving behavior sample data is divided into limited drive and gathers, and running time is greater than or equal to the driving of default third time threshold
Behavior sample data, which are divided into, freely drives set.
Optionally, first computing unit includes:
Second divides subelement, each driving behavior sample for including according to the corresponding first set of kid
The driving behavior sample data that the corresponding first set of the kid includes is divided by the travel speed that data include
Multiple second sets, the travel speed in each driving behavior sample data in same second set are located at same speed
Section, the kid are any driver in the M driver;
Second computation subunit, for calculating described each according to the driving behavior sample data in each second set
The corresponding multiple driving behavior values of second set;
Form subelement, for will the corresponding driving behavior value of each second set, form described second and drive
The corresponding eigenmatrix of the person of sailing.
Optionally, second computation subunit executes the driving behavior sample number according in each second set
According to calculating the operation of the corresponding multiple driving behavior values of each second set, comprising:
Transversal displacement in the lane for including according to any driving behavior sample data in second set, in the unit time
Operating range, gas pedal depth, brake pedal depth, steering wheel angle angular speed, transverse direction in the unit time in the unit time
Acceleration and vehicle angular speed calculate the corresponding multiple characteristic values of the driving behavior sample data, the multiple characteristic value packet
Include the lane lateral shift value and the first ratio in the unit time between operating range, brake in the unit time
The second ratio between pedal depth and the unit time length, gas pedal depth and the unit in the unit time
The 4th ratio between third ratio, the transverse acceleration and the vehicle angular speed and the direction between time span
Disk corner angular speed;
Corresponding first ratio of each driving behavior sample data that the second set includes is ranked up, from sequence
Select the first ratio for coming target position as a driving behavior value in the first sequence of ratio values afterwards;
Corresponding second ratio of each driving behavior sample data that the second set includes is ranked up, from sequence
Select the second ratio for coming target position as a driving behavior value in the second sequence of ratio values afterwards;
The corresponding third ratio of each driving behavior sample data that the second set includes is ranked up, from sequence
Select the third ratio for coming target position as a driving behavior value in third sequence of ratio values afterwards;
Corresponding 4th ratio of each driving behavior sample data that the second set includes is ranked up, from sequence
Select to come the 4th ratio of target position in the 4th sequence of ratio values afterwards as a driving behavior value;
The corresponding steering wheel angle angular speed of each driving behavior sample data that the second set includes is arranged
Sequence selects the steering wheel angle angular speed for coming target position as one from the steering wheel angle angular speed sequence after sequence
Driving behavior value.
The beneficial effect of the technical scheme provided by the present invention is that:
By obtaining the sample data sets of M driver, according to the sample number of each driver in the M driver
According to set, the Euclidean distance between any two driver in the M driver is calculated, according to appointing in the M driver
The Euclidean distance anticipated between two drivers determines that at least one driver clusters, divides so as to realize driver
Class.
Detailed description of the invention
Fig. 1 is a kind of method flow diagram for classification driver that the embodiment of the present invention 1 provides;
Fig. 2 is a kind of method flow diagram for classification driver that the embodiment of the present invention 2 provides;
Fig. 3 is a kind of square law device structural schematic diagram for classification driver that the embodiment of the present invention 3 provides;
Fig. 4 is a kind of square law device structural schematic diagram for classification driver that the embodiment of the present invention 4 provides.
Specific embodiment
To make the object, technical solutions and advantages of the present invention clearer, below in conjunction with attached drawing to embodiment party of the present invention
Formula is described in further detail.
Embodiment 1
Referring to Fig. 1, the embodiment of the invention provides the methods of driver that classifies a kind of, comprising:
Step 101: obtaining the sample data sets of M driver.
Wherein, the sample data sets of driver include the driving behavior sample data acquired in N number of unit time, this is driven
Behavior sample data are sailed to include the travel speed of driver-operated vehicle, transversal displacement in lane, travel in the unit time
Distance, gas pedal depth in the unit time, steering wheel angle angular speed, laterally accelerate brake pedal depth in the unit time
Degree, vehicle angular speed, running distance and leading vehicle distance in the unit time, the leading vehicle distance be between the vehicle and front truck away from
From in the same lane of front truck for traveling before the vehicle and the automobile nearest from the vehicle, M and N are respectively the whole of size 1
Number.
Step 102: according to the sample data sets of each driver in the M driver, calculating in the M driver
Any two driver driving behavior sample data between Euclidean distance.
Wherein, Euclidean distance is for reflecting the similar degree of the driving habit of two drivers.
Step 103: according to the Euclidean distance between any two driver in the M driver, by the M driver
It is clustered at least one driver cluster.
In embodiments of the present invention, the sample data sets for obtaining M driver, according to each of the M driver
The sample data sets of driver calculate the Euclidean distance between any two driver in the M driver, according to the M
The Euclidean distance between any two driver in a driver determines that at least one driver clusters, so as to realize
Classify to driver.In addition, being gathered according to the Euclidean distance between any two driver in the M driver
Class can not need default classification in advance in this way.
Embodiment 2
Referring to fig. 2, the embodiment of the invention provides the methods of driver that classifies a kind of, comprising:
Step 201: obtaining the sample data sets of M driver.
Wherein, the sample data sets of driver include the driving behavior sample data acquired in N number of unit time, this is driven
Behavior sample data are sailed to include the travel speed of driver-operated vehicle, transversal displacement in lane, travel in the unit time
Distance, gas pedal depth in the unit time, steering wheel angle angular speed, laterally accelerate brake pedal depth in the unit time
Degree, vehicle angular speed, running distance and leading vehicle distance in the unit time, the leading vehicle distance be between the vehicle and front truck away from
From front truck is to travel automobile before the vehicle and nearest from the vehicle in same lane with the vehicle, and M and N are respectively
The integer of size 1.
The sample data sets of driver can be obtained by driving simulator, or by the way that at least one is arranged on vehicle
A sensor obtains the sample data sets of driver.
For driving simulator obtain driver sample data sets by way of, in actual implementation, Ke Yirang
Any one driver drives the driving simulator.During the driver drives the driving simulator, every a unit
Time just drives the travel speed of vehicle, acceleration, transversal displacement, list in lane from reading the driver in the drive simulation
Operating range, gas pedal depth, brake pedal depth, steering wheel angle angle speed in the unit time in the unit time in the time of position
Degree, transverse acceleration, vehicle angular speed, the data such as running distance and leading vehicle distance in the unit time, when can also obtain current
Between, turn signal state and the video data etc. to driver shooting.The data that will finally be read from the driving simulator
Form a driving behavior sample data of the driver within the current one time.N number of unit time is acquired in a manner described
N number of driving behavior sample data is formed the sample data sets of the driver by interior driving behavior sample data.
By way of sample data sets for obtaining driver by the way that at least one sensor is arranged on vehicle, in reality
When border is realized, it can be arranged in vehicle and accelerate in location settings sensors such as steering wheel for vehicle, gas pedal and brake pedals
It spends sensor and radar is set in the headstock position of vehicle, a driver then can be allowed to drive the vehicle.In the driving
Member drives the process of the vehicle driving, every a unit time from being arranged in steering wheel for vehicle, gas pedal and brake pedal
On sensor obtain steering wheel angle angular speed, in the unit time gas pedal depth and in the unit time brake pedal into
It is deep;According to lateral in the travel speed of data acquisition driver driving vehicle of acceleration transducer output, acceleration, lane
Offset, operating range, transverse acceleration, vehicle angular speed and running distance in the unit time in the unit time, and pass through
Radar positioned at headstock obtains leading vehicle distance.Current time can also be obtained, turn signal state and to driver shooting
Video data etc..The steering wheel angle angular speed that finally will acquire, gas pedal depth in the unit time are braked in the unit time
Pedal depth, travel speed, acceleration, transversal displacement, operating range, transverse acceleration, vehicle in the unit time in lane
Angular speed, the data such as running distance and leading vehicle distance form one within the current one time of the driver and drive in the unit time
Sail behavior sample data.The driving behavior sample data in N number of unit time is acquired in a manner described, by N number of driving behavior
Sample data forms the sample data sets of the driver.
Wherein, N can be with integer values such as values 1000,2000,3000.M can be with the integer values such as 100,2000,10000.
Step 202: the travel speed and leading vehicle distance that the driving behavior sample data according to each driver includes, respectively
The sample data sets of each driver are divided into multiple first sets.
Wherein, first set includes following driving set, limited driving set and freely driving set.This step can lead to
Following two steps are crossed to realize, comprising:
2021: the traveling that each driving behavior sample data that the sample data sets according to the first driver include includes
Running time needed for speed, acceleration and leading vehicle distance calculate the complete leading vehicle distance of vehicle driving obtains each driving row
For the corresponding running time of sample data, the first driver is any driver in M driver.
For any one driving behavior sample data in the sample data sets of the first driver, according to the driving behavior
The travel speed and leading vehicle distance that sample data includes calculate running time required for the complete leading vehicle distance of vehicle driving,
Using the running time as the corresponding running time of sample driving behavior sample data.
It, can be by above-mentioned for other each driving behavior sample datas in the sample data sets of the first driver
Mode calculates the corresponding running time of other each driving behavior sample datas.
2022: the driving behavior sample data that running time is less than or equal to default first time threshold being divided into and is followed
Set is driven, running time is greater than default first time threshold and is less than the driving behavior sample number of default second time threshold
Gather according to limited drive is divided into, the driving behavior sample data that running time is greater than or equal to default third time threshold is drawn
It assigns to and freely drives set.
For example, it is assumed that default first time threshold is 6 seconds, presetting second time threshold is 12 seconds, then running time is small
Being divided into or equal to 6 seconds driving behavior sample datas follows driving to gather, and running time is greater than 6 seconds and less than 12 seconds
Driving behavior sample data is divided into limited drive and gathers, and running time is greater than or equal to 12 seconds driving behavior samples
Data, which are divided into, freely drives set.
Step 203: including according to each driving behavior sample data that the corresponding first set of kid includes
The driving behavior sample data that the corresponding first set of the kid includes is divided into multiple second collection by travel speed
It closes.
Wherein, the travel speed in each driving behavior sample data in same second set is located at same speed
Section, kid are any driver in M driver.
Multiple speed intervals can be set in advance, for each driving behavior sample data in first set, determine every
The travel speed for including is located at same speed area by the speed interval where the travel speed that a driving behavior sample data includes
Between driving behavior sample data be divided into same second set.
Step 204: according to the driving behavior sample data in the corresponding each second set of kid, calculating each
The corresponding multiple driving behavior values of second set.
Driving behavior value is used to describe the driving behavior habit of driver.
This step can be realized by the following steps, comprising:
2041: for each second set, the vehicle for including according to any driving behavior sample data in the second set
Transversal displacement in road, operating range in the unit time, gas pedal depth in the unit time, in the unit time brake pedal into
Depth, steering wheel angle angular speed, transverse acceleration and vehicle angular speed calculate the corresponding multiple spies of the driving behavior sample data
Value indicative.
Wherein, multiple characteristic value include the lane lateral shift value and in the unit time between operating range first
Ratio, the second ratio in the unit time between brake pedal depth and the unit time length, throttle in the unit time
The 4th ratio between third ratio, the transverse acceleration and the vehicle angular speed between pedal depth and the unit time length
Value and direction disk corner angular speed.
2042: corresponding first ratio of each driving behavior sample data that the second set includes is ranked up, from
Select the first ratio for coming target position as a driving behavior value in the first sequence of ratio values after sequence.
Between the driving behavior sample data total number that target position can be preset ratio and the second set includes
Product.
For example, it is assumed that preset ratio is 0.85, the driving behavior sample data total number which includes is
200, target position 170.The second set includes corresponding first ratio of 200 driving behavior sample datas in this way, to this
200 the first ratios are ranked up, select to come from the first sequence of ratio values after sequence the first ratio of the 170th position as
One driving behavior value.
2043: corresponding second ratio of each driving behavior sample data that the second set includes is ranked up, from
Select the second ratio for coming target position as a driving behavior value in the second sequence of ratio values after sequence.
2044: the corresponding third ratio of each driving behavior sample data that the second set includes is ranked up, from
Select the third ratio for coming target position as a driving behavior value in third sequence of ratio values after sequence.
2045: corresponding 4th ratio of each driving behavior sample data that the second set includes is ranked up, from
Select to come the 4th ratio of target position in the 4th sequence of ratio values after sequence as a driving behavior value.
2046: the corresponding steering wheel angle angular speed of each driving behavior sample data that the second set includes is carried out
Sequence, selects the steering wheel angle angular speed for coming target position as one from the steering wheel angle angular speed sequence after sequence
A driving behavior value.
The corresponding driving behavior value of second set includes five.Kid corresponds to multiple second sets, by upper
The corresponding five driving behavior values of the available each second set of the step of step 2041 is stated to 2046.
Step 205: by the corresponding driving behavior value of each second set, forming the corresponding feature square of kid
Battle array.
The corresponding five driving behavior values of each second set.It is assumed that kid corresponds to four second sets, then
The eigenmatrix of 5x4 can be formed.
For other each drivers in the M driver by above-mentioned kid in the way of to calculate other every
The eigenmatrix of a driver.The eigenmatrix of driver can react the driving habit of driver.
Step 206: according to the eigenmatrix of each driver, calculating the driving behavior sample data of any two driver
Between Euclidean distance.
Euclidean distance between the driving behavior sample data of two drivers is used to reflect the driving of two drivers
It is accustomed to similar degree.
This step can be that the eigenmatrix of each driver is formed a whole matrix, every row of the whole matrix
A corresponding driver, which includes the eigenmatrix of the corresponding driver of the row.It is calculating between any two driver
When Euclidean distance, the corresponding row of two drivers is read from whole matrix, it is corresponding according to two drivers of reading
Row calculates the Euclidean distance between two drivers by the preset algorithm for calculating Euclidean distance.
For any row in whole matrix, it is assumed that the eigenmatrix of the corresponding driver of the row isThen
The corresponding a line of the driver can be [a1, b1, c1, a2, b2, c2, a3, b3, c3] in whole matrix.
Wherein, the algorithm for calculating Euclidean distance can be euclidean (Euclidean distance)
Step 207: according to the Euclidean between the driving behavior sample data of any two driver in the M driver
The M driver is clustered at least one driver cluster by distance.
This step may include following two steps, be respectively as follows:
2071: according to the Euclidean between the driving behavior sample data of any two driver in the M driver away from
From building MxM-1 Euclidean matrix, every row in M row in the Euclidean matrix corresponds to a driver, each column pair in M-1 column
A driver is answered, which includes the Euclidean distance between any two driver.
2072: the Euclidean distance of corresponding a line of each driver in the Euclidean matrix is read, according to the driver couple
The Euclidean distance of a line answered calculates the corresponding planar point coordinate of the driver by preset algorithm.
Preset algorithm can be MDS (Multidimensional Scaling, Multidimensional Scaling) algorithm.
2073: according to the corresponding planar point coordinate of each driver, by preset kmeans algorithm by the M driver
It is clustered into predetermined number driver cluster.
It may include multiple predetermined numbers, respectively a1, a2 ... an, n are default integer.Kmeans algorithm can export
A1 driver's cluster and the corresponding silhouette coefficient of a1 export a2 driver's cluster and the corresponding silhouette coefficient ... of a2
An driver's cluster of output and the corresponding silhouette coefficient of an.Effect of the silhouette coefficient to assess cluster, value is bigger, table
Show that corresponding classifying quality is better.Then the corresponding predetermined number a of selection largest contours coefficient, a driver of output is gathered
Class is clustered as final driver.
Due to obtaining multiple first sets in step 203, above-mentioned steps 203 to 207 are executed to each first set
Operation obtains driver's cluster.
Step 208: being clustered according to obtained driver, in conjunction with the whole matrix that M driver forms, utilize preset point
Class tree algorithm obtains driver's disaggregated model.
Driver's disaggregated model includes that each driver clusters corresponding multiple driving behavior sample data ranges, multiple
Driving behavior sample data range is respectively gas pedal depth range, brake pedal depth model in the unit time in the unit time
It encloses, steering wheel angle angular velocity range, transverse acceleration range and steering wheel angle angular velocity range etc..
In the present embodiment, after executing the step 207, if getting the sample data set of the M+1 driver
It closes;Determine the driving behavior sample where each driving behavior sample data in the sample data sets of the M+1 driver
Data area determines driver's cluster where the M+1 driver according to determining driving behavior sample data range.
It, can be according to the driving of the driver of same cluster since the driving habit for being located at the driver of same cluster is similar
It is accustomed to providing service to the driver for being located at the cluster.For example, it is assumed that the driving habit of each driver of the cluster be drive compared with
It for ferociousness, can travel in this way as each driver of the cluster at relatively hazardous section, prompt letter can be sent to driver
Breath, the prompt information are taken care traveling for prompting the driver.
In embodiments of the present invention, the sample data sets for obtaining M driver, according to each of the M driver
The sample data sets of driver calculate the Euclidean distance between any two driver in the M driver, according to the M
The Euclidean distance between any two driver in a driver, using Kmeans clustering method, preset classification number be 2,3,
4,5,6,7,8,9,10 class, then calculates the silhouette coefficient of different classifications number, and the selection highest classification number of silhouette coefficient is target
Classification number, classifies to driver so as to realize.
Following is embodiment of the present disclosure, can be used for executing embodiments of the present disclosure.It is real for disclosure device
Undisclosed details in example is applied, embodiments of the present disclosure is please referred to.
Embodiment 3
Referring to Fig. 3, the embodiment of the invention provides the device 300 of driver that classifies a kind of, described device 300 includes:
Module 301 is obtained, for obtaining the sample data sets of M driver, the sample data sets of driver include N
The driving behavior sample data acquired in a unit time, the driving behavior sample data includes the driver-operated vehicle
Travel speed, acceleration, transversal displacement in lane, operating range in the unit time, in the unit time gas pedal into
Brake pedal depth, steering wheel angle angular speed, transverse acceleration, vehicle angular speed, unit time expert in the deep, unit time
Vehicle distance and leading vehicle distance, the leading vehicle distance are the distance between the vehicle and front truck, and the front truck is in same lane
Automobile before the vehicle and nearest from the vehicle is travelled, M and N are respectively the integer of size 1;
Computing module 302 calculates institute for the sample data sets according to each driver in the M driver
The Euclidean distance between the driving behavior sample data of any two driver in M driver is stated, the Euclidean distance is used
In the similar degree of driving habit for reflecting described two drivers;
Determining module 303, for inciting somebody to action according to the Euclidean distance between any two driver in the M driver
The M driver is clustered at least one driver cluster.
Optionally, the computing module 302 includes:
Division unit, travel speed and front truck for including according to the driving behavior sample data of each driver
The sample data sets of each driver are divided into multiple first sets respectively by distance;
First computing unit, for calculating each driver according to the corresponding first set of each driver
Eigenmatrix, the eigenmatrix of driver is used to react the driving habit of the driver;
Second computing unit calculates driving for any two driver for the eigenmatrix according to each driver
Sail the Euclidean distance between behavior sample data.
Optionally, the division unit includes:
First computation subunit, each driving behavior sample for including according to the sample data sets of the first driver
Travel speed, acceleration and the leading vehicle distance that data include calculate needed for the complete leading vehicle distance of the vehicle driving when driving
Between, the corresponding running time of each driving behavior sample data is obtained, the first driver is appointing in the M driver
One driver;
First divides subelement, for running time to be less than or equal to the driving behavior sample of default first time threshold
Data, which are divided into, follows driving to gather, and running time is greater than default first time threshold and is less than default second time threshold
Driving behavior sample data is divided into limited drive and gathers, and running time is greater than or equal to the driving of default third time threshold
Behavior sample data, which are divided into, freely drives set.
Optionally, first computing unit includes:
Second divides subelement, each driving behavior sample for including according to the corresponding first set of kid
The driving behavior sample data that the corresponding first set of the kid includes is divided by the travel speed that data include
Multiple second sets, the travel speed in each driving behavior sample data in same second set are located at same speed
Section, the kid are any driver in the M driver;
Second computation subunit, for calculating described each according to the driving behavior sample data in each second set
The corresponding multiple driving behavior values of second set;
Form subelement, for will the corresponding driving behavior value of each second set, form described second and drive
The corresponding eigenmatrix of the person of sailing.
Optionally, second computation subunit executes the driving behavior sample number according in each second set
According to calculating the operation of the corresponding multiple driving behavior values of each second set, comprising:
Transversal displacement in the lane for including according to any driving behavior sample data in second set, in the unit time
Operating range, gas pedal depth, brake pedal depth, steering wheel angle angular speed, transverse direction in the unit time in the unit time
Acceleration and vehicle angular speed calculate the corresponding multiple characteristic values of the driving behavior sample data, the multiple characteristic value packet
Include the lane lateral shift value and the first ratio in the unit time between operating range, brake in the unit time
The second ratio between pedal depth and the unit time length, gas pedal depth and the unit in the unit time
The 4th ratio between third ratio, the transverse acceleration and the vehicle angular speed and the direction between time span
Disk corner angular speed;
Corresponding first ratio of each driving behavior sample data that the second set includes is ranked up, from sequence
Select the first ratio for coming target position as a driving behavior value in the first sequence of ratio values afterwards;
Corresponding second ratio of each driving behavior sample data that the second set includes is ranked up, from sequence
Select the second ratio for coming target position as a driving behavior value in the second sequence of ratio values afterwards;
The corresponding third ratio of each driving behavior sample data that the second set includes is ranked up, from sequence
Select the third ratio for coming target position as a driving behavior value in third sequence of ratio values afterwards;
Corresponding 4th ratio of each driving behavior sample data that the second set includes is ranked up, from sequence
Select to come the 4th ratio of target position in the 4th sequence of ratio values afterwards as a driving behavior value;
The corresponding steering wheel angle angular speed of each driving behavior sample data that the second set includes is arranged
Sequence selects the steering wheel angle angular speed for coming target position as one from the steering wheel angle angular speed sequence after sequence
Driving behavior value.
In embodiments of the present invention, by obtaining the sample data sets of M driver, according in the M driver
The sample data sets of each driver calculate the Euclidean distance between any two driver in the M driver, according to
Euclidean distance between the driving behavior sample data of any two driver in the M driver, determines that at least one is driven
The person's of sailing cluster, classifies to driver so as to realize.
About the device in above-described embodiment, wherein modules execute the concrete mode of operation in related this method
Embodiment in be described in detail, no detailed explanation will be given here.
Fig. 4 is a kind of block diagram of the device 400 of driver that classifies shown according to an exemplary embodiment.For example, device
400 can be mobile phone, computer, digital broadcasting terminal, messaging device, game console, tablet device, and medical treatment is set
It is standby, body-building equipment, personal digital assistant etc..
Referring to Fig. 4, device 400 may include following one or more components: processing component 402, memory 404, power supply
Component 406, multimedia component 408, audio component 410, the interface 412 of input/output (I/O), sensor module 414, and
Communication component 416.
The integrated operation of the usual control device 400 of processing component 402, such as with display, telephone call, data communication, phase
Machine operation and record operate associated operation.Processing component 402 may include that one or more processors 420 refer to execute
It enables, to perform all or part of the steps of the methods described above.In addition, processing component 402 may include one or more modules, just
Interaction between processing component 402 and other assemblies.For example, processing component 402 may include multi-media module, it is more to facilitate
Interaction between media component 408 and processing component 402.
Memory 404 is configured as storing various types of data to support the operation in device 400.These data are shown
Example includes the instruction of any application or method for operating on device 400, contact data, and telephone book data disappears
Breath, picture, video etc..Memory 404 can be by any kind of volatibility or non-volatile memory device or their group
It closes and realizes, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM) is erasable to compile
Journey read-only memory (EPROM), programmable read only memory (PROM), read-only memory (ROM), magnetic memory, flash
Device, disk or CD.
Power supply module 406 provides electric power for the various assemblies of device 400.Power supply module 406 may include power management system
System, one or more power supplys and other with for device 400 generate, manage, and distribute the associated component of electric power.
Multimedia component 408 includes the screen of one output interface of offer between described device 400 and user.One
In a little embodiments, screen may include liquid crystal display (LCD) and touch panel (TP).If screen includes touch panel, screen
Curtain may be implemented as touch screen, to receive input signal from the user.Touch panel includes one or more touch sensings
Device is to sense the gesture on touch, slide, and touch panel.The touch sensor can not only sense touch or sliding action
Boundary, but also detect duration and pressure associated with the touch or slide operation.In some embodiments, more matchmakers
Body component 408 includes a front camera and/or rear camera.When device 400 is in operation mode, such as screening-mode or
When video mode, front camera and/or rear camera can receive external multi-medium data.Each front camera and
Rear camera can be a fixed optical lens system or have focusing and optical zoom capabilities.
Audio component 410 is configured as output and/or input audio signal.For example, audio component 410 includes a Mike
Wind (MIC), when device 400 is in operation mode, when such as call mode, recording mode, and voice recognition mode, microphone is matched
It is set to reception external audio signal.The received audio signal can be further stored in memory 404 or via communication set
Part 416 is sent.In some embodiments, audio component 410 further includes a loudspeaker, is used for output audio signal.
I/O interface 412 provides interface between processing component 402 and peripheral interface module, and above-mentioned peripheral interface module can
To be keyboard, click wheel, button etc..These buttons may include, but are not limited to: home button, volume button, start button and lock
Determine button.
Sensor module 414 includes one or more sensors, and the state for providing various aspects for device 400 is commented
Estimate.For example, sensor module 414 can detecte the state that opens/closes of device 400, and the relative positioning of component, for example, it is described
Component is the display and keypad of device 400, and sensor module 414 can be with 400 1 components of detection device 400 or device
Position change, the existence or non-existence that user contacts with device 400,400 orientation of device or acceleration/deceleration and device 400
Temperature change.Sensor module 414 may include proximity sensor, be configured to detect without any physical contact
Presence of nearby objects.Sensor module 414 can also include optical sensor, such as CMOS or ccd image sensor, at
As being used in application.In some embodiments, which can also include acceleration transducer, gyro sensors
Device, Magnetic Sensor, pressure sensor or temperature sensor.
Communication component 416 is configured to facilitate the communication of wired or wireless way between device 400 and other equipment.Device
400 can access the wireless network based on communication standard, such as WiFi, 2G or 3G or their combination.In an exemplary implementation
In example, communication component 416 receives broadcast singal or broadcast related information from external broadcasting management system via broadcast channel.
In one exemplary embodiment, the communication component 416 further includes near-field communication (NFC) module, to promote short range communication.Example
Such as, NFC module can be based on radio frequency identification (RFID) technology, Infrared Data Association (IrDA) technology, ultra wide band (UWB) technology,
Bluetooth (BT) technology and other technologies are realized.
In the exemplary embodiment, device 400 can be believed by one or more application specific integrated circuit (ASIC), number
Number processor (DSP), digital signal processing appts (DSPD), programmable logic device (PLD), field programmable gate array
(FPGA), controller, microcontroller, microprocessor or other electronic components are realized, for executing the above method.
In the exemplary embodiment, a kind of non-transitorycomputer readable storage medium including instruction, example are additionally provided
It such as include the memory 404 of instruction, above-metioned instruction can be executed by the processor 420 of device 400 to complete the above method.For example,
The non-transitorycomputer readable storage medium can be ROM, random access memory (RAM), CD-ROM, tape, floppy disk
With optical data storage devices etc..
A kind of non-transitorycomputer readable storage medium, when the instruction in the storage medium is by the processing of device 400
When device executes, so that a kind of method that device 400 is able to carry out driver that classifies, which comprises
The sample data sets of M driver are obtained, the sample data sets of driver include acquisition in N number of unit time
Driving behavior sample data, the driving behavior sample data includes the travel speed of the driver-operated vehicle, vehicle
Transversal displacement in road, operating range in the unit time, gas pedal depth in the unit time, in the unit time brake pedal into
Depth, steering wheel angle angular speed, transverse acceleration, vehicle angular speed, running distance and leading vehicle distance in the unit time, before described
Vehicle distance is the distance between the vehicle and front truck, and the front truck is traveling in same lane before the vehicle and from institute
The nearest automobile of vehicle is stated, M and N are respectively the integer of size 1;
According to the sample data sets of each driver in the M driver, appointing in the M driver is calculated
Euclidean distance between the driving behavior sample data of two drivers of anticipating, the Euclidean distance is for reflecting described two driving
The similar degree of driving habit of member;
According to the Euclidean distance between the driving behavior sample data of any two driver in the M driver,
The M driver is clustered at least one driver cluster.
Optionally, the sample data sets according to each driver in the M driver calculate the M
Euclidean distance between the driving behavior sample data of any two driver in driver, comprising:
Travel speed, acceleration and the leading vehicle distance that driving behavior sample data according to each driver includes,
The sample data sets of each driver are divided into multiple first sets respectively;
According to the corresponding first set of each driver, the eigenmatrix of each driver, driver are calculated
Eigenmatrix be used to react the driving habit of the driver;
According to the eigenmatrix of each driver, between the driving behavior sample data for calculating any two driver
Euclidean distance.
Optionally, the driving behavior sample data according to each driver includes travel speed and front truck away from
From the sample data sets of each driver are divided into multiple first sets respectively, comprising:
The travel speed that each driving behavior sample data that sample data sets according to the first driver include includes
Running time needed for calculating the complete leading vehicle distance of the vehicle driving with leading vehicle distance obtains each driving behavior sample
The corresponding running time of notebook data, the first driver are any driver in the M driver;
The driving behavior sample data that running time is less than or equal to default first time threshold is divided into and follows driving
Set, is greater than default first time threshold for running time and the driving behavior sample data for being less than default second time threshold is drawn
It assigns to limited drive to gather, the driving behavior sample data that running time is greater than or equal to default third time threshold is divided into
Freely drive set.
Optionally, described according to the corresponding first set of each driver, calculate the feature of each driver
Matrix, comprising:
According to the travel speed that each driving behavior sample data that the corresponding first set of kid includes includes,
The driving behavior sample data that the corresponding first set of the kid includes is divided into multiple second sets, is located at same
The travel speed in each driving behavior sample data in one second set is located at same speed interval, the kid
For any driver in the M driver;
According to the driving behavior sample data in each second set, calculate that each second set is corresponding multiple to drive
Sail behavioural characteristic value;
By the corresponding driving behavior value of each second set, the corresponding feature square of the kid is formed
Battle array.
Optionally, the driving behavior sample data according in each second set calculates each second set
Corresponding multiple driving behavior values, comprising:
Transversal displacement in the lane for including according to any driving behavior sample data in second set, in the unit time
Operating range, gas pedal depth, brake pedal depth, steering wheel angle angular speed, transverse direction in the unit time in the unit time
Acceleration and vehicle angular speed calculate the corresponding multiple characteristic values of the driving behavior sample data, the multiple characteristic value packet
Include the lane lateral shift value and the first ratio in the unit time between operating range, brake in the unit time
The second ratio between pedal depth and the unit time length, gas pedal depth and the unit in the unit time
The 4th ratio between third ratio, the transverse acceleration and the vehicle angular speed and the direction between time span
Disk corner angular speed;
Corresponding first ratio of each driving behavior sample data that the second set includes is ranked up, from sequence
Select the first ratio for coming target position as a driving behavior value in the first sequence of ratio values afterwards;
Corresponding second ratio of each driving behavior sample data that the second set includes is ranked up, from sequence
Select the second ratio for coming target position as a driving behavior value in the second sequence of ratio values afterwards;
The corresponding third ratio of each driving behavior sample data that the second set includes is ranked up, from sequence
Select the third ratio for coming target position as a driving behavior value in third sequence of ratio values afterwards;
Corresponding 4th ratio of each driving behavior sample data that the second set includes is ranked up, from sequence
Select to come the 4th ratio of target position in the 4th sequence of ratio values afterwards as a driving behavior value;
The corresponding steering wheel angle angular speed of each driving behavior sample data that the second set includes is arranged
Sequence selects the steering wheel angle angular speed for coming target position as one from the steering wheel angle angular speed sequence after sequence
Driving behavior value.
In embodiments of the present invention, by obtaining the sample data sets of M driver, according in the M driver
The sample data sets of each driver calculate the Euclidean distance between any two driver in the M driver, according to
The Euclidean distance between any two driver in the M driver determines that at least one driver clusters, so as to reality
Now classify to driver.
Those of ordinary skill in the art will appreciate that realizing that all or part of the steps of above-described embodiment can pass through hardware
It completes, relevant hardware can also be instructed to complete by program, the program can store in a kind of computer-readable
In storage medium, storage medium mentioned above can be read-only memory, disk or CD etc..
The foregoing is merely presently preferred embodiments of the present invention, is not intended to limit the invention, it is all in spirit of the invention and
Within principle, any modification, equivalent replacement, improvement and so on be should all be included in the protection scope of the present invention.
Claims (6)
1. a kind of method for the driver that classifies, which is characterized in that the described method includes:
The sample data sets of M driver are obtained, the sample data sets of driver include driving for interior acquisition of N number of unit time
Sail behavior sample data, the driving behavior sample data includes the travel speed of the driver-operated vehicle, in lane
Transversal displacement, operating range in the unit time, gas pedal depth in the unit time, brake pedal depth in the unit time,
Steering wheel angle angular speed, transverse acceleration, vehicle angular speed, running distance and leading vehicle distance in the unit time, the front truck
Distance is the distance between the vehicle and front truck, and the front truck is to travel before the vehicle and from described in same lane
The nearest automobile of vehicle, M and N are respectively the integer for being greater than 1;
Travel speed, acceleration and the leading vehicle distance that driving behavior sample data according to each driver includes, respectively
The sample data sets of each driver are divided into multiple first sets;
According to the corresponding first set of each driver, the eigenmatrix of each driver, the spy of driver are calculated
Sign matrix is used to react the driving habit of the driver;
According to the eigenmatrix of each driver, the Europe between the driving behavior sample data of any two driver is calculated
Family name's distance, the Euclidean distance is for reflecting the similar degree of the driving habit of described two drivers;
According to the Euclidean distance building between the driving behavior sample data of any two driver in the M driver
MxM-1 Euclidean matrix, the corresponding driver of every row in M row in the Euclidean matrix, each column in the M-1 column are corresponding
One driver, the Euclidean matrix include the Euclidean distance between any two driver;
The Euclidean distance for reading corresponding a line of each driver in the Euclidean matrix, according to the driver corresponding one
Capable Euclidean distance calculates the corresponding planar point coordinate of the driver by preset algorithm;
It is described according to the corresponding planar point coordinate of each driver, the M driver is gathered by preset kmeans algorithm
Class is clustered at predetermined number driver;
Wherein, the travel speed and leading vehicle distance that the driving behavior sample data according to each driver includes, point
The sample data sets of each driver are not divided into multiple first sets, comprising:
The travel speed that each driving behavior sample data that sample data sets according to the first driver include includes is with before
Running time needed for vehicle distance calculates the complete leading vehicle distance of vehicle driving, obtains each driving behavior sample number
According to corresponding running time, the first driver is any driver in the M driver;
The driving behavior sample data that running time is less than or equal to default first time threshold, which is divided into, follows driving to gather,
Running time is greater than default first time threshold and the driving behavior sample data for being less than default second time threshold is divided into
It is limited to drive set, the driving behavior sample data that running time is greater than or equal to default third time threshold is divided into freedom
Drive set.
2. the method as described in claim 1, which is characterized in that it is described according to the corresponding first set of each driver,
Calculate the eigenmatrix of each driver, comprising:
According to the travel speed that each driving behavior sample data that the corresponding first set of kid includes includes, by institute
It states the driving behavior sample data that the corresponding first set of kid includes and is divided into multiple second sets, be located at same the
The travel speed in each driving behavior sample data in two set is located at same speed interval, and the kid is institute
State any driver in M driver;
According to the driving behavior sample data in each second set, the corresponding multiple driving rows of each second set are calculated
It is characterized value;
By the corresponding driving behavior value of each second set, the corresponding eigenmatrix of the kid is formed.
3. method according to claim 2, which is characterized in that the driving behavior sample number according in each second set
According to calculating the corresponding multiple driving behavior values of each second set, comprising:
Transversal displacement in the lane for including according to any driving behavior sample data in second set travels in the unit time
Distance, gas pedal depth in the unit time, steering wheel angle angular speed, laterally accelerate brake pedal depth in the unit time
Degree and vehicle angular speed, calculate the corresponding multiple characteristic values of the driving behavior sample data, the multiple characteristic value includes institute
State lane lateral shift value and the first ratio in the unit time between operating range, brake pedal in the unit time
The second ratio between depth and the unit time length, gas pedal depth and the unit time in the unit time
The 4th ratio and the steering wheel turn between third ratio, the transverse acceleration and the vehicle angular speed between length
Angle angular speed;
Corresponding first ratio of each driving behavior sample data that the second set includes is ranked up, after sequence
Select the first ratio for coming target position as a driving behavior value in first sequence of ratio values;
Corresponding second ratio of each driving behavior sample data that the second set includes is ranked up, after sequence
Select the second ratio for coming target position as a driving behavior value in second sequence of ratio values;
The corresponding third ratio of each driving behavior sample data that the second set includes is ranked up, after sequence
Select the third ratio for coming target position as a driving behavior value in third sequence of ratio values;
Corresponding 4th ratio of each driving behavior sample data that the second set includes is ranked up, after sequence
Select the 4th ratio for coming target position as a driving behavior value in 4th sequence of ratio values;
The corresponding steering wheel angle angular speed of each driving behavior sample data that the second set includes is ranked up, from
The steering wheel angle angular speed for coming target position is selected to drive in steering wheel angle angular speed sequence after sequence as one
Behavioural characteristic value.
4. a kind of device for the driver that classifies, which is characterized in that described device includes:
Module is obtained, for obtaining the sample data sets of M driver, the sample data sets of driver include N number of unit
The driving behavior sample data acquired in time, the driving behavior sample data includes the row of the driver-operated vehicle
Sail speed, transversal displacement in lane, operating range in the unit time, gas pedal depth in the unit time, in the unit time
Brake pedal depth, steering wheel angle angular speed, transverse acceleration, vehicle angular speed, running distance and front truck in the unit time
Distance, the leading vehicle distance are the distance between the vehicle and front truck, and the front truck is to travel in same lane in the vehicle
Before and the automobile nearest from the vehicle, M and N are respectively the integer for being greater than 1;
Division unit, travel speed, acceleration for including according to the driving behavior sample data of each driver and
The sample data sets of each driver are divided into multiple first sets respectively by leading vehicle distance;
First computing unit, for calculating the spy of each driver according to the corresponding first set of each driver
Matrix is levied, the eigenmatrix of driver is used to react the driving habit of the driver;
Second computing unit calculates the driving row of any two driver for the eigenmatrix according to each driver
Euclidean distance between sample data, the Euclidean distance is for reflecting the similar journey of the driving habit of described two drivers
Degree;
Determining module, between the driving behavior sample data according to any two driver in the M driver
The M driver is clustered at least one driver cluster by Euclidean distance;
Wherein, the Euclidean between the driving behavior sample data according to any two driver in the M driver
The M driver is clustered at least one driver cluster by distance, comprising:
According to the Euclidean distance building between the driving behavior sample data of any two driver in the M driver
MxM-1 Euclidean matrix, the corresponding driver of every row in M row in the Euclidean matrix, each column in the M-1 column are corresponding
One driver, the Euclidean matrix include the Euclidean distance between any two driver;
The Euclidean distance for reading corresponding a line of each driver in the Euclidean matrix, according to the driver corresponding one
Capable Euclidean distance calculates the corresponding planar point coordinate of the driver by preset algorithm;
It is described according to the corresponding planar point coordinate of each driver, the M driver is gathered by preset kmeans algorithm
Class is clustered at predetermined number driver;
Wherein, the travel speed and leading vehicle distance that the driving behavior sample data according to each driver includes, point
The sample data sets of each driver are not divided into multiple first sets, comprising:
The travel speed that each driving behavior sample data that sample data sets according to the first driver include includes is with before
Running time needed for vehicle distance calculates the complete leading vehicle distance of vehicle driving, obtains each driving behavior sample number
According to corresponding running time, the first driver is any driver in the M driver;
The driving behavior sample data that running time is less than or equal to default first time threshold, which is divided into, follows driving to gather,
Running time is greater than default first time threshold and the driving behavior sample data for being less than default second time threshold is divided into
It is limited to drive set, the driving behavior sample data that running time is greater than or equal to default third time threshold is divided into freedom
Drive set.
5. device as claimed in claim 4, which is characterized in that first computing unit includes:
Second divides subelement, each driving behavior sample data for including according to the corresponding first set of kid
Including travel speed, the driving behavior sample data that the corresponding first set of the kid includes is divided into multiple
Second set, the travel speed in each driving behavior sample data in same second set are located at same speed area
Between, the kid is any driver in the M driver;
Second computation subunit, for calculating described each second according to the driving behavior sample data in each second set
Gather corresponding multiple driving behavior values;
Subelement is formed, for forming the kid for the corresponding driving behavior value of each second set
Corresponding eigenmatrix.
6. device as claimed in claim 5, which is characterized in that second computation subunit executes the basis each second
Driving behavior sample data in set calculates the operation of the corresponding multiple driving behavior values of each second set,
Include:
Transversal displacement in the lane for including according to any driving behavior sample data in second set travels in the unit time
Distance, gas pedal depth in the unit time, steering wheel angle angular speed, laterally accelerate brake pedal depth in the unit time
Degree and vehicle angular speed, calculate the corresponding multiple characteristic values of the driving behavior sample data, the multiple characteristic value includes institute
State lane lateral shift value and the first ratio in the unit time between operating range, brake pedal in the unit time
The second ratio between depth and the unit time length, gas pedal depth and the unit time in the unit time
The 4th ratio and the steering wheel turn between third ratio, the transverse acceleration and the vehicle angular speed between length
Angle angular speed;
Corresponding first ratio of each driving behavior sample data that the second set includes is ranked up, after sequence
Select the first ratio for coming target position as a driving behavior value in first sequence of ratio values;
Corresponding second ratio of each driving behavior sample data that the second set includes is ranked up, after sequence
Select the second ratio for coming target position as a driving behavior value in second sequence of ratio values;
The corresponding third ratio of each driving behavior sample data that the second set includes is ranked up, after sequence
Select the third ratio for coming target position as a driving behavior value in third sequence of ratio values;
Corresponding 4th ratio of each driving behavior sample data that the second set includes is ranked up, after sequence
Select the 4th ratio for coming target position as a driving behavior value in 4th sequence of ratio values;
The corresponding steering wheel angle angular speed of each driving behavior sample data that the second set includes is ranked up, from
The steering wheel angle angular speed for coming target position is selected to drive in steering wheel angle angular speed sequence after sequence as one
Behavioural characteristic value.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710784429.8A CN107585164B (en) | 2017-09-04 | 2017-09-04 | A kind of method and device for the driver that classifies |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710784429.8A CN107585164B (en) | 2017-09-04 | 2017-09-04 | A kind of method and device for the driver that classifies |
Publications (2)
Publication Number | Publication Date |
---|---|
CN107585164A CN107585164A (en) | 2018-01-16 |
CN107585164B true CN107585164B (en) | 2019-11-22 |
Family
ID=61051775
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710784429.8A Active CN107585164B (en) | 2017-09-04 | 2017-09-04 | A kind of method and device for the driver that classifies |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107585164B (en) |
Families Citing this family (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109033332B (en) * | 2018-07-20 | 2020-12-25 | 汉纳森(厦门)数据股份有限公司 | Driving behavior analysis method, medium and system |
CN110304068B (en) * | 2019-06-24 | 2021-02-19 | 中国第一汽车股份有限公司 | Method, device, equipment and storage medium for collecting automobile driving environment information |
CN110533094B (en) * | 2019-08-26 | 2022-11-15 | 汉纳森(厦门)数据股份有限公司 | Evaluation method and system for driver |
CN111516693A (en) * | 2020-04-09 | 2020-08-11 | 吉利汽车研究院(宁波)有限公司 | Method for self-adapting driving mode and vehicle-mounted terminal |
CN111506627B (en) * | 2020-04-21 | 2023-05-30 | 成都路行通信息技术有限公司 | Target behavior clustering method and system |
CN111968365B (en) * | 2020-07-24 | 2022-02-15 | 武汉理工大学 | Non-signalized intersection vehicle behavior analysis method and system and storage medium |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103531042A (en) * | 2013-10-25 | 2014-01-22 | 吉林大学 | Rear-end collision pre-warning method based on driver types |
CN105160883A (en) * | 2015-10-20 | 2015-12-16 | 重庆邮电大学 | Energy-saving driving behavior analysis method based on big data |
CN105426638A (en) * | 2015-12-24 | 2016-03-23 | 吉林大学 | Driver behavior characteristic identification device |
CN106740829A (en) * | 2017-03-23 | 2017-05-31 | 吉林大学 | Based on the double semi-dragging truck riding stability automatic identifications of cluster analysis and early warning system |
Family Cites Families (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP4797948B2 (en) * | 2006-11-22 | 2011-10-19 | 株式会社デンソー | Driving behavior estimation method and apparatus |
JP5392686B2 (en) * | 2011-09-26 | 2014-01-22 | トヨタ自動車株式会社 | Driving support apparatus and method |
-
2017
- 2017-09-04 CN CN201710784429.8A patent/CN107585164B/en active Active
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103531042A (en) * | 2013-10-25 | 2014-01-22 | 吉林大学 | Rear-end collision pre-warning method based on driver types |
CN105160883A (en) * | 2015-10-20 | 2015-12-16 | 重庆邮电大学 | Energy-saving driving behavior analysis method based on big data |
CN105426638A (en) * | 2015-12-24 | 2016-03-23 | 吉林大学 | Driver behavior characteristic identification device |
CN106740829A (en) * | 2017-03-23 | 2017-05-31 | 吉林大学 | Based on the double semi-dragging truck riding stability automatic identifications of cluster analysis and early warning system |
Also Published As
Publication number | Publication date |
---|---|
CN107585164A (en) | 2018-01-16 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107585164B (en) | A kind of method and device for the driver that classifies | |
CN105511631B (en) | Gesture identification method and device | |
CN106004883B (en) | The method and device that rule-breaking vehicle is reminded | |
CN106355573B (en) | The localization method and device of object in picture | |
CN105488957B (en) | Method for detecting fatigue driving and device | |
CN106651955A (en) | Method and device for positioning object in picture | |
CN106295511B (en) | Face tracking method and device | |
CN106503617A (en) | Model training method and device | |
CN106599251A (en) | Method and device for displaying anchor rankings | |
CN106339680A (en) | Human face key point positioning method and device | |
CN104503888B (en) | The method and device of alarm prompt | |
CN107492115A (en) | The detection method and device of destination object | |
CN106951884A (en) | Gather method, device and the electronic equipment of fingerprint | |
CN105718056B (en) | Gesture identification method and device | |
CN107368810A (en) | Method for detecting human face and device | |
CN106778773A (en) | The localization method and device of object in picture | |
CN109670458A (en) | A kind of licence plate recognition method and device | |
CN105335714B (en) | Photo processing method, device and equipment | |
CN107563994A (en) | The conspicuousness detection method and device of image | |
CN107316484A (en) | Travel reminding method and device, electronic equipment and computer-readable recording medium | |
CN106557759A (en) | A kind of sign board information getting method and device | |
CN107688385A (en) | A kind of control method and device | |
CN109978891A (en) | Image processing method and device, electronic equipment and storage medium | |
CN106648063A (en) | Gesture recognition method and device | |
CN106775224A (en) | Remark information method to set up and 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 | ||
CB03 | Change of inventor or designer information | ||
CB03 | Change of inventor or designer information |
Inventor after: Zhang Weihan Inventor after: Wang Meng Inventor after: Mao Yan Inventor after: Guo Da Inventor after: Di Shengde Inventor before: Zhang Weihan Inventor before: Wang Meng Inventor before: Mao Yan Inventor before: Di Shengde |