CN106781503A - Method and apparatus for monitoring driving behavior - Google Patents
Method and apparatus for monitoring driving behavior Download PDFInfo
- Publication number
- CN106781503A CN106781503A CN201710046084.6A CN201710046084A CN106781503A CN 106781503 A CN106781503 A CN 106781503A CN 201710046084 A CN201710046084 A CN 201710046084A CN 106781503 A CN106781503 A CN 106781503A
- Authority
- CN
- China
- Prior art keywords
- driver
- value
- driving behavior
- label
- parameter
- 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
- G08G1/0129—Traffic data processing for creating historical data or processing based on historical data
Landscapes
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Traffic Control Systems (AREA)
Abstract
This application discloses the method and apparatus for monitoring driving behavior.One specific embodiment of methods described includes:Historical trajectory data is analyzed using driver behavior modeling model, the driving behavior of monitoring objective driver;Driver behavior modeling model is obtained through the following steps:Obtain historical trajectory data set and the running cost data acquisition system of multiple drivers;Historical trajectory data set and running cost data acquisition system are processed respectively, determine the driving behavior parameter value and running cost parameter value of each driver;Respectively to each label of driver's mark first and the second label;Learn the driving behavior parameter value of multiple drivers of the driving behavior parameter value and the second label of multiple drivers of the first label using machine learning algorithm, extract characteristic parameter, and the above-mentioned driver behavior modeling model of feature based parameter determination.The implementation method realizes the abundant excavation to the historical trajectory data of driver, and the driving behavior to driver carries out quantization monitoring.
Description
Technical field
The application is related to field of computer technology, and in particular to driver behavior modeling field, more particularly to a kind of for supervising
The method and apparatus for surveying driving behavior.
Background technology
As economic society sustained and rapid development, masses' purchase car rigid demand are vigorous, car ownership continues in quick increasing
Trend long.It is adapted with vehicle guaranteeding organic quantity rapid growth, vehicle driver quantity is also presented the trend of increasing substantially.Motor vehicle
And driver's quantity is increased rapidly, while the production and living for giving people offer convenience, also bring the safety that can not be ignored hidden
Suffer from.
Low driving age driver is such as anxious to accelerate or suddenly slow down due to unskilled caused bad custom of driving;And the driving age high
The bad custom of driving such as the high speed joyride of driver, can all endanger the life and health of pedestrian or driver.Therefore, how to quantify
It is problem demanding prompt solution that the driving behavior of driver is monitored.
The content of the invention
The purpose of the application is to propose a kind of to solve background above skill for monitoring the method and apparatus of driving behavior
The technical problem that art part is mentioned.
In a first aspect, this application provides a kind of method for monitoring driving behavior, the above method includes:Obtain and drive
The historical trajectory data of behavior monitoring model and target driver;Historical trajectory data is entered using driver behavior modeling model
Row analysis, the driving behavior of monitoring objective driver;Wherein, above-mentioned driver behavior modeling model is obtained through the following steps
's:Obtain historical trajectory data set and the running cost data acquisition system of multiple drivers;Historical trajectory data collection is processed respectively
Close and running cost data acquisition system, determine the driving behavior parameter value and running cost parameter value of each driver;To travel into
This parameter value is labeled as the first label less than the driver of the first preset value, by running cost parameter value more than the second preset value
Driver is labeled as the second label;Learn the driving behavior of the multiple drivers indicated by the first label using machine learning algorithm
The driving behavior parameter value of the multiple drivers indicated by parameter value and the second label, extraction meets pre-conditioned driving row
It is parameter as characteristic parameter, and the above-mentioned driver behavior modeling model of feature based parameter determination.
In certain embodiments, historical trajectory data includes the location and time of multiple tracing points;And treatment is gone through respectively
The set of history track data and running cost data acquisition system, determine the driving behavior parameter value and running cost parameter of each driver
Value, including:Determine the displacement between the adjacent tracing point of any two and duration in historical trajectory data;It is timely according to displacement
It is long, determine driving behavior parameter value of each driver in each tracing point, above-mentioned driving behavior parameter includes:Speed and traveling angle
Degree.
In certain embodiments, according to the displacement between the adjacent tracing point of any two and duration, determine that each drives
Member each tracing point driving behavior parameter value, including:According to each driver in the velocity amplitude of each tracing point, determine that each is driven
The velocity distribution curve of the person of sailing;Determine velocity distribution curve middling speed angle value more than the number of times of default friction speed threshold value and every
The secondary duration more than default friction speed threshold value;According to velocity distribution curve, the cumulative distribution function of speed is determined;Really
Default different probability is worth corresponding velocity amplitude in the cumulative distribution function of constant speed degree.
In certain embodiments, above-mentioned driving behavior parameter also includes:Acceleration;And according to the adjacent rail of any two
Displacement and duration between mark point, determine driving behavior parameter value of each driver in each tracing point, including:Driven according to each
The velocity distribution curve of the person of sailing, determines the acceleration of each tracing point;Determine the acceleration profile curve of each driver;It is determined that
Acceleration magnitude is more than the number of times of default different acceleration rate thresholds and more than default different acceleration in acceleration profile curve
Spend the first total duration of threshold value;Determine that acceleration magnitude is less than zero and absolute value adds more than default difference in acceleration profile curve
Second total duration of the number of times and absolute value of threshold speed more than different acceleration rate thresholds;According to the acceleration of each driver
Distribution curve, determines the cumulative distribution function of acceleration;Determine default different probability value in the cumulative distribution function of acceleration
Corresponding acceleration magnitude.
In certain embodiments, above-mentioned driving behavior parameter includes continuous driving duration;And it is adjacent according to any two
Tracing point between displacement and duration, determine driving behavior parameter value of each driver in each tracing point, including:For every
Individual driver, according to the displacement between the adjacent tracing point of any two and duration, determines that displacement is less than preset displacement and duration
Less than two moment of adjacent track point of preset duration;In moment and historical trajectory data according to identified tracing point
First moment of tracing point, the moment of last tracing point, determine at least one continuous driving duration of each driver.
In certain embodiments, according to the displacement between the adjacent tracing point of any two and duration, determine that each drives
Member each tracing point driving behavior parameter value, including:For each driver, the traveling angle according to each tracing point, really
Surely traveling angle is located at the velocity distribution curve in default different angular ranges;Determine that each velocity distribution curve is corresponding tired
Product distribution function;Determine the corresponding velocity amplitude of different probability in different cumulative distribution function.
In certain embodiments, above-mentioned running cost parameter includes:The maintenance of the fuel consumption values and unit distance of unit distance
Cost value;And running cost parameter is labeled as the first label less than the driver of the first preset value, by running cost parameter
The second label is labeled as more than the driver of the second preset value, including:By the maintenance of the fuel consumption values of unit distance and unit distance
The driver that cost value is respectively less than the first preset value is labeled as the first label;By the fuel consumption values of unit distance and the dimension of unit distance
Repair cost value and be all higher than the driver of the second preset value labeled as the second label.
In certain embodiments, above-mentioned first label is the 3rd preset value, and above-mentioned second label is the 4th preset value;And
Learn driving behavior parameter value and the second label institute of the multiple drivers indicated by the first label using machine learning algorithm
The driving behavior parameter value of multiple drivers of instruction, extraction meets pre-conditioned driving behavior parameter as characteristic parameter,
Including:Learnt the driving behavior parameter value and second of the multiple drivers indicated by the first label using machine learning algorithm
The driving behavior parameter value of the multiple drivers indicated by label, determines the P values of each driving behavior parameter;Each driving is calculated to go
It is the Pearson correlation coefficients between parameter value and the 3rd preset value or the 4th preset value;Extract P values be more than the 5th preset value and
Pearson correlation coefficients are more than the driving behavior parameter of the 6th preset value as characteristic parameter.
In certain embodiments, feature based parameter determination driver behavior modeling model, including:Based on each characteristic parameter
P values and Pearson correlation coefficients, determine the weight of each characteristic parameter;Based on each characteristic parameter and corresponding weight, driven
Behavior monitoring model.
Second aspect, this application provides a kind of device for monitoring driving behavior, said apparatus include:Obtain single
Unit, the historical trajectory data for obtaining driver behavior modeling model and target driver;Monitoring unit, for using driving
Behavior monitoring model is analyzed to historical trajectory data, the driving behavior of monitoring objective driver;Wherein, driver behavior modeling
Model is obtained by model construction unit, and model construction unit includes:Acquisition module, for obtaining going through for multiple drivers
The set of history track data and running cost data acquisition system;Processing module, for processing historical trajectory data set and traveling respectively
Cost data set, determines the driving behavior parameter value and running cost parameter value of each driver;Mark module, for that will go
Driver of the cost parameter value less than the first preset value is sailed labeled as the first label, running cost parameter value is preset more than second
The driver of value is labeled as the second label;Determining module is more indicated by the first label for being learnt using machine learning algorithm
The driving behavior parameter value of the multiple drivers indicated by the driving behavior parameter value and the second label of individual driver, extracts symbol
Pre-conditioned driving behavior parameter is closed as characteristic parameter, and the above-mentioned driver behavior modeling model of feature based parameter determination.
In certain embodiments, historical trajectory data includes the location and time of multiple tracing points;And processing module is entered
One step is used for:Determine the displacement between the adjacent tracing point of any two and duration in historical trajectory data;According to above-mentioned displacement
And duration, determining driving behavior parameter value of each driver in each tracing point, above-mentioned driving behavior parameter includes:Speed and row
Sail angle.
In certain embodiments, processing module is further used for:According to each driver each tracing point velocity amplitude, really
The velocity distribution curve of fixed each driver;Determine that velocity distribution curve middling speed angle value is secondary more than default friction speed threshold value
Count and every time more than the duration of default friction speed threshold value;According to velocity distribution curve, the iterated integral of speed is determined
Cloth function;Determine the corresponding velocity amplitude of default different probability value in the cumulative distribution function of speed.
In certain embodiments, above-mentioned driving behavior parameter also includes:Acceleration;And processing module is further used for:
According to the velocity distribution curve of each driver, the acceleration of each tracing point is determined;Determine the acceleration point of each driver
Cloth curve;Acceleration magnitude is more than the number of times of default different acceleration rate thresholds and more than default in determining acceleration profile curve
Different acceleration rate thresholds the first total duration;Determine that acceleration magnitude is less than zero and absolute value is more than pre- in acceleration profile curve
If different acceleration rate thresholds number of times and absolute value more than different acceleration rate thresholds the second total duration;According to each driving
The acceleration profile curve of member, determines the cumulative distribution function of acceleration;Determine default in the cumulative distribution function of acceleration
Different probability is worth corresponding acceleration magnitude.
In certain embodiments, above-mentioned driving behavior parameter includes:It is continuous to drive duration;And processing module is further used
In:For each driver, according to the displacement between the adjacent tracing point of any two and duration, determine that displacement is less than default position
Move and duration less than preset duration two moment of adjacent track point;Moment and history rail according to identified tracing point
At first moment of tracing point, moment of last tracing point in mark data, determine that at least one of each driver is continuous
Drive duration.
In certain embodiments, processing module is further used for:For each driver, according to the traveling of each tracing point
Angle, it is determined that traveling angle is located at the velocity distribution curve in default different angular ranges;Determine each velocity distribution curve
Corresponding cumulative distribution function;Determine the corresponding velocity amplitude of different probability in different cumulative distribution function.
In certain embodiments, above-mentioned running cost parameter includes:The maintenance of the fuel consumption values and unit distance of unit distance
Cost value;And mark module is further used for:The maintenance cost value of the fuel consumption values of unit distance and unit distance is respectively less than
The driver of the first preset value is labeled as the first label;The maintenance cost value of the fuel consumption values of unit distance and unit distance is big
The second label is labeled as in the driver of the second preset value.
In certain embodiments, above-mentioned first label is the 3rd preset value, and above-mentioned second label is the 4th preset value;And
Determining module is further used for:Learnt the driving behavior of the multiple drivers indicated by the first label using machine learning algorithm
The driving behavior parameter value of the multiple drivers indicated by parameter value and the second label, determines the P of each driving behavior parameter
Value;Calculate each driving behavior parameter value and the Pearson correlation coefficients between the 3rd preset value or the 4th preset value;Extract P values big
In the driving behavior parameter of the 5th preset value and Pearson correlation coefficients more than the 6th preset value as characteristic parameter.
In certain embodiments, determining module is further used for:P values and Pearson's phase relation based on each characteristic parameter
Number, determines the weight of each characteristic parameter;Based on each characteristic parameter and corresponding weight, above-mentioned driver behavior modeling model is obtained.
The method and apparatus for monitoring driving behavior that the application is provided, by the historical track number to multiple drivers
It is respectively processed according to set and running cost parameter sets, obtains the driving behavior parameter value and running cost of each driver
Parameter value, then the running cost parameter according to each driver is that the driver for meeting different condition marks different labels, then
Learn the driving behavior parameter value of the driver of different labels using machine learning algorithm, extraction meets pre-conditioned driving row
Be parameter as characteristic parameter, based on features described above parameter determination driver behavior modeling model, recycle above-mentioned driving behavior prison
Survey model to be analyzed the historical trajectory data of target driver, realize the monitoring to target driver driving behavior.It is above-mentioned
Embodiment realizes the abundant excavation to the historical trajectory data of driver, and the driving behavior to driver carries out quantization monitoring.
Brief description of the drawings
By the detailed description made to non-limiting example made with reference to the following drawings of reading, the application other
Feature, objects and advantages will become more apparent upon:
Fig. 1 is the flow chart of one embodiment of the method for monitoring driving behavior according to the application;
Fig. 2 is that the application can apply to exemplary system architecture figure therein;
Fig. 3 is the flow of the determination driver behavior modeling model of the method for monitoring driving behavior according to the application
Figure;
Fig. 4 is the driving behavior parameter according to each driver of the determination of the method for monitoring driving behavior of the application
One embodiment flow chart;
Fig. 4 a are the schematic diagrames of the velocity distribution curve of the method for monitoring driving behavior according to the application;
Fig. 5 is the structural representation of one embodiment of the device for monitoring driving behavior according to the application;
Fig. 6 is adapted for the structural representation for realizing the terminal device of the embodiment of the present application or the computer system of server
Figure.
Specific embodiment
The application is described in further detail with reference to the accompanying drawings and examples.It is understood that this place is retouched
The specific embodiment stated is used only for explaining related invention, rather than the restriction to the invention.It also should be noted that, in order to
Be easy to description, be illustrate only in accompanying drawing to about the related part of invention.
It should be noted that in the case where not conflicting, the feature in embodiment and embodiment in the application can phase
Mutually combination.Describe the application in detail below with reference to the accompanying drawings and in conjunction with the embodiments.
Fig. 1 shows the flow chart 100 of one embodiment of the method for monitoring driving behavior according to the application.Such as
Shown in Fig. 1, the present embodiment is comprised the following steps for monitoring the method for driving behavior:
Step 101, obtains the historical trajectory data of driver behavior modeling model and target driver.
In the present embodiment, driver behavior modeling model can be the monitoring model built according to various machine learning algorithms,
Its corresponding relation that can include historical trajectory data and driver behavior modeling result.That is, by a historical trajectory data
It is input into above-mentioned driver behavior modeling model, it is possible to obtain a driver behavior modeling result.Above-mentioned monitoring result can include
Below at least one:Numerical value, the analysis and summary to driving behavior of various parameters (such as speed, acceleration) in driving procedure
(such as often hypervelocity, lane change are excessively frequent), to scoring of driving behavior etc..
Above-mentioned target driver can be driving behavior driver to be monitored.For example when the driving behavior of the present embodiment is supervised
When survey model is applied to car insurance company, above-mentioned target driver can be insured the owner of vehicle, and insurance company can
The monitoring result of the driving behavior according to target driver sets insurance premium;Or when the driver behavior modeling mould of the present embodiment
When type is used for cartography company, above-mentioned target driver can be streetscape map collection person, and cartography company can be according to mesh
The monitoring result for marking the driving behavior of driver is managed to each driver.
Above-mentioned historical trajectory data can be the data that target driver drives vehicle running path, and above-mentioned driving path can
Constituted with by multiple tracing points, the position of each tracing point can be included in above-mentioned historical trajectory data, angle is travelled and is arrived
Moment up to the tracing point etc..Above-mentioned position can be coordinate (such as gps coordinate), can also be street information (such as XX
XX cities of province XX areas XX streets XX);Above-mentioned traveling angle can be tangent line and direct north of the tracing point on driving path
Angle, can also be between tangent line of tangent line and a upper tracing point of the tracing point on driving path on driving path
Angle.It is understood that above-mentioned historical trajectory data is to be arranged in order what is formed according to the moment for reaching each tracing point.
The method for monitoring driving behavior of the present embodiment, typically by terminal or server execution, above-mentioned terminal or clothes
Business device can be connected with vehicle communication.Terminal or server when above-mentioned historical trajectory data is obtained, can directly from vehicle
Each sensor connection storage device in obtain, the data being locally stored can also be obtained.
In the present embodiment, when server needs to obtain historical trajectory data from vehicle, its corresponding system architecture diagram is such as
Shown in Fig. 2.In Fig. 2, system architecture 200 can include vehicle 201, network 202 and server 203.Network 202 is used in vehicle
The medium of communication link is provided between 201 and server 203.Network 202 can include various connection types, such as wired, nothing
Line communication link or fiber optic cables etc..
GPS chip can be included on vehicle 201, can be with the traveling-position of registration of vehicle 201;Can also be filled including timing
Put, the moment of each traveling-position can be reached with registration of vehicle 201.Certainly, on vehicle 201 can also include velocity sensor,
Acceleration transducer etc., travel speed and acceleration of the difference registration of vehicle 201 in each traveling-position.
Server 203 can be to provide the server of various services, such as to the historical trajectory data of vehicle 201 at
The background server of reason.Background server can obtain the historical trajectory data of vehicle 201, and be analyzed and obtain driver's
Driver behavior modeling result.
It should be noted that the method for monitoring driving behavior that the embodiment of the present application is provided is general by server
203 perform, correspondingly, the device for monitoring driving behavior typically set with server 203.
It should be understood that the number of the vehicle, network and server in Fig. 2 is only schematical.According to needs are realized, can
With with any number of vehicle, network and server.
Fig. 1 is returned, in step 102, historical trajectory data is analyzed using driver behavior modeling model, monitoring objective
The driving behavior of driver.
After above-mentioned driver behavior modeling model and historical trajectory data is got, it is possible to use driver behavior modeling model
Historical trajectory data is analyzed, the driving behavior of monitoring objective driver obtains monitoring result.Wherein, above-mentioned driving row
For 301~step 304 is obtained the step of monitoring model in Fig. 3 by showing, Fig. 3 is to be driven for monitoring according to the application
Sail the schematic flow sheet 300 of the determination driver behavior modeling model of the method for behavior.
Step 301, obtains historical trajectory data set and the running cost data acquisition system of multiple drivers.
Create above-mentioned driver behavior modeling model when, first have to obtain multiple drivers historical trajectory data set and
Running cost parameter sets.Wherein, running cost data can include the expense spent in unit operating range, such as oil consumption expense
With, maintenance cost, the expense of traffic accident etc..
Step 302, processes historical trajectory data set and running cost data acquisition system respectively, determines driving for each driver
Sail behavioral parameters value and running cost parameter value.
After above-mentioned historical data set and running cost data acquisition system is obtained, above two data set is processed respectively
Close, to determine the driving behavior parameter and running cost parameter of each driver.Above-mentioned treatment can include calculating above-mentioned traveling
The mileage in path, it is also possible to including calculating the speed of each tracing point, angle etc., can also include calculating above-mentioned driving path institute
Expense of cost etc..Driving behavior parameter can be the various various parameters that can reflect driver's driving efficiency or custom, example
Such as can be speed, acceleration, traveling angle.Running cost parameter can be that reflection driver spends in unit distance
The various parameters of expense, for example, can be oil consumption expense, maintenance cost.
Step 303, the first label is labeled as by running cost parameter value less than the driver of the first preset value, will be travelled into
This parameter value is labeled as the second label more than the driver of the second preset value.
Running cost parameter value is being obtained, is being the part setting label of above-mentioned multiple drivers.Specifically, will travel into
This parameter value is labeled as the first label less than the driver of the first preset value, by running cost parameter value more than the second preset value
Driver is labeled as the second label.Above-mentioned first label, the second label can be represented by different numerical value, it is also possible to by different
Storage location is represented.It is understood that above-mentioned first preset value is less than or equal to the second preset value.
In some optional implementations of the present embodiment, when label is set for above-mentioned driver, can also be first
Running cost parameter value according to each driver, carries out ascending sequence.By running cost parameter value in above-mentioned sequence preceding
The driver of the first preset ratio is labeled as the first label, by running cost parameter value in above-mentioned sequence in rear second preset ratio
Driver be labeled as the second label.
Step 304, the driving behavior parameter of the multiple drivers indicated by the first label is learnt using machine learning algorithm
The driving behavior parameter value of the multiple drivers indicated by value and the second label, extraction meets pre-conditioned driving behavior ginseng
Number is used as characteristic parameter, and feature based parameter determination driver behavior modeling model.
After part driver setting label in for multiple drivers, first is labeled as using machine learning algorithm study
The driving behavior parameter value of the driver of label and the driving behavior parameter value of the driver labeled as the second label.Above-mentioned machine
Learning algorithm can be including logistic regression algorithm, SVMs, random forest, decision tree etc..It is understood that this reality
Apply example not to be defined the type of machine learning algorithm, those skilled in the art can select machine according to practical application scene
The type of device learning algorithm.
Machine learning algorithm can drive row after the driving behavior parameter value of driver of different labels is learnt from multiple
For in parameter extract meet pre-conditioned driving behavior parameter as characteristic parameter, it is above-mentioned it is pre-conditioned can include and first
The correlation of label or the second label is more than the relevance between threshold value, each driving behavior parameter less than threshold value etc..It is then based on
State characteristic parameter and determine driver behavior modeling model, driver behavior modeling model can be by various fortune to each characteristic ginseng value
The model of numerical value is exported after calculation, or one model of report of output is analyzed to each characteristic ginseng value.
The method for monitoring driving behavior that above-described embodiment of the application is provided, by the history to multiple drivers
Track data set and running cost parameter sets are respectively processed, and obtain the driving behavior parameter value and row of each driver
Cost parameter value is sailed, then the running cost parameter according to each driver is that the driver for meeting different condition marks different marks
Sign, recycle machine learning algorithm to learn the driving behavior parameter value of the driver of different labels, extraction meets pre-conditioned
Driving behavior parameter, based on features described above parameter determination driver behavior modeling model, recycles above-mentioned driving as characteristic parameter
Behavior monitoring model is analyzed to the historical trajectory data of target driver, realizes the prison to target driver driving behavior
Survey.The abundant excavation to the historical trajectory data of driver is above embodiments enabled, to the driving behavior amount of carrying out of driver
Change monitoring.
In some optional implementations of the present embodiment, above-mentioned running cost parameter can include the oil of unit distance
The maintenance cost value of consumption value and unit distance.Above-mentioned steps 303 specifically can be by the following sub-step not shown in Fig. 3 come real
It is existing:
The maintenance cost value of the fuel consumption values of unit distance and unit distance is respectively less than driver's mark of the first preset value
It is the first label;The maintenance cost value of the fuel consumption values of unit distance and unit distance is all higher than driver's mark of the second preset value
It is designated as the second label.
The fuel consumption values of unit distance and the maintenance cost value of unit distance are smaller, illustrate the driving habit of the driver compared with
Good, the probability that traffic accident occurs is small, and oil consumption is less, is that such driver sets the first label.The fuel consumption values of unit distance
And the maintenance cost value of unit distance is larger, illustrate that the driver's is poor, the probability that traffic accident occurs is big, and oil consumption compared with
It is many, it is that such driver sets the second label.In this implementation, above-mentioned first label and the second label can be respectively " 0 "
" 1 ".
Fig. 4 shows the driving behavior according to each driver of the determination of the method for monitoring driving behavior of the application
The flow chart 400 of one embodiment of parameter, Fig. 4 a show the schematic diagram of velocity distribution curve.It is above-mentioned to go through in the present embodiment
History track data includes the location and time of multiple tracing points.As shown in Figure 4, the above method is comprised the following steps:
Step 401, determines the displacement between the adjacent tracing point of any two and duration in historical trajectory data.
Because historical trajectory data includes multiple tracing points, and the location and time including each tracing point, therefore, can
Displacement and duration between the tracing point adjacent to determine each two.
In some optional implementations of the present embodiment, the when a length of fixed value between above-mentioned multiple tracing points,
For example, above-mentioned duration can be 2 seconds.
Step 402, according to above-mentioned displacement and duration, determines driving behavior parameter value of each driver in each tracing point.
In the present embodiment, above-mentioned driving behavior parameter includes speed and traveling angle.Speed can be by the distance in displacement
Ratio with duration determines that traveling angle can be determined by the friendship degree in displacement with the angle of direct north.
Step 403, it is determined that each driving behavior parameter value with velocity correlation.
Above-mentioned steps 403 can specifically be realized by the following sub-step not shown in Fig. 4:
According to each driver in the velocity amplitude of each tracing point, the velocity distribution curve of each driver is determined;It is determined that fast
Degree distribution curve middling speed angle value is more than the number of times of default friction speed threshold value and every time more than default friction speed threshold value
Duration;According to velocity distribution curve, the cumulative distribution function of speed is determined;Determine pre- in the cumulative distribution function of speed
If different probability be worth corresponding velocity amplitude.
After the velocity amplitude that each tracing point is determined, it may be determined that the speed of each driver is dependent variable, the time is certainly
The velocity distribution curve of variable.Number of times of the velocity amplitude beyond friction speed threshold value can be determined in above-mentioned velocity distribution curve,
Can determine exceeding the duration of above-mentioned threshold speed every time simultaneously.Above-mentioned friction speed threshold value can include 50km/h,
80km/h, 120km/h etc..As shown in fig. 4 a, in velocity distribution curve, velocity amplitude is more than 50km/h 1 time, more than 80km/h 1
It is secondary, more than 120km/h 1 time, the duration more than 50km/h is t6-t1, the duration more than 80km/h is t5-t2, surpass
The duration for crossing 120km/h is t4-t3.Then according to above-mentioned velocity distribution curve, determine the cumulative distribution function of speed, tire out
Product distribution function is used to describe the probability distribution of variable.Default different probability value can be determined in above-mentioned cumulative distribution function
Corresponding velocity amplitude, above-mentioned default different probability value can be from 0.2, to terminate to 0.95, and step-length is 0.05, i.e., calculate respectively
Corresponding velocity amplitude when probability is 0.2,0.25,0.3,0.35 ... 0.95.
Step 404, it is determined that each driving behavior parameter value related to acceleration.
In the present embodiment, driving behavior parameter also includes acceleration.After velocity distribution curve is determined, can be according to each
Slope at tracing point determines the acceleration of each tracing point, and above-mentioned steps 404 specifically can be by the following son not shown in Fig. 4
Step is realized:
According to the velocity distribution curve of each driver, the acceleration of each tracing point is determined;Determine each driver's
Acceleration profile curve;Determine acceleration magnitude in acceleration profile curve more than the number of times of default different acceleration rate thresholds and
More than the first total duration of default different acceleration rate thresholds;Acceleration magnitude is less than zero and absolute in determining acceleration profile curve
Number of times and absolute value second total duration more than different acceleration rate thresholds of the value more than default different acceleration rate thresholds;According to
The acceleration profile curve of each driver, determines the cumulative distribution function of acceleration;Determine the cumulative distribution function of acceleration
In default different probability be worth corresponding acceleration magnitude.
After velocity distribution curve is determined, the acceleration of each tracing point can be determined according to the slope at each tracing point,
May thereby determine that the acceleration profile curve of each driver.It is on the occasion of deceleration brief acceleration is due to accelerating brief acceleration
Negative value, in order to determine that each driver accelerates or anxious situation about slowing down with the presence or absence of anxious, it is first determined acceleration magnitude is beyond default
The number of times of different acceleration rate thresholds and the first total duration beyond above-mentioned default different acceleration rate thresholds.Above-mentioned different adds
Threshold speed can be 10m/s2、15m/s2, the first total duration is for every time beyond 10m/s2Duration summation plus exceeding every time
15m/s2Duration summation.It is then determined that acceleration magnitude is less than the number of times of default different acceleration rate thresholds, and (i.e. acceleration magnitude is small
In zero, but absolute value is more than the number of times of different acceleration rate thresholds) and it is second total every time less than above-mentioned different acceleration rate thresholds
Duration.It is understood that accelerating and anxious deceleration for anxious, its acceleration rate threshold can be with identical, it is also possible to different.For example, right
18m/s can be respectively set in the minus threshold value of acceleration2、21m/s2, the second total duration is for every time less than 18m/s2Duration
Summation is plus every time less than 21m/s2Duration summation.Further according to acceleration profile curve, the cumulative distribution letter of acceleration is determined
Number, determines the corresponding acceleration magnitude of default different probability value in the cumulative distribution function of acceleration.It is understood that this
Locating default different probability value can be identical with the probable value in step 403, it is also possible to different.For example, default difference herein
Probable value can terminate from 0.8 to 1, and step-length is 0.05, i.e., calculate corresponding when probability is 0.85,0.9,0.95,1 respectively
Acceleration magnitude.
Although it is understood that the present embodiment schematically illustrates the value of above-mentioned threshold speed, acceleration rate threshold
Value and probable value value, but this is only schematical, and the present embodiment is not limited this, and those skilled in the art can
The value of above-mentioned threshold value is set according to practical application scene.
Flow 400 in the present embodiment highlights the step of processing historical trajectory data.Thus, the present embodiment institute
The scheme of description can carry out various careful treatment to historical trajectory data such that it is able to the driving of the determination driver of quantization
Behavioral parameters.
In some optional implementations of the present embodiment, above-mentioned driving behavior parameter also includes continuous driving duration.
It is determined that each driver driving behavior parameter when also include Fig. 4 not shown in following steps:
For each driver, according to the displacement between the adjacent tracing point of any two and duration, determine that displacement is less than
Two moment of adjacent track point of preset displacement and duration less than preset duration;Moment according to identified tracing point and
At first moment of tracing point, moment of last tracing point in historical trajectory data, determine at least the one of each driver
Individual continuous driving duration.
In this implementation, when the displacement between two adjacent tracing points is less than default displacement, and two tracing points
Between duration be more than preset duration when, it can be assumed that driver parking rest.Above-mentioned preset displacement can be 5 meters, above-mentioned
Preset duration can be 20 minutes, and certain this implementation does not limit the value of preset displacement and preset duration.Then basis
First moment of tracing point and last tracing point in the moment of the tracing point of above-mentioned determination and historical trajectory data
At the moment, determine at least one continuous driving duration of each driver.
For example, 7200 tracing points are had in historical trajectory data, the 1st moment of tracing point is 9:30, the
3600 moment of tracing point are 11:30, the 3601st moment of tracing point is 11:The moment of the 50, the 7200th tracing point is
13:50.Then the driver includes that two continuously drive durations, a length of 2 hours during first continuous driving, second continuous driving
Duration is also 2 hours.
In some optional implementations of the present embodiment, determining the driving behavior parameter of each driver also includes figure
Following steps not shown in 4:
For each driver, the traveling angle according to each tracing point, it is determined that traveling angle is located at default different angles
Velocity distribution curve in the range of degree;Determine the corresponding cumulative distribution function of each velocity distribution curve;Determine different iterated integrals
The corresponding velocity amplitude of different probability in cloth function.
In this implementation, driving habit that can be according to historical trajectory data to driver when turning is monitored.
Angle of turn can be divided first, be assert that angle of turn is small radian between 15 °~45 °, between 45 °~90 °
It is medium radian, is big radian more than 90 °.Because each tracing point packet rows sails angle, therefore can be by traveling angle position
Each tracing point between 15 °~45 ° is arranged sequentially in time, will travel each rail that angle is located between 45 °~90 °
Mark point is arranged sequentially in time, will be travelled each tracing point of the angle more than 90 ° and is arranged sequentially in time, then
With reference to the speed of each tracing point, three velocity distribution curves are obtained.The corresponding iterated integral of each velocity distribution curve is determined respectively
Cloth function, it is then determined that the corresponding speed of different probability.Above-mentioned different probability can be with 0.8,0.85,0.9,0.95.Can be with
Understand, the corresponding probable value of each velocity distribution curve can be with identical, it is also possible to different.
In some optional implementations of the present embodiment, above-mentioned driving behavior parameter can also include traveling angle with
The product of speed, intensity of referred to as turning.Because the traveling angle and speed of each tracing point are it has been determined that the then turning of each tracing point
Intensity level also determines.Turning intensity level according to each tracing point, it may be determined that turning intensity level is more than the ratio of predetermined threshold value, together
Sample can also determine the cumulative distribution function of turning intensity, and turning when probable value is 0.8,0.85,0.9,0.95 is determined respectively
Curved intensity level.
In some optional implementations of the present embodiment, above-mentioned driving behavior parameter can also include speed and accelerate
The product of the absolute value of degree, referred to as accelerates power.With turning intensity similarly, determine during the acceleration power value of each tracing point
's.The cumulative distribution function for accelerating power is may thereby determine that, is determined respectively when probable value is 0.2,0.4,0.6,0.8,1
Accelerate power value.
After the above-mentioned treatment to historical trajectory data, the driving behavior parameter value of each driver can include it is above-mentioned not
It is (including big with the corresponding velocity amplitude of probability, number of times and duration beyond friction speed threshold value, the corresponding acceleration magnitude of different probability
In zero-sum less than zero), beyond different acceleration rate thresholds number of times and total duration, the number of times less than different acceleration rate thresholds and it is total when
The ratio of long, each continuous driving duration, the velocity amplitude of the corresponding each angular range of different probability, turning intensity level more than predetermined threshold value
Example, the corresponding each turning intensity level of different probability, the corresponding each acceleration power value of different probability.For being marked with driving for label
The person of sailing, with label value as dependent variable, using above-mentioned each driving behavior parameter value as independent variable, determines the coefficient value of each independent variable.
The independent variable and dependent variable of each driver constitute an equation, in order to determine the coefficient value of each dependent variable, it is desirable to equation
The number of formula is greater than the number of coefficient value to be determined, it is therefore desirable to the number for being marked with the driver of label is greater than
The number of above-mentioned each driving behavior parameter value.In order to more fully consider shadow of each driving behavior parameter value to driver's label
Ring, can be equal with the number of the driver labeled as the second label by the number labeled as the driver of the first label.
In step 304, the driving behavior parameter value and label value of each driver are learnt using machine learning algorithm, it is determined that
The coefficient value of each driving behavior parameter.Afterwards, each driving behavior parameter value is tested, calculates each driving behavior parameter
P values.P values are smaller, show that result is more notable.The Pearson's phase relation between each driving behavior parameter value and label value is calculated simultaneously
Number, Pearson correlation coefficients are for reflecting two statistics of linear variable displacement degree of correlation.By P values more than the 5th preset value and
Pearson correlation coefficients are more than the driving behavior parameter of the 6th preset value as characteristic parameter.In the present embodiment, can will be above-mentioned
5th preset value is taken as 0.05, the 6th preset value is taken as 0.2, so that it is determined that multiple features ginseng of driving behavior can be reflected
Number.
It is determined that during driver behavior modeling model, the history that above-mentioned multiple characteristic parameters determine target driver can be based on
The corresponding driver behavior modeling result of track data, in order to protrude influence degree of certain parameter to driver behavior modeling result,
Weight can be set for each characteristic parameter.It is determined that each characteristic parameter weight when, can be with P values and Pearson correlation coefficients
Independent variable, substitute into cost function, obtain the value between [0,1], using this value as each characteristic parameter weight.According to each feature
Parameter and its corresponding weight, obtain driver behavior modeling model.
In the driving behavior using above-mentioned driver behavior modeling model monitoring target driver, can be by target driver
Historical trajectory data import driver behavior modeling model, after above-mentioned each characteristic ginseng value is calculated, target can be obtained
The driver behavior modeling value of driver.Those skilled in the art can determine target driver according to this driver behavior modeling value
Driving behavior.
With further reference to Fig. 5, as the realization to method shown in above-mentioned each figure, driven for monitoring this application provides one kind
One embodiment of the device of behavior is sailed, the device embodiment is corresponding with the embodiment of the method shown in Fig. 1, the device specifically may be used
To be applied in various electronic equipments.
As shown in figure 5, the present embodiment includes for monitoring the device 500 of driving behavior:Acquiring unit 501, monitoring are single
Unit 502 and model construction unit 503.
Acquiring unit 501, the historical trajectory data for obtaining driver behavior modeling model and target driver.
Monitoring unit 502, for being analyzed to historical trajectory data using driver behavior modeling model, monitoring objective is driven
The driving behavior of the person of sailing.
Wherein, above-mentioned driver behavior modeling model is by model construction unit 503 by being obtained, above-mentioned model construction unit
503 include:Acquisition module 5031, processing module 5032, mark module 5033 and determining module 5034.
Wherein, acquisition module 5031, historical trajectory data set and running cost data for obtaining multiple drivers
Set.
Processing module 5032, for processing historical trajectory data set and running cost data acquisition system respectively, determines each
The driving behavior parameter value and running cost parameter value of driver.
Mark module 5033, for the driver by running cost parameter value less than the first preset value labeled as the first mark
Sign, running cost parameter value is labeled as the second label more than the driver of the second preset value.
Determining module 5034, the driving for learning the multiple drivers indicated by the first label using machine learning algorithm
The driving behavior parameter value of the multiple drivers indicated by behavioral parameters value and the second label, extraction meets pre-conditioned driving
Behavioral parameters are sailed as characteristic parameter, and feature based parameter determination driver behavior modeling model.
In some optional implementations of the present embodiment, above-mentioned historical trajectory data includes the position of multiple tracing points
And the moment.Above-mentioned processing module 5032 can be further used for:Determine the adjacent tracing point of any two in historical trajectory data
Between displacement and duration;According to displacement and duration, driving behavior parameter value of each driver in each tracing point is determined, it is above-mentioned
Driving behavior parameter includes:Speed and traveling angle.
In some optional implementations of the present embodiment, above-mentioned processing module 5032 can also be further used for:Root
According to each driver in the velocity amplitude of each tracing point, the velocity distribution curve of each driver is determined;Determine above-mentioned VELOCITY DISTRIBUTION
Curve middling speed angle value is more than the number of times of default friction speed threshold value and is more than continuing for default friction speed threshold value every time
Duration;According to velocity distribution curve, the cumulative distribution function of speed is determined;Determine to be preset in the cumulative distribution function of above-mentioned speed
Different probability be worth corresponding velocity amplitude.
In some optional implementations of the present embodiment, above-mentioned driving behavior parameter also includes:Acceleration.Above-mentioned place
Reason module 5032 can also be further used for:According to the velocity distribution curve of each driver, the acceleration of each tracing point is determined
Degree;Determine the acceleration profile curve of each driver;Acceleration magnitude is more than default difference in determining acceleration profile curve
The number of times of acceleration rate threshold and the first total duration more than default different acceleration rate thresholds;In determining acceleration profile curve
Acceleration magnitude is less than zero and absolute value is more than different acceleration more than the number of times and absolute value of default different acceleration rate thresholds
Second total duration of threshold value;Acceleration profile curve according to each driver, determines the cumulative distribution function of acceleration;It is determined that
Default different probability is worth corresponding acceleration magnitude in the cumulative distribution function of acceleration.
In some optional implementations of the present embodiment, above-mentioned driving behavior parameter also includes:It is continuous to drive duration.
Above-mentioned processing module 5032 can also be further used for:For each driver, according between the adjacent tracing point of any two
Displacement and duration, determine above-mentioned displacement less than preset displacement and above-mentioned duration less than two adjacent track points of preset duration
Moment;First moment of tracing point, last rail in moment and historical trajectory data according to identified tracing point
At the moment of mark point, determine at least one continuous driving duration of each driver.
In some optional implementations of the present embodiment, above-mentioned processing module 5032 can also be further used for:It is right
In each driver, the traveling angle according to each tracing point, it is determined that traveling angle is located in default different angular ranges
Velocity distribution curve;Determine the corresponding cumulative distribution function of each velocity distribution curve;Determine in different cumulative distribution function not
With the corresponding velocity amplitude of probability.
In some optional implementations of the present embodiment, above-mentioned running cost parameter includes:The oil consumption of unit distance
The maintenance cost value of value and unit distance.Above-mentioned mark module 5033 can also be further used for:By the fuel consumption values of unit distance
And the maintenance cost value of unit distance is respectively less than the driver of the first preset value labeled as the first label;By the oil consumption of unit distance
The driver that the maintenance cost value of value and unit distance is all higher than the second preset value is labeled as the second label.
In some optional implementations of the present embodiment, above-mentioned first label is the 3rd preset value, above-mentioned second mark
It is the 4th preset value to sign.Above-mentioned determining module 5034 can also be further used for:First is marked using machine learning algorithm study
Sign the driving behavior of the multiple drivers indicated by the driving behavior parameter value and the second label of indicated multiple drivers
Parameter value, determines the P values of each driving behavior parameter;Calculate each driving behavior parameter value and the 3rd preset value or the 4th preset value
Between Pearson correlation coefficients;P values are extracted more than the 5th preset value and Pearson correlation coefficients are more than driving for the 6th preset value
Behavioral parameters are sailed as characteristic parameter.
In some optional implementations of the present embodiment, above-mentioned determining module 5034 can also be further used for:Base
In the P values and Pearson correlation coefficients of each characteristic parameter, the weight of each characteristic parameter is determined;Based on each characteristic parameter and corresponding
Weight, obtains above-mentioned driver behavior modeling model.
The device for monitoring driving behavior that above-described embodiment of the application is provided, by processing module to acquisition module
The historical trajectory data set of multiple drivers of acquisition and running cost parameter sets are respectively processed, and obtain each driving
The driving behavior parameter value and running cost parameter value of member, then mark module is symbol according to the running cost parameter of each driver
The driver for closing different condition marks different labels, and determining module recycles machine learning algorithm to learn the driving of different labels
The driving behavior parameter value of member, extraction meets pre-conditioned driving behavior parameter as characteristic parameter, based on features described above ginseng
Number determines driver behavior modeling model, and monitoring unit recycles the target that above-mentioned driver behavior modeling model is obtained to acquiring unit
The historical trajectory data of driver is analyzed, and realizes the monitoring to target driver driving behavior.Above embodiments enable
Abundant excavation to the historical trajectory data of driver, the driving behavior to driver carries out quantization monitoring.
It should be appreciated that for monitor the unit 501 described in the device 500 of driving behavior to unit 502 respectively with reference
Each step in method described in Fig. 1 is corresponding, module 5031 to module 5034 respectively with the method described in Fig. 1 in
Each step is corresponding.Thus, the operation and feature above with respect to the method description for monitoring driving behavior is equally applicable to
Device 500 and the unit for wherein including, will not be repeated here.The corresponding units of device 500 can with server or terminal in
Unit cooperates to realize the scheme of the embodiment of the present application.
Below with reference to Fig. 6, it illustrates the calculating for being suitable to terminal device or server for realizing the embodiment of the present application
The structural representation of machine system 600.
As shown in fig. 6, computer system 600 includes CPU (CPU) 601, it can be according to storage read-only
Program in memory (ROM) 602 or be loaded into program in random access storage device (RAM) 603 from storage part 608 and
Perform various appropriate actions and treatment.In RAM 603, the system that is also stored with 600 operates required various programs and data.
CPU 601, ROM 602 and RAM 603 are connected with each other by bus 604.Input/output (I/O) interface 605 is also connected to always
Line 604.
I/O interfaces 605 are connected to lower component:Including the importation 606 of keyboard, mouse etc.;Penetrated including such as negative electrode
The output par, c 607 of spool (CRT), liquid crystal display (LCD) etc. and loudspeaker etc.;Storage part 608 including hard disk etc.;
And the communications portion 609 of the NIC including LAN card, modem etc..Communications portion 609 via such as because
The network of spy's net performs communication process.Driver 610 is also according to needing to be connected to I/O interfaces 605.Detachable media 611, such as
Disk, CD, magneto-optic disk, semiconductor memory etc., as needed on driver 610, in order to read from it
Computer program be mounted into as needed storage part 608.
Especially, in accordance with an embodiment of the present disclosure, the process above with reference to flow chart description may be implemented as computer
Software program.For example, embodiment of the disclosure includes a kind of computer program product, it includes being tangibly embodied in machine readable
Computer program on medium, above computer program bag is containing the program code for the method shown in execution flow chart.At this
In the embodiment of sample, the computer program can be downloaded and installed by communications portion 609 from network, and/or from removable
Medium 611 is unloaded to be mounted.When the computer program is performed by CPU (CPU) 601, in execution the present processes
The above-mentioned functions of restriction.
Flow chart and block diagram in accompanying drawing, it is illustrated that according to the system of the various embodiments of the application, method and computer journey
The architectural framework in the cards of sequence product, function and operation.At this point, each square frame in flow chart or block diagram can generation
One part for module, program segment or code of table a, part for above-mentioned module, program segment or code includes one or more
Executable instruction for realizing the logic function of regulation.It should also be noted that in some realizations as replacement, institute in square frame
The function of mark can also occur with different from the order marked in accompanying drawing.For example, two square frame reality for succeedingly representing
On can perform substantially in parallel, they can also be performed in the opposite order sometimes, and this is depending on involved function.Also
It is noted that the combination of the square frame in each square frame and block diagram and/or flow chart in block diagram and/or flow chart, Ke Yiyong
Perform the function of regulation or the special hardware based system of operation to realize, or can be referred to computer with specialized hardware
The combination of order is realized.
Being described in involved unit in the embodiment of the present application can be realized by way of software, it is also possible to by hard
The mode of part is realized.Described unit can also be set within a processor, for example, can be described as:A kind of processor bag
Include acquiring unit, monitoring unit and model construction unit.Wherein, the title of these units is not constituted to this under certain conditions
Unit restriction in itself, for example, acquiring unit is also described as " obtaining driver behavior modeling model and target driver
Historical trajectory data unit ".
As on the other hand, present invention also provides a kind of nonvolatile computer storage media, the non-volatile calculating
Machine storage medium can be the nonvolatile computer storage media included in device described in above-described embodiment;Can also
It is individualism, without the nonvolatile computer storage media allocated into terminal.Above-mentioned nonvolatile computer storage media
Be stored with one or more program, when said one or multiple programs are performed by an equipment so that the equipment:Obtain
Take the historical trajectory data of driver behavior modeling model and target driver;Using driver behavior modeling model to historical track
Data are analyzed, the driving behavior of monitoring objective driver;Wherein, above-mentioned driver behavior modeling model through the following steps that
Obtain:Obtain historical trajectory data set and the running cost data acquisition system of multiple drivers;Historical track number is processed respectively
According to set and running cost data acquisition system, the driving behavior parameter value and running cost parameter value of each driver are determined;Will row
Driver of the cost parameter value less than the first preset value is sailed labeled as the first label, running cost parameter value is preset more than second
The driver of value is labeled as the second label;Learn the driving of the multiple drivers indicated by the first label using machine learning algorithm
The driving behavior parameter value of the multiple drivers indicated by behavioral parameters value and the second label, extraction meets pre-conditioned driving
Behavioral parameters are sailed as characteristic parameter, and based on features described above parameter determination driver behavior modeling model.
Above description is only the preferred embodiment and the explanation to institute's application technology principle of the application.People in the art
Member is it should be appreciated that involved invention scope in the application, however it is not limited to the technology of the particular combination of above-mentioned technical characteristic
Scheme, while should also cover in the case where foregoing invention design is not departed from, is carried out by above-mentioned technical characteristic or its equivalent feature
Other technical schemes for being combined and being formed.Such as features described above has similar work(with (but not limited to) disclosed herein
The technical scheme that the technical characteristic of energy is replaced mutually and formed.
Claims (18)
1. a kind of method for monitoring driving behavior, it is characterised in that methods described includes:
Obtain the historical trajectory data of driver behavior modeling model and target driver;
The historical trajectory data is analyzed using the driver behavior modeling model, monitors driving for the target driver
Sail behavior;
Wherein, the driver behavior modeling model is obtained through the following steps:
Obtain historical trajectory data set and the running cost data acquisition system of multiple drivers;
The historical trajectory data set and the running cost data acquisition system are processed respectively, determine the driving row of each driver
It is parameter value and running cost parameter value;
The running cost parameter value is labeled as the first label less than the driver of the first preset value, by running cost ginseng
Numerical value is labeled as the second label more than the driver of the second preset value;
Learn driving behavior parameter value and the institute of the multiple drivers indicated by first label using machine learning algorithm
The driving behavior parameter value of the multiple drivers indicated by the second label is stated, extraction meets pre-conditioned driving behavior parameter and makees
Parameter is characterized, and the driver behavior modeling model is determined based on the characteristic parameter.
2. method according to claim 1, it is characterised in that the historical trajectory data includes the position of multiple tracing points
And the moment;And
It is described to process the historical trajectory data set and the running cost data acquisition system respectively, determine driving for each driver
Behavioral parameters value and running cost parameter value are sailed, including:
Determine the displacement between the adjacent tracing point of any two and duration in the historical trajectory data;
According to the displacement and the duration, driving behavior parameter value of each driver in each tracing point, the driving are determined
Behavioral parameters include:Speed and traveling angle.
3. method according to claim 2, it is characterised in that between the tracing point adjacent according to any two
Displacement and duration, determine driving behavior parameter value of each driver in each tracing point, including:
According to each driver in the velocity amplitude of each tracing point, the velocity distribution curve of each driver is determined;
Determine the velocity distribution curve middling speed angle value more than the number of times of default friction speed threshold value and every time more than described
The duration of default friction speed threshold value;
According to the velocity distribution curve, the cumulative distribution function of speed is determined;
Determine the corresponding velocity amplitude of default different probability value in the cumulative distribution function of the speed.
4. method according to claim 3, it is characterised in that the driving behavior parameter also includes:Acceleration;And
Displacement and duration between the tracing point adjacent according to any two, determine each driver in each tracing point
Driving behavior parameter value, including:
According to the velocity distribution curve of each driver, the acceleration of each tracing point is determined;
Determine the acceleration profile curve of each driver;
Acceleration magnitude is more than the number of times of default different acceleration rate thresholds and more than institute in determining the acceleration profile curve
State the first total duration of default different acceleration rate thresholds;
Determine that acceleration magnitude is less than zero and absolute value is more than default different acceleration rate thresholds in the acceleration profile curve
Number of times and the absolute value are more than the second total duration of the different acceleration rate thresholds;
According to the acceleration profile curve of each driver, the cumulative distribution function of acceleration is determined;
Determine the corresponding acceleration magnitude of default different probability value in the cumulative distribution function of the acceleration.
5. method according to claim 2, it is characterised in that the driving behavior parameter includes continuous driving duration;With
And
Displacement and duration between the tracing point adjacent according to any two, determine each driver in each tracing point
Driving behavior parameter value, including:
For each driver, according to the displacement between the adjacent tracing point of any two and duration, the displacement is determined
Two moment of adjacent track point less than preset displacement and the duration less than preset duration;
First moment of tracing point in moment and the historical trajectory data according to identified tracing point, last
At the moment of tracing point, determine at least one continuous driving duration of each driver.
6. method according to claim 2, it is characterised in that between the tracing point adjacent according to any two
Displacement and duration, determine driving behavior parameter value of each driver in each tracing point, including:
For each driver, the traveling angle according to each tracing point determines that the traveling angle is located at default different angles
Velocity distribution curve in the range of degree;
Determine the corresponding cumulative distribution function of each velocity distribution curve;
Determine the corresponding velocity amplitude of different probability in the different cumulative distribution function.
7. the method according to claim any one of 1-6, it is characterised in that the running cost parameter includes:Unit away from
From fuel consumption values and unit distance maintenance cost value;And
It is described that the running cost parameter is labeled as the first label less than the driver of the first preset value, by the running cost
Parameter is labeled as the second label more than the driver of the second preset value, including:
The maintenance cost value of the fuel consumption values of the unit distance and the unit distance is respectively less than the driver of the first preset value
Labeled as the first label;
The maintenance cost value of the fuel consumption values of the unit distance and the unit distance is all higher than the driver of the second preset value
Labeled as the second label.
8. the method according to claim any one of 1-6, it is characterised in that first label is the 3rd preset value, institute
The second label is stated for the 4th preset value;And
The utilization machine learning algorithm learn the driving behavior parameter value of the multiple drivers indicated by first label with
And the driving behavior parameter value of the multiple drivers indicated by second label, extract and meet pre-conditioned driving behavior ginseng
Count as characteristic parameter, including:
Using machine learning algorithm study by the driving behavior parameter value of the multiple drivers indicated by first label and
The driving behavior parameter value of the multiple drivers indicated by second label, determines the P values of each driving behavior parameter;
Calculate the Pearson correlation coefficients between each driving behavior parameter value and the 3rd preset value or the 4th preset value;
Extract the driving behavior parameter that the P values are more than the 6th preset value more than the 5th preset value and the Pearson correlation coefficients
As characteristic parameter.
9. method according to claim 8, it is characterised in that described that the driving behavior is determined based on the characteristic parameter
Monitoring model, including:
P values and Pearson correlation coefficients based on each characteristic parameter, determine the weight of each characteristic parameter;
Based on each characteristic parameter and corresponding weight, the driver behavior modeling model is obtained.
10. a kind of device for monitoring driving behavior, it is characterised in that described device includes:
Acquiring unit, the historical trajectory data for obtaining driver behavior modeling model and target driver;
Monitoring unit, for being analyzed to the historical trajectory data using the driver behavior modeling model, monitoring is described
The driving behavior of target driver;
Wherein, the driver behavior modeling model is obtained by model construction unit, and the model construction unit includes:
Acquisition module, historical trajectory data set and running cost data acquisition system for obtaining multiple drivers;
Processing module, for processing the historical trajectory data set and the running cost data acquisition system respectively, determines each
The driving behavior parameter value and running cost parameter value of driver;
Mark module, for the running cost parameter value to be labeled as into the first label less than the driver of the first preset value, will
The running cost parameter value is labeled as the second label more than the driver of the second preset value;
Determining module, the driving behavior for learning the multiple drivers indicated by first label using machine learning algorithm
The driving behavior parameter value of the multiple drivers indicated by parameter value and second label, extraction meets pre-conditioned driving
Behavioral parameters are sailed as characteristic parameter, and the driver behavior modeling model is determined based on the characteristic parameter.
11. devices according to claim 10, it is characterised in that the historical trajectory data includes the position of multiple tracing points
Put and the moment;And
The processing module is further used for:
Determine the displacement between the adjacent tracing point of any two and duration in the historical trajectory data;
According to the displacement and the duration, driving behavior parameter value of each driver in each tracing point, the driving are determined
Behavioral parameters include:Speed and traveling angle.
12. devices according to claim 11, it is characterised in that the processing module is further used for:
According to each driver in the velocity amplitude of each tracing point, the velocity distribution curve of each driver is determined;
Determine the velocity distribution curve middling speed angle value more than the number of times of default friction speed threshold value and every time more than described
The duration of default friction speed threshold value;
According to the velocity distribution curve, the cumulative distribution function of speed is determined;
Determine the corresponding velocity amplitude of default different probability value in the cumulative distribution function of the speed.
13. devices according to claim 12, it is characterised in that the driving behavior parameter also includes:Acceleration;And
The processing module is further used for:
According to the velocity distribution curve of each driver, the acceleration of each tracing point is determined;
Determine the acceleration profile curve of each driver;
Acceleration magnitude is more than the number of times of default different acceleration rate thresholds and more than institute in determining the acceleration profile curve
State the first total duration of default different acceleration rate thresholds;
Determine that acceleration magnitude is less than zero and absolute value is more than default different acceleration rate thresholds in the acceleration profile curve
Number of times and the absolute value are more than the second total duration of the different acceleration rate thresholds;
According to the acceleration profile curve of each driver, the cumulative distribution function of acceleration is determined;
Determine the corresponding acceleration magnitude of default different probability value in the cumulative distribution function of the acceleration.
14. devices according to claim 11, it is characterised in that the driving behavior parameter includes:It is continuous to drive duration;
And
The processing module is further used for:
For each driver, according to the displacement between the adjacent tracing point of any two and duration, the displacement is determined
Two moment of adjacent track point less than preset displacement and the duration less than preset duration;
First moment of tracing point in moment and the historical trajectory data according to identified tracing point, last
At the moment of tracing point, determine at least one continuous driving duration of each driver.
15. devices according to claim 11, it is characterised in that the processing module is further used for:
For each driver, the traveling angle according to each tracing point determines that the traveling angle is located at default different angles
Velocity distribution curve in the range of degree;
Determine the corresponding cumulative distribution function of each velocity distribution curve;
Determine the corresponding velocity amplitude of different probability in the different cumulative distribution function.
16. device according to claim any one of 10-15, it is characterised in that the running cost parameter includes:Unit
The fuel consumption values of distance and the maintenance cost value of unit distance;And
The mark module is further used for:
The maintenance cost value of the fuel consumption values of the unit distance and the unit distance is respectively less than the driver of the first preset value
Labeled as the first label;
The maintenance cost value of the fuel consumption values of the unit distance and the unit distance is all higher than the driver of the second preset value
Labeled as the second label.
17. device according to claim any one of 10-15, it is characterised in that first label is the 3rd preset value,
Second label is the 4th preset value;And
The determining module is further used for:
Using machine learning algorithm study by the driving behavior parameter value of the multiple drivers indicated by first label and
The driving behavior parameter value of the multiple drivers indicated by second label, determines the P values of each driving behavior parameter;
Calculate the Pearson correlation coefficients between each driving behavior parameter value and the 3rd preset value or the 4th preset value;
Extract the driving behavior parameter that the P values are more than the 6th preset value more than the 5th preset value and the Pearson correlation coefficients
As characteristic parameter.
18. devices according to claim 17, it is characterised in that the determining module is further used for:
P values and Pearson correlation coefficients based on each characteristic parameter, determine the weight of each characteristic parameter;
Based on each characteristic parameter and corresponding weight, the driver behavior modeling model is obtained.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710046084.6A CN106781503B (en) | 2017-01-22 | 2017-01-22 | Method and apparatus for monitoring driving behavior |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710046084.6A CN106781503B (en) | 2017-01-22 | 2017-01-22 | Method and apparatus for monitoring driving behavior |
Publications (2)
Publication Number | Publication Date |
---|---|
CN106781503A true CN106781503A (en) | 2017-05-31 |
CN106781503B CN106781503B (en) | 2019-04-05 |
Family
ID=58945223
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710046084.6A Active CN106781503B (en) | 2017-01-22 | 2017-01-22 | Method and apparatus for monitoring driving behavior |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106781503B (en) |
Cited By (14)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107657812A (en) * | 2017-08-29 | 2018-02-02 | 陈飞 | A kind of method that Dynamic Programming parking stall is carried out according to traffic flow forecasting |
CN108806021A (en) * | 2018-06-12 | 2018-11-13 | 重庆大学 | Electric vehicle target road section energy consumption prediction technique based on physical model and roadway characteristic parameter |
CN109102194A (en) * | 2018-08-20 | 2018-12-28 | 合肥优控科技有限公司 | A kind of driving behavior methods of marking based on global positioning system and inertial sensor |
CN109151773A (en) * | 2018-07-17 | 2019-01-04 | Oppo广东移动通信有限公司 | Information cuing method and Related product |
CN109493448A (en) * | 2018-09-26 | 2019-03-19 | 平安科技(深圳)有限公司 | Driving recording data processing method, device, computer equipment and storage medium |
CN109543497A (en) * | 2017-09-20 | 2019-03-29 | 顾泽苍 | A kind of construction method of more purposes control machine learning model suitable for automatic Pilot |
CN109919293A (en) * | 2019-02-22 | 2019-06-21 | 深兰科技(上海)有限公司 | A kind of dangerous driving determination method and device |
CN110288826A (en) * | 2019-05-24 | 2019-09-27 | 浙江工业大学 | Traffic control sub-district clustering method based on multisource data fusion and MILP |
CN110956801A (en) * | 2018-09-27 | 2020-04-03 | 株式会社斯巴鲁 | Moving body monitoring device, vehicle control system using same, and traffic system |
CN111489460A (en) * | 2019-01-28 | 2020-08-04 | 北京嘀嘀无限科技发展有限公司 | Travel data processing method, travel data processing device, navigation equipment and computer storage medium |
CN112319489A (en) * | 2020-11-18 | 2021-02-05 | 三一重型装备有限公司 | Driving behavior monitoring method, driving behavior monitoring system, server and storage medium |
CN113762755A (en) * | 2021-08-30 | 2021-12-07 | 一汽解放汽车有限公司 | Method and device for pushing driver analysis report, computer equipment and storage medium |
CN115662184A (en) * | 2022-09-09 | 2023-01-31 | 湖南大学 | Vehicle driving risk assessment method |
CN116749989A (en) * | 2023-07-24 | 2023-09-15 | 吉林大学 | Method, device, equipment and storage medium for identifying turning driving habit of driver |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103456167A (en) * | 2013-09-17 | 2013-12-18 | 重庆大学 | Good driving skill parameter obtaining method based on critical areas |
EP3073450A1 (en) * | 2015-03-27 | 2016-09-28 | Tata Consultancy Services Limited | System and method for monitoring driving behavior of a driver |
CN106056162A (en) * | 2016-06-07 | 2016-10-26 | 浙江大学 | A traffic safety credit scoring method based on GPS track and traffic law-violation records |
CN106203735A (en) * | 2016-07-27 | 2016-12-07 | 北京工业大学 | A kind of automobile driver driving behavior energy consumption characters measuring method |
-
2017
- 2017-01-22 CN CN201710046084.6A patent/CN106781503B/en active Active
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103456167A (en) * | 2013-09-17 | 2013-12-18 | 重庆大学 | Good driving skill parameter obtaining method based on critical areas |
EP3073450A1 (en) * | 2015-03-27 | 2016-09-28 | Tata Consultancy Services Limited | System and method for monitoring driving behavior of a driver |
CN106056162A (en) * | 2016-06-07 | 2016-10-26 | 浙江大学 | A traffic safety credit scoring method based on GPS track and traffic law-violation records |
CN106203735A (en) * | 2016-07-27 | 2016-12-07 | 北京工业大学 | A kind of automobile driver driving behavior energy consumption characters measuring method |
Cited By (18)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107657812A (en) * | 2017-08-29 | 2018-02-02 | 陈飞 | A kind of method that Dynamic Programming parking stall is carried out according to traffic flow forecasting |
CN109543497A (en) * | 2017-09-20 | 2019-03-29 | 顾泽苍 | A kind of construction method of more purposes control machine learning model suitable for automatic Pilot |
CN108806021A (en) * | 2018-06-12 | 2018-11-13 | 重庆大学 | Electric vehicle target road section energy consumption prediction technique based on physical model and roadway characteristic parameter |
CN109151773A (en) * | 2018-07-17 | 2019-01-04 | Oppo广东移动通信有限公司 | Information cuing method and Related product |
CN109102194A (en) * | 2018-08-20 | 2018-12-28 | 合肥优控科技有限公司 | A kind of driving behavior methods of marking based on global positioning system and inertial sensor |
CN109493448A (en) * | 2018-09-26 | 2019-03-19 | 平安科技(深圳)有限公司 | Driving recording data processing method, device, computer equipment and storage medium |
CN110956801A (en) * | 2018-09-27 | 2020-04-03 | 株式会社斯巴鲁 | Moving body monitoring device, vehicle control system using same, and traffic system |
CN111489460A (en) * | 2019-01-28 | 2020-08-04 | 北京嘀嘀无限科技发展有限公司 | Travel data processing method, travel data processing device, navigation equipment and computer storage medium |
CN109919293A (en) * | 2019-02-22 | 2019-06-21 | 深兰科技(上海)有限公司 | A kind of dangerous driving determination method and device |
CN110288826A (en) * | 2019-05-24 | 2019-09-27 | 浙江工业大学 | Traffic control sub-district clustering method based on multisource data fusion and MILP |
CN110288826B (en) * | 2019-05-24 | 2020-11-13 | 浙江工业大学 | Traffic control subregion clustering division method based on multi-source data fusion and MILP |
CN112319489A (en) * | 2020-11-18 | 2021-02-05 | 三一重型装备有限公司 | Driving behavior monitoring method, driving behavior monitoring system, server and storage medium |
CN112319489B (en) * | 2020-11-18 | 2022-03-04 | 三一重型装备有限公司 | Driving behavior monitoring method, driving behavior monitoring system, server and storage medium |
CN113762755A (en) * | 2021-08-30 | 2021-12-07 | 一汽解放汽车有限公司 | Method and device for pushing driver analysis report, computer equipment and storage medium |
CN115662184A (en) * | 2022-09-09 | 2023-01-31 | 湖南大学 | Vehicle driving risk assessment method |
CN115662184B (en) * | 2022-09-09 | 2023-11-24 | 湖南大学 | Vehicle driving risk assessment method |
CN116749989A (en) * | 2023-07-24 | 2023-09-15 | 吉林大学 | Method, device, equipment and storage medium for identifying turning driving habit of driver |
CN116749989B (en) * | 2023-07-24 | 2023-11-07 | 吉林大学 | Method, device, equipment and storage medium for identifying turning driving habit of driver |
Also Published As
Publication number | Publication date |
---|---|
CN106781503B (en) | 2019-04-05 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106781503A (en) | Method and apparatus for monitoring driving behavior | |
CN112465395A (en) | Multi-dimensional comprehensive evaluation method and device for automatically-driven automobile | |
CN103895649B (en) | A kind of driver safety driving warning method | |
CN106347359A (en) | Method and device for operating autonomous vehicle | |
CN107784251A (en) | The method evaluated based on image recognition technology driving behavior | |
CN105868787A (en) | Electric car driving range evaluation method based on working condition identification and fuzzy energy consumption | |
CN105527110B (en) | The appraisal procedure and device of automobile fuel ecomomy | |
CN107953888A (en) | A kind of road type recognition methods and system | |
CN115081508B (en) | Traffic running risk parallel simulation system based on traffic digital twin | |
CN109993966A (en) | A kind of method and device of building user portrait | |
CN106956680A (en) | A kind of electric automobile driving behavior identifying and analyzing method | |
Singh et al. | Deep learning in the automotive industry: Recent advances and application examples | |
CN108333959A (en) | A kind of energy saving method of operating of locomotive based on convolutional neural networks model | |
CN115762169B (en) | Unmanned intelligent control system and method for sanitation vehicle | |
CN107180534A (en) | The express highway section average speed method of estimation of support vector regression fusion | |
CN115291515A (en) | Automatic driving simulation test system and evaluation method based on digital twinning | |
CN103606247A (en) | Traffic early-warning method and system by means of vehicle conditions and driver physiological parameters | |
CN113762360A (en) | Surrounding rock grade prediction method in TBM tunneling process based on SMOTE + ADACOST algorithm | |
CN115221234A (en) | Method and system for portraying user based on power assembly data | |
CN103383819B (en) | Based on the desert road vehicle travel speed prediction computing system of driver's cognitive features | |
CN114495421B (en) | Intelligent open type road construction operation monitoring and early warning method and system | |
Ranacher et al. | A model to estimate and interpret the energy-efficiency of movement patterns in urban road traffic | |
CN115618294A (en) | Internet of vehicles driving big data abnormity marking method and electronic equipment | |
Shulajkovska et al. | EU smart cities: towards a new framework of urban digital transformation | |
CN113147781A (en) | Intelligent driving information display system for automobile |
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 |