CN106128099B - Driver's recognition methods and device - Google Patents
Driver's recognition methods and device Download PDFInfo
- Publication number
- CN106128099B CN106128099B CN201610513833.7A CN201610513833A CN106128099B CN 106128099 B CN106128099 B CN 106128099B CN 201610513833 A CN201610513833 A CN 201610513833A CN 106128099 B CN106128099 B CN 106128099B
- Authority
- CN
- China
- Prior art keywords
- driving data
- driver
- data
- disaggregated model
- driving
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Classifications
-
- 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
Abstract
The present invention provides a kind of driver's recognition methods and device, and wherein method includes: the driving data for obtaining current vehicle, and driving data includes: the running section data of vehicle driving data, driver status data and current vehicle;Quantification treatment is carried out to the driving data of current vehicle, obtains the driving data of presets;The driving data of presets is input in the recurrence disaggregated model being pre-created, judge whether the driver of current vehicle is default driver according to the output result for returning disaggregated model, when the driver of current vehicle is default driver, personalized service is provided to preset driver based on driving data and the corresponding driving habit data of default driver.
Description
Technical field
The present invention relates to field of communication technology more particularly to a kind of driver's recognition methods and devices.
Background technique
With communication, universal and intelligent mobile terminal the height covering of development of Mobile Internet technology, vehicle device market of networking
It flourishes, many personalized, customization vehicle-mounted services occurs.By taking digital map navigation as an example, in addition to providing roading, boat
The service such as line, common address administration, real-time traffic condition, the also collection of offer route, the message based on user search history are recommended
Deng service.
However, the offer of above-mentioned various services, dependent on the vehicle data of the acquisitions such as OBD terminal or driving data etc., base
It is analyzed in these data, service can only be provided for vehicle.And the driver for driving vehicle can have multiple, OBD terminal
Etc. being difficult to differentiate the current driver identity for driving vehicle, accordingly, it is difficult to the personalized service for driver is provided, for example,
For the fatigue monitoring of specific driver or assisting automobile driver etc..
Summary of the invention
The present invention provides a kind of driver's recognition methods and device, for solving to be difficult to provide in the prior art for driving
The problem of personalized service of member.
The first aspect of the invention is to provide a kind of driver's recognition methods, comprising:
Obtain current vehicle driving data, the driving data include: vehicle driving data, driver status data with
And the running section data of the current vehicle;
Quantification treatment is carried out to the driving data of the current vehicle, obtains the driving data of presets;
The driving data of the presets is input in the recurrence disaggregated model being pre-created, according to recurrence classification mould
The output result of type judges whether the driver of current vehicle is default driver;
If the driver of current vehicle is default driver, it is based on the driving data and the default driver couple
The driving habit data answered provide service for the default driver.
Further, the driving data by the presets is input to it in the recurrence disaggregated model being pre-created
Before, further includes:
It obtains the first sample driving data for driving each driver of current vehicle and the first sample drives number
According to corresponding model theory output valve;
Quantification treatment is carried out to the first sample driving data, obtains the first sample driving data of presets;
The first sample driving data of the presets is exported to initial and is returned in disaggregated model, is returned according to initial
The output result of disaggregated model and the corresponding model theory output valve of the first sample driving data return classification to initial
The regression coefficient of model is adjusted, and obtains the recurrence disaggregated model.
Further, described export the first sample driving data of the presets to initial returns disaggregated model
In, according to the initial output result and the corresponding model theory output valve of the first sample driving data for returning disaggregated model
The initial regression coefficient for returning disaggregated model is adjusted, after obtaining the recurrence disaggregated model, further includes:
It obtains the detection sample driving data for driving each driver of current vehicle and the detection sample drives number
According to corresponding model theory output valve;
Quantification treatment is carried out to the detection sample driving data, obtains the detection sample driving data of presets;
The detection sample driving data of the presets is exported into the recurrence disaggregated model, judges the recurrence
Whether the output result of disaggregated model model theory output valve corresponding with the detection sample driving data matches;
If corresponding output result and the ratio of the matched detection sample driving data of corresponding model theory output valve are big
In being equal to pre-set ratio, then the regression coefficient for returning disaggregated model is not adjusted.
Further, described export the first sample driving data of the presets to initial returns disaggregated model
In, according to the initial output result and the corresponding model theory output valve of the first sample driving data for returning disaggregated model
The initial regression coefficient for returning disaggregated model is adjusted, after obtaining the recurrence disaggregated model, further includes:
If corresponding output result and the ratio of the matched detection sample driving data of corresponding model theory output valve are small
In pre-set ratio, then obtains the second sample driving data for driving each driver of current vehicle and second sample is driven
The corresponding model theory output valve of data is sailed, the second sample driving data and the second sample driving data pair are based on
The model theory output valve answered to it is described return disaggregated model regression coefficient be adjusted, until corresponding output result with it is right
Until the ratio of the matched detection sample driving data of the model theory output valve answered is more than or equal to pre-set ratio.
Further, it is described return disaggregated model formula be,
Wherein, z=w0HB+w1ST+w2SB+w3RC+w4SD+w5RL+w6FD+w7AS+w8FKM;
Wherein, σ (z) is to return the output of disaggregated model as a result, HB, ST, SB, RC, SD, RL, FD, AS and FKM are default
Parameters in the driving data of form.
Further, the vehicle driving data include: acceleration, speed, steering wheel angle, average speed per hour and oil consumption;
Driver status data include: seatbelt wearing state and fatigue state;
Running section data include: speed limit data and traffic lights data.
In the present invention, a kind of driver's recognition methods is provided, by obtaining the driving data of current vehicle, driving data packet
It includes: the running section data of vehicle driving data, driver status data and current vehicle;To the driving data of current vehicle
Quantification treatment is carried out, the driving data of presets is obtained;The driving data of presets is input to the recurrence being pre-created
In disaggregated model, judge whether the driver of current vehicle is default driver according to the output result for returning disaggregated model,
When the driver of current vehicle is default driver, it is based on driving data and the corresponding driving habit data of default driver
Default driver provides personalized service.
The second aspect of the invention is to provide a kind of driver identification device, comprising:
First obtains module, and for obtaining the driving data of current vehicle, the driving data includes: vehicle driving number
According to, driver status data and the running section data of the current vehicle;
First processing module carries out quantification treatment for the driving data to the current vehicle, obtains presets
Driving data;
Input module, for the driving data of the presets to be input in the recurrence disaggregated model being pre-created,
Judge whether the driver of current vehicle is default driver according to the output result for returning disaggregated model;
Module is provided, is when presetting driver, to be based on the driving data and institute for the driver in current vehicle
It states the corresponding driving habit data of default driver and provides service for the default driver.
Further, the device further include:
Second obtains module, is pre-created for being input to the driving data of the presets in the input module
Recurrence disaggregated model in front of, obtain the first sample driving data for driving each driver of current vehicle and described the
The corresponding model theory output valve of one sample driving data;
Second processing module obtains the of presets for carrying out quantification treatment to the first sample driving data
One sample driving data;
Module being adjusted, returning disaggregated model for exporting the first sample driving data of the presets to initial
In, according to the initial output result and the corresponding model theory output valve of the first sample driving data for returning disaggregated model
The initial regression coefficient for returning disaggregated model is adjusted, the recurrence disaggregated model is obtained.
Further, the device further include:
Third obtains module, in the adjustment module according to the output result of initial recurrence disaggregated model and described
The corresponding model theory output valve of first sample driving data is adjusted the initial regression coefficient for returning disaggregated model, obtains
After the recurrence disaggregated model, the detection sample driving data for driving each driver of current vehicle and the inspection are obtained
The corresponding model theory output valve of this driving data of test sample;
Third processing module obtains the inspection of presets for carrying out quantification treatment to the detection sample driving data
This driving data of test sample;
Judgment module, for exporting the detection sample driving data of the presets to the recurrence disaggregated model
In, judge that the output result model theory output valve corresponding with the detection sample driving data for returning disaggregated model is
No matching;
Operation module, for being driven in corresponding output result with the matched detection sample of corresponding model theory output valve
When the ratio of data is more than or equal to pre-set ratio, the regression coefficient for returning disaggregated model is not adjusted.
Further, it is described return disaggregated model formula be,
Wherein, z=w0HB+w1ST+w2SB+w3RC+w4SD+w5RL+w6FD+w7AS+w8FKM;
Wherein, σ (z) is to return the output of disaggregated model as a result, HB, ST, SB, RC, SD, RL, FD, AS and FKM are default
Parameters in the driving data of form.
In the present invention, a kind of driver identification device is provided, by obtaining the driving data of current vehicle, driving data packet
It includes: the running section data of vehicle driving data, driver status data and current vehicle;To the driving data of current vehicle
Quantification treatment is carried out, the driving data of presets is obtained;The driving data of presets is input to the recurrence being pre-created
In disaggregated model, judge whether the driver of current vehicle is default driver according to the output result for returning disaggregated model,
When the driver of current vehicle is default driver, it is based on driving data and the corresponding driving habit data of default driver
Default driver provides personalized service.
Detailed description of the invention
Fig. 1 is the flow chart of driver's recognition methods one embodiment provided by the invention;
Fig. 2 is the flow chart of another embodiment of driver's recognition methods provided by the invention;
Fig. 3 is the structural schematic diagram of driver identification device one embodiment provided by the invention;
Fig. 4 is the structural schematic diagram of another embodiment of driver identification device provided by the invention;
Fig. 5 is the structural schematic diagram of another embodiment of driver identification device provided by the invention.
Specific embodiment
In order to make the object, technical scheme and advantages of the embodiment of the invention clearer, below in conjunction with the embodiment of the present invention
In attached drawing, technical scheme in the embodiment of the invention is clearly and completely described, it is clear that described embodiment is
A part of the embodiment of the present invention, instead of all the embodiments.Based on the embodiments of the present invention, those of ordinary skill in the art
Every other embodiment obtained without making creative work, shall fall within the protection scope of the present invention.
Fig. 1 is the flow chart of driver's recognition methods one embodiment provided by the invention, as shown in Figure 1, comprising:
101, obtain current vehicle driving data, driving data include: vehicle driving data, driver status data with
And the running section data of current vehicle.
The executing subject of driver's recognition methods provided by the invention is driver identification device, driver identification device tool
Body can be car-mounted terminal or the onboard servers etc. connecting with car-mounted terminal, and driver identification device can also be to be mounted on
Software etc. on car-mounted terminal or onboard servers.
Wherein, obtain the mode of the driving data of current vehicle at least can there are three types of: vehicle intelligent terminal OBD, drive
The vehicular applications or onboard operations system installed on the mobile terminal of member.Vehicle driving data are specifically as follows acceleration, speed
Degree, steering wheel angle, average speed per hour and oil consumption etc.;Driver status data may include: seatbelt wearing state and tired shape
State etc.;Running section data may include: speed limit data and traffic lights data etc..
Further, vehicle driving data can also include: lane line signal, direction modulating signal, throttle signal, clutch
Signal, shift signal and gyro data etc..In the above parameter any one or be combined with each other and can embody driving
Member following driving behavior: bring to a halt, take a sudden turn, seatbelt wearing state, whether rapidly rob lamp, whether drive over the speed limit, whether
Press lanes, whether fatigue driving, average speed per hour and fuel consumption per hundred kilometers etc..
102, quantification treatment is carried out to the driving data of current vehicle, obtains the driving data of presets.
Specifically, the driving data to current vehicle carries out quantification treatment, the driving data of obtained presets is specific
It can be with are as follows: hundred kilometers of numbers of bringing to a halt, hundred kilometers of zig zag numbers, seatbelt wearing situation rapidly rob modulation frequency, hundred kilometers of hypervelocities rows
Sail rate, hundred kilometers of delay unloading diatom traveling number, hundred kilometers of fatigue driving numbers, hundred kilometers of average speed per hours and fuel consumption per hundred kilometers etc..
103, the driving data of presets is input in the recurrence disaggregated model being pre-created, according to recurrence classification mould
The output result of type judges whether the driver of current vehicle is default driver.
Wherein, the formula for returning disaggregated model can be,
Wherein, z=w0HB+w1ST+w2SB+w3RC+w4SD+w5RL+w6FD+w7AS+w8FKM;
Wherein, σ (z) is to return the output of disaggregated model as a result, HB, ST, SB, RC, SD, RL, FD, AS and FKM are default
Parameters in the driving data of form.
Corresponding, HB is hundred kilometers of numbers of bringing to a halt;ST is hundred kilometers of zig zag numbers;SB is seatbelt wearing situation;RC is
Rapidly rob modulation frequency;SD is hundred kilometers of rates of driving over the speed limit;RL is that hundred kilometers of diatoms of delaying unloading travel number;FD is hundred kilometers of fatigue drivings
Number;AS is hundred kilometers of average speed per hours;FKM is fuel consumption per hundred kilometers.W0, W1, W2, W3, W4, W5, W6, W7, W8 are followed successively by hundred kilometers
Bring to a halt number, hundred kilometers of zig zag numbers, seatbelt wearing situation, rapidly rob modulation frequency, hundred kilometers of rates of driving over the speed limit, hundred kilometers pressure
Lane line travels the regression coefficient of number, hundred kilometers of fatigue driving numbers, hundred kilometers of average speed per hours and fuel consumption per hundred kilometers.
Specifically, can be obtained after the driving data of presets is input in the recurrence disaggregated model being pre-created
To output valve of the range between 0-1, when output valve is more than or equal to 0.5, indicate that the driver of current vehicle is car owner;
When output valve is less than 0.5, indicate that the driver of current vehicle is non-car owner.
If 104, the driver of current vehicle is default driver, corresponding based on driving data and default driver
Driving habit data provide service for default driver.
Wherein, default driver can be car owner or non-car owner.
In the present embodiment, a kind of driver's recognition methods is provided, by obtaining the driving data of current vehicle, driving data
It include: the running section data of vehicle driving data, driver status data and current vehicle;To the driving number of current vehicle
According to quantification treatment is carried out, the driving data of presets is obtained;The driving data of presets is input to time being pre-created
Return in disaggregated model, judge whether the driver of current vehicle is default driver according to the output result for returning disaggregated model,
When the driver of current vehicle is default driver, it is based on driving data and the corresponding driving habit data of default driver
Personalized service is provided to preset driver.
Fig. 2 is the flow chart that driver's recognition methods provided by the invention has one embodiment, as shown in Fig. 2, in Fig. 1 institute
On the basis of showing embodiment, before step 103, can also include:
105, it obtains the first sample driving data for driving each driver of current vehicle and first sample drives number
According to corresponding model theory output valve.
Wherein, first sample driving data be specifically as follows current time for the previous period in drive current vehicle it is each
The history driving data of driver.The length of this time, which can according to need, to be set.
106, quantification treatment is carried out to first sample driving data, obtains the first sample driving data of presets.
It wherein, herein can be with the place of the driving data of reference pair current vehicle to the quantification treatment of first sample driving data
Reason mode, is no longer described in detail herein.
107, the first sample driving data of presets is exported to initial and is returned in disaggregated model, returned according to initial
The corresponding model theory output valve of output result and first sample driving data of disaggregated model returns disaggregated model to initial
Regression coefficient be adjusted, obtain return disaggregated model.
It further, can also include: the detection sample for obtaining each driver for driving current vehicle after step 107
This driving data and the corresponding model theory output valve of detection sample driving data;Detection sample driving data is quantified
Processing, obtains the detection sample driving data of presets;The detection sample driving data of presets is exported to recurrence point
In class model, whether the output result for returning disaggregated model model theory output valve corresponding with detection sample driving data is judged
Matching;If it is corresponding output result and corresponding model theory output valve it is matched detection sample driving data ratio greater than etc.
In pre-set ratio, then the regression coefficient for returning disaggregated model is not adjusted.
In addition, it is necessary to be illustrated, if corresponding output result and the corresponding matched inspection of model theory output valve
The ratio of this driving data of test sample is less than pre-set ratio, then obtains the second sample driving for driving each driver of current vehicle
Data and the corresponding model theory output valve of the second sample driving data are based on the second sample driving data and the second sample
The corresponding model theory output valve of driving data is adjusted the regression coefficient for returning disaggregated model, until corresponding output is tied
Until the ratio of fruit and the matched detection sample driving data of corresponding model theory output valve is more than or equal to pre-set ratio.
In the present embodiment, a kind of driver's recognition methods is provided, by obtaining the driving data of current vehicle, driving data
It include: the running section data of vehicle driving data, driver status data and current vehicle;To the driving number of current vehicle
According to quantification treatment is carried out, the driving data of presets is obtained;Obtain the first sample for driving each driver of current vehicle
Driving data and the corresponding model theory output valve of first sample driving data;Of each driver based on current vehicle
One sample driving data and the corresponding model theory output valve of first sample driving data return in disaggregated model to initial
Each regression coefficient is adjusted, and obtains returning disaggregated model;The driving data of presets is input to time being pre-created
Return in disaggregated model, judge whether the driver of current vehicle is default driver according to the output result for returning disaggregated model,
When the driver of current vehicle is default driver, it is based on driving data and the corresponding driving habit data of default driver
Personalized service is provided to preset driver.
Those of ordinary skill in the art will appreciate that: realize that all or part of the steps of above-mentioned each method embodiment can lead to
The relevant hardware of program instruction is crossed to complete.Program above-mentioned can be stored in a computer readable storage medium.The journey
When being executed, execution includes the steps that above-mentioned each method embodiment to sequence;And storage medium above-mentioned include: ROM, RAM, magnetic disk or
The various media that can store program code such as person's CD.
Fig. 3 is the structural schematic diagram of driver identification device one embodiment provided by the invention, as shown in Figure 3, comprising:
First obtains module 31, for obtaining the driving data of current vehicle, driving data include: vehicle driving data,
The running section data of driver status data and current vehicle;
First processing module 32 carries out quantification treatment for the driving data to current vehicle, obtains driving for presets
Sail data;
Input module 33, for the driving data of presets to be input in the recurrence disaggregated model being pre-created, root
Judge whether the driver of current vehicle is default driver according to the output result for returning disaggregated model;
Module 34 is provided, is based on driving data and to be preset when presetting driver for the driver in current vehicle
The corresponding driving habit data of driver provide service for default driver.
Driver identification device provided by the invention is specifically as follows car-mounted terminal or connect with car-mounted terminal vehicle-mounted
Server etc., driver identification device can also be the software etc. being mounted in car-mounted terminal or onboard servers.
Wherein, obtain the mode of the driving data of current vehicle at least can there are three types of: vehicle intelligent terminal OBD, drive
The vehicular applications or onboard operations system installed on the mobile terminal of member.Vehicle driving data are specifically as follows acceleration, speed
Degree, steering wheel angle, average speed per hour and oil consumption etc.;Driver status data may include: seatbelt wearing state and tired shape
State etc.;Running section data may include: speed limit data and traffic lights data etc..
Further, vehicle driving data can also include: lane line signal, direction modulating signal, throttle signal, clutch
Signal, shift signal and gyro data etc..In the above parameter any one or be combined with each other and can embody driving
Member following driving behavior: bring to a halt, take a sudden turn, seatbelt wearing state, whether rapidly rob lamp, whether drive over the speed limit, whether
Press lanes, whether fatigue driving, average speed per hour and fuel consumption per hundred kilometers etc..
Specifically, the driving data to current vehicle carries out quantification treatment, the driving data of obtained presets is specific
It can be with are as follows: hundred kilometers of numbers of bringing to a halt, hundred kilometers of zig zag numbers, seatbelt wearing situation rapidly rob modulation frequency, hundred kilometers of hypervelocities rows
Sail rate, hundred kilometers of delay unloading diatom traveling number, hundred kilometers of fatigue driving numbers, hundred kilometers of average speed per hours and fuel consumption per hundred kilometers etc..
Further, the formula for returning disaggregated model can be,
Wherein, z=w0HB+w1ST+w2SB+w3RC+w4SD+w5RL+w6FD+w7AS+w8FKM;
Wherein, σ (z) is to return the output of disaggregated model as a result, HB, ST, SB, RC, SD, RL, FD, AS and FKM are default
Parameters in the driving data of form.
Corresponding, HB is hundred kilometers of numbers of bringing to a halt;ST is hundred kilometers of zig zag numbers;SB is seatbelt wearing situation;RC is
Rapidly rob modulation frequency;SD is hundred kilometers of rates of driving over the speed limit;RL is that hundred kilometers of diatoms of delaying unloading travel number;FD is hundred kilometers of fatigue drivings
Number;AS is hundred kilometers of average speed per hours;FKM is fuel consumption per hundred kilometers.W0, W1, W2, W3, W4, W5, W6, W7, W8 are followed successively by hundred kilometers
Bring to a halt number, hundred kilometers of zig zag numbers, seatbelt wearing situation, rapidly rob modulation frequency, hundred kilometers of rates of driving over the speed limit, hundred kilometers pressure
Lane line travels the regression coefficient of number, hundred kilometers of fatigue driving numbers, hundred kilometers of average speed per hours and fuel consumption per hundred kilometers.
Specifically, can be obtained after the driving data of presets is input in the recurrence disaggregated model being pre-created
To output valve of the range between 0-1, when output valve is more than or equal to 0.5, indicate that the driver of current vehicle is car owner;
When output valve is less than 0.5, indicate that the driver of current vehicle is non-car owner.
Further, Fig. 4 is the structural schematic diagram of another embodiment of driver identification device provided by the invention, is such as schemed
Shown in 4, on the basis of embodiment shown in Fig. 3, the driver identification device further include:
Second obtains module 35, for the driving data of presets to be input to the recurrence being pre-created in input module
Before in disaggregated model, obtains the first sample driving data for driving each driver of current vehicle and first sample drives
The corresponding model theory output valve of data;
Second processing module 36 obtains the first of presets for carrying out quantification treatment to first sample driving data
Sample driving data;
Module 37 being adjusted, being returned in disaggregated model for exporting the first sample driving data of presets to initial,
According to the initial output result for returning disaggregated model and the corresponding model theory output valve of first sample driving data to initial
The regression coefficient for returning disaggregated model is adjusted, and obtains returning disaggregated model.
Further, Fig. 5 is the structural schematic diagram of another embodiment of driver identification device provided by the invention, is such as schemed
Shown in 5, on the basis of the embodiment shown in fig. 4, the driver identification device further include:
Third obtains module 38, for the output result and the first sample in adjustment module according to initial recurrence disaggregated model
The corresponding model theory output valve of this driving data is adjusted the initial regression coefficient for returning disaggregated model, obtains returning and divide
After class model, the detection sample driving data for driving each driver of current vehicle and detection sample driving data are obtained
Corresponding model theory output valve;
Third processing module 39 obtains the detection of presets for carrying out quantification treatment to detection sample driving data
Sample driving data;
Judgment module 40 judges for exporting the detection sample driving data of presets to returning in disaggregated model
Whether the output result model theory output valve corresponding with detection sample driving data for returning disaggregated model matches;
Operation module 41, for being driven in corresponding output result with the matched detection sample of corresponding model theory output valve
When sailing the ratio of data more than or equal to pre-set ratio, the regression coefficient for returning disaggregated model is not adjusted.
In addition, it is necessary to be illustrated, if corresponding output result and the corresponding matched inspection of model theory output valve
The ratio of this driving data of test sample is less than pre-set ratio, then obtains the second sample driving for driving each driver of current vehicle
Data and the corresponding model theory output valve of the second sample driving data are based on the second sample driving data and the second sample
The corresponding model theory output valve of driving data is adjusted the regression coefficient for returning disaggregated model, until corresponding output is tied
Until the ratio of fruit and the matched detection sample driving data of corresponding model theory output valve is more than or equal to pre-set ratio.
In the present embodiment, a kind of driver identification device is provided, by obtaining the driving data of current vehicle, driving data
It include: the running section data of vehicle driving data, driver status data and current vehicle;To the driving number of current vehicle
According to quantification treatment is carried out, the driving data of presets is obtained;The driving data of presets is input to time being pre-created
Return in disaggregated model, judge whether the driver of current vehicle is default driver according to the output result for returning disaggregated model,
When the driver of current vehicle is default driver, it is based on driving data and the corresponding driving habit data of default driver
Personalized service is provided to preset driver.
Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present invention., rather than its limitations;To the greatest extent
Pipe present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that: its according to
So be possible to modify the technical solutions described in the foregoing embodiments, or to some or all of the technical features into
Row equivalent replacement;And these are modified or replaceed, various embodiments of the present invention technology that it does not separate the essence of the corresponding technical solution
The range of scheme.
Claims (9)
1. a kind of driver's recognition methods characterized by comprising
The driving data of current vehicle is obtained, the driving data includes: vehicle driving data, driver status data and institute
State the running section data of current vehicle;
Quantification treatment is carried out to the driving data of the current vehicle, obtains the driving data of presets;
The driving data of the presets is input in the recurrence disaggregated model being pre-created, according to recurrence disaggregated model
Output result judges whether the driver of current vehicle is default driver;
If the driver of current vehicle is default driver, corresponding based on the driving data and the default driver
Driving habit data provide service for the default driver;
The vehicle driving data include: acceleration, speed, steering wheel angle, average speed per hour and oil consumption;
Driver status data include: seatbelt wearing state and fatigue state;
Running section data include: speed limit data and traffic lights data.
2. the method according to claim 1, wherein the driving data by the presets be input to it is pre-
Before in the recurrence disaggregated model first created, further includes:
Obtain the first sample driving data and the first sample driving data pair for driving each driver of current vehicle
The model theory output valve answered;
Quantification treatment is carried out to the first sample driving data, obtains the first sample driving data of presets;
The first sample driving data of the presets is exported to initial and is returned in disaggregated model, returns classification according to initial
The output result of model and the corresponding model theory output valve of the first sample driving data return disaggregated model to initial
Regression coefficient be adjusted, obtain the recurrence disaggregated model.
3. according to the method described in claim 2, it is characterized in that, the first sample driving data by the presets
Output returns in disaggregated model to initial, drives number according to the initial output result for returning disaggregated model and the first sample
The initial regression coefficient for returning disaggregated model is adjusted according to corresponding model theory output valve, obtains the recurrence classification mould
After type, further includes:
Obtain the detection sample driving data and the detection sample driving data pair for driving each driver of current vehicle
The model theory output valve answered;
Quantification treatment is carried out to the detection sample driving data, obtains the detection sample driving data of presets;
The detection sample driving data of the presets is exported into the recurrence disaggregated model, judges the recurrence classification
Whether the output result of model model theory output valve corresponding with the detection sample driving data matches;
If it is corresponding output result and corresponding model theory output valve it is matched detection sample driving data ratio greater than etc.
In pre-set ratio, then the regression coefficient for returning disaggregated model is not adjusted.
4. according to the method described in claim 3, it is characterized in that, the first sample driving data by the presets
Output returns in disaggregated model to initial, drives number according to the initial output result for returning disaggregated model and the first sample
The initial regression coefficient for returning disaggregated model is adjusted according to corresponding model theory output valve, obtains the recurrence classification mould
After type, further includes:
If corresponding output result and the ratio of the matched detection sample driving data of corresponding model theory output valve are less than pre-
If ratio, then obtains the second sample driving data for driving each driver of current vehicle and second sample drives number
It is corresponding based on the second sample driving data and the second sample driving data according to corresponding model theory output valve
Model theory output valve to it is described return disaggregated model regression coefficient be adjusted, until corresponding output result with it is corresponding
Until the ratio of the matched detection sample driving data of model theory output valve is more than or equal to pre-set ratio.
5. the method according to claim 1, wherein it is described return disaggregated model formula be,
Wherein, z=w0HB+w1ST+w2SB+w3RC+w4SD+w5RL+w6FD+w7AS+w8FKM;
Wherein, σ (z) is to return the output of disaggregated model as a result, HB, ST, SB, RC, SD, RL, FD, AS and FKM are presets
Driving data in parameters;HB is hundred kilometers of numbers of bringing to a halt;ST is hundred kilometers of zig zag numbers;SB is seatbelt wearing feelings
Condition;RC is rapidly to rob modulation frequency;SD is hundred kilometers of rates of driving over the speed limit;RL is that hundred kilometers of diatoms of delaying unloading travel number;FD is hundred kilometers
Fatigue driving number;AS is hundred kilometers of average speed per hours;FKM is fuel consumption per hundred kilometers.
6. a kind of driver identification device characterized by comprising
First obtains module, and for obtaining the driving data of current vehicle, the driving data includes: vehicle driving data, drives
The running section data of the person's of sailing status data and the current vehicle;
First processing module carries out quantification treatment for the driving data to the current vehicle, obtains the driving of presets
Data;
Input module, for the driving data of the presets to be input in the recurrence disaggregated model being pre-created, according to
The output result for returning disaggregated model judges whether the driver of current vehicle is default driver;
Module is provided, when for the driver in current vehicle being default driver, based on the driving data and described pre-
If the corresponding driving habit data of driver provide service for the default driver;
Wherein, the vehicle driving data include: acceleration, speed, steering wheel angle, average speed per hour and oil consumption;
Driver status data include: seatbelt wearing state and fatigue state;
Running section data include: speed limit data and traffic lights data.
7. device according to claim 6, which is characterized in that further include:
Second obtains module, for the driving data of the presets to be input to time being pre-created in the input module
Before returning in disaggregated model, the first sample driving data and first sample for driving each driver of current vehicle are obtained
The corresponding model theory output valve of this driving data;
Second processing module obtains the first sample of presets for carrying out quantification treatment to the first sample driving data
This driving data;
Module being adjusted, being returned in disaggregated model for exporting the first sample driving data of the presets to initial, root
According to the initial output result for returning disaggregated model and the corresponding model theory output valve of the first sample driving data to first
The regression coefficient for beginning to return disaggregated model is adjusted, and obtains the recurrence disaggregated model.
8. device according to claim 7, which is characterized in that further include:
Third obtains module, for the output result and described first in the adjustment module according to initial recurrence disaggregated model
The corresponding model theory output valve of sample driving data is adjusted the initial regression coefficient for returning disaggregated model, obtains described
After returning disaggregated model, the detection sample driving data and the detection sample for driving each driver of current vehicle are obtained
The corresponding model theory output valve of this driving data;
Third processing module obtains the detection sample of presets for carrying out quantification treatment to the detection sample driving data
This driving data;
Judgment module is sentenced for exporting the detection sample driving data of the presets into the recurrence disaggregated model
Break it is described return disaggregated model output result model theory output valve corresponding with the detection sample driving data whether
Match;
Operation module, in corresponding output result and the matched detection sample driving data of corresponding model theory output valve
Ratio be more than or equal to pre-set ratio when, not to it is described return disaggregated model regression coefficient be adjusted.
9. device according to claim 6, which is characterized in that it is described return disaggregated model formula be,
Wherein, z=w0HB+w1ST+w2SB+w3RC+w4SD+w5RL+w6FD+w7AS+w8FKM;
Wherein, σ (z) is to return the output of disaggregated model as a result, HB, ST, SB, RC, SD, RL, FD, AS and FKM are presets
Driving data in parameters;HB is hundred kilometers of numbers of bringing to a halt;ST is hundred kilometers of zig zag numbers;SB is seatbelt wearing feelings
Condition;RC is rapidly to rob modulation frequency;SD is hundred kilometers of rates of driving over the speed limit;RL is that hundred kilometers of diatoms of delaying unloading travel number;FD is hundred kilometers
Fatigue driving number;AS is hundred kilometers of average speed per hours;FKM is fuel consumption per hundred kilometers.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610513833.7A CN106128099B (en) | 2016-07-01 | 2016-07-01 | Driver's recognition methods and device |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610513833.7A CN106128099B (en) | 2016-07-01 | 2016-07-01 | Driver's recognition methods and device |
Publications (2)
Publication Number | Publication Date |
---|---|
CN106128099A CN106128099A (en) | 2016-11-16 |
CN106128099B true CN106128099B (en) | 2018-12-07 |
Family
ID=57468155
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610513833.7A Active CN106128099B (en) | 2016-07-01 | 2016-07-01 | Driver's recognition methods and device |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106128099B (en) |
Families Citing this family (15)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107665579A (en) * | 2016-07-27 | 2018-02-06 | 上海博泰悦臻网络技术服务有限公司 | A kind of user's driving behavior monitoring method and device |
CN108128264B (en) * | 2016-11-30 | 2020-03-20 | 中国移动通信有限公司研究院 | Driver identity recognition method and device |
CN107038332A (en) * | 2017-01-03 | 2017-08-11 | 阿里巴巴集团控股有限公司 | A kind of object selection method and device |
CN108944799B (en) * | 2017-05-18 | 2022-06-03 | 腾讯科技(深圳)有限公司 | Vehicle driving behavior abnormity processing method and device |
CN107215307A (en) * | 2017-05-24 | 2017-09-29 | 清华大学深圳研究生院 | Driver identity recognition methods and system based on vehicle sensors correction data |
CN108229567B (en) * | 2018-01-09 | 2021-06-15 | 荣联科技集团股份有限公司 | Driver identity recognition method and device |
CN108280482B (en) * | 2018-01-30 | 2020-10-16 | 广州小鹏汽车科技有限公司 | Driver identification method, device and system based on user behaviors |
CN108725444B (en) * | 2018-05-19 | 2020-12-29 | 智车优行科技(北京)有限公司 | Driving method and device, electronic device, vehicle, program, and medium |
CN109050520A (en) * | 2018-08-16 | 2018-12-21 | 上海小蚁科技有限公司 | Vehicle driving state based reminding method and device, computer readable storage medium |
CN110443185B (en) * | 2019-07-31 | 2020-11-24 | 北京京东智能城市大数据研究院 | Driver identification method, driver identification device, electronic device, and storage medium |
CN110455303A (en) * | 2019-08-05 | 2019-11-15 | 深圳市大拿科技有限公司 | AR air navigation aid, device and the AR navigation terminal suitable for vehicle |
CN111422203B (en) * | 2020-02-28 | 2022-03-15 | 南京交通职业技术学院 | Driving behavior evaluation method and device |
CN113799717A (en) * | 2020-06-12 | 2021-12-17 | 广州汽车集团股份有限公司 | Fatigue driving relieving method and system and computer readable storage medium |
CN112417983A (en) * | 2020-10-28 | 2021-02-26 | 在行(杭州)大数据科技有限公司 | Vehicle driver determination method, device, equipment and medium based on multi-source data |
WO2023225811A1 (en) * | 2022-05-23 | 2023-11-30 | 华为技术有限公司 | Method and apparatus for assisting with driving, and vehicle |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101633359A (en) * | 2008-07-24 | 2010-01-27 | 通用汽车环球科技运作公司 | Adaptive vehicle control system with driving style recognition |
CN102686476A (en) * | 2009-12-25 | 2012-09-19 | 雅马哈发动机株式会社 | Rider characteristics assessment device and straddle-ridden vehicle provided therewith |
CN104765598A (en) * | 2014-01-06 | 2015-07-08 | 哈曼国际工业有限公司 | Automatic driver identification |
CN105303829A (en) * | 2015-09-11 | 2016-02-03 | 深圳市乐驰互联技术有限公司 | Vehicle driver emotion recognition method and device |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
MX2007014997A (en) * | 2005-06-01 | 2008-04-22 | Innosurance Inc | Motor vehicle operating data collection and analysis. |
-
2016
- 2016-07-01 CN CN201610513833.7A patent/CN106128099B/en active Active
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101633359A (en) * | 2008-07-24 | 2010-01-27 | 通用汽车环球科技运作公司 | Adaptive vehicle control system with driving style recognition |
CN102686476A (en) * | 2009-12-25 | 2012-09-19 | 雅马哈发动机株式会社 | Rider characteristics assessment device and straddle-ridden vehicle provided therewith |
CN104765598A (en) * | 2014-01-06 | 2015-07-08 | 哈曼国际工业有限公司 | Automatic driver identification |
CN105303829A (en) * | 2015-09-11 | 2016-02-03 | 深圳市乐驰互联技术有限公司 | Vehicle driver emotion recognition method and device |
Also Published As
Publication number | Publication date |
---|---|
CN106128099A (en) | 2016-11-16 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106128099B (en) | Driver's recognition methods and device | |
CN107444402B (en) | Vehicle mode scheduling with learning user preferences | |
US10223919B2 (en) | Vehicle pedestrian safety system and methods of use and manufacture thereof | |
AU2019205817B2 (en) | Software validation for autonomous vehicles | |
CN109817008B (en) | System and method for unprotected left turn in heavy traffic situations in autonomous vehicles | |
US9747730B2 (en) | Driver measurement and incentive system for improving fuel-efficiency | |
US11348053B2 (en) | Generating predictive information associated with vehicle products/services | |
CN109421630A (en) | For monitoring the controller architecture of the health of autonomous vehicle | |
WO2019190655A1 (en) | Safety enhanced computer assisted driving method and apparatus | |
DE102019105874A1 (en) | Automated driving systems and control logic for cloud-based scenario planning of autonomous vehicles | |
CN107433949B (en) | System and method for vehicle adaptive driving control | |
US20150015416A1 (en) | System and method for setting warning reference of advanced driver assistance system | |
US20140172220A1 (en) | Unmanned autonomous traveling service apparatus and method based on driving information database | |
US20140379171A1 (en) | Apparatus and method for controlling vehicle | |
CN105185112A (en) | Driving behavior analysis and recognition method and system | |
CN110576808B (en) | Vehicle, vehicle machine equipment and scene information pushing method based on artificial intelligence | |
CN104709164A (en) | Prompt method and system of driver state based on driving behaviors | |
WO2021088395A1 (en) | Vehicle navigation method and terminal | |
CN108280482A (en) | Driver's recognition methods based on user behavior, apparatus and system | |
US10692252B2 (en) | Integrated interface for situation awareness information alert, advise, and inform | |
US20180130349A1 (en) | Methods and systems for displaying virtual signs based on vehicle to everything communications | |
US20210031765A1 (en) | Simulating Braking When Speeding on Cruise Control to Facilitate Use of ISA System | |
CN113928328A (en) | Impaired driving assistance | |
US20210061288A1 (en) | Driver driving style detection and application system | |
CN111540224A (en) | Road data processing method and related equipment |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant | ||
TR01 | Transfer of patent right | ||
TR01 | Transfer of patent right |
Effective date of registration: 20200327 Address after: 200030 D1, building 2, No. 55 Huaihai West Road, Shanghai, Xuhui District Patentee after: ZEBRA NETWORK TECHNOLOGY Co.,Ltd. Address before: 201805 Shanghai City, Jiading District Anting Town Road No. 569, room 415 a. Patentee before: BANMA INFORMATION TECHNOLOGY Co.,Ltd. |