CN105374211B - The system and method for driving risk and aiding in vehicle insurance price is calculated based on multi-source data - Google Patents
The system and method for driving risk and aiding in vehicle insurance price is calculated based on multi-source data Download PDFInfo
- Publication number
- CN105374211B CN105374211B CN201510904331.2A CN201510904331A CN105374211B CN 105374211 B CN105374211 B CN 105374211B CN 201510904331 A CN201510904331 A CN 201510904331A CN 105374211 B CN105374211 B CN 105374211B
- Authority
- CN
- China
- Prior art keywords
- risk
- user
- driving
- data
- submodule
- 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.)
- Expired - Fee Related
Links
Landscapes
- Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention discloses a kind of system and method for being calculated based on multi-source data and driving risk and aiding in vehicle insurance price, the system includes the intelligent mobile terminal and remote server of interconnection；There is some data sensor collectors and application in intelligent mobile terminal；Risk model algorithmic system is installed, including scene drives risk analysis submodule, divert one's attention driving model identification submodule, user's travel behaviour analysis submodule and driving behavior Assessment for classification system submodule on remote server；The Traffic Information that this method is obtained by the data and remote server that are gathered to intelligent mobile terminal is analyzed, and calculates the scoring in each submodule, and carry out vehicle insurance price according to scoring.It is an advantage of the invention that, by the collection of multi-source data with merging, driving behavior to user is analyzed, can to the travel behaviour of driver, custom of driving, drive risk and effectively be demarcated, so as to be that the vehicle insurance pricing model based on driving behavior is provided fundamental basis and technical support.
Description
Technical field
The invention belongs to traffic safety and data statistics technical field, and in particular to one kind is calculated based on multi-source data and driven
The system and method for risk and auxiliary vehicle insurance price.
Background technology
Common vehicle insurance pricing model be typically based on such as driver's age, sex, the driving age, Living city, accident record,
The static informations such as history of settling a claim, and ignore the driving custom of driver, the individual factors such as driving of diverting one's attention.And in fact, these
Factor is likely more important for the compensation risk that the traffic safety of driver may need to undertake with insurance company.In year
In the case of age, driving age etc. all identicals, if driver drive every year 20000 kilometers, often drive over the speed limit, brake
Throttle is all stepped on more violent, often makes a phone call or sends short messages during driving, and another driver only opens 5,000 kilometers every year, usually
Driving is in compliance with traffic rules, it is however generally that the danger coefficient of first driver can be far above with the probability of traffic accident occurs
Second.If insurance company imposes same premium to two people, a series of problem may be brought, is also unfavorable for insuring
Company accurately calculates customer risk, subdivision customer group.
This is directed to, the automobile insurance computation schema based on driving behavior（ Usage Based Insurance,
UBI）Come into vogue in recent years in American-European countries.Method used by them, the overwhelming majority is all from OBD
（OBD-II）Port, by a hardware, vehicle traveling process is included into the information records such as real-time speed, acceleration and deceleration and got off,
And remote server is passed back so that data analysis uses.This technology hardware costs, data acquisition duration, data acquisition it is complete
Face property etc. all there is it is certain the defects of.Due to hardware facility expense costly, user is typically only allowed for from insurance
Company's short-term lease.During this period, driver's often cautious trip, and the mistake of observation period one is waited, user will return
Again to the driving behavior being accustomed to before.In addition, this method also can not detect whether driver is connect when driving
Make a phone call, receive and dispatch the divert one's attention driving behavior closely related with driving risk such as short message.
The content of the invention
Driven according to the deficiencies of the prior art described above, It is an object of the present invention to provide one kind is calculated based on multi-source data
The system and method for risk and auxiliary vehicle insurance price, the system and method are travelled by the driver gathered to intelligent mobile terminal
Track, sensing data and the fusion calculation of the multi-source data such as Traffic Net information, dynamic traffic situation progress on the way, with
Driving behavior, driving custom to user are analyzed, so as to which the driving risk to user quantifies, for based on driving behavior
Vehicle insurance pricing model provide fundamental basis.
The object of the invention is realized and completed by following technical scheme：
It is a kind of that the system for driving risk with aiding in vehicle insurance price is calculated based on multi-source data, it is characterised in that the system bag
Include can interactive communication intelligent mobile terminal and remote server；In the intelligent mobile terminal there are some data sensors to adopt
Storage, and application for users to use is installed；The risk model algorithm system of interactive communication is installed on the remote server
System and data collecting system, the risk model algorithmic system include scene and drive risk analysis submodule, divert one's attention to drive mould
Formula identification submodule, user's travel behaviour analysis submodule and driving behavior Assessment for classification system submodule；Wherein, the intelligence
Energy mobile terminal is with the data collecting system interactive communication, and the driving behavior Assessment for classification system submodule is the same as the scene
Drive risk analysis submodule, divert one's attention driving model identification submodule and user's travel behaviour analysis submodule interactive communication.
Data collecting system on the remote server is used to obtain Traffic Information and the intelligent mobile is whole
Gathered data are applied at end, and the data collecting system drives risk analysis submodule, driving model of diverting one's attention with the scene
Identify submodule and user's travel behaviour analysis submodule interactive communication.
Some data sensor collectors in the intelligent mobile terminal are global location chip, accelerometer and gyro
Instrument.
A kind of to be related to any of the above-described method for being calculated based on multi-source data and driving risk with aiding in vehicle insurance price, its feature exists
Comprise the following steps in methods described：
In user on the run, global location chip, accelerometer and the gyroscope in the intelligent mobile terminal
Real-time latitude and longitude coordinates, direction of traffic, instantaneous velocity, acceleration and angular speed are acquired and passed by the application
Deliver on the remote server；
The data collecting system obtains Traffic Net information, dynamic traffic data and comes from the intelligence automatically
The input data of energy mobile terminal application, and send into the risk model algorithmic system, the risk model algorithmic system
Input data is subjected to fusion treatment；
The scene drives risk analysis submodule：（1）Utilize real-time latitude and longitude coordinates, direction of traffic, instantaneous velocity
User is obtained in the travel speed by way of section, the average speed of vehicle where obtaining user using dynamic traffic data on track
Degree, by the travel speed of user compared with the vehicle average speed on the track of place, and is obtained by Traffic Information
System judges the driving scene residing for user, and synthetic user defines relative to the difference V-V of vehicle average speed on the track of place
Dependent variable, the risk a as caused by the difference under the scene；And the risk accumulation respectively by way of section is added after trip terminates
Act temporarily as driving risk A of this time trip based on relative velocity；（2）Utilize track where Traffic Net acquisition of information user
On speed limit L, if the difference of the speed limit L on the travel speed V of user and place track exceedes certain threshold value, judge
Hypervelocity behavior and hypervelocity behavior harmful grade, then the scene according to residing for judging Traffic Net information, is calculated corresponding super
Risk b caused by fast behavior harmful grade, and the risk accumulated weights at all moment are gone out as this after trip terminates
Driving risk B of the row based on hypervelocity behavior；（3）The brake of user is counted using real-time latitude and longitude coordinates and acceleration information
Train number number and acceleration and deceleration number, comprehensive vehicle position, direction of advance, dynamic traffic data determine the scene residing for user, meter
User is calculated to risk c existing for vehicle operating aspect, and this is used as to the risk accumulated weights at all moment after trip terminates
Secondary driving risk C of the trip based on acceleration and deceleration；
The driving model identification submodule of diverting one's attention, judges user in car using instantaneous velocity, acceleration and angular speed
The behavior of diverting one's attention of operating handset in motion state, and wind corresponding to species according to behavior of diverting one's attention and its time span accumulation
Assess D in danger；
Latitude and longitude coordinates that user's travel behaviour analysis submodule is gathered by the intelligent mobile terminal and
Instantaneous velocity, it is right according to the distance travelled of this trip of user, duration, path, anxious acceleration, anxious deceleration and zig zag information
This time trip and driving behavior of user is analyzed and gives corresponding risk assessment E；
The driving behavior Assessment for classification system submodule calculates the scene and drives risk analysis submodule, described respectively
Divert one's attention driving model identification submodule and user's travel behaviour analysis submodule final driving risk score value.
After user's accumulation reaches the driving risk score value of stipulated number and duration, according to the driving risk score value
Calculate the corresponding vehicle insurance price of the user.
It is an advantage of the invention that by the collection of multi-source data with merging, the driving behavior to user is analyzed, can be right
The travel behaviour of driver, custom of driving, driving risk are effectively demarcated, so as to be the vehicle insurance price based on driving behavior
Pattern is provided fundamental basis and technical support；The result of driving behavior analysis can also be presented to use on mobile terminal client terminal
Family so that the problem of in user cognition oneself driving behavior, and improved；On the whole, this technology can improve road network
Traffic safety, and reduce the various losses caused by traffic accident；Extensive popularization based on current smart mobile phone, this method tool
There is the advantages of cost is cheap, popularization is convenient, suitable continual analysis driving behavior, it is often more important that, the use of mobile terminal collection
Family track data can combine with Traffic Net information, dynamic traffic situation etc., so as to the feelings according to residing for user
Scape pattern, more accurately estimate driving behavior and its risk of driver；In addition, by collection with analyzing on intelligent mobile terminal
Data in the sensors such as accelerometer, gyroscope, it can be determined that driver whether carried out taking in startup procedure phone,
Receive and dispatch the behavior of diverting one's attention using mobile phone such as short message.
Brief description of the drawings
Fig. 1 is to calculate the method flow diagram for driving risk and aiding in vehicle insurance price in the present invention based on multi-source data；
Fig. 2 drives risk analysis schematic flow sheet for scene in the present invention；
Fig. 3 drives risk analysis schematic flow sheet to divert one's attention in the present invention；
Fig. 4 drives risk analysis case schematic diagram for analysis in the present invention；
Fig. 5 is the schematic diagram of driving behavior staging hierarchy in the present invention.
Embodiment
The feature of the present invention and other correlated characteristics are described in further detail by embodiment below in conjunction with accompanying drawing, with
It is easy to the understanding of technical staff of the same trade：
Embodiment：The present embodiment more particularly to it is a kind of based on multi-source data calculate drive risk with aid in vehicle insurance fix a price be
System and method, this method is the data based on intelligent mobile terminal data acquisition, with reference to Traffic Net information, dynamic traffic
The multi-source datas such as situation, by the travel behaviour of data mining analysis driver, the features such as custom of driving, and enter to driving risk
The effective quantitatively calibrating of row, so as to provide support for the vehicle insurance pricing model based on driving behavior.
As shown in figure 1, the system bag for driving risk and aiding in vehicle insurance price is calculated based on multi-source data in the present embodiment
The intelligent mobile terminal and remote server of interconnection are included, wherein：
Customized application that can be for users to use is installed, the customized application passes through some data sensors on intelligent mobile terminal
Collector, specially global location chip（GPS）, accelerometer and gyroscope, during being travelled for collection vehicle
The data such as real-time latitude and longitude coordinates, height above sea level, direction of traffic, positional precision, instantaneous velocity, acceleration and angular speed, these
Data will be uploaded in remote server by the customized application.
Data collecting system and risk model algorithmic system are installed on remote server, wherein,（1）Data acquisition system
Unite includes Traffic Net information, dynamic traffic data and comes from intelligent mobile terminal to apply upper input for acquisition
Data, and by these data inputs into risk model algorithmic system；（2）Risk model algorithmic system includes scene and drives risk
Analysis submodule, divert one's attention driving model identification submodule, user's travel behaviour analysis submodule and driving behavior Assessment for classification
System submodule, each submodule can obtain multi-source input data to carry out risk analysis from data collecting system, and be essence
Calculate insurance premium and theoretical foundation is provided.
As Figure 1-5, the method for driving risk with aiding in vehicle insurance price is calculated based on multi-source data in the present embodiment
Specifically comprise the following steps：
（1）As shown in figure 1, user first turns on the customized application being installed on intelligent mobile terminal, destination is inputted, and
Confirm that driving starts, the navigation information that user can be provided by customized application arrives at；
In user's driving procedure, intelligent mobile terminal can be global location chip (GPS), accelerometer, gyroscope institute
The data of collection at a certain time interval, are transmitted back to remote server and are stored and analyzed, and the data of collection are included in real time
Latitude and longitude coordinates, height above sea level, direction of traffic, positional precision, instantaneous velocity, acceleration and angular speed etc.；
（2）Data collecting system in remote server obtains and stores Traffic Net information and dynamically hand over automatically
Logical data, wherein, Traffic Net information mainly includes the tables such as road section, intersection position, section speed limit, category of roads
The attribute of transportation network essential characteristic is levied, and dynamic traffic data then includes each period（Generally it is with 5 minutes or 15 minutes
Interval）It is interior, traffic flow speed and traffic flow information on each bar road section；In addition, the data collecting system is also from intelligence
Mobile terminal includes real-time latitude and longitude coordinates, height above sea level, direction of traffic, positional precision, instantaneous velocity, acceleration using interior acquisition
The data such as degree and angular speed；
（3）Risk model algorithmic system in remote server obtains above-mentioned steps（1）、（2）In multi-source input data
Afterwards, the information that different types of data can be associated according to geographical position, timestamp etc., data link operation is carried out；Root
According to positional information, the user trajectory data gathered from intelligent mobile terminal can be with Traffic Net informational linkage to one
Rise, you can to judge which section user in some special time, is just travelled on；According to time and space attribute, can incite somebody to action
User is linked together with dynamic traffic situation, you can to judge on the section of user's traveling, traffic flow around it is flat
Equal speed and the degree of crowding；After data fusion completion, handed over from various user data and the road of intelligent mobile terminal collection
Open network information, dynamic traffic situation link together, and think that the driving behavior analysis module of system, including scene drive risk
Analysis submodule, driving model identification submodule of diverting one's attention, user's travel behaviour analysis submodule are provided and driven needed for Risk Calculation
The input data wanted；
（4）As shown in Fig. 2 what scene in risk model algorithmic system drove that risk analysis module refers to is exactly in multi-source number
After fusion, the Traffic Net information that is now in reference to user, dynamic traffic condition information, the feelings residing for user are judged
Scape pattern, and to the calculating that driving behavior of the user under various scenes and risk are carried out, it is specific as follows：
A. the difference based on relative velocity, which calculates, drives risk, i.e. utilizes real-time latitude and longitude coordinates, direction of traffic, wink
Shi Sudu obtains the user in the travel speed by way of section, the vehicle where obtaining user using dynamic traffic data on track
Average speed, by the travel speed of user compared with the vehicle average speed on the track of place, and by road network information and
Traffic judges the driving scene residing for the user, such as the expressway of congestion, and there are signal lamp, downstream road section congestion in front
Deng then synthetic user defines dependent variable relative to the difference v-V of traffic flow speed, as caused by the difference under the scene
Risk a；And after trip terminates to the risk accumulated weights in each section as this driving wind of the trip based on relative velocity
Dangerous A；
Generally, due to the presence for being with garage in traffic flow, the difference of both will not be very big；If the row of vehicle
Sail the lasting average speed apparently higher than wagon flow around of speed, model algorithm system can identify the driving behavior of driver compared with
More radical for ordinary people, passing behavior happens occasionally, it is meant that drives the presence of risk；And on the other hand, if vehicle
Travel speed it is lasting be significantly lower than average speed, then show that the driving behavior of this driver is more conservative, car with surrounding
Transport condition there is larger difference, can also produce certain driving risk；
B. calculated based on the drive speed of user with the comparison of the speed limit in track where it and drive risk, i.e. utilize road
Speed limit where the transportation network acquisition of information user of road on track, if the travel speed v and speed limit L of user difference exceedes
Certain threshold value, then judge hypervelocity behavior, and hypervelocity behavior harmful grade.Then according to residing for judging traffic and road network information
Scene, and calculate under the scene, risk and b caused by the hypervelocity behavior of corresponding harmful grade；It is and right after trip terminates
The risk accumulated weights at all moment are as this driving risk B based on hypervelocity behavior that goes on a journey；
In general, in the case that traffic is unimpeded, the speed of user also should not significantly exceed road
Road speed limit；If the system detects that the drive speed of user exceedes section speed limit for a long time, then user can be judged in this section
On hypervelocity behavior be present, it is higher so as to estimate the driving risk of user；In addition, on the section that speed limit is 50km/h（Such as city
Road）Exceed the speed limit 5km/h and in speed limit 110km/h section（Such as highway）Hypervelocity 5km/h risk effect is different；Together
Sample, in same section the rush hours（Peak period）The effect to be exceeded the speed limit when the risk of hypervelocity is relative to free flow speed also has difference；
By analyzing road speed limit, traffic flow conditions, it is possible to determine that the contextual model residing for user, and the drive speed of user is directed to,
Furious driving risk existing for calculating；
C. the acceleration and deceleration information based on user, which calculates, drives risk, i.e. will characterize plus-minus of the user to vehicle operating behavior
Fast information and number of bringing to a halt, with characterizing next intersection in the mean velocity information of traffic congestion degree, road network
Positional information, the vehicle operation behavior, the information such as real-time traffic condition that need to take at next crossing combine, with this
It is right in the driving behavior so as to quantitative demarcation user to judge driving environment residing for user, need the operation that carries out
Risk danger c existing in terms of vehicle operating, and the risk accumulated weights at all moment are gone on a journey as this after trip terminates
Driving risk C based on acceleration and deceleration；
In this submodule, more typical several scenes are：Cornering operation at crossing is more, and user travels shape to vehicle
Judgement, the correction done required for state are also more frequent, drive risk and also accordingly increase；When traffic flow congestion is more serious, Yong Huxu
Brake, the start-up operation to be taken is more frequent, in fact it could happen that the probability of traffic accident is also higher；It is more unimpeded in traffic conditions
In the case of, when apart from intersection sections of road farther out, the traveling shape of vehicle should not go out the preferable user of driving experience
Existing larger fluctuation, i.e., the behavior such as should not occur frequently touching on the brake, accelerate too much, and otherwise the driving behavior of user is more unstable
Calmly, the manipulation to vehicle is more unskilled.For above-mentioned scene, if these behaviors that user occurs are more, show that it drives row
It is also higher in risk existing for the operation link to vehicle in；
（5）As shown in Figure 3,4, the driving model identification submodule of diverting one's attention in model algorithm system utilizes instantaneous velocity, added
Speed and angular speed judge the behavior of diverting one's attention of operating handset of the user in state of motion of vehicle, and according to the kind for behavior of diverting one's attention
Class and its time span, and to driving behavior influence accumulation corresponding to risk assessment D；
During user and mobile phone interact, for different type of action, hardware data sensing acquisition device energy
Capture different types of data；For example the process that ear side receives calls is taken out and be put into mobile phone by user from pocket,
More obvious data fluctuations can be seen on hardware data sensing acquisition device, and receives calls and finishes, mobile phone is put back into pocket
When, again it can be seen that an obvious wave process；And short message is received and dispatched, webpage etc. is browsed and acts triggered hardware data sensing
Collector data fluctuations type is again more different compared with taking phone；Pass through the data to acceleration and mobile phone angle, application
Algorithm for pattern recognition, can be to amount of action of the user conducted in the startup procedure, beginning acted every time, the end time, dynamic
Make duration, type of action, influence degree of vehicle drive etc. is analyzed, and the foundation of risk is driven in this, as evaluation；
Three-axis sensor data on smart mobile phone, the i.e. x-axis of accelerometer, y-axis, x-axis, the y of z-axis data and gyroscope
Axle, z-axis data can respectively from different directions, the action that is carried out to user of different angle is described；In data acquisition with depositing
After storage, system can pre-process to these initial data, including application data sampling algorithm, i.e., complete from the data gathered
Concentrate and extract a part of sample progress subsequent analysis that may characterize user action, and application Denoising Algorithm carries out data and gone
Make an uproar, to reduce interference signal present in data acquisition to the influence for the movement recognition algorithm that will be carried out below；
Then, model algorithm system is using the feature occurred in an application feature extraction algorithm extraction data, including each characteristic point
At the time of, geographical position, and the shape of each indicatrix；Then, action is used based on the data characteristics extracted, system
Decision algorithm identify driver each using mobile phone act at the beginning of between and terminal node, i.e., the when span acted every time
Degree；
After the time span of each behavior is identified, system can be according to the data fluctuations detected on gyroscope
Situation, further this result is verified using user action verification algorithm；Algorithm first can be to being gathered in gyroscope
Data carry out sampling operation, and in the signal trifle that the every a pair action nodes identified are partitioned into, based on gyroscope
Data fluctuations calculate the characteristic parameters such as data capacity；Above parameter eventually be used to verify that previously deducing the user come moves
Make, i.e., the action authenticity in each signal trifle is examined；The result examined may finally characterize user and drive
During driving behavior of diverting one's attention, such as take phone, receive and dispatch short message, browse webpage, using mobile phone application etc. number, when
Grow, and influence to traveling state of vehicle etc.；Finally, it is in office with reference to the driving speed information in GPS movement locus, i.e. user
One moment, the instantaneous driving speed information in any geographical position, system can identify the car when these driving behaviors of diverting one's attention occur
Operation conditions, so as to extract vehicle in motion process, behavior of diverting one's attention that user is carried out and is calculated based on this and divert one's attention
Drive the analysis result of risk；
The analysis of cases to initial data and result of calculation involved by Fig. 3 is illustrated in figure 4, wherein, " acceleration counts
According to " chart and " gyro data " chart be respectively original that intelligent mobile terminal accelerometer x-axis is gathered with gyroscope x-axis
Beginning data, the transverse axis in figure represent that time, vertical pivot represent the data value that sensor collects；From the figure, it can be seen that the 250th
Second, 450 seconds, the time such as 1000 seconds or so, when user begins to use mobile phone, " accelerometer data " chart and " gyro
Corresponding signal fluctuation can all occur in instrument data " chart；
Through diverting one's attention to drive the processing of risk analysis submodule, i.e. Signal Pretreatment, denoising, feature extraction, action recognition, dynamic
The step such as verify, model algorithm system can extrapolate the driving " divert one's attention to drive to calculate result " as shown in chart in Fig. 4
Member uses the time section of mobile phone, and transverse axis be the time in figure, when vertical pivot is 0, represents that event occurs, when vertical pivot is equal to 1, table
Show that mobile phone is used in user；
The car that the description of " Vehicle Speed " chart collects from the global location chip on intelligent mobile terminal in Fig. 4
Travel speed, therefrom it can be seen that vehicle is sometimes in high-speed travel state, stationary condition is then in sometimes；According to traveling speed
Degree, " travel condition of vehicle " chart are further demarcated the travel conditions of vehicle with stationary condition；With reference to " vehicle is run
Vehicle running state described in state " chart, intelligence is used with the user described in " diverting one's attention to drive to calculate result " chart
The situation of energy mobile phone, system may finally weed out the user action that traveling state of vehicle is not influenceed under inactive state, only know
Do not go out divert one's attention driver behavior number, section and duration that vehicle user under transport condition is engaged in, and drive the cross is calculated with this
Risk in journey；
（6）The information such as logical the gathered position of user's travel behaviour analysis submodule, speed in model algorithm system, root
According to behaviors such as the mileage of this trip of user, time, path, anxious acceleration, anxious deceleration, zig zags, this trip to driver
Global analysis is carried out with driving behavior and gives corresponding risk assessment E；
In general, distance travelled is higher, the time that driver is exposed in traffic flow also can be longer, due to fatigue driving
Also accordingly increased etc. risk is driven caused by factor.One two hours driver on and off duty that drive daily, it drives risk phase
Compare one only weekend once in a while using vehicle people for it is significantly higher；And for the travel time, if driver is frequent
Gone on a journey after midnight, the factor such as physiological status of low visibility and driver based on road considers, the danger now driven
Highest when coefficient is usual；And peak period is gone on a journey, because road vehicle is more, space headway is shorter, wagon flow is stopped for a walk
Stop, it is also relatively large to drive risk；If selection the off-peak hours on daytime trip if, due to road vehicle quantity compared with
It is few, while visibility is higher, driving is typically safest；In addition, it is however generally that brake is stepped on more violent, or during automobile starting
Throttle is stepped on more ruthless, generally represents that the driving behavior of this driver is more radical with respect to for other people, so as to cause to brake
Shi Yuhou, which waits, to knock into the back, and the probability for the front truck that knocks into the back on startup is higher；
（7）As shown in figure 5, the driving behavior Assessment for classification system submodule of system, then can drive wind according to system scene
Danger analysis submodule, driving model identification submodule of diverting one's attention, the result of calculation of user's travel behaviour analysis submodule, items are referred to
Mark is weighted consideration, the overall risk of Comprehensive Assessment user's driving behavior；After the evaluation score unified metric of three submodules
It will be displayed on three coordinates, coordinate value states that the fraction that user obtains in this reference axis is lower, and it is driven closer to summit
Sailing danger is higher；The area that three coordinate lines mark off signifies the composite score of user's driving behavior, each module output
Risk is higher, corresponding scores are lower, the area finally marked off on the diagram is smaller, and the risk of its driving behavior is higher；
（8）Model algorithm system can store the trip driving behavior fraction of each user each time, and return result to
User is presented in the customized application of intelligent mobile terminal；For user's behavior more that may be present having much room for improvement, system
Some close friend's promptings can be provided the user with, with for reference；
（9）User can also authoring system, by the result of long-term driving behavior Comprehensive Assessment with cooperation insurance institution
Share, so as to which auxiliary calculates the vehicle insurance number that user should pay on this basis；When intelligent mobile end is used for multiple times in user
Trip is completed at end, and the driving behavior of system of users have accumulated enough data and be used as according to after, and system can be with cooperation
Insurance institution together, asked according to user, calculate based on user drive risk vehicle insurance price；In general, user's drives
Sail that behavior is safer, the premium paid required for it will be lower；If the system detects that dangerous driving behavior it is higher, user
The premium of required payment can also go up accordingly.
Claims (2)
1. a kind of calculate the method for driving risk with aiding in vehicle insurance price based on multi-source data, it is characterised in that methods described is related to
A kind of that the system for driving risk with aiding in vehicle insurance price is calculated based on multi-source data, the system includes can interactive communication
Intelligent mobile terminal and remote server；There are some data sensor collectors in the intelligent mobile terminal, and be provided with
Application for users to use；Risk model algorithmic system and the data acquisition of interactive communication are installed on the remote server
System, the risk model algorithmic system include scene and drive risk analysis submodule, driving model identification submodule of diverting one's attention, use
Family travel behaviour analysis submodule and driving behavior Assessment for classification system submodule；Wherein, the same institute of the intelligent mobile terminal
Data collecting system interactive communication is stated, the driving behavior Assessment for classification system submodule drives risk analysis with the scene
Module, divert one's attention driving model identification submodule and user's travel behaviour analysis submodule interactive communication；
Methods described comprises the following steps：
In user on the run, the global location chip in the intelligent mobile terminal, accelerometer and gyroscope will be real
When latitude and longitude coordinates, direction of traffic, instantaneous velocity, acceleration and angular speed be acquired and be sent to by the application
On the remote server；
The data collecting system obtains Traffic Net information, dynamic traffic data and comes from the intelligent sliding automatically
The input data of dynamic terminal applies, and send into the risk model algorithmic system, the risk model algorithmic system will be defeated
Enter data and carry out fusion treatment；
The scene drives risk analysis submodule：（1）Obtained using real-time latitude and longitude coordinates, direction of traffic, instantaneous velocity
User is in the travel speed by way of section, the vehicle average speed where obtaining user using dynamic traffic data on track, general
The travel speed of user obtains system by Traffic Information and sentenced compared with the vehicle average speed on the track of place
Driving scene residing for disconnected user, synthetic user define dependent variable relative to the difference V-V of vehicle average speed on the track of place,
Risk a as caused by the difference under the scene；And to respectively by way of the risk accumulated weights conduct in section after trip terminates
Driving risk A of this time trip based on relative velocity；（2）Utilize the limit on track where Traffic Net acquisition of information user
Fast value L, if the travel speed V of user and the speed limit L on the track of place difference exceed certain threshold value, judge hypervelocity row
For and hypervelocity behavior harmful grade, then the scene according to residing for judging Traffic Net information, calculates corresponding hypervelocity behavior
Risk b caused by harmful grade, and the risk accumulated weights at all moment are based on as this trip after trip terminates
The driving risk B of hypervelocity behavior；（3）The brake number of user is counted using real-time latitude and longitude coordinates and acceleration information
And acceleration and deceleration number, comprehensive vehicle position, direction of advance, dynamic traffic data determine the scene residing for user, calculate user
To risk c existing for vehicle operating aspect, and the risk accumulated weights at all moment are gone on a journey as this after trip terminates
Driving risk C based on acceleration and deceleration；
The driving model identification submodule of diverting one's attention, judges that user transports in vehicle using instantaneous velocity, acceleration and angular speed
The behavior of diverting one's attention of the intelligent mobile terminal in dynamic state, and accumulated and corresponded to according to the species and its time span of behavior of diverting one's attention
Risk assessment D；
Latitude and longitude coordinates that user's travel behaviour analysis submodule is gathered by the intelligent mobile terminal and instantaneous
Speed, according to the distance travelled of this trip of user, duration, path, anxious acceleration, anxious deceleration and zig zag information, to user
This time trip and driving behavior analyzed and give corresponding risk assessment E；
The driving behavior Assessment for classification system submodule calculates the scene and drives risk analysis submodule, described diverts one's attention respectively
Driving model identifies the final driving risk score value of submodule and user's travel behaviour analysis submodule.
2. a kind of calculated based on multi-source data according to claim 1 drives risk with aiding in the method that vehicle insurance is fixed a price, its
It is characterised by after user's accumulation reaches the driving risk score value of stipulated number and duration, according to the driving risk score value
Calculate the corresponding vehicle insurance price of the user.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510904331.2A CN105374211B (en) | 2015-12-09 | 2015-12-09 | The system and method for driving risk and aiding in vehicle insurance price is calculated based on multi-source data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510904331.2A CN105374211B (en) | 2015-12-09 | 2015-12-09 | The system and method for driving risk and aiding in vehicle insurance price is calculated based on multi-source data |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105374211A CN105374211A (en) | 2016-03-02 |
| CN105374211B true CN105374211B (en) | 2018-01-05 |
Family
ID=55376362
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510904331.2A Expired - Fee Related CN105374211B (en) | 2015-12-09 | 2015-12-09 | The system and method for driving risk and aiding in vehicle insurance price is calculated based on multi-source data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105374211B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US11820385B2 (en) * | 2020-07-31 | 2023-11-21 | GM Global Technology Operations LLC | System and method for evaluating driver performance |
Families Citing this family (53)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106022928A (en) * | 2016-05-25 | 2016-10-12 | 财付通支付科技有限公司 | Data processing method and device |
| CN106022846A (en) * | 2016-06-17 | 2016-10-12 | 深圳市慧动创想科技有限公司 | Automobile insurance pricing method, second-hand automobile pricing method and corresponding devices |
| JP6849705B2 (en) * | 2016-06-24 | 2021-03-24 | スイス リインシュランス カンパニー リミテッド | Autonomous or partially autonomous vehicles, including automated risk control systems, and corresponding methods |
| CN105930943A (en) * | 2016-07-11 | 2016-09-07 | 上海安吉星信息服务有限公司 | Method and device for predicting driving risk |
| CN106297283A (en) * | 2016-08-11 | 2017-01-04 | 深圳市元征科技股份有限公司 | Safe driving appraisal procedure based on vehicle intelligent unit and system |
| WO2018028799A1 (en) * | 2016-08-12 | 2018-02-15 | Swiss Reinsurance Company Ltd. | Telematics system with vehicle-embedded telematics devices (oem line fitted) for score-driven, automated insurance and corresponding method |
| CN106530094A (en) * | 2016-08-31 | 2017-03-22 | 江苏鸿信系统集成有限公司 | Vehicle insurance assessment system and assessment method |
| CN106412021B (en) * | 2016-08-31 | 2019-08-30 | 杭州好好开车科技有限公司 | Three urgent thing parts determine the method uploaded with data under a kind of solution flow restriction |
| WO2018046102A1 (en) * | 2016-09-10 | 2018-03-15 | Swiss Reinsurance Company Ltd. | Automated, telematics-based system with score-driven triggering and operation of automated sharing economy risk-transfer systems and corresponding method thereof |
| CN106447139A (en) * | 2016-12-06 | 2017-02-22 | 北京中交兴路信息科技有限公司 | Actuarial method and device based on vehicle driving behaviors |
| CN106780254A (en) * | 2016-12-07 | 2017-05-31 | 东软集团股份有限公司 | Traffic safety analysis method and terminal device |
| CN106789481B (en) * | 2017-01-19 | 2020-11-13 | 深圳国科极光科技有限公司 | Data visualization integral monitoring system for smart home |
| CN107180219A (en) * | 2017-01-25 | 2017-09-19 | 问众智能信息科技（北京）有限公司 | Driving dangerousness coefficient appraisal procedure and device based on multi-modal information |
| CN107169869A (en) * | 2017-04-06 | 2017-09-15 | 平安科技（深圳）有限公司 | Information processing method and information processor |
| JP7092116B2 (en) * | 2017-04-14 | 2022-06-28 | ソニーグループ株式会社 | Information processing equipment, information processing methods, and programs |
| CN107368202B (en) * | 2017-07-13 | 2020-08-28 | 东软集团股份有限公司 | Method and device for recognizing behavior of driver using mobile phone and computing equipment |
| CN109285075B (en) * | 2017-07-19 | 2022-03-01 | 腾讯科技（深圳）有限公司 | Claims risk assessment method and device and server |
| WO2019048034A1 (en) * | 2017-09-06 | 2019-03-14 | Swiss Reinsurance Company Ltd. | Electronic logging and track identification system for mobile telematics devices, and corresponding method thereof |
| CN107657537A (en) * | 2017-09-14 | 2018-02-02 | 青岛车盟信息技术服务有限公司 | UBI collecting vehicle informations analysis system and car owner's classification and premium discount method |
| CN109754595B (en) * | 2017-11-01 | 2022-02-01 | 阿里巴巴集团控股有限公司 | Vehicle risk assessment method and device and interface equipment |
| CN107908742A (en) * | 2017-11-15 | 2018-04-13 | 百度在线网络技术（北京）有限公司 | Method and apparatus for output information |
| CN108256766A (en) * | 2018-01-17 | 2018-07-06 | 合肥工业大学 | A kind of car insurance accounting method based on dangerous driving behavior |
| CN108280415A (en) * | 2018-01-17 | 2018-07-13 | 武汉理工大学 | Driving behavior recognition methods based on intelligent mobile terminal |
| CN108320232A (en) * | 2018-02-02 | 2018-07-24 | 斑马网络技术有限公司 | Insurance coverage of driving a vehicle generates system and method |
| CN108765020A (en) * | 2018-02-07 | 2018-11-06 | 上海小娜汽车技术有限公司 | A kind of UBI pricing systems for full dose vehicle of being networked based on preceding entrucking |
| CN110389577B (en) * | 2018-04-17 | 2022-04-01 | 北京三快在线科技有限公司 | Method and device for determining driving style |
| EP3567565A1 (en) * | 2018-05-09 | 2019-11-13 | Volkswagen AG | Apparatus, method, computer program, base station and vehicle for providing information related to an approaching vehicle |
| CN108711204B (en) * | 2018-05-18 | 2020-07-31 | 长安大学 | Driving abnormity detection system and method integrating human-vehicle-road multi-source information |
| CN108985947A (en) * | 2018-06-19 | 2018-12-11 | 上海博泰悦臻电子设备制造有限公司 | Car insurance fee payment method and system based on car accident probability of happening |
| CN109061706A (en) * | 2018-07-17 | 2018-12-21 | 江苏新通达电子科技股份有限公司 | A method of the vehicle drive behavioural analysis based on T-Box and real-time road map datum |
| CN109118055B (en) * | 2018-07-19 | 2021-12-21 | 众安信息技术服务有限公司 | Driving behavior scoring method and device |
| CN109214289B (en) * | 2018-08-02 | 2021-10-22 | 厦门瑞为信息技术有限公司 | Method for recognizing two-stage calling behavior from whole to local |
| CN109447127A (en) * | 2018-09-29 | 2019-03-08 | 深圳市元征科技股份有限公司 | Data processing method and device |
| CN109325705A (en) * | 2018-10-11 | 2019-02-12 | 北京三驰惯性科技股份有限公司 | A kind of driving habit methods of marking and system based on inertia integration technology |
| CN109606373B (en) * | 2018-11-29 | 2020-06-30 | 哈尔滨工业大学 | Visibility-considered driving task demand evaluation method |
| CN109829601B (en) * | 2018-12-07 | 2021-03-23 | 深圳大学 | Method and system for predicting risk behavior of driver driving vehicle |
| CN109671275B (en) * | 2019-02-14 | 2020-11-24 | 成都路行通信息技术有限公司 | Method for acquiring vehicle and traffic state |
| CN110276953A (en) * | 2019-06-28 | 2019-09-24 | 青岛无车承运服务中心有限公司 | Rule-breaking vehicle travel risk analysis method based on BEI-DOU position system |
| CN110239560A (en) * | 2019-07-08 | 2019-09-17 | 瞬联软件科技（北京）有限公司 | A kind of safe driving habits methods of marking and device |
| CN110490752A (en) * | 2019-08-21 | 2019-11-22 | 福州大学 | Car insurance analysis and automatic recommendation service system and its working method based on driving behavior data |
| CN110555733A (en) * | 2019-09-02 | 2019-12-10 | 上海评驾科技有限公司 | method for identifying travel driving of user based on smart phone |
| CN110727706A (en) * | 2019-09-02 | 2020-01-24 | 清华大学苏州汽车研究院（相城） | Method for rapidly extracting and grading risk driving scene for intelligent networking automobile test |
| JP7263997B2 (en) * | 2019-09-20 | 2023-04-25 | トヨタ自動車株式会社 | DRIVING ACTION EVALUATION DEVICE, METHOD AND PROGRAM |
| CN110648532B (en) * | 2019-09-22 | 2020-08-18 | 江苏顺泰交通集团有限公司 | Traffic monitoring system based on wisdom traffic thing networking |
| CN110517522B (en) * | 2019-09-30 | 2022-03-15 | 重庆元韩汽车技术设计研究院有限公司 | Vehicle speed limiting system and method for remote control |
| CN112351419A (en) * | 2020-06-02 | 2021-02-09 | 北京车与车科技有限公司 | Vehicle insurance method based on non-hardware equipment paying according to actual application |
| CN112070617A (en) * | 2020-07-29 | 2020-12-11 | 中软国际科技服务有限公司 | Method for realizing flexible pricing of vehicle insurance service |
| CN113379945A (en) * | 2021-07-26 | 2021-09-10 | 陕西天行健车联网信息技术有限公司 | Vehicle driving behavior analysis device, method and system |
| CN113763044B (en) * | 2021-09-03 | 2023-11-07 | 北京交通大学 | High-speed railway dynamic pricing method based on passenger travel behavior analysis |
| CN114136331A (en) * | 2021-11-23 | 2022-03-04 | 常熟理工学院 | Driving habit evaluation method and system based on micro-electromechanical gyroscope and detection equipment |
| CN114379559B (en) * | 2021-12-30 | 2024-01-26 | 武汉理工大学 | Driving risk evaluation feature portrait method based on vehicle information acquisition system |
| CN115169996B (en) * | 2022-09-06 | 2022-12-13 | 天津所托瑞安汽车科技有限公司 | Road risk determination method, apparatus and storage medium |
| CN117094830B (en) * | 2023-10-20 | 2024-03-26 | 国任财产保险股份有限公司 | Artificial intelligent insurance full-chain application method and system |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103150675B (en) * | 2013-01-30 | 2016-04-27 | 郁佳敏 | The risk monitoring system of car insurance |
| KR20150024472A (en) * | 2013-08-26 | 2015-03-09 | 김광석 | System for calculating car insuarance fee and method thereof |
| TWI493511B (en) * | 2013-09-04 | 2015-07-21 | Ind Tech Res Inst | Method and system for detecting conditions of drivers, and electronic apparatus thereof |
| CN104318477A (en) * | 2014-11-11 | 2015-01-28 | 西红柿科技（武汉）有限公司 | Vehicle insurance evaluation method based on big data |
-
2015
- 2015-12-09 CN CN201510904331.2A patent/CN105374211B/en not_active Expired - Fee Related
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US11820385B2 (en) * | 2020-07-31 | 2023-11-21 | GM Global Technology Operations LLC | System and method for evaluating driver performance |
Also Published As
| Publication number | Publication date |
|---|---|
| CN105374211A (en) | 2016-03-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105374211B (en) | The system and method for driving risk and aiding in vehicle insurance price is calculated based on multi-source data | |
| US11069159B1 (en) | Driving trip and pattern analysis | |
| CN111247565B (en) | Electronic logging and tracking detection system for mobile telematics devices and corresponding method thereof | |
| US10163275B1 (en) | Driving trip and pattern analysis | |
| CN107784587B (en) | Driving behavior evaluation system | |
| US10023200B2 (en) | Driver profiling system and method | |
| US10540723B1 (en) | Methods of providing insurance savings based upon telematics and usage-based insurance | |
| CN108256714A (en) | A kind of wheelpath real-time risk assessment model based on car networking big data | |
| CN107784251A (en) | The method evaluated based on image recognition technology driving behavior | |
| CN109416873A (en) | The autonomous motor vehicles in autonomous or part and its correlation method with automation risk control system | |
| CN107257756A (en) | Technology for aiding in vehicle in the case of road condition change | |
| CN102878998A (en) | Vehicle fueling prompting method based on path programming | |
| CN107240264B (en) | A kind of non-effective driving trace recognition methods of vehicle and urban road facility planing method | |
| CN108848460A (en) | People's vehicle correlating method based on RFID and GPS data | |
| CN109816977A (en) | A kind of integrative design intersection evaluation system of data-driven | |
| CN101958043A (en) | Highway section calculation element hourage and method thereof | |
| CN101964941A (en) | Intelligent navigation and position service system and method based on dynamic information | |
| CN106022846A (en) | Automobile insurance pricing method, second-hand automobile pricing method and corresponding devices | |
| CN205038808U (en) | Position monitored control system | |
| CN105096590B (en) | Traffic information creating method and traffic information generating device | |
| CN103366560A (en) | Vehicle-following detection method, system and application for road traffic state | |
| CN109278758A (en) | A kind of intelligent vehicle personalized driving learning system based on smart phone | |
| CN109410576A (en) | Road condition analyzing method, apparatus, storage medium and the system of multisource data fusion | |
| CN113928333B (en) | Energy consumption reduction method and system based on auxiliary driving | |
| CN111222898B (en) | Method for counting network taxi and computer readable storage medium |
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 | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20180105 Termination date: 20181209 |
|
| CF01 | Termination of patent right due to non-payment of annual fee |