CN109670970A - A kind of driving behavior methods of marking, device and computer readable storage medium - Google Patents
A kind of driving behavior methods of marking, device and computer readable storage medium Download PDFInfo
- Publication number
- CN109670970A CN109670970A CN201811433626.6A CN201811433626A CN109670970A CN 109670970 A CN109670970 A CN 109670970A CN 201811433626 A CN201811433626 A CN 201811433626A CN 109670970 A CN109670970 A CN 109670970A
- Authority
- CN
- China
- Prior art keywords
- driving
- sample
- driver
- data
- scoring
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 104
- 238000003860 storage Methods 0.000 title claims abstract description 18
- 238000009825 accumulation Methods 0.000 claims abstract description 33
- 230000008569 process Effects 0.000 claims abstract description 30
- 230000001186 cumulative effect Effects 0.000 claims abstract description 26
- 238000009826 distribution Methods 0.000 claims description 10
- 239000000284 extract Substances 0.000 claims description 9
- 238000013507 mapping Methods 0.000 claims description 9
- 238000004590 computer program Methods 0.000 claims description 8
- 238000005315 distribution function Methods 0.000 claims description 8
- 241000208340 Araliaceae Species 0.000 claims description 2
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 claims description 2
- 235000003140 Panax quinquefolius Nutrition 0.000 claims description 2
- 235000008434 ginseng Nutrition 0.000 claims description 2
- 238000005516 engineering process Methods 0.000 abstract description 4
- 238000004458 analytical method Methods 0.000 abstract description 2
- 230000003542 behavioural effect Effects 0.000 abstract description 2
- 230000006399 behavior Effects 0.000 description 107
- 238000004422 calculation algorithm Methods 0.000 description 10
- 238000010586 diagram Methods 0.000 description 8
- 238000012545 processing Methods 0.000 description 7
- 230000001133 acceleration Effects 0.000 description 6
- 238000004364 calculation method Methods 0.000 description 5
- 238000012986 modification Methods 0.000 description 5
- 230000004048 modification Effects 0.000 description 5
- 238000012549 training Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 3
- 241001269238 Data Species 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 238000013135 deep learning Methods 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 230000013016 learning Effects 0.000 description 2
- 238000010801 machine learning Methods 0.000 description 2
- 230000006855 networking Effects 0.000 description 2
- 238000010606 normalization Methods 0.000 description 2
- 206010039203 Road traffic accident Diseases 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000012512 characterization method Methods 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 238000003066 decision tree Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 231100001261 hazardous Toxicity 0.000 description 1
- 238000012417 linear regression Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000007637 random forest analysis Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000013077 scoring method Methods 0.000 description 1
- 238000005406 washing Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/08—Insurance
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
Landscapes
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Development Economics (AREA)
- Economics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Marketing (AREA)
- Finance (AREA)
- Accounting & Taxation (AREA)
- Educational Administration (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Game Theory and Decision Science (AREA)
- Quality & Reliability (AREA)
- Operations Research (AREA)
- Technology Law (AREA)
- Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)
- Control Of Driving Devices And Active Controlling Of Vehicle (AREA)
Abstract
The invention discloses a kind of driving behavior methods of marking, device and computer readable storage mediums, belong to vehicle drive behavioral analysis technology field.Method includes: accumulation sample data, driving data and insurance policy data including sample driver；Determine current generation of the sample data in cumulative process, wherein cumulative process includes other stages after cold-start phase and cold-start phase；It is scored using corresponding driving methods of marking of current accumulation stage the driving behavior of current driver's.The embodiment of the present invention, which can be realized the different phase in data accumulation, can carry out driving behavior scoring.
Description
Technical field
The present invention relates to vehicle drive behavioral analysis technology field more particularly to a kind of driving behavior methods of marking, device
And computer readable storage medium.
Background technique
In recent years, the quantity of motor vehicles is more and more, while as car networking develops rapidly, in conjunction with car networking technology
The vehicle insurance product fixed a price based on driver's driving behavior it is also more and more.
UBI (Usage Based Insurance) vehicle insurance, which refers to, uses data price based on driving behavior and vehicle
Car insurance is the novel vehicle insurance occurred under the background of vehicle insurance rate liberalization.Insurance company is by collecting driving behavior number
Accordingly and vehicle operation data by Data Analysis Services assesses the driving behavior risk class of driver.It goes for driving
Car owner preferably, insurance company can give more preferential, bad for driving behavior car owner, and insurance company can be correspondingly
Improve premium.Facilitate car owner as a result, and cultivate good driving behavior, reduces accident, reduction is in danger and settles a claim, to change
Kind traffic condition, reduces social cost.
Therefore, for insurance company, firstly the need of the driving number based on driver before being fixed a price for vehicle insurance product
It is at present usually that driving behavior is obtained using the method for supervised learning in machine learning according to the assessment for making driving behavior risk
With the relationship between risk that drives, training sample needs while using data and the number of settling a claim that is in danger comprising driving behavior and vehicle
According to.Acquire driving behavior and vehicle and use data, usually by vehicle-mounted OBD (On-Board Diagnostic) equipment or
The equipment such as smart phone, obtaining vehicle operation data by the sensor in equipment can also be by taking the photograph if equipment is attached to camera
As head obtains traveling video to obtain embodying the further data of driving habit.As the accurate measurement of degree of risk, need
Know whether the driver being observed occurs traffic accident in the same period that driving behavior is observed, and to insurance company
The case where claim, using the rate of being in danger or loss ratio as the characterization of driving risk.After obtaining both of the above, driving data is made
For the feature in supervision algorithm, as the supervisory signals in supervision algorithm, supervision algorithm is based on training number for rate of being in danger or loss ratio
According to obtaining the relationship of feature and supervisory signals, that is, driving data and be in danger rate, the relationship of Claims Resolution rate.It is driven for needing to judge
The target sample of behaviorist risk, that is, the driver of only driving data are sailed, the deduction relationship obtained by supervision algorithm obtains
Obtain its driving behavior risk.
The method of this kind of supervised learnings needs to accumulate a large amount of driving data and data of settling a claim of being in danger as a result, and goes out
The danger Claims Resolution period needs consistent with driving data collection period, settles a claim data or data are not achieved centainly if be not in danger
Quantity, algorithm are just difficult to start.And in actual operation, at the beginning of system operation, the often more convenient acquisition of driving data,
But being in danger will not usually occur with Claims Resolution at once, so the number of settling a claim that is in danger can not just be obtained while acquiring driving data
According to, at the same with drive stroke and data accumulation, even if being in danger, due to Claims Resolution process comprising survey, setting loss, maintenance,
Multiple steps such as Claims Resolution, need certain time, are in danger and the acquisition for data of settling a claim is likely present the delay of a period of time, into
And supervision algorithm is made also to be difficult to start.
Summary of the invention
The purpose of the embodiment of the present invention is that providing a kind of driving behavior methods of marking, device and computer-readable storage medium
Matter accurately drives target driver by using different driving methods of marking in the different phase of data accumulation
Sail behavior scoring prediction.The specific technical solution of the embodiment of the present invention is as follows:
In a first aspect, the embodiment of the invention provides a kind of driving behavior methods of marking, which comprises
Accumulate sample data, driving data and insurance policy data including sample driver；
Determine current generation of the sample data in cumulative process, wherein the cumulative process includes cold start-up rank
Other stages after section and the cold-start phase；
It is scored using current accumulation stage corresponding driving methods of marking the driving behavior of current driver's.
In some embodiments, other described stages include initial stage, mid-term stage and later stage；
The sample data when cold-start phase does not include the insurance policy data of sample driver；
The sample data when initial stage includes that the driving data of multiple sample drivers and minimal amount of insurance are protected
Forms data；
The sample data when mid-term stage includes that driving data and the part sample of multiple sample drivers is driven
The insurance policy data for the person of sailing；
The sample data when later stage includes the driving data and corresponding insurance policy of multiple sample drivers
Data.
In some embodiments, it is described to use the current accumulation rank when current generation is the cold-start phase
The corresponding driving methods of marking of section carries out scoring to the driving behavior of current driver's
The driving data of the current driver's is obtained, and extracts a variety of driving characteristics of the current driver's；
Several dimensions are divided into a variety of driving characteristics, each dimension includes several driving characteristics；
According to default standards of grading, the scoring of the various driving characteristics is obtained；
The scoring of the various driving characteristics in each dimension is weighted, each dimension is obtained
Scoring；
The scoring of each dimension is weighted, the driving behavior scoring of the current driver's is obtained.
In some embodiments, it is described to use the current accumulation stage when current generation is the initial stage
Corresponding driving methods of marking carries out scoring to the driving behavior of current driver's
The a variety of samples for extracting each sample driver respectively from the driving data of each sample driver drive
Feature；
According to a variety of sample driving characteristics of each sample driver, the distribution of the various sample driving characteristics is calculated
Parameter；
The driving data of the current driver's is obtained, and extracts a variety of driving characteristics of the current driver's；
According to the distribution parameter of the various sample driving characteristics, calculates separately the various of the current driver's and described drive
The cumulative distribution function for sailing feature, using as the corresponding scoring of the various driving characteristics；
The scoring of the various driving characteristics is weighted, the driving behavior for obtaining the current driver's is commented
Point.
In some embodiments, it is described to use the current accumulation stage when current generation is the mid-term stage
Corresponding driving methods of marking carries out scoring to the driving behavior of current driver's
It is obtained each described for the part sample driver according to the insurance policy data of each sample driver
The driving of sample driver is scored；
Clustering is carried out the driving data of the part sample driver, obtains multiple cluster centres, every a kind of work
It for a risk class cluster, and is scored according to the driving of the part sample driver, calculates the driving of each risk class cluster
Scoring；
Obtain the driving data of the current driver's, and calculate the driving datas of the current driver's with it is the multiple
The similarity distance of cluster centre；
According to the calculated result of similarity distance, risk class cluster corresponding to the current driver's is determined, and will be true
The driving scoring for the risk class cluster made is scored as the driving of the current driver's.
In some embodiments, it is described to use the current accumulation stage when current generation is the later stage
Corresponding driving methods of marking carries out scoring to the driving behavior of current driver's
For the multiple sample driver, each sample is extracted respectively from the driving data of each sample driver
A variety of driving characteristics of this driver, and according to the insurance policy data of each sample driver, it obtains each sample and drives
The driving for the person of sailing is scored；
It is scored according to the driving of the driving characteristics of each sample driver and each sample driver, establishes and drive row
For Rating Model；
It is scored using the driving behavior Rating Model the driving behavior of current driver's.
In some embodiments, the insurance policy data according to each sample driver obtain each sample
The driving of driver is scored
For the insurance policy data of each sample driver, following operation is executed:
The numerical value of settling a claim that is in danger is obtained from the insurance policy data；
According to default mapping table, determining and described driving scoring of the numerical value with mapping relations of settling a claim that be in danger, to make
It scores for the driving of the sample driver.
Second aspect, the embodiment of the present invention provide a kind of driving behavior scoring apparatus, and described device includes:
Accumulate module, for accumulating sample data, driving data and insurance policy data including sample driver；
Determining module, for determining current generation of the sample data in cumulative process, wherein the cumulative process
Including other stages after cold-start phase and the cold-start phase；
Grading module, for using the corresponding driving for driving methods of marking to current driver's of the current accumulation stage
Behavior is scored.
The third aspect, the embodiment of the present invention provide a kind of driving behavior scoring apparatus, comprising:
One or more processors；
Storage device, for storing one or more programs；
When one or more of programs are executed by one or more of processors, so that one or more of processing
Device realizes driving behavior methods of marking as described in relation to the first aspect.
Fourth aspect, the embodiment of the present invention provide a kind of computer readable storage medium, are stored thereon with computer program,
Driving behavior methods of marking as described in relation to the first aspect is realized when described program is executed by processor.
Driving behavior methods of marking, device and computer readable storage medium provided in an embodiment of the present invention, pass through accumulation
Sample data, and determine current generation of the sample data in cumulative process, and use the corresponding driving of current accumulation stage
Methods of marking scores to the driving behavior of current driver's.It is driven it is possible thereby to be just capable of providing at the beginning of driving data acquisition
Behavior scoring is sailed, and with the accumulation of driving data and the addition for data of settling a claim, gradually Optimal Parameters and model, thus real
The different phase of present data accumulation can carry out the assessment of driving behavior risk.
Detailed description of the invention
To describe the technical solutions in the embodiments of the present invention more clearly, make required in being described below to embodiment
Attached drawing is briefly described, it should be apparent that, drawings in the following description are only some embodiments of the invention, for
For those of ordinary skill in the art, without creative efforts, it can also be obtained according to these attached drawings other
Attached drawing.
Fig. 1 shows the flow chart of driving behavior methods of marking according to an embodiment of the invention；
Fig. 2 shows the block diagrams of driving behavior scoring apparatus according to another embodiment of the present invention.
Specific embodiment
To make the object, technical solutions and advantages of the present invention clearer, below in conjunction with attached in the embodiment of the present invention
Figure, technical scheme in the embodiment of the invention is clearly and completely described, it is clear that described embodiment is only this
Invention a part of the embodiment, instead of all the embodiments.Based on the embodiments of the present invention, those of ordinary skill in the art exist
Every other embodiment obtained under the premise of creative work is not made, shall fall within the protection scope of the present invention.
Driving behavior methods of marking provided in an embodiment of the present invention, this method can lead in the different phase of data accumulation
It crosses and driving behavior score in predicting is accurately carried out to target driver using different driving behavior methods of marking, the driving behavior
The executing subject of methods of marking can be server, wherein server can pass through network and the shifting equipped with mobile SDK module
Dynamic terminal and vehicle-mounted depth camera head module are communicatively coupled, and server can also pass through preset interface and insurance policy system
It is docked, to obtain the insurance policy data of driver；Wherein, server can be individual server, be also possible to by more
The server zone of a server composition, and in the server zone, it can communicate connection between multiple servers；Wherein, it takes
The mobile terminal for being loaded with mobile SDK module is the mobile terminal of driver, can collect driver by mobile SDK module
Driving behavior data be uploaded to server, vehicle-mounted depth camera head module is mounted on the vehicle of driver, can will be acquired
To driving video data be uploaded to server.
Fig. 1 shows the flow chart of driving behavior methods of marking according to an embodiment of the invention, shown referring to Fig.1, should
Driving behavior methods of marking may include step:
S1, accumulation sample data, driving data and insurance policy data including sample driver.
Wherein, the driving data of sample driver may include driving behavior data, driving environment data and driving video
At least one of data.
Wherein it is possible to obtain the driving behavior data of sample driver by mobile SDK module.Driving behavior data can be with
Various essential informations when being vehicle driving may include driving time information, mileage information, velocity information, direction information, warp
Latitude information, altitude information, mobile phone communication status information, anxious acceleration information, anxious deceleration and zig zag information etc..
In the specific implementation process, it can be driven by the mobile SDK module in the mobile terminal of sample driver in sample
GPS, accelerometer and gyroscope sensor data are acquired in the driving procedure for the person of sailing, to obtain the driving behavior of sample driver
Data, and the driving behavior data of sample driver are uploaded onto the server, the driving behavior by server to sample driver
The identity of data and sample driver carry out binding storage.
Wherein it is possible to obtain the driving environment data of sample driver by preset interface.Driving environment data can be
Various environmental informations relevant to driving behavior in locating environment are driven, may include section speed limit, driving region, road class
Type, orographic condition, driving current weather condition etc..After obtaining the driving environment data of sample driver by preset interface,
Driving environment data are uploaded onto the server, by server to the driving environment data of sample driver and the body of sample driver
Part mark carries out binding storage.
Wherein it is possible to obtain driving video data by vehicle-mounted camera.Driving video data are that camera is collected
Video during driving may include ranging information, lane information, traffic information, driving event etc..When vehicle-mounted camera acquires
To after driving video data, driving video data are uploaded onto the server, by server to the driving video number of sample driver
Binding storage is carried out according to the identity with sample driver.
Wherein it is possible to obtain the insurance policy data of sample driver by preset interface.Insurance policy data can be
Various information relevant to the insurance policy of driver may include the essential information, declaration form purchase information and declaration form of driver
Settle a claim odd number, declaration form Claims Resolution volume etc., wherein declaration form buy information including insuring kind, the information such as amount of insuring.
In the specific implementation process, server can be docked by preset interface with insurance policy system, according to sample
The identity of this driver gets insurance policy corresponding with the identity of sample driver from business declaration form system
Data.
It should be noted that above-mentioned driver identity mark can be the cell-phone number of driver, user name, identity card or
Other are capable of the information of unique identification driver identity.
S2, current generation of the sample data in cumulative process is determined, wherein cumulative process includes cold-start phase and cold
Other stages after startup stage.
Wherein, other stages include initial stage, mid-term stage and later stage.Sample data when cold-start phase is not
Insurance policy data including sample driver；Sample data when initial stage includes the driving data of multiple sample drivers
With minimal amount of insurance policy data；Sample data when mid-term stage includes driving data and the part of multiple sample drivers
The insurance policy data of sample driver；Sample data when later stage includes the driving data of multiple sample drivers and right
The insurance policy data answered.
S3, it is scored using corresponding driving methods of marking of current accumulation stage the driving behavior of current driver's.
Wherein, different phase carries out driving behavior scoring using different driving methods of marking.
Driving behavior methods of marking provided in an embodiment of the present invention by accumulating sample data, and determines that sample data exists
Current generation in cumulative process, and use the corresponding driving for driving methods of marking to current driver's of current accumulation stage
Behavior is scored.It is possible thereby to just be capable of providing driving behavior scoring at the beginning of driving data acquisition, and with driving number
According to accumulation and data of settling a claim addition, gradually Optimal Parameters and model, to realize that the different phase in data accumulation is equal
It can carry out the assessment of driving behavior risk.
In one embodiment of the invention, the cold-start phase in the cumulative process that the current generation is sample data
When, the driving data of sample driver just starts to accumulate, and there is no the insurance policy data of sample driver, and base can be used
Driving behavior scoring is carried out to current driver's in the driving methods of marking of rule and default weight.Specifically, above mentioned step S3
It is middle to be scored using corresponding driving methods of marking of current accumulation stage the driving behavior of current driver's, it may include step
It is rapid:
S311, the driving data for obtaining current driver's, and extract a variety of driving characteristics of current driver's.
Wherein, the driving data of current driver's may include driving behavior data, driving environment data and driving video
At least one of data.
Specifically, driving behavior data are obtained by mobile SDK module, and it includes every for extracting from driving behavior data
Duan Hangcheng or the driving range of unit interval drive duration, maximum drive speed, anxious acceleration times, anxious deceleration number, urgency
Number of turns, sudden turn of events road number, whether fatigue driving, whether dangerous periods driving at least one driving behavior.
Driving environment data are obtained by preset interface, and extracting from driving environment data includes every section of stroke or list
Whether whether the hypervelocity number and duration of position period are in hazardous environment, are in and are familiar with section, have in bad weather
At least one driving environment feature.
Driving video data are obtained by vehicle-mounted camera, extraction includes apart from speed ratio, is from driving video data
It is no follow lane, front event occur when whether slow down at least one driving video feature.
S312, a variety of driving characteristics are divided into several dimensions, each dimension includes several driving characteristics.
Specifically, a variety of driving characteristics of extraction are divided into several dimensions, such as speed, mileage, time, environment, driving
Behavior etc., each dimension include several features.For example, " speed " this dimension may include the relevant several features of speed: super
Fast number, hypervelocity duration, highest drive speed etc., " driving behavior " this dimension includes several spies relevant to driver behavior
Sign: anxious acceleration times, anxious deceleration number, zig zag number, sudden turn of events road number, apart from speed ratio, whether follow lane, front thing
Whether part slows down when occurring.
S313, basis preset standards of grading, obtain the scoring of various driving characteristics.
Specifically, be set separately standards of grading to various driving characteristics, the corresponding standards of grading of various driving characteristics can be with
Different set is done as the case may be.
Illustratively, the standards of grading of this driving characteristics of number of exceeding the speed limit can be with are as follows:
Exceed the speed limit number score=100-10/ driving range of hypervelocity number *, and removing boundary is 0, indicates average every kilometer of hypervelocity 1
It is secondary, 10 points are reduced, average every kilometer of hypervelocity number >=10, which is scored at 0.
S314, the scoring of the various driving characteristics in each dimension is weighted, obtains the scoring of each dimension.
Specifically, the various features scoring in each dimension is added according to the feature weight set to various driving characteristics
Power summation obtains the scoring of each dimension, wherein the sum of feature weight in each dimension is 1.
Dimension scoring calculation formula are as follows: dimension scoring=∑ feature scoring * feature weight.
S315, the scoring of each dimension is weighted, obtains the driving behavior scoring of current driver's.
Specifically, obtaining each drive to the scoring weighted sum of each dimension according to the dimensionality weight to each dimension set
The driving behavior for the person of sailing is scored, wherein the sum of each dimensionality weight is 1.
Driving behavior scoring calculation formula are as follows: driving behavior scoring=∑ dimension scoring * dimensionality weight.
In the embodiment of the present invention, when the current generation is cold-start phase, the driving data of sample driver just starts
Accumulation, there is no the insurance policy data of sample driver, by using the corresponding driving methods of marking of cold-start phase to working as
Preceding driver carries out driving behavior scoring, be able to solve in the prior art due to system initial operating stage sample data accumulate it is insufficient and
It is difficult to start supervision algorithm, and then leads to not the problem of carrying out driving behavior scoring.
In one embodiment of the invention, the current generation be sample data cumulative process in initial stage when,
The driving data of a certain amount of sample driver is had accumulated, the insurance policy data of sample driver still do not have seldom or almost
Have, it is integrally relatively low with driver's driving data degree of association, the driving methods of marking pair based on feature distribution function can be used
Current driver's carry out driving behavior scoring.Specifically, being scored in above mentioned step S3 using the corresponding driving of current accumulation stage
Method scores to the driving behavior of current driver's, may include step:
S321, a variety of samples for extracting each sample driver respectively from the driving data of each sample driver drive special
Sign.
Specifically, the process can refer to step S311, will not be repeated here herein.
S322, a variety of sample driving characteristics according to each sample driver calculate the distribution ginseng of various sample driving characteristics
Number.
Specifically, assuming that sample driving characteristics obey certain distribution, the sample of all sample drivers can be driven
Feature is summarized, and is cleaned to data are summarized, including carries out necessary rejecting outliers, data normalization, based on clear
Data after washing are fitted to obtain the parameter of the distribution function of sample driving characteristics obedience, and so on, it obtains other samples and drives
Sail the distribution parameter of feature.
Illustratively, if a certain sample driving characteristics, such as: average every kilometer of anxious acceleration times x obeys exponential distribution,
Cumulative distribution function is as follows, wherein λacc> 0,
The driving characteristics of all sample drivers are summarized, necessary rejecting outliers, data normalization is carried out, is based on
Data after cleaning are fitted to obtain this feature, that is, the parameter of distribution function that average every kilometer of anxious acceleration times are obeyed
λacc。
S323, the driving data for obtaining current driver's, and extract a variety of driving characteristics of current driver's.
Specifically, the process can refer to step S311, will not be repeated here herein.
S324, according to the distribution parameter of various sample driving characteristics, calculate separately the various driving characteristics of current driver's
Cumulative distribution function, using as the corresponding scoring of various driving characteristics.
Illustratively, for a certain driving characteristics of current driver's, such as: average every kilometer of anxious acceleration times xobj,
Parameter lambda according to the exponential distribution that the driving characteristics are obeyedaccObtain the cumulative distribution function value of the driving characteristicsIn this, as the corresponding scoring of the driving characteristics.
S325, the scoring of various driving characteristics is weighted, obtains the driving behavior scoring of current driver's.
In the embodiment of the present invention, when the current generation is initial stage, the driving of a certain amount of sample driver is had accumulated
Data, the insurance policy data of sample driver are still seldom or almost without whole with driver's driving data degree of association
It is relatively low, driving behavior scoring, energy can be carried out to current driver's by using the corresponding driving methods of marking of initial stage
It is enough to solve to be difficult to start supervision algorithm since system initial operating stage sample data accumulates insufficient in the prior art, and then lead to nothing
Method carries out the problem of driving behavior scoring.
In one embodiment of the invention, the current generation be sample data cumulative process in mid-term stage when,
The driving data of a certain amount of sample driver and the insurance policy data of part sample driver are had accumulated, can be used and be based on
The driving methods of marking of clustering carries out driving behavior scoring to current driver's.Specifically, use is worked as in above mentioned step S3
Preceding accumulation stage, corresponding driving methods of marking scored to the driving behavior of current driver's, can specifically include step:
S331, it is directed to part sample driver, according to the insurance policy data of each sample driver, obtains each sample and drive
The driving scoring of member.
Specifically, being directed to the insurance policy data of each sample driver, following operation is executed:
The numerical value of settling a claim that is in danger is obtained from insurance policy data, according to default mapping table, is determined and the number of settling a claim that is in danger
Being worth, there is the driving of mapping relations to score, using the driving scoring as sample driver；Wherein, in default mapping table,
The more high corresponding driving behavior scoring of Claims Resolution rate is lower.
Wherein, the numerical value of settling a claim of being in danger can be and extract sample driver's from the insurance policy data of sample driver
Rate of being in danger or loss ratio are commented according to the rate of being in danger or Claims Resolution rate by the driving behavior that preset mapping table obtains sample driver
Point, using the scoring label as sample driver.Wherein, in mapping table, the more high corresponding driving behavior of Claims Resolution rate is commented
Point lower, illustratively, fraction range can be 0~100.
S332, clustering is carried out to the driving data of part sample driver, obtains multiple cluster centres, every a kind of work
It for a risk class cluster, and is scored according to the driving of part sample driver, calculates the driving scoring of each risk class cluster.
Wherein it is possible to carry out clustering, every one kind using driving data of the K-means algorithm to part sample driver
As a risk class cluster, a cluster centre is obtained, it is believed that the driver in same category has same or similar
Risk level, using the average value of the driving scoring of the sample driver in same category as the category (i.e. the risk class cluster)
Driving scoring.
S333, obtain current driver's driving data, and calculate current driver's driving data and multiple clusters in
The similarity distance of the heart.
Specifically, the embodiment of the present invention is not limited specific calculating process.
S334, according to the calculated result of similarity distance, determine risk class cluster corresponding to current driver's, and will be true
The driving scoring for the risk class cluster made is scored as the driving of current driver's.
Specifically, using the corresponding risk class cluster of the minimum value in the calculated result of similarity distance as current driver's
Corresponding risk class cluster.
In the embodiment of the present invention, the current generation be sample data cumulative process in mid-term stage when, have accumulated one
The driving data of quantitative sample driver and the insurance policy data of part sample driver, can be by using mid-term stage
Corresponding driving methods of marking carries out driving behavior scoring to current driver's, is able to solve in the prior art since system is run
The accumulation of initial stage sample data is insufficient and is difficult to start supervision algorithm, and then leads to not the problem of carrying out driving behavior scoring.
In one embodiment of the invention, when the current generation is later stage, sample driver driving data and reason
Compensation data are more complete, the scoring of driver's driving data and Claims Resolution data correlation than more complete, after can be used based on training
The driving methods of marking of model carries out driving behavior scoring to current driver's.Work as foreset specifically, using in above mentioned step S3
Tired stage corresponding driving methods of marking scores to the driving behavior of current driver's, can specifically include step:
S341, multiple sample drivers are directed to, extract each sample respectively from the driving data of each sample driver and drives
A variety of driving characteristics of member, and according to the insurance policy data of each sample driver, obtain the driving scoring of each sample driver.
Specifically, extracting a variety of of each sample driver respectively from the driving data of each sample driver in the step
The process of driving characteristics is identical as step S311, and details are not described herein again.
In the step, according to the insurance policy data of each sample driver, the driving scoring of each sample driver is obtained
Process is identical as step S331, and details are not described herein again.
S342, it is scored according to the driving characteristics of each sample driver and the driving of each sample driver, establishes driving behavior
Rating Model.
Specifically, the driving scoring of driving characteristics and each sample driver to each sample driver, passes through conventional machines
Study or deep learning method establish driving behavior Rating Model, and driving behavior Rating Model is carried out offline storage, with
For being called when online driving behavior scoring.
Wherein it is possible to establish driving behavior scoring mould using the methods of linear regression, random forest, decision tree, xgboost
Type, the present invention are not limited this.
S343, it is scored using driving behavior Rating Model the driving behavior of current driver's.
Specifically, extracting the driving characteristics of current driver's from the driving data of current driver's；By current driver's
Driving characteristics be input in driving behavior Rating Model, the driving behavior for obtaining current driver's is scored and is exported.
In the embodiment of the present invention, the current generation be sample data cumulative process in later stage when, due to sample
Driver's driving data and Claims Resolution data are more complete, driver's driving data with data correlation of settling a claim than more complete, therefore can
To obtain driving Rating Model using machine learning or deep learning training, and then driving behavior is carried out to current driver's and is commented
Point.
Fig. 2 shows the block diagrams of driving behavior scoring apparatus according to another embodiment of the present invention.The embodiment of the present invention mentions
The driving behavior scoring apparatus of confession is used to execute the driving behavior methods of marking in above-described embodiment, referring to shown in Fig. 2, the device
Include:
Accumulate module 21, for accumulating sample data, driving data and insurance policy data including sample driver；
Determining module 22, for determining current generation of the sample data in cumulative process, wherein cumulative process includes cold
Other stages after startup stage and cold-start phase；
Grading module 23, for using the corresponding methods of marking that drives of current accumulation stage to the driving row of current driver's
To score.
Driving behavior scoring apparatus provided in this embodiment, with driving behavior methods of marking provided by the embodiment of the present invention
Belong to same inventive concept, driving behavior methods of marking provided by any embodiment of the invention can be performed, have and execute driving
The corresponding functional module of behavior scoring method and beneficial effect.The not technical detail of detailed description in the present embodiment, reference can be made to
Driving behavior methods of marking provided in an embodiment of the present invention, is not repeated here herein.
In addition, another embodiment of the present invention additionally provides a kind of driving behavior scoring apparatus, comprising:
One or more processors；
Storage device, for storing one or more programs；
When one or more of programs are executed by one or more of processors, so that one or more of processing
Device realizes the driving behavior methods of marking as described in above-described embodiment.
In addition, another embodiment of the present invention additionally provides a kind of computer readable storage medium, it is stored thereon with computer
Program realizes the driving behavior methods of marking as described in above-described embodiment when described program is executed by processor.
It should be understood by those skilled in the art that, the embodiment in the embodiment of the present invention can provide as method, system or meter
Calculation machine program product.Therefore, complete hardware embodiment, complete software embodiment can be used in the embodiment of the present invention or combine soft
The form of the embodiment of part and hardware aspect.Moreover, being can be used in the embodiment of the present invention in one or more wherein includes meter
Computer-usable storage medium (including but not limited to magnetic disk storage, CD-ROM, the optical memory of calculation machine usable program code
Deng) on the form of computer program product implemented.
It is referring to the method for middle embodiment, equipment (system) according to embodiments of the present invention and to calculate in the embodiment of the present invention
The flowchart and/or the block diagram of machine program product describes.It should be understood that can be realized by computer program instructions flow chart and/or
The combination of the process and/or box in each flow and/or block and flowchart and/or the block diagram in block diagram.It can mention
For the processing of these computer program instructions to general purpose computer, special purpose computer, Embedded Processor or other programmable datas
The processor of equipment is to generate a machine, so that being executed by computer or the processor of other programmable data processing devices
Instruction generation refer to for realizing in one or more flows of the flowchart and/or one or more blocks of the block diagram
The device of fixed function.
These computer program instructions, which may also be stored in, is able to guide computer or other programmable data processing devices with spy
Determine in the computer-readable memory that mode works, so that it includes referring to that instruction stored in the computer readable memory, which generates,
Enable the manufacture of device, the command device realize in one box of one or more flows of the flowchart and/or block diagram or
The function of being specified in multiple boxes.
These computer program instructions also can be loaded onto a computer or other programmable data processing device, so that counting
Series of operation steps are executed on calculation machine or other programmable devices to generate computer implemented processing, thus in computer or
The instruction executed on other programmable devices is provided for realizing in one or more flows of the flowchart and/or block diagram one
The step of function of being specified in a box or multiple boxes.
Although the preferred embodiment in the embodiment of the present invention has been described, once a person skilled in the art knows
Basic creative concept, then additional changes and modifications may be made to these embodiments.So appended claims are intended to explain
Being includes preferred embodiment and all change and modification for falling into range in the embodiment of the present invention.
Obviously, various changes and modifications can be made to the invention without departing from essence of the invention by those skilled in the art
Mind and range.In this way, if these modifications and changes of the present invention belongs to the range of the claims in the present invention and its equivalent technologies
Within, then the present invention is also intended to include these modifications and variations.
Claims (10)
1. a kind of driving behavior methods of marking, which is characterized in that the method includes the steps:
Accumulate sample data, driving data and insurance policy data including sample driver；
Determine current generation of the sample data in cumulative process, wherein the cumulative process include cold-start phase and
Other stages after the cold-start phase；
It is scored using current accumulation stage corresponding driving methods of marking the driving behavior of current driver's.
2. the method according to claim 1, wherein other described stages include initial stage, mid-term stage and
Later stage；
The sample data when cold-start phase does not include the insurance policy data of sample driver；
The sample data when initial stage includes the driving data and minimal amount of insurance policy number of multiple sample drivers
According to；
The sample data when mid-term stage includes driving data and the part sample driver of multiple sample drivers
Insurance policy data；
The sample data when later stage include multiple sample drivers driving data and corresponding insurance policy data.
3. according to the method described in claim 2, it is characterized in that, the current generation be the cold-start phase when, it is described
Carrying out scoring to the driving behavior of current driver's using current accumulation stage corresponding driving methods of marking includes:
The driving data of the current driver's is obtained, and extracts a variety of driving characteristics of the current driver's；
Several dimensions are divided into a variety of driving characteristics, each dimension includes several driving characteristics；
According to default standards of grading, the scoring of the various driving characteristics is obtained；
The scoring of the various driving characteristics in each dimension is weighted, commenting for each dimension is obtained
Point；
The scoring of each dimension is weighted, the driving behavior scoring of the current driver's is obtained.
4. according to the method described in claim 2, it is characterized in that, the current generation be the initial stage when, it is described to make
Carrying out scoring to the driving behavior of current driver's with current accumulation stage corresponding driving methods of marking includes:
Extract a variety of sample driving characteristics of each sample driver respectively from the driving data of each sample driver；
According to a variety of sample driving characteristics of each sample driver, the distribution ginseng of the various sample driving characteristics is calculated
Number；
The driving data of the current driver's is obtained, and extracts a variety of driving characteristics of the current driver's；
According to the distribution parameter of the various sample driving characteristics, the various driving for calculating separately the current driver's are special
The cumulative distribution function of sign, using as the corresponding scoring of the various driving characteristics；
The scoring of the various driving characteristics is weighted, the driving behavior scoring of the current driver's is obtained.
5. according to the method described in claim 2, it is characterized in that, the current generation be the mid-term stage when, it is described to make
Carrying out scoring to the driving behavior of current driver's with current accumulation stage corresponding driving methods of marking includes:
Each sample is obtained according to the insurance policy data of each sample driver for the part sample driver
The driving of driver is scored；
Clustering is carried out the driving data of the part sample driver, obtains multiple cluster centres, it is every a kind of as one
A risk class cluster, and scored according to the driving of the part sample driver, calculate the driving scoring of each risk class cluster；
Obtain the driving data of the current driver's, and calculate the current driver's driving data and the multiple cluster
The similarity distance at center；
According to the calculated result of similarity distance, risk class cluster corresponding to the current driver's is determined, and will determine
The risk class cluster driving scoring as the current driver's driving scoring.
6. according to the method described in claim 2, it is characterized in that, the current generation is the later stage, the use
Current accumulation stage corresponding driving methods of marking carries out scoring to the driving behavior of current driver's
For the multiple sample driver, each sample is extracted respectively from the driving data of each sample driver and is driven
The a variety of driving characteristics for the person of sailing, and according to the insurance policy data of each sample driver, obtain each sample driver
Driving scoring；
It is scored according to the driving of the driving characteristics of each sample driver and each sample driver, establishes driving behavior and comment
Sub-model；
It is scored using the driving behavior Rating Model the driving behavior of current driver's.
7. method according to claim 5 or 6, which is characterized in that described to be protected according to the insurance of each sample driver
Forms data, the driving scoring for obtaining each sample driver include:
For the insurance policy data of each sample driver, following operation is executed:
The numerical value of settling a claim that is in danger is obtained from the insurance policy data；
It is determining to score with the numerical value of settling a claim of being in danger with the driving of mapping relations according to default mapping table, using as institute
State the driving scoring of sample driver.
8. a kind of driving behavior scoring apparatus, which is characterized in that described device is for executing such as claim 1~7 any one
The driving behavior methods of marking, described device include:
Accumulate module, for accumulating sample data, driving data and insurance policy data including sample driver；
Determining module, for determining current generation of the sample data in cumulative process, wherein the cumulative process includes
Other stages after cold-start phase and the cold-start phase；
Grading module, for using the corresponding driving behavior for driving methods of marking to current driver's of the current accumulation stage
It scores.
9. a kind of driving behavior scoring apparatus characterized by comprising
One or more processors；
Storage device, for storing one or more programs；
When one or more of programs are executed by one or more of processors, so that one or more of processors are real
The now driving behavior methods of marking as described in claim 1~7 any one.
10. a kind of computer readable storage medium, is stored thereon with computer program, which is characterized in that described program is processed
The driving behavior methods of marking as described in claim 1~7 any one is realized when device executes.
Priority Applications (4)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811433626.6A CN109670970B (en) | 2018-11-28 | 2018-11-28 | Driving behavior scoring method and device and computer readable storage medium |
| PCT/CN2019/095164 WO2020107894A1 (en) | 2018-11-28 | 2019-07-09 | Driving behavior scoring method and device and computer-readable storage medium |
| SG11202005593WA SG11202005593WA (en) | 2018-11-28 | 2019-07-09 | Driving behavior scoring method, device and computer readable storage medium |
| JP2019554753A JP6918137B2 (en) | 2018-11-28 | 2019-07-09 | Driving behavior evaluation method, device and computer-readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811433626.6A CN109670970B (en) | 2018-11-28 | 2018-11-28 | Driving behavior scoring method and device and computer readable storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109670970A true CN109670970A (en) | 2019-04-23 |
| CN109670970B CN109670970B (en) | 2020-12-22 |
Family
ID=66143248
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811433626.6A Active CN109670970B (en) | 2018-11-28 | 2018-11-28 | Driving behavior scoring method and device and computer readable storage medium |
Country Status (4)
| Country | Link |
|---|---|
| JP (1) | JP6918137B2 (en) |
| CN (1) | CN109670970B (en) |
| SG (1) | SG11202005593WA (en) |
| WO (1) | WO2020107894A1 (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2020107894A1 (en) * | 2018-11-28 | 2020-06-04 | 众安信息技术服务有限公司 | Driving behavior scoring method and device and computer-readable storage medium |
| CN112749721A (en) * | 2019-10-31 | 2021-05-04 | 彩虹无线（北京）新技术有限公司 | Driving risk evaluation model training method and device |
| CN112937591A (en) * | 2019-12-11 | 2021-06-11 | 彩虹无线（北京）新技术有限公司 | Driving safety monitoring method, device, equipment and computer readable storage medium |
| CN113119981A (en) * | 2021-04-09 | 2021-07-16 | 东风汽车集团股份有限公司 | Vehicle active safety control method, system and storage medium |
| CN113635915A (en) * | 2021-08-24 | 2021-11-12 | 中国人民解放军陆军装甲兵学院 | Vehicle driving early warning method and device, electronic equipment and storage medium |
| CN114407904A (en) * | 2022-02-11 | 2022-04-29 | 西北工业大学 | Method, device and system for monitoring aggressive driving behavior of driver |
| CN116821805A (en) * | 2023-06-28 | 2023-09-29 | 运脉云技术有限公司 | Vehicle service platform system for monitoring driving behavior and driving behavior monitoring method |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113298361A (en) * | 2021-05-06 | 2021-08-24 | 深圳市锐明技术股份有限公司 | Dangerous driving behavior evaluation method and device, electronic equipment and system |
| CN115953858A (en) * | 2022-11-29 | 2023-04-11 | 摩尔线程智能科技(北京)有限责任公司 | Vehicle-mounted DMS-based driving scoring method and device and electronic equipment |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106651133A (en) * | 2016-11-18 | 2017-05-10 | 杭州好好开车科技有限公司 | User driving behavior scoring method based on ADAS realized through using mobile phone |
| CN106815312A (en) * | 2016-12-21 | 2017-06-09 | 东软集团股份有限公司 | A kind of driver's evaluation method and device |
| CN107038860A (en) * | 2016-11-18 | 2017-08-11 | 杭州好好开车科技有限公司 | A kind of user's driving behavior methods of marking based on ADAS technologies and regression model |
| CN107203945A (en) * | 2017-06-12 | 2017-09-26 | 清华大学苏州汽车研究院（吴江） | Vehicle insurance grading evaluation method and device |
| CN107784251A (en) * | 2016-08-25 | 2018-03-09 | 大连楼兰科技股份有限公司 | The method evaluated based on image recognition technology driving behavior |
| CN107784587A (en) * | 2016-08-25 | 2018-03-09 | 大连楼兰科技股份有限公司 | A kind of driving behavior evaluation system |
Family Cites Families (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP4978747B2 (en) * | 2011-11-16 | 2012-07-18 | 日産自動車株式会社 | Vehicle driving support device and vehicle driving support method |
| CN106127586A (en) * | 2016-06-17 | 2016-11-16 | 上海经达信息科技股份有限公司 | Vehicle insurance rate aid decision-making system under big data age |
| CN107845039A (en) * | 2016-09-20 | 2018-03-27 | 得道车联网络科技（上海）有限公司 | A kind of adaptive car networking vehicle insurance Rating Model of scale free |
| JP7074069B2 (en) * | 2016-12-22 | 2022-05-24 | ソニーグループ株式会社 | Information processing equipment and methods, and programs |
| JP7156268B2 (en) * | 2017-03-29 | 2022-10-19 | ソニーグループ株式会社 | Information processing device, information processing system, information processing method, and program |
| CN107203943A (en) * | 2017-04-06 | 2017-09-26 | 北京保程保险公估有限公司 | Motor vehicle business insurance pricing system |
| CN108492053A (en) * | 2018-04-11 | 2018-09-04 | 北京汽车研究总院有限公司 | The training of driver's risk evaluation model, methods of risk assessment and device |
| CN109670970B (en) * | 2018-11-28 | 2020-12-22 | 众安信息技术服务有限公司 | Driving behavior scoring method and device and computer readable storage medium |
-
2018
- 2018-11-28 CN CN201811433626.6A patent/CN109670970B/en active Active
-
2019
- 2019-07-09 JP JP2019554753A patent/JP6918137B2/en active Active
- 2019-07-09 WO PCT/CN2019/095164 patent/WO2020107894A1/en active Application Filing
- 2019-07-09 SG SG11202005593WA patent/SG11202005593WA/en unknown
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107784251A (en) * | 2016-08-25 | 2018-03-09 | 大连楼兰科技股份有限公司 | The method evaluated based on image recognition technology driving behavior |
| CN107784587A (en) * | 2016-08-25 | 2018-03-09 | 大连楼兰科技股份有限公司 | A kind of driving behavior evaluation system |
| CN106651133A (en) * | 2016-11-18 | 2017-05-10 | 杭州好好开车科技有限公司 | User driving behavior scoring method based on ADAS realized through using mobile phone |
| CN107038860A (en) * | 2016-11-18 | 2017-08-11 | 杭州好好开车科技有限公司 | A kind of user's driving behavior methods of marking based on ADAS technologies and regression model |
| CN106815312A (en) * | 2016-12-21 | 2017-06-09 | 东软集团股份有限公司 | A kind of driver's evaluation method and device |
| CN107203945A (en) * | 2017-06-12 | 2017-09-26 | 清华大学苏州汽车研究院（吴江） | Vehicle insurance grading evaluation method and device |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2020107894A1 (en) * | 2018-11-28 | 2020-06-04 | 众安信息技术服务有限公司 | Driving behavior scoring method and device and computer-readable storage medium |
| CN112749721A (en) * | 2019-10-31 | 2021-05-04 | 彩虹无线（北京）新技术有限公司 | Driving risk evaluation model training method and device |
| CN112937591A (en) * | 2019-12-11 | 2021-06-11 | 彩虹无线（北京）新技术有限公司 | Driving safety monitoring method, device, equipment and computer readable storage medium |
| CN112937591B (en) * | 2019-12-11 | 2023-04-07 | 彩虹无线（北京）新技术有限公司 | Driving safety monitoring method, device, equipment and computer readable storage medium |
| CN113119981A (en) * | 2021-04-09 | 2021-07-16 | 东风汽车集团股份有限公司 | Vehicle active safety control method, system and storage medium |
| CN113635915A (en) * | 2021-08-24 | 2021-11-12 | 中国人民解放军陆军装甲兵学院 | Vehicle driving early warning method and device, electronic equipment and storage medium |
| CN113635915B (en) * | 2021-08-24 | 2023-01-06 | 中国人民解放军陆军装甲兵学院 | Vehicle driving early warning method and device, electronic equipment and storage medium |
| CN114407904A (en) * | 2022-02-11 | 2022-04-29 | 西北工业大学 | Method, device and system for monitoring aggressive driving behavior of driver |
| CN116821805A (en) * | 2023-06-28 | 2023-09-29 | 运脉云技术有限公司 | Vehicle service platform system for monitoring driving behavior and driving behavior monitoring method |
Also Published As
| Publication number | Publication date |
|---|---|
| JP6918137B2 (en) | 2021-08-11 |
| WO2020107894A1 (en) | 2020-06-04 |
| JP2021509978A (en) | 2021-04-08 |
| CN109670970B (en) | 2020-12-22 |
| SG11202005593WA (en) | 2020-07-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109670970A (en) | A kind of driving behavior methods of marking, device and computer readable storage medium | |
| CN109118055B (en) | Driving behavior scoring method and device | |
| CN106934876B (en) | A kind of recognition methods and system of vehicle abnormality driving event | |
| CN111062240B (en) | Monitoring method and device for automobile driving safety, computer equipment and storage medium | |
| CN104599545B (en) | For the driving states monitoring method in driving conditions, device and navigation equipment | |
| CN107784597B (en) | Travel mode identification method and device, terminal equipment and storage medium | |
| EP3578433A1 (en) | Method for estimating an accident risk of an autonomous vehicle | |
| CN107807625B (en) | End-to-end-based automatic driving system comfort evaluation method and device | |
| CN110447214A (en) | A kind of system, method, apparatus and storage medium identifying driving behavior | |
| CN108446824A (en) | A kind of methods of risk assessment of driving behavior, device, equipment and storage medium | |
| CN111860561A (en) | Method, device, equipment and storage medium for identifying abnormal stopping behavior of network appointment vehicle | |
| US10990837B1 (en) | Systems and methods for utilizing machine learning and feature selection to classify driving behavior | |
| CN110766937B (en) | Parking spot identification method and device, electronic equipment and readable storage medium | |
| CN110705774A (en) | Vehicle energy consumption analysis prediction method and system | |
| CN110001653A (en) | A kind of driving behavior appraisal procedure, server and computer-readable medium | |
| CN107292663A (en) | Vehicle insurance pricing method and device | |
| CN110263836B (en) | Bad driving state identification method based on multi-feature convolutional neural network | |
| Kar et al. | Scotto: Real-time driver behavior scoring using in-vehicle data | |
| CN116453345B (en) | Bus driving safety early warning method and system based on driving risk feedback | |
| CN106651133B (en) | Method for achieving user driving behavior scoring based on ADAS by using mobile phone | |
| CN116796158A (en) | Method and system for collecting intelligent evaluation data of vehicle and vehicle | |
| CN115027497B (en) | Target vehicle cut-in intention prediction method and readable storage medium | |
| CN115841712A (en) | Driving data processing method, device and equipment based on V2X technology | |
| CN112989194B (en) | Recommendation method and system integrating user request and service preference of Internet of vehicles | |
| EP4264436A1 (en) | Generating unknown-unsafe scenarios, improving automated vehicles, computer system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| REG | Reference to a national code |
Ref country code: HK Ref legal event code: DE Ref document number: 40003621 Country of ref document: HK |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20240306 Address after: Room 1179, W Zone, 11th Floor, Building 1, No. 158 Shuanglian Road, Qingpu District, Shanghai, 201702 Patentee after: Shanghai Zhongan Information Technology Service Co.,Ltd. Country or region after: China Address before: 518000 Room 201, building A, No. 1, Qian Wan Road, Qianhai Shenzhen Hong Kong cooperation zone, Shenzhen, Guangdong (Shenzhen Qianhai business secretary Co., Ltd.) Patentee before: ZHONGAN INFORMATION TECHNOLOGY SERVICE Co.,Ltd. Country or region before: China |
|
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20240415 Address after: Room 1179, W Zone, 11th Floor, Building 1, No. 158 Shuanglian Road, Qingpu District, Shanghai, 201702 Patentee after: Shanghai Zhongan Information Technology Service Co.,Ltd. Country or region after: China Address before: 518000 Room 201, building A, No. 1, Qian Wan Road, Qianhai Shenzhen Hong Kong cooperation zone, Shenzhen, Guangdong (Shenzhen Qianhai business secretary Co., Ltd.) Patentee before: ZHONGAN INFORMATION TECHNOLOGY SERVICE Co.,Ltd. Country or region before: China |