CN107203945A - Vehicle insurance grading evaluation method and device - Google Patents
Vehicle insurance grading evaluation method and device Download PDFInfo
- Publication number
- CN107203945A CN107203945A CN201710437233.1A CN201710437233A CN107203945A CN 107203945 A CN107203945 A CN 107203945A CN 201710437233 A CN201710437233 A CN 201710437233A CN 107203945 A CN107203945 A CN 107203945A
- Authority
- CN
- China
- Prior art keywords
- risk
- msub
- information
- feature
- mrow
- 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.)
- Pending
Links
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
Landscapes
- Business, Economics & Management (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Engineering & Computer Science (AREA)
- Development Economics (AREA)
- Economics (AREA)
- Marketing (AREA)
- Strategic Management (AREA)
- Technology Law (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)
Abstract
The present invention relates to a kind of vehicle insurance grading evaluation method and device, belong to intelligent automobile technical field.This method carries out feature of risk extraction first, obtains driver, drives the feature of risk of vehicle, the feature of risk of 8 dimension description driver's driving behaviors later in conjunction with mounted remote information definition;Feature of risk and the mathematical modeling whether being in danger then are set up by logistic regression, model parameter estimated by maximum likelihood method using historical data, after model parameter is obtained, the value-at-risk threshold value of different risk stratification groups is determined;Finally, for user to be assessed, its feature of risk and value-at-risk are calculated, risk class division is carried out according to risk class tablet.The present invention can be effectively combined drivers information, driving information of vehicles and driving behavior and vehicle risk grade is divided, and overall process is without manually participating in and independent of personal experience, and method is directly perceived effective, easy to use.
Description
Technical field
The present embodiments relate to intelligent automobile technical field, more particularly to a kind of vehicle insurance grading evaluation method and device.
Background technology
Insurance premium determine be insurance business core link.In vehicle insurance business, by weighing policy information i.e.:Insure
People and its information of vehicles, estimate vehicle insurance expense.It is relatively simple that the expense of traditional vehicle insurance determines logic, general according to static
Data, the main attribute related including the driver attribute related to vehicle is classified, and risk is carried out by fixed formula
Assess.However, the larger limitation of the presence of these static natures, first, most static nature is voluntarily converged by insurer
Insurance company is offered, such as the personal information and average annual driving range of insurer, the data that these are voluntarily reported are not necessarily
It is real, objective and accurate;Secondly as the particularity of domestic insurance market, it may appear that insurer, car owner and
The situation of the not necessarily same people of actual driver.Determine if only premium is carried out according to the feature of a wherein people, may
Error can be caused.
With the development of wireless communication technique, GPS technology and computer technology, based on vehicle insurance (the Usage Based used
Insurance, hereinafter referred to as UBI) arise at the historic moment.UBI be otherwise known as with drive pay (Pay-As-YouDrive, PAYD) or
With how driving paying (Pay-How-You-Drive, PHYD).The distance travelled pair based on driver is referred to driving to pay
Vehicle insurance is fixed a price, and refers to that the driving behavior based on driver is fixed a price to vehicle insurance with how to drive to pay.UBI core
It is that the use data of vehicle are determined to premium based on objective reality, and these are otherwise known as using data in UBI
Mounted remote information, including global positioning system (GPS) data and in-car sensing data etc..
UBI is beneficial for insurance company, driver and entire society.For insurance company, pass through
UBI can accurately formulate premium for individual, effectively improve the efficiency and benefit of insurance company.Secondly, come for driver
Say, the driver of low-risk can be reduced by premium and obtain interests economically.Driven simultaneously as premium has directly been reacted
Sailing danger, the dynamic purpose that reduction premium is reached by improving their driving behavior of driver.Finally, UBI pairs is promoted
Entire society improve traffic, reduce traffic accident, reduce traffic emission and energy resource consumption in terms of be also it is helpful,
It is finally reached the purpose for lifting whole traffic system.
Therefore, it is not provided with a kind of effective method that vehicle insurance to user carries out rank evaluation in the prior art.
The content of the invention
For above-mentioned technical problem, the embodiments of the invention provide a kind of vehicle insurance grading evaluation method and device, with to driving
The risk class that the person of sailing drives vehicle is effectively assessed.
On the one hand, the embodiments of the invention provide a kind of vehicle insurance grading evaluation method, methods described includes:
Using policy information and mounted remote information as data source, the feature of risk information of vehicle insurance is extracted, wherein, the risk
Characteristic information includes:Driver's characteristic information, vehicle characteristic information, and driving behavior information;
The assessment models on the probability that is in danger are set up, and according to maximum likelihood estimate to the parameter in the assessment models
Estimated;
Using the feature of risk information as the input of the assessment models, the vehicle insurance grading to user is estimated.
On the other hand, the embodiment of the present invention additionally provides a kind of vehicle insurance classified estimation device, and described device includes:
Feature extraction module, for using policy information and mounted remote information as data source, extracting the feature of risk of vehicle insurance
Information, wherein, the feature of risk information includes:Driver's characteristic information, vehicle characteristic information, and driving behavior letter
Breath;
Model building module, for setting up the assessment models on the probability that is in danger, and according to maximum likelihood estimate to institute
The parameter stated in assessment models is estimated;
Evaluation module, for the input using the feature of risk information as the assessment models, the vehicle insurance to user is graded
It is estimated.
Vehicle insurance grading evaluation method and device provided in an embodiment of the present invention, its feature and advantage are:
1st, the inventive method effectively make use of mounted remote information, is translated into and weighs the 8 of driver's traveling behavior
Dimension indicator, is assessed for follow-up vehicle risk.
2nd, the present invention is estimated based on historical data by maximum likelihood method to model parameter, and evaluation process is not required to very important person
Participate in, it is to avoid because the assessment errors caused by the experience of people.
3rd, the present invention proposes the car steering Risk Forecast Method that a kind of logic-based is returned, can be effectively to driving
The risk class of member's driving is estimated.
Brief description of the drawings
By reading the detailed description made to non-limiting example made with reference to the following drawings, of the invention is other
Feature, objects and advantages will become more apparent upon:
Fig. 1 is the flow chart for the vehicle insurance grading evaluation method that first embodiment of the invention is provided;
Fig. 2 is the structure chart for the vehicle insurance classified estimation device that second embodiment of the invention is provided.
Embodiment
The present invention is described in further detail with reference to the accompanying drawings and examples.It is understood that this place is retouched
The specific embodiment stated is used only for explaining the present invention, rather than limitation of the invention.It also should be noted that, in order to just
Part related to the present invention rather than entire infrastructure are illustrate only in description, accompanying drawing.
First embodiment
Present embodiments provide a kind of technical scheme of vehicle insurance grading evaluation method.Referring to Fig. 1, in the technical scheme,
Vehicle insurance grading evaluation method includes:S11, using policy information and mounted remote information as data source, extracts the feature of risk of vehicle insurance
Information;S12, sets up the assessment models on the probability that is in danger, and according to maximum likelihood estimate to the ginseng in the assessment models
Number is estimated;S13, using the feature of risk information as the input of the assessment models, the vehicle insurance to user is commented
Estimate.
Specifically, referring to Fig. 1, vehicle insurance grading evaluation method includes:
1) feature of risk is extracted, and the factor for reacting automobile risk is referred to as into feature of risk, and feature of risk includes driving here
People's feature, vehicle characteristics, driving behavior.
1-1) extract driver's feature.Driver's feature is entirely from user's policy information.Including:
Judge driver's sex, women is designated as 1, and male is designated as 0.This feature is designated as FEMALE.
Judge whether driver is young, if the age, which is not higher than, is designated as 1 for 31 years old, represents young, be otherwise designated as 0.This feature
It is designated as YOUND.
Judge whether driver is older, if the age, which is not less than, is designated as 1 for 45 years old, represents older, be otherwise designated as 0.This feature
It is designated as OLD.
Judge whether driver has steady operation, if the work unit of its registration is listed company or government, cause
Unit is designated as 1, represents stable, is otherwise designated as 0.This feature is designated as STATE_JOB.
Judge whether driver had the record that is in danger at upper 1 year, have, be designated as 1, be otherwise designated as 0.This feature is designated as
CLAIM_LY。
Judge whether driver uses new channel, be designated as 1 if it is bought by internet, expression uses new channel,
Otherwise it is designated as 0.This feature is designated as INTERNET_SALE.
The annual distance travelled of driver, is rounded up in units of ten thousand kilometers.This feature is designated as ANNUAL_MIL.
1-2) extract vehicle characteristics.Vehicle characteristics are entirely from user's policy information.Including:
Vehicle price, is rounded up in units of ten thousand yuan.This feature is designated as CAR_PRICE.
Whether be new car, be if it is designated as 1, be otherwise designated as 0 if judging vehicle.This feature is designated as NEW_CAR.
Whether be large car, be designated as 1 if vehicle is more than 5, expression is large car, is otherwise designated as 0 if judging vehicle.
This feature is designated as SIZE.
Vehicle airbag number.This feature is designated as AIRBAG.
Judge whether vehicle has safety alarm, if being then designated as 1, be otherwise designated as 0.This feature is designated as ALARM.
1-3) extract user's driving behavior.Driving behavior comes from mounted remote information, and by calculating
Arrive.
Average number of times of bringing to a halt per hour is calculated, using always bringing to a halt number of times in mounted remote information divided by running time is obtained
Arrive.This feature is designated as HARD_BRK.
Trunk roads mileages of transport route ratio is calculated, according to country《Urban planning quota index temporary provisions》If, garage
Sail and its mileage is then counted on through street and trunk roads for trunk roads mileage, be otherwise designated as non-trunk roads mileage (i.e. secondary distributor road and branch
Road), the ratio that trunk roads mileage accounts for total kilometres is trunk roads mileages of transport route ratio.This feature is designated as PCT_FAST_WAY.
Evaluation work day mileage ratio, the mileage for occurring (i.e. Mon-Fri) on weekdays is working day mileage, working day
The ratio that mileage accounts for total kilometrage is working day mileage ratio.This feature is designated as PCT_WKD.
Night mileage ratio is calculated, it is night mileage to occur at late 8 points to early mileage, and night mileage accounts for total kilometrage at 5 points
Ratio is night mileage ratio.This feature is designated as PCT_NIGHT.
Calculating speed is in mileage ratio interval 0-30km/h.This feature is designated as PCT_SPEED1.
Calculating speed is in more than 90km/h distance ratios.This feature is designated as PCT_SPEED2.
Strange mileages of transport route ratio is calculated, assert that by the road of 1 time and 2 times be strange road, strange mileages of transport route is accounted for always
Mileage ratio is strange mileages of transport route ratio.This feature is designated as PCT_FMLRT1.
Stranger mileages of transport route ratio is calculated, assert that by the road of 3 to 8 times be stranger road, stranger mileages of transport route
Total kilometrage ratio is accounted for for stranger mileages of transport route ratio.This feature is designated as PCT_FMLRT2.
2) model is set up and parameter Estimation
N number of driver's declaration form, mounted remote information and its situation of being in danger 2-1) are collected from historical data, is distinguished
Numbering is 1,2,3 ..., N, referred to as data set.Specifically, used here as 4683 liang of private cars driver's policy information and its
The on-vehicle information produced during traveling is as true training dataset, while the data set contained the private car in 1 year
The record that is in danger, this data set is randomly divided into two groups of Dataset1(totally 2342), Dataset2(totally 2341).
2-2) for each driver n, operated in repeating 1), obtain xn={ FEMALEn,YOUNGn,OLDn,…,PCT_
FMLRT1n,PCT_FMLRT2nAmount to 20 dimensional features.And its situation y that is in danger thenn={ 0,1 }, wherein 1 represents occurred
Danger, 0 represents not to be in danger.
2-3) pair with driver n, defining its probability that is in danger using dualistic logistic regression is:
Wherein β1For n*1 coefficient matrix, β0For intercept.
2-4) for data set, by all probability multiplications that are in danger, the likelihood function of model can be obtained:
2-5) using maximum likelihood estimate to coefficient matrix β1With intercept β0Estimated.
Specifically, Dataset is passed through1Data set is estimated that the parameter matrix estimate as shown in table 1, notes here
Figure parameters refer to coefficient corresponding to parameter t, such as figure parameters FEMALE is referred to corresponding to FEMALE features
Coefficient.
Table 1
2-6) for all driver n ∈ N, by step 2-5) in obtained coefficient matrix β1With intercept β0Formula 2 is substituted into,
Obtain P (yn=l | xn) be every driver value-at-risk.All value-at-risks are ranked up from big to small, and take 10 points of positions (i.e.
The 10%th is ordered as in all value-at-risks, similarly hereinafter) value-at-risk be excessive risk threshold value Rh, it is medium or high risk threshold to take 50 points of position value-at-risks
Value Rmh;It is medium to low-risk threshold value R to take 90 points of position value-at-risksml.Then the corresponding risk range of different risk class as shown in table 2, should
Table is referred to as risk class tablet, and wherein actual value is according to Dataset1Obtained threshold value actual value.
Table 2
3) risk assessment, the step carries out risk class assessment for driver r.
Operated in 3-1) repeating 1), obtain xr={ FEMALEr,YOUNGr,OLDr,…,PCT_FMLRT1r,PCT_
FMLRT2rAmount to 20 dimension feature of risk.
3-2) using formula (1), and by step 2-5) in obtained coefficient matrix β1With intercept β0Formula (1) is substituted into, is obtained
P(yr=l | xr) both drivers value-at-risk.
3-3) the risk rating for actually obtaining the driver of the table of comparisons 3.
Specifically, using Dataset2In all data carry out risk rating, then calculate and driven under different risk class
As shown in table 3, the excessive risk group probability that is in danger goes out apparently higher than other groups, medium to low-risk group and low-risk group for ratio that the person of sailing is in danger
Dangerous probability is extremely low, it is seen that this method can be good at dividing consumer's risk grade.
Table 3
Second embodiment
Present embodiments provide a kind of technical scheme of vehicle insurance classified estimation device.Referring to Fig. 2, vehicle insurance classified estimation device
Including:Feature extraction module 21, model building module 22, and evaluation module 23.
Feature extraction module 21 is used for using policy information and mounted remote information as data source, extracts the feature of risk of vehicle insurance
Information, wherein, the feature of risk information includes:Driver's characteristic information, vehicle characteristic information, and driving behavior letter
Breath.
Model building module 22 is used to set up the assessment models on the probability that is in danger, and according to maximum likelihood estimate to institute
The parameter stated in assessment models is estimated.
Evaluation module 23 is used for the input using the feature of risk information as the assessment models, and the vehicle insurance to user is graded
It is estimated.
It is preferred that, the feature extraction module 21 includes:First extracting unit, the second extracting unit, and the 3rd extraction
Unit.
First extracting unit is used to, according to the policy information, extract driver's characteristic information.
Second extracting unit is used to, according to the policy information, extract vehicle characteristic information.
3rd extracting unit is used for the driving behavior information that user is extracted according to mounted remote information.
It is preferred that, the model building module 22 includes:Vector sets up unit, model definition unit, and parameter Estimation
Unit.
Vector sets up unit, the feature of risk vector for the feature of risk information to be constituted to setting.
Model definition unit, is in danger the assessment models of probability for defining driver.Wherein, the assessment models are:
In above formula, xnFor feature of risk vector, ynFor mark of being in danger (1 represents to be in danger, and 0 represents not to be in danger), β1To be
Number vector, β0For intercept.
Parameter estimation unit is used to, according to maximum likelihood estimate, estimate the model parameter in the assessment models.
It is preferred that, the evaluation module 23 includes:Computing unit and grading unit.
Computing unit is used for the probability that is in danger that driver is calculated according to the assessment models.
Unit of grading is used for according to preset risk class tablet, gets the vehicle insurance grade of driver.
The preferred embodiments of the present invention are the foregoing is only, are not intended to limit the invention, for those skilled in the art
For, the present invention can have various changes and change.It is all any modifications made within spirit and principles of the present invention, equivalent
Replace, improve etc., it should be included in the scope of the protection.
Claims (8)
1. a kind of vehicle insurance grading evaluation method, it is characterised in that including:
Using policy information and mounted remote information as data source, the feature of risk information of vehicle insurance is extracted, wherein, the feature of risk
Information includes:Driver's characteristic information, vehicle characteristic information, and driving behavior information;
The assessment models on the probability that is in danger are set up, and the parameter in the assessment models is carried out according to maximum likelihood estimate
Estimation;
Using the feature of risk information as the input of the assessment models, the vehicle insurance grading to user is estimated.
2. according to the method described in claim 1, it is characterised in that using policy information and mounted remote information as data source, take out
Dangerous feature of risk information of picking up the car includes:
According to the policy information, driver's characteristic information is extracted;
According to the policy information, vehicle characteristic information is extracted;
According to mounted remote information, the driving behavior information of user is extracted.
3. according to the method described in claim 1, it is characterised in that set up the assessment models on the probability that is in danger, and according to most
The maximum-likelihood estimation technique carries out estimation to the parameter in the assessment models to be included:
The feature of risk information is constituted to the feature of risk vector of setting;
The assessment models of driver's probability of occurrence are defined, wherein, the assessment models are:
<mrow>
<mi>P</mi>
<mrow>
<mo>(</mo>
<msub>
<mi>y</mi>
<mi>n</mi>
</msub>
<mo>=</mo>
<mn>1</mn>
<mo>|</mo>
<msub>
<mi>x</mi>
<mi>n</mi>
</msub>
<mo>)</mo>
</mrow>
<mo>=</mo>
<mfrac>
<mrow>
<mi>exp</mi>
<mrow>
<mo>(</mo>
<msub>
<mi>&beta;</mi>
<mn>0</mn>
</msub>
<mo>+</mo>
<msub>
<mi>x</mi>
<mi>n</mi>
</msub>
<msub>
<mi>&beta;</mi>
<mn>1</mn>
</msub>
<mo>)</mo>
</mrow>
</mrow>
<mrow>
<mn>1</mn>
<mo>+</mo>
<mi>exp</mi>
<mrow>
<mo>(</mo>
<msub>
<mi>&beta;</mi>
<mn>0</mn>
</msub>
<mo>+</mo>
<msub>
<mi>x</mi>
<mi>n</mi>
</msub>
<mi>&beta;</mi>
<mo>)</mo>
</mrow>
</mrow>
</mfrac>
<mo>,</mo>
</mrow>
Wherein, xnFor feature of risk vector, ynFor the mark, β of being in danger1For coefficient vector, β0For intercept;
According to maximum likelihood estimate, the model parameter in the assessment models is estimated.
4. the method according to claim, it is characterised in that using the feature of risk information as the defeated of the assessment models
Enter, the grading of the vehicle insurance of user is estimated including:
According to the assessment models, the probability that is in danger of driver is calculated;
According to preset risk class tablet, the vehicle insurance grade of driver is got.
5. a kind of vehicle insurance classified estimation device, it is characterised in that including:
Feature extraction module, for using policy information and mounted remote information as data source, extracting the feature of risk information of vehicle insurance,
Wherein, the feature of risk information includes:Driver's characteristic information, vehicle characteristic information, and driving behavior information;
Model building module, for setting up the assessment models on the probability that is in danger, and according to maximum likelihood estimate to institute's commentary
The parameter estimated in model is estimated;
Evaluation module, for the input using the feature of risk information as the assessment models, the vehicle insurance grading to user is carried out
Assess.
6. method according to claim 5, it is characterised in that the feature extraction module includes:
First extracting unit, for according to the policy information, extracting driver's characteristic information;
Second extracting unit, for according to the policy information, extracting vehicle characteristic information;
3rd extracting unit, for according to mounted remote information, extracting the driving behavior information of user.
7. method according to claim 5, it is characterised in that the model building module includes:
Vector sets up unit, the feature of risk vector for the feature of risk information to be constituted to setting;
Model definition unit, is in danger the assessment models of probability for defining driver, wherein, the assessment models are:
<mrow>
<mi>P</mi>
<mrow>
<mo>(</mo>
<msub>
<mi>y</mi>
<mi>n</mi>
</msub>
<mo>=</mo>
<mn>1</mn>
<mo>|</mo>
<msub>
<mi>x</mi>
<mi>n</mi>
</msub>
<mo>)</mo>
</mrow>
<mo>=</mo>
<mfrac>
<mrow>
<mi>exp</mi>
<mrow>
<mo>(</mo>
<msub>
<mi>&beta;</mi>
<mn>0</mn>
</msub>
<mo>+</mo>
<msub>
<mi>x</mi>
<mi>n</mi>
</msub>
<msub>
<mi>&beta;</mi>
<mn>1</mn>
</msub>
<mo>)</mo>
</mrow>
</mrow>
<mrow>
<mn>1</mn>
<mo>+</mo>
<mi>exp</mi>
<mrow>
<mo>(</mo>
<msub>
<mi>&beta;</mi>
<mn>0</mn>
</msub>
<mo>+</mo>
<msub>
<mi>x</mi>
<mi>n</mi>
</msub>
<mi>&beta;</mi>
<mo>)</mo>
</mrow>
</mrow>
</mfrac>
<mo>,</mo>
</mrow>
Wherein, xnFor feature of risk vector, ynFor the mark, β of being in danger1For coefficient vector, β0For intercept;
Parameter estimation unit, for according to maximum likelihood estimate, estimating the model parameter in the assessment models.
8. method according to claim 5, it is characterised in that the evaluation module includes:
Computing unit, for according to the assessment models, calculating the probability that is in danger of driver;
Grading unit, for according to preset risk class tablet, getting the vehicle insurance grade of driver.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710437233.1A CN107203945A (en) | 2017-06-12 | 2017-06-12 | Vehicle insurance grading evaluation method and device |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710437233.1A CN107203945A (en) | 2017-06-12 | 2017-06-12 | Vehicle insurance grading evaluation method and device |
Publications (1)
Publication Number | Publication Date |
---|---|
CN107203945A true CN107203945A (en) | 2017-09-26 |
Family
ID=59907448
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710437233.1A Pending CN107203945A (en) | 2017-06-12 | 2017-06-12 | Vehicle insurance grading evaluation method and device |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107203945A (en) |
Cited By (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107818513A (en) * | 2017-11-24 | 2018-03-20 | 泰康保险集团股份有限公司 | Methods of risk assessment and device, storage medium, electronic equipment |
CN107862339A (en) * | 2017-11-15 | 2018-03-30 | 百度在线网络技术(北京)有限公司 | Method and apparatus for output information |
CN107945311A (en) * | 2017-11-29 | 2018-04-20 | 深圳市轱辘车联数据技术有限公司 | A kind of method for early warning of dangerous driving behavior, device, storage medium and server |
CN108446824A (en) * | 2018-02-08 | 2018-08-24 | 深圳市赛格导航科技股份有限公司 | A kind of methods of risk assessment of driving behavior, device, equipment and storage medium |
CN109118055A (en) * | 2018-07-19 | 2019-01-01 | 众安信息技术服务有限公司 | A kind of driving behavior methods of marking and device |
CN109460964A (en) * | 2018-09-29 | 2019-03-12 | 中国平安财产保险股份有限公司 | Method, apparatus and computer equipment based on the more newly-generated vehicle insurance price list of data |
CN109670970A (en) * | 2018-11-28 | 2019-04-23 | 众安信息技术服务有限公司 | A kind of driving behavior methods of marking, device and computer readable storage medium |
CN109829601A (en) * | 2018-12-07 | 2019-05-31 | 深圳大学 | A kind of driver drives the prediction technique and system of vehicle risk behavior |
CN110059952A (en) * | 2019-04-12 | 2019-07-26 | 中国人民财产保险股份有限公司 | Vehicle insurance methods of risk assessment, device, equipment and storage medium |
CN111222994A (en) * | 2018-11-23 | 2020-06-02 | 泰康保险集团股份有限公司 | Client risk assessment method, device, medium and electronic equipment |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106022926A (en) * | 2016-05-25 | 2016-10-12 | 彩虹无线(北京)新技术有限公司 | Premium deduction method based on mileage and driving behavior safety |
CN106411998A (en) * | 2016-07-15 | 2017-02-15 | 南京邮电大学 | Prediction method for UBI (Usage-Based Insurance) system based on internet of vehicles big data |
CN106408423A (en) * | 2016-11-25 | 2017-02-15 | 泰康保险集团股份有限公司 | Method and system for risk assessment and method for constructing system for risk assessment |
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 |
CN106530094A (en) * | 2016-08-31 | 2017-03-22 | 江苏鸿信***集成有限公司 | Vehicle insurance assessment system and assessment method |
CN106803207A (en) * | 2016-08-10 | 2017-06-06 | 中国石油大学(华东) | A kind of method for quantitatively evaluating and device for oil field oil-containing gas |
-
2017
- 2017-06-12 CN CN201710437233.1A patent/CN107203945A/en active Pending
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106022926A (en) * | 2016-05-25 | 2016-10-12 | 彩虹无线(北京)新技术有限公司 | Premium deduction method based on mileage and driving behavior safety |
CN106411998A (en) * | 2016-07-15 | 2017-02-15 | 南京邮电大学 | Prediction method for UBI (Usage-Based Insurance) system based on internet of vehicles big data |
CN106803207A (en) * | 2016-08-10 | 2017-06-06 | 中国石油大学(华东) | A kind of method for quantitatively evaluating and device for oil field oil-containing gas |
CN106530094A (en) * | 2016-08-31 | 2017-03-22 | 江苏鸿信***集成有限公司 | Vehicle insurance assessment system and assessment method |
CN106408423A (en) * | 2016-11-25 | 2017-02-15 | 泰康保险集团股份有限公司 | Method and system for risk assessment and method for constructing system for risk assessment |
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 |
Non-Patent Citations (2)
Title |
---|
廖绚,李兴绪: "基于Logit模型的银行个人信贷风险管理评估", 《统计与决策》 * |
辛颖: "关于logistic模型在建立信用评价体系的应用", 《工程经济》 * |
Cited By (14)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107862339A (en) * | 2017-11-15 | 2018-03-30 | 百度在线网络技术(北京)有限公司 | Method and apparatus for output information |
CN107862339B (en) * | 2017-11-15 | 2022-04-29 | 百度在线网络技术(北京)有限公司 | Method and apparatus for outputting information |
CN107818513A (en) * | 2017-11-24 | 2018-03-20 | 泰康保险集团股份有限公司 | Methods of risk assessment and device, storage medium, electronic equipment |
CN107945311A (en) * | 2017-11-29 | 2018-04-20 | 深圳市轱辘车联数据技术有限公司 | A kind of method for early warning of dangerous driving behavior, device, storage medium and server |
CN108446824A (en) * | 2018-02-08 | 2018-08-24 | 深圳市赛格导航科技股份有限公司 | A kind of methods of risk assessment of driving behavior, device, equipment and storage medium |
CN109118055A (en) * | 2018-07-19 | 2019-01-01 | 众安信息技术服务有限公司 | A kind of driving behavior methods of marking and device |
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 |
CN109460964A (en) * | 2018-09-29 | 2019-03-12 | 中国平安财产保险股份有限公司 | Method, apparatus and computer equipment based on the more newly-generated vehicle insurance price list of data |
CN111222994A (en) * | 2018-11-23 | 2020-06-02 | 泰康保险集团股份有限公司 | Client risk assessment method, device, medium and electronic equipment |
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 |
CN109670970A (en) * | 2018-11-28 | 2019-04-23 | 众安信息技术服务有限公司 | A kind of driving behavior methods of marking, device and computer readable storage medium |
CN109829601B (en) * | 2018-12-07 | 2021-03-23 | 深圳大学 | Method and system for predicting risk behavior of driver driving vehicle |
CN109829601A (en) * | 2018-12-07 | 2019-05-31 | 深圳大学 | A kind of driver drives the prediction technique and system of vehicle risk behavior |
CN110059952A (en) * | 2019-04-12 | 2019-07-26 | 中国人民财产保险股份有限公司 | Vehicle insurance methods of risk assessment, device, equipment and storage medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107203945A (en) | Vehicle insurance grading evaluation method and device | |
CN105865472A (en) | Vehicle-mounted navigation method based on least oil consumption | |
Frank et al. | An assessment of urban form and pedestrian and transit improvements as an integrated GHG reduction strategy. | |
CN103295414A (en) | Bus arrival time forecasting method based on mass historical GPS (global position system) trajectory data | |
CN106781456A (en) | The assessment data processing method and system of a kind of vehicle drive security | |
CN105654721B (en) | A kind of method for calculating public transport OD amounts using bus IC card and vehicle GPS data | |
CN104504099A (en) | Position-trajectory-based travel state splitting method | |
CN105469602A (en) | Method for predicting bus passenger waiting time range based on IC card data | |
CN104318757B (en) | Bus bus or train route section Forecasting Methodology working time on a kind of public transportation lane | |
Gao et al. | Park-and-ride service design under a price-based tradable credits scheme in a linear monocentric city | |
CN104517040A (en) | Method for calculating in-carriage congestion degree of public traffic vehicle based on IC card data | |
CN104599002A (en) | Order value predicting method and equipment | |
Zhu et al. | Green routing fuel saving opportunity assessment: A case study using large-scale real-world travel data | |
CN114550445B (en) | Urban area traffic safety state assessment method and device | |
CN103942952A (en) | Assessment method for road network function gradation state grades | |
Bera et al. | Assessing consumer preferences for plug-in hybrid electric vehicle (PHEV): an Indian perspective | |
CN106600030A (en) | Travel reserved time calculation method based on road network journey time reliability | |
CN104392076B (en) | City road network pedestrian traffic accident black spot recognition method | |
CN105260932A (en) | Credit scoring method for traffic safety recessive factors | |
Bera et al. | Commuters' Willingness-to-Pay for the Attributes of Plug-in Hybrid Electric Vehicle: A Case Study in Kolkata, India | |
Rabbani et al. | Indicators of injury severity of truck crashes using random parameter logit modeling | |
Constantinescu et al. | Impact study of telematics auto insurance | |
Gunathilaka et al. | Household travel survey method for vehicle kilometers travel estimations: A case study in a developing country. | |
Burris et al. | Travelers’ value of time and reliability as measured on Katy Freeway | |
Rodier et al. | How Can Automated Vehicles Increase Access to Marginalized Populations and Reduce Congestion, Vehicle Miles Traveled, and Greenhouse Gas Emissions? A Case Study in the City of Los Angeles |
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 | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170926 |