CN105512453B - A kind of vehicle risk judgment method and device based on history mileage - Google Patents
A kind of vehicle risk judgment method and device based on history mileage Download PDFInfo
- Publication number
- CN105512453B CN105512453B CN201410544859.9A CN201410544859A CN105512453B CN 105512453 B CN105512453 B CN 105512453B CN 201410544859 A CN201410544859 A CN 201410544859A CN 105512453 B CN105512453 B CN 105512453B
- Authority
- CN
- China
- Prior art keywords
- mileage
- matrix
- vehicle
- accident
- normalized
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
A kind of vehicle risk judgment method and device based on history mileage build mileage statistical condition first, and then the statistical information according to mileage at different conditions, establishes accident mileage matrix and common mileage matrix:After obtaining two matroid information, data training is carried out to it, a risk judgment coefficient is given to each mileage statistical condition, in the method for risk judgment coefficient and mileage number linear combination summation, structure accident system of linear equations and normal linear equation group, it is 1 to enable each equation output result in accident system of linear equations, each equation is equal to 0 in normal linear equation group.The solution of system of linear equations, the i.e. solution of risk judgment coefficient finally are obtained with the method for maximal possibility estimation, obtains training result.According to the risk judgment coefficient that training obtains, its risk probability can be calculated with the mileage statistical data of other vehicles, to judge that the possibility of accident occurs for the vehicle, be provided for dynamic adjustment car insurance expense and more suit the actual reference of vehicle.
Description
Technical field
The present invention relates to car accident risk assessment field, especially a kind of vehicle risk judgement side based on history mileage
Method and device.
Background technology
When calculating car insurance rate, the actual use risk of the more difficult accurate judgement vehicle of conventional method is dynamically to adjust
Whole most suitable insurance premium, traditional car insurance expense by fixed user data, (such as join by car owner's age, driving age, vehicle
Number, vehicle price) and simple statistical data (such as history be in danger number) decision, actual vehicle service condition is not accounted for, and
Cannot react vehicle usually when drive, how drive road conditions, driving behavior how.Cause business vehicle insurance in the market
The declaration form for belonging to indifference is unfavorable for insurance business and builds differential declaration form.
Invention content
It is a primary object of the present invention to overcome drawbacks described above in the prior art, a kind of vehicle based on history mileage is proposed
Risk judgment method and apparatus.
The present invention adopts the following technical scheme that:
A kind of vehicle risk judgment method based on history mileage, it is characterised in that:For the number in car networking database
According to pre-establishing n mileage statistical condition, judgment step is as follows:
1) all history mileages for having the vehicle of accident record before traffic injury time in M months are united
Meter, it take row, accident vehicle as capable accident mileage matrix m of mileage statistical condition to buildij, i=1,2 ..., L are different vehicles
, j=1,2 ..., n are different mileage statistical conditions, L > n+1;By going through for the vehicle of all zero defects records in M months
History mileage is counted, build by row, zero defects vehicle of mileage statistical condition be row common mileage matrix m'ij, i=
1,2 ..., K is different vehicle, and j=1,2 ..., n are different mileage statistical conditions, K > n+1;
2) it is normalized accident mileage matrix and common mileage matrix to obtain normalized accident mileage respectively
Matrix aij, i=1,2 ..., L are different vehicle, and j=1,2 ..., n are different mileage statistical conditions, L > n+1, and normalization
Common mileage matrix cij, i=1,2 ..., K are different vehicle, and j=1,2 ..., n are different mileage statistical conditions, K > n+
1;
3) regression model being made of linear equation is established:Wherein j=1,2 ..., n, β0,β1,
β2,…,βnFor n+1 risk factor value, g is risk probability, and between 0-1,0 indicates that accident does not occur certainly probability value, 1
Accident occurs certainly for expression;
4) by normalized accident mileage matrix aijIn every a line bring intoAnd g=1 is set, structure
At an accident system of linear equations;By normalized common mileage matrix cijIn every a line bring intoAnd
G=0 is set, a normal linear equation group is constituted;Accident system of linear equations and normal linear equation group are merged to obtain as follows
Training equation group:
Then, the training equation group is solved, risk factor value β is obtained0,β1,β2,…,βn;
5) for any one vehicle E, traveling of the vehicle in nearest M months is calculated separately according to n mileage statistical condition
Mileage matrix mj, j=1,2 ..., n, by mileage travelled matrix mjIt is normalized, obtains normalized mileage travelled matrix
ej, j=1,2 ..., n;
6) according to the risk factor value of step 4), the accident risk probability of vehicle E is calculated:
G'=β0+β1e1+β2e2+…+βnen。
Preferably, described by accident mileage matrix m in step 2)ijIt is normalized, specially:By accident
Mileage matrix mijEvery data line add up, obtain the cumulative mileage value D of rowi,By accident mileage matrix mij
Every data line divided by corresponding Di, to obtain the normalization accident mileage matrix
Preferably, in step 2), common mileage matrix is normalized respectively, specially:By common mileage
Matrix m'ijEvery data line add up, obtain the cumulative mileage value D of rowi',By common mileage matrix m'ij
Every data line divided by corresponding Di', to obtain the common mileage matrix of normalization
Preferably, the mileage statistical condition includes vehicle on friction speed section or different dates in week or intraday
The mileage of different periods or different zones road.
Preferably, in step 5), by mileage travelled matrix mjIt is normalized, refers to:By mileage travelled matrix mjIt is every
A data are added up to obtainAgain by mileage travelled matrix mjIn each data divided by D obtain it is described normalized
Mileage travelled matrix
Preferably, the mileage statistical condition n takes 27, includes several speed intervals, several dates in week, several
A different periods and several different zones roads.
Preferably, in step 4), the training equation group is solved using maximum likelihood estimate, obtains the risk system
Numerical value β0,β1,β2,…,βn。
A kind of vehicle risk judgment means based on history mileage, it is characterised in that:Including
Mileage statistical module, for carrying out statistic of classification to the data in car networking database according to mileage statistical condition;
Risk factor training module is connected with mileage statistical module, including accident vehicle mileage processing unit and zero defects
Vehicle mileage processing unit and risk factor computing unit;The accident vehicle mileage processing unit is used for according to mileage statistical module
The data structure accident mileage matrix of statistics is simultaneously normalized;The zero defects vehicle mileage processing unit is used for according to inner
The data of journey statistical module counts build common mileage matrix and are normalized;The risk factor computing unit application root
According to normalized accident mileage matrix and normalized common mileage matrix structure training equation group and use maximal possibility estimation
Method solves the training equation group, to obtain risk factor value;
Risk judgment module is connected with mileage statistical module and risk factor training module, for counting mould according to mileage
The data of block statistics obtain the mileage travelled matrix of any vehicle and are normalized, in conjunction with obtained risk factor value
Accident risk probability is calculated;
Car networking database is connected with mileage statistical module, and the history running data for storing all vehicles includes
GPS location, mileage, time, speed and accident record.
By the above-mentioned description of this invention it is found that compared with prior art, the present invention has the advantages that:
The present invention utilizes these information automatic decision vehicle risk situations in car networking database, builds mileage system first
Meter condition, mileage statistical condition are made of conditions such as different time, speed, circuits, are counted mileage under these conditions and are reflected
The use tendency of vehicle under different factors.Then the statistical information according to mileage at different conditions, is established in accident
Journey matrix and common mileage matrix:Accident mileage matrix by generation accident alarming vehicle in period before accident it is each in
Mileage composition under journey statistical condition;Common mileage matrix by not occurring the vehicle of accident in each in a period of time
Mileage composition under journey statistical condition.After obtaining two matroid information, data training is carried out to it, is united to each mileage
Meter condition gives a risk judgment coefficient, in the method for risk judgment coefficient and mileage number linear combination summation, builds accident
System of linear equations and normal linear equation group, it is 1 to enable each equation output result in accident system of linear equations, indicates to send out certainly
It makes trouble former, each equation is equal to 0 in normal linear equation group, indicates that accident does not occur certainly.Finally use maximal possibility estimation
Method obtain the solution of system of linear equations, the i.e. solution of risk judgment coefficient, obtain training result.The risk obtained according to training is sentenced
Disconnected coefficient, can calculate its risk probability with the mileage statistical data of other vehicles, to judge that accident occurs for the vehicle can
Energy property provides for dynamic adjustment car insurance expense and more suits the actual reference of vehicle.
Description of the drawings
Fig. 1 is apparatus of the present invention schematic diagram.
Specific implementation mode
Below by way of specific implementation mode, the invention will be further described.
In actual car networking system, the history running data of many vehicles is had recorded in car networking database, including:
GPS location combining geographic information system can also be obtained vehicle row by GPS location, mileage, time, speed, accident record etc.
Whether category of roads, city or the suburb sailed are more than the information such as section speed limit.
A kind of vehicle risk judgment method based on history mileage of the present invention, for the data in car networking database,
27 mileage statistical conditions are pre-established, are specifically included as follows:
A) mileage of the vehicle under friction speed section.Mileage statistical data of the vehicle under friction speed section represents
When vehicle uses the case where speed speed.Such as vehicle speed is divided into 5 grades for a class with every 30km/h speed differences,
In higher than the vehicle speed of 120km/h be classified as a shelves, therefore share 5 mileage statistical conditions at various speeds, such as following table
1:
Table 1
Condition | 1 | 2 | 3 | 4 | 5 |
Speed interval | 0-30km/h | 30-60km/h | 60-90km/h | 90-120km/h | >120km/h |
B) mileage of the vehicle under the different dates in week.The laws of use situation which represent vehicles in one week.This hair
It is bright to arrive Zhou Tianwei conditions on every Mondays, the mileage under the conditions of statistics is each, therefore share 7 mileage statistics items under different weeks
Part, such as the following table 2:
Table 2
Condition | 6 | 7 | 8 | 9 | 10 | 11 | 12 |
Date in week | Monday | Tuesday | Wednesday | Thursday | Friday | Saturday | Sunday |
C) mileage of the vehicle under one day different periods.Which represent vehicles in intraday service condition, for example whether
It is used in peak period on and off duty, if used in the fatigue high-risk period in morning.By the time with every 2 hours for section, draw
It is divided into 12 statistical conditions 3:
Table 3
D) mileage of the vehicle under different zones road.Which represent service condition of the vehicle under different geographical environments,
For example whether often running high speed, whether often traveling etc. in urban district.Region is divided into 3 statistical conditions, such as the following table 4:
Table 4
Condition | 25 | 26 | 27 |
Region | Highway | Downtown roads | Non- downtown roads |
Specific method and step is as follows:
1) all history mileages for having the vehicle of accident record before traffic injury time in 6 months are united
Meter, it take row, accident vehicle as capable accident mileage matrix m of mileage statistical condition to buildij, i=1,2 ..., L are different vehicles
, j=1,2 ..., 27 is different mileage statistical conditions, L > 28;By going through for the vehicle of all zero defects in 6 months record
History mileage is counted, build by row, zero defects vehicle of mileage statistical condition be row common mileage matrix m'ij, i=
1,2 ..., K is different vehicle, and j=1,2 ..., 27 is different mileage statistical conditions, K > 28.
2) it is normalized accident mileage matrix and common mileage matrix to obtain normalized accident mileage respectively
Matrix aij, described by accident mileage matrix mijIt is normalized, specially:By accident mileage matrix mijEvery a line
Data add up, and obtain the cumulative mileage value D of rowi,By accident mileage matrix mijEvery data line divided by right
The D answeredi, to obtain the normalization accident mileage matrix For different vehicle, j=1,
2 ..., 27 be different mileage statistical conditions, L > 28.
Common mileage matrix is normalized respectively, specially:By common mileage matrix m'ijEvery data line
It adds up, obtains the cumulative mileage value D of rowi',By common mileage matrix m'ijEvery data line divided by correspondence
Di', to obtain the common mileage matrix of normalization For different vehicle, j=1,
2 ..., 27 be different mileage statistical conditions, K > 28.
3) regression model being made of linear equation is established:Wherein j=1,2 ..., 27, β0,β1,
β2,…,βnFor 28 risk factor values, g is risk probability, and between 0-1,0 indicates that accident, 1 table does not occur certainly probability value
Show and accident occurs certainly.
4) by normalized accident mileage matrix aijIn every a line bring intoAnd g=1 is set, structure
At an accident system of linear equations;By normalized common mileage matrix cijIn every a line bring intoAnd
G=0 is set, a normal linear equation group is constituted;Accident system of linear equations and normal linear equation group are merged to obtain as follows
Training equation group:
Wherein, equation number is more than risk factor number, then, the training side in being solved 4) using maximum likelihood estimate
Journey group obtains risk factor value β0,β1,β2,…,βn。
5) for any one vehicle E, traveling of the vehicle in nearest 6 months is calculated separately according to 27 mileage statistical conditions
Mileage matrix mj, j=1,2 ..., 27, by mileage travelled matrix mjIt is normalized, obtains normalized mileage travelled matrix
ej, j=1,2 ..., 27;In step 5), by mileage travelled matrix mjIt is normalized, refers to:By mileage travelled matrix mj's
Each data are added up to obtainAgain by mileage travelled matrix mjIn each data divided by D obtain the normalization
Mileage travelled matrix
6) according to the risk factor value of step 4), the accident risk probability of vehicle E is calculated:G'=β0+β1e1+β2e2
+…+βnen.G ' are calculated whether close to 1, if taking T=| g ' -1 | T is less than a smaller number ε (T<ε, ε<0.01), then show
G ' are indicated according to nearly six months mileage travel situations of vehicle E, it is more likely that accident will occur, therefore suitably carry very close to 1
Height adjustment vehicle premium next year;If g ' keep off 1, g ' are judged whether close to 0, using equally smaller number ε as reference, such as
Fruit | g ' |<ε(ε<0.01), then g ' indicate, according to nearly six months mileage travel situations of vehicle E, may to send out very close to 0
Former probability of making trouble is very low, can suitably reduce and adjust vehicle premium next year.
Referring to Fig.1, the present invention also proposes a kind of vehicle risk judgment means based on history mileage, including
Mileage statistical module, for carrying out statistic of classification to the data in car networking database according to mileage statistical condition.
Risk factor training module is connected with mileage statistical module, including accident vehicle mileage processing unit and zero defects
Vehicle mileage processing unit and risk factor computing unit;The accident vehicle mileage processing unit is used for according to mileage statistical module
The data structure accident mileage matrix of statistics is simultaneously normalized;The zero defects vehicle mileage processing unit is used for according to inner
The data of journey statistical module counts build common mileage matrix and are normalized;The risk factor computing unit application root
According to normalized accident mileage matrix and normalized common mileage matrix structure training equation group and use maximal possibility estimation
Method solves the training equation group, to obtain risk factor value.
Risk judgment module is connected with mileage statistical module and risk factor training module, for counting mould according to mileage
The data of block statistics obtain the mileage travelled matrix of any vehicle and are normalized, in conjunction with obtained risk factor value
Accident risk probability is calculated.
Car networking database is connected with mileage statistical module, and the history running data for storing all vehicles includes
GPS location, mileage, time, speed and accident record.
The present invention utilizes these information automatic decision vehicle risk situations in car networking database, builds mileage system first
Meter condition, mileage statistical condition are made of conditions such as different time, speed, circuits, are counted mileage under these conditions and are reflected
The use tendency of vehicle under different factors.Then the statistical information according to mileage at different conditions, is established in accident
Journey matrix and common mileage matrix:Accident mileage matrix by generation accident alarming vehicle in period before accident it is each in
Mileage composition under journey statistical condition;Common mileage matrix by not occurring the vehicle of accident in each in a period of time
Mileage composition under journey statistical condition.After obtaining two matroid information, data training is carried out to it, is united to each mileage
Meter condition gives a risk judgment coefficient, in the method for risk judgment coefficient and mileage number linear combination summation, builds accident
System of linear equations and normal linear equation group, it is 1 to enable each equation output result in accident system of linear equations, indicates to send out certainly
It makes trouble former, each equation is equal to 0 in normal linear equation group, indicates that accident does not occur certainly.Finally use maximal possibility estimation
Method obtain the solution of system of linear equations, the i.e. solution of risk judgment coefficient, obtain training result.The risk obtained according to training is sentenced
Disconnected coefficient, can calculate its risk probability with the mileage statistical data of other vehicles, to judge that accident occurs for the vehicle can
Energy property provides for dynamic adjustment car insurance expense and more suits the actual reference of vehicle.
The specific implementation mode of the present invention is above are only, but the design concept of the present invention is not limited thereto, it is all to utilize this
Conceive the change for carrying out unsubstantiality to the present invention, the behavior for invading the scope of the present invention should all be belonged to.
Claims (8)
1. a kind of vehicle risk judgment method based on history mileage, it is characterised in that:For the data in car networking database,
N mileage statistical condition is pre-established, judgment step is as follows:
1) all history mileages for having the vehicle of accident record before traffic injury time in M months are counted, structure
It is capable accident mileage matrix m to build by row, accident vehicle of mileage statistical conditionij, i=1,2 ..., L are different vehicle, j=
1,2 ..., n is different mileage statistical conditions, L > n+1;By the history mileage of the vehicle of all zero defects records in M months
Data are counted, build by row, zero defects vehicle of mileage statistical condition be row common mileage matrix m'ij, i=1,
2 ..., K is different vehicle, and j=1,2 ..., n are different mileage statistical conditions, K > n+1;
2) it is normalized accident mileage matrix and common mileage matrix to obtain normalized accident mileage matrix respectively
aij, i=1,2 ..., L are different vehicle, and j=1,2 ..., n are different mileage statistical conditions, L > n+1 and normalized general
Tongli journey matrix cij, i=1,2 ..., K are different vehicle, and j=1,2 ..., n are different mileage statistical conditions, K > n+1;
3) regression model being made of linear equation is established:Wherein j=1,2 ..., n, β0,β1,β2,…,
βnFor n+1 risk factor value, g is risk probability, and probability value is between 0-1, and 0 indicates that accident does not occur certainly, and 1 indicates to agree
Surely accident occurs;
4) by normalized accident mileage matrix aijIn every a line bring intoAnd g=1 is set, constitute one
Accident system of linear equations;By normalized common mileage matrix cijIn every a line bring intoAnd set g=
0, constitute a normal linear equation group;Merge accident system of linear equations and normal linear equation group to obtain following training equation
Group:
Then, the training equation group is solved, risk factor value β is obtained0,β1,β2,…,βn;
5) for any one vehicle E, mileage travelled of the vehicle in nearest M months is calculated separately according to n mileage statistical condition
Matrix mj, j=1,2 ..., n, by mileage travelled matrix mjIt is normalized, obtains normalized mileage travelled matrix ej, j
=1,2 ..., n;
6) according to the risk factor value of step 4), the accident risk probability of vehicle E is calculated:
G'=β0+β1e1+β2e2+…+βnen。
2. a kind of vehicle risk judgment method based on history mileage as described in claim 1, it is characterised in that:In step 2)
In, it is described by accident mileage matrix mijIt is normalized, specially:
By accident mileage matrix mijEvery data line add up, obtain the cumulative mileage value D of rowi,By accident
Mileage matrix mijEvery data line divided by corresponding Di, to obtain the normalization accident mileage matrix
3. a kind of vehicle risk judgment method based on history mileage as described in claim 1, it is characterised in that:In step 2)
In, common mileage matrix is normalized respectively, specially:By common mileage matrix m'ijEvery data line carry out
It is cumulative, obtain the cumulative mileage value D of rowi',By common mileage matrix m'ijEvery data line divided by corresponding
Di', to obtain the common mileage matrix of normalization
4. a kind of vehicle risk judgment method based on history mileage as described in claim 1, it is characterised in that:The mileage
Statistical condition includes vehicle in friction speed section or different dates in week or intraday different periods or different zones road
Mileage.
5. a kind of vehicle risk judgment method based on history mileage as described in claim requires 1, it is characterised in that:In step
It is rapid 5) in, by mileage travelled matrix mjIt is normalized, refers to:By mileage travelled matrix mjEach data added up to obtainAgain by mileage travelled matrix mjIn each data divided by D obtain the normalized mileage travelled matrix
6. a kind of vehicle risk judgment method based on history mileage as described in claim 1, it is characterised in that:The mileage
Statistical condition n takes 27, includes several speed intervals, several dates in week, several different periods and several differences
Area road.
7. a kind of vehicle risk judgment method based on history mileage as described in claim 1, it is characterised in that:In step 4)
In, the training equation group is solved using maximum likelihood estimate, obtains the risk factor value β0,β1,β2,…,βn。
8. a kind of vehicle risk judgment means based on history mileage, it is characterised in that:Including
Mileage statistical module, for carrying out statistic of classification to the data in car networking database according to mileage statistical condition;
Risk factor training module is connected with mileage statistical module, including accident vehicle mileage processing unit and zero defects vehicle
Mileage processing unit and risk factor computing unit;The accident vehicle mileage processing unit is used for according to mileage statistical module counts
Data structure accident mileage matrix and be normalized;The zero defects vehicle mileage processing unit according to mileage for uniting
The data of meter module statistics build common mileage matrix and are normalized;The risk factor computing unit applies basis to return
The one accident mileage matrix changed and normalized common mileage matrix structure training equation group are simultaneously asked using maximum likelihood estimate
The training equation group is solved, to obtain risk factor value;
Risk judgment module is connected with mileage statistical module and risk factor training module, for being united according to mileage statistical module
The data of meter obtain the mileage travelled matrix of any vehicle and are normalized, and are calculated in conjunction with obtained risk factor value
Obtain accident risk probability;
Car networking database is connected with mileage statistical module, and the history running data for storing all vehicles, includes GPS
Position, mileage, time, speed and accident record.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201410544859.9A CN105512453B (en) | 2014-10-15 | 2014-10-15 | A kind of vehicle risk judgment method and device based on history mileage |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201410544859.9A CN105512453B (en) | 2014-10-15 | 2014-10-15 | A kind of vehicle risk judgment method and device based on history mileage |
Publications (2)
Publication Number | Publication Date |
---|---|
CN105512453A CN105512453A (en) | 2016-04-20 |
CN105512453B true CN105512453B (en) | 2018-10-16 |
Family
ID=55720433
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201410544859.9A Active CN105512453B (en) | 2014-10-15 | 2014-10-15 | A kind of vehicle risk judgment method and device based on history mileage |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN105512453B (en) |
Families Citing this family (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109754595B (en) * | 2017-11-01 | 2022-02-01 | 阿里巴巴集团控股有限公司 | Vehicle risk assessment method and device and interface equipment |
CN109934725A (en) * | 2019-03-22 | 2019-06-25 | 宋捍强 | A kind of car insurance charging method, device, charge system and storage medium |
CN113362137B (en) * | 2021-06-11 | 2024-04-05 | 北京十一贝科技有限公司 | Insurance product recommendation method and device, terminal equipment and storage medium |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101937421A (en) * | 2009-07-03 | 2011-01-05 | 上海大潮电子技术有限公司 | Method for collecting real-time operation information of vehicle for operation security risk assessment |
CN102034009A (en) * | 2010-12-20 | 2011-04-27 | 东南大学 | Equivalent road accident number method-based identifying equipment for accident-prone sections |
US7937278B1 (en) * | 2005-01-18 | 2011-05-03 | Allstate Insurance Company | Usage-based insurance cost determination system and method |
CN202662060U (en) * | 2012-01-19 | 2013-01-09 | 北京赛德斯汽车信息技术有限公司 | Automobile insurance information service system utilizing vehicle-mounted information |
CN103150675A (en) * | 2013-01-30 | 2013-06-12 | 郁佳敏 | Risk monitoring system of automobile insurance |
Family Cites Families (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2003323555A (en) * | 2002-04-30 | 2003-11-14 | Hewlett Packard Japan Ltd | Method and system for information distribution |
WO2013026047A2 (en) * | 2011-08-17 | 2013-02-21 | Trans Union Llc | Systems and methods for generating vehicle insurance premium quotes based on a vehicle history |
-
2014
- 2014-10-15 CN CN201410544859.9A patent/CN105512453B/en active Active
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US7937278B1 (en) * | 2005-01-18 | 2011-05-03 | Allstate Insurance Company | Usage-based insurance cost determination system and method |
CN101937421A (en) * | 2009-07-03 | 2011-01-05 | 上海大潮电子技术有限公司 | Method for collecting real-time operation information of vehicle for operation security risk assessment |
CN102034009A (en) * | 2010-12-20 | 2011-04-27 | 东南大学 | Equivalent road accident number method-based identifying equipment for accident-prone sections |
CN202662060U (en) * | 2012-01-19 | 2013-01-09 | 北京赛德斯汽车信息技术有限公司 | Automobile insurance information service system utilizing vehicle-mounted information |
CN103150675A (en) * | 2013-01-30 | 2013-06-12 | 郁佳敏 | Risk monitoring system of automobile insurance |
Non-Patent Citations (1)
Title |
---|
行驶里程数对车险净保费的影响研究;张连增 等;《保险研究》;20120630(第6期);第29-38页 * |
Also Published As
Publication number | Publication date |
---|---|
CN105512453A (en) | 2016-04-20 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Tuli et al. | Factors influencing the usage of shared E-scooters in Chicago | |
Li et al. | Analysis of morning commute route choice patterns using global positioning system–based vehicle activity data | |
EP2619059B1 (en) | Driver profiling system and method | |
Teal | Carpooling: Who, how and why | |
Brown | The open economy: Justice Frankfurter and the position of the judiciary | |
Rahman et al. | Users' views on current and future real‐time bus information systems | |
CN105512453B (en) | A kind of vehicle risk judgment method and device based on history mileage | |
Choocharukul et al. | User perceptions and engineering definitions of highway level of service: an exploratory statistical comparison | |
CN109637134A (en) | A kind of public transport device matching process | |
CN107657537A (en) | UBI collecting vehicle informations analysis system and car owner's classification and premium discount method | |
CN107918826A (en) | The driver's evaluation and dispatching method that a kind of driving environment perceives | |
Blower et al. | Type of motor carrier and driver history in fatal bus crashes | |
Khoo et al. | Short-term impact analysis of fuel price policy change on travel demand in Malaysian cities | |
Atubi et al. | Contemporary analysis of variability in road traffic accidents in Lagos State, Nigeria | |
Cooper et al. | The efficiency of using non-culpable crash-claim involvements from insurance data as a means of estimating travel exposure for road user sub-groups | |
Durkin et al. | Geographic analysis of traffic injury in Wisconsin: impact on case fatality of distance to level I/II trauma care | |
Thorpe et al. | A telephone survey of stated travel responses to fuel shortages | |
Sinniah et al. | The framework for assessing public transportation by using competitiveness index indicators | |
Deka | Impacts of standardizing school start time on children and household workers–An examination with NHTS data | |
Walker et al. | Quantitative study of attitudes, motivations and beliefs related to speeding and speed enforcement | |
Farid et al. | Enhancing Crash Data Reporting to Highway Safety Partners in Wyoming by Utilizing Big Data Analysis and Survey Techniques | |
Chu | An assessment of public transportation markets using NHTS data | |
Keall et al. | Are SUVs dangerous vehicles? | |
Mohammed et al. | Determining Travel Behaviour in Petaling Jaya, Malaysia | |
Bouzir et al. | Passengers' activities in multimodal transportation stations |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |