CN113781244B - Method and system for generating insurance premium, electronic device and storage medium - Google Patents
Method and system for generating insurance premium, electronic device and storage medium Download PDFInfo
- Publication number
- CN113781244B CN113781244B CN202110947067.6A CN202110947067A CN113781244B CN 113781244 B CN113781244 B CN 113781244B CN 202110947067 A CN202110947067 A CN 202110947067A CN 113781244 B CN113781244 B CN 113781244B
- Authority
- CN
- China
- Prior art keywords
- vehicle
- driving behavior
- mileage
- premium
- insurance premium
- 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
- 238000000034 method Methods 0.000 title claims abstract description 64
- 230000006399 behavior Effects 0.000 claims description 147
- 230000000875 corresponding effect Effects 0.000 claims description 54
- 230000001133 acceleration Effects 0.000 claims description 28
- 238000004590 computer program Methods 0.000 claims description 7
- 230000002596 correlated effect Effects 0.000 claims description 6
- 230000008569 process Effects 0.000 abstract description 24
- 230000008447 perception Effects 0.000 abstract description 8
- 238000004458 analytical method Methods 0.000 abstract description 3
- 230000009471 action Effects 0.000 description 16
- 238000004364 calculation method Methods 0.000 description 13
- 238000012545 processing Methods 0.000 description 7
- 230000008859 change Effects 0.000 description 6
- 238000005516 engineering process Methods 0.000 description 5
- 230000006870 function Effects 0.000 description 5
- 230000005540 biological transmission Effects 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 238000004422 calculation algorithm Methods 0.000 description 2
- 238000013136 deep learning model Methods 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000004069 differentiation Effects 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 2
- 239000007788 liquid Substances 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000003491 array Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000003287 optical effect Effects 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
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0611—Request for offers or quotes
Landscapes
- Business, Economics & Management (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Marketing (AREA)
- Economics (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Development Economics (AREA)
- Theoretical Computer Science (AREA)
- Technology Law (AREA)
- Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)
Abstract
The invention discloses a method and a system for generating insurance premium, electronic equipment and a storage medium, wherein the method for generating insurance premium comprises the following steps: acquiring driving behavior data corresponding to a vehicle; inputting the driving behavior data into a driving behavior scoring model to obtain a driving behavior score corresponding to the vehicle; and determining the insurance premium according to the driving behavior score. According to the method and the system for generating the vehicle insurance premium, the electronic equipment and the storage medium, through analysis of the driving behavior data corresponding to the vehicle, the risk level generated in the using process of the vehicle can be distinguished more accurately, the generated vehicle insurance premium is more reasonable, and the perception of a vehicle owner on the driving behavior of the vehicle owner can be improved through the vehicle insurance premium, so that unreasonable driving habits are improved.
Description
Technical Field
The present invention relates to the field of information technologies, and in particular, to a method and system for generating a vehicle insurance premium, an electronic device, and a storage medium.
Background
Traditional vehicle insurance pricing is generally based on demographic attributes of the vehicle owners, such as gender, age; and vehicle attributes such as vehicle type, vehicle price, and vehicle age; and distinguishing the risk of accident claims of the vehicle by historical information such as insurance and violation records, thereby making corresponding premium price. However, the above factors are not factors directly causing an accident, and there is a lack of accuracy in predicting the risk of a vehicle accident by the above factors.
Disclosure of Invention
The invention aims to overcome the defects that the generation basis of the insurance premium is unreasonable and the determination of the insurance premium is not fully considered in the prior art, and provides a method and a system for generating the insurance premium, electronic equipment and a storage medium.
The invention solves the technical problems by the following technical scheme:
the invention provides a method for generating insurance premium of vehicles, which comprises the following steps:
acquiring driving behavior data corresponding to a vehicle;
inputting the driving behavior data into a driving behavior scoring model to obtain a driving behavior score corresponding to the vehicle;
and determining the insurance premium according to the driving behavior score.
Preferably, the step of determining the insurance premium according to the driving behavior score includes:
obtaining mileage unit price according to the driving behavior score and the target mileage; the mileage unit price and the driving behavior score are positively correlated;
and determining the insurance premium corresponding to the target mileage according to the target mileage and mileage unit price.
Preferably, the driving behavior data includes at least one of a number of sudden acceleration per unit distance, a number of sudden avoidance, a number of sudden braking, and a duration of fatigue driving.
Preferably, the step of obtaining driving behavior data corresponding to the vehicle includes:
and acquiring driving behavior data corresponding to the vehicle through a block chain.
The invention also provides a system for generating the insurance premium, which is characterized by comprising the following steps:
the acquisition module is used for acquiring driving behavior data corresponding to the vehicle;
the scoring module is used for inputting the driving behavior data into a driving behavior scoring model so as to acquire a driving behavior score corresponding to the vehicle;
and the premium generation module is used for determining the insurance premium of the vehicle according to the driving behavior score.
Preferably, the unit price obtaining unit is used for obtaining mileage unit price according to the driving behavior score and the target mileage; the mileage unit price and the driving behavior score are positively correlated;
and the premium determining unit is used for determining the insurance premium corresponding to the target mileage according to the target mileage and mileage unit price.
Preferably, the driving behavior data includes at least one of a number of sudden acceleration per unit distance, a number of sudden avoidance, a number of sudden braking, and a duration of fatigue driving.
Preferably, the acquiring module is specifically configured to acquire driving behavior data corresponding to the vehicle through a blockchain.
The method and the system for generating the vehicle insurance premium, the electronic equipment and the storage medium have the advantages that through analysis of the driving behavior data corresponding to the vehicle, the risk level generated in the using process of the vehicle can be distinguished more accurately, the generated vehicle insurance premium is more reasonable, and the perception of a vehicle owner on the driving behavior of the vehicle owner can be improved through the vehicle insurance premium, so that unreasonable driving habits are improved.
Drawings
Fig. 1 is a flow chart of a method for generating a vehicle insurance premium according to embodiment 1 of the present invention.
Fig. 2 is a flow chart of a calculation process of the vehicle insurance premium according to embodiment 1 of the present invention.
Fig. 3 is a schematic block diagram of a system for generating a vehicle insurance premium according to embodiment 2 of the present invention.
Fig. 4 is a block diagram showing the structure of an electronic device according to embodiment 3 of the present invention.
Detailed Description
The invention is further illustrated by means of the following examples, which are not intended to limit the scope of the invention.
Example 1
Referring to fig. 1, the embodiment specifically provides a method for generating a vehicle insurance premium, including the steps of:
s1, driving behavior data corresponding to a vehicle are obtained.
S2, inputting driving behavior data into a driving behavior scoring model to obtain driving behavior scores corresponding to the vehicle;
s3, determining the insurance premium of the vehicle according to the driving behavior score.
The method and the device generate the vehicle insurance premium based on the driving behaviors corresponding to the vehicle, namely, the higher the driving behavior evaluation of the vehicle owner is, the smaller the driving risk is considered; accordingly, a lower insurance premium for the vehicle is determined.
In one example, the insurance premium of the present embodiment may be a current insurance premium directly generated according to the driving behavior of the previous period (for example, the previous year, the quarter, or a certain amount).
In another example, the current insurance premium may be divided into a first-term premium and a premium on a mileage basis. For example, the vehicle owner pays first an initial premium each year when buying the vehicle insurance, the initial premium comprising a certain mileage; after the first time of the limit is used up, the mileage limit is purchased according to the mileage unit price. Of course, the first-period premium may also be combined with the validity period to determine the actual underwriting period according to the mileage amount, for example, the running out of the mileage amount of the first-period premium or the expiration of the validity period is regarded as the corresponding underwriting responsibility termination.
For the first-period premium, the basic value premium of the first-period premium can be determined according to the traditional vehicle insurance pricing result, and the pay-per-sale proportion p is set first The first-period premium of the vehicle owner is premium p first . For the mileage limit corresponding to the first-period premium, the method can be based on the score mil of the annual mileage of the whole vehicle owner x To make the determination. For example, define x<50 years of mileage. Wherein the annual mileage of the whole car owner, i.e. the kilometers displayed by the current code table sensor/the actual vehicle age (year) of the car owner, e.g. mile 10 ,mile 20 ,…,mile 50 Respectively representing the fractional number of 10% -50% of the annual mileage of the whole vehicle owner, wherein, for example, the annual mileage is 50% of the mil of the whole vehicle owner 50 10000 km.
After the first-period premium is determined, purchasing mileage according to mileage unit price on the basis; the product of the mileage amount and the mileage unit price is the renewal premium, so that the renewal premium determines the final insurance premium on the basis of the first-period premium determination. Referring to fig. 2, a flow chart of a calculation process for the vehicle insurance premium described above is shown, in which a driving behavior scoring model may be used to score driving behavior data. It will be appreciated by those skilled in the art that the method for generating the vehicle insurance premium of the present embodiment may include, but is not limited to, determining a renewal premium. Furthermore, the above determination of the first-period premium is only one implementation, and does not impose any limitation on the inventive vehicle insurance premium generation method.
Specifically, step S1 obtains driving behavior data of the vehicle, and step S2 processes the driving behavior data through a driving behavior scoring model to obtain a driving behavior score corresponding to the vehicle.
The step S1 may be performed on a manually driven vehicle or a current hybrid automatic driving vehicle, that is, the driving behavior of the vehicle has both a manual driving behavior participated by a vehicle owner and a driving behavior automatically controlled by the vehicle. It will be appreciated that both should be processed separately in scoring the vehicle driving behaviour described above.
As a preferred embodiment, the driving behavior data includes, but is not limited to, the number of sudden acceleration per unit distance, the number of sudden avoidance, the number of sudden braking, and the duration of fatigue driving. The fatigue driving duration can be combined with a set fatigue driving duration threshold, and is obtained according to the judgment of the duration of continuous driving or the judgment of the duration of a manual driving mode in the intelligent vehicle, for example, the duration exceeding the fatigue driving duration threshold is 3 hours, and the fatigue driving is judged as exceeding the duration.
First, for the manual driving behavior, the control actions thereof on the vehicle body include drive control, brake control, and steering control.
In addition, along with the maturity of intelligent vehicle technology, the data when the vehicle is driven can be continuously obtained through various sensors that the configuration was passed through to the vehicle and the driving habit of car owner is analyzed based on this, and then the height of judgement car owner's driving behavior risk is followed. The difference between intelligent drive vehicles and conventional vehicles is the redundancy set up, for example by adding clutches, engine control units, redundant steering motors and force feedback. The direction and angle of steering wheel rotation is controlled by a decision system based on a deep learning model of road detection or driving patterns through information collected by a perception system.
The intelligent driving can send out corresponding prompts when manual driving and automatic driving are alternately performed, for example, a green light is used for indicating that the steering wheel is currently controlled for automatic driving; and blue light indicates that the steering wheel needs to be manually taken over. But even so, most drivers are required to place their hands on the steering wheel.
The steering control corresponds to a vehicle body control that changes the direction of the vehicle, i.e., a steering wheel control action that is generally understood. For a vehicle with an automatic steering function, when the vehicle is controlled by a person, the steering wheel is rotated by manual operation, steering data collected when the steering wheel is rotated can be used for judging parameters such as the steering amplitude and the like, so that a lane change scene implemented by manual behaviors is restored, and accordingly, the number of times of emergency avoidance per unit distance can be obtained based on the parameters.
The drive control corresponds to a body control action of the drive vehicle for achieving acceleration of the vehicle, i.e., a throttle action. The electronic accelerator converts the driving intention of a driver into an electronic signal through an electronic structure in a pedal, transmits the electronic signal to an engine controller through a bus, and adjusts a whole vehicle power system to achieve the driving purpose after the operation of the latter according to the whole vehicle working condition. The throttle opening of the electronic accelerator pedal is controlled by a motor, the acceleration intention is transmitted to an engine controller through a position sensor of the accelerator pedal, and the engine controller adjusts a throttle valve body through the motor. Meanwhile, the electronic throttle opening sensor feeds back the detected opening signal to the engine controller to realize closed-loop control of the electronic throttle opening. When the electronic accelerator is manually operated to step on the pedal, related parameters can be obtained, the vehicle body control action implemented by manual driving actions can be obtained based on the main parameters of the electronic accelerator, such as the acceleration intention signal, the position sensor parameter, the throttle opening signal and the like, the braking force value of corresponding operation is obtained, and further, parameters of acceleration and the like in the acceleration process are judged, and driving behavior data such as the number of rapid acceleration and the like in a unit distance are obtained.
The braking control corresponds to a braking action on the vehicle body, for example, in a manual driving operation by adopting an electronic brake, when an electronic brake pedal is stepped on, parameters such as the pressure of an electronic brake liquid can be obtained, so that a corresponding braking force value is obtained, and further parameters such as the acceleration in a deceleration process are judged, and driving behavior data such as the emergency braking times in a unit distance are obtained.
While for a vehicle in an autonomous driving mode, control of the vehicle is typically based on an autonomous driving instruction of the vehicle computing unit and is achieved by a drive-by-wire system. Finally, the vehicle body control such as acceleration, deceleration, steering and the like is realized. The vehicle computing unit is generally integrated in a TBOX (car box), and mainly generates an automatic driving instruction based on the integrated data obtained by processing the related algorithm based on a central processing unit, a graphic processor and a programmable chip architecture, so as to realize autonomous driving control of the vehicle. The device comprises a longitudinal control command and a transverse control command. Longitudinal control commands, i.e. speed control, include acceleration, deceleration related control commands, such as when to accelerate, when to decelerate, what the acceleration is, etc. The lateral control instructions are behavior control, how to change the lane, when to overtake, etc. Besides, the automatic driving instruction sent by the vehicle computing unit can control the gearbox and even the engine to complete the speed change and steering actions of the vehicle in a matching way.
In a preferred embodiment, step S1 may acquire driving behavior data corresponding to the vehicle through a blockchain. Blockchain networks are public networks that can provide low cost development, deployment, operation, interworking, and internet of vehicles applications. The blockchain application participant does not need to set a server or cloud service to build a blockchain running environment of the participant, and can realize the information of the Internet of vehicles only by setting an interface for accessing the blockchain network at the terminal or directly using unified service provided by the service network.
In this embodiment, the unique identifier of the vehicle, such as the frame number, the owner identification number, the corresponding insurance number of the vehicle, etc., may be obtained as an account number to log into the blockchain network. The parameter state information generated in the vehicle driving process is sent to the blockchain technology uplink in real time, and meanwhile, the encryption of the vehicle information can be ensured through the unique identification login. On the basis, the driving process of the vehicle can be traced back through a time axis according to the established authority, and the vehicle driving process information encrypted through the blockchain not only has the timestamp with high credibility, but also can avoid tampering, and the privacy of a vehicle owner is ensured. According to the method, the system and the device, the driving behavior data of the vehicle are obtained through the blockchain, the real-time transmission, confidentiality and retrospective transmission of the driving behavior data of the vehicle can be guaranteed, the confidence is high, and the follow-up processing is convenient.
Step S2, driving behavior data are input into a driving behavior scoring model to obtain driving behavior scores corresponding to the vehicle. Of course, the driving behavior scoring model may be implemented in the cloud by acquiring driving behavior data from a blockchain network, or may be a local or local area network server.
Wherein driving score calculation may include, but is not limited to, the following:
1) Driving behavior scoring model: inputting driving behavior data x 1 ,x 2 ,…,x n For example, the emergency acceleration times of hundred kilometers, the fatigue driving time of hundred kilometers and the like, to obtain the predicted value of the odds score of the vehicle owner's annual policy, namely, building a model f (x 1 ,x 2 ,…,x n )＝score。
2) Normalized model scoring: assume that each owner i gets a score by the above model i The method comprises the steps of carrying out a first treatment on the surface of the As shown in FIG. 2, the average odds of the historical policy of the owners of the population obtained from the claim data is a factor (typically 60% -80%), and the score is based on the above i Finding one or more owners with odds equal to or close to claim, and obtaining a driving behavior score corresponding to odds of claim based on the obtained driving behavior scores (if the odds of the owners are equal to or close to claim, the driving behavior scores of the owners can be processed by taking average, median and the like) claim . The score for each owner i is ultimately calculated as score i ＝score i /score claim I.e. the driving behaviour score of each vehicle owner is represented by a multiple of the score corresponding to the average odds.
In an alternative embodiment, step S3 includes:
s31, acquiring mileage unit price according to the driving behavior score and the target mileage; mileage unit price and driving behavior score are positively correlated;
s32, determining the insurance premium corresponding to the target mileage according to the target mileage and mileage unit price.
Calculating mileage unit price in step S31 may include, but is not limited to, the following:
assume that a vehicle owner has a score for current driving i Mileage unit price of premium renewal:
unitprice＝premium*max(0,g(score i )-p first ))/(mile 50 -mile x )。
where g () is a score adjustment function used to scale the distribution of scores and let g (score) i ) As much as possible greater than p first I.e., the first-payment proportion of the first-term premium. g () may take the form of ln (), sqrt (), (). Sup.n, etc.
Whereby mileage unit price and driving behavior score i And shows positive correlation. And updating mileage unit price each time using the current latest driving score of the vehicle owner.
Step S32 calculates a vehicle insurance premium, for example, determines a renewal premium based on mileage unit price and target mileage: t=unitprice. Further, in combination with the first-period premium, a vehicle insurance premium corresponding to the target mileage is determined.
The method of generating the vehicle insurance premium of the present embodiment is specifically described below by a vehicle insurance premium calculation process, but those skilled in the art will recognize that this calculation process does not constitute a limitation on the present method.
First, the first-term premium and mileage limit are determined: basic value premium=5000 yuan of insurance fee. First-order-of-charge ratio p first Calculated as 30%.
Assume that the overall vehicle owner has a fractional number of mils for annual mileage 30 ＝3000km；mile 50 ＝10000km。
The first-period premium of a certain vehicle is 5000 x 30% = 1500 yuan, and contains 3000km mileage;
the mileage amount is regarded as a period in each time, the user can be reminded of timely renewal before the amount is used up, renewal premium of the next period is calculated at the moment, and three-gear mileage amounts of 1000, 3000 and 5000km are provided.
Assuming that a certain vehicle has a month average mileage of 1000km, the mileage of 3000km is used up for 4 months, assuming that the driving behavior score at the time is 0.9, if 1000km is continuously purchased, the renewal premium is paid:
unitprice＝premium*max(0,g(score i )-p first ))/(mile 50 -mile x )
=5000 x (0.9-0.3)/(10000-3000) =429 yuan;
assuming that the 1000km credit is exhausted again by 5 months, at this time, assuming that the driving behavior score is reduced to 0.8, if 3000km is continuously purchased, a renewal premium is paid:
3 x 5000 x (0.8-0.3)/(10000-3000) =1071 yuan.
According to the method for generating the vehicle insurance premium, through analysis of the driving behavior data corresponding to the vehicle, the risk level generated in the using process of the vehicle can be distinguished more accurately, the generated vehicle insurance premium is more reasonable, and the perception of a vehicle owner on the driving behavior of the vehicle owner can be improved through the vehicle insurance premium, so that unreasonable driving habits are improved. Specifically, the first-period premium and the renewal premium are set, mileage unit price is determined by scoring driving behavior data in renewal premium calculation, premium differentiation of owners with different risks is achieved, and perception of the owners on the premium is enhanced by renewal based on mileage. In addition, through reasonably setting calculation parameters of mileage unit price, the risk that mileage unit price is difficult to calculate and premium may not be collected in the past is avoided. Finally, the driving behavior score of the vehicle owner is updated in real time and used for influencing the renewal price, so that the vehicle owner dynamically improves the driving behavior of the vehicle owner, and the accident rate is reduced.
Example 2
Referring to fig. 3, the embodiment specifically provides a system for generating a vehicle insurance premium, including:
the acquisition module 1 is used for acquiring driving behavior data corresponding to the vehicle;
the scoring module 2 is used for inputting the driving behavior data into a driving behavior scoring model so as to obtain the driving behavior score corresponding to the vehicle;
and the premium generation module 3 is used for determining the insurance premium of the vehicle according to the driving behavior score.
The method and the device generate the vehicle insurance premium based on the driving behaviors corresponding to the vehicle, namely, the higher the driving behavior evaluation of the vehicle owner is, the smaller the driving risk is considered; accordingly, a lower insurance premium for the vehicle is determined.
In one example, the insurance premium of the present embodiment may be a current insurance premium directly generated according to the driving behavior of the previous period (for example, the previous year, the quarter, or a certain amount).
In another example, the current insurance premium may be divided into a first-term premium and a premium on a mileage basis. For example, the vehicle owner pays first an initial premium each year when buying the vehicle insurance, the initial premium comprising a certain mileage; after the first time of the limit is used up, the mileage limit is purchased according to the mileage unit price. Of course, the first-period premium may also be combined with the validity period to determine the actual underwriting period according to the mileage amount, for example, the running out of the mileage amount of the first-period premium or the expiration of the validity period is regarded as the corresponding underwriting responsibility termination.
For the first-period premium, the basic value premium of the first-period premium can be determined according to the traditional vehicle insurance pricing result, and the pay-per-sale proportion p is set first The first-period premium of the vehicle owner is premium p first . For the mileage limit corresponding to the first-period premium, the method can be based on the score mil of the annual mileage of the whole vehicle owner x To make the determination. For example, define x<50 years of mileage. Wherein the annual mileage of the whole car owner, i.e. the kilometers displayed by the current code table sensor/the actual vehicle age (year) of the car owner, e.g. mile 10 ,mile 20 ,…,mile 50 Respectively representing the fractional number of 10% -50% of the annual mileage of the whole vehicle owner, wherein, for example, the annual mileage is 50% of the mil of the whole vehicle owner 50 10000 km.
After the first-period premium is determined, purchasing mileage according to mileage unit price on the basis; the product of the mileage amount and the mileage unit price is the renewal premium, so that the renewal premium determines the final insurance premium on the basis of the first-period premium determination. Referring to fig. 2, a flow chart of a calculation process for the vehicle insurance premium described above is shown, in which a driving behavior scoring model may be used to score driving behavior data. It will be appreciated by those skilled in the art that the method for generating the vehicle insurance premium of the present embodiment may include, but is not limited to, determining a renewal premium. Furthermore, the above determination of the first-period premium is only one implementation, and does not impose any limitation on the inventive vehicle insurance premium generation method.
Specifically, the acquiring module 1 acquires driving behavior data of the vehicle, and the scoring module 2 processes the driving behavior data through a driving behavior scoring model to acquire a driving behavior score corresponding to the vehicle.
The acquiring module 1 may process the driving behavior data of the vehicle according to a manually driven vehicle or a current hybrid automatic driving vehicle, that is, the driving behavior of the vehicle has both a manual driving behavior participated by a vehicle owner and a driving behavior automatically controlled by the vehicle. It will be appreciated that both should be processed separately in scoring the vehicle driving behaviour described above.
As a preferred embodiment, the driving behavior data includes, but is not limited to, the number of sudden acceleration per unit distance, the number of sudden avoidance, the number of sudden braking, and the duration of fatigue driving. The fatigue driving duration can be combined with a set fatigue driving duration threshold, and is obtained according to the judgment of the duration of continuous driving or the judgment of the duration of a manual driving mode in the intelligent vehicle, for example, the duration exceeding the fatigue driving duration threshold is 3 hours, and the fatigue driving is judged as exceeding the duration.
First, for the manual driving behavior, the control actions thereof on the vehicle body include drive control, brake control, and steering control.
In addition, along with the maturity of intelligent vehicle technology, the data when the vehicle is driven can be continuously obtained through various sensors that the configuration was passed through to the vehicle and the driving habit of car owner is analyzed based on this, and then the height of judgement car owner's driving behavior risk is followed. The difference between intelligent drive vehicles and conventional vehicles is the redundancy set up, for example by adding clutches, engine control units, redundant steering motors and force feedback. The direction and angle of steering wheel rotation is controlled by a decision system based on a deep learning model of road detection or driving patterns through information collected by a perception system.
The intelligent driving can send out corresponding prompts when manual driving and automatic driving are alternately performed, for example, a green light is used for indicating that the steering wheel is currently controlled for automatic driving; and blue light indicates that the steering wheel needs to be manually taken over. But even so, most drivers are required to place their hands on the steering wheel.
The steering control corresponds to a vehicle body control that changes the direction of the vehicle, i.e., a steering wheel control action that is generally understood. For a vehicle with an automatic steering function, when the vehicle is controlled by a person, the steering wheel is rotated by manual operation, steering data collected when the steering wheel is rotated can be used for judging parameters such as the steering amplitude and the like, so that a lane change scene implemented by manual behaviors is restored, and accordingly, the number of times of emergency avoidance per unit distance can be obtained based on the parameters.
The drive control corresponds to a body control action of the drive vehicle for achieving acceleration of the vehicle, i.e., a throttle action. The electronic accelerator converts the driving intention of a driver into an electronic signal through an electronic structure in a pedal, transmits the electronic signal to an engine controller through a bus, and adjusts a whole vehicle power system to achieve the driving purpose after the operation of the latter according to the whole vehicle working condition. The throttle opening of the electronic accelerator pedal is controlled by a motor, the acceleration intention is transmitted to an engine controller through a position sensor of the accelerator pedal, and the engine controller adjusts a throttle valve body through the motor. Meanwhile, the electronic throttle opening sensor feeds back the detected opening signal to the engine controller to realize closed-loop control of the electronic throttle opening. When the electronic accelerator is manually operated to step on the pedal, related parameters can be obtained, the vehicle body control action implemented by manual driving actions can be obtained based on the main parameters of the electronic accelerator, such as the acceleration intention signal, the position sensor parameter, the throttle opening signal and the like, the braking force value of corresponding operation is obtained, and further, parameters of acceleration and the like in the acceleration process are judged, and driving behavior data such as the number of rapid acceleration and the like in a unit distance are obtained.
The braking control corresponds to a braking action on the vehicle body, for example, in a manual driving operation by adopting an electronic brake, when an electronic brake pedal is stepped on, parameters such as the pressure of an electronic brake liquid can be obtained, so that a corresponding braking force value is obtained, and further parameters such as the acceleration in a deceleration process are judged, and driving behavior data such as the emergency braking times in a unit distance are obtained.
While for a vehicle in an autonomous driving mode, control of the vehicle is typically based on an autonomous driving instruction of the vehicle computing unit and is achieved by a drive-by-wire system. Finally, the vehicle body control such as acceleration, deceleration, steering and the like is realized. The vehicle computing unit is generally integrated in the TBOX, and mainly generates an automatic driving instruction based on the integrated data obtained by processing the related algorithm based on the central processing unit, the graphic processor and the programmable chip architecture, so as to realize autonomous driving control of the vehicle. The device comprises a longitudinal control command and a transverse control command. Longitudinal control commands, i.e. speed control, include acceleration, deceleration related control commands, such as when to accelerate, when to decelerate, what the acceleration is, etc. The lateral control instructions are behavior control, how to change the lane, when to overtake, etc. Besides, the automatic driving instruction sent by the vehicle computing unit can control the gearbox and even the engine to complete the speed change and steering actions of the vehicle in a matching way.
As a preferred embodiment, the acquiring module 1 may acquire driving behavior data corresponding to the vehicle through a blockchain. Blockchain networks are public networks that can provide low cost development, deployment, operation, interworking, and internet of vehicles applications. The blockchain application participant does not need to set a server or cloud service to build a blockchain running environment of the participant, and can realize the information of the Internet of vehicles only by setting an interface for accessing the blockchain network at the terminal or directly using unified service provided by the service network.
In this embodiment, the unique identifier of the vehicle, such as the frame number, the owner identification number, the corresponding insurance number of the vehicle, etc., may be obtained as an account number to log into the blockchain network. The parameter state information generated in the vehicle driving process is sent to the blockchain technology uplink in real time, and meanwhile, the encryption of the vehicle information can be ensured through the unique identification login. On the basis, the driving process of the vehicle can be traced back through a time axis according to the established authority, and the vehicle driving process information encrypted through the blockchain not only has the timestamp with high credibility, but also can avoid tampering, and the privacy of a vehicle owner is ensured. According to the method, the system and the device, the driving behavior data of the vehicle are obtained through the blockchain, the real-time transmission, confidentiality and retrospective transmission of the driving behavior data of the vehicle can be guaranteed, the confidence is high, and the follow-up processing is convenient.
The scoring module 2 inputs the driving behavior data into a driving behavior scoring model to obtain a driving behavior score corresponding to the vehicle. Of course, the driving behavior scoring model may be implemented in the cloud by acquiring driving behavior data from a blockchain network, or may be a local or local area network server.
Wherein driving score calculation may include, but is not limited to, the following:
1) Driving behavior scoring model: inputting driving behavior data x 1 ,x 2 ,…,x n For example, the emergency acceleration times of hundred kilometers, the fatigue driving time of hundred kilometers and the like, to obtain the predicted value of the odds score of the vehicle owner's annual policy, namely, building a model f (x 1 ,x 2 ,…,x n )＝score。
2) Normalized model scoring: assume that each owner i gets a score by the above model i The method comprises the steps of carrying out a first treatment on the surface of the As shown in FIG. 2, the average odds of the historical policy of the owners of the population obtained from the claim data is a factor (typically 60% -80%), and the score is based on the above i Finding one or more owners with odds equal to or close to claim, and obtaining a driving behavior score corresponding to odds of claim based on the obtained driving behavior scores (if the odds of the owners are equal to or close to claim, the driving behavior scores of the owners can be processed by taking average, median and the like) claim . The score for each owner i is ultimately calculated as score i ＝score i /score claim I.e. the driving behavior of each vehicle owner is scored corresponding to the average oddsIs expressed as a multiple of (a).
In an alternative embodiment, the premium generation module 3 includes:
a unit price acquisition unit 31 for acquiring mileage unit price based on the driving behavior score and the target mileage; mileage unit price and driving behavior score are positively correlated;
and a premium determination unit 32 for determining a premium for the vehicle insurance corresponding to the target mileage according to the target mileage and mileage unit price.
The unit price obtaining unit 31 calculates mileage unit price may include, but is not limited to, the following ways:
assume that a vehicle owner has a score for current driving i Mileage unit price of premium renewal:
unitprice＝premium*max(0,g(score i )-p first ))/(mile 50 -mile x )。
where g () is a score adjustment function used to scale the distribution of scores and let g (score) i ) As much as possible greater than p first I.e., the first-payment proportion of the first-term premium. g () may take the form of ln (), sqrt (), (). Sup.n, etc.
Whereby mileage unit price and driving behavior score i And shows positive correlation. And updating mileage unit price each time using the current latest driving score of the vehicle owner.
The premium determination unit 32 calculates a vehicle insurance premium, for example, determines the vehicle insurance premium based on mileage unit price and target mileage: t=unitprice. Further, in combination with the first-period premium, a vehicle insurance premium corresponding to the target mileage is determined.
The method of generating the vehicle insurance premium of the present embodiment is specifically described below by a vehicle insurance premium calculation process, but those skilled in the art will recognize that this calculation process does not constitute a limitation on the present method.
First, the first-term premium and mileage limit are determined: basic value premium=5000 yuan of insurance fee. First-order-of-charge ratio p first Calculated as 30%.
Assume that the overall vehicle owner has a fractional number of mils for annual mileage 30 ＝3000km；mile 50 ＝10000km。
The first-period premium of a certain vehicle is 5000 x 30% = 1500 yuan, and contains 3000km mileage;
the mileage amount is regarded as a period in each time, the user can be reminded of timely renewal before the amount is used up, renewal premium of the next period is calculated at the moment, and three-gear mileage amounts of 1000, 3000 and 5000km are provided.
Assuming that a certain vehicle has a month average mileage of 1000km, the mileage of 3000km is used up for 4 months, assuming that the driving behavior score at the time is 0.9, if 1000km is continuously purchased, the renewal premium is paid:
unitprice＝premium*max(0,g(score i )-p first ))/(mile 50 -mile x )
=5000 x (0.9-0.3)/(10000-3000) =429 yuan;
assuming that the 1000km credit is exhausted again by 5 months, at this time, assuming that the driving behavior score is reduced to 0.8, if 3000km is continuously purchased, a renewal premium is paid:
3 x 5000 x (0.8-0.3)/(10000-3000) =1071 yuan.
The system for generating the vehicle insurance premium in the embodiment can more accurately distinguish the risk level generated in the using process of the vehicle through analyzing the driving behavior data corresponding to the vehicle, the generated vehicle insurance premium is more reasonable, and the perception of a vehicle owner to the driving behavior of the vehicle owner can be improved through the vehicle insurance premium, so that unreasonable driving habits are improved. Specifically, the first-period premium and the renewal premium are set, mileage unit price is determined by scoring driving behavior data in renewal premium calculation, premium differentiation of owners with different risks is achieved, and perception of the owners on the premium is enhanced by renewal based on mileage. In addition, through reasonably setting calculation parameters of mileage unit price, the risk that mileage unit price is difficult to calculate and premium may not be collected in the past is avoided. Finally, the driving behavior score of the vehicle owner is updated in real time and used for influencing the renewal price, so that the vehicle owner dynamically improves the driving behavior of the vehicle owner, and the accident rate is reduced.
Example 3
Fig. 4 is a schematic structural diagram of an electronic device according to embodiment 3 of the present invention. The electronic device includes a memory, a processor, and a computer program stored on the memory and executable on the processor, and the processor implements the vehicle insurance premium generation method in embodiment 1 when executing the program. The electronic device 30 shown in fig. 4 is merely an example and should not be construed as limiting the functionality and scope of use of embodiments of the present invention.
As shown in fig. 4, the electronic device 30 may be embodied in the form of a general purpose computing device, which may be a server device, for example. Components of electronic device 30 may include, but are not limited to: the at least one processor 31, the at least one memory 32, a bus 33 connecting the different system components, including the memory 32 and the processor 31.
The bus 33 includes a data bus, an address bus, and a control bus.
Memory 32 may include volatile memory such as Random Access Memory (RAM) 321 and/or cache memory 322, and may further include Read Only Memory (ROM) 323.
Memory 32 may also include a program/utility 325 having a set (at least one) of program modules 324, such program modules 324 including, but not limited to: an operating system, one or more application programs, other program modules, and program data, each or some combination of which may include an implementation of a network environment.
The processor 31 executes various functional applications and data processing, such as a vehicle insurance premium generation method in embodiment 1 of the present invention, by executing a computer program stored in the memory 32.
The electronic device 30 may also communicate with one or more external devices 34 (e.g., keyboard, pointing device, etc.). Such communication may be through an input/output (I/O) interface 35. Also, model-generating device 30 may also communicate with one or more networks, such as a Local Area Network (LAN), a Wide Area Network (WAN), and/or a public network, such as the internet, via network adapter 36. As shown in fig. 4, network adapter 36 communicates with the other modules of model-generating device 30 via bus 33. It should be appreciated that although not shown in the figures, other hardware and/or software modules may be used in connection with the model-generating device 30, including, but not limited to: microcode, device drivers, redundant processors, external disk drive arrays, RAID (disk array) systems, tape drives, data backup storage systems, and the like.
It should be noted that although several units/modules or sub-units/modules of an electronic device are mentioned in the above detailed description, such a division is merely exemplary and not mandatory. Indeed, the features and functionality of two or more units/modules described above may be embodied in one unit/module in accordance with embodiments of the present invention. Conversely, the features and functions of one unit/module described above may be further divided into ones that are embodied by a plurality of units/modules.
Example 4
The present embodiment provides a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements the steps in the vehicle insurance premium generation method in embodiment 1.
More specifically, among others, readable storage media may be employed including, but not limited to: portable disk, hard disk, random access memory, read only memory, erasable programmable read only memory, optical storage device, magnetic storage device, or any suitable combination of the foregoing.
In a possible embodiment, the invention may also be implemented in the form of a program product comprising program code for causing a terminal device to carry out the steps of the method for generating a vehicle insurance premium in embodiment 1, when the program product is run on the terminal device.
Wherein the program code for carrying out the invention may be written in any combination of one or more programming languages, the program code may execute entirely on the user device, partly on the user device, as a stand-alone software package, partly on the user device, partly on a remote device or entirely on the remote device.
While specific embodiments of the invention have been described above, it will be appreciated by those skilled in the art that this is by way of example only, and the scope of the invention is defined by the appended claims. Various changes and modifications to these embodiments may be made by those skilled in the art without departing from the principles and spirit of the invention, but such changes and modifications fall within the scope of the invention.
Claims (8)
1. A method for generating a vehicle insurance premium, the method comprising the steps of:
acquiring driving behavior data corresponding to a vehicle; the driving behavior of the vehicle includes a manual driving behavior and a vehicle automatic driving behavior;
inputting the driving behavior data into a driving behavior scoring model to obtain a driving behavior score corresponding to the vehicle;
determining the insurance premium according to the driving behavior score;
the step of determining the insurance premium according to the driving behavior score includes:
obtaining mileage unit price according to the driving behavior score and the target mileage; the mileage unit price and the driving behavior score are positively correlated;
and determining the insurance premium corresponding to the target mileage according to the target mileage and mileage unit price.
2. The method for generating a vehicle insurance premium of claim 1, wherein the driving behavior data includes at least one of a number of rapid acceleration per unit distance, a number of emergency avoidance per unit distance, a number of emergency braking per unit distance, and a duration of fatigue driving.
3. The method for generating a vehicle insurance premium as claimed in claim 1 or 2, wherein said step of acquiring driving behavior data corresponding to the vehicle includes:
and acquiring driving behavior data corresponding to the vehicle through a block chain.
4. A system for generating a vehicle insurance premium, said system comprising:
the acquisition module is used for acquiring driving behavior data corresponding to the vehicle; the driving behavior of the vehicle includes a manual driving behavior and a vehicle automatic driving behavior;
the scoring module is used for inputting the driving behavior data into a driving behavior scoring model so as to acquire a driving behavior score corresponding to the vehicle;
the premium generation module is used for determining the insurance premium of the vehicle according to the driving behavior score;
the premium generation module includes:
a unit price obtaining unit for obtaining mileage unit price according to the driving behavior score and the target mileage; the mileage unit price and the driving behavior score are positively correlated;
and the premium determining unit is used for determining the insurance premium corresponding to the target mileage according to the target mileage and mileage unit price.
5. The method of claim 4, wherein the driving behavior data includes at least one of a number of rapid acceleration per unit distance, a number of emergency avoidance per unit distance, a number of emergency braking per unit distance, and a length of time for fatigue driving.
6. The method for generating a vehicle insurance premium as claimed in claim 4 or 5, wherein the acquiring module is specifically configured to acquire driving behavior data corresponding to the vehicle through a blockchain.
7. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the method of generating a vehicle insurance premium of any of claims 1-3 when the computer program is executed by the processor.
8. A computer-readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the method of generating a vehicle insurance premium of any of claims 1 to 3.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110947067.6A CN113781244B (en) | 2021-08-18 | 2021-08-18 | Method and system for generating insurance premium, electronic device and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110947067.6A CN113781244B (en) | 2021-08-18 | 2021-08-18 | Method and system for generating insurance premium, electronic device and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113781244A CN113781244A (en) | 2021-12-10 |
| CN113781244B true CN113781244B (en) | 2023-12-01 |
Family
ID=78838165
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110947067.6A Active CN113781244B (en) | 2021-08-18 | 2021-08-18 | Method and system for generating insurance premium, electronic device and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113781244B (en) |
Citations (6)
| 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 |
| KR102082680B1 (en) * | 2019-07-26 | 2020-05-29 | 캐롯손해보험 주식회사 | Automated system for estimating insurance premium based on trip information of vehicle |
| CN112039956A (en) * | 2020-08-13 | 2020-12-04 | 宜宾凯翼汽车有限公司 | Driving data-based vehicle insurance data monitoring and processing system and method |
| CN112613998A (en) * | 2020-12-16 | 2021-04-06 | 深圳市麦谷科技有限公司 | Vehicle insurance premium pricing method and system based on driving behavior scoring model |
| CN112712318A (en) * | 2020-12-31 | 2021-04-27 | 优车库网络科技发展(深圳)有限公司 | Information processing method, information processing device, computer equipment and storage medium |
| US10997662B1 (en) * | 2014-10-24 | 2021-05-04 | State Farm Mutual Automobile Insurance Company | Targeted messaging process |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US11661073B2 (en) * | 2018-08-23 | 2023-05-30 | Hartford Fire Insurance Company | Electronics to remotely monitor and control a machine via a mobile personal communication device |
-
2021
- 2021-08-18 CN CN202110947067.6A patent/CN113781244B/en active Active
Patent Citations (7)
| 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 |
| US10109013B1 (en) * | 2005-01-18 | 2018-10-23 | Allstate Insurance Company | Usage-based insurance cost determination system and method |
| US10997662B1 (en) * | 2014-10-24 | 2021-05-04 | State Farm Mutual Automobile Insurance Company | Targeted messaging process |
| KR102082680B1 (en) * | 2019-07-26 | 2020-05-29 | 캐롯손해보험 주식회사 | Automated system for estimating insurance premium based on trip information of vehicle |
| CN112039956A (en) * | 2020-08-13 | 2020-12-04 | 宜宾凯翼汽车有限公司 | Driving data-based vehicle insurance data monitoring and processing system and method |
| CN112613998A (en) * | 2020-12-16 | 2021-04-06 | 深圳市麦谷科技有限公司 | Vehicle insurance premium pricing method and system based on driving behavior scoring model |
| CN112712318A (en) * | 2020-12-31 | 2021-04-27 | 优车库网络科技发展(深圳)有限公司 | Information processing method, information processing device, computer equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113781244A (en) | 2021-12-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP7371359B2 (en) | Digital twin for vehicle risk assessment | |
| US9747730B2 (en) | Driver measurement and incentive system for improving fuel-efficiency | |
| US11900738B2 (en) | Systems and methods to obtain feedback in response to autonomous vehicle failure events | |
| US10346888B2 (en) | Systems and methods to obtain passenger feedback in response to autonomous vehicle driving events | |
| US10210479B2 (en) | Computerized sysem and method for data acquistion and application of disparate data to two stage bayesian networks to generate centrally maintained portable driving score data | |
| WO2017168883A1 (en) | Information processing device, information processing method, program, and system | |
| US11657318B2 (en) | Assessing ride quality for autonomous vehicles | |
| EP3710327A1 (en) | Software validation for autonomous vehicles | |
| US20230008123A1 (en) | Systems and methods for providing multiple carbon offset sources | |
| US20220242448A1 (en) | Method, apparatus and device for determining behavioral driving habit and controlling vehicle driving | |
| CN107368069A (en) | The generation method and generating means of automatic Pilot control strategy based on car networking | |
| CN110920539A (en) | Vehicle driving analysis method and device, electronic device and computer storage medium | |
| CN114030475A (en) | Vehicle driving assisting method and device, vehicle and storage medium | |
| CN111047047A (en) | Driving model training method and device, electronic equipment and computer storage medium | |
| CN113781244B (en) | Method and system for generating insurance premium, electronic device and storage medium | |
| WO2023045791A1 (en) | Lane keeping method and apparatus, device, medium, and system | |
| CN114103966A (en) | Control method, device and system for driving assistance | |
| US20230267491A1 (en) | Systems and methods for managing insurance | |
| Galvani | Optimal-control-based ADAS for driver warning and autonomous intervention using manoeuvre jerks for risk assessment | |
| CN117549911A (en) | Driving behavior auxiliary correction method and system and electronic equipment | |
| CN116946150A (en) | Optimization method of automobile anti-collision early warning model based on driver characteristics | |
| Liang et al. | Analyzing Rear-End Collision Risk Relevant to Autonomous Vehicles by Using a Humanlike Brake Model | |
| CN115979679A (en) | Method, apparatus and storage medium for testing actual road of automatic driving system | |
| CN115695418A (en) | Information processing method and device, electronic device and storage medium |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |