CN111598664A - Price forecasting method and device based on vehicle information identification - Google Patents
Price forecasting method and device based on vehicle information identification Download PDFInfo
- Publication number
- CN111598664A CN111598664A CN202010419773.9A CN202010419773A CN111598664A CN 111598664 A CN111598664 A CN 111598664A CN 202010419773 A CN202010419773 A CN 202010419773A CN 111598664 A CN111598664 A CN 111598664A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- price
- insurance
- premium
- risk
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
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
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0611—Request for offers or quotes
-
- 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
Abstract
The application discloses a price forecasting method and device based on vehicle information identification, and the method comprises the following steps: acquiring vehicle information, and acquiring real-time data of a current vehicle according to the vehicle information; and substituting the real-time data into the trained pre-quoted price model to calculate the forecast price premium. The method and the device can directly acquire the real-time information of the current vehicle of the vehicle owner through the vehicle information, and automatically calculate the pre-insurance premium of the vehicle owner according to the forecast price model, so that premium information meeting the intention of the vehicle owner is acquired; in addition, corresponding adjustment can be performed according to the current requirements of the car owner, and the insurance business requirements can be quickly and efficiently completed.
Description
Technical Field
The application relates to the technical field of information identification, in particular to a price forecasting method and device based on vehicle information identification.
Background
At present, most insurance companies have vehicle insurance services, and because the vehicle insurance selling period is 30 days before the vehicle insurance is due, the insurance companies can only quote and check in the selling period, and the vehicle insurance quotation which is 30 days ahead is called as pre-quotation. In order to meet the demand of the car washing beauty shop for the price forecast, the car insurance price forecast capability is needed as the support of the car insurance sales business.
The existing insurance companies with price forecasting capability in the market are very few, the information provided by the vehicle owner is very complicated, and the predicted numerical error is large; in addition, most insurance companies support pre-quotes for up to 60 days. The application scene of the model is as follows: when a car enters a beauty shop, a shop owner can capture car information (such as a license plate number) through a camera to know the price range of the car insurance of the car owner in the next year, and important reference information is provided for the shop owner to sell the car insurance.
Disclosure of Invention
The embodiment of the application provides a price forecasting method and device based on vehicle information identification, so that vehicle information of a vehicle owner is directly obtained through the vehicle information, and the pre-paid premium of the vehicle owner is automatically calculated according to a price forecasting model.
In view of the above, a first aspect of the present application provides a forecast price method based on vehicle information identification, the method including:
acquiring vehicle information, and acquiring real-time data of a current vehicle according to the vehicle information;
and substituting the real-time data into the trained pre-quotation model to calculate the forecast premium.
Optionally, substituting the real-time data into the trained pre-quoted price model, and before calculating the forecast premium, further comprising:
acquiring vehicle historical data;
and training the forecast price model by using the vehicle historical data.
Optionally, after the acquiring the vehicle history data, the method further includes:
and preprocessing the vehicle historical data.
Optionally, the preprocessing the vehicle history data specifically includes:
data cleaning: clearing 0 data and abnormal value data in the vehicle historical data;
data arrangement: merging the vehicle data and the vehicle insurance data in the vehicle historical data, and classifying different sub-dangerous species data in the business insurance;
feature extraction: and clustering the historical data of the vehicles by using a clustering algorithm, observing the structure of the clustered data, and determining the threshold value of the classification interval.
Optionally, substituting the real-time data into the trained pre-quotation model, and calculating the pre-quotation premium specifically comprises:
s1: judging whether the use property of the current vehicle is a household automobile or not according to the real-time data of the current vehicle;
s2: inputting the purchase price, seat number, service life and/or insurance quota of the new vehicle in the real-time data of the current vehicle into trained pre-quotation models corresponding to various dangerous species, and calculating to obtain quotations of the various dangerous species;
s3: and acquiring a parameter set of the commercial risk sub-risk purchased by the current vehicle and an exemption parameter set whether to purchase the commercial risk sub-risk, and calculating a total commercial risk price according to the sub-risk parameter set, the exemption parameter set and the sets of various risk prices calculated in S2.
Optionally, the step of inputting the purchase price, seat number, vehicle age and/or insurance quota of the new vehicle in the real-time data of the current vehicle into trained pre-quoted price models corresponding to various dangerous categories, and the calculation of the quoted price of each dangerous category specifically includes:
s21: classifying premium intervals according to the purchase price, seat number and service years of the vehicle in the real-time data of the current vehicle, and determining the premium intervals of the forced insurance of the responsibility of the motor vehicle traffic accident; determining the insurance price of the forced insurance of the responsibility of the motor vehicle traffic accident according to the current new vehicle purchase price, seat number and premium interval of the service years of the vehicle;
s22: bringing the purchase price, seat number and service year of the new vehicle of the current vehicle into a trained vehicle damage risk forecasting price model, and calculating to obtain the insurance application price of the vehicle damage risk;
s23: classifying premium intervals according to the purchase price, seat number and service years of the vehicle of the new vehicle in the real-time data of the current vehicle, determining the premium interval of the third party responsibility insurance, and calculating the insurance application price of the third party responsibility insurance according to the premium interval and a third party responsibility insurance forecast price model corresponding to the premium interval;
s24: bringing the purchase price, the seat number and the service years of the new vehicle of the current vehicle into a trained theft emergency forecasting price model, and calculating to obtain the insurance price of the theft emergency;
s25: judging whether the current vehicle is an import vehicle, if so, bringing the purchase price, seat number and service life of the new vehicle of the current vehicle into a trained import glass risk forecast price model to obtain the insurance price of the import glass risk; otherwise, bringing the new vehicle purchase price, the seat number and the service years of the vehicle of the current vehicle into the trained national glass insurance forecast price model to obtain the insurance price of the national glass insurance;
s26: substituting the new vehicle purchase price, the seat number and the service year of the current vehicle into the trained self-ignition risk forecast price model and the water risk pre-quotation model to respectively obtain the self-ignition risk price and the water risk insurance investment price of the current vehicle;
s27: classifying premium intervals according to the purchase price, seat number and service years of the vehicle in the real-time data of the current vehicle, determining the premium intervals of the scratch insurance, and substituting the insurance quota into a scratch insurance forecast price model corresponding to the premium intervals of the scratch insurance to obtain the insurance price of the scratch insurance;
s28: and classifying premium intervals according to the purchase price, seat number and service years of the vehicle of the new vehicle in the real-time data of the current vehicle, determining the premium intervals of the on-board personnel liability insurance, and substituting the insurance quota into an on-board personnel liability insurance forecast price model corresponding to the on-board personnel liability insurance premium intervals to obtain the insurance price of the on-board personnel liability insurance.
Optionally, the pre-quotation model specifically includes:
linear regression model Y β0+β1x1+β2x2+β3x3+
Or
Polynomial regression model Y β0+β1x1+β2x2+β0x3+β3x1x2+β4x1x2+β5x2x3+β6x2x3+0
In the formula, the purchase price x of the new vehicle1Number of seats x2Number of years of use x3Y is the output prediction premium, β is the model coefficient, which is different depending on the risk.
A second aspect of the present application provides a price forecasting apparatus based on vehicle information identification, the apparatus including:
the information acquisition unit is used for acquiring vehicle information and acquiring real-time data of a current vehicle according to the vehicle information;
and the premium calculation unit is used for substituting the real-time data into the trained pre-quotation model to calculate the forecast premium.
Optionally, the preprocessing unit further includes:
the data cleaning unit is used for clearing 0 data in the historical data and clearing abnormal value data;
and the data integral unit is used for combining the vehicle data and the vehicle insurance data and classifying different sub-dangerous type data in the business insurance.
Optionally, the method further includes:
and the model training unit is used for acquiring vehicle historical data and training the forecast price model by adopting the vehicle historical data.
The model training unit further comprises:
and the preprocessing unit is used for preprocessing the vehicle historical data.
According to the technical scheme, the method has the following advantages:
the embodiment of the application provides a price forecasting method and device based on vehicle information identification, and the method comprises the steps of obtaining vehicle information and obtaining real-time data of a current vehicle according to the vehicle information; and substituting the real-time data into the trained pre-quoted price model to calculate the forecast price premium.
The method and the device can directly acquire the real-time information of the current vehicle of the vehicle owner through the vehicle information, and automatically calculate the pre-insurance premium of the vehicle owner according to the forecast price model, so that premium information meeting the intention of the vehicle owner is acquired; in addition, corresponding adjustment can be performed according to the current requirements of the car owner, and the insurance business requirements can be quickly and efficiently completed.
Drawings
FIG. 1 is a method diagram of one embodiment of a predictive pricing method based on vehicle information identification of the present application;
FIG. 2 is a method diagram of another embodiment of a forecasted price method based on vehicle information identification of the present application;
fig. 3 is a schematic structural diagram of an embodiment of a price forecasting device based on vehicle information identification according to the present application.
Detailed Description
The method and the device can directly acquire the real-time information of the current vehicle of the vehicle owner through the vehicle information, and automatically calculate the pre-insurance premium of the vehicle owner according to the forecast price model, so that premium information meeting the intention of the vehicle owner is acquired; in addition, corresponding adjustment can be performed according to the current requirements of the car owner, and the insurance business requirements can be quickly and efficiently completed.
In order to make the technical solutions of the present application better understood, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
Referring to fig. 1, fig. 1 is a method diagram of an embodiment of a price forecasting method based on vehicle information identification according to the present application, as shown in fig. 1, where fig. 1 includes:
101. and acquiring vehicle information, and acquiring real-time data of the current vehicle according to the vehicle information.
It should be noted that the acquired vehicle information may be acquired by a camera of a car washing and beauty shop, or may be manually input by a car owner; the past year insurance information of the current vehicle and the vehicle information can be obtained according to the vehicle information, wherein the past year insurance information comprises the insurance type and the insurance amount participated by the past year owner, and the vehicle information comprises the use property (whether the vehicle is used at home), the country or import and the like of the vehicle.
102. And substituting the real-time data into the trained pre-quoted price model to calculate the forecast price premium.
It should be noted that, a forecast price model is established according to existing data of the current vehicle, including previous year insurance information of the vehicle and vehicle information, wherein the forecast price model can obtain a corresponding forecast price model of each risk according to a linear regression method, for example, for the vehicle damage, a linear regression formula related to the vehicle damage forecast price premium can be obtained by fitting according to the relationship between the vehicle damage in the previous year vehicle history data and other parameters of the vehicle, so that the vehicle damage forecast price premium of the vehicle can be solved according to other currently known parameters of the vehicle. The real-time data of the current vehicle is brought into the vehicle damage forecast price model, so that the vehicle damage forecast price premium meeting the will of the vehicle owner can be quickly calculated.
According to the method and the device, the real-time data of the current vehicle of the vehicle owner can be directly obtained through the vehicle information, and the pre-insurance premium of the vehicle owner is automatically calculated according to the forecast price model, so that the premium information meeting the intention of the vehicle owner is obtained.
For easy understanding, please refer to fig. 2, fig. 2 is a method diagram of another embodiment of a price forecasting method based on vehicle information identification according to the present application, and as shown in fig. 2, the method specifically includes:
201. and acquiring vehicle information, and acquiring real-time data of the current vehicle according to the vehicle information.
It should be noted that the acquired vehicle information may be acquired by a camera of a car washing and beauty shop, or may be manually input by a car owner; insurance information and vehicle information corresponding to the past year of the vehicle can be obtained according to the vehicle information, wherein the past year insurance information comprises insurance types and insurance amounts participated by past year owners, and the vehicle information comprises the use properties (whether the vehicles are used at home), the home or import.
In a specific embodiment, the data with the highest occurrence frequency of the insurance types and the insurance amounts in the past year insurance information can be selected as the insurance information of the present year, for example, the parameter with the highest occurrence frequency in the non-exempting parameters of the business risk sub-risk categories and the business risk sub-risk categories of the past year insurance of the vehicle is selected as the non-exempting parameters of the business risk sub-risk categories and the business risk sub-risk categories of the present year.
202. And judging whether the use property of the vehicle is a household automobile or not according to the historical data corresponding to the vehicle.
It should be noted that the history data includes vehicle information, wherein the vehicle information also includes vehicle usage properties, so that it may be determined whether the vehicle is a home automobile first, and in one embodiment, only the home automobile is pre-quoted.
203. And inputting the purchase price, seat number, service year and/or insurance quota of the new vehicle in the vehicle historical data into trained pre-quotation models corresponding to various dangerous types, and calculating to obtain quotations of the various dangerous types.
It should be noted that, the process of obtaining the pre-quotation model includes:
2031. vehicle history data is acquired.
In the present application, it is necessary to acquire a large amount of vehicle history data and train the forecast price model, so as to obtain the forecast price models of various vehicle risks with relatively convergence and high accuracy. The acquired vehicle history data comprises the purchase price of the new vehicle, seat number, service years of the vehicle, insurance quota and the like.
2032. And preprocessing the historical data.
It should be noted that, the preprocessing of the historical data includes data cleaning: clearing 0 data in historical data and clearing abnormal value data; data arrangement: and combining the vehicle data with the vehicle insurance data, and classifying different sub-dangerous species data in the business insurance.
When 0 data exists in the historical data, the data with the data of 0 is eliminated, the data with obvious abnormality is eliminated, the historical data after the data elimination is combined, different sub-risk types of data in the business risk are classified, and the class parameter with the most occurrence frequency in the classified data can be used as the business risk sub-risk type of the current year and the parameter of the business risk sub-risk type without the risk.
The characteristic extraction comprises clustering the historical data by using a clustering algorithm, observing the structure of the clustered historical data, and determining the threshold value of the classification interval, thereby classifying the characteristics according to the threshold value of the classification interval.
2033. And training the forecast price model by using vehicle historical data.
Specifically, the historical data of a large number of vehicles, such as the purchase price of a new vehicle, the seat number, and the year of use of the vehicle, may be obtained by performing linear fitting by substituting into a regression formula:
linear regression model Y β0+β1x1+β2x2+β3x3+
Or
Polynomial regression model Y β0+β1x1+β2x2+β0x3+β3x1x2+β4x1x2+β5x2x3+β6x2x3+0
In the formula, the purchase price x of the new vehicle1Number of seats x2Number of years of use x3And Y is the predicted premium of the output.
The relationship between the purchase price of the new vehicle, the seat number, the service years of the vehicle and the insurance investment price predicted by the vehicle damage can be obtained through the formula.
It should be noted that, in a specific embodiment, the purchase price, seat number, vehicle age and/or insurance quota of the new vehicle in the vehicle history data are input into the trained pre-quote model corresponding to each risk, and the calculation of the quote of each risk may include:
s21: classifying premium intervals according to the purchase price, seat number and service years of the automobile in the historical data of the automobile, and determining the premium intervals of the forced insurance of the responsibility of the motor vehicle traffic accident; and determining the insurance price of the motor vehicle traffic accident obligation mandatory insurance according to the insurance premium interval in which the current new vehicle purchase price, seat number and service life of the vehicle are positioned.
Specifically, for example, the purchase price of the new car: 10 to 20 ten thousand; seat number: 0 to 6; the number of years of use: the insurance price of the motor vehicle traffic accident liability mandatory insurance from 0 to 5 is 100 yuan, and when the vehicle information needing to be pre-quoted is 15 ten thousand yuan, 5 seats and 2 years respectively, the output insurance price is 100 yuan. The insurance premium intervals of the motor vehicle traffic accident liability compulsory insurance can be divided according to the historical data, and the specific division and the corresponding insurance application price can also be obtained by performing interval fitting on the corresponding relation between the new vehicle purchase price, the seat number, the automobile service year and the insurance application price in the historical data.
S22: and (4) bringing the current new vehicle purchase price, seat number and service year of the vehicle into the trained vehicle damage risk forecasting price model, and calculating to obtain the insurance application price of the vehicle damage.
In one embodiment, the number of seats is first determined, and if the number of seats: and when the seat number is more than 6, the regression formula for calculating the vehicle damage is trained to be y ═ 1+2 purchase price +3 seat number +4 years, and when the seat number is more than 6, the regression formula for calculating the vehicle damage is trained to be y ═ 2+4 purchase price +6 seat number +8 years. The vehicle information that needs to be pre-quoted at this time is 15 yuan, 5 seats and 2 years, respectively, and the vehicle damage price output at this time is 54 yuan.
S23: and classifying the premium intervals according to the purchase price, the seat number and the service years of the automobile in the historical data of the automobile, determining the premium intervals of the third party liability insurance, and calculating the insurance price of the third party liability insurance according to the premium intervals and a third party liability insurance forecast price model corresponding to the premium intervals.
Specifically, the premium intervals of the liability insurance of the third party can be divided according to the purchase price, seat number and service year of the new vehicle in the historical data, and the specific division and the corresponding insurance price can also be obtained by performing interval fitting according to the corresponding relationship between the purchase price, seat number, service year of the new vehicle and insurance price in the historical data.
Can be obtained by model training in advance, and the purchase price is as follows: 10 to 20 ten thousand, seat number: 0 to 6, years of use: when the time is 0 to 5, the insurance quota lambda of the three1The risk price of the vehicle is 200 yuan when 100000 yuan. At the moment, the vehicle information needing to be quoted in advance is 15 ten thousand yuan, 5 seats and 2 years respectively, the insurance premium limit of the three selected is 10 ten thousand yuan, and the output insurance price at the moment is 200 yuan. This embodiment is for illustration only and does not represent an actual calculation relationship.
S24: and (4) bringing the current new vehicle purchase price, seat number and service life of the vehicle into the trained emergency forecasting price model, and calculating to obtain the insurance price of the emergency.
Specifically, the premium intervals for theft and emergency rescue can be divided according to the purchase price, seat number and service year of the new vehicle in the historical data, and the specific division and the corresponding insurance price can also be obtained by performing interval fitting according to the corresponding relationship between the purchase price, seat number, service year of the new vehicle and insurance price in the historical data.
In one specific embodiment, the trained regression formula for calculating theft emergency is y + 1+2 purchase price +3 seat +4 years +5 purchase price +6 seat +7 years. At this time, the vehicle information that needs to be pre-quoted is 15 yuan, 5 seats and 2 years, respectively, and then the theft and rescue price output at this time is 625 yuan.
S25: judging whether the vehicle is an import vehicle, if so, bringing the current new vehicle purchase price, seat number and service life of the vehicle into a trained import glass risk forecast price model to obtain the import glass risk insurance investment price; otherwise, the current new vehicle purchase price, seat number and service year of the vehicle are brought into the trained national glass insurance forecast price model to obtain the insurance price of the national glass insurance.
Specifically, it may be determined whether the vehicle is an import vehicle, and separate calculation may be performed for glass risk of a domestic vehicle and an import vehicle. In addition, the premium intervals of the glass insurance can be divided according to the purchase price, the seat number and the service years of the automobile in the historical data, and the specific division and the corresponding insurance price can also be obtained by interval fitting of the corresponding relation between the purchase price, the seat number, the service years of the automobile and the insurance price of the new automobile in the historical data.
S26: and substituting the current new vehicle purchase price, seat number and vehicle service year of the vehicle into the trained self-ignition risk forecast price model and the water risk pre-quoted price model to respectively obtain the self-ignition risk price and the water risk insurance investment price of the vehicle.
Specifically, the premium intervals of the self-ignition risk and the water risk can be divided according to the purchase price, the seat number and the service year of the new vehicle in the historical data, and the specific division and the corresponding insurance price can also be obtained by performing interval fitting according to the corresponding relationship between the purchase price, the seat number, the service year of the new vehicle and the insurance price in the historical data.
S27: classifying premium intervals according to the purchase price, seat number and service year of the new vehicle in the vehicle historical data, determining the premium intervals of the scratch risk, and substituting the insurance quota into a scratch risk forecast price model corresponding to the premium intervals of the scratch risk to obtain the insurance price of the scratch risk.
Specifically, the premium intervals of the scratch risk may be divided according to the purchase price, seat number, and year of use of the vehicle in the historical data, and the specific division and the corresponding insurance price may also be obtained by performing interval fitting according to the corresponding relationship between the purchase price, seat number, year of use of the vehicle, and insurance price of the new vehicle in the historical data.
S28: and classifying premium intervals according to the purchase price, seat number and service years of the automobile of the new automobile in the historical data of the automobile, determining the premium intervals of the on-board personnel responsibility insurance, and substituting the insurance quota into an on-board personnel responsibility insurance forecast price model corresponding to the premium intervals of the on-board personnel responsibility insurance to obtain the insurance price of the on-board personnel responsibility insurance.
Specifically, the premium intervals of the liability insurance of the personnel on the vehicle can be divided according to the purchase price, seat number and service year of the new vehicle in the historical data, and the specific division and the corresponding insurance price can also be obtained by performing interval fitting according to the corresponding relationship between the purchase price, seat number, service year of the new vehicle and insurance price in the historical data.
In one particular embodiment, the trained model: purchase price: 10 to 20 ten thousand, seat number: 0 to 6, years of use: when the vehicle is 0 to 5, the on-board personnel responsibility (driver or passenger) risk price calculation formula of the vehicle is that y is 1+2 lambda1+3λ2+4λ3The vehicle needing the pre-quoted price selects the guarantee amount of the on-board personal liability insurance (driver or passenger) as lambda 3 which is 100000 yuan, and since the term does not relate to the insurance amount of the three and the scratch insurance amount, lambda 1 and lambda 2 in the formula are 0, and the price output at this time is 400001 yuan obtained by substituting the formula.
In the formula, λ ═ λ (λ)1，λ2，λ3) The vehicle owner selected insurance quota vector input by the model. In the business insurance related to the model, only three sub-risk categories, namely three risks, scratch risk and on-board personnel responsibility risk, are included, and the user can select the insurance line. Accordingly, λ 1 represents the three insurance quota selected by the user, λ 2 represents the scratch insurance quota selected by the user, and λ 3 represents the on-board person liability insurance quota selected by the user. When calculating the risk of the three, the lambda 2 and the lambda 3 are 0; when the scratch risk is calculated, lambda 1 and lambda 3 are taken as 0; similarly, when calculating the responsibility insurance of the personnel on the vehicle, λ 1 and λ 2 take 0. This embodiment is only usedBy way of illustration, not representative of actual computational relationships.
204. Acquiring a parameter set of the commercial risk sub-risk purchased by the vehicle and an exemption risk parameter set of whether the commercial risk sub-risk is purchased or not, and calculating the total commercial risk price according to the sub-risk parameter set, the exemption risk parameter set and the set of various risk prices calculated in 203.
It should be noted that, from the historical data, the set M ═ of the commercial risk category parameter (μ) whether the current vehicle purchased or not can be obtained1，μ2，...，μ9) And whether to purchase the commercial risk category without counting the set of risk-free parameters
Further comprising the step 204 of adding the business insurance to obtain the total price Y ═ of the business insurance1,Y2,...,Y9) Wherein the parameter values in M and L are 0 or 1, i.e. 1 if the corresponding sub-risk category is purchased or the indemnity risk is not counted, and 0 otherwise.
In a particular embodiment, for example: a vehicle owner purchases the vehicle damage insurance, the three insurance, the vehicle personnel responsibility (driver) and the vehicle personnel responsibility (passenger) insurance, and purchases the non-counting claims-free insurance of the vehicle damage insurance and the three insurance, the data on the non-counting claims-free rate network can be found, and the two premium rates without counting the claims are 20% of the original premium rate. Through the calculation of step 204, assuming that the forecast prices of several commercial risk categories of Y are 100 yuan, 200 yuan, 300 yuan and 400 yuan in sequence, whether to purchase each commercial risk category parameter set M ═ 1,1,0,0,0,0, 1,1, where μ1，μ2，μ8，μ9Respectively representing the vehicle damage insurance, the three insurance, the vehicle personnel responsibility (driver) and the vehicle personnel responsibility (passenger) insurance, and whether the parameter set L of the purchased sub-risk category of the commercial insurance without the claim is equal to (1,1,0,0,0,0,0, 0), then the final output total price of the first due commercial insurance is:
the total number is 1060 yuan.
The final total premium includes Y10And the sum of the insurance application prices of the traffic accident liability mandatory insurance. It should be noted that this embodiment is merely an example, and does not represent an actual calculation relationship. In addition, in specific application, the owner can change the insurance types according to own needs to ensure that the will of the client can be met.
The above is an embodiment of the method of the present application, and the present application further provides an embodiment of a price forecasting device based on vehicle information identification, as shown in fig. 3, specifically including:
the information acquiring unit 301 is configured to acquire vehicle information and acquire real-time data of a current vehicle according to the vehicle information.
And the premium calculation unit 302 is used for substituting the real-time data into the trained pre-quotation model to calculate the forecast premium.
In a specific embodiment, the method further comprises the following steps:
and the preprocessing unit is used for preprocessing the historical data.
A history data acquisition unit for acquiring vehicle history data;
and the model training unit is used for training the forecast price model by adopting the vehicle historical data.
It is clear to those skilled in the art that, for convenience and brevity of description, the specific working processes of the above-described systems, apparatuses and units may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.
In this application, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
It should be understood that in the present application, "at least one" means one or more, "a plurality" means two or more. "and/or" for describing an association relationship of associated objects, indicating that there may be three relationships, e.g., "a and/or B" may indicate: only A, only B and both A and B are present, wherein A and B may be singular or plural. The character "/" generally indicates that the former and latter associated objects are in an "or" relationship. "at least one of the following" or similar expressions refer to any combination of these items, including any combination of single item(s) or plural items. For example, at least one (one) of a, b, or c, may represent: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", wherein a, b, c may be single or plural.
In the several embodiments provided in the present application, it should be understood that the disclosed apparatus and method may be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the units is only one logical division, and other divisions may be realized in practice, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form.
In addition, functional units in the embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.
The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present application may be substantially implemented or contributed to by the prior art, or all or part of the technical solution may be embodied in a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present application. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
The above embodiments are only used for illustrating the technical solutions of the present application, and not for limiting the same; although the present application has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions in the embodiments of the present application.
Claims (10)
1. A price forecasting method based on vehicle information identification is characterized by comprising the following steps:
acquiring vehicle information, and acquiring real-time data of a current vehicle according to the vehicle information;
and substituting the real-time data into the trained pre-quotation model to calculate the forecast premium.
2. The vehicle information identification-based forecasted price method of claim 1, wherein substituting said real-time data into a trained pre-quote model further comprises, prior to calculating a forecasted price premium:
acquiring vehicle historical data;
and training the forecast price model by using the vehicle historical data.
3. The vehicle information identification-based forecasted price method of claim 2, further comprising, after said obtaining vehicle history data:
and preprocessing the vehicle historical data.
4. The vehicle information identification-based price forecasting method according to claim 3, wherein the preprocessing of the vehicle history data is specifically:
data cleaning: clearing 0 data and abnormal value data in the vehicle historical data;
data arrangement: merging the vehicle data and the vehicle insurance data in the vehicle historical data, and classifying different sub-dangerous species data in the business insurance;
feature extraction: and clustering the historical data of the vehicles by using a clustering algorithm, observing the structure of the clustered data, and determining the threshold value of the classification interval.
5. The vehicle information identification-based price forecasting method according to claim 1, wherein the step of substituting the real-time data into the trained pre-quoted price model to calculate the pre-quoted premium specifically comprises the steps of:
s1: judging whether the use property of the current vehicle is a household automobile or not according to the real-time data of the current vehicle;
s2: inputting the purchase price, seat number, service life and/or insurance quota of the new vehicle in the real-time data of the current vehicle into trained pre-quotation models corresponding to various dangerous species, and calculating to obtain quotations of the various dangerous species;
s3: and acquiring a parameter set of the commercial risk sub-risk purchased by the current vehicle and an exemption parameter set whether to purchase the commercial risk sub-risk, and calculating a total commercial risk price according to the sub-risk parameter set, the exemption parameter set and the sets of various risk prices calculated in S2.
6. The price forecasting method based on vehicle information identification as claimed in claim 5, wherein the price forecasting method is characterized in that the purchase price, seat number, vehicle age and/or insurance quota of the new vehicle in the real-time data of the current vehicle are inputted into the trained pre-quoted price models corresponding to each risk category, and the quoted price of each risk category is calculated by:
s21: classifying premium intervals according to the purchase price, seat number and service years of the vehicle in the real-time data of the current vehicle, and determining the premium intervals of the forced insurance of the responsibility of the motor vehicle traffic accident; determining the insurance price of the forced insurance of the responsibility of the motor vehicle traffic accident according to the current new vehicle purchase price, seat number and premium interval of the service years of the vehicle;
s22: bringing the purchase price, seat number and service year of the new vehicle of the current vehicle into a trained vehicle damage risk forecasting price model, and calculating to obtain the insurance application price of the vehicle damage risk;
s23: classifying premium intervals according to the purchase price, seat number and service years of the vehicle of the new vehicle in the real-time data of the current vehicle, determining the premium interval of the third party responsibility insurance, and calculating the insurance application price of the third party responsibility insurance according to the premium interval and a third party responsibility insurance forecast price model corresponding to the premium interval;
s24: bringing the purchase price, the seat number and the service years of the new vehicle of the current vehicle into a trained theft emergency forecasting price model, and calculating to obtain the insurance price of the theft emergency;
s25: judging whether the current vehicle is an import vehicle, if so, bringing the purchase price, seat number and service life of the new vehicle of the current vehicle into a trained import glass risk forecast price model to obtain the insurance price of the import glass risk; otherwise, bringing the new vehicle purchase price, the seat number and the service years of the vehicle of the current vehicle into the trained national glass insurance forecast price model to obtain the insurance price of the national glass insurance;
s26: substituting the new vehicle purchase price, the seat number and the service year of the current vehicle into the trained self-ignition risk forecast price model and the water risk pre-quotation model to respectively obtain the self-ignition risk price and the water risk insurance investment price of the current vehicle;
s27: classifying premium intervals according to the purchase price, seat number and service years of the vehicle in the real-time data of the current vehicle, determining the premium intervals of the scratch insurance, and substituting the insurance quota into a scratch insurance forecast price model corresponding to the premium intervals of the scratch insurance to obtain the insurance price of the scratch insurance;
s28: and classifying premium intervals according to the purchase price, seat number and service years of the vehicle of the new vehicle in the real-time data of the current vehicle, determining the premium intervals of the on-board personnel liability insurance, and substituting the insurance quota into an on-board personnel liability insurance forecast price model corresponding to the on-board personnel liability insurance premium intervals to obtain the insurance price of the on-board personnel liability insurance.
7. The vehicle information identification-based price forecasting method according to claim 1, wherein the pre-pricing model is specifically:
linear regression model Y β0+β1x1+β2x2+β3x3+
Or
Polynomial regression model Y β0+β1x1+β2x2+β0x3+β3x1x2+β4x1x2+β5x2x3+β6x2x3+0
In the formula, the purchase price x of the new vehicle1Number of seats x2Number of years of use x3Y is the output prediction premium, β is the model coefficient, which is different depending on the risk.
8. A price forecasting device based on vehicle information identification is characterized by comprising:
the information acquisition unit is used for acquiring vehicle information and acquiring real-time data of a current vehicle according to the vehicle information;
and the premium calculation unit is used for substituting the real-time data into the trained pre-quotation model to calculate the forecast premium.
9. The vehicle information identification-based forecasted price device of claim 8, further comprising:
a history data acquisition unit for acquiring vehicle history data;
and the model training unit is used for training the forecast price model by adopting the vehicle historical data.
10. The vehicle information identification-based forecasted price device of claim 8, further comprising:
and the preprocessing unit is used for preprocessing the vehicle historical data.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010419773.9A CN111598664A (en) | 2020-05-18 | 2020-05-18 | Price forecasting method and device based on vehicle information identification |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010419773.9A CN111598664A (en) | 2020-05-18 | 2020-05-18 | Price forecasting method and device based on vehicle information identification |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111598664A true CN111598664A (en) | 2020-08-28 |
Family
ID=72192247
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010419773.9A Pending CN111598664A (en) | 2020-05-18 | 2020-05-18 | Price forecasting method and device based on vehicle information identification |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111598664A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113887741A (en) * | 2021-11-05 | 2022-01-04 | 深圳市电子商务安全证书管理有限公司 | Data generation method, device, equipment and storage medium based on federal learning |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20120095782A1 (en) * | 2010-10-14 | 2012-04-19 | Nicholas Ryan Munger | System and method for managing derivative market insurance transactions |
| CN108256714A (en) * | 2016-12-29 | 2018-07-06 | 得道车联网络科技（上海）有限公司 | A kind of wheelpath real-time risk assessment model based on car networking big data |
| CN108564421A (en) * | 2018-05-07 | 2018-09-21 | 中国平安财产保险股份有限公司 | Car insurance pricing method, device, equipment and computer storage media |
| CN110163759A (en) * | 2018-02-12 | 2019-08-23 | 北京直通万连科技有限公司 | A kind of vehicle insurance scheme generation method |
| CN110781187A (en) * | 2019-10-18 | 2020-02-11 | 海腾保险代理有限公司 | Car insurance quotation method and device, equipment and storage medium |
| CN110910257A (en) * | 2019-11-15 | 2020-03-24 | 泰康保险集团股份有限公司 | Information prediction method, information prediction device, electronic equipment and computer readable medium |
-
2020
- 2020-05-18 CN CN202010419773.9A patent/CN111598664A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20120095782A1 (en) * | 2010-10-14 | 2012-04-19 | Nicholas Ryan Munger | System and method for managing derivative market insurance transactions |
| CN108256714A (en) * | 2016-12-29 | 2018-07-06 | 得道车联网络科技（上海）有限公司 | A kind of wheelpath real-time risk assessment model based on car networking big data |
| CN110163759A (en) * | 2018-02-12 | 2019-08-23 | 北京直通万连科技有限公司 | A kind of vehicle insurance scheme generation method |
| CN108564421A (en) * | 2018-05-07 | 2018-09-21 | 中国平安财产保险股份有限公司 | Car insurance pricing method, device, equipment and computer storage media |
| CN110781187A (en) * | 2019-10-18 | 2020-02-11 | 海腾保险代理有限公司 | Car insurance quotation method and device, equipment and storage medium |
| CN110910257A (en) * | 2019-11-15 | 2020-03-24 | 泰康保险集团股份有限公司 | Information prediction method, information prediction device, electronic equipment and computer readable medium |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113887741A (en) * | 2021-11-05 | 2022-01-04 | 深圳市电子商务安全证书管理有限公司 | Data generation method, device, equipment and storage medium based on federal learning |
| CN113887741B (en) * | 2021-11-05 | 2022-09-30 | 深圳市电子商务安全证书管理有限公司 | Data generation method, device, equipment and storage medium based on federal learning |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10504159B2 (en) | Wholesale/trade-in pricing system, method and computer program product therefor | |
| US11062338B2 (en) | Used-vehicle algorithmic pricing engine method and system | |
| US20060259350A1 (en) | System and method for identifying a market by projecting demand and identifying supply | |
| US11410206B2 (en) | Systems and methods for transformation of raw data to actionable data | |
| US20170300991A1 (en) | Used-vehicle algorithmic pricing engine method and system | |
| JP2014523057A (en) | System and method for analysis and presentation of used vehicle pricing data | |
| US20130006809A1 (en) | Method and system for providing a certified swap price for a vehicle | |
| US20150363855A1 (en) | Systems and Methods for Automatic Popular Configuration Generation | |
| CN110634021A (en) | Big data based vehicle estimation method, system, device and readable storage medium | |
| CN109377286A (en) | The method, apparatus and computer equipment of insurance price are calculated based on prediction model | |
| US11915290B2 (en) | Systems and methods for determining and leveraging geography-dependent relative desirability of products | |
| CN111598664A (en) | Price forecasting method and device based on vehicle information identification | |
| Kehrle et al. | Who moves first? An intensity-based measure for information flows across stock exchanges | |
| CN110428281B (en) | Method and device for jointly determining peer-to-peer resource quantity aiming at multiple associated products | |
| CN110910163A (en) | Automobile distribution customer demand analysis method and system based on customer relationship management system | |
| KR20150142407A (en) | Non-Life insurance Other damage part Integrated process system | |
| KR20180106478A (en) | Rent system for a car based on purchasing prise of a used car | |
| CN111523911A (en) | Matched stack formula marketing system based on automobile parts | |
| KR20150126465A (en) | Knowledge information dealing system through on-line | |
| WO2022177820A9 (en) | Quantitative asset valuation and disposition system | |
| CN110458302B (en) | Vehicle push repairing method and system based on user satisfaction | |
| KR20210026315A (en) | Used car selling management system | |
| CN115907994A (en) | Data object transaction early warning method, device and system | |
| CN109840824A (en) | The car fare price comparing system of worldwide vehicle | |
| US20220358595A1 (en) | Non-Discriminatory and Non-Individualized Vehicle Insurance Pricing Methodology Using Advanced Data Collection and Analytics |
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 | ||
| TA01 | Transfer of patent application right | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20210204 Address after: 510000 room 304, 239-257 Tianfu Road, Tianhe District, Guangzhou City, Guangdong Province (office only) Applicant after: Guangzhou Langsheng Internet Technology Co.,Ltd. Address before: 510000 room 216, no.22-3, Kemu Long South Road, Tianhe District, Guangzhou City, Guangdong Province (office only) Applicant before: Guangzhou Landau Information Technology Co.,Ltd. |
|
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200828 |