CN115797084A - Insurance pricing guidance method based on driving behavior of vehicle owner and related equipment thereof - Google Patents
Insurance pricing guidance method based on driving behavior of vehicle owner and related equipment thereof Download PDFInfo
- Publication number
- CN115797084A CN115797084A CN202211559307.6A CN202211559307A CN115797084A CN 115797084 A CN115797084 A CN 115797084A CN 202211559307 A CN202211559307 A CN 202211559307A CN 115797084 A CN115797084 A CN 115797084A
- Authority
- CN
- China
- Prior art keywords
- driving behavior
- characteristic data
- insurance
- data
- vehicle owner
- 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
Landscapes
- Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)
Abstract
The embodiment of the application belongs to the technical field of financial science and technology, is applied to the field of insurance pricing guidance in financial services, and relates to an insurance pricing guidance method based on driving behaviors of vehicle owners and related equipment thereof, wherein the insurance pricing guidance method comprises the steps of carrying out modeling according to multidimensional driving behavior characteristic data and insurance claim characteristic data corresponding to historical vehicle owners to obtain a driving behavior and claim relationship prediction model; inputting driving behavior characteristic data of a new insurance vehicle owner client into the driving behavior and claim relationship prediction model, and predicting the corresponding out-of-insurance claim characteristic data of the vehicle owner to be detected; and outputting the characteristic data of the insurance claim payment as a pricing basis. The method and the system build a driving behavior and claim relationship prediction model through a machine learning mode, predict the insurance claim characteristic data of the new insurance vehicle owner through the driving behavior and claim relationship prediction model after learning training, and combine the driving behavior data of the new insurance vehicle owner to carry out insurance pricing, so that the method and the system are more scientific.
Description
Technical Field
The application relates to the technical field of financial science and technology, in particular to an insurance pricing guidance method based on driving behaviors of car owners and related equipment thereof.
Background
The simple customer grading based on the insurance taking times and the payment taking times is an excessively simple customer grading mode, the mode takes the result as the guide to conduct insurance quotation pricing guidance, the data is single according to the basis, and the driving habits of customers are often the key factors for determining whether traffic accidents occur or not. In the safety insurance, a vehicle owner ecological circle is created through a self-developed good vehicle owner APP, and on the premise of permission of a customer, a 'safety operation' function is started to encourage the vehicle owner to voluntarily use the 'driving earning' function to upload driving behavior data.
At present, taking the car insurance pricing service in the financial science and technology service as an example, only the insurance pricing is performed in the above mode and is not scientific enough, the invention provides another insurance pricing method, which fully combines the driving behavior data and the insurance reimbursement data of the car owner to perform insurance pricing prediction together, so as to solve the problem that the data basis of the insurance pricing in the prior art is not scientific enough.
Disclosure of Invention
The embodiment of the application aims to provide an insurance pricing guidance method based on driving behaviors of car owners and related equipment thereof, so as to solve the problem that the data basis of insurance pricing in the prior art is not scientific enough.
In order to solve the technical problem, an embodiment of the present application provides an insurance pricing guidance method based on driving behaviors of car owners, and the following technical solutions are adopted:
an insurance pricing guidance method based on driving behaviors of car owners comprises the following steps:
collecting driving behavior data respectively uploaded by a plurality of vehicle owners;
performing numerical processing on the driving behavior data corresponding to each vehicle owner based on a preset processing assembly to obtain multi-dimensional driving behavior characteristic data;
acquiring the characteristic data of the claims for the insurance benefits corresponding to the car owners respectively according to a preset underwriting information platform;
performing regional segmentation processing on the multidimensional driving behavior characteristic data and the settlement characteristic data according to driving behaviors corresponding to the car owners to obtain N prediction model sample groups, wherein N is a positive integer;
modeling the N prediction model sample groups respectively by adopting an elastic network regression algorithm to obtain N driving behavior and claim relationship prediction models;
acquiring driving behavior data uploaded by a vehicle owner to be detected, and performing numerical processing to acquire multi-dimensional driving behavior characteristic data corresponding to the vehicle owner to be detected, wherein the driving behavior characteristic data comprises a driving behavior place;
inputting the driving behavior characteristic data serving as input data into the driving behavior and claim relationship prediction model, and predicting the claim characteristic data corresponding to the vehicle owner to be tested;
and outputting the characteristic data of the claims as pricing basis.
Further, the step of obtaining multidimensional driving behavior characteristic data based on numerical processing of the driving behavior data corresponding to each vehicle owner by the preset processing component specifically includes:
according to a preset time limit condition and a preset algorithm plug-in, carrying out numerical processing on the driving behavior data corresponding to each vehicle owner to obtain numerical driving behavior data corresponding to each vehicle owner;
and taking the numerical driving behavior data corresponding to each vehicle owner as the multi-dimensional driving behavior characteristic data corresponding to the vehicle owner.
Further, the step of obtaining the pay-out characteristic data corresponding to each of the plurality of vehicle owners according to the preset underwriting information platform specifically includes:
according to the corresponding time limiting condition and a preset algorithm plug-in, carrying out numerical processing on the claim data corresponding to each vehicle owner to obtain the numerical claim data corresponding to each vehicle owner;
and taking the numerical insurance claim payment data corresponding to each vehicle owner as insurance claim payment characteristic data corresponding to the vehicle owner.
Further, the step of performing regional segmentation processing on the multidimensional driving behavior characteristic data and the settlement characteristic data according to the driving behaviors corresponding to the plurality of vehicle owners specifically includes:
in the process of executing the step of collecting the driving behavior data respectively uploaded by a plurality of vehicle owners, the method further comprises the following steps: acquiring driving behavior places where the plurality of vehicle owners respectively locate when the driving behavior data is acquired according to a preset data acquisition APP or a positioning interface built in terminal equipment provided with the preset data acquisition APP;
integrating and counting the driving behavior places of the plurality of car owners, and setting different numbers according to different driving behavior places;
setting a contrast relation between the multidimensional driving behavior characteristic data and the pay-out characteristic data corresponding to the same vehicle owner;
integrating the multidimensional driving behavior characteristic data and the pay-out characteristic data which respectively correspond to different vehicle owners in the same driving behavior area to generate a prediction model sample group, and using the difference numbers as the difference numbers of the prediction model sample group.
Further, the step of respectively modeling the N prediction model sample groups by using an elastic network regression algorithm to obtain N prediction models of driving behavior and reimbursement relationship specifically includes:
acquiring the multidimensional driving behavior characteristic data and the pay-out characteristic data which respectively correspond to different vehicle owners in the same driving behavior region and are contained in the current prediction model sample group according to the distinguishing numbers;
inputting the multidimensional driving behavior characteristic data and the pay-out characteristic data into a pre-constructed artificial intelligence learning model, performing learning training, and obtaining a linear regression relationship between the multidimensional driving behavior characteristic data and the pay-out characteristic data, wherein when the artificial intelligence learning model is pre-constructed, a cost function of the artificial intelligence learning model is dynamically adjusted in advance according to an elastic network regression algorithm;
and obtaining a model after learning training corresponding to each distinguishing number, namely obtaining a driving behavior and claim relationship prediction model with the same number as the segmentation processing number.
Further, in this embodiment, before the step of inputting the multidimensional driving behavior characteristic data and the pay-out characteristic data into a pre-constructed artificial intelligence learning model for learning training, the method further includes:
integrating the multidimensional driving behavior characteristic data and the insurance claim paying characteristic data which respectively correspond to different vehicle owners in the same driving behavior place;
according to the integration result and a preset first proportional algorithm, acquiring weight coefficients of all the driving behavior characteristic data in the multidimensional driving behavior characteristic data in all different vehicle owners in the same driving behavior area, and constructing a weight coefficient matrix and a first regular expression item corresponding to the multidimensional driving behavior characteristic data;
and according to the integration result and a preset second proportional algorithm, acquiring the weight coefficient of each claim characteristic data in the claim characteristic data in all different vehicle owners in the same driving behavior, and constructing a second regular expression corresponding to the claim characteristic data.
Further, the step of dynamically adjusting the cost function of the artificial intelligence learning model in advance according to an elastic network regression algorithm when the artificial intelligence learning model is pre-constructed specifically includes:
according to a preset elastic network regression algorithm:
obtaining a weight coefficient value corresponding to each driving behavior characteristic data in the multidimensional driving behavior characteristic data when cos (x) is the minimum value, wherein omega is T A weight coefficient matrix corresponding to the driving behavior characteristic data in multiple dimensions | ω | 1 For the first canonical expression term, | ω | 1 ＝|ω 1 |+|ω 2 |+…+|ω i-1 |+|ω i I, the serial number of the current characteristic data in the multidimensional driving behavior characteristic data, the number of all characteristic data in the multidimensional driving behavior characteristic data, | omega | 2 In order for the second regular expression term to be,
j is the serial number of the current feature in the claim characteristic data, is the number of all the feature data in the claim characteristic data, ω is a weight coefficient corresponding to each driving behavior feature data in the multidimensional driving behavior feature data, and λ and ρ are preset constants for commonly controlling the sizes of the first regular expression term and the second regular expression term;
when cos (x) is the minimum value, the weight coefficient value corresponding to each driving behavior characteristic data in the multi-dimensional driving behavior characteristic data is used as a target configuration item to carry out weight configuration on the pre-constructed artificial intelligence learning model;
and the artificial intelligence learning model after the weight configuration is finished is a driving behavior and claim relationship prediction model after learning training is finished.
In order to solve the above technical problem, an embodiment of the present application further provides an insurance pricing guidance device based on driving behaviors of vehicle owners, which adopts the following technical scheme:
an insurance pricing guidance device based on driving behaviors of car owners comprises:
the driving behavior data acquisition module is used for acquiring driving behavior data uploaded by a plurality of vehicle owners respectively;
the driving behavior characteristic data acquisition module is used for carrying out numerical processing on the driving behavior data corresponding to each vehicle owner based on a preset processing assembly to acquire multi-dimensional driving behavior characteristic data;
the system comprises an insurance claim paying characteristic data acquisition module, an insurance claim paying characteristic data acquisition module and an insurance claim paying characteristic data acquisition module, wherein the insurance claim paying characteristic data acquisition module is used for acquiring insurance claim paying characteristic data corresponding to a plurality of vehicle owners respectively according to a preset insurance acceptance information platform;
the characteristic data segmentation processing module is used for performing regional segmentation processing on the multidimensional driving behavior characteristic data and the claim paying characteristic data according to the driving behaviors corresponding to the plurality of vehicle owners to obtain N prediction model sample groups, wherein N is a positive integer;
the prediction model modeling module is used for respectively modeling the N prediction model sample groups by adopting an elastic network regression algorithm to obtain N driving behavior and claim relationship prediction models;
the test data acquisition module is used for acquiring driving behavior data uploaded by a vehicle owner to be tested, carrying out numerical processing and acquiring multi-dimensional driving behavior characteristic data corresponding to the vehicle owner to be tested, wherein the driving behavior characteristic data comprises a driving behavior place;
the model prediction module is used for inputting the driving behavior characteristic data serving as input data into the driving behavior and claim relationship prediction model and predicting the claim characteristic data corresponding to the vehicle owner to be tested;
and the output result feedback module is used for outputting the characteristic data of the claims as pricing basis.
In order to solve the above technical problem, an embodiment of the present application further provides a computer device, which adopts the following technical solutions:
a computer device comprising a memory and a processor, wherein the memory stores computer readable instructions, and the processor implements the steps of the insurance pricing guidance method based on driving behavior of vehicle owners when executing the computer readable instructions.
In order to solve the above technical problem, an embodiment of the present application further provides a computer-readable storage medium, which adopts the following technical solutions:
a computer readable storage medium having computer readable instructions stored thereon which, when executed by a processor, implement the steps of an insurance pricing guidance method based on driving behavior of vehicle owners as described above.
Compared with the prior art, the embodiment of the application mainly has the following beneficial effects:
according to the insurance pricing guidance method based on the driving behaviors of the vehicle owners, modeling is carried out according to multi-dimensional driving behavior characteristic data and insurance claim characteristic data corresponding to historical vehicle owners, and a driving behavior and claim relationship prediction model is obtained; inputting driving behavior characteristic data of a new insurance vehicle owner client into the driving behavior and claim relationship prediction model, and predicting the corresponding out-of-insurance claim characteristic data of the vehicle owner to be detected; and outputting the characteristic data of the insurance claim payment as a pricing basis. The method and the system build a driving behavior and claim relationship prediction model through a machine learning mode, predict the insurance claim characteristic data of the new insurance vehicle owner through the driving behavior and claim relationship prediction model after learning training, and combine the driving behavior data of the new insurance vehicle owner to carry out insurance pricing, so that the method and the system are more scientific.
Drawings
In order to more clearly illustrate the solution of the present application, the drawings needed for describing the embodiments of the present application will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present application, and that other drawings can be obtained by those skilled in the art without inventive effort.
FIG. 1 is an exemplary system architecture diagram in which the present application may be applied;
FIG. 2 is a flow diagram of one embodiment of an insurance pricing guidance method based on vehicle owner driving behavior according to the present application;
FIG. 3 is a schematic block diagram of an embodiment of an insurance pricing guidance device based on vehicle owner driving behavior according to the present application;
FIG. 4 is a block diagram of one embodiment of a computer device according to the present application.
Detailed Description
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs; the terminology used in the description of the application herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the application; the terms "including" and "having," and any variations thereof in the description and claims of this application and the description of the figures above, are intended to cover non-exclusive inclusions. The terms "first," "second," and the like in the description and claims of this application or in the above-described drawings are used for distinguishing between different objects and not for describing a particular order.
Reference herein to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment can be included in at least one embodiment of the application. The appearances of the phrase in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. It is explicitly and implicitly understood by one skilled in the art that the embodiments described herein can be combined with other embodiments.
In order to make the technical solutions better understood by those skilled in the art, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings.
As shown in fig. 1, the system architecture 100 may include terminal devices 101, 102, 103, a network 104, and a server 105. The network 104 serves as a medium for providing communication links between the terminal devices 101, 102, 103 and the server 105. Network 104 may include various connection types, such as wired, wireless communication links, or fiber optic cables, to name a few.
The user may use the terminal devices 101, 102, 103 to interact with the server 105 via the network 104 to receive or send messages or the like. The terminal devices 101, 102, 103 may have various communication client applications installed thereon, such as a web browser application, a shopping application, a search application, an instant messaging tool, a mailbox client, social platform software, and the like.
The terminal devices 101, 102, 103 may be various electronic devices having a display screen and supporting web browsing, including but not limited to a smart phone, a tablet computer, an e-book reader, an MP3 player (Moving Picture experts Group Audio Layer III, motion Picture experts compression standard Audio Layer 3), an MP4 player (Moving Picture experts Group Audio Layer IV, motion Picture experts compression standard Audio Layer 4), a laptop portable computer, a desktop computer, and the like.
The server 105 may be a server providing various services, such as a background server providing support for pages displayed on the terminal devices 101, 102, 103.
It should be noted that the insurance pricing guidance method based on the driving behavior of the vehicle owner provided by the embodiment of the present application is generally executed by the server/terminal device, and accordingly, the insurance pricing guidance device based on the driving behavior of the vehicle owner is generally disposed in the server/terminal device.
It should be understood that the number of terminal devices, networks, and servers in fig. 1 is merely illustrative. There may be any number of terminal devices, networks, and servers, as desired for implementation.
With continued reference to FIG. 2, a flow diagram of one embodiment of an insurance pricing guidance method based on vehicle owner driving behavior according to the present application is shown. The insurance pricing guidance method based on the driving behavior of the car owner comprises the following steps:
In this embodiment, the driving behavior data that a plurality of car owners uploaded respectively can be gathered according to the appointed collection interface in presetting data acquisition APP, data acquisition APP can be for good car owner APP, appointed collection interface can be carry out the interface of car owner driving behavior data acquisition in the good car owner APP of peace.
The driving behavior records of the owner clients with the 'safe operation' function in the safe owner APP are collected, multi-dimensional driving behavior characteristic data are obtained after secondary processing, and insurance pricing guidance information of new and safe owner clients can be predicted conveniently by combining the driving behavior data and insurance pricing information of the historical owner clients.
In this embodiment, the step of obtaining the multidimensional driving behavior characteristic data by performing the numerical processing on the driving behavior data corresponding to each vehicle owner based on the preset processing component specifically includes: according to a preset time limit condition and a preset algorithm plug-in, carrying out numerical processing on the driving behavior data corresponding to each vehicle owner to obtain numerical driving behavior data corresponding to each vehicle owner; and taking the numerical driving behavior data corresponding to each vehicle owner as the multi-dimensional driving behavior characteristic data corresponding to the vehicle owner.
In this embodiment, the step of performing a numerical processing on the driving behavior data corresponding to each vehicle owner according to a preset time limit condition and a preset algorithm plug-in to obtain the numerical driving behavior data corresponding to each vehicle owner specifically includes: under the condition that the time limiting condition is a null value, acquiring the average speed of single driving, the highest mileage of single driving, the highest emergency braking frequency of single driving, the turning frequency of single driving, the sharp turning frequency of single driving, the highest time of single driving and the highest path city number of single driving corresponding to each vehicle owner according to the algorithm plug-in, and taking the obtained data as numerical driving behavior data when the time limiting condition corresponding to the vehicle owner is the null value; under the condition that the time limit condition is the latest month, acquiring the driving average speed of the latest month, the driving maximum speed of the latest month, the driving mileage of the latest month, the accumulated emergency braking times of the latest month, the accumulated turning times of the latest month, the accumulated sharp turning times of the latest month, the accumulated driving time of the latest month, the accumulated violation times of the latest month, the accumulated long distance times of the latest month and the maximum driving duration of the latest month corresponding to each vehicle owner according to the algorithm plug-in, and taking the acquired driving average speed of the latest month, the driving maximum speed of the latest month, the accumulated violation times of the latest month, the accumulated emergency braking times of the latest month and the maximum driving duration of the latest month as numerical driving behavior data when the time limit condition corresponding to each vehicle owner is the latest month; under the condition that the time limiting condition is the last three months, acquiring the average driving speed of the last three months, the highest driving speed of the last three months, the driving mileage of the last three months, the accumulated emergency braking times of the last three months, the accumulated turning times of the last three months, the accumulated sharp turning times of the last three months, the accumulated driving time of the last three months, the accumulated violation times of the last three months, the long distance times of the last three months and the highest driving duration of the last three months corresponding to each vehicle owner according to the algorithm plug-in as the numerical driving behavior data when the time limiting condition corresponding to the vehicle owner is the last three months; and under the condition that the time limit condition is the last year, acquiring the driving average speed, the driving maximum speed, the driving mileage, the accumulated emergency braking times, the accumulated turning times, the accumulated sharp turning times, the accumulated driving time, the accumulated violation times, the accumulated long distance times and the maximum driving duration corresponding to each vehicle owner in the last year according to the algorithm plug-in, wherein the driving average speed, the driving maximum speed, the driving mileage, the accumulated emergency braking times, the accumulated turning times, the accumulated sharp turning times, the accumulated driving time, the accumulated violation times, the accumulated long distance times and the maximum driving duration are corresponding to each vehicle owner in the last year, and taking the driving average speed, the driving maximum speed, the accumulated driving mileage, the accumulated violation times, the accumulated distance times and the maximum driving duration as numerical driving behavior data corresponding to each vehicle owner in the last year.
In this embodiment, the algorithm plug-in refers to an algorithm integration component that can perform a series of algorithms such as statistical summation and average calculation on the driving behavior data, and can finally obtain multi-dimensional driving behavior feature data.
In this embodiment, a time constraint condition may be selectively set before using the algorithm plug-in, for setting a time-dependent dimension of the driving behavior data. The driving behavior characteristic data under different time dimensions can be acquired more flexibly through the time limiting conditions, such as: obtaining driving behavior data for the last month, obtaining driving behavior data for the last half year, and so on.
In this embodiment, in the step of obtaining the multidimensional driving behavior feature data, the multidimensional driving behavior feature data at least includes: <xnotran> , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , . </xnotran>
In this embodiment, the step of obtaining the pay-out characteristic data corresponding to each of the plurality of car owners according to the preset underwriting information platform specifically includes: according to the corresponding time limiting condition and a preset algorithm plug-in, carrying out numerical processing on the claim data corresponding to each vehicle owner to obtain the numerical claim data corresponding to each vehicle owner; and taking the numerical insurance claim data corresponding to each vehicle owner as insurance claim characteristic data corresponding to the vehicle owner.
In this embodiment, the step of performing a digitized processing on the claim data corresponding to each vehicle owner according to the corresponding time limit condition and the preset algorithm plugin to obtain the digitized claim data corresponding to each vehicle owner specifically includes: under the condition that the time limiting condition is null, acquiring the single highest paying amount corresponding to each vehicle owner according to the algorithm plug-in, and taking the single highest paying amount as numerical paying-out data when the time limiting condition corresponding to each vehicle owner is null; under the condition that the time limit condition is the latest month, acquiring the latest monthly insurance number, the latest monthly payment maximum amount and the latest monthly payment total amount corresponding to each vehicle owner according to the algorithm plug-in, and taking the latest monthly insurance number, the latest monthly payment maximum amount and the latest monthly payment total amount as numerical insurance payment data when the time limit condition corresponding to each vehicle owner is the latest month; under the condition that the time limit condition is the last three months, acquiring the number of the risks of the last three months, the highest amount of the claims of the last three months and the total amount of the claims of the last three months corresponding to each vehicle owner according to the algorithm plug-in, and taking the number of the risks of the last three months, the highest amount of the claims of the last three months and the total amount of the claims of the last three months as numerical risk claim data when the time limit condition corresponding to each vehicle owner is the last three months; and under the condition that the time limit condition is the last year, acquiring the number of times of leaving insurance in the last year, the highest amount of the money paid in the last year and the total amount of the money paid in the last year corresponding to each owner according to the algorithm plug-in as numerical data of leaving insurance payment when the time limit condition corresponding to each owner is the last year.
In this embodiment, the insurance acceptance information platform may be a data platform for an insurance company to record the insurance claims information of the customer car owner, and taking safe car insurance as an example, the insurance acceptance information platform may be a data platform for a safe car insurance science and technology company to record the insurance claims information of the customer car owner.
In this embodiment, in the step of obtaining the pay-out characteristic data corresponding to each of the plurality of vehicle owners, the pay-out characteristic data at least includes: the highest amount paid for a single time, the number of times of the last month's claim, the highest amount paid for the last month, the total amount paid for the last month, the number of times of the last three months' claim, the highest amount paid for the last three months 'claim, the total amount paid for the last three months' claim, the number of times paid for the last year, the highest amount paid for the last year's claim, and the total amount paid for the last year's claim.
By acquiring the claim data corresponding to the vehicle owner, the claim data and the driving behavior data are used as a group of associated characteristic data, and the association relation between the claim data and the driving behavior data is obtained, so that data basis is provided for predicting the claim data of the vehicle owner according to the driving behavior data of the new vehicle owner client.
And 204, performing regional segmentation processing on the multidimensional driving behavior characteristic data and the claim paying characteristic data according to the driving behaviors corresponding to the plurality of vehicle owners to obtain N prediction model sample groups, wherein N is a positive integer.
In this embodiment, the step of performing regional segmentation processing on the multidimensional driving behavior characteristic data and the pay-out characteristic data according to the driving behaviors corresponding to the plurality of car owners specifically includes: in the process of executing the step of collecting the driving behavior data respectively uploaded by a plurality of vehicle owners, the method further comprises the following steps: acquiring driving behavior places where the plurality of vehicle owners are respectively located when the driving behavior data are acquired according to the data acquisition APP or a positioning interface built in terminal equipment provided with the data acquisition APP; integrating and counting the driving behavior places of the plurality of car owners, and setting different numbers according to different driving behavior places; setting a contrast relation between the multidimensional driving behavior characteristic data and the pay-out characteristic data corresponding to the same vehicle owner; integrating the multidimensional driving behavior characteristic data and the pay-out characteristic data which respectively correspond to different vehicle owners in the same driving behavior area to generate a prediction model sample group, and using the difference numbers as the difference numbers of the prediction model sample group.
The driving behavior characteristic data and the insurance claim characteristic data of the multiple dimensions are subjected to regional segmentation processing through the driving behaviors, so that the condition that all the driving behavior characteristic data and the insurance claim characteristic data are only used for training one prediction model is avoided, the condition that the regional characteristic is taken as a unit when the prediction model is constructed subsequently is ensured due to overlarge training data set, meanwhile, the prediction model is constructed by combining the regional characteristic, and the driving behavior habits in different regions are indirectly distinguished.
And step 205, modeling the N prediction model sample groups respectively by adopting an elastic network regression algorithm, and acquiring N driving behavior and claim relationship prediction models.
In this embodiment, the step of respectively modeling the N prediction model sample groups by using an elastic network regression algorithm to obtain N prediction models of driving behavior and claim relationship specifically includes: acquiring the multidimensional driving behavior characteristic data and the pay-out characteristic data which respectively correspond to different vehicle owners in the same driving behavior region and are contained in the current prediction model sample group according to the distinguishing numbers; inputting the multidimensional driving behavior characteristic data and the insurance claim characteristic data into a pre-constructed artificial intelligent learning model, and performing learning training to obtain a linear regression relationship between the multidimensional driving behavior characteristic data and the insurance claim characteristic data, wherein when the artificial intelligent learning model is pre-constructed, a cost function of the artificial intelligent learning model is dynamically adjusted in advance according to an elastic network regression algorithm; and obtaining a model after learning training corresponding to each distinguishing number, namely obtaining a driving behavior and claim relationship prediction model with the same number as the segmentation processing number.
And performing learning model iterative training by adopting an elastic network regression algorithm to obtain a relation prediction model between the multidimensional driving behavior characteristic data and the pay-out characteristic data in different domains.
The method adopts an Elastic network Regression algorithm (Elastic Net Regression), not only retains the property of feature selection of the Lasso Regression, but also considers the stability of the ridge Regression, and two regularization methods of the ridge Regression and the Lasso Regression are adopted, when a plurality of features are related and more useless features exist, the Lasso Regression can only randomly select one of the more useful features to perform Regression function (cost function) calculation, and the ridge Regression can select all the features to perform the Regression function (cost function) calculation.
In this embodiment, before the step of inputting the multidimensional driving behavior feature data and the pay-out feature data into a pre-constructed artificial intelligence learning model for learning and training is performed, the method further includes: integrating the multidimensional driving behavior characteristic data and the insurance claim paying characteristic data which respectively correspond to different vehicle owners in the same driving behavior place; according to the integration result and a preset first proportional algorithm, acquiring weight coefficients of all the driving behavior characteristic data in the multidimensional driving behavior characteristic data in all different vehicle owners in the same driving behavior area, and constructing a weight coefficient matrix and a first regular expression item corresponding to the multidimensional driving behavior characteristic data; and according to the integration result and a preset second proportional algorithm, acquiring the weight coefficient of each claim characteristic data in the claim characteristic data in all different vehicle owners in the same driving behavior, and constructing a second regular expression corresponding to the claim characteristic data.
In this embodiment, the first proportional algorithm and the second proportional algorithm are substantially probability value algorithms, and taking the average speed of driving in the last year in the multidimensional driving behavior characteristic data as an example, assuming that the number of data of the average speed of driving in the last year of the vehicle owner collected in a certain region is 1 ten thousand, the number of data of the average speed of driving in the last year is 100, and the number of data of the average speed of driving in the last year is 9000, it can be obtained that the weight coefficient corresponding to the average speed of driving in the last year of 110KM/H is 0.01, and the weight coefficient corresponding to the average speed of driving in the last year of 60KM/H is 0.9, where KM/H is kilometer per hour. The common driving behavior habits of most vehicle owners in the same region can be screened out through the weight coefficients.
In this embodiment, the step of dynamically adjusting the cost function of the artificial intelligence learning model in advance according to an elastic network regression algorithm when the artificial intelligence learning model is pre-constructed specifically includes: according to a preset elastic network regression algorithm:
obtaining a weight coefficient value corresponding to each driving behavior characteristic data in the multidimensional driving behavior characteristic data when cos (x) is the minimum value, wherein omega is T A weight coefficient matrix corresponding to the driving behavior characteristic data representing the multiple dimensions, | ω | 1 For the first canonical expression term, | ω | 1 ＝|ω 1 |+|ω 2 |+…+|ω i-1 |+|ω i A serial number of the current characteristic data in the multi-dimensional driving behavior characteristic data, N is the number of all characteristic data in the multi-dimensional driving behavior characteristic data, | omega | 2 In order for the second regular expression term to be,
j is the serial number of the current characteristic in the pay-out characteristic data, M is the number of all characteristic data in the pay-out characteristic data, omega is a weight coefficient corresponding to each driving behavior characteristic data in the multidimensional driving behavior characteristic data, and lambda and rho are preset constants and are used for controlling the size of the first regular expression item and the size of the second regular expression item together; when cos (x) is the minimum value, the weight coefficient value corresponding to each driving behavior characteristic data in the multi-dimensional driving behavior characteristic data is used as a target configuration item to carry out weight configuration on the pre-constructed artificial intelligence learning model; and the artificial intelligence learning model after the weight configuration is finished is a driving behavior and paying relationship prediction model after learning training is finished.
In this embodiment, a coordinate descent method and a double loop iteration method are substantially used when the cost function is obtained, the feature data category of the multidimensional driving behavior feature data is used as an inner loop frequency, that is, N is used as an inner loop frequency, the feature data category of the pay-out feature data is used as an outer loop frequency, that is, M is used as an outer loop frequency, and the association relationship between each feature data in the pay-out feature data and each driving behavior feature data in the multidimensional driving behavior feature data is identified by the double loop iteration method.
And a cost function is obtained in a machine learning mode, and a weight coefficient value corresponding to each driving behavior characteristic data in the multidimensional driving behavior characteristic data when the cost function is the minimum value is used as a target configuration item, so that the accuracy of a driving behavior and claim relationship prediction model is ensured.
And step 206, collecting driving behavior data uploaded by the vehicle owner to be tested, and performing numerical processing to obtain multi-dimensional driving behavior characteristic data corresponding to the vehicle owner to be tested, wherein the driving behavior characteristic data comprises a driving behavior place.
By executing the steps 201 to 202, multidimensional driving behavior characteristic data corresponding to the new owner is obtained.
And step 207, inputting the driving behavior characteristic data serving as input data into the driving behavior and claim relationship prediction model, and predicting the claim characteristic data corresponding to the vehicle owner to be tested.
And step 208, outputting the characteristic data of the claims as pricing basis.
According to the method, modeling is carried out according to multi-dimensional driving behavior characteristic data and insurance claim characteristic data corresponding to historical vehicle owners, and a driving behavior and claim relationship prediction model is obtained; inputting driving behavior characteristic data of a new insurance vehicle owner client into the driving behavior and claim relationship prediction model, and predicting the corresponding out-of-insurance claim characteristic data of the vehicle owner to be detected; and outputting the characteristic data of the claims as pricing basis. The method and the system build a driving behavior and claim relationship prediction model through a machine learning mode, predict the insurance claim characteristic data of the new insurance vehicle owner through the driving behavior and claim relationship prediction model after learning training, and combine the driving behavior data of the new insurance vehicle owner to carry out insurance pricing, so that the method and the system are more scientific.
The embodiment of the application can acquire and process related data based on an artificial intelligence technology. Among them, artificial Intelligence (AI) is a theory, method, technique and application system that simulates, extends and expands human Intelligence using a digital computer or a machine controlled by a digital computer, senses the environment, acquires knowledge and uses the knowledge to obtain the best result.
The artificial intelligence infrastructure generally includes technologies such as sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, big data processing technologies, operation/interaction systems, mechatronics, and the like. The artificial intelligence software technology mainly comprises a computer vision technology, a robot technology, a biological recognition technology, a voice processing technology, a natural language processing technology, machine learning/deep learning and the like.
In the embodiment of the application, a driving behavior and claim relation prediction model is established in a machine learning mode, then, the driving behavior and claim relation prediction model after learning training is used for predicting the insurance claim characteristic data of the new insurance vehicle owner, and insurance pricing is carried out by combining the driving behavior data of the new insurance vehicle owner, so that the method is more scientific.
With further reference to fig. 3, as an implementation of the method shown in fig. 2, the present application provides an embodiment of an insurance pricing guidance device based on driving behavior of an owner, where the embodiment of the device corresponds to the embodiment of the method shown in fig. 2, and the device may be specifically applied to various electronic devices.
As shown in fig. 3, the insurance pricing guidance device 300 according to the present embodiment includes: the driving behavior data acquisition module 301, the driving behavior characteristic data acquisition module 302, the claim paying characteristic data acquisition module 303, the characteristic data segmentation processing module 304, the prediction model modeling module 305, the test data acquisition module 306, the model prediction module 307 and the output result feedback module 308. Wherein:
the driving behavior data acquisition module 301 is used for acquiring driving behavior data uploaded by a plurality of vehicle owners respectively;
the driving behavior characteristic data acquisition module 302 is configured to perform numerical processing on the driving behavior data corresponding to each vehicle owner based on a preset processing component to acquire multidimensional driving behavior characteristic data;
the insurance claim pay characteristic data acquisition module 303 is configured to acquire insurance claim pay characteristic data corresponding to each of the plurality of car owners according to a preset insurance acceptance information platform;
the feature data segmentation processing module 304 is configured to perform regional segmentation processing on the multidimensional driving behavior feature data and the claim paying feature data according to driving behaviors corresponding to the plurality of vehicle owners to obtain N prediction model sample groups, where N is a positive integer;
the prediction model modeling module 305 is configured to respectively model the N prediction model sample groups by using an elastic network regression algorithm, and obtain N prediction models of driving behavior and claim relationship;
the test data acquisition module 306 is configured to acquire driving behavior data uploaded by a vehicle owner to be tested, perform numerical processing, and acquire multi-dimensional driving behavior feature data corresponding to the vehicle owner to be tested, where the driving behavior feature data includes a driving behavior place;
the model prediction module 307 is configured to input the driving behavior feature data as input data to the driving behavior and claim relationship prediction model, and predict claim characteristic data corresponding to the vehicle owner to be detected;
and the output result feedback module 308 is configured to output the characteristic data of the claims as a pricing basis.
Modeling is carried out according to multidimensional driving behavior characteristic data and insurance claim characteristic data corresponding to historical vehicle owners, and a driving behavior and claim relationship prediction model is obtained; inputting driving behavior characteristic data of a customer of a new insured vehicle owner into the driving behavior and claim relationship prediction model, and predicting the corresponding insurance claim characteristic data of the vehicle owner to be tested; and outputting the characteristic data of the claims as pricing basis. The method and the system build a driving behavior and claim relationship prediction model through a machine learning mode, predict the insurance claim characteristic data of the new insurance vehicle owner through the driving behavior and claim relationship prediction model after learning training, and combine the driving behavior data of the new insurance vehicle owner to carry out insurance pricing, so that the method and the system are more scientific.
Those skilled in the art will appreciate that all or part of the processes of the methods of the embodiments described above can be implemented by hardware related to computer readable instructions, which can be stored in a computer readable storage medium, and when executed, the programs can include the processes of the embodiments of the methods described above. The storage medium may be a non-volatile storage medium such as a magnetic disk, an optical disk, a Read-Only Memory (ROM), or a Random Access Memory (RAM).
It should be understood that, although the steps in the flowcharts of the figures are shown in order as indicated by the arrows, the steps are not necessarily performed in order as indicated by the arrows. The steps are not performed in the exact order shown and may be performed in other orders unless explicitly stated herein. Moreover, at least a portion of the steps in the flow chart of the figure may include multiple sub-steps or multiple stages, which are not necessarily performed at the same time, but may be performed at different times, which are not necessarily performed in sequence, but may be performed alternately or alternately with other steps or at least a portion of the sub-steps or stages of other steps.
In order to solve the technical problem, an embodiment of the present application further provides a computer device. Referring to fig. 4 in particular, fig. 4 is a block diagram of a basic structure of a computer device according to the embodiment.
The computer device 4 comprises a memory 4a, a processor 4b, and a network interface 4c, which are communicatively connected to each other via a system bus. It is noted that only a computer device 4 having components 4a-4c is shown, but it is understood that not all of the shown components are required to be implemented, and that more or fewer components may be implemented instead. As will be understood by those skilled in the art, the computer device is a device capable of automatically performing numerical calculation and/or information processing according to a preset or stored instruction, and the hardware includes, but is not limited to, a microprocessor, an Application Specific Integrated Circuit (ASIC), a Programmable Gate Array (FPGA), a Digital Signal Processor (DSP), an embedded device, and the like.
The computer device can be a desktop computer, a notebook, a palm computer, a cloud server and other computing devices. The computer equipment can carry out man-machine interaction with a user through a keyboard, a mouse, a remote controller, a touch panel or voice control equipment and the like.
The memory 4a includes at least one type of readable storage medium including a flash memory, a hard disk, a multimedia card, a card type memory (e.g., SD or DX memory, etc.), a Random Access Memory (RAM), a Static Random Access Memory (SRAM), a Read Only Memory (ROM), an Electrically Erasable Programmable Read Only Memory (EEPROM), a Programmable Read Only Memory (PROM), a magnetic memory, a magnetic disk, an optical disk, etc. In some embodiments, the storage 4a may be an internal storage unit of the computer device 4, such as a hard disk or a memory of the computer device 4. In other embodiments, the memory 4a may also be an external storage device of the computer device 4, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), and the like, which are provided on the computer device 4. Of course, the memory 4a may also comprise both an internal storage unit of the computer device 4 and an external storage device thereof. In this embodiment, the memory 4a is generally used for storing an operating system and various application software installed in the computer device 4, such as computer readable instructions of an insurance pricing guidance method based on driving behaviors of vehicle owners. The memory 4a may also be used to temporarily store various types of data that have been output or are to be output.
The processor 4b may be a Central Processing Unit (CPU), a controller, a microcontroller, a microprocessor, or other data Processing chip in some embodiments. The processor 4b is typically used to control the overall operation of the computer device 4. In this embodiment, the processor 4b is configured to execute computer readable instructions stored in the memory 4a or process data, such as executing computer readable instructions of the insurance pricing guidance method based on driving behaviors of vehicle owners.
The network interface 4c may comprise a wireless network interface or a wired network interface, and the network interface 4c is generally used for establishing communication connections between the computer device 4 and other electronic devices.
The computer equipment that this embodiment provided belongs to financial science and technology technical field. Modeling is carried out according to multidimensional driving behavior characteristic data and insurance claim characteristic data corresponding to historical vehicle owners, and a driving behavior and claim relationship prediction model is obtained; inputting driving behavior characteristic data of a new insurance vehicle owner client into the driving behavior and claim relationship prediction model, and predicting the corresponding out-of-insurance claim characteristic data of the vehicle owner to be detected; and outputting the characteristic data of the claims as pricing basis. According to the method and the system, a driving behavior and claim relationship prediction model is established in a machine learning mode, then, the driving behavior and claim relationship prediction model after learning training is used for predicting the insurance claim characteristic data of a new insurance vehicle owner, and insurance pricing is carried out by combining the driving behavior data of the new insurance vehicle owner, so that the method and the system are more scientific.
The present application further provides another embodiment, which is to provide a computer readable storage medium storing computer readable instructions executable by a processor to cause the processor to perform the steps of the method for pricing guidance for insurance based on driving behavior of an owner as described above.
The embodiment provides a computer-readable storage medium, and belongs to the technical field of financial technologies. Modeling is carried out according to multidimensional driving behavior characteristic data and insurance claim characteristic data corresponding to historical vehicle owners, and a driving behavior and claim relationship prediction model is obtained; inputting driving behavior characteristic data of a customer of a new insured vehicle owner into the driving behavior and claim relationship prediction model, and predicting the corresponding insurance claim characteristic data of the vehicle owner to be tested; and outputting the characteristic data of the claims as pricing basis. According to the method and the system, a driving behavior and claim relationship prediction model is established in a machine learning mode, then, the driving behavior and claim relationship prediction model after learning training is used for predicting the insurance claim characteristic data of a new insurance vehicle owner, and insurance pricing is carried out by combining the driving behavior data of the new insurance vehicle owner, so that the method and the system are more scientific.
Through the above description of the embodiments, those skilled in the art will clearly understand that the method of the above embodiments can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware, but in many cases, the former is a better implementation manner. Based on such understanding, the technical solutions of the present application may be embodied in the form of a software product, which is stored in a storage medium (such as ROM/RAM, magnetic disk, optical disk) and includes instructions for enabling a terminal device (such as a mobile phone, a computer, a server, an air conditioner, or a network device) to execute the method according to the embodiments of the present application.
It should be understood that the above-described embodiments are merely exemplary of some, and not all, embodiments of the present application, and that the drawings illustrate preferred embodiments of the present application without limiting the scope of the claims appended hereto. This application is capable of embodiments in many different forms and the embodiments are provided so that this disclosure will be thorough and complete. Although the present application has been described in detail with reference to the foregoing embodiments, it will be apparent to one skilled in the art that the present application may be practiced without modification or with equivalents of some of the features described in the foregoing embodiments. All equivalent structures made by using the contents of the specification and the drawings of the present application are directly or indirectly applied to other related technical fields and are within the protection scope of the present application.
Claims (10)
1. An insurance pricing guidance method based on driving behaviors of car owners is characterized by comprising the following steps:
collecting driving behavior data respectively uploaded by a plurality of vehicle owners;
performing numerical processing on the driving behavior data corresponding to each vehicle owner based on a preset processing assembly to obtain multi-dimensional driving behavior characteristic data;
acquiring the characteristic data of the claims for the insurance benefits corresponding to the car owners respectively according to a preset underwriting information platform;
performing regional segmentation processing on the multidimensional driving behavior characteristic data and the pay-out characteristic data according to the driving behaviors corresponding to the plurality of vehicle owners to obtain N prediction model sample groups, wherein N is a positive integer;
modeling the N prediction model sample groups respectively by adopting an elastic network regression algorithm to obtain N driving behavior and claim relationship prediction models;
acquiring driving behavior data uploaded by a vehicle owner to be detected, and performing numerical processing to acquire multi-dimensional driving behavior characteristic data corresponding to the vehicle owner to be detected, wherein the driving behavior characteristic data comprises a driving behavior place;
inputting the driving behavior characteristic data serving as input data into the driving behavior and claim relationship prediction model, and predicting the claim characteristic data corresponding to the vehicle owner to be tested;
and outputting the characteristic data of the insurance claim payment as a pricing basis.
2. The insurance pricing guidance method based on vehicle owner driving behaviors according to claim 1, wherein the step of obtaining multidimensional driving behavior feature data by numerically processing the driving behavior data corresponding to each vehicle owner based on a preset processing component specifically comprises:
according to a preset time limit condition and a preset algorithm plug-in, carrying out numerical processing on the driving behavior data corresponding to each vehicle owner to obtain numerical driving behavior data corresponding to each vehicle owner;
and taking the numerical driving behavior data corresponding to each vehicle owner as the multi-dimensional driving behavior characteristic data corresponding to the vehicle owner.
3. The insurance pricing guidance method based on the driving behaviors of the car owners according to claim 2, wherein the step of obtaining the characteristic data of the insurance claim corresponding to each of the car owners according to a preset insurance acceptance information platform specifically comprises:
according to the corresponding time limiting condition and a preset algorithm plug-in, carrying out numerical processing on the claim data corresponding to each vehicle owner to obtain the numerical claim data corresponding to each vehicle owner;
and taking the numerical insurance claim data corresponding to each vehicle owner as insurance claim characteristic data corresponding to the vehicle owner.
4. The insurance pricing and guiding method based on the driving behaviors of the car owners according to claim 1, wherein the step of performing regional segmentation processing on the multidimensional driving behavior characteristic data and the claim settlement characteristic data according to the driving behaviors corresponding to the car owners specifically comprises:
in the process of executing the step of collecting the driving behavior data respectively uploaded by a plurality of vehicle owners, the method further comprises the following steps: acquiring driving behavior places where the plurality of vehicle owners respectively locate when the driving behavior data is acquired according to a preset data acquisition APP or a positioning interface built in terminal equipment provided with the preset data acquisition APP;
integrating and counting the driving behavior places of the plurality of car owners, and setting different numbers according to different driving behavior places;
setting a contrast relation between the multidimensional driving behavior characteristic data and the pay-out characteristic data corresponding to the same vehicle owner;
integrating the multidimensional driving behavior characteristic data and the pay-out characteristic data which respectively correspond to different vehicle owners in the same driving behavior area to generate a prediction model sample group, and using the difference numbers as the difference numbers of the prediction model sample group.
5. The insurance pricing guidance method based on vehicle owner driving behaviors according to claim 4, wherein the prediction model sample set comprises multidimensional driving behavior feature data and pay-out feature data of different vehicle owners in the same driving behavior region, and the step of modeling the N prediction model sample sets respectively by using an elastic network regression algorithm to obtain N driving behavior and pay relationship prediction models specifically comprises:
acquiring the multidimensional driving behavior characteristic data and the insurance claim characteristic data which respectively correspond to different car owners in the same driving behavior region and are contained in the current prediction model sample group according to the distinguishing numbers;
inputting the multidimensional driving behavior characteristic data and the pay-out characteristic data into a pre-constructed artificial intelligence learning model, performing learning training, and obtaining a linear regression relationship between the multidimensional driving behavior characteristic data and the pay-out characteristic data, wherein when the artificial intelligence learning model is pre-constructed, a cost function of the artificial intelligence learning model is dynamically adjusted in advance according to an elastic network regression algorithm;
and obtaining a model after learning training corresponding to each distinguishing number, namely obtaining a driving behavior and claim relationship prediction model with the same number as the segmentation processing number.
6. The insurance pricing guidance method based on the driving behaviors of the vehicle owners according to claim 5, wherein before the step of inputting the multidimensional driving behavior feature data and the pay-out feature data into a pre-constructed artificial intelligence learning model for learning training, the method further comprises:
integrating the multidimensional driving behavior characteristic data and the insurance claim paying characteristic data which respectively correspond to different vehicle owners in the same driving behavior place;
according to the integration result and a preset first proportional algorithm, acquiring weight coefficients of all the driving behavior characteristic data in the multidimensional driving behavior characteristic data in all different vehicle owners in the same driving behavior area, and constructing a weight coefficient matrix and a first regular expression item corresponding to the multidimensional driving behavior characteristic data;
and according to the integration result and a preset second proportional algorithm, acquiring the weight coefficient of each claim characteristic data in the claim characteristic data in all different vehicle owners in the same driving behavior, and constructing a second regular expression corresponding to the claim characteristic data.
7. The insurance pricing guidance method based on driving behavior of vehicle owners according to claim 6, wherein the step of dynamically adjusting the cost function of the artificial intelligent learning model in advance according to the elastic network regression algorithm when the artificial intelligent learning model is pre-constructed specifically comprises:
according to a preset elastic network regression algorithm:
obtaining a weight coefficient value corresponding to each driving behavior characteristic data in the multidimensional driving behavior characteristic data when cos (x) is the minimum value, wherein omega is T A weight coefficient matrix representing the multidimensional driving behavior characteristic data, i | | ω | | sweet wind 1 Is a first regular expression term, | omega | | caldol 1 ＝|ω 1 |+|ω 2 |+…+|ω i-1 |+|ω i I is the serial number of the current characteristic data in the multidimensional driving behavior characteristic data, and N is the serial number in the multidimensional driving behavior characteristic dataThe number of the characteristic data, | omega | non-calculation 2 In order for the second regular expression term to be,
j is the serial number of the current feature in the claim characteristic data, M is the number of all feature data in the claim characteristic data, ω is a weight coefficient corresponding to each driving behavior feature data in the multidimensional driving behavior feature data, and λ and ρ are preset constants for controlling the sizes of the first regular expression term and the second regular expression term together;
when cos (x) is the minimum value, the weight coefficient value corresponding to each driving behavior characteristic data in the multi-dimensional driving behavior characteristic data is used as a target configuration item to carry out weight configuration on the pre-constructed artificial intelligence learning model;
and the artificial intelligence learning model after the weight configuration is finished is a driving behavior and claim relationship prediction model after learning training is finished.
8. The utility model provides an insurance pricing guides device based on car owner's driving action which characterized in that includes:
the driving behavior data acquisition module is used for acquiring driving behavior data uploaded by a plurality of vehicle owners respectively;
the driving behavior characteristic data acquisition module is used for carrying out numerical processing on the driving behavior data corresponding to each vehicle owner based on a preset processing assembly to acquire multi-dimensional driving behavior characteristic data;
the insurance claim pay characteristic data acquisition module is used for acquiring insurance claim pay characteristic data corresponding to the vehicle owners respectively according to a preset underwriting information platform;
the characteristic data segmentation processing module is used for performing regional segmentation processing on the multidimensional driving behavior characteristic data and the insurance claim paying characteristic data according to the driving behaviors corresponding to the car owners to obtain N prediction model sample groups, wherein N is a positive integer;
the prediction model modeling module is used for respectively modeling the N prediction model sample groups by adopting an elastic network regression algorithm to obtain N prediction models of driving behavior and claim relationship;
the test data acquisition module is used for acquiring driving behavior data uploaded by a vehicle owner to be tested, carrying out numerical processing and acquiring multi-dimensional driving behavior characteristic data corresponding to the vehicle owner to be tested, wherein the driving behavior characteristic data comprises a driving behavior place;
the model prediction module is used for inputting the driving behavior characteristic data serving as input data into the driving behavior and claim relationship prediction model and predicting the claim characteristic data corresponding to the vehicle owner to be tested;
and the output result feedback module is used for outputting the characteristic data of the claims as pricing basis.
9. A computer device comprising a memory having computer readable instructions stored therein and a processor which when executed implements the steps of the method of insurance pricing guidance based on vehicle owner driving behavior of any of claims 1 to 7.
10. A computer readable storage medium having computer readable instructions stored thereon which, when executed by a processor, implement the steps of the insurance pricing guidance method based on vehicle owner driving behavior according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211559307.6A CN115797084A (en) | 2022-12-06 | 2022-12-06 | Insurance pricing guidance method based on driving behavior of vehicle owner and related equipment thereof |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211559307.6A CN115797084A (en) | 2022-12-06 | 2022-12-06 | Insurance pricing guidance method based on driving behavior of vehicle owner and related equipment thereof |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115797084A true CN115797084A (en) | 2023-03-14 |
Family
ID=85417423
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211559307.6A Pending CN115797084A (en) | 2022-12-06 | 2022-12-06 | Insurance pricing guidance method based on driving behavior of vehicle owner and related equipment thereof |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115797084A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117273961A (en) * | 2023-10-09 | 2023-12-22 | 上海金润联汇数字科技有限公司 | Assessment method, device, equipment and medium for vehicle insurance data |
-
2022
- 2022-12-06 CN CN202211559307.6A patent/CN115797084A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117273961A (en) * | 2023-10-09 | 2023-12-22 | 上海金润联汇数字科技有限公司 | Assessment method, device, equipment and medium for vehicle insurance data |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112148987A (en) | Message pushing method based on target object activity and related equipment | |
| CN113326991B (en) | Automatic authorization method, device, computer equipment and storage medium | |
| CN112085378B (en) | Resource allocation method, device, computer equipment and storage medium | |
| CN114926282A (en) | Abnormal transaction identification method and device, computer equipment and storage medium | |
| CN115099326A (en) | Behavior prediction method, behavior prediction device, behavior prediction equipment and storage medium based on artificial intelligence | |
| CN112925911A (en) | Complaint classification method based on multi-modal data and related equipment thereof | |
| CN115936895A (en) | Risk assessment method, device and equipment based on artificial intelligence and storage medium | |
| CN112990583A (en) | Method and equipment for determining mold entering characteristics of data prediction model | |
| CN115757075A (en) | Task abnormity detection method and device, computer equipment and storage medium | |
| CN115797084A (en) | Insurance pricing guidance method based on driving behavior of vehicle owner and related equipment thereof | |
| CN113506023A (en) | Working behavior data analysis method, device, equipment and storage medium | |
| CN117391866A (en) | Data processing method, device, equipment and storage medium thereof | |
| CN116843395A (en) | Alarm classification method, device, equipment and storage medium of service system | |
| CN115587830A (en) | Work task excitation method and device, computer equipment and storage medium | |
| CN112084408A (en) | List data screening method and device, computer equipment and storage medium | |
| CN115374861A (en) | Artificial intelligence based anomaly prediction method, device, equipment and storage medium | |
| CN117408820A (en) | Vehicle risk selection prediction method, device, equipment and storage medium thereof | |
| CN117391632A (en) | Case report processing method, device, computer equipment and storage medium | |
| CN117290597A (en) | Information pushing method, device, equipment and storage medium based on artificial intelligence | |
| CN116797380A (en) | Financial data processing method and related equipment thereof | |
| CN117407750A (en) | Metadata-based data quality monitoring method, device, equipment and storage medium | |
| CN116071169A (en) | Dynamic adjustment method, device and equipment for car insurance quote and storage medium thereof | |
| CN116977095A (en) | Dynamic wind control early warning method and device, computer equipment and storage medium | |
| CN117708366A (en) | Image retrieval method, device, equipment and storage medium based on artificial intelligence | |
| CN117853202A (en) | Product recommendation method, device, computer equipment 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 |