Fee setting method, device and computer equipment based on data processing
By performing grid analysis of users' driving trajectory and operation data, the problem of traditional insurance pricing relying on static data is solved, and the refined evaluation of driving style and personalized premium recommendations are realized, which improves the accuracy and scientificity of insurance. .
Patent Information
- Application Number
- CN202110435236.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2021-04-22
- Publication Date
- 2024-11-08
- Estimated Expiration
- 2041-04-22
AI Technical Summary
The traditional car insurance pricing model relies on the static data of the vehicle and cannot accurately evaluate the driver's risk factors, resulting in low premium accuracy and UBI's mileage pricing method that is flawed, making it impossible to effectively distinguish driving technology and risk probability.
By receiving the user's vehicle insurance request, querying their driving trajectory and operation data, performing grid processing, analyzing the driving labels and scores of each grid, accumulating the driving score, determining the vehicle premium based on the score, and recommending matching insurance products .
It realizes a refined analysis of users' driving styles, provides personalized premium customization, and improves the scientificity of risk assessment and premium accuracy of vehicle insurance.
Smart Images

Figure CN113065902B_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the technical field of data analysis, and in particular to a fee setting method, device and computer equipment based on data processing. Background Art
[0002] After purchasing a vehicle, users generally need to purchase insurance for the vehicle. In addition to the compulsory traffic insurance, users usually purchase other commercial insurance. At present, traditional insurance products in the auto insurance market mainly use static data of the vehicle to evaluate the vehicle premium, such as the vehicle model, manufacturer, and age, but risks are often caused by human factors, and personal risk factors are complex and diverse, so information asymmetry has become a common problem. For example, insurance companies cannot know the driver's driving behavior, and the insured may hide personal information to gain benefits. Therefore, the pricing model of traditional insurance products is unreasonable.
[0003] With the development of the Internet of Vehicles, Internet of Vehicles technology is increasingly being used in the insurance industry. Therefore, innovative insurance products based on UBI (Usage Based Insurance) have emerged. However, the current UBI pricing based on mileage has serious defects. For example, people who drive frequently have good driving skills and habits, and have high mileage but a low probability of accidents. People who rarely drive have a higher probability of accidents. Therefore, this pricing method makes the accuracy of the set vehicle premiums low. Summary of the invention
[0004] The main purpose of this application is to provide a fee setting method, device and computer equipment based on data processing, aiming to solve the technical problem that the current fee setting method based on data processing is relatively rough and has low accuracy.
[0005] In order to achieve the above-mentioned invention object, the present application proposes a fee setting method based on data processing, comprising:
[0006] Receiving a vehicle insurance formulation request initiated by a user, and extracting user information of the user from the vehicle insurance formulation request;
[0007] querying the driving trajectory of the user within a preset time period and the driving operation data of the user on the driving trajectory according to the user information; wherein the driving trajectory is pre-stored on a driving map;
[0008] Gridding the driving trajectory of the driving map to obtain a plurality of grids;
[0009] Analyze the sub-driving trajectory and sub-driving operation data of the user in each grid, and determine the optimal driving label of the user in each grid according to the analysis result; wherein the sub-driving trajectory is the driving trajectory in a single grid, and the sub-driving operation data is the driving operation data of the user on the sub-driving trajectory;
[0010] The driving scores of the corresponding grids are determined according to the optimal driving labels of the grids, the driving scores of the grids are accumulated to obtain the driving score of the user on the driving trajectory, and the vehicle insurance premium of the user is determined according to the driving score.
[0011] Preferably, the step of analyzing the sub-driving trajectory and sub-driving operation data of the user in each grid and determining the optimal driving label of the user in each grid according to the analysis result includes:
[0012] Acquire driving operation data of other users in the same grid except the user;
[0013] The sub-driving trajectory, sub-driving operation data and driving operation data of other users in each grid are analyzed to determine the optimal driving label of the user in each grid.
[0014] Furthermore, after the step of determining the optimal driving label of the user in each grid according to the analysis result, the method further includes:
[0015] Filter out target driving labels that affect safe driving from the optimal driving labels of each grid;
[0016] Calculate the number of grids of the same target driving label, sort the target driving labels in descending order of the number of grids, and obtain the target driving labels with the first N grid numbers, where N is an integer greater than or equal to 1;
[0017] Recommending corresponding insurance products to the user based on the top N target driving tags; wherein the insurance products contain insurance clauses for the top N target driving tags.
[0018] Furthermore, before the step of querying the driving trajectory of the user within a preset time period according to the user information, it also includes:
[0019] Get the user's trajectory points at each time point;
[0020] Filtering and denoising the trajectory points to obtain target trajectory points;
[0021] Segmenting the target trajectory point according to the time interval of the target trajectory point to obtain at least one trajectory segment;
[0022] The at least one trajectory segment is fitted onto an actual driving road to obtain a driving trajectory of the user within a preset time period.
[0023] Preferably, the step of determining the driving scores of the corresponding grids according to the optimal driving labels of the grids comprises:
[0024] According to the optimal driving labels of each grid, the optimal driving label value of each optimal driving label is searched from the comparison table; wherein the optimal driving label values corresponding to each optimal driving label are pre-stored in the comparison table;
[0025] The optimal driving label value of each optimal driving label is used as the driving score of each corresponding grid.
[0026] Furthermore, before the step of querying the optimal driving label value of each optimal driving label from the comparison table according to the optimal driving label of each grid, it also includes:
[0027] Obtain pre-collected vehicle insurance claim records;
[0028] According to the vehicle insurance compensation records, the total insurance compensation amount caused by various optimal driving labels in historical traffic accidents is counted;
[0029] The optimal driving label values of various optimal driving labels are set according to the total insurance compensation amount, and the optimal driving label values of various optimal driving labels are stored in a comparison table.
[0030] Preferably, the step of calculating the total insurance compensation amount caused by various optimal driving labels in historical traffic accidents according to the vehicle insurance compensation record includes:
[0031] According to the vehicle insurance compensation record, query the number of traffic accidents that occurred in historical traffic accidents for various optimal driving labels and the insurance compensation amount caused by each traffic accident;
[0032] The total insurance compensation amount is calculated based on the number of traffic accidents and the insurance compensation amount caused by each traffic accident.
[0033] The present application also provides a fee setting device based on data processing, comprising:
[0034] An extraction module, used to receive a vehicle insurance formulation request initiated by a user, and extract user information of the user from the vehicle insurance formulation request;
[0035] A query module, used to query the driving trajectory of the user within a preset time period and the driving operation data of the user on the driving trajectory according to the user information; wherein the driving trajectory is pre-stored on a driving map;
[0036] A grid processing module, used for gridding the driving trajectory of the driving map to obtain a plurality of grids;
[0037] An analysis module, used for analyzing the sub-driving trajectory and sub-driving operation data of the user in each grid, and determining the optimal driving label of the user in each grid according to the analysis result; wherein the sub-driving trajectory is the driving trajectory in a single grid, and the sub-driving operation data is the driving operation data of the user on the sub-driving trajectory;
[0038] A determination module is used to determine the driving scores of the corresponding grids according to the optimal driving labels of the grids, accumulate the driving scores of the grids to obtain the driving score of the user on the driving trajectory, and determine the vehicle insurance premium of the user according to the driving score.
[0039] The present application also provides a computer device, comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of any one of the above methods when executing the computer program.
[0040] The present application also provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the steps of any of the above-mentioned methods are implemented.
[0041] The fee setting method, device and computer equipment based on data processing of the present application receive a vehicle insurance formulation request initiated by a user, and extract the user information of the user from the vehicle insurance formulation request; query the driving trajectory of the user within a preset time period and the driving operation data of the user on the driving trajectory according to the user information; grid the driving trajectory to obtain multiple grids; and analyze the sub-driving trajectory and sub-driving operation data of the user in each grid, and determine the optimal driving label of the user in each grid according to the analysis result; determine the driving score of each corresponding grid according to the optimal driving label of each grid, and obtain the driving score of the user on the driving trajectory after accumulating the driving scores of each grid, and determine the vehicle premium of the user according to the driving score, so as to obtain the optimal driving label of each driving trajectory of the user by analyzing each driving trajectory of the user within the preset time period, and realize the refined analysis of the user's driving style, so as to provide a strong basis for formulating a matching vehicle premium for each user, so that the driving score and vehicle premium finally obtained are more in line with the actual situation of each user, and personalized customization is realized, and the risk assessment of vehicle insurance is more complete and scientific, thereby improving the accuracy of vehicle premium. BRIEF DESCRIPTION OF THE DRAWINGS
[0042] Figure 1 A flowchart of a method for setting fees based on data processing according to an embodiment of the present application;
[0043] Figure 2 This is a schematic block diagram of the structure of a fee setting device based on data processing according to an embodiment of the present application;
[0044] Figure 3 A schematic block diagram of the structure of a computer device according to an embodiment of the present application.
[0045] The realization of the purpose, functional features and advantages of this application will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION
[0046] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.
[0047] Reference Figure 1 , a method for setting fees based on data processing is provided in an embodiment of the present application, and the method for setting fees based on data processing comprises the steps of:
[0048] S1. receiving a vehicle insurance formulation request initiated by a user, and extracting user information of the user from the vehicle insurance formulation request;
[0049] S2. Querying the driving trajectory of the user within a preset time period and the driving operation data of the user on the driving trajectory according to the user information; wherein the driving trajectory is pre-stored on a driving map;
[0050] S3, gridding the driving trajectory of the driving map to obtain a plurality of grids;
[0051] S4, analyzing the sub-driving trajectory and sub-driving operation data of the user in each grid, and determining the optimal driving label of the user in each grid according to the analysis result; wherein the sub-driving trajectory is the driving trajectory in a single grid, and the sub-driving operation data is the driving operation data of the user on the sub-driving trajectory;
[0052] S5. Determine a driving score of each corresponding grid according to the optimal driving label of each grid, accumulate the driving scores of each grid to obtain a driving score of the user on the driving trajectory, and determine a vehicle insurance premium of the user according to the driving score.
[0053] As described in step S1, when applying for insurance for a vehicle, the user can log in to the insurance application interface through a mobile terminal or the insurance company's self-service terminal and initiate a vehicle insurance formulation request. After the server receives the vehicle insurance formulation request, it extracts the user's user information from the vehicle insurance formulation request. The user information includes at least one of a user name, an ID number, and an insurance account number.
[0054] As described in step S2, each user can be encouraged to upload the driving trajectory and the user's driving operation data on the driving trajectory in the APP of the mobile terminal in advance by means of rewards, or cooperate with manufacturers to obtain Internet of Vehicles data, extract the driving trajectory and the user's driving operation data on the driving trajectory from the Internet of Vehicles data, and save the uploaded driving trajectory and its driving operation data in the database for subsequent query and use. When the server receives the user's vehicle insurance formulation request, it queries the user's driving trajectory in the recent period of time according to the user information to analyze the driving trajectory in the recent period of time and determine the user's driving style. Among them, the driving trajectory can be a vector in seconds, including: time, longitude and latitude, altitude, direction, speed. The driving operation data is the user's behavior data on the driving trajectory, such as braking to slow down, stepping on the accelerator to accelerate, turning right, etc.
[0055] As described in step S3, in this step, the driving trajectory can be gridded according to the driving time period to form multiple grids with 10*10KM as the unit, each grid is used as a calculation unit, and each grid contains at least one section of the driving trajectory.
[0056] As described in step S4, in this step, the driving trajectory is divided into multiple sub-driving trajectories in units of grids, and the driving operation data of the user on the sub-driving trajectory is used as the sub-driving operation data. According to the sub-driving trajectory and the sub-driving operation data in each grid, at least one driving label of the user in each grid is analyzed and determined, and the optimal driving label that best matches the user on the sub-driving trajectory is screened out from at least one driving label. Among them, the driving data includes: average speed per 100 kilometers, number of rapid accelerations per 100 kilometers, number of rapid decelerations per 100 kilometers, number of sharp turns per 100 kilometers, number of speeding per 100 kilometers, traffic jam time per 100 kilometers, average mileage per trip, average driving speed per trip, average number of rapid accelerations per trip, average number of rapid decelerations per trip, average number of sharp turns per trip, average number of speeding per trip, maximum driving speed, maximum number of rapid accelerations, maximum number of rapid decelerations, maximum number of sharp turns, maximum number of speeding, and the longest fatigue driving time. One or more of the optimal driving label is used to characterize the driving behavior characteristics that best match the user, such as speeding, sudden braking, not turning on the turn signal, running a red light, etc.
[0057] As described in step S5, the driving scores of the corresponding grids are determined according to the optimal driving labels of each grid, and the driving scores of all grids are accumulated to obtain the driving score of the user on the driving trajectory, and the vehicle premium of the user is determined according to the driving score, so as to achieve a refined analysis of the user's driving style, so as to provide a strong basis for formulating a matching vehicle premium for each user, so that the risk assessment of vehicle insurance is more complete and scientific, thereby improving the accuracy of the vehicle premium. Among them, the level of driving score is determined by the level of driving risk of the user reflected by the optimal driving label. For example, when the optimal driving label reflects that the user has dangerous driving behavior, the driving score of the corresponding grid is low; on the contrary, when the optimal driving label reflects that the user does not have dangerous driving behavior, the driving score of the corresponding grid is high, so as to determine the driving score corresponding to each optimal driving label. In addition, the vehicle premium of the user is inversely proportional to the driving score, that is, when the user's driving score is higher, it indicates that the user's driving habits are better, and the vehicle premium for the user is lower at this time.
[0058] The fee setting method based on data processing of the present application receives a vehicle insurance formulation request initiated by a user, and extracts the user information of the user from the vehicle insurance formulation request; queries the driving trajectory of the user within a preset time period and the driving operation data of the user on the driving trajectory according to the user information; performs grid processing on the driving trajectory to obtain multiple grids; and analyzes the sub-driving trajectory and sub-driving operation data of the user in each grid, and determines the optimal driving label of the user in each grid according to the analysis result; determines the driving score of each corresponding grid according to the optimal driving label of each grid, and obtains the driving score of the user on the driving trajectory after accumulating the driving scores of each grid, and determines the vehicle premium of the user according to the driving score, so as to obtain the optimal driving label of each driving trajectory of the user by analyzing each driving trajectory of the user within the preset time period, and realizes the refined analysis of the user's driving style, so as to provide a strong basis for formulating a matching vehicle premium for each user, so that the driving score and vehicle premium finally obtained are more in line with the actual situation of each user, and personalized customization is realized, and the risk assessment of vehicle insurance is more complete and scientific, thereby improving the accuracy of vehicle premium.
[0059] In one embodiment, the step of determining the vehicle insurance premium of the user according to the driving score may specifically include:
[0060] Extracting the number of times the user drives in the driving trajectory from the driving operation data, and determining a driving weight based on the number of times the user drives; wherein the driving weight is inversely proportional to the number of times the user drives;
[0061] The vehicle insurance premium of the user is determined according to the driving score and the driving weight.
[0062] In this embodiment, the driving weight can be set according to the number of times the user drives on different driving tracks. For example, when the user drives on a driving track with a small number of driving times, it indicates that the user is relatively unfamiliar with the driving track, and the corresponding driving weight is set to be high. At this time, even on the basis of the same driving score, the higher the driving weight, the larger the value calculated, which indicates that the user's driving habits in unfamiliar driving tracks are also good, and the corresponding vehicle premium set for the user is low. On the contrary, when the user drives on a driving track with a large number of driving times, it indicates that the user is relatively familiar with the driving track, and the corresponding driving weight is set to be low. At this time, even on the basis of the same driving score, the lower the driving weight, the smaller the value calculated, and the corresponding vehicle premium set for the user is high. Therefore, by further combining the user's familiarity with the driving track to determine the vehicle insurance, the calculated vehicle premium is more in line with the user's actual driving situation.
[0063] In one embodiment, in step S4, the step of analyzing the sub-driving trajectory and sub-driving operation data of the user in each grid and determining the optimal driving label of the user in each grid according to the analysis result may specifically include:
[0064] S41, obtaining driving operation data of other users in the same grid except the user;
[0065] S42: Analyze the sub-driving trajectory, sub-driving operation data of the user in each grid and the driving operation data of other users to determine the optimal driving label of the user in each grid.
[0066] In this embodiment, the quality of a user's driving behavior is not only related to the user's own driving behavior, but also to the road environment and the driving operations of other drivers in the same area. By comparing with other drivers in the same area, the quality of the user's driving habits can be better portrayed. Therefore, this embodiment analyzes the sub-driving trajectory and sub-driving operation data of the user in each grid, and combines the driving operation data of other users to determine the optimal driving label of the user in each grid, so that the optimal driving label obtained by analysis is more accurate.
[0067] The driving operation data of other users in the same grid may include the relative speed of the user with other drivers in the same area grid, the amount of sudden acceleration events compared with other drivers, and the amount of angular velocity exceeding a threshold compared with other drivers.
[0068] In addition, the optimal driving tag for users can be determined by combining road environment data analysis. Road environment data can be obtained by downloading open source data sets, such as the OpenStreetMap published by the country, to obtain road environment data on the driving trajectory. The road environment data includes road latitude and longitude, road type, speed limit and other information.
[0069] In one embodiment, in step S4, after the step of determining the optimal driving label of the user in each grid according to the analysis result, the following steps may also be included:
[0070] Filter out target driving labels that affect safe driving from the optimal driving labels of each grid;
[0071] Calculate the number of grids of the same target driving label, sort the target driving labels in descending order of the number of grids, and obtain the target driving labels with the first N grid numbers, where N is an integer greater than or equal to 1;
[0072] Recommending corresponding insurance products to the user based on the top N target driving tags; wherein the insurance products contain insurance clauses for the top N target driving tags.
[0073] This embodiment screens out target driving tags that affect safe driving based on all optimal driving tags, such as speeding, sudden braking, not using turn signals, and other types of target driving tags, and sorts the target driving tags according to the number of grids corresponding to the same target driving tag, and screens out the target driving tags with the top N grid numbers, and recommends corresponding insurance products according to the target driving tags with the top N grid numbers. Among them, the N position can be set according to actual needs. For example, when the user's top three optimal driving tags include wading, that is, when the user drives on a low-lying road for a long time or parks in a low-lying garage for a long time, the user can be recommended for wading insurance, which includes insurance clauses after wading, thereby achieving accurate recommendation of insurance. For example, if the user frequently makes sharp turns, sudden brakes, etc., it means that the user's driving behavior is relatively radical, not cautious enough, and easily leads to accidents. The probability of collision or other accidents is high, so an insurance product with a higher insurance amount can be recommended.
[0074] In one embodiment, before the step of querying the driving trajectory of the user within a preset time period according to the user information, the following steps may also be included:
[0075] Get the user's trajectory points at each time point;
[0076] Filtering and denoising the trajectory points to obtain target trajectory points;
[0077] Segmenting the target trajectory point according to the time interval of the target trajectory point to obtain at least one trajectory segment;
[0078] The at least one trajectory segment is fitted onto an actual driving road to obtain a driving trajectory of the user within a preset time period.
[0079] This embodiment can obtain the user's trajectory points at various time points by using a positioning device of the user's vehicle or a mobile terminal placed on the vehicle. The trajectory points can be represented in the form of coordinates, and data processing is performed on the obtained trajectory points, such as filtering and denoising, to filter out trajectory points containing noise to obtain target trajectory points; then, the target trajectory points are segmented according to the time interval of the target trajectory points to obtain at least one trajectory segment; and the user's driving trajectory is drawn using the at least one trajectory segment.
[0080] Among them, the denoising process of the track points in the track segment is to use the denoising algorithm to process the track points in the track segments of the multiple track segments formed by the above segmentation. In the denoising process, the parameters of the denoising algorithm can be adjusted in advance according to the characteristics of the track points in each track segment, and then the track points in the corresponding track segment are denoised according to the adjusted denoising algorithm. First, after obtaining the track segment to be denoised, the characteristic data of the track points in the current track segment are extracted, such as the number of track points, the interval time between two adjacent track points, the actual distance, and the speed of the track scene; based on these characteristics, the parameters of the denoising algorithm used at that time are adjusted so that the adjusted denoising algorithm is more suitable for denoising the track point data in the current track segment, and obtains track points that are closer to the actual situation. Then, the denoising algorithm with adjusted parameter values is used to denoise the track point data in the current track segment, and retain the non-noise track points. Among them, the types of denoising algorithms include various spatial clustering algorithms or filtering algorithms.
[0081] In addition, in order to ensure that the number of trajectory points contained in each trajectory segment is within a certain range and facilitate subsequent data processing, the trajectory segment containing more trajectory point data can be further divided into multiple trajectory segments to maintain the number of trajectory points in each trajectory segment within a specified range.
[0082] Furthermore, this embodiment fits the trajectory points that deviate from the actual driving road within a certain range to the nearest road network to restore the actual driving road trajectory corresponding to the trajectory points, thereby ensuring the accuracy of the driving trajectory.
[0083] In one embodiment, the step of determining the driving scores of the corresponding grids according to the optimal driving labels of the grids may specifically include:
[0084] According to the optimal driving labels of each grid, the optimal driving label value of each optimal driving label is searched from the comparison table; wherein the optimal driving label values corresponding to each optimal driving label are pre-stored in the comparison table;
[0085] The optimal driving label value of each optimal driving label is used as the driving score of each corresponding grid.
[0086] In this embodiment, the optimal driving label values of various optimal driving labels can be saved in the form of a comparison table, such as the optimal driving label value of speeding is -5, the optimal driving label value of not using a turn signal is -3, the optimal driving label value of running a red light is -10, the optimal driving label value of normal driving is 5, and the optimal driving label value of giving way to pedestrians is 8. The optimal driving label value can also be used directly or multiplied by a weight as the driving score of each grid, so as to simply and quickly determine the driving score of each grid.
[0087] Furthermore, before the step of searching the reference table for the optimal driving label value of each optimal driving label according to the optimal driving label of each grid, the method may further include:
[0088] Obtain pre-collected vehicle insurance claim records;
[0089] According to the vehicle insurance compensation records, the total insurance compensation amount caused by various optimal driving labels in historical traffic accidents is counted;
[0090] The optimal driving label values of various optimal driving labels are set according to the total insurance compensation amount, and the optimal driving label values of various optimal driving labels are stored in a comparison table.
[0091] In this embodiment, the driving score is directly or indirectly related to the user's insurance compensation, so the optimal driving label value can be determined based on the total insurance compensation caused by various optimal driving labels. For example, when the total insurance compensation caused by a traffic accident caused by running a red light is high, the set optimal driving label value is low, and the corresponding driving score is also low. Therefore, the vehicle insurance premium set for the user is higher, so that the optimal driving label value is determined based on the historical insurance compensation amount, which is more in line with the actual situation.
[0092] Preferably, the step of calculating the total insurance compensation amount caused by various optimal driving labels in historical traffic accidents according to the vehicle insurance compensation record may specifically include:
[0093] According to the vehicle insurance compensation record, query the number of traffic accidents that occurred in historical traffic accidents for various optimal driving labels and the insurance compensation amount caused by each traffic accident;
[0094] The total insurance compensation amount is calculated based on the number of traffic accidents and the insurance compensation amount caused by each traffic accident.
[0095] This embodiment can query the number of traffic accidents that occurred in historical traffic accidents for various optimal driving labels and the insurance compensation amount caused by each traffic accident, and accumulate the insurance compensation amount caused by each traffic accident to obtain the total insurance compensation amount, and the calculation method is simple.
[0096] Reference Figure 2 In an embodiment of the present application, a fee setting device based on data processing is also provided, comprising:
[0097] Extraction module 1, used to receive a vehicle insurance formulation request initiated by a user, and extract user information of the user from the vehicle insurance formulation request;
[0098] A query module 2, used to query the driving trajectory of the user within a preset time period and the driving operation data of the user on the driving trajectory according to the user information; wherein the driving trajectory is pre-stored on a driving map;
[0099] A grid processing module 3, used for gridding the driving trajectory of the driving map to obtain a plurality of grids;
[0100] An analysis module 4 is used to analyze the sub-driving trajectory and sub-driving operation data of the user in each grid, and determine the optimal driving label of the user in each grid according to the analysis result; wherein the sub-driving trajectory is the driving trajectory in a single grid, and the sub-driving operation data is the driving operation data of the user on the sub-driving trajectory;
[0101] The determination module 5 is used to determine the driving scores of the corresponding grids according to the optimal driving labels of the grids, accumulate the driving scores of the grids, obtain the driving score of the user on the driving trajectory, and determine the vehicle insurance premium of the user according to the driving score.
[0102] When applying for insurance for a vehicle, a user can log in to the insurance application interface through a mobile terminal or an insurance company's self-service terminal and initiate a vehicle insurance preparation request. After the server receives the vehicle insurance preparation request, it extracts the user's user information from the vehicle insurance preparation request. The user information includes at least one of a user name, an ID number, and an insurance account number.
[0103] This embodiment can encourage each user to upload the driving trajectory and the user's driving operation data on the driving trajectory in the APP of the mobile terminal in advance by means of rewards, or cooperate with manufacturers to obtain Internet of Vehicles data, extract the driving trajectory and the user's driving operation data on the driving trajectory from the Internet of Vehicles data, and save the uploaded driving trajectory and its driving operation data in the database for subsequent query and use. When the server receives the user's vehicle insurance formulation request, it queries the user's driving trajectory in the recent period of time according to the user information to analyze the driving trajectory in the recent period of time and determine the user's driving style. Among them, the driving trajectory can be a vector in seconds, including: time, longitude and latitude, altitude, direction, speed. The driving operation data is the user's behavior data on the driving trajectory, such as braking to slow down, stepping on the accelerator to accelerate, turning right, etc.
[0104] In addition, the present embodiment can also process the driving trajectory into grids according to the driving time period, forming a plurality of grids in units of 10*10 km, each grid being a calculation unit, and each grid containing at least one section of the driving trajectory.
[0105] The driving track is divided into multiple sub-driving tracks in units of grids, and the driving operation data of the user on the sub-driving track is used as the sub-driving operation data. According to the sub-driving track and the sub-driving operation data in each grid, at least one driving label of the user in each grid is analyzed and determined, and the optimal driving label that best matches the user on the sub-driving track is screened out from the at least one driving label. Among them, the driving data includes: average speed per 100 kilometers, number of rapid accelerations per 100 kilometers, number of rapid decelerations per 100 kilometers, number of sharp turns per 100 kilometers, number of speeding per 100 kilometers, traffic jam time per 100 kilometers, average mileage per trip, average driving speed per trip, average number of rapid accelerations per trip, average number of rapid decelerations per trip, average number of sharp turns per trip, average number of speeding per trip, maximum driving speed, maximum number of rapid accelerations, maximum number of rapid decelerations, maximum number of sharp turns, maximum number of speeding, and the longest fatigue driving time. One or more of the optimal driving label is used to characterize the driving behavior characteristics that best match the user, such as speeding, sudden braking, not turning on the turn signal, running a red light, etc.
[0106] The driving scores of the corresponding grids are determined according to the optimal driving labels of each grid, and the driving scores of all grids are accumulated to obtain the driving score of the user on the driving trajectory, and the vehicle premium of the user is determined according to the driving score, so as to realize the refined analysis of the user's driving style, so as to provide a strong basis for formulating a matching vehicle premium for each user, so that the risk assessment of vehicle insurance is more complete and scientific, thereby improving the accuracy of vehicle premium. Among them, the driving score is determined by the driving risk of the user reflected by the optimal driving label. For example, when the optimal driving label reflects that the user has dangerous driving behavior, the driving score of the corresponding grid is low; on the contrary, when the optimal driving label reflects that the user does not have dangerous driving behavior, the driving score of the corresponding grid is high, so as to determine the driving score corresponding to each optimal driving label. In addition, the vehicle premium of the user is inversely proportional to the driving score, that is, when the user's driving score is higher, it indicates that the user's driving habits are better, and the vehicle premium for the user is lower at this time.
[0107] As described above, it can be understood that the various components of the fee setting device based on data processing proposed in this application can realize the functions of any one of the fee setting methods based on data processing described above, and the specific structure will not be repeated.
[0108] Reference Figure 3 In an embodiment of the present application, a computer device is also provided. The computer device may be a server, and its internal structure may be as follows: Figure 3As shown. The computer device includes a processor, a memory, a network interface and a database connected through a system bus. Among them, the processor designed by the computer is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used for data such as relationship extraction models and drug discovery models. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a fee setting method based on data processing is implemented.
[0109] The processor executes the fee setting method based on data processing, including:
[0110] Receiving a vehicle insurance formulation request initiated by a user, and extracting user information of the user from the vehicle insurance formulation request;
[0111] querying the driving trajectory of the user within a preset time period and the driving operation data of the user on the driving trajectory according to the user information; wherein the driving trajectory is pre-stored on a driving map;
[0112] Gridding the driving trajectory of the driving map to obtain a plurality of grids;
[0113] Analyze the sub-driving trajectory and sub-driving operation data of the user in each grid, and determine the optimal driving label of the user in each grid according to the analysis result; wherein the sub-driving trajectory is the driving trajectory in a single grid, and the sub-driving operation data is the driving operation data of the user on the sub-driving trajectory;
[0114] The driving scores of the corresponding grids are determined according to the optimal driving labels of the grids, the driving scores of the grids are accumulated to obtain the driving score of the user on the driving trajectory, and the vehicle insurance premium of the user is determined according to the driving score.
[0115] An embodiment of the present application further provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, a fee setting method based on data processing is implemented, including the steps of:
[0116] Receiving a vehicle insurance formulation request initiated by a user, and extracting user information of the user from the vehicle insurance formulation request;
[0117] querying the driving trajectory of the user within a preset time period and the driving operation data of the user on the driving trajectory according to the user information; wherein the driving trajectory is pre-stored on a driving map;
[0118] Gridding the driving trajectory of the driving map to obtain a plurality of grids;
[0119] Analyze the sub-driving trajectory and sub-driving operation data of the user in each grid, and determine the optimal driving label of the user in each grid according to the analysis result; wherein the sub-driving trajectory is the driving trajectory in a single grid, and the sub-driving operation data is the driving operation data of the user on the sub-driving trajectory;
[0120] The driving scores of the corresponding grids are determined according to the optimal driving labels of the grids, the driving scores of the grids are accumulated to obtain the driving score of the user on the driving trajectory, and the vehicle insurance premium of the user is determined according to the driving score.
[0121] Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media provided in this application and used in the embodiments may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (SSRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.
[0122] In summary, the greatest beneficial effects of this application are:
[0123] The fee setting method, device and computer equipment based on data processing of the present application receive a vehicle insurance formulation request initiated by a user, and extract the user information of the user from the vehicle insurance formulation request; query the driving trajectory of the user within a preset time period and the driving operation data of the user on the driving trajectory according to the user information; grid the driving trajectory to obtain multiple grids; and analyze the sub-driving trajectory and sub-driving operation data of the user in each grid, and determine the optimal driving label of the user in each grid according to the analysis result; determine the driving score of each corresponding grid according to the optimal driving label of each grid, and obtain the driving score of the user on the driving trajectory after accumulating the driving scores of each grid, and determine the vehicle premium of the user according to the driving score, so as to obtain the optimal driving label of each driving trajectory of the user by analyzing each driving trajectory of the user within the preset time period, and realize the refined analysis of the user's driving style, so as to provide a strong basis for formulating a matching vehicle premium for each user, so that the driving score and vehicle premium finally obtained are more in line with the actual situation of each user, and personalized customization is realized, and the risk assessment of vehicle insurance is more complete and scientific, thereby improving the accuracy of vehicle premium.
[0124] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, device, article or method including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, device, article or method. In the absence of further restrictions, an element defined by the sentence "includes a ..." does not exclude the existence of other identical elements in the process, device, article or method including the element.
[0125] The above description is only a preferred embodiment of the present application, and does not limit the patent scope of the present application. Any equivalent structure or equivalent process transformation made using the contents of the present application specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present application.
Claims
1. A fee setting method based on data processing, It is characterized in that include: Receiving a vehicle insurance formulation request initiated by a user, and extracting user information of the user from the vehicle insurance formulation request; Querying the driving trajectory of the user within a preset time period and the driving operation data of the user on the driving trajectory according to the user information; wherein the driving trajectory is pre-stored on a driving map; Gridding the driving trajectory of the driving map to obtain a plurality of grids; Analyze the sub-driving trajectory and sub-driving operation data of the user in each grid, and determine the optimal driving label of the user in each grid according to the analysis result; wherein the sub-driving trajectory is the driving trajectory in a single grid, and the sub-driving operation data is the driving operation data of the user on the sub-driving trajectory; Determine the driving score of each corresponding grid according to the optimal driving label of each grid, accumulate the driving scores of each grid to obtain the driving score of the user on the driving trajectory, and determine the vehicle insurance premium of the user according to the driving score; The step of determining the vehicle insurance premium of the user according to the driving score comprises: Extracting the number of times the user drives in the driving trajectory from the driving operation data, and determining a driving weight based on the number of times the user drives; wherein the driving weight is inversely proportional to the number of times the user drives; Determine the vehicle insurance premium of the user according to the driving score and the driving weight; The step of analyzing the sub-driving trajectory and sub-driving operation data of the user in each grid and determining the optimal driving label of the user in each grid according to the analysis result includes: Acquire driving operation data of other users in the same grid except the user; wherein the driving operation data of other users in the same grid include the relative speed of the user with other drivers in the same area grid, the amount of sudden acceleration events compared with other drivers, and the amount of angular velocity exceeding a threshold compared with other drivers; Analyze the sub-driving trajectory, sub-driving operation data and driving operation data of other users in each grid, and determine the optimal driving label of the user in each grid in combination with road environment data; wherein the road environment data includes road longitude and latitude, road type and speed limit information; After the step of determining the optimal driving label of the user in each grid according to the analysis result, the method further includes: Filter out target driving labels that affect safe driving from the optimal driving labels of each grid; Calculate the number of grids of the same target driving label, sort the target driving labels in descending order of the number of grids, and obtain the target driving labels with the first N grid numbers, where N is an integer greater than or equal to 1; Recommending corresponding insurance products to the user based on the top N target driving tags; wherein the insurance products contain insurance clauses for the top N target optimal driving tags.
2. The method according to claim 1, It is characterized in that Before the step of querying the driving trajectory of the user within a preset time period according to the user information, the method further includes: Get the user's trajectory points at each time point; Filtering and denoising the trajectory points to obtain target trajectory points; Segmenting the target trajectory point according to the time interval of the target trajectory point to obtain at least one trajectory segment; The at least one trajectory segment is fitted onto an actual driving road to obtain a driving trajectory of the user within a preset time period.
3. The method according to claim 1, It is characterized in that The step of determining the driving scores of the corresponding grids according to the optimal driving labels of the grids comprises: According to the optimal driving labels of each grid, the optimal driving label value of each optimal driving label is searched from the comparison table; wherein the optimal driving label values corresponding to each optimal driving label are pre-stored in the comparison table; The optimal driving label value of each optimal driving label is used as the driving score of each corresponding grid.
4. The method according to claim 3, It is characterized in that Before the step of querying the optimal driving label value of each optimal driving label from the comparison table according to the optimal driving label of each grid, the method further includes: Obtain pre-collected vehicle insurance claim records; According to the vehicle insurance compensation records, the total insurance compensation amount caused by various optimal driving labels in historical traffic accidents is counted; The optimal driving label values of various optimal driving labels are set according to the total insurance compensation amount, and the optimal driving label values of various optimal driving labels are stored in a comparison table.
5. The method according to claim 4, It is characterized in that The step of calculating the total insurance compensation amount caused by various optimal driving labels in historical traffic accidents according to the vehicle insurance compensation record includes: According to the vehicle insurance compensation record, query the number of traffic accidents that occurred in historical traffic accidents for various optimal driving labels and the insurance compensation amount caused by each traffic accident; The total insurance compensation amount is calculated based on the number of traffic accidents and the insurance compensation amount caused by each traffic accident.
6. A fee setting device based on data processing, used to execute the method according to any one of claims 1 to 5, It is characterized in that include: An extraction module, used to receive a vehicle insurance formulation request initiated by a user, and extract user information of the user from the vehicle insurance formulation request; A query module, used to query the driving trajectory of the user within a preset time period and the driving operation data of the user on the driving trajectory according to the user information; wherein the driving trajectory is pre-stored on a driving map; A grid processing module, used for gridding the driving trajectory of the driving map to obtain a plurality of grids; An analysis module, used for analyzing the sub-driving trajectory and sub-driving operation data of the user in each grid, and determining the optimal driving label of the user in each grid according to the analysis result; wherein the sub-driving trajectory is the driving trajectory in a single grid, and the sub-driving operation data is the driving operation data of the user on the sub-driving trajectory; a determination module, configured to determine a driving score of each corresponding grid according to the optimal driving label of each grid, accumulate the driving scores of each grid to obtain a driving score of the user on the driving trajectory, and determine a vehicle insurance premium of the user according to the driving score; The step of determining the vehicle insurance premium of the user according to the driving score comprises: Extracting the number of times the user drives in the driving trajectory from the driving operation data, and determining a driving weight based on the number of times the user drives; wherein the driving weight is inversely proportional to the number of times the user drives; The vehicle insurance premium of the user is determined according to the driving score and the driving weight.
7. A computer device comprising a memory and a processor, wherein the memory stores a computer program. It is characterized in that When the processor executes the computer program, the steps of the fee setting method based on data processing according to any one of claims 1 to 5 are implemented.
8. A computer-readable storage medium having a computer program stored thereon, It is characterized in that When the computer program is executed by a processor, the steps of the fee setting method based on data processing according to any one of claims 1 to 5 are implemented.
