CN109670970B - Driving behavior scoring method and device and computer readable storage medium - Google Patents
Driving behavior scoring method and device and computer readable storage medium Download PDFInfo
- Publication number
- CN109670970B CN109670970B CN201811433626.6A CN201811433626A CN109670970B CN 109670970 B CN109670970 B CN 109670970B CN 201811433626 A CN201811433626 A CN 201811433626A CN 109670970 B CN109670970 B CN 109670970B
- Authority
- CN
- China
- Prior art keywords
- driving
- sample
- data
- driver
- stage
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000013077 scoring method Methods 0.000 title claims abstract description 55
- 238000003860 storage Methods 0.000 title claims abstract description 15
- 238000009825 accumulation Methods 0.000 claims abstract description 63
- 238000000034 method Methods 0.000 claims abstract description 27
- 238000004364 calculation method Methods 0.000 claims description 16
- 238000005315 distribution function Methods 0.000 claims description 11
- 238000004590 computer program Methods 0.000 claims description 10
- 238000009826 distribution Methods 0.000 claims description 10
- 238000013507 mapping Methods 0.000 claims description 9
- 230000001186 cumulative effect Effects 0.000 claims description 8
- 238000007621 cluster analysis Methods 0.000 claims description 5
- 238000004458 analytical method Methods 0.000 abstract description 2
- 230000006399 behavior Effects 0.000 description 112
- 238000010586 diagram Methods 0.000 description 11
- 238000004422 calculation algorithm Methods 0.000 description 10
- 230000008569 process Effects 0.000 description 9
- 230000001133 acceleration Effects 0.000 description 6
- 238000012986 modification Methods 0.000 description 5
- 230000004048 modification Effects 0.000 description 5
- 238000012545 processing Methods 0.000 description 5
- 230000006870 function Effects 0.000 description 4
- 238000010801 machine learning Methods 0.000 description 3
- 238000012544 monitoring process Methods 0.000 description 3
- 238000012549 training Methods 0.000 description 3
- 230000002159 abnormal effect Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 238000013135 deep learning Methods 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 210000001503 joint Anatomy 0.000 description 2
- 238000010606 normalization Methods 0.000 description 2
- 206010039203 Road traffic accident Diseases 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000003066 decision tree Methods 0.000 description 1
- 230000003111 delayed effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 238000012417 linear regression Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000007637 random forest analysis Methods 0.000 description 1
- 238000012502 risk assessment Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/08—Insurance
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
Abstract
The invention discloses a driving behavior scoring method and device and a computer readable storage medium, and belongs to the technical field of vehicle driving behavior analysis. The method comprises the following steps: accumulating sample data including driving data and insurance policy data of a sample driver; determining the current stage of the sample data in an accumulation process, wherein the accumulation process comprises a cold start stage and other stages after the cold start stage; and grading the driving behavior of the current driver by using a driving grading method corresponding to the current accumulation stage. The embodiment of the invention can realize that the driving behavior scoring can be carried out at different stages of data accumulation.
Description
Technical Field
The invention relates to the technical field of vehicle driving behavior analysis, in particular to a driving behavior scoring method and device and a computer readable storage medium.
Background
In recent years, the number of motor vehicles is increasing, and with the rapid development of the internet of vehicles, the number of car insurance products which are priced based on the driving behaviors of drivers and combined with the internet of vehicles technology is also increasing.
The ubi (use Based insurance) vehicle insurance refers to vehicle insurance priced Based on driving behavior and vehicle usage data, and is a new vehicle insurance appearing under the background of free vehicle insurance rates. The insurance company collects the driving behavior data and the vehicle operation data, and evaluates the driving behavior risk level of the driver through data analysis and processing. For car owners with good driving behaviors, the insurance company can give more preference, and for car owners with poor driving behaviors, the insurance company can correspondingly improve the premium. Therefore, the system is beneficial to the vehicle owner to develop good driving behaviors, reduce accidents and reduce risks and claims, thereby improving traffic conditions and reducing social cost.
Therefore, for insurance companies, before pricing car insurance products, driving behavior risk assessment needs to be made based on driving data of drivers, currently, a supervised learning method in machine learning is usually adopted to obtain the relationship between driving behavior and driving risk, and training samples need to contain driving behavior and vehicle use data as well as insurance claim settlement data. The driving behavior and the vehicle use data are collected, vehicle driving data are obtained through a sensor in a vehicle-mounted OBD (On-Board Diagnostic) device or a smart phone and other devices, and if the device is provided with a camera, a driving video can be obtained through the camera so as to obtain further data reflecting driving habits. As an accurate measure of the degree of risk, it is necessary to know whether the observed driver has a traffic accident or not in the same period of driving behavior observation and the condition of making a claim to the insurance company, and the risk ratio or the payout ratio is taken as an indication of the driving risk. After the two are obtained, the driving data is used as the feature in the supervision algorithm, the risk ratio or the loss ratio is used as the supervision signal in the supervision algorithm, and the supervision algorithm obtains the relationship between the feature and the supervision signal based on the training data, namely the relationship between the driving data and the risk ratio or the loss ratio. And for a target sample needing to judge the driving behavior risk, namely, a driver with only driving data, obtaining the driving behavior risk by an inference relation obtained by a supervision algorithm.
Therefore, the supervised learning method needs to accumulate a large amount of driving data and risk claim data, the risk claim period needs to be consistent with the driving data acquisition period, and if the risk claim data is not available or the data does not reach a certain amount, the algorithm is difficult to start. In actual operation, driving data are often convenient to collect at the beginning of system operation, but insurance and claim settlement usually do not occur immediately, so that insurance claim settlement data cannot be obtained while collecting driving data, and along with the accumulation of driving trips and data, even if insurance occurs, since a claim settlement flow comprises a plurality of steps of investigation, damage assessment, maintenance, claim settlement and the like, a certain time is required, and the insurance and claim settlement data are possibly delayed for a period of time, so that a supervision algorithm is difficult to start.
Disclosure of Invention
An object of an embodiment of the present invention is to provide a driving behavior scoring method, device and computer-readable storage medium, which accurately predict a driving behavior score of a target driver by using different driving scoring methods in different stages of data accumulation. The specific technical scheme of the embodiment of the invention is as follows:
in a first aspect, an embodiment of the present invention provides a driving behavior scoring method, where the method includes:
accumulating sample data including driving data and insurance policy data of a sample driver;
determining a current stage of the sample data in an accumulation process, wherein the accumulation process comprises a cold start stage and other stages after the cold start stage;
and grading the driving behavior of the current driver by using the driving grading method corresponding to the current accumulation stage.
In some embodiments, the other stages include an early stage, a mid stage, and a late stage;
the sample data in the cold start stage does not include insurance policy data of a sample driver;
the sample data in the initial stage comprises driving data of a plurality of sample drivers and a very small amount of insurance policy data;
the sample data at the middle stage comprises driving data of a plurality of sample drivers and insurance policy data of a part of the sample drivers;
the sample data at the later stage comprises driving data of a plurality of sample drivers and corresponding insurance policy data.
In some embodiments, when the current stage is the cold start stage, the scoring the driving behavior of the current driver by using the driving scoring method corresponding to the current accumulation stage includes:
acquiring the driving data of the current driver, and extracting various driving characteristics of the current driver;
dividing the plurality of driving characteristics into a plurality of dimensions, wherein each dimension comprises a plurality of driving characteristics;
obtaining scores of various driving characteristics according to a preset scoring standard;
carrying out weighted calculation on the scores of all the driving characteristics in all the dimensions to obtain the scores of all the dimensions;
and carrying out weighted calculation on the scores of the dimensions to obtain the driving behavior score of the current driver.
In some embodiments, when the current stage is the initial stage, the scoring the driving behavior of the current driver by using the driving scoring method corresponding to the current accumulation stage includes:
respectively extracting a plurality of sample driving characteristics of each sample driver from the driving data of each sample driver;
calculating distribution parameters of various sample driving characteristics according to various sample driving characteristics of the sample drivers;
acquiring the driving data of the current driver, and extracting various driving characteristics of the current driver;
respectively calculating the cumulative distribution function of various driving characteristics of the current driver according to the distribution parameters of various sample driving characteristics, and taking the cumulative distribution function as a score corresponding to various driving characteristics;
and carrying out weighted calculation on the scores of the various driving characteristics to obtain the driving behavior score of the current driver.
In some embodiments, when the current stage is the middle stage, the scoring the driving behavior of the current driver by using the driving scoring method corresponding to the current accumulation stage includes:
aiming at part of the sample drivers, obtaining driving scores of the sample drivers according to insurance policy data of the sample drivers;
performing cluster analysis on the driving data of part of the sample drivers to obtain a plurality of cluster centers, wherein each cluster is used as a risk grade cluster, and calculating the driving grade of each risk grade cluster according to the driving grade of part of the sample drivers;
acquiring the driving data of the current driver, and calculating the similarity distance between the driving data of the current driver and the plurality of clustering centers;
and determining a risk grade cluster corresponding to the current driver according to the calculation result of the similarity distance, and taking the driving score of the determined risk grade cluster as the driving score of the current driver.
In some embodiments, when the current stage is the later stage, the scoring the driving behavior of the current driver by using the driving scoring method corresponding to the current accumulation stage includes:
for the plurality of sample drivers, respectively extracting a plurality of driving characteristics of each sample driver from the driving data of each sample driver, and acquiring the driving score of each sample driver according to the insurance policy data of each sample driver;
establishing a driving behavior scoring model according to the driving characteristics of the sample drivers and the driving scores of the sample drivers;
and scoring the driving behavior of the current driver by using the driving behavior scoring model.
In some embodiments, said obtaining a driving score for each of said sample drivers based on insurance policy data for each of said sample drivers comprises:
for each of the sample driver's insurance policy data, performing the following operations:
acquiring an insurance claim settlement value from the insurance policy data;
and determining the driving score which has a mapping relation with the claim settlement numerical value according to a preset mapping relation table to serve as the driving score of the sample driver.
In a second aspect, an embodiment of the present invention provides a driving behavior scoring apparatus, where the apparatus includes:
the accumulation module is used for accumulating sample data, including driving data of a sample driver and insurance policy data;
the determining module is used for determining the current stage of the sample data in an accumulation process, wherein the accumulation process comprises a cold start stage and other stages after the cold start stage;
and the scoring module is used for scoring the driving behavior of the current driver by using the driving scoring method corresponding to the current accumulation stage.
In a third aspect, an embodiment of the present invention provides a driving behavior scoring apparatus, including:
one or more processors;
storage means for storing one or more programs;
when executed by the one or more processors, cause the one or more processors to implement the driving behavior scoring method of the first aspect.
In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, on which a computer program is stored, which when executed by a processor implements the driving behavior scoring method according to the first aspect.
According to the driving behavior scoring method, the driving behavior scoring device and the computer readable storage medium, the current stage of the sample data in the accumulation process is determined by accumulating the sample data, and the driving behavior of the current driver is scored by using the driving scoring method corresponding to the current accumulation stage. Therefore, driving behavior scores can be provided at the beginning of driving data acquisition, and parameters and models are gradually optimized along with the accumulation of driving data and the addition of claim data, so that the driving behavior risk can be evaluated in different stages of data accumulation.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed to be used in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
FIG. 1 illustrates a flow diagram of a driving behavior scoring method according to an embodiment of the present invention;
fig. 2 shows a block diagram of a driving behavior scoring apparatus according to another embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The driving behavior scoring method provided by the embodiment of the invention can accurately predict the scoring of the driving behavior of a target driver by using different driving behavior scoring methods in different stages of data accumulation, wherein an execution main body of the driving behavior scoring method can be a server, the server can be in communication connection with a mobile terminal and a vehicle-mounted depth camera module which are provided with a mobile SDK module through a network, and the server can also be in butt joint with an insurance policy system through a preset interface to obtain the insurance policy data of the driver; the server can be a single server or a server group consisting of a plurality of servers, and the plurality of servers can be in communication connection in the server group; the mobile terminal loaded with the mobile SDK module is a mobile terminal of a driver, driving behavior data of the driver can be collected by the mobile SDK module and uploaded to the server, and the vehicle-mounted depth camera module is mounted on a vehicle of the driver and can upload collected driving video data to the server.
Fig. 1 is a flowchart illustrating a driving behavior scoring method according to an embodiment of the present invention, and referring to fig. 1, the driving behavior scoring method may include the steps of:
and S1, accumulating sample data including driving data and insurance policy data of the sample driver.
Wherein the driving data of the sample driver may include at least one of driving behavior data, driving environment data, and driving video data.
Wherein, the driving behavior data of the sample driver can be obtained by the mobile SDK module. The driving behavior data may be various basic information when the vehicle is running, and may include driving time information, mileage information, speed information, steering information, longitude and latitude information, altitude information, mobile phone call state information, rapid acceleration information, rapid deceleration information, rapid turning information, and the like.
In the specific implementation process, the GPS, the accelerometer and the gyroscope sensor data can be collected in the driving process of the sample driver through a mobile SDK module in the mobile terminal of the sample driver to obtain the driving behavior data of the sample driver, the driving behavior data of the sample driver is uploaded to a server, and the server binds and stores the driving behavior data of the sample driver and the identity identification of the sample driver.
Wherein, the driving environment data of the sample driver can be obtained through a preset interface. The driving environment data can be various environmental information related to driving behaviors in the environment where the driver is located, and can include road section speed limit, driving areas, road types, terrain conditions, current driving weather conditions and the like. After the driving environment data of the sample driver are obtained through the preset interface, the driving environment data are uploaded to the server, and the server binds and stores the driving environment data of the sample driver and the identity of the sample driver.
The driving video data can be acquired through the vehicle-mounted camera. The driving video data is a video acquired by the camera during driving, and may include distance measuring information, lane information, road condition information, driving events, and the like. After the vehicle-mounted camera collects the driving video data, the driving video data are uploaded to the server, and the server binds and stores the driving video data of the sample driver and the identity of the sample driver.
Wherein, the insurance policy data of the sample driver can be obtained through the preset interface. The insurance policy data may be various information related to the driver's insurance policy, and may include driver's basic information, policy purchase information including information on insurance application varieties, insurance application amount, and the like, and policy settlement amount, insurance application amount, and the like.
In a specific implementation process, the server may be in butt joint with the insurance policy system through a preset interface, and acquire insurance policy data corresponding to the identity of the sample driver from the business policy system according to the identity of the sample driver.
It should be noted that the driver identification may be a mobile phone number, a user name, an identification card of the driver, or other information that can uniquely identify the driver.
And S2, determining the current stage of the sample data in the accumulation process, wherein the accumulation process comprises a cold start stage and other stages after the cold start stage.
Wherein the other stages include an early stage, a middle stage, and a late stage. The sample data in the cold start stage does not include insurance policy data of a sample driver; the sample data in the initial stage comprises driving data of a plurality of sample drivers and a very small amount of insurance policy data; the sample data at the middle stage comprises driving data of a plurality of sample drivers and insurance policy data of partial sample drivers; the sample data at the later stage includes driving data of a plurality of sample drivers and corresponding insurance policy data.
And S3, scoring the driving behavior of the current driver by using the driving scoring method corresponding to the current accumulation stage.
Wherein, different driving scoring methods are used for scoring the driving behaviors at different stages.
According to the driving behavior scoring method provided by the embodiment of the invention, the current stage of the sample data in the accumulation process is determined by accumulating the sample data, and the driving behavior of the current driver is scored by using the driving scoring method corresponding to the current accumulation stage. Therefore, driving behavior scores can be provided at the beginning of driving data acquisition, and parameters and models are gradually optimized along with the accumulation of driving data and the addition of claim data, so that the driving behavior risk can be evaluated in different stages of data accumulation.
In an embodiment of the present invention, when the current stage is a cold start stage in the accumulation process of the sample data, the driving data of the sample driver just starts to be accumulated, and there is no insurance policy data of the sample driver, and a driving scoring method based on rules and preset weights may be used to score the driving behavior of the current driver. Specifically, the step S3 of scoring the driving behavior of the current driver by using the driving scoring method corresponding to the current accumulation stage may include the steps of:
s311, obtaining the driving data of the current driver, and extracting various driving characteristics of the current driver.
Wherein the driving data of the current driver may include at least one of driving behavior data, driving environment data, and driving video data.
Specifically, the driving behavior data is obtained through the mobile SDK module, and at least one driving behavior characteristic comprising driving mileage, driving duration, maximum driving speed, rapid acceleration times, rapid deceleration times, rapid turning times, rapid lane changing times, fatigue driving and driving in dangerous time periods is extracted from the driving behavior data.
The driving environment data is obtained through a preset interface, and at least one driving environment characteristic including the number and duration of overspeed times of each section of travel or unit time period, whether the driving environment characteristic is in a dangerous environment, whether the driving environment characteristic is in a familiar road section, and whether severe weather exists is extracted from the driving environment data.
The driving video data are obtained through the vehicle-mounted camera, and at least one driving video feature including a vehicle-to-vehicle speed ratio, whether to follow a lane and whether to decelerate when a front event occurs is extracted from the driving video data.
S312, dividing the multiple driving characteristics into a plurality of dimensions, wherein each dimension comprises a plurality of driving characteristics.
Specifically, the extracted multiple driving features are divided into a plurality of dimensions, such as speed, mileage, time, environment, driving behavior, and the like, and each dimension includes a plurality of features. For example, the dimension "speed" may contain several characteristics related to speed: the number of speeding, the length of time of speeding, the maximum driving speed, etc., the dimension "driving behavior" contains several characteristics related to the driving operation: the number of rapid acceleration, the number of rapid deceleration, the number of rapid turning, the number of rapid lane change, the speed ratio of the vehicle, whether to follow the lane, whether to decelerate when a front event occurs, and the like.
And S313, obtaining scores of various driving characteristics according to a preset scoring standard.
Specifically, scoring standards are respectively set for various driving characteristics, and the scoring standards corresponding to the various driving characteristics can be set differently according to specific conditions.
For example, the scoring criteria for the driving characteristics of the number of speeding may be:
the number of speeding times score is 100-number of speeding times 10/driving range, the lower bound is 0, 10 points are deducted when the average speed per kilometer is 1, the average speed per kilometer > is 10, and the driving characteristic score is 0.
And S314, carrying out weighted calculation on the scores of various driving characteristics in each dimension to obtain the score of each dimension.
Specifically, according to feature weights set for various driving features, the feature scores in each dimension are weighted and summed to obtain a score of each dimension, wherein the sum of the feature weights in each dimension is 1.
The calculation formula of the dimension score is as follows: dimension score ═ Σ feature score × -feature weight.
And S315, carrying out weighted calculation on the scores of all dimensions to obtain the driving behavior score of the current driver.
Specifically, according to the dimension weight values set for each dimension, the driving behavior scores of each driver are obtained by weighting and summing the scores of each dimension, wherein the sum of the weight values of each dimension is 1.
The driving behavior score calculation formula is as follows: and scoring the driving behavior as ═ dimension score ═ dimension weight.
In the embodiment of the invention, when the current stage is the cold start stage, the driving data of the sample driver just begins to be accumulated, the insurance policy data of the sample driver is not available, and the driving behavior scoring of the current driver is carried out by using the driving scoring method corresponding to the cold start stage, so that the problem that the monitoring algorithm is difficult to start due to insufficient accumulation of the sample data at the initial operation stage of the system, and the driving behavior scoring cannot be carried out in the prior art can be solved.
In one embodiment of the invention, when the current stage is the initial stage in the accumulation process of the sample data, a certain amount of driving data of the sample driver is accumulated, the insurance policy data of the sample driver is still few or almost none, the association degree with the driving data of the driver is low overall, and the driving behavior of the current driver can be scored by using a driving scoring method based on a characteristic distribution function. Specifically, the step S3 of scoring the driving behavior of the current driver by using the driving scoring method corresponding to the current accumulation stage may include the steps of:
s321, extracting a plurality of sample driving characteristics of each sample driver from the driving data of each sample driver.
Specifically, the process may refer to step S311, which is not described herein.
And S322, calculating distribution parameters of various sample driving characteristics according to various sample driving characteristics of various sample drivers.
Specifically, assuming that the sample driving characteristics obey a certain distribution, the sample driving characteristics of all the sample drivers can be summarized, the summarized data is cleaned, the necessary abnormal value detection and data normalization are performed, parameters of a distribution function obeyed by the sample driving characteristics are obtained based on the cleaned data fitting, and by analogy, distribution parameters of other sample driving characteristics are obtained.
Illustratively, suppose a certain driving characteristic, such as: the average number of rapid accelerations x per kilometer follows an exponential distribution, with a cumulative distribution function as follows, whereacc＞0，
Summarizing the driving characteristics of all sample drivers, carrying out necessary abnormal value detection and data normalization, and fitting to obtain the characteristics based on the cleaned data, namely the parameter lambda of the distribution function obeying the average rapid acceleration times per kilometeracc。
And S323, acquiring the driving data of the current driver, and extracting various driving characteristics of the current driver.
Specifically, the process may refer to step S311, which is not described herein.
And S324, respectively calculating the cumulative distribution functions of various driving characteristics of the current driver according to the distribution parameters of various sample driving characteristics, and taking the cumulative distribution functions as scores corresponding to the various driving characteristics.
For example, for a certain driving characteristic of the current driver, for example: average number of rapid accelerations per kilometer xobjParameter λ of exponential distribution obeyed by the driving characteristicsaccObtaining the cumulative distribution function value of the driving characteristics
And the score is used as the corresponding score of the driving characteristic.
And S325, carrying out weighted calculation on the scores of various driving characteristics to obtain the driving behavior score of the current driver.
In the embodiment of the invention, when the current stage is the initial stage, a certain amount of sample driver driving data is accumulated, the sample driver insurance policy data is still little or almost no, the degree of correlation with the driver driving data is low as a whole, the driving behavior scoring can be performed on the current driver by using the driving scoring method corresponding to the initial stage, and the problem that the driving behavior scoring cannot be performed due to the fact that the monitoring algorithm is difficult to start because the system runs the insufficient accumulation of the initial sample data in the prior art can be solved.
In an embodiment of the present invention, when the current stage is a middle stage in the accumulation process of the sample data, a certain amount of driving data of the sample driver and insurance policy data of a part of the sample drivers are accumulated, and a driving behavior scoring method based on cluster analysis may be used to score the current driver. Specifically, the step S3 of scoring the driving behavior of the current driver by using the driving scoring method corresponding to the current accumulation stage may specifically include the steps of:
and S331, aiming at partial sample drivers, obtaining the driving scores of the sample drivers according to the insurance policy data of the sample drivers.
Specifically, for each sample driver's insurance policy data, the following operations are performed:
acquiring an insurance claim settlement value from insurance policy data, and determining a driving score having a mapping relation with the insurance claim settlement value according to a preset mapping relation table to be used as a driving score of a sample driver; in the preset mapping relation table, the higher the claim settlement rate is, the lower the corresponding driving behavior score is.
The risk occurrence and claim settlement value can be obtained by extracting risk occurrence rate or claim rate of the sample driver from insurance policy data of the sample driver, and obtaining driving behavior score of the sample driver according to the risk occurrence rate or the claim rate and a preset mapping relation table to serve as a score label of the sample driver. In the mapping relation table, the higher the claim settlement rate is, the lower the corresponding driving behavior score is, and for example, the score range may be 0 to 100.
S332, performing cluster analysis on the driving data of the partial sample drivers to obtain a plurality of cluster centers, wherein each cluster is used as a risk grade cluster, and calculating the driving grade of each risk grade cluster according to the driving grade of the partial sample drivers.
The driving data of a part of sample drivers can be subjected to cluster analysis by using a K-means algorithm, each class is used as a risk level cluster, a cluster center is obtained, drivers in the same class are considered to have the same or similar risk level, and the average value of the driving scores of the sample drivers in the same class is used as the driving score of the class (namely the risk level cluster).
S333, acquiring the driving data of the current driver, and calculating the similarity distance between the driving data of the current driver and the plurality of clustering centers.
Specifically, the embodiment of the present invention does not limit the specific calculation process.
And S334, determining a risk grade cluster corresponding to the current driver according to the calculation result of the similarity distance, and taking the driving score of the determined risk grade cluster as the driving score of the current driver.
Specifically, a risk level cluster corresponding to the minimum value in the calculation results of the similarity distance is used as a risk level cluster corresponding to the current driver.
In the embodiment of the invention, when the current stage is the middle stage in the accumulation process of the sample data, a certain amount of driving data of the sample driver and insurance policy data of part of the sample drivers are accumulated, the driving behavior of the current driver can be scored by using the driving scoring method corresponding to the middle stage, and the problem that the driving behavior scoring cannot be performed due to the fact that the monitoring algorithm is difficult to start because the sample data accumulation at the initial stage of system operation is insufficient in the prior art can be solved.
In an embodiment of the invention, when the current stage is the later stage, the sample driver driving data and the claim settlement data are complete, the correlation between the driver driving data and the claim settlement data is complete, and a driving scoring method based on a trained scoring model can be used for scoring the driving behavior of the current driver. Specifically, the step S3 of scoring the driving behavior of the current driver by using the driving scoring method corresponding to the current accumulation stage may specifically include the steps of:
and S341, aiming at the sample drivers, extracting various driving characteristics of the sample drivers from the driving data of the sample drivers, and acquiring the driving scores of the sample drivers according to the insurance policy data of the sample drivers.
Specifically, in this step, the process of extracting the multiple driving characteristics of each sample driver from the driving data of each sample driver is the same as that in step S311, and is not described here again.
In this step, the process of obtaining the driving score of each sample driver according to the insurance policy data of each sample driver is the same as that in step S331, and is not described here again.
And S342, establishing a driving behavior scoring model according to the driving characteristics of the drivers in the samples and the driving scores of the drivers in the samples.
Specifically, a driving behavior scoring model is established for the driving characteristics of each sample driver and the driving scores of each sample driver through a traditional machine learning or deep learning method, and the driving behavior scoring model is stored offline for calling during online driving behavior scoring.
The driving behavior scoring model may be established by using methods such as linear regression, random forest, decision tree, xgboost, and the like, which is not limited in the present invention.
And S343, grading the driving behavior of the current driver by using the driving behavior grading model.
Specifically, the driving characteristics of the current driver are extracted from the driving data of the current driver; and inputting the driving characteristics of the current driver into the driving behavior scoring model to obtain and output the driving behavior score of the current driver.
In the embodiment of the invention, when the current stage is the later stage in the accumulation process of the sample data, the sample driver driving data and the claim settlement data are complete, and the correlation between the driver driving data and the claim settlement data is complete, so that a driving scoring model can be obtained by adopting machine learning or deep learning training, and the driving behavior of the current driver is scored.
Fig. 2 shows a block diagram of a driving behavior scoring apparatus according to another embodiment of the present invention. The driving behavior scoring device provided by the embodiment of the invention is used for executing the driving behavior scoring method in the embodiment, and as shown in fig. 2, the device comprises:
the accumulation module 21 is used for accumulating sample data, including driving data of a sample driver and insurance policy data;
the determining module 22 is configured to determine a current stage of the sample data in an accumulation process, where the accumulation process includes a cold start stage and other stages after the cold start stage;
and the scoring module 23 is configured to score the driving behavior of the current driver by using a driving scoring method corresponding to the current accumulation stage.
The driving behavior scoring device provided by the embodiment of the invention belongs to the same inventive concept as the driving behavior scoring method provided by the embodiment of the invention, can execute the driving behavior scoring method provided by any embodiment of the invention, and has the corresponding functional modules and beneficial effects of executing the driving behavior scoring method. For details of the driving behavior scoring method provided in the embodiment of the present invention, reference may be made to the technical details that are not described in detail in the embodiment of the present invention, and details are not repeated here.
In addition, another embodiment of the present invention further provides a driving behavior scoring apparatus, including:
one or more processors;
storage means for storing one or more programs;
when executed by the one or more processors, cause the one or more processors to implement a driving behavior scoring method as described in the embodiments above.
Furthermore, another embodiment of the present invention also provides a computer-readable storage medium, on which a computer program is stored, which when executed by a processor implements the driving behavior scoring method according to the above embodiment.
As will be appreciated by one of skill in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, embodiments of the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, embodiments of the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
Embodiments of the present invention are described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
While preferred embodiments of the present invention have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. Therefore, it is intended that the appended claims be interpreted as including preferred embodiments and all such alterations and modifications as fall within the scope of the embodiments of the invention.
It will be apparent to those skilled in the art that various changes and modifications may be made in the present invention without departing from the spirit and scope of the invention. Thus, if such modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include such modifications and variations.
Claims (10)
1. A driving behavior scoring method, characterized in that the method comprises the steps of:
accumulating sample data including driving data and insurance policy data of a sample driver;
determining a current accumulation stage of the sample data in an accumulation process, wherein the accumulation process comprises a cold start stage and other stages after the cold start stage, and different stages in the accumulation process correspond to different driving scoring methods;
and grading the driving behavior of the current driver by using the driving grading method corresponding to the current accumulation stage.
2. The method of claim 1, wherein the other stages include an early stage, a middle stage, and a late stage;
the sample data in the cold start stage does not include insurance policy data of a sample driver;
the sample data in the initial stage comprises driving data and insurance policy data of a plurality of sample drivers;
the sample data at the middle stage comprises driving data of a plurality of sample drivers and insurance policy data of partial sample drivers, and the data volume of the insurance policy data at the initial stage is smaller than that of the insurance policy data at the middle stage;
the sample data at the later stage comprises driving data of a plurality of sample drivers and corresponding insurance policy data, and the data volume of the insurance policy data at the later stage is greater than that of the insurance policy data at the middle stage.
3. The method according to claim 2, wherein when the current accumulation phase is the cold start phase, the scoring the driving behavior of the current driver by using the driving scoring method corresponding to the current accumulation phase comprises:
acquiring the driving data of the current driver, and extracting various driving characteristics of the current driver;
dividing the plurality of driving characteristics into a plurality of dimensions, wherein each dimension comprises a plurality of driving characteristics;
obtaining scores of various driving characteristics according to a preset scoring standard;
carrying out weighted calculation on the scores of all the driving characteristics in all the dimensions to obtain the scores of all the dimensions;
and carrying out weighted calculation on the scores of the dimensions to obtain the driving behavior score of the current driver.
4. The method according to claim 2, wherein when the current accumulation stage is the initial stage, the scoring the driving behavior of the current driver by using the driving scoring method corresponding to the current accumulation stage comprises:
respectively extracting a plurality of sample driving characteristics of each sample driver from the driving data of each sample driver;
calculating distribution parameters of various sample driving characteristics according to various sample driving characteristics of the sample drivers;
acquiring the driving data of the current driver, and extracting various driving characteristics of the current driver;
respectively calculating the cumulative distribution function of various driving characteristics of the current driver according to the distribution parameters of various sample driving characteristics, and taking the cumulative distribution function as a score corresponding to various driving characteristics;
and carrying out weighted calculation on the scores of the various driving characteristics to obtain the driving behavior score of the current driver.
5. The method according to claim 2, wherein when the current accumulation stage is the middle stage, the scoring the driving behavior of the current driver by using the driving scoring method corresponding to the current accumulation stage comprises:
aiming at part of the sample drivers, obtaining driving scores of the sample drivers according to insurance policy data of the sample drivers;
performing cluster analysis on the driving data of part of the sample drivers to obtain a plurality of cluster centers, wherein each cluster is used as a risk grade cluster, and calculating the driving grade of each risk grade cluster according to the driving grade of part of the sample drivers;
acquiring the driving data of the current driver, and calculating the similarity distance between the driving data of the current driver and the plurality of clustering centers;
and determining a risk grade cluster corresponding to the current driver according to the calculation result of the similarity distance, and taking the driving score of the determined risk grade cluster as the driving score of the current driver.
6. The method of claim 2, wherein the current accumulation phase is the later phase, and the scoring the driving behavior of the current driver using the driving scoring method corresponding to the current accumulation phase comprises:
for the plurality of sample drivers, respectively extracting a plurality of driving characteristics of each sample driver from the driving data of each sample driver, and acquiring the driving score of each sample driver according to the insurance policy data of each sample driver;
establishing a driving behavior scoring model according to the driving characteristics of the sample drivers and the driving scores of the sample drivers;
and scoring the driving behavior of the current driver by using the driving behavior scoring model.
7. The method of claim 5 or 6, wherein the obtaining a driving score for each of the sample drivers based on the insurance policy data for each of the sample drivers comprises:
for each of the sample driver's insurance policy data, performing the following operations:
acquiring an insurance claim settlement value from the insurance policy data;
and determining the driving score which has a mapping relation with the claim settlement numerical value according to a preset mapping relation table to serve as the driving score of the sample driver.
8. A driving behavior scoring device for executing the driving behavior scoring method according to any one of claims 1 to 7, the device comprising:
the accumulation module is used for accumulating sample data, including driving data of a sample driver and insurance policy data;
the determining module is used for determining the current accumulation stage of the sample data in the accumulation process, wherein the accumulation process comprises a cold start stage and other stages after the cold start stage;
and the scoring module is used for scoring the driving behavior of the current driver by using the driving scoring method corresponding to the current accumulation stage.
9. A driving behavior scoring device, comprising:
one or more processors;
storage means for storing one or more programs;
when executed by the one or more processors, cause the one or more processors to implement a driving behavior scoring method as recited in any one of claims 1-7.
10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, implements a driving behavior scoring method according to any one of claims 1 to 7.
Priority Applications (4)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811433626.6A CN109670970B (en) | 2018-11-28 | 2018-11-28 | Driving behavior scoring method and device and computer readable storage medium |
| JP2019554753A JP6918137B2 (en) | 2018-11-28 | 2019-07-09 | Driving behavior evaluation method, device and computer-readable storage medium |
| PCT/CN2019/095164 WO2020107894A1 (en) | 2018-11-28 | 2019-07-09 | Driving behavior scoring method and device and computer-readable storage medium |
| SG11202005593WA SG11202005593WA (en) | 2018-11-28 | 2019-07-09 | Driving behavior scoring method, device and computer readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811433626.6A CN109670970B (en) | 2018-11-28 | 2018-11-28 | Driving behavior scoring method and device and computer readable storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109670970A CN109670970A (en) | 2019-04-23 |
| CN109670970B true CN109670970B (en) | 2020-12-22 |
Family
ID=66143248
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811433626.6A Active CN109670970B (en) | 2018-11-28 | 2018-11-28 | Driving behavior scoring method and device and computer readable storage medium |
Country Status (4)
| Country | Link |
|---|---|
| JP (1) | JP6918137B2 (en) |
| CN (1) | CN109670970B (en) |
| SG (1) | SG11202005593WA (en) |
| WO (1) | WO2020107894A1 (en) |
Families Citing this family (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109670970B (en) * | 2018-11-28 | 2020-12-22 | 众安信息技术服务有限公司 | Driving behavior scoring method and device and computer readable storage medium |
| CN112749721A (en) * | 2019-10-31 | 2021-05-04 | 彩虹无线（北京）新技术有限公司 | Driving risk evaluation model training method and device |
| CN112937591B (en) * | 2019-12-11 | 2023-04-07 | 彩虹无线（北京）新技术有限公司 | Driving safety monitoring method, device, equipment and computer readable storage medium |
| CN113119981B (en) * | 2021-04-09 | 2022-06-17 | 东风汽车集团股份有限公司 | Vehicle active safety control method, system and storage medium |
| CN113298361A (en) * | 2021-05-06 | 2021-08-24 | 深圳市锐明技术股份有限公司 | Dangerous driving behavior evaluation method and device, electronic equipment and system |
| CN113635915B (en) * | 2021-08-24 | 2023-01-06 | 中国人民解放军陆军装甲兵学院 | Vehicle driving early warning method and device, electronic equipment and storage medium |
| CN114407904A (en) * | 2022-02-11 | 2022-04-29 | 西北工业大学 | Method, device and system for monitoring aggressive driving behavior of driver |
| CN116821805A (en) * | 2023-06-28 | 2023-09-29 | 运脉云技术有限公司 | Vehicle service platform system for monitoring driving behavior and driving behavior monitoring method |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107203945A (en) * | 2017-06-12 | 2017-09-26 | 清华大学苏州汽车研究院（吴江） | Vehicle insurance grading evaluation method and device |
Family Cites Families (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106127586A (en) * | 2016-06-17 | 2016-11-16 | 上海经达信息科技股份有限公司 | Vehicle insurance rate aid decision-making system under big data age |
| CN107784251A (en) * | 2016-08-25 | 2018-03-09 | 大连楼兰科技股份有限公司 | The method evaluated based on image recognition technology driving behavior |
| CN107784587B (en) * | 2016-08-25 | 2021-09-14 | 大连楼兰科技股份有限公司 | Driving behavior evaluation system |
| CN107845039A (en) * | 2016-09-20 | 2018-03-27 | 得道车联网络科技（上海）有限公司 | A kind of adaptive car networking vehicle insurance Rating Model of scale free |
| CN107038860B (en) * | 2016-11-18 | 2019-07-23 | 杭州好好开车科技有限公司 | A kind of user's driving behavior methods of marking based on ADAS technology and regression model |
| CN106651133B (en) * | 2016-11-18 | 2020-07-10 | 杭州好好开车科技有限公司 | Method for achieving user driving behavior scoring based on ADAS by using mobile phone |
| CN106815312A (en) * | 2016-12-21 | 2017-06-09 | 东软集团股份有限公司 | A kind of driver's evaluation method and device |
| DE112018001724T5 (en) * | 2017-03-29 | 2020-01-09 | Sony Corporation | INFORMATION PROCESSING DEVICE, INFORMATION PROCESSING SYSTEM, INFORMATION PROCESSING PROCESS AND PROGRAM |
| CN107203943A (en) * | 2017-04-06 | 2017-09-26 | 北京保程保险公估有限公司 | Motor vehicle business insurance pricing system |
| CN108492053A (en) * | 2018-04-11 | 2018-09-04 | 北京汽车研究总院有限公司 | The training of driver's risk evaluation model, methods of risk assessment and device |
| CN109670970B (en) * | 2018-11-28 | 2020-12-22 | 众安信息技术服务有限公司 | Driving behavior scoring method and device and computer readable storage medium |
-
2018
- 2018-11-28 CN CN201811433626.6A patent/CN109670970B/en active Active
-
2019
- 2019-07-09 JP JP2019554753A patent/JP6918137B2/en active Active
- 2019-07-09 WO PCT/CN2019/095164 patent/WO2020107894A1/en active Application Filing
- 2019-07-09 SG SG11202005593WA patent/SG11202005593WA/en unknown
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107203945A (en) * | 2017-06-12 | 2017-09-26 | 清华大学苏州汽车研究院（吴江） | Vehicle insurance grading evaluation method and device |
Also Published As
| Publication number | Publication date |
|---|---|
| JP2021509978A (en) | 2021-04-08 |
| JP6918137B2 (en) | 2021-08-11 |
| SG11202005593WA (en) | 2020-07-29 |
| WO2020107894A1 (en) | 2020-06-04 |
| CN109670970A (en) | 2019-04-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109670970B (en) | Driving behavior scoring method and device and computer readable storage medium | |
| CN109118055B (en) | Driving behavior scoring method and device | |
| CN107784587B (en) | Driving behavior evaluation system | |
| US11407410B2 (en) | Method and system for estimating an accident risk of an autonomous vehicle | |
| EP3239686A1 (en) | Method for determining driving characteristics of a vehicle | |
| Castignani et al. | An evaluation study of driver profiling fuzzy algorithms using smartphones | |
| CN105374211A (en) | System and method for calculating driving risks and assisting automobile insurance pricing based on multi-source data | |
| CN109840612A (en) | User's driving behavior analysis method and system | |
| US11710082B2 (en) | Systems and methods for utilizing machine learning and feature selection to classify driving behavior | |
| CN109658272A (en) | Driving behavior evaluation system and Insurance Pricing system based on driving behavior | |
| CN106022846A (en) | Automobile insurance pricing method, second-hand automobile pricing method and corresponding devices | |
| EP3578433B1 (en) | Method for estimating an accident risk of an autonomous vehicle | |
| CN112937591B (en) | Driving safety monitoring method, device, equipment and computer readable storage medium | |
| CN111523932A (en) | Scoring method, device and system for network car booking service and storage medium | |
| Wu et al. | Clustering of several typical behavioral characteristics of commercial vehicle drivers based on GPS data mining: Case study of highways in China | |
| CN110263836B (en) | Bad driving state identification method based on multi-feature convolutional neural network | |
| CN111489459A (en) | Vehicle data analysis method | |
| CN106651133B (en) | Method for achieving user driving behavior scoring based on ADAS by using mobile phone | |
| CN112508228A (en) | Driving behavior risk prediction method and system | |
| CN108268678B (en) | Driving behavior analysis method, device and system | |
| US20230237584A1 (en) | Systems and methods for evaluating vehicle insurance claims | |
| CN113658426A (en) | Vehicle accident identification method and device | |
| US20220340148A1 (en) | Method for estimating an accident risk of an autonomous vehicle | |
| CN110827152A (en) | Insurance evaluation method, system and server | |
| CN117093818B (en) | Method and system for measuring and calculating carbon emission of urban distribution logistics vehicle |
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 | ||
| REG | Reference to a national code |
Ref country code: HK Ref legal event code: DE Ref document number: 40003621 Country of ref document: HK |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20240306 Address after: Room 1179, W Zone, 11th Floor, Building 1, No. 158 Shuanglian Road, Qingpu District, Shanghai, 201702 Patentee after: Shanghai Zhongan Information Technology Service Co.,Ltd. Country or region after: China Address before: 518000 Room 201, building A, No. 1, Qian Wan Road, Qianhai Shenzhen Hong Kong cooperation zone, Shenzhen, Guangdong (Shenzhen Qianhai business secretary Co., Ltd.) Patentee before: ZHONGAN INFORMATION TECHNOLOGY SERVICE Co.,Ltd. Country or region before: China |
|
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20240415 Address after: Room 1179, W Zone, 11th Floor, Building 1, No. 158 Shuanglian Road, Qingpu District, Shanghai, 201702 Patentee after: Shanghai Zhongan Information Technology Service Co.,Ltd. Country or region after: China Address before: 518000 Room 201, building A, No. 1, Qian Wan Road, Qianhai Shenzhen Hong Kong cooperation zone, Shenzhen, Guangdong (Shenzhen Qianhai business secretary Co., Ltd.) Patentee before: ZHONGAN INFORMATION TECHNOLOGY SERVICE Co.,Ltd. Country or region before: China |