CN114331181A - Vehicle driving behavior risk analysis method based on big data - Google Patents
Vehicle driving behavior risk analysis method based on big data Download PDFInfo
- Publication number
- CN114331181A CN114331181A CN202111673557.8A CN202111673557A CN114331181A CN 114331181 A CN114331181 A CN 114331181A CN 202111673557 A CN202111673557 A CN 202111673557A CN 114331181 A CN114331181 A CN 114331181A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- information
- data
- vehicle information
- driver
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Landscapes
- Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)
Abstract
The invention provides a vehicle driving behavior risk analysis method based on big data, which comprises the following steps: s1, acquiring road network information, arranging RFID acquisition points on roads, acquiring vehicle information through an RFID reader-writer, and acquiring vehicle information through image acquisition equipment arranged at the RFID acquisition points; s2, performing abnormal data elimination according to the vehicle information acquired by the RFID reader and the vehicle information acquired by the image equipment, and fitting to form a vehicle track based on the data with the abnormal data eliminated; s3, determining a driving risk factor based on the track of the vehicle and the vehicle information; s4, constructing a risk scoring model based on the driving risk factors, and calculating the risk score of the vehicle; by the method, the trip behavior and the trip information of the vehicle are analyzed based on the combined action of the RFID and the image information, so that the risk of vehicle driving can be accurately scored, and accurate data support is provided for insurance line estimation.
Description
Technical Field
The invention relates to a risk analysis method, in particular to a vehicle driving behavior risk analysis method based on big data.
Background
With the rapid growth of motor vehicles, the automobile insurance industry has become the mainstay industry of the entire insurance industry with the rapid development of the automobile market.
At present, one of the insurance based on use (UBI for short) records the use data of each individual vehicle through a front-end induction system, models, analyzes and quantifies the driving behavior of each individual vehicle, and then carries out risk rating and establishes premium.
Traditional risk prediction is realized by statistical analysis (adding certain subjective assumption) on the basis of historical claim settlement data and sampling investigation, but the risk of driving behaviors of a vehicle cannot be accurately determined by the analysis mode, so that the insurance amount cannot be accurately estimated.
Therefore, in order to solve the above problems, a new technical means is needed.
Disclosure of Invention
In view of the above, the present invention provides a vehicle driving behavior risk analysis method based on big data, which analyzes travel behavior and travel information of a vehicle based on combined action of RFID and image information, so as to accurately score a risk of vehicle driving and provide accurate data support for estimating an insurance amount.
The invention provides a vehicle driving behavior risk analysis method based on big data, which comprises the following steps:
s1, acquiring road network information, arranging RFID acquisition points on roads, acquiring vehicle information through an RFID reader-writer, and acquiring vehicle information through image acquisition equipment arranged at the RFID acquisition points;
s2, performing abnormal data elimination according to the vehicle information acquired by the RFID reader and the vehicle information acquired by the image equipment, and fitting to form a vehicle track based on the data with the abnormal data eliminated;
s3, determining a driving risk factor based on the track of the vehicle and the vehicle information;
and S4, constructing a risk scoring model based on the driving risk factors, and calculating the risk score of the vehicle.
Further, in step S1, the vehicle information and the driver information acquired by the RFID reader/writer, wherein: the information of the vehicle comprises a license plate number, vehicle operation attributes, vehicle types and vehicle insurance declaration times;
the driver information comprises driver identity information, driver driving age, driver gender, driver age and driver historical violation times.
Further, in step S1, the vehicle information acquired by the image capturing device includes the license plate number, the vehicle color, and the driver face information.
Further, comparing, fusing and removing abnormal data between the vehicle information collected by the RFID reader and the image information collected by the image device specifically includes:
extracting license plate numbers in the vehicle information acquired by the RFID reader-writer and license plate numbers in the vehicle information acquired by the image acquisition equipment;
and judging whether the license plate numbers in the two pieces of vehicle information are consistent, if so, further judging whether the distance between the position points of the RFID reader-writer and the image acquisition equipment is smaller than a set threshold value, if so, taking the vehicle information acquired by the current RFID reader-writer and the image acquisition equipment as effective data, and otherwise, taking the vehicle information acquired by the current RFID reader-writer and the image acquisition equipment as effective data.
Further, determining the driving risk factor based on the trajectory of the vehicle and the vehicle information specifically includes:
counting the track of the current vehicle in a set time period, and determining the travel path preference of a driver according to the track;
counting the travel time of the current vehicle in each day within a set time period, and determining the travel time preference of a driver according to the travel time;
and acquiring the average speed of the current vehicle in each trip in a set time period according to the RFID reader, wherein the average speed is the average speed in the off-peak time period, and obtaining the out-of-limit probability according to the average speed.
Further, in step S4, the risk scoring model is specifically as follows:
wherein S isiInitial value of credit, p, representing preference in ithiIs the ith preference value, betaiWeight value, alpha, representing the ith preferencemWeighting the vehicle operation attribute values; when m is 1, the weight coefficient of the private car is, when m is 2, the weight coefficient of the taxi is, when m is 3, the weight coefficient of the large-sized passenger car is, and when m is 4, the weight coefficient of the truck is; λ is an integrated weight coefficient, i is 1,2,3, and represents a travel time preference when i is 1; when i is 2, the preference of the travel route is given, and when i is 3, the probability of the average vehicle speed exceeding the limit is given;
wherein:rθ1is the sex coefficient, rθ2Denotes the age coefficient, λθ1Is gender weight, λθ2Representing the age weight, pbRepresenting the ratio of the travel times of the insurance declaration in a set time period; when theta is 1, theta is 2, musMu is the historical violation number of the vehicle in the set time period for setting the violation number limit value.
The invention has the beneficial effects that: according to the invention, the trip behavior and trip information of the vehicle are analyzed based on the combined action of the RFID and the image information, so that the risk of vehicle driving can be accurately scored, and accurate data support is provided for insurance amount estimation.
Drawings
The invention is further described below with reference to the following figures and examples:
FIG. 1 is a flow chart of the present invention.
Detailed Description
The present invention is further described in detail below:
the invention provides a vehicle driving behavior risk analysis method based on big data, which comprises the following steps:
s1, acquiring road network information, arranging RFID acquisition points on roads, acquiring vehicle information through an RFID reader-writer, and acquiring vehicle information through image acquisition equipment arranged at the RFID acquisition points;
s2, performing abnormal data elimination according to the vehicle information acquired by the RFID reader and the vehicle information acquired by the image equipment, and fitting to form a vehicle track based on the data with the abnormal data eliminated;
s3, determining a driving risk factor based on the track of the vehicle and the vehicle information;
s4, constructing a risk scoring model based on the driving risk factors, and calculating the risk score of the vehicle; by the method, the trip behavior and the trip information of the vehicle are analyzed based on the combined action of the RFID and the image information, so that the risk of vehicle driving can be accurately scored, and accurate data support is provided for insurance line estimation.
In this embodiment, in step S1, the vehicle information and the driver information acquired by the RFID reader, where: the information of the vehicle comprises a license plate number, vehicle operation attributes, vehicle types and vehicle insurance declaration times;
the driver information comprises driver identity information, driver driving age, driver gender, driver age and driver historical violation times.
In this embodiment, in step S1, the vehicle information acquired by the image acquisition device includes the license plate number, the vehicle color, and the driver face information.
Calling prestored vehicle information including license plate numbers, vehicle types, vehicle colors and the like from a database, matching and comparing the prestored vehicle information with the information acquired in real time, and using the information to eliminate fake license plates and other operations so as to ensure the accuracy of evaluation, and performing early warning when fake license plates, good license plate shielding and the like exist; and directly set its risk score to 0.
In this embodiment, comparing, fusing, and removing abnormal data between the vehicle information collected by the RFID reader and the image information collected by the image device specifically includes:
extracting license plate numbers in the vehicle information acquired by the RFID reader-writer and license plate numbers in the vehicle information acquired by the image acquisition equipment;
judging whether license plate numbers in the two pieces of vehicle information are consistent, if so, further judging whether the distance between the position points of the RFID reader-writer and the image acquisition equipment is smaller than a set threshold value, if so, taking the vehicle information acquired by the current RFID reader-writer and the image acquisition equipment as effective data, otherwise, taking the vehicle information acquired by the current RFID reader-writer and the image acquisition equipment as effective data; under the above operation, the accuracy of the final evaluation result can be ensured.
In this embodiment, determining the driving risk factor based on the trajectory of the vehicle and the vehicle information specifically includes:
counting the track of the current vehicle in a set time period, and determining the travel path preference of a driver according to the track; the travel route preference is the ratio of the number of passes to the total number of travels of a certain route within a set time;
counting the travel time of the current vehicle in each day within a set time period, and determining the travel time preference of a driver according to the travel time; the travel time preference is the ratio of the number of trips at a certain time period to the total trip number within a set time;
acquiring the average speed of each trip of the current vehicle in a set time period according to the RFID reader-writer, wherein the average speed is the average speed in an off-peak time period, and obtaining an out-of-limit probability according to the average speed, namely the ratio of the number of times that the average speed exceeds the set speed to the total trip number;
in the above, the trip times are determined in the following manner: such as: after the A vehicle passes through the four ABCD acquisition points in sequence, the information of the vehicle, which is not acquired by other acquisition points in the same day, is counted as 1 trip, after the A vehicle passes through the ABCD acquisition points in sequence, the A vehicle passes through the EFG acquisition points in sequence at intervals, the distance between the D acquisition point and the E acquisition point is calculated and divided by the average traffic flow speed in the interval time to obtain a time t, if the time t is equal to the interval time, the A vehicle is counted as the current A vehicle for one trip, and if the time t is less than the interval time, the A vehicle stays and passes through the ABCD and the EFG acquisition points in sequence is counted as two trips.
In this embodiment, in step S4, the risk scoring model is specifically as follows:
wherein S isiInitial value of credit, p, representing preference in ithiIs the ith preference value, betaiWeight value, alpha, representing the ith preferencemWeighting the vehicle operation attribute values; when m is 1, the weight coefficient of the private car is, when m is 2, the weight coefficient of the taxi is, when m is 3, the weight coefficient of the large-sized passenger car is, and when m is 4, the weight coefficient of the truck is; λ is an integrated weight coefficient, i is 1,2,3, and represents a travel time preference when i is 1; when i is 2, the preference of the travel route is given, and when i is 3, the probability of the average vehicle speed exceeding the limit is given;
wherein:rθ1is the sex coefficient, rθ2Denotes the age coefficient, λθ1Is gender weight, λθ2Representing the age weight, pbRepresenting the ratio of the travel times of the insurance declaration in a set time period; when theta is 1, theta is 2, musIn order to set the limit value of the number of violations, mu is the historical number of violations of the vehicle in the set time period, A is an initial score, and through the calculation, the higher the score of the calculation result is, the lower the risk of the driving behavior of the vehicle is, and the lower the premium limit is estimated.
Finally, the above embodiments are only for illustrating the technical solutions of the present invention and not for limiting, although the present invention has been described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that modifications or equivalent substitutions may be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, and all of them should be covered in the claims of the present invention.
Claims (6)
1. A vehicle driving behavior risk analysis method based on big data is characterized in that: the method comprises the following steps:
s1, acquiring road network information, arranging RFID acquisition points on roads, acquiring vehicle information through an RFID reader-writer, and acquiring vehicle information through image acquisition equipment arranged at the RFID acquisition points;
s2, performing abnormal data elimination according to the vehicle information acquired by the RFID reader and the vehicle information acquired by the image equipment, and fitting to form a vehicle track based on the data with the abnormal data eliminated;
s3, determining a driving risk factor based on the track of the vehicle and the vehicle information;
and S4, constructing a risk scoring model based on the driving risk factors, and calculating the risk score of the vehicle.
2. The big-data-based vehicle driving behavior risk analysis method according to claim 1, wherein: in step S1, the vehicle information and the driver information acquired by the RFID reader/writer, where: the information of the vehicle comprises a license plate number, vehicle operation attributes, vehicle types and vehicle insurance declaration times;
the driver information comprises driver identity information, driver driving age, driver gender, driver age and driver historical violation times.
3. The big-data-based vehicle driving behavior risk analysis method according to claim 1, wherein: in step S1, the vehicle information acquired by the image acquisition device includes the license plate number, the vehicle color, and the driver face information.
4. The big-data-based vehicle driving behavior risk analysis method according to claim 1, wherein: the step of comparing, fusing and eliminating abnormal data of the vehicle information collected by the RFID reader and the image information collected by the image device specifically comprises the following steps:
extracting license plate numbers in the vehicle information acquired by the RFID reader-writer and license plate numbers in the vehicle information acquired by the image acquisition equipment;
and judging whether the license plate numbers in the two pieces of vehicle information are consistent, if so, further judging whether the distance between the position points of the RFID reader-writer and the image acquisition equipment is smaller than a set threshold value, if so, taking the vehicle information acquired by the current RFID reader-writer and the image acquisition equipment as effective data, and otherwise, taking the vehicle information acquired by the current RFID reader-writer and the image acquisition equipment as effective data.
5. The big-data-based vehicle driving behavior risk analysis method according to claim 4, wherein: determining the driving risk factor based on the trajectory of the vehicle and the vehicle information specifically includes:
counting the track of the current vehicle in a set time period, and determining the travel path preference of a driver according to the track;
counting the travel time of the current vehicle in each day within a set time period, and determining the travel time preference of a driver according to the travel time;
and acquiring the average speed of the current vehicle in each trip in a set time period according to the RFID reader, wherein the average speed is the average speed in the off-peak time period, and obtaining the out-of-limit probability according to the average speed.
6. The big-data-based vehicle driving behavior risk analysis method according to claim 1, wherein: in step S4, the risk scoring model is specifically as follows:
wherein S isiInitial value of credit, p, representing preference in ithiIs the ith preference value, betaiWeight value, alpha, representing the ith preferencemWeighting the vehicle operation attribute values; when m is 1, the weight coefficient of the private car is, when m is 2, the weight coefficient of the taxi is, when m is 3, the weight coefficient of the large-sized passenger car is, and when m is 4, the weight coefficient of the truck is; λ is an integrated weight coefficient, i is 1,2,3, and represents a travel time preference when i is 1; when i is 2, the preference of the travel route is given, and when i is 3, the probability of the average vehicle speed exceeding the limit is given;
wherein:rθ1is the sex coefficient, rθ2Denotes the age coefficient, λθ1Is gender weight, λθ2Representing the age weight, pbRepresenting the ratio of the travel times of the insurance declaration in a set time period; when theta is 1, theta is 2, musMu is the historical violation number of the vehicle in the set time period for setting the violation number limit value.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111673557.8A CN114331181A (en) | 2021-12-31 | 2021-12-31 | Vehicle driving behavior risk analysis method based on big data |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111673557.8A CN114331181A (en) | 2021-12-31 | 2021-12-31 | Vehicle driving behavior risk analysis method based on big data |
Publications (1)
Publication Number | Publication Date |
---|---|
CN114331181A true CN114331181A (en) | 2022-04-12 |
Family
ID=81020603
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202111673557.8A Pending CN114331181A (en) | 2021-12-31 | 2021-12-31 | Vehicle driving behavior risk analysis method based on big data |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN114331181A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117549913A (en) * | 2024-01-11 | 2024-02-13 | 交通运输部水运科学研究所 | Safe driving early warning system for mixed flow of port and district tank truck |
-
2021
- 2021-12-31 CN CN202111673557.8A patent/CN114331181A/en active Pending
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117549913A (en) * | 2024-01-11 | 2024-02-13 | 交通运输部水运科学研究所 | Safe driving early warning system for mixed flow of port and district tank truck |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
KR101617349B1 (en) | Diagnostic system and method for the analysis of driving behavior | |
CN111860561A (en) | Method, device, equipment and storage medium for identifying abnormal stopping behavior of network appointment vehicle | |
CN110751828B (en) | Road congestion measuring method and device, computer equipment and storage medium | |
US9082072B1 (en) | Method for applying usage based data | |
CN109670970B (en) | Driving behavior scoring method and device and computer readable storage medium | |
CN101465059B (en) | Early-warning system for inspecting and judging urban road traffic safety situation | |
CN107918826B (en) | Driver evaluation and scheduling method for driving environment perception | |
CN109242227A (en) | The driving risk and assessment models of car steering behavior | |
CN108764375B (en) | Highway goods stock transprovincially matching process and device | |
CN106846153A (en) | A kind of vehicle insurance compensates method and system | |
CN112215497B (en) | Pure electric vehicle operation risk early warning method | |
CN114999181B (en) | Highway vehicle speed abnormality identification method based on ETC system data | |
CN108803559A (en) | Vehicle trouble analysis method, device and system | |
CN115035491A (en) | Driving behavior road condition early warning method based on federal learning | |
CN115713858A (en) | Intelligent traffic operation management and control system based on traffic big data | |
CN114331181A (en) | Vehicle driving behavior risk analysis method based on big data | |
CN109887292B (en) | Vehicle type identification method and system | |
CN114333320B (en) | Vehicle driving behavior risk assessment system based on RFID | |
CN108596688A (en) | A kind of taxi passenger information acquisition methods and medium | |
CN110723148A (en) | Method and device for identifying bad driving behaviors | |
CN113743815A (en) | Risk monitoring method and device for operating vehicle, storage medium and computer equipment | |
CN112967497A (en) | Shared automobile supervision system and supervision method | |
CN114757447B (en) | Multi-model mixed passenger transport hub station passenger flow prediction method and system | |
CN111489556B (en) | Method for judging attaching behavior of commercial vehicle | |
CN114119256A (en) | UBI dangerous chemical vehicle driving behavior acquisition and analysis system and premium discount method |
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 |