CN112508228A - Driving behavior risk prediction method and system - Google Patents

Driving behavior risk prediction method and system Download PDF

Info

Publication number
CN112508228A
CN112508228A CN202011209242.3A CN202011209242A CN112508228A CN 112508228 A CN112508228 A CN 112508228A CN 202011209242 A CN202011209242 A CN 202011209242A CN 112508228 A CN112508228 A CN 112508228A
Authority
CN
China
Prior art keywords
data
parameters
vehicle
risk prediction
driving behavior
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
Application number
CN202011209242.3A
Other languages
Chinese (zh)
Inventor
李朋超
周娜娜
弭如坤
周逢军
王坤
魏斌
许媛
魏国亮
刘露
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Advanced Technology Research Institute of Beijing Institute of Technology
Original Assignee
Advanced Technology Research Institute of Beijing Institute of Technology
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Advanced Technology Research Institute of Beijing Institute of Technology filed Critical Advanced Technology Research Institute of Beijing Institute of Technology
Priority to CN202011209242.3A priority Critical patent/CN112508228A/en
Publication of CN112508228A publication Critical patent/CN112508228A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
    • 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
    • G06Q10/0635—Risk analysis of enterprise or organisation activities
    • 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
    • G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/10—Services
    • G06Q50/26—Government or public services
    • G06Q50/265—Personal security, identity or safety
    • G—PHYSICS
    • G07—CHECKING-DEVICES
    • G07C—TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
    • G07C5/00—Registering or indicating the working of vehicles
    • G07C5/008—Registering or indicating the working of vehicles communicating information to a remotely located station
    • G—PHYSICS
    • G07—CHECKING-DEVICES
    • G07C—TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
    • G07C5/00—Registering or indicating the working of vehicles
    • G07C5/08—Registering or indicating performance data other than driving, working, idle, or waiting time, with or without registering driving, working, idle or waiting time
    • G07C5/0841—Registering performance data
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16Y—INFORMATION AND COMMUNICATION TECHNOLOGY SPECIALLY ADAPTED FOR THE INTERNET OF THINGS [IoT]
    • G16Y10/00—Economic sectors
    • G16Y10/40—Transportation
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16Y—INFORMATION AND COMMUNICATION TECHNOLOGY SPECIALLY ADAPTED FOR THE INTERNET OF THINGS [IoT]
    • G16Y20/00—Information sensed or collected by the things
    • G16Y20/10—Information sensed or collected by the things relating to the environment, e.g. temperature; relating to location
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16Y—INFORMATION AND COMMUNICATION TECHNOLOGY SPECIALLY ADAPTED FOR THE INTERNET OF THINGS [IoT]
    • G16Y20/00—Information sensed or collected by the things
    • G16Y20/20—Information sensed or collected by the things relating to the thing itself
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16Y—INFORMATION AND COMMUNICATION TECHNOLOGY SPECIALLY ADAPTED FOR THE INTERNET OF THINGS [IoT]
    • G16Y40/00—IoT characterised by the purpose of the information processing
    • G16Y40/10—Detection; Monitoring
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16Y—INFORMATION AND COMMUNICATION TECHNOLOGY SPECIALLY ADAPTED FOR THE INTERNET OF THINGS [IoT]
    • G16Y40/00—IoT characterised by the purpose of the information processing
    • G16Y40/20—Analytics; Diagnosis
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16Y—INFORMATION AND COMMUNICATION TECHNOLOGY SPECIALLY ADAPTED FOR THE INTERNET OF THINGS [IoT]
    • G16Y40/00—IoT characterised by the purpose of the information processing
    • G16Y40/50—Safety; Security of things, users, data or systems

Landscapes

  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Human Resources & Organizations (AREA)
  • Computing Systems (AREA)
  • Economics (AREA)
  • Strategic Management (AREA)
  • General Physics & Mathematics (AREA)
  • Physics & Mathematics (AREA)
  • Tourism & Hospitality (AREA)
  • Development Economics (AREA)
  • General Business, Economics & Management (AREA)
  • General Health & Medical Sciences (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Operations Research (AREA)
  • Marketing (AREA)
  • Theoretical Computer Science (AREA)
  • Health & Medical Sciences (AREA)
  • Computer Security & Cryptography (AREA)
  • Quality & Reliability (AREA)
  • Educational Administration (AREA)
  • Game Theory and Decision Science (AREA)
  • Biomedical Technology (AREA)
  • Environmental & Geological Engineering (AREA)
  • Toxicology (AREA)
  • Primary Health Care (AREA)
  • Accounting & Taxation (AREA)
  • Traffic Control Systems (AREA)

Abstract

The invention relates to a driving behavior risk prediction method and a driving behavior risk prediction system. The method comprises the steps of obtaining historical travel data; performing data cleaning on the historical stroke data; label definition is carried out on the cleaned travel data to obtain label parameters; determining a trained risk prediction model by adopting a Fibonacci algorithm according to the label parameters; acquiring current travel data; and determining current label parameters according to the current travel data, and then predicting the risk by using the trained risk prediction model. The risk assessment method and the risk assessment system can dynamically and timely judge the risk and ensure the real-time performance of risk assessment and early warning.

Description

Driving behavior risk prediction method and system
Technical Field
The invention relates to the field of driving behavior risk prediction, in particular to a driving behavior risk prediction method and a driving behavior risk prediction system.
Background
Since 2010 the internet of vehicles technology entered the view of society, the internet of vehicles underwent a lengthy process from germination to growth. The generalized Internet of Vehicles (Internet of Vehicles) is a huge interactive network formed by information such as vehicle position, speed and route. The vehicle can complete the collection of self environment and state information through devices such as a GPS, an RFID, a sensor, a camera image processing device and the like; through the internet technology, all vehicles can transmit and gather various information of the vehicles to the central processing unit; through computer technology, the information of a large number of vehicles can be analyzed and processed, so that the optimal routes of different vehicles can be calculated, road conditions can be reported in time, and signal lamp periods can be arranged. The dynamic mobile communication system realizes the network communication between the vehicle and the public by the interaction of vehicle and vehicle, vehicle and road, vehicle and person, vehicle and sensing equipment, etc. The system can realize information sharing through interconnection and intercommunication of vehicles, vehicles and people and vehicles and roads, collect information of vehicles, roads and environments, process, calculate, share and safely release the information collected by multiple sources on an information network platform, effectively guide and supervise the vehicles according to different functional requirements, and provide professional multimedia and mobile internet application services.
The car networking system utilizes advanced sensing technology, network technology, computing technology, control technology and intelligent technology to comprehensively sense roads and traffic, realizes interaction of large-range and large-capacity data among a plurality of systems, controls all traffic of each car, controls all traffic of each road in a time-space mode, and provides networks and applications mainly for traffic efficiency and traffic safety.
The collection and processing of driving behavior data in the internet of vehicles system are important for the accuracy of the system, a risk judgment technology for establishing a driving behavior scoring model by collecting and cleaning data is provided at present, the risk of a driver is evaluated by scoring, the higher the score is, the better the driving behavior is, and otherwise, the worse the driving behavior is. The dimensions generally participating in evaluation mainly include driving mileage, driving duration, average speed, maximum speed, rapid acceleration times, rapid deceleration times, rapid turning times, night driving times, fatigue driving times and the like, and the data dimensions are used for scoring through respective driving behavior models.
The existing scoring method and the existing scoring technology can only score and judge the risk of the driving behavior after a single trip is finished, cannot dynamically score, cannot timely carry out risk early warning on accidents possibly occurring in the current trip, and have hysteresis for judging the accident risk.
Disclosure of Invention
The invention aims to provide a driving behavior risk prediction method and a driving behavior risk prediction system, which can dynamically and timely judge risks and ensure the real-time performance of risk evaluation and early warning.
In order to achieve the purpose, the invention provides the following scheme:
a driving behavior risk prediction method, comprising:
acquiring historical travel data; the trip data includes: driving behavior data, vehicle self data, vehicle claim data, road condition data and weather data; the driving behavior data includes: equipment identification, instantaneous speed, average speed, lateral acceleration, longitudinal acceleration, driving mileage, driving time, mileage segment number, sudden acceleration times/occurrence time, sudden braking times/occurrence time and sudden turning times/occurrence time; the vehicle own data includes: license plate number information, frame number, age of vehicle, gender of driver, age of driver, driving age of driver, and vehicle value; the vehicle claims data includes: historical insurance making times, historical insurance making amount, violation times, violation types, insurance making times in the last year, insurance making amount in the last year and whether insurance is not made for 3 years;
performing data cleaning on the historical stroke data;
label definition is carried out on the cleaned travel data to obtain label parameters; the label parameters are driving behavior parameters, vehicle parameters, claim settlement parameters, map parameters and weather parameters, and the data take the license plate number as a unique identifier;
determining a trained risk prediction model by adopting a Fibonacci algorithm according to the label parameters; the risk prediction model takes the label parameters as input and takes risk scores as output;
acquiring current travel data;
and determining current label parameters according to the current travel data, and then predicting the risk by using the trained risk prediction model.
Optionally, the obtaining historical travel data specifically includes:
collecting the driving behavior data by using a vehicle networking hardware terminal; the car networking hardware terminal includes: the system comprises a vehicle-mounted computer, a mobile phone end, a vehicle-mounted T-BOX and a vehicle-mounted automatic diagnosis system OBD;
acquiring data of the vehicle and the vehicle claim settlement data according to the frame number and the license plate number information;
and acquiring map data and weather data by using a map or a web crawler.
Optionally, the tag definition is performed on the cleaned trip data to obtain tag parameters, and the method specifically includes:
performing label definition on the cleaned travel data to obtain the driving behavior parameters, the vehicle parameters, the claim settlement parameters, the map parameters and the weather parameters;
splicing the driving behavior parameters, the vehicle parameters, the claim settlement parameters and the map parameters for one time by taking the license plate number as a unique identifier;
and performing secondary splicing on the parameters subjected to the primary splicing and the weather parameters according to time to obtain label parameters.
Optionally, the determining a trained risk prediction model by using a fibonacci algorithm according to the label parameter specifically includes:
acquiring the risk prediction model;
and training the risk prediction model by using a Fibonacci algorithm according to the label parameters and Python software, and determining the trained risk prediction model.
A driving behavior risk prediction system, comprising:
the historical travel data acquisition module is used for acquiring historical travel data; the trip data includes: driving behavior data, vehicle self data, vehicle claim data, road condition data and weather data; the driving behavior data includes: equipment identification, instantaneous speed, average speed, lateral acceleration, longitudinal acceleration, driving mileage, driving time, mileage segment number, sudden acceleration times/occurrence time, sudden braking times/occurrence time and sudden turning times/occurrence time; the vehicle own data includes: license plate number information, frame number, age of vehicle, gender of driver, age of driver, driving age of driver, and vehicle value; the vehicle claims data includes: historical insurance making times, historical insurance making amount, violation times, violation types, insurance making times in the last year, insurance making amount in the last year and whether insurance is not made for 3 years;
the data cleaning module is used for cleaning the historical stroke data;
the label parameter determining module is used for defining labels for the cleaned travel data to obtain label parameters; the label parameters are driving behavior parameters, vehicle parameters, claim settlement parameters, map parameters and weather parameters, and the data take the license plate number as a unique identifier;
the trained risk prediction model determining module is used for determining a trained risk prediction model by adopting a Fibonacci algorithm according to the label parameters; the risk prediction model takes the label parameters as input and takes risk scores as output;
the current travel data acquisition module is used for acquiring current travel data;
and the risk prediction module is used for determining the current label parameters according to the current travel data and then predicting the risk by utilizing the trained risk prediction model.
Optionally, the historical trip data acquiring module specifically includes:
the driving behavior data acquisition unit is used for acquiring the driving behavior data by using a vehicle networking hardware terminal; the car networking hardware terminal includes: the system comprises a vehicle-mounted computer, a mobile phone end, a vehicle-mounted T-BOX and a vehicle-mounted automatic diagnosis system OBD;
the vehicle self data and vehicle claim settlement data acquisition unit is used for acquiring the vehicle self data and the vehicle claim settlement data according to the frame number and license plate number information;
and the map data and weather data acquisition unit is used for acquiring the map data and the weather data by using a map or a web crawler.
Optionally, the tag parameter determining module specifically includes:
the label definition unit is used for performing label definition on the cleaned travel data to obtain the driving behavior parameters, the vehicle parameters, the claim settlement parameters, the map parameters and the weather parameters;
the primary splicing unit is used for splicing the driving behavior parameters, the vehicle parameters, the claim settlement parameters and the map parameters for the first time by taking the license plate number as a unique identifier;
and the secondary splicing unit is used for carrying out secondary splicing on the parameters subjected to the primary splicing and the weather parameters according to time to obtain the label parameters.
Optionally, the trained risk prediction model determining module specifically includes:
a risk prediction model acquisition unit configured to acquire the risk prediction model;
and the trained risk prediction model determining unit is used for training the risk prediction model by utilizing Python software and a Fibonacci algorithm according to the label parameters to determine the trained risk prediction model.
According to the specific embodiment provided by the invention, the invention discloses the following technical effects:
according to the driving behavior risk prediction method and system provided by the invention, in order to ensure the accuracy of data, the acquired travel data are cleaned firstly, then the cleaned data are integrated into one piece of data, namely the label parameter, and a trained risk prediction model is determined by utilizing the label parameter and adopting a Fibonacci algorithm. And then, determining the risk and probability of the current vehicle trip by using the trained risk prediction model, and outputting the current accident risk probability. The method and the device solve the problems that the conventional scoring method and the conventional scoring technology can only score the driving behaviors after a single trip is finished, judge risks, cannot dynamically score, cannot timely perform risk early warning on accidents possibly occurring in the trip and have hysteresis for judging the accident risks. Furthermore, the risk prediction capability of the Internet of vehicles is improved, and dynamic risk scoring is realized; the prediction of the high-incidence point of the travel accident is realized, the accident is reduced, the property loss of the car owner is reduced, and the life safety of the car owner is guaranteed.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings needed to be used in the embodiments will be briefly described 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 without inventive exercise.
FIG. 1 is a schematic flow chart of a driving behavior risk prediction method according to the present invention;
fig. 2 is a schematic structural diagram of a driving behavior risk prediction system provided by the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the 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 invention aims to provide a driving behavior risk prediction method and a driving behavior risk prediction system, which can dynamically and timely judge risks and ensure the real-time performance of risk evaluation and early warning.
In order to make the aforementioned objects, features and advantages of the present invention comprehensible, embodiments accompanied with figures are described in further detail below.
Fig. 1 is a schematic flow chart of a driving behavior risk prediction method provided by the present invention, and as shown in fig. 1, the driving behavior risk prediction method provided by the present invention includes:
s101, acquiring historical travel data; the trip data includes: driving behavior data, vehicle self data, vehicle claim data, road condition data and weather data; the driving behavior data includes: equipment identification, instantaneous speed, average speed, lateral acceleration, longitudinal acceleration, driving mileage, driving time, mileage segment number, sudden acceleration times/occurrence time, sudden braking times/occurrence time and sudden turning times/occurrence time; the vehicle own data includes: license plate number information, frame number, age of vehicle, gender of driver, age of driver, driving age of driver, and vehicle value; the vehicle claims data includes: historical insurance times, historical insurance amount, violation times, violation types, insurance times of the last year, insurance amount of the last year and whether no insurance is given for 3 years.
S101 specifically comprises the following steps:
collecting the driving behavior data by using a vehicle networking hardware terminal; the car networking hardware terminal includes: the system comprises a vehicle-mounted computer, a mobile phone end, a vehicle-mounted T-BOX and a vehicle-mounted automatic diagnosis system OBD.
And acquiring the data of the vehicle and the vehicle claim settlement data according to the information of the frame number and the license plate number.
And acquiring map data and weather data by using a map or a web crawler.
And S102, performing data cleaning on the historical process data.
Data cleaning cleans noise data such as null value, data loss to gathering, screens each data respectively according to the rule of table 1, and the deletion field contains the null value or has the data that the field loses, and table 1 is as follows:
TABLE 1
Figure BDA0002758234520000061
Figure BDA0002758234520000071
Figure BDA0002758234520000081
S103, label definition is carried out on the cleaned travel data to obtain label parameters; the label parameter is a piece of data of driving behavior parameter, vehicle parameter, claim settlement parameter, map parameter and weather parameter with license plate number as the unique identifier.
S103 specifically comprises the following steps:
and defining the label of the cleaned travel data to obtain the driving behavior parameter, the vehicle parameter, the claim settlement parameter, the map parameter and the weather parameter.
Wherein the driving behavior parameters include: unique identification, GPS speed, low speed ratio, acceleration, fatigue driving times, driving kilometers, travel segment number, total driving time length, average speed, rapid acceleration times/time, rapid deceleration times/time, rapid turning times/time and rapid lane changing times/time.
The vehicle parameters include: vehicle brand, vehicle value, frame number, vehicle age, driver gender, age, and driving age.
Claim parameters include: number of violations, type of violations, number of ventures in recent 3 years, location of ventures, time of ventures, amount of claims, and type of incident.
The map parameters include: and predicting the traffic condition of the point.
The weather parameters include: the current local weather conditions of the day.
And splicing the driving behavior parameters, the vehicle parameters, the claim settlement parameters and the map parameters for one time by taking the license plate number as a unique identifier.
And performing secondary splicing on the parameters subjected to the primary splicing and the weather parameters according to time to obtain label parameters.
As a specific example, tag definition is performed on the cleaned trip data to obtain tag parameters, as shown in table 2, table 2 is as follows:
TABLE 2
Figure BDA0002758234520000091
S104, determining a trained risk prediction model by adopting a Fibonacci algorithm according to the label parameters; the risk prediction model takes the tag parameters as input and takes risk scores as output.
In order to ensure the prediction accuracy of the trained risk prediction model, the model is optimized and upgraded regularly by combining historical claim settlement data.
S104 specifically comprises the following steps:
and acquiring the risk prediction model.
And training the risk prediction model by using a Fibonacci algorithm according to the label parameters and Python software, and determining the trained risk prediction model.
According to the Fibonacci recursion theory, assuming that the influence of each factor on the occurrence of the accident is the same, f factors are provided in total, k represents that each independent factor has k equal possible results, the probability of each result is 1/k, and the probability P of each occurrence/accumulation of the accident isn(k, m) is:
Figure BDA0002758234520000101
wherein n is a value of the random variable x, that is, the total trip times when the event a is { accident occurrence m times }. m represents the occurrence of the accident m times.
For a single trip, m is 1, i.e. the probability of 1 accident occurring in the current trip is
Figure BDA0002758234520000102
Wherein P is0The accident occurrence probability is accumulated before the current journey is started. The probability of m accidents occurring for the accumulated journey is Pn(k,m)。
And S105, acquiring current travel data.
And S106, determining the current label parameters according to the current travel data, and then predicting the risk by using the trained risk prediction model.
As a specific embodiment, after a vehicle starts, travel driving behavior parameters are collected through a vehicle networking hardware terminal (a vehicle-mounted computer, a mobile phone terminal, a T-BOX (T-BOX), an OBD (on-board diagnostics) and the like) according to the frequency of 5 s/time, and by combining vehicle parameters (system prestoring), map parameters (navigation access) and weather parameters (local official network weather parameters are obtained through a web crawler according to positioning), invalid data are deleted by cleaning 2 data, valid data are reserved, then 3 label definition is carried out, the driving behavior parameters, the vehicle parameters, claim settlement parameters and the map parameters are spliced into a piece of data by taking a license plate number as a unique identifier, the spliced data and the weather data are spliced according to time to form a piece of complete data, the complete data are input into a trained model, and the risk and the probability of the vehicle traveling at this time can be calculated through model calculation, and outputting the current accident risk probability, wherein the result can be used for early warning the driver in advance and can be output risk scores by combining a system, refreshing the accumulated scores, scoring the travel after the single travel is finished, and refreshing the accumulated scores. Meanwhile, the method can be used for risk pricing of insurance and provides data support for UBI insurance products.
Fig. 2 is a schematic structural diagram of a driving behavior risk prediction system provided by the present invention, and as shown in fig. 2, the driving behavior risk prediction system provided by the present invention includes: a historical trip data acquisition module 201, a data cleansing module 202, a tag parameter determination module 203, a trained risk prediction model determination module 204, a current trip data acquisition module 205, and a risk prediction module 206.
The historical travel data acquisition module 201 is used for acquiring historical travel data; the trip data includes: driving behavior data, vehicle self data, vehicle claim data, road condition data and weather data; the driving behavior data includes: equipment identification, instantaneous speed, average speed, lateral acceleration, longitudinal acceleration, driving mileage, driving time, mileage segment number, sudden acceleration times/occurrence time, sudden braking times/occurrence time and sudden turning times/occurrence time; the vehicle own data includes: license plate number information, frame number, age of vehicle, gender of driver, age of driver, driving age of driver, and vehicle value; the vehicle claims data includes: historical insurance making times, historical insurance making amount, violation times, violation types, insurance making times in the last year, insurance making amount in the last year and whether insurance is not made for 3 years;
the data cleaning module 202 is used for performing data cleaning on the historical process data.
The label parameter determining module 203 is configured to perform label definition on the cleaned trip data to obtain a label parameter; the label parameter is a piece of data of driving behavior parameter, vehicle parameter, claim settlement parameter, map parameter and weather parameter with license plate number as the unique identifier.
The trained risk prediction model determining module 204 is configured to determine a trained risk prediction model by using a fibonacci algorithm according to the tag parameter; the risk prediction model takes the tag parameters as input and takes risk scores as output.
The current trip data acquisition module 205 is configured to acquire current trip data.
The risk prediction module 206 is configured to determine a current tag parameter according to the current trip data, and then perform risk prediction using the trained risk prediction model.
The historical trip data acquiring module 201 specifically includes: the system comprises a driving behavior data acquisition unit, a vehicle self data and vehicle claim settlement data acquisition unit and a map data and weather data acquisition unit.
The driving behavior data acquisition unit is used for acquiring the driving behavior data by utilizing a hardware terminal of the internet of vehicles; the car networking hardware terminal includes: the system comprises a vehicle-mounted computer, a mobile phone end, a vehicle-mounted T-BOX and a vehicle-mounted automatic diagnosis system OBD.
The vehicle self data and vehicle claim settlement data acquisition unit is used for acquiring the vehicle self data and the vehicle claim settlement data according to the frame number and the license plate number information.
The map data and weather data acquisition unit is used for acquiring map data and weather data by using a map or a web crawler.
The tag parameter determining module 203 specifically includes: the label splicing system comprises a label defining unit, a primary splicing unit and a secondary splicing unit.
The label definition unit is used for performing label definition on the cleaned travel data to obtain the driving behavior parameters, the vehicle parameters, the claim settlement parameters, the map parameters and the weather parameters.
And the primary splicing unit is used for splicing the driving behavior parameters, the vehicle parameters, the claim settlement parameters and the map parameters at one time by taking the license plate number as a unique identifier.
And the secondary splicing unit is used for carrying out secondary splicing on the parameters subjected to the primary splicing and the weather parameters according to time to obtain the label parameters.
The trained risk prediction model determining module 204 specifically includes: a risk prediction model obtaining unit and a trained risk prediction model determining unit.
The risk prediction model obtaining unit is used for obtaining the risk prediction model.
And the trained risk prediction model determining unit is used for training the risk prediction model by utilizing Python software and a Fibonacci algorithm according to the label parameters to determine the trained risk prediction model.
The embodiments in the present description are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments are referred to each other. For the system disclosed by the embodiment, the description is relatively simple because the system corresponds to the method disclosed by the embodiment, and the relevant points can be referred to the method part for description.
The principles and embodiments of the present invention have been described herein using specific examples, which are provided only to help understand the method and the core concept of the present invention; meanwhile, for a person skilled in the art, according to the idea of the present invention, the specific embodiments and the application range may be changed. In view of the above, the present disclosure should not be construed as limiting the invention.

Claims (8)

1. A driving behavior risk prediction method, comprising:
acquiring historical travel data; the trip data includes: driving behavior data, vehicle self data, vehicle claim data, road condition data and weather data; the driving behavior data includes: equipment identification, instantaneous speed, average speed, lateral acceleration, longitudinal acceleration, driving mileage, driving time, mileage segment number, sudden acceleration times/occurrence time, sudden braking times/occurrence time and sudden turning times/occurrence time; the vehicle own data includes: license plate number information, frame number, age of vehicle, gender of driver, age of driver, driving age of driver, and vehicle value; the vehicle claims data includes: historical insurance making times, historical insurance making amount, violation times, violation types, insurance making times in the last year, insurance making amount in the last year and whether insurance is not made for 3 years;
performing data cleaning on the historical stroke data;
label definition is carried out on the cleaned travel data to obtain label parameters; the label parameters are driving behavior parameters, vehicle parameters, claim settlement parameters, map parameters and weather parameters, and the data take the license plate number as a unique identifier;
determining a trained risk prediction model by adopting a Fibonacci algorithm according to the label parameters; the risk prediction model takes the label parameters as input and takes risk scores as output;
acquiring current travel data;
and determining current label parameters according to the current travel data, and then predicting the risk by using the trained risk prediction model.
2. The driving behavior risk prediction method according to claim 1, wherein the obtaining of historical trip data specifically includes:
collecting the driving behavior data by using a vehicle networking hardware terminal; the car networking hardware terminal includes: the system comprises a vehicle-mounted computer, a mobile phone end, a vehicle-mounted T-BOX and a vehicle-mounted automatic diagnosis system OBD;
acquiring data of the vehicle and the vehicle claim settlement data according to the frame number and the license plate number information;
and acquiring map data and weather data by using a map or a web crawler.
3. The method for predicting the risk of the driving behavior according to claim 1, wherein the label definition is performed on the cleaned travel data to obtain a label parameter, and specifically comprises:
performing label definition on the cleaned travel data to obtain the driving behavior parameters, the vehicle parameters, the claim settlement parameters, the map parameters and the weather parameters;
splicing the driving behavior parameters, the vehicle parameters, the claim settlement parameters and the map parameters for one time by taking the license plate number as a unique identifier;
and performing secondary splicing on the parameters subjected to the primary splicing and the weather parameters according to time to obtain label parameters.
4. The method for predicting the risk of the driving behavior according to claim 1, wherein the step of determining the trained risk prediction model by using a fibonacci algorithm according to the label parameter specifically comprises:
acquiring the risk prediction model;
and training the risk prediction model by using a Fibonacci algorithm according to the label parameters and Python software, and determining the trained risk prediction model.
5. A driving behavior risk prediction system, comprising:
the historical travel data acquisition module is used for acquiring historical travel data; the trip data includes: driving behavior data, vehicle self data, vehicle claim data, road condition data and weather data; the driving behavior data includes: equipment identification, instantaneous speed, average speed, lateral acceleration, longitudinal acceleration, driving mileage, driving time, mileage segment number, sudden acceleration times/occurrence time, sudden braking times/occurrence time and sudden turning times/occurrence time; the vehicle own data includes: license plate number information, frame number, age of vehicle, gender of driver, age of driver, driving age of driver, and vehicle value; the vehicle claims data includes: historical insurance making times, historical insurance making amount, violation times, violation types, insurance making times in the last year, insurance making amount in the last year and whether insurance is not made for 3 years;
the data cleaning module is used for cleaning the historical stroke data;
the label parameter determining module is used for defining labels for the cleaned travel data to obtain label parameters; the label parameters are driving behavior parameters, vehicle parameters, claim settlement parameters, map parameters and weather parameters, and the data take the license plate number as a unique identifier;
the trained risk prediction model determining module is used for determining a trained risk prediction model by adopting a Fibonacci algorithm according to the label parameters; the risk prediction model takes the label parameters as input and takes risk scores as output;
the current travel data acquisition module is used for acquiring current travel data;
and the risk prediction module is used for determining the current label parameters according to the current travel data and then predicting the risk by utilizing the trained risk prediction model.
6. The driving behavior risk prediction system according to claim 5, wherein the historical trip data acquisition module specifically comprises:
the driving behavior data acquisition unit is used for acquiring the driving behavior data by using a vehicle networking hardware terminal; the car networking hardware terminal includes: the system comprises a vehicle-mounted computer, a mobile phone end, a vehicle-mounted T-BOX and a vehicle-mounted automatic diagnosis system OBD;
the vehicle self data and vehicle claim settlement data acquisition unit is used for acquiring the vehicle self data and the vehicle claim settlement data according to the frame number and license plate number information;
and the map data and weather data acquisition unit is used for acquiring the map data and the weather data by using a map or a web crawler.
7. The driving behavior risk prediction system of claim 5, wherein the tag parameter determination module specifically comprises:
the label definition unit is used for performing label definition on the cleaned travel data to obtain the driving behavior parameters, the vehicle parameters, the claim settlement parameters, the map parameters and the weather parameters;
the primary splicing unit is used for splicing the driving behavior parameters, the vehicle parameters, the claim settlement parameters and the map parameters for the first time by taking the license plate number as a unique identifier;
and the secondary splicing unit is used for carrying out secondary splicing on the parameters subjected to the primary splicing and the weather parameters according to time to obtain the label parameters.
8. The driving behavior risk prediction system of claim 5, wherein the trained risk prediction model determination module specifically comprises:
a risk prediction model acquisition unit configured to acquire the risk prediction model;
and the trained risk prediction model determining unit is used for training the risk prediction model by utilizing Python software and a Fibonacci algorithm according to the label parameters to determine the trained risk prediction model.
CN202011209242.3A 2020-11-03 2020-11-03 Driving behavior risk prediction method and system Pending CN112508228A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202011209242.3A CN112508228A (en) 2020-11-03 2020-11-03 Driving behavior risk prediction method and system

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202011209242.3A CN112508228A (en) 2020-11-03 2020-11-03 Driving behavior risk prediction method and system

Publications (1)

Publication Number Publication Date
CN112508228A true CN112508228A (en) 2021-03-16

Family

ID=74955302

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202011209242.3A Pending CN112508228A (en) 2020-11-03 2020-11-03 Driving behavior risk prediction method and system

Country Status (1)

Country Link
CN (1) CN112508228A (en)

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113252057A (en) * 2021-05-13 2021-08-13 青岛科技大学 Method and system for identifying driving tendency based on high altitude navigation data
CN113762755A (en) * 2021-08-30 2021-12-07 一汽解放汽车有限公司 Method and device for pushing driver analysis report, computer equipment and storage medium
CN114999022A (en) * 2022-05-19 2022-09-02 成都亿盟恒信科技有限公司 Driving habit analysis method and system based on historical driving data
CN117035422A (en) * 2023-08-22 2023-11-10 鱼快创领智能科技(南京)有限公司 Method for predicting freight train line transportation risk

Citations (13)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20060235780A1 (en) * 2005-04-19 2006-10-19 Carney Scott M Methodology of utilizing Fibonacci numbers to analyze and predict trends in financial markets
CN102693275A (en) * 2011-03-23 2012-09-26 Abb研究有限公司 Method for searching global maximum power point
CN104636955A (en) * 2014-12-30 2015-05-20 东莞市掌商信息科技有限公司 Merchant management information integration method and merchant management information integration system based on mobile internet
CN106096024A (en) * 2016-06-24 2016-11-09 北京京东尚科信息技术有限公司 The appraisal procedure of address similarity and apparatus for evaluating
CN108256714A (en) * 2016-12-29 2018-07-06 得道车联网络科技（上海）有限公司 A kind of wheelpath real-time risk assessment model based on car networking big data
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
CN108681964A (en) * 2018-04-19 2018-10-19 腾讯科技（深圳）有限公司 A kind of business settlement system and settlement of transactions control method
CN109388376A (en) * 2018-09-29 2019-02-26 平安科技（深圳）有限公司 Risk of software development appraisal procedure, device, equipment and readable storage medium storing program for executing
CN110288096A (en) * 2019-06-28 2019-09-27 江苏满运软件科技有限公司 Prediction model training and prediction technique, device, electronic equipment, storage medium
CN111009327A (en) * 2019-12-19 2020-04-14 京东方科技集团股份有限公司 Risk prediction method, device, system and medium
CN111402060A (en) * 2020-02-19 2020-07-10 长沙君财资产管理有限公司 Stock market prediction method
CN111582734A (en) * 2020-05-12 2020-08-25 上海海洋大学 Ocean pollution comparative analysis and risk assessment intelligent method based on python crawler system and SVM
CN111767522A (en) * 2020-06-29 2020-10-13 杭州海康威视系统技术有限公司 Recursive algorithm implementation method and device and electronic equipment

Patent Citations (13)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20060235780A1 (en) * 2005-04-19 2006-10-19 Carney Scott M Methodology of utilizing Fibonacci numbers to analyze and predict trends in financial markets
CN102693275A (en) * 2011-03-23 2012-09-26 Abb研究有限公司 Method for searching global maximum power point
CN104636955A (en) * 2014-12-30 2015-05-20 东莞市掌商信息科技有限公司 Merchant management information integration method and merchant management information integration system based on mobile internet
CN106096024A (en) * 2016-06-24 2016-11-09 北京京东尚科信息技术有限公司 The appraisal procedure of address similarity and apparatus for evaluating
CN108256714A (en) * 2016-12-29 2018-07-06 得道车联网络科技（上海）有限公司 A kind of wheelpath real-time risk assessment model based on car networking big data
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
CN108681964A (en) * 2018-04-19 2018-10-19 腾讯科技（深圳）有限公司 A kind of business settlement system and settlement of transactions control method
CN109388376A (en) * 2018-09-29 2019-02-26 平安科技（深圳）有限公司 Risk of software development appraisal procedure, device, equipment and readable storage medium storing program for executing
CN110288096A (en) * 2019-06-28 2019-09-27 江苏满运软件科技有限公司 Prediction model training and prediction technique, device, electronic equipment, storage medium
CN111009327A (en) * 2019-12-19 2020-04-14 京东方科技集团股份有限公司 Risk prediction method, device, system and medium
CN111402060A (en) * 2020-02-19 2020-07-10 长沙君财资产管理有限公司 Stock market prediction method
CN111582734A (en) * 2020-05-12 2020-08-25 上海海洋大学 Ocean pollution comparative analysis and risk assessment intelligent method based on python crawler system and SVM
CN111767522A (en) * 2020-06-29 2020-10-13 杭州海康威视系统技术有限公司 Recursive algorithm implementation method and device and electronic equipment

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113252057A (en) * 2021-05-13 2021-08-13 青岛科技大学 Method and system for identifying driving tendency based on high altitude navigation data
CN113762755A (en) * 2021-08-30 2021-12-07 一汽解放汽车有限公司 Method and device for pushing driver analysis report, computer equipment and storage medium
CN114999022A (en) * 2022-05-19 2022-09-02 成都亿盟恒信科技有限公司 Driving habit analysis method and system based on historical driving data
CN114999022B (en) * 2022-05-19 2024-05-17 成都亿盟恒信科技有限公司 Driving habit analysis system based on historical driving data
CN117035422A (en) * 2023-08-22 2023-11-10 鱼快创领智能科技(南京)有限公司 Method for predicting freight train line transportation risk

Similar Documents

Publication Publication Date Title
US20210407015A1 (en) Methods of determining accident cause and/or fault using telematics data
US10748419B1 (en) Vehicular traffic alerts for avoidance of abnormal traffic conditions
CN112508228A (en) Driving behavior risk prediction method and system
Tselentis et al. Innovative insurance schemes: pay as/how you drive
CN109416873B (en) Autonomous or partially autonomous motor vehicle with automated risk control system and corresponding method
US10872379B1 (en) Collision risk-based engagement and disengagement of autonomous control of a vehicle
US10490078B1 (en) Technology for providing real-time route safety and risk feedback
CN109670970B (en) Driving behavior scoring method and device and computer readable storage medium
CN105374211A (en) System and method for calculating driving risks and assisting automobile insurance pricing based on multi-source data
DE112016006295T5 (en) CLOUD-BASED DYNAMIC SYSTEM AND METHOD FOR VEHICLE SHARING
CN107784587A (en) A kind of driving behavior evaluation system
CN112598169B (en) Traffic operation situation assessment method, system and device
CN106022846A (en) Automobile insurance pricing method, second-hand automobile pricing method and corresponding devices
US20210024058A1 (en) Evaluating the safety performance of vehicles
CN112734242A (en) Method and device for analyzing availability of vehicle running track data, storage medium and terminal
CN112629524A (en) Travel path recommendation management method and device and electronic equipment
CN109214827A (en) A kind of method and apparatus that identification vehicle brush list deceives benefit behavior
William et al. Edge based Web Computing for Traffic Control Management for Distributed Environment Conditions
Ferreira et al. Vehicular sensing: Emergence of a massive urban scanner
CN118014404A (en) Intelligent optimization method and system based on parking lot system
CN110853358A (en) Insurance processing method based on driving behaviors and Internet of things intelligent terminal
CN113848073A (en) Human-vehicle collision probability prediction driving assistance method and system
Montero et al. Case study on cooperative car data for estimating traffic states in an urban network
CN112215481A (en) Method for determining business capability of ride-on test and driving test and business capability display system
CN114038202A (en) Parking guidance system and method based on intelligent park traffic flow

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
RJ01 Rejection of invention patent application after publication

Application publication date: 20210316

RJ01 Rejection of invention patent application after publication