CN110968839A - Driving risk assessment method, device, equipment and storage medium - Google Patents
Driving risk assessment method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN110968839A CN110968839A CN201911233101.2A CN201911233101A CN110968839A CN 110968839 A CN110968839 A CN 110968839A CN 201911233101 A CN201911233101 A CN 201911233101A CN 110968839 A CN110968839 A CN 110968839A
- Authority
- CN
- China
- Prior art keywords
- driving
- data
- risk
- vehicle
- risk assessment
- 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.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/18—Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression analysis
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Software Systems (AREA)
- Mathematical Physics (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Pure & Applied Mathematics (AREA)
- Mathematical Optimization (AREA)
- Evolutionary Computation (AREA)
- Mathematical Analysis (AREA)
- Computational Mathematics (AREA)
- Computing Systems (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Molecular Biology (AREA)
- Evolutionary Biology (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Operations Research (AREA)
- Probability & Statistics with Applications (AREA)
- Computational Linguistics (AREA)
- Algebra (AREA)
- Databases & Information Systems (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Medical Informatics (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention provides a driving risk assessment method, a driving risk assessment device, driving risk assessment equipment and a storage medium. The driving risk assessment method includes: the method comprises the steps of collecting driving data of each vehicle in a preset number of vehicles within a first set time length; aiming at one vehicle in a preset number of vehicles, inputting the driving data of the vehicle into one or more established risk assessment models; aiming at one risk evaluation model in one or more risk evaluation models, evaluating the accuracy of the risk evaluation model by utilizing each risk evaluation data output by the risk evaluation model to obtain an accuracy evaluation result; and establishing a driving risk evaluation model for evaluating the driving risk of the vehicle according to one or more accuracy evaluation results. By evaluating the accuracy of each risk evaluation model and establishing the driving risk evaluation model according to the accuracy evaluation result, the driving risk evaluation model with high accuracy of vehicle driving risk evaluation can be obtained.
Description
Technical Field
The invention relates to the technical field of internet, in particular to a driving risk assessment method, a driving risk assessment device, driving risk assessment equipment and a storage medium.
Background
With the increasing number of automobiles, people are increasingly associated with automobile insurance. The conventional three principles of 'from car', 'from use' and 'from person' of the car insurance rate pricing are determined by only the condition of the vehicle to be insured from the beginning, and are determined by comprehensively evaluating the condition of the vehicle to be insured, the use condition of the vehicle and the personal condition of a driver and acquiring the driving risk of the vehicle.
By adopting a big data analysis technology, a risk assessment model which comprehensively considers the condition of the vehicle to be protected, the use condition of the vehicle and the personal condition of the driver is established, and a driving risk accuracy assessment result for representing the driving risk can be obtained. However, the analysis accuracy of the existing risk assessment model is often not high, which often results in low accuracy of the vehicle driving risk assessment result when the existing risk analysis model is used for assessing the vehicle driving risk.
Disclosure of Invention
In view of this, embodiments of the present invention provide a driving risk assessment method, apparatus, device, and storage medium. The driving risk assessment model established by the driving risk assessment method, the driving risk assessment device, the driving risk assessment equipment and the storage medium can improve the accuracy of vehicle driving risk assessment to a certain extent.
In one aspect of the embodiments of the present invention, a driving risk assessment method is provided, where the method includes:
step S1: the method comprises the steps of collecting driving data of each vehicle in a preset number of vehicles within a first set time length;
step S2: for a vehicle in the preset number of vehicles, inputting the driving data of the vehicle into one or more established risk assessment models, so that the driving data of the vehicle is analyzed by using the one or more risk assessment models respectively, and risk assessment data which are output by each risk assessment model and can represent the driving risk of the vehicle is obtained;
step S3: aiming at one risk evaluation model in the one or more risk evaluation models, evaluating the accuracy of the risk evaluation model by utilizing each risk evaluation data output by the risk evaluation model to obtain an accuracy evaluation result;
step S4: and establishing a driving risk evaluation model for evaluating the driving risk of the vehicle according to one or more accuracy evaluation results.
In one aspect of the embodiments of the present invention, a driving risk assessment apparatus is provided, where the apparatus includes:
the system comprises an acquisition module, a storage module and a control module, wherein the acquisition module is used for acquiring driving data of each vehicle in a preset number of vehicles within a first set time length;
the analysis module is used for inputting the driving data of one vehicle in the preset number of vehicles into one or more established risk assessment models, so that the driving data of the vehicle are analyzed by using the one or more risk assessment models respectively, and the risk assessment data which are output by the risk assessment models and can represent the driving risk of the vehicle are obtained;
the evaluation module is used for evaluating the accuracy of the risk evaluation model by utilizing each risk evaluation data output by the risk evaluation model aiming at one risk evaluation model in the one or more risk evaluation models to obtain an accuracy evaluation result;
and the establishing module is used for establishing a driving risk evaluation model for evaluating the driving risk of the vehicle according to one or more accuracy evaluation results.
In one aspect of the embodiments of the present invention, there is provided a driving risk assessment apparatus, including: at least one processor, at least one memory, and computer program instructions stored in the memory that, when executed by the processor, implement the driving risk assessment method as described above.
In one aspect of the embodiments of the present invention, there is provided a storage medium having stored thereon computer program instructions, which when executed by a processor, implement the method of the first aspect in the above embodiments.
In conclusion, the beneficial effects of the invention are as follows:
according to the driving risk assessment method, the driving risk assessment device, the driving risk assessment equipment and the storage medium, the accuracy of each risk assessment model is assessed, the driving risk assessment model is established according to the accuracy assessment result, and the driving risk assessment model with high accuracy of vehicle driving risk assessment can be obtained.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required to be used in the embodiments of the present invention will be briefly described below, and for those skilled in the art, without any creative effort, other drawings may be obtained according to the drawings, and these drawings are all within the protection scope of the present invention.
Fig. 1 is a schematic flow chart of a driving risk assessment method according to an embodiment of the present invention;
FIG. 2 is a driving data table applied to the method of FIG. 1;
fig. 3 is a schematic flow chart of a driving risk assessment method according to an embodiment of the present invention;
fig. 4 is a schematic flow chart of a driving risk assessment method according to an embodiment of the present invention;
fig. 5 is a schematic flow chart of a driving risk assessment method according to an embodiment of the present invention;
fig. 6 is a schematic flow chart of a driving risk assessment method according to an embodiment of the present invention;
fig. 7 is a schematic flow chart illustrating a driving risk assessment method according to an embodiment of the present invention;
fig. 8 is a schematic flow chart illustrating a driving risk assessment method according to an embodiment of the present invention;
fig. 9 is a schematic flow chart of a driving risk assessment method according to an embodiment of the present invention;
fig. 10 is a schematic flow chart illustrating a driving risk assessment method according to an embodiment of the present invention;
fig. 11 is a schematic connection diagram of a driving risk assessment apparatus according to an embodiment of the present invention;
fig. 12 is a schematic connection diagram of a driving risk assessment apparatus according to an embodiment of the present invention;
fig. 13 is a schematic connection diagram of a driving risk assessment apparatus according to an embodiment of the present invention;
fig. 14 is a schematic connection diagram of a driving risk assessment apparatus according to an embodiment of the present invention;
fig. 15 is a schematic connection diagram of a driving risk assessment apparatus according to an embodiment of the present invention;
fig. 16 is a schematic connection diagram of a driving risk assessment apparatus according to an embodiment of the present invention;
fig. 17 is a schematic connection diagram of a driving risk assessment apparatus according to an embodiment of the present invention;
fig. 18 is a schematic connection diagram of a driving risk assessment apparatus according to an embodiment of the present invention;
fig. 19 is a schematic connection diagram of devices in a driving risk assessment system according to an embodiment of the present invention.
Detailed Description
Features and exemplary embodiments of various aspects of the present invention will be described in detail below, and in order to make objects, technical solutions and advantages of the present invention more apparent, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not to be construed as limiting the invention. It will be apparent to one skilled in the art that the present invention may be practiced without some of these specific details. The following description of the embodiments is merely intended to provide a better understanding of the present invention by illustrating examples of the present invention.
It is noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
An embodiment of the present invention provides a driving risk assessment method, as shown in fig. 1, including the following steps S1-S4:
step S1: the method comprises the steps of collecting driving data of each vehicle in a preset number of vehicles within a first set time length.
The preset number is an integer greater than or equal to 1. The predetermined number of vehicles includes one or more vehicles. The first set time length is a natural number greater than zero. The method for acquiring the driving data of each vehicle in the preset number of vehicles within a first set time comprises the following steps: some or all of the driving data shown in fig. 2 for each of the predetermined number of vehicles for a first set period of time is collected. FIG. 2 is a table of collected driving data.
As shown in fig. 2, the collected driving data includes: one or more of driver personal data, vehicle data, trip mileage data, travel time data, travel route data, other data. All the driving data collected here are driving data of each of a preset number of vehicles.
For one vehicle of a preset number of vehicles, the collected personal data of the driver comprises personal data of the driver of the vehicle. The collected personal data of the driver of the vehicle comprises: sex data, age data, driving license state data, violation record data, deduction data, sharp plus/sharp minus/sharp turn/sharp lane change data, driving behavior habit data and the like of the driver are data which are related to the individual of the driver.
For one vehicle in a preset number of vehicles, the collected vehicle data includes vehicle condition data of the vehicle. The vehicle data collected for the vehicle includes: brand data, displacement data, vehicle fault diagnosis data, highest vehicle speed data, use data, vehicle safety system data, chassis system data, vehicle violation data, vehicle dynamic data, finished vehicle system data and the like of the vehicle are related to the vehicle.
The collected mileage data includes mileage data of one vehicle among a preset number of vehicles. The collected driving mileage data of the vehicle includes: the vehicle driving mileage data includes data related to the driving mileage of the vehicle, such as morning and evening rush hour mileage data, holiday mileage data, vehicle fault diagnosis data, late midnight mileage data, single driving mileage data, total driving mileage data, and the like.
For one vehicle in a preset number of vehicles, the collected travel time data comprises the travel time data of the vehicle. The collected travel time data of the vehicle comprises: the travel time of the vehicle is related to the travel time of the vehicle, such as single travel time, travel starting time, different speed time, night travel time and the like.
Collecting driving data of a vehicle includes:
for one vehicle in the preset number of vehicles, the collected driving route data comprises the driving route data of the vehicle. The collected driving route data of the vehicle comprises: data on the traveling route of the vehicle, such as the passing administrative area data, the passing road type data, the familiar route condition data, the single trip average speed data, and the like, of the vehicle.
For one vehicle in the preset number of vehicles, other data of the vehicle, such as annual mileage data and annual time data of the vehicle, are also collected.
Through collecting a plurality of driving data of a preset number of vehicles within a first set time, the driving data can be analyzed, and risk assessment data representing driving risks are obtained.
Step S2: and for one vehicle in the preset number of vehicles, inputting the driving data of the vehicle into one or more established risk assessment models, so that the driving data of the vehicle is analyzed by using the one or more risk assessment models respectively, and risk assessment data which are output by the risk assessment models and can represent the driving risk of the vehicle is obtained.
Before the driving data of the vehicle is analyzed, one or more risk assessment models capable of analyzing the driving data are established. And inputting the driving data of the vehicle to each risk assessment model of the established one or more risk assessment models, processing the driving data of the vehicle by utilizing the one or more risk assessment models respectively, and outputting the risk assessment data representing the driving risk of the vehicle.
Inputting the driving data of the vehicle into one or more established risk assessment models, so as to analyze the driving data of the vehicle by using the risk assessment models, and acquiring risk assessment data which is output by each risk assessment model and can represent the driving risk of the vehicle, wherein the risk assessment data comprises: aiming at one vehicle in a preset number of vehicles, all driving data of the vehicle are respectively input into one or more risk assessment models, and after the input driving data of the vehicle are respectively analyzed and processed by each risk assessment model, the risk assessment data capable of representing the driving risk of the vehicle are output.
In one embodiment, the established one or more risk assessment models include: one or more of a GLM Model (generalized Linear Model), a decision tree Model, and a neural network Model.
Step S2 includes: and aiming at one vehicle in the preset number of vehicles, inputting each piece of driving data of the vehicle into one or more of the GLM model, the decision tree model and the neural network model, and obtaining the risk assessment data which are respectively output by each risk assessment model and represent the driving risk of the vehicle.
For one of the vehicles in the preset number, the driving data of the vehicle is input into one or more of the GLM model, the decision tree model and the neural network model, so that driving risk data which are output by each model and represent the driving risk of the vehicle can be obtained.
In one embodiment, as shown in fig. 3, step S2 includes:
step S204: and aiming at one vehicle in the preset number of vehicles, inputting all the driving data of the vehicle into a GLM (global positioning management) model, and obtaining the risk assessment data of the vehicle output by the GLM model.
The driving data of one vehicle among the preset number of vehicles has been collected in step S1. According to the method, collected driving data of a vehicle in a preset number of vehicles are input into a GLM model, risk assessment data of the vehicle output by the GLM model can be obtained, and the risk assessment data of the vehicle output by the GLM model can represent the driving risk of the vehicle.
The GLM model is a common vehicle driving risk assessment model. The biggest characteristic of the GLM model is to expand the type of distribution, and assume that the mean of the response variables is equal to the linear combination of the interpretation variables after being transformed by some kind of connecting function.
The GLM model can be represented by the following structure:
β therein0,β1,β2,…,βMFor the parameter to be estimated, { YiI 1,2, …, N, are independent of each other and obey an exponential distribution EDF. For example, the probability (density) function has the following expression, which is called an exponential distribution:
β estimated by data0,β1,β2,…,βMThe parameters are the most important part of the overall analysis.
Step S205: and aiming at one vehicle in the preset number of vehicles, inputting all the driving data of the vehicle into the decision tree model, and obtaining the risk assessment data of the vehicle output by the decision tree model.
For a vehicle in a preset number of vehicles, inputting the collected driving data of the vehicle into a decision tree model, so that the risk assessment data of the vehicle output by the decision tree model can be obtained, and the risk assessment data of the vehicle output by the decision tree model can represent the driving risk of the vehicle.
Decision tree models are common algorithmic models in machine learning. The invention adopts CART algorithm in decision tree model to calculate. The CART algorithm has the characteristics of accurate calculation and high operation efficiency.
Step S206: and aiming at one vehicle in the preset number of vehicles, inputting all the driving data of the vehicle into the neural network model, and obtaining the risk assessment data of the vehicle output by the neural network model.
For one vehicle in the preset number of vehicles, the collected driving data of the vehicle is input into the neural network model, the risk assessment data of the vehicle output by the neural network model can be obtained, and the risk assessment data of the vehicle output by the neural network model can represent the driving risk of the vehicle.
The computational units of the neural network model are neurons (neuron), also known as nodes or units (unit).
The calculation formula is as follows:
Y＝f(w1.X1+w2.X2+b)
wherein f (w1.X1+ w2.X2+ b) is a neuron. The neuron receives input data X1 (weight w1), X2 (weight w2) and a bias of 1 (weight b), and generates an output Y after computation by a function f ().
And inputting all driving data into a neuron for calculation, wherein the output data is risk evaluation data.
In one embodiment, the more input data each risk assessment model has, the more accurate the calculation. As shown in fig. 4, for a vehicle of the preset number of vehicles, when the collected driving data of the vehicle is less, the driving data may be expanded by step S11 before step S2, and more data that may be input into the risk assessment model may be generated.
Step S11: and generating derived driving data of the vehicle by using the driving data of the vehicle aiming at one vehicle in the preset number of vehicles.
Through a set algorithm, a plurality of derivative driving data can be generated by utilizing the collected driving data expansion. The driving data and the plurality of derived driving data generated by expansion are simultaneously input into the risk assessment model, so that the calculation accuracy of the risk assessment model can be improved.
As shown in fig. 5, step S11 includes:
step S111: and expanding the driving data of one vehicle in the preset number of vehicles by using a calculation formula Y-lnX to obtain derivative driving data of the vehicle, wherein Y is the derivative driving data, and X is the driving data.
Step S112: for one vehicle in the preset number of vehicles, utilizing a calculation formula of Y-eXAnd expanding the driving data of the vehicle to obtain derivative driving data of the vehicle, wherein Y is the derivative driving data, and X is the driving data.
Step S113: and for one vehicle in the preset number of vehicles, expanding the driving data of the vehicle by using a calculation formula Y-Xn to obtain derivative driving data of the vehicle, wherein Y is the derivative driving data, X is the driving data, and n is an integer greater than zero.
In step S11, one driving data can be expanded to generate three derived driving data by the calculation of the above steps S111 to S113.
Step S2 further includes: and for one vehicle in the preset number of vehicles, inputting the driving data of the vehicle and the derivative driving data of the vehicle into one or more established risk assessment models, analyzing the driving data and the derivative driving data by using the one or more risk assessment models, and acquiring risk assessment data which can represent the driving risk of the vehicle and is output by each risk assessment model.
For one vehicle in the preset number of vehicles, the acquired driving data of the vehicle and the derivative driving data generated by the driving data expansion of the vehicle are simultaneously input into the risk assessment model, so that the accuracy of the risk assessment data which is output by the risk assessment model and represents the driving risk of the vehicle can be improved.
In one embodiment, the collected driving data includes: one or more of driver personal data, vehicle data, mileage data, travel time data, and travel route data. Step S201 further includes: analyzing one or more of the personal data of the driver, the vehicle data, the mileage data, the travel time data and the travel route data to obtain a plurality of risk factors representing the relation between the driving data and the driving risk.
As shown in fig. 6, the analyzing each driving data using the risk assessment model in step S2 includes:
step S201: and analyzing the driving data of the vehicle aiming at one vehicle in the preset number of vehicles to obtain a plurality of risk factors respectively representing the relation between the driving data and the driving risk.
For one of the vehicles in the preset number, the risk factor represents a relationship between each driving data of the vehicle and the driving risk of the vehicle.
In one embodiment, for a vehicle of the predetermined number of vehicles, the collected driving data for the vehicle includes: personal data of the driver of the vehicle, vehicle data, mileage data, travel time data, travel route data, and the like.
As shown in fig. 7, in step S201, analyzing the driving data of the vehicle to obtain a plurality of risk factors respectively representing the relationship between each driving data and the driving risk includes:
and step S2011, analyzing the personal data of the driver and acquiring a risk factor representing the relationship between the personal data of the driver and the driving risk.
For a vehicle of a preset number of vehicles, the collected driver personal data of the vehicle driver comprises: the age data, sex data, driving age data, driving license state data, violation record data, deduction data, sharp acceleration/sharp reduction/sharp turning/sharp lane change data and the like of the vehicle driver.
By analyzing and processing the driver personal data, a risk factor representing the relationship between the driver personal data and the driving risk can be acquired. The risk factor representing the driver's personal data in relation to the driving risk can show the driver's personal influence on the driving risk.
In one embodiment, for a vehicle of the preset number of vehicles, the higher the risk factor of the vehicle representing the driver personal data versus driving risk relationship, the lower the driving risk of the vehicle.
Step S2012: and analyzing the vehicle data to obtain a risk factor representing the relationship between the vehicle data and the driving risk.
For a vehicle of a preset number of vehicles, the collected vehicle data of the vehicle comprises: brand data, displacement data, usage data, maximum vehicle speed data, vehicle fault diagnosis data, vehicle safety factor data, chassis system data and the like of the vehicle.
By analyzing and processing the vehicle data, a risk factor indicating a relationship between the vehicle data and the driving risk can be acquired. A risk factor representing the relationship of vehicle data to driving risk can indicate the impact of the vehicle on driving risk.
In one embodiment, for a vehicle of the preset number of vehicles, the higher the risk factor of the vehicle representing the relationship of the vehicle data to the driving risk, the lower the driving risk of the vehicle.
Step S2013: and analyzing the driving mileage data to obtain a risk factor representing the relation between the driving mileage data and the driving risk.
For a vehicle in a preset number of vehicles, the collected mileage data of the vehicle includes: the vehicle comprises early and late peak mileage data, holiday mileage data, vehicle fault diagnosis data, late midnight mileage data, single-time mileage data, total mileage data and the like.
By analyzing and processing the mileage data, a risk factor representing the relationship between the mileage data and the driving risk can be obtained. A risk factor representing the relationship of the mileage data to the driving risk can show the influence of the vehicle mileage on the driving risk.
In one embodiment, for a vehicle of the preset number of vehicles, the higher the risk factor of the vehicle representing the relationship between the vehicle mileage and the driving risk, the lower the driving risk of the vehicle.
Step S2014: and analyzing the travel time data to obtain a risk factor representing the relationship between the travel time data and the driving risk.
For a vehicle in a preset number of vehicles, the collected travel time data of the vehicle comprises: single travel time, trip start time, different speed times, night travel time, etc.
By analyzing and processing the travel time data, a risk factor representing the relationship between the vehicle travel time data and the driving risk can be acquired. The risk factor representing the relation between the vehicle travel time and the driving risk can display the influence of the vehicle travel time on the driving risk.
In one embodiment, for a vehicle in the preset number of vehicles, the higher the risk factor of the vehicle representing the relationship between the travel time and the driving risk of the vehicle, the lower the driving risk of the vehicle.
Step S2015: and analyzing the driving route data to obtain a risk factor representing the relation between the driving route data and the driving risk.
For a vehicle in a preset number of vehicles, the collected driving route data of the vehicle comprises: administrative region-passing data, road-passing type data, familiar route condition data, single-trip uniform speed data, and the like.
By analyzing and processing the travel route data, a risk factor indicating a relationship between the vehicle travel route data and the driving risk can be acquired. The risk factor representing the relationship of the vehicle travel route data to the driving risk can show the influence of the vehicle's frequent travel route on the driving risk.
In one embodiment, for a vehicle of the preset number of vehicles, the higher the risk factor of the vehicle representing the relationship between the vehicle travel route data and the driving risk, the lower the driving risk of the vehicle.
In one embodiment, for a vehicle of the preset number of vehicles, the collected driving data of the vehicle comprises: the driving mileage data of the vehicle and the time data corresponding to the trip mileage.
Step S201 further includes: and analyzing the travel mileage data and the time data corresponding to the travel mileage to obtain a risk factor representing the relationship between the travel mileage and the driving risk in a period of time.
For one vehicle in the preset number of vehicles, the driving mileage data of the vehicle and the time data corresponding to the driving mileage are analyzed, and a risk factor representing the relation between the driving mileage of the vehicle and the driving risk in a period of time can be obtained.
For one vehicle in a preset number of vehicles, analyzing the driving mileage data of the vehicle and the time data corresponding to the driving mileage comprises the following steps: and dividing the driving mileage data of the vehicle by the time data corresponding to the driving mileage to obtain a risk factor representing the relation between the driving mileage of the vehicle and the driving risk in a period of time. At this time, the greater the risk factor indicating the relationship between the driving range and the driving risk of the vehicle over a period of time, the greater the driving risk of the vehicle.
In one embodiment, for a vehicle of the preset number of vehicles, the collected driving data of the vehicle comprises: travel time data of the vehicle and travel speed data corresponding to the travel time data.
As shown in fig. 8, step S201 further includes:
step S2016: the travel speeds are classified into different categories according to travel speed data corresponding to the travel time data.
The running speed of the vehicle can be divided into a low-speed running stage, a medium-low speed running stage, a medium-high speed running stage, and a high-speed running stage according to running speed data corresponding to the running time data.
Step S2017: and respectively acquiring the running time of each speed category in a running period.
According to the collected running time data and the running speed data corresponding to the running time data, the running time of each speed category in a running time period can be acquired respectively.
According to the collected running time data and the running speed data corresponding to the running time data, the running time of the vehicle in a low-speed running stage, the running time in a medium-low speed running stage, the running time in a medium-high speed running stage and the running time in a high-speed running stage in a running period can be obtained.
Step S2018: dividing the running time corresponding to each speed category by the running time period to obtain a plurality of speed factors;
dividing each speed category by the travel period, respectively, can obtain a plurality of speed factors. The running time of the vehicle in the low-speed running stage, the running time in the medium-high-speed running stage, and the running time in the high-speed running stage are divided by the running time period, respectively, so that the speed factor in the low-speed running stage, the speed factor in the medium-high-speed running stage, and the speed factor in the high-speed running stage can be obtained.
Step S2019: and processing each speed factor to obtain a risk factor representing the relation between the running speed and the driving risk.
Processing each speed factor includes: and respectively multiplying the speed factor of the low-speed running stage, the speed factor of the medium-low speed running stage, the speed factor of the medium-high speed running stage and the speed factor of the high-speed running stage by corresponding weights, and then adding the multiplied values to obtain a risk factor representing the relation between the running speed and the driving risk.
For a vehicle of the preset number of vehicles, the risk factor representing the relation between the running speed and the driving risk can represent the relation between the running speed of the vehicle and the driving risk of the vehicle.
In one embodiment, for a vehicle of the preset number of vehicles, the collected driving data of the vehicle comprises: the driving range data of the vehicle and the number of driving hazard events within the driving range.
Step S201 further includes: and processing the driving mileage data and the occurrence frequency of the driving dangerous events in the driving mileage to obtain a risk factor representing the occurrence frequency of the driving dangerous events in the driving mileage.
Processing the driving mileage data and the occurrence frequency of driving dangerous events in the driving mileage to obtain a risk factor representing the occurrence frequency of the driving dangerous events in the driving mileage, and the method comprises the following steps: and aiming at one vehicle in the preset number of vehicles, dividing the driving range data of the vehicle by the occurrence frequency of the driving dangerous events in the driving range to obtain a risk factor representing the occurrence frequency of the driving dangerous events in the driving range of the vehicle.
For a vehicle of the preset number of vehicles, the risk factor representing the number of driving risk events occurring within the driving range of the vehicle can represent the likelihood of the driving risk event occurring for the vehicle.
Step S202: and processing each risk factor to obtain risk evaluation data representing the driving risk of the vehicle.
Each risk factor acquired in step S201 can represent the relationship between each driving data and the driving risk. By processing each risk factor, risk assessment data indicating the driving risk of the vehicle can be acquired.
In one embodiment, for a vehicle in a preset number of vehicles, processing each risk factor to obtain risk assessment data representing the driving risk of the vehicle includes: and adding the risk factors of the vehicle, and taking the sum of the risk factors as risk evaluation data representing the driving risk of the vehicle.
In another embodiment, for a vehicle in a preset number of vehicles, processing each risk factor to obtain risk assessment data representing the driving risk of the vehicle includes: and multiplying each risk factor of the vehicle by the corresponding weight respectively and then adding the product to obtain risk evaluation data representing the driving risk of the vehicle.
For a vehicle of the preset number of vehicles, the risk assessment data for the driving risk of the vehicle can represent the driving risk of the vehicle.
In one embodiment, for a vehicle of the preset number of vehicles, the greater the risk assessment data for that vehicle, the lower the driving risk for that vehicle.
Step S3: and aiming at one risk evaluation model in the one or more risk evaluation models, evaluating the accuracy of the risk evaluation model by using each risk evaluation data output by the risk evaluation model to obtain an accuracy evaluation result.
Each risk assessment data includes risk assessment data for each vehicle of the first set number of vehicles output by each risk assessment model. And outputting risk evaluation data of each vehicle in the first set number of vehicles by using each risk evaluation model, evaluating the accuracy of each risk evaluation model, and obtaining the accuracy evaluation result of each risk evaluation model.
In one embodiment, as shown in fig. 9, the evaluating the accuracy of each risk assessment model using each risk assessment data in step S3 includes:
step S301: and aiming at one risk evaluation model in the one or more risk evaluation models, dividing each vehicle in the preset number of vehicles into different groups according to the size of the risk evaluation data output by the corresponding risk evaluation model.
For a risk assessment model, dividing each vehicle of the preset number of vehicles into different groups according to the size of risk assessment data output by the corresponding risk assessment model, including: dividing the vehicles with the risk evaluation data output by the risk evaluation model smaller than a fourth set value into a group; dividing the vehicles with the risk evaluation data output by the risk evaluation model larger than a fourth set value and smaller than a fifth set value into a group; and classifying the vehicles with the risk assessment data output by the risk assessment model larger than the fifth set value into a group.
Step S302: and collecting the total times of the risks of the vehicles in each group in the risk assessment model within a second set time length.
In step S301, after the vehicles in the preset number of vehicles are grouped according to the risk assessment data output by the risk assessment model, collecting the total number of times of risk occurrence of each group of vehicles in the risk assessment model within a second set time period includes: and adding the number of times of the vehicle in the group to take out the risk within a second set time period aiming at one group in the risk assessment model to obtain the total number of times of the group to take out the risk.
Step S303: and evaluating the accuracy of the risk evaluation model by using the risk times of each group in the risk evaluation model to obtain an accuracy evaluation result of the risk evaluation model.
The total number of times of risk in each group in the risk assessment model collected in step S302. The total number of times of risk occurrence of each group corresponds to a numerical range in which the risk assessment data of each vehicle in the group output by the risk assessment model is located. The accuracy of the risk assessment model can be assessed by utilizing the corresponding relation between the total number of times of risk of each group in the risk assessment model and the value interval where the risk assessment data of each vehicle in the group output by the risk assessment model is located.
According to the accuracy evaluation results of the risk evaluation models, a driving risk evaluation model for evaluating the driving risk of the vehicle can be established.
Step S4: and establishing a driving risk evaluation model for evaluating the driving risk of the vehicle according to one or more accuracy evaluation results.
In one embodiment, establishing a driving risk assessment model based on one or more of the accuracy assessment results comprises: and taking the risk evaluation model with good accuracy evaluation result as a driving risk evaluation model.
In one embodiment, establishing a driving risk assessment model based on one or more of the accuracy assessment results comprises: and aiming at the accuracy evaluation result of a risk evaluation model, optimizing the risk evaluation model, so that the risk evaluation model can analyze the driving risk of the vehicle more accurately.
In one embodiment, the driving risk assessment model for assessing the driving risk of the vehicle is established according to the accuracy assessment result of each risk assessment model. The established driving risk assessment model comprises a calculation formula:
step S4 includes: by the calculation formula:
acquiring the driving risk evaluation result; wherein i is 1,2, 3 … …, M is an integer of 1 or more, M is a hydrogen atomiRisk assessment data output for the risk assessment model; wiIn order to be a weight factor, the weight factor,
and P is a driving risk evaluation result which is output by the driving risk evaluation model and can represent the driving risk of the vehicle.
Each risk assessment model MiIs different in accuracy, and its corresponding weight factor WiDifferent. The more accurate the risk assessment model, the larger the corresponding weighting factor.
Wherein, in one embodiment, M is 3, i is 1,2, 3, M1Risk assessment data output for GLM model, M2Risk assessment data, M, output for a decision Tree model3And (4) risk assessment data output by the neural network model.
The driving risk assessment model comprises a calculation formula: p ═ W1×M1+W2×M2+W3×M3(ii) a And P is a driving risk evaluation result which is output by the driving risk evaluation model and can represent the driving risk of the vehicle.
As shown in fig. 10, step S4 further includes:
step S401: for each vehicle to be evaluated, when the quantity of the driving data of the vehicle is less than a first set value, W is added1、W2、W3Is set as W1＜W2＜W3。
Aiming at each vehicle to be evaluated, when the quantity of the driving data of the vehicle to be evaluated, which is acquired and input into each risk evaluation model, is smaller than a first set value, the evaluation accuracy of the neural network model on the driving risk of the vehicle to be evaluated is greater than the evaluation accuracy of the decision tree model on the driving risk of the vehicle to be evaluated, and the evaluation accuracy of the decision tree model on the driving risk of the vehicle to be evaluated is greater than the evaluation accuracy of the GLM model on the driving risk of the vehicle to be evaluated.
When the driving risk of a vehicle to be evaluated is evaluated, the less the quantity of the collected driving data of the vehicle is, the more accurate the neural network model is adopted.
Therefore, for each vehicle to be evaluated, when the number of the driving data of the vehicle is smaller than a first set value, W1＜W2＜W3。
Step S402: for each evaluated vehicle, when the number of the driving data of the vehicle is greater than a first set value and less than a second set value, W is calculated1、W2、W3Is set as W1＜W2＞W3。
And aiming at each vehicle to be evaluated, when the quantity of the driving data of the vehicle to be evaluated, which is collected and input into each risk evaluation model, is greater than a first set value and smaller than a second set value, the evaluation accuracy of the decision tree model on the driving risk of the vehicle is the highest.
Step S403: for each evaluated vehicle, when the number of the driving data of the vehicle is larger than a second set value, W is set1、W2、W3Is set as W1＞W2＞W3。
Aiming at each vehicle to be evaluated, when the quantity of the driving data of the vehicle to be evaluated, which is acquired and input into each risk evaluation model, is smaller than a first set value, the evaluation accuracy of the GLM model on the driving risk of the vehicle to be evaluated is greater than the evaluation accuracy of the decision tree model on the driving risk of the vehicle to be evaluated, and the evaluation accuracy of the decision tree model on the driving risk of the vehicle to be evaluated is greater than the evaluation accuracy of the neural network model on the driving risk of the vehicle to be evaluated.
When the driving risk of a vehicle to be evaluated is evaluated, the more the quantity of the collected driving data of the vehicle is, the more accurate the GLM model is adopted.
Therefore, the GLM model is suitable for carrying out driving risk assessment on the vehicle with a large amount of collected driving data; the decision tree model is suitable for carrying out driving risk assessment on the vehicles with the moderate collected driving data quantity; the neural network model is suitable for carrying out driving risk assessment on the vehicle with less collected driving data;
after the driving risk evaluation model is established, the driving risk of the vehicle can be evaluated by using the driving risk evaluation model. Evaluating the driving risk of the vehicle by using a driving risk evaluation model, comprising the following steps: and inputting the driving data of a vehicle into a driving risk evaluation model, and obtaining a driving risk accuracy evaluation result of the vehicle through the driving risk evaluation model.
After the driving risk accuracy evaluation result of a vehicle is obtained, the driving risk accuracy evaluation result can be utilized to determine the vehicle insurance rate pricing of the vehicle.
According to the driving risk assessment method, the accuracy of each risk assessment model is assessed, the driving risk assessment model is established according to the accuracy assessment result, the accuracy of the driving risk assessment model for assessing the driving risk of the vehicle can be improved, and the pricing of the car insurance rate obtained through the driving risk assessment model is reasonable.
The embodiment of the invention also provides a driving risk assessment device. As shown in fig. 11 to 19, the driving risk assessment apparatus includes:
the acquisition module 210 is configured to acquire driving data of each vehicle in a preset number of vehicles within a first set time period;
an analysis module 220, configured to, for a vehicle in the preset number of vehicles, input the driving data of the vehicle into one or more established risk assessment models, so as to analyze the driving data of the vehicle by using the one or more risk assessment models, and obtain risk assessment data that can represent the driving risk of the vehicle and is output by each risk assessment model;
an evaluation module 230, configured to evaluate, for one of the one or more risk evaluation models, accuracy of the risk evaluation model by using each of the risk evaluation data output by the risk evaluation model, so as to obtain an accuracy evaluation result;
the establishing module 240 is configured to establish a driving risk assessment model for assessing the driving risk of the vehicle according to one or more accuracy assessment results.
In an embodiment of the driving risk assessment apparatus provided in the present invention, the analysis module 220 includes:
the analysis submodule 221 is configured to analyze the driving data of one vehicle of the preset number of vehicles to obtain a plurality of risk factors representing a relationship between the driving data and a driving risk;
and the processing submodule 222 is used for processing each risk factor to obtain risk evaluation data representing the driving risk of the vehicle.
In a driving risk assessment apparatus according to an embodiment of the present invention, the driving data includes: one or more of driver personal data, vehicle data, trip mileage data, travel time data, travel route data;
the analysis sub-module 221 is further configured to analyze one or more of the personal data of the driver, the vehicle data, the mileage data, the trip time data, and the driving route data, and obtain a plurality of risk factors representing a relationship between the driving data and a driving risk.
In an embodiment of the present invention, the driving risk assessment apparatus includes: driving mileage data and time data corresponding to trip mileage;
the analysis submodule 221 is further configured to analyze the driving mileage data and the time data corresponding to the trip mileage to obtain a risk factor representing a relationship between the driving mileage and the driving risk over a period of time.
In an embodiment of the present invention, the driving risk assessment apparatus includes: travel time data and travel speed data corresponding to the travel time data;
the analysis sub-module 221 includes:
a classification unit 2216 for classifying the traveling speeds into different categories according to traveling speed data corresponding to the traveling time data;
an obtaining unit 2217 configured to obtain travel times of the respective speed categories in a travel period, respectively;
a calculating unit 2218, configured to divide the driving time corresponding to each speed category by the driving time period to obtain a plurality of speed factors;
a processing unit 2219, configured to process each of the speed factors to obtain a risk factor indicating a relationship between a traveling speed and the driving risk.
In an embodiment of the present invention, the driving risk assessment apparatus includes: driving mileage data and the number of driving dangerous events within the driving mileage;
the analysis submodule 221 is further configured to process the driving mileage data and the number of occurrences of the driving risk event within the driving mileage, and acquire a risk factor representing the number of occurrences of the driving risk event within the driving mileage.
In an embodiment of the present invention, the driving risk assessment apparatus includes: one or more of a GLM model, a decision tree model, and a neural network model;
the analysis module 220 includes: and aiming at one vehicle in the preset number of vehicles, inputting each piece of driving data of the vehicle into one or more of the GLM model, the decision tree model and the neural network model, and obtaining the risk assessment data which are respectively output by each risk assessment model and represent the driving risk of the vehicle.
In an embodiment of the present invention, the driving risk assessment apparatus includes a calculation formula:
the establishing module 240 is further configured to:
acquiring the driving risk evaluation result;
wherein i is 1,2, 3 …, M is an integer of 1 or more, M is a hydrogen atomiThe risk assessment data output for the risk assessment model; wiIn order to be a weight factor, the weight factor,
and P is a driving risk evaluation result which is output by the driving risk evaluation model and can represent the driving risk of the vehicle.
In the driving risk assessment device according to an embodiment of the present invention, M is 3, i is 1,2, 3, M1The risk assessment data, M, output for the GLM model2The risk assessment data, M, output for the decision tree model3The risk assessment data output for the neural network model;
establishing the step 240 comprises:
a first setting submodule 241 for setting W for each vehicle to be evaluated when the number of the driving data of the vehicle is smaller than a first set value1、W2、W3Is set as W1＜W2＜W3；
A second setting submodule 242 for setting, for each vehicle to be evaluated, W when the number of the driving data of the vehicle is larger than a first set value and smaller than a second set value1、W2、W3Is set as W1＜W2＞W3；
A third setting submodule 243 for setting, for each vehicle to be evaluated, W when the number of the driving data of the vehicle is larger than a second set value1、W2、W3Is set as W1＞W2＞W3。
In the driving risk assessment apparatus according to an embodiment of the present invention, the apparatus further includes:
a generating module 215, configured to generate, for one of the vehicles in the preset number of vehicles, derived driving data of the vehicle using the driving data of the vehicle;
the analysis module 220 is further configured to, for a vehicle of the preset number of vehicles, input the driving data of the vehicle and the derived driving data of the vehicle into one or more established risk assessment models, so as to analyze the driving data and the derived driving data by using the risk assessment models, and obtain risk assessment data that can represent the driving risk of the vehicle and is output by the risk assessment models.
In the driving risk assessment apparatus according to an embodiment of the present invention, the generating module 215 includes:
a first calculating submodule 2151, configured to expand the driving data by using a calculation formula Y-lnX to obtain a derivative risk factor, where Y is derivative driving data and X is driving data;
a second calculation submodel 2152 for using the calculation formula Y ═ eXExpanding the driving data to obtain derivative risk factors, wherein Y is derivative driving data, and X is driving data;
a third calculation submodule 2153 for calculating the formula Y ═ XnExpanding the driving data to obtain derivative risk factors, wherein Y is derivativeDriving data is generated, X is the driving data, and n is an integer greater than zero.
In the driving risk assessment apparatus according to an embodiment of the present invention, the assessment module 230 includes:
a grouping submodule 234 configured to, for one of the one or more risk assessment models, group each of the vehicles in the preset number of vehicles into different groups according to the size of risk assessment data output by the corresponding risk assessment model;
the collecting submodule 235 is used for collecting the total number of times of the risk of each group of vehicles in the risk assessment model within a second set time length;
and the evaluation submodule 236 is configured to evaluate the accuracy of the risk evaluation model by using the risk times of each group in the risk evaluation model, and obtain an accuracy evaluation result of the risk evaluation model.
When the device is used for driving risk assessment, the operation method of each module in the device is the same as the driving risk assessment method, so the using method of each module in the device is also the same as the driving risk assessment method. The use method and the operation method of each module in the driving risk assessment device can refer to the driving risk assessment method, and are not repeated.
An embodiment of the present invention provides a driving risk assessment system, as shown in fig. 1, including: driving risk assessment device 110, network 120, and a plurality of data acquisition devices 130.
The data collecting device 130 includes a driving recorder, a vehicle-mounted camera, a position sensor, and the like, and is configured to collect driving data of each vehicle in a preset number of vehicles, and send the collected driving data to the driving risk assessment device 110 through the network 120.
The driving risk assessment device 110 includes a memory 111, a processor 112, and an access device 113. The memory 111, processor 112 and access device 113 are connected by a bus 114.
Processor 112 includes one or more Integrated circuits that may include a Central Processing Unit (CPU), or an Application Specific Integrated Circuit (ASIC), or may be configured to implement an embodiment of the present invention.
Memory 111 may include mass storage for data or instructions. By way of example, and not limitation, memory 111 may include a Hard Disk Drive (HDD), a floppy Disk Drive, flash memory, an optical Disk, a magneto-optical Disk, tape, or a Universal Serial Bus (USB) Drive or a combination of two or more of these. Memory 111 may include removable or non-removable (or fixed) media, where appropriate. The memory 111 may be internal or external to the data processing apparatus, where appropriate. In a particular embodiment, the memory 111 is a non-volatile solid-state memory. In a particular embodiment, the memory 111 includes Read Only Memory (ROM). Where appropriate, the ROM may be mask-programmed ROM, Programmable ROM (PROM), Erasable PROM (EPROM), Electrically Erasable PROM (EEPROM), electrically rewritable ROM (EAROM), or flash memory or a combination of two or more of these.
The access device 113 is mainly used for implementing communication between modules, apparatuses, units and/or devices in the embodiments of the present invention.
Bus 114 includes hardware, software, or both that couple the components of the driving risk assessment device to each other. By way of example, and not limitation, the bus 114 may include an Accelerated Graphics Port (AGP) or other graphics bus, an Enhanced Industry Standard Architecture (EISA) bus, a Front Side Bus (FSB), a Hyper Transport (HT) interconnect, an Industry Standard Architecture (ISA) bus, an infiniband interconnect, a Low Pin Count (LPC) bus, a memory bus, a Micro Channel Architecture (MCA) bus, a Peripheral Component Interconnect (PCI) bus, a PCI-Express (PCI-X) bus, a Serial Advanced Technology Attachment (SATA) bus, a video electronics standards association local (VLB) bus, or other suitable bus, or a combination of two or more of these. Bus 114 may include one or more buses, where appropriate. Although specific buses have been described and shown in the embodiments of the invention, any suitable buses or interconnects are contemplated by the invention.
The processor 112 may implement any of the driving risk assessment methods in the above embodiments by reading and executing computer program instructions stored in the memory 111.
In addition, in combination with the driving risk assessment method in the above embodiments, the embodiments of the present invention may be implemented by providing a computer-readable storage medium. The computer readable storage medium having stored thereon computer program instructions; the computer program instructions, when executed by a processor, implement any of the driving risk assessment methods of the above embodiments.
In summary, the driving risk assessment method, the driving risk assessment device, the driving risk assessment equipment and the storage medium provided by the embodiment of the invention have the characteristic of high accuracy in vehicle driving risk assessment.
It is to be understood that the invention is not limited to the specific arrangements and instrumentality described above and shown in the drawings. A detailed description of known methods is omitted herein for the sake of brevity. In the above embodiments, several specific steps are described and shown as examples. However, the method processes of the present invention are not limited to the specific steps described and illustrated, and those skilled in the art can make various changes, modifications and additions or change the order between the steps after comprehending the spirit of the present invention.
The functional blocks shown in the above-described structural block diagrams may be implemented as hardware, software, firmware, or a combination thereof. When implemented in hardware, it may be, for example, an electronic circuit, an Application Specific Integrated Circuit (ASIC), suitable firmware, plug-in, function card, or the like. When implemented in software, the elements of the invention are the programs or code segments used to perform the required tasks. The program or code segments may be stored in a machine-readable medium or transmitted by a data signal carried in a carrier wave over a transmission medium or a communication link. A "machine-readable medium" may include any medium that can store or transfer information. Examples of a machine-readable medium include electronic circuits, semiconductor memory devices, ROM, flash memory, Erasable ROM (EROM), floppy disks, CD-ROMs, optical disks, hard disks, fiber optic media, Radio Frequency (RF) links, and so forth. The code segments may be downloaded via computer networks such as the internet, intranet, etc.
It should also be noted that the exemplary embodiments mentioned in this patent describe some methods or systems based on a series of steps or devices. However, the present invention is not limited to the order of the above-described steps, that is, the steps may be performed in the order mentioned in the embodiments, may be performed in an order different from the order in the embodiments, or may be performed simultaneously.
As described above, only the specific embodiments of the present invention are provided, and it can be clearly understood by those skilled in the art that, for convenience and brevity of description, the specific working processes of the system, the module and the unit described above may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again. It should be understood that the scope of the present invention is not limited thereto, and any person skilled in the art can easily conceive various equivalent modifications or substitutions within the technical scope of the present invention, and these modifications or substitutions should be covered within the scope of the present invention.
Claims (13)
1. A driving risk assessment method, characterized in that the method comprises:
step S1: the method comprises the steps of collecting driving data of each vehicle in a preset number of vehicles within a first set time length;
step S2: for a vehicle in the preset number of vehicles, inputting the driving data of the vehicle into one or more established risk assessment models, so that the driving data of the vehicle is analyzed by using the one or more risk assessment models respectively, and risk assessment data which are output by each risk assessment model and can represent the driving risk of the vehicle is obtained;
step S3: aiming at one risk evaluation model in the one or more risk evaluation models, evaluating the accuracy of the risk evaluation model by utilizing each risk evaluation data output by the risk evaluation model to obtain an accuracy evaluation result;
step S4: and establishing a driving risk evaluation model for evaluating the driving risk of the vehicle according to one or more accuracy evaluation results.
2. The driving risk assessment method according to claim 1, wherein step S2 includes:
step S201: analyzing the driving data of one vehicle in the preset number of vehicles to obtain a plurality of risk factors representing the relation between the driving data and the driving risk;
step S202: and processing each risk factor to obtain risk evaluation data representing the driving risk of the vehicle.
3. The driving risk assessment method according to claim 2, wherein when the driving data includes one or more of driver personal data, vehicle data, mileage data, travel time data, travel route data, the step S201 includes: analyzing one or more of the personal data of the driver, the vehicle data, the mileage data, the travel time data and the travel route data to obtain a plurality of risk factors representing the relation between the driving data and the driving risk;
when the driving risk data includes mileage data and time data corresponding to mileage, the step S201 includes: analyzing the travel mileage data and the time data corresponding to the trip mileage to obtain a risk factor representing the relationship between the travel mileage and the driving risk within a period of time;
when the driving risk data includes the driving distance data and the number of driving risk events occurring within the driving distance, the step S201 includes: and processing the driving mileage data and the occurrence frequency of the driving dangerous events in the driving mileage to obtain a risk factor representing the occurrence frequency of the driving dangerous events in the driving mileage.
4. The driving risk assessment method according to claim 2, wherein the driving risk data comprises: travel time data and travel speed data corresponding to the travel time data;
step S201 includes:
step S2016: dividing the travel speed into different categories according to travel speed data corresponding to the travel time data;
step S2017: respectively acquiring the running time of each speed category in a running time period;
step S2018: dividing the running time corresponding to each speed category by the running time period to obtain a plurality of speed factors;
step S2019: and processing each speed factor to obtain a risk factor representing the relation between the running speed and the driving risk.
5. The driving risk assessment method according to claim 1, wherein the risk assessment model comprises: one or more of a GLM model, a decision tree model, and a neural network model;
step S2 includes: and aiming at one vehicle in the preset number of vehicles, inputting each piece of driving data of the vehicle into one or more of the GLM model, the decision tree model and the neural network model, and obtaining the risk assessment data which are respectively output by each risk assessment model and represent the driving risk of the vehicle.
6. The driving risk assessment method according to any one of claims 1 to 5, wherein the driving risk assessment model includes a calculation formula:
step S4 includes: by the calculation formula:
obtaining the driving risk accuracy evaluation result;
wherein i is 1,2, 3 …, M is an integer of 1 or more, M is a hydrogen atomiOutput for the risk assessment modelSaid risk assessment data; wiIn order to be a weight factor, the weight factor,
and P is a driving risk evaluation result which is output by the driving risk evaluation model and can represent the driving risk of the vehicle.
7. The driving risk assessment method according to claim 6, wherein M is 3, and i is 1,2, 3, M1The risk assessment data, M, output for the GLM model2The risk assessment data, M, output for the decision tree model3The risk assessment data output for the neural network model;
step S4 further includes:
step S401: for each vehicle to be evaluated, when the quantity of the driving data of the vehicle is less than a first set value, W is added1、W2、W3Is set as W1＜W2＜W3。
8. The driving risk assessment method according to claim 1, wherein step S2 is preceded by:
step S11: generating, for one of the preset number of vehicles, derived driving data of the vehicle using the driving data of the vehicle;
step S2 further includes: and for one vehicle in the preset number of vehicles, inputting the driving data of the vehicle and the derivative driving data of the vehicle into one or more established risk assessment models, analyzing the driving data and the derivative driving data by using the one or more risk assessment models, and acquiring risk assessment data which can represent the driving risk of the vehicle and is output by each risk assessment model.
9. The driving risk assessment method according to claim 8, wherein step S11 further comprises:
step S111: and expanding the driving data of one vehicle in the preset number of vehicles by using a calculation formula Y-lnX to obtain derivative driving data of the vehicle, wherein Y is the derivative driving data, and X is the driving data.
10. The driving risk assessment method according to claim 1, wherein step S3 includes:
step S301: for one risk assessment model of the one or more risk assessment models, dividing each vehicle of the preset number of vehicles into different groups according to the size of risk assessment data output by the corresponding risk assessment model;
step S302: collecting the total times of the vehicle groups in the risk assessment model within a second set time length;
step S303: and evaluating the accuracy of the risk evaluation model by using the risk times of each group in the risk evaluation model to obtain an accuracy evaluation result of the risk evaluation model.
11. A driving risk assessment apparatus, characterized in that the apparatus comprises:
the system comprises an acquisition module, a storage module and a control module, wherein the acquisition module is used for acquiring driving data of each vehicle in a preset number of vehicles within a first set time length;
the analysis module is used for inputting the driving data of one vehicle in the preset number of vehicles into one or more established risk assessment models, so that the driving data of the vehicle are analyzed by using the one or more risk assessment models respectively, and the risk assessment data which are output by the risk assessment models and can represent the driving risk of the vehicle are obtained;
the evaluation module is used for evaluating the accuracy of the risk evaluation model by utilizing each risk evaluation data output by the risk evaluation model aiming at one risk evaluation model in the one or more risk evaluation models to obtain an accuracy evaluation result;
and the establishing module is used for establishing a driving risk evaluation model for evaluating the driving risk of the vehicle according to one or more accuracy evaluation results.
12. A driving risk assessment apparatus, characterized by comprising: at least one processor, at least one memory, and computer program instructions stored in the memory, which when executed by the processor, implement the method of any of claims 1-10.
13. A storage medium having stored thereon computer program instructions, which when executed by a processor, implement the method of any one of claims 1-10.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911233101.2A CN110968839B (en) | 2019-12-05 | 2019-12-05 | Driving risk assessment method, device, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911233101.2A CN110968839B (en) | 2019-12-05 | 2019-12-05 | Driving risk assessment method, device, equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110968839A true CN110968839A (en) | 2020-04-07 |
| CN110968839B CN110968839B (en) | 2024-07-05 |
Family
ID=70032990
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911233101.2A Active CN110968839B (en) | 2019-12-05 | 2019-12-05 | Driving risk assessment method, device, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110968839B (en) |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111652498A (en) * | 2020-05-29 | 2020-09-11 | 李欣蕊 | Automobile driving risk scoring system and method |
| CN111951550A (en) * | 2020-08-06 | 2020-11-17 | 华南理工大学 | Traffic safety risk monitoring method, device, storage medium and computer equipment |
| CN112232621A (en) * | 2020-08-31 | 2021-01-15 | 南斗六星系统集成有限公司 | Driving behavior scoring method and device based on exponential probability distribution hybrid model |
| CN112597835A (en) * | 2020-12-11 | 2021-04-02 | 国汽(北京)智能网联汽车研究院有限公司 | Driving behavior evaluation method and device, electronic equipment and readable storage medium |
| CN113554370A (en) * | 2020-04-23 | 2021-10-26 | 中国石油化工股份有限公司 | Safety risk assessment method and device for hazardous chemical substance transport vehicle |
| CN113554248A (en) * | 2020-04-23 | 2021-10-26 | 中国石油化工股份有限公司 | Risk dynamic early warning assessment method and device for hazardous chemical substance transport vehicle |
| CN114092267A (en) * | 2022-01-18 | 2022-02-25 | 成都车晓科技有限公司 | High-risk vehicle insurance customer car insurance evaluation method and system based on machine learning |
| CN114898340A (en) * | 2022-06-14 | 2022-08-12 | 北京宏瓴科技发展有限公司 | Method and system for evaluating driving behavior risk based on positioning data |
| CN116109145A (en) * | 2023-04-10 | 2023-05-12 | 天津所托瑞安汽车科技有限公司 | Risk assessment method, device, terminal and storage medium for vehicle driving route |
| CN119067450A (en) * | 2024-09-03 | 2024-12-03 | 东风汽车集团股份有限公司 | Functional safety controllability analysis method and related equipment |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105892471A (en) * | 2016-07-01 | 2016-08-24 | 北京智行者科技有限公司 | Automatic automobile driving method and device |
| CN106651162A (en) * | 2016-12-09 | 2017-05-10 | 思建科技有限公司 | Big data-based driving risk assessment method |
| CN107292528A (en) * | 2017-06-30 | 2017-10-24 | 阿里巴巴集团控股有限公司 | Vehicle insurance Risk Forecast Method, device and server |
| CN108446824A (en) * | 2018-02-08 | 2018-08-24 | 深圳市赛格导航科技股份有限公司 | A kind of methods of risk assessment of driving behavior, device, equipment and storage medium |
-
2019
- 2019-12-05 CN CN201911233101.2A patent/CN110968839B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105892471A (en) * | 2016-07-01 | 2016-08-24 | 北京智行者科技有限公司 | Automatic automobile driving method and device |
| CN106651162A (en) * | 2016-12-09 | 2017-05-10 | 思建科技有限公司 | Big data-based driving risk assessment method |
| CN107292528A (en) * | 2017-06-30 | 2017-10-24 | 阿里巴巴集团控股有限公司 | Vehicle insurance Risk Forecast Method, device and server |
| CN108446824A (en) * | 2018-02-08 | 2018-08-24 | 深圳市赛格导航科技股份有限公司 | A kind of methods of risk assessment of driving behavior, device, equipment and storage medium |
Non-Patent Citations (2)
| Title |
|---|
| 孟生旺等: "驾驶行为保险的风险预测模型研究", 《保险研究》 * |
| 孟生旺等: "驾驶行为保险的风险预测模型研究", 《保险研究》, no. 8, 31 December 2018 (2018-12-31), pages 21 - 34 * |
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113554370A (en) * | 2020-04-23 | 2021-10-26 | 中国石油化工股份有限公司 | Safety risk assessment method and device for hazardous chemical substance transport vehicle |
| CN113554248A (en) * | 2020-04-23 | 2021-10-26 | 中国石油化工股份有限公司 | Risk dynamic early warning assessment method and device for hazardous chemical substance transport vehicle |
| CN111652498A (en) * | 2020-05-29 | 2020-09-11 | 李欣蕊 | Automobile driving risk scoring system and method |
| CN111951550A (en) * | 2020-08-06 | 2020-11-17 | 华南理工大学 | Traffic safety risk monitoring method, device, storage medium and computer equipment |
| CN111951550B (en) * | 2020-08-06 | 2021-10-29 | 华南理工大学 | Traffic safety risk monitoring method, device, storage medium and computer equipment |
| CN112232621B (en) * | 2020-08-31 | 2023-07-04 | 南斗六星系统集成有限公司 | Driving Behavior Scoring Method and Device Based on Exponential Probability Distribution Mixed Model |
| CN112232621A (en) * | 2020-08-31 | 2021-01-15 | 南斗六星系统集成有限公司 | Driving behavior scoring method and device based on exponential probability distribution hybrid model |
| CN112597835A (en) * | 2020-12-11 | 2021-04-02 | 国汽(北京)智能网联汽车研究院有限公司 | Driving behavior evaluation method and device, electronic equipment and readable storage medium |
| CN114092267A (en) * | 2022-01-18 | 2022-02-25 | 成都车晓科技有限公司 | High-risk vehicle insurance customer car insurance evaluation method and system based on machine learning |
| CN114898340A (en) * | 2022-06-14 | 2022-08-12 | 北京宏瓴科技发展有限公司 | Method and system for evaluating driving behavior risk based on positioning data |
| CN116109145A (en) * | 2023-04-10 | 2023-05-12 | 天津所托瑞安汽车科技有限公司 | Risk assessment method, device, terminal and storage medium for vehicle driving route |
| CN116109145B (en) * | 2023-04-10 | 2023-06-20 | 天津所托瑞安汽车科技有限公司 | Risk assessment method, device, terminal and storage medium for vehicle driving route |
| CN119067450A (en) * | 2024-09-03 | 2024-12-03 | 东风汽车集团股份有限公司 | Functional safety controllability analysis method and related equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110968839B (en) | 2024-07-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110968839B (en) | Driving risk assessment method, device, equipment and storage medium | |
| Carfora et al. | A “pay-how-you-drive” car insurance approach through cluster analysis: MF Carfora et al. | |
| CN110091751B (en) | Electric automobile endurance mileage prediction method, device and medium based on deep learning | |
| KR101617349B1 (en) | Diagnostic system and method for the analysis of driving behavior | |
| CN115565373B (en) | Expressway tunnel accident real-time risk prediction method, device, equipment and medium | |
| WO2020107894A1 (en) | Driving behavior scoring method and device and computer-readable storage medium | |
| Castignani et al. | An evaluation study of driver profiling fuzzy algorithms using smartphones | |
| CN111452799B (en) | Driving behavior evaluation method and system | |
| CN108556682B (en) | Driving range prediction method, device and equipment | |
| CN114897312B (en) | Driving behavior scoring method, device, equipment and storage medium | |
| CN114329921A (en) | Method, device, equipment and medium for evaluating reliability performance of whole vehicle | |
| CN117932921A (en) | Evaluation method of intelligent driving simulation system, electronic equipment and storage medium | |
| CN119116971A (en) | Driving intention recognition method, device, equipment and storage medium | |
| CN101957941A (en) | The method of discerning the problem of showing especially based on the fusion conspicuousness and the susceptibility of time trend | |
| CN115841712B (en) | Driving data processing method, device and equipment based on V2X technology | |
| CN112348039B (en) | Training method of driving behavior analysis model, driving behavior analysis method and equipment | |
| CN115510990A (en) | Model training method and related device | |
| CN113486748A (en) | Method for predicting friction coefficient of automatic driving road surface, electronic device and medium | |
| CN115345261B (en) | Vehicle track authenticity checking method and device and electronic equipment | |
| CN116503081A (en) | Method, device, equipment and storage medium for evaluating value of second-hand vehicle | |
| CN112597835B (en) | Driving behavior evaluation method and device, electronic equipment and readable storage medium | |
| CN115170304A (en) | Method and device for extracting risk feature description | |
| CN106067038A (en) | Establishment of remote damage assessment system and method based on artificial intelligence supervised learning naive Bayesian method | |
| CN119128539B (en) | Similar vehicle model-based risk model construction method, device, equipment and medium | |
| CN118313845B (en) | Development method, device, medium and equipment for random actual road working conditions |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |