CN109033332B - Driving behavior analysis method, medium and system - Google Patents
Driving behavior analysis method, medium and system Download PDFInfo
- Publication number
- CN109033332B CN109033332B CN201810801891.9A CN201810801891A CN109033332B CN 109033332 B CN109033332 B CN 109033332B CN 201810801891 A CN201810801891 A CN 201810801891A CN 109033332 B CN109033332 B CN 109033332B
- Authority
- CN
- China
- Prior art keywords
- driving behavior
- driving
- driver
- characteristic
- clustering
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W40/00—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models
- B60W40/08—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models related to drivers or passengers
- B60W40/09—Driving style or behaviour
Abstract
The invention discloses a driving behavior analysis method, which comprises the following steps: acquiring driving data of a driver; extracting the characteristics to obtain a driving behavior characteristic matrix in combination with the driving process of the vehicle; screening to obtain final characteristics; measuring feature similarity according to the final features, establishing connecting edges, and respectively clustering the driver groups by adopting a clustering algorithm based on the connecting edges to obtain a clustering result; obtaining a clustering result with high accuracy; the driving behavior characteristics of each driving of the driver are classified into driving behavior dimensions according to the clustering result with high accuracy, and a radar map is adopted to perform user portrayal on the driving preference of the driver so as to obtain single-dimensional degree scores and multi-dimensional comprehensive scores; analyzing factors influencing the driving behavior of the driver according to the single-dimensional score and the multi-dimensional comprehensive score; the invention also discloses a medium and a system, which can realize the multidimensional comprehensive evaluation of the driving behavior of each driver and serve as the basis for correcting the bad driving habits of the drivers.
Description
Technical Field
The invention relates to the technical field of data processing, in particular to a driving behavior analysis method, medium and system.
Background
In urban traffic environments, poor driving behavior of the vehicle driver (e.g., rapid acceleration, rapid braking, and driving), severely affects the safety of the urban traffic environment and ride comfort of the passengers.
In the actual process of riding or driving the vehicle, people often intuitively know the bad driving behavior of the driver through a single dimension, for example, intuitively know the bad habit of the driver through physical perception in the process of sudden braking of the driver, or intuitively know the bad habit of the driver through the sudden acceleration behavior of the vehicle and the vehicle speed value in the process of driving the vehicle. These methods are difficult to comprehensively reflect the driving habits of the drivers, and cannot comprehensively evaluate the driving behaviors of each driver in a multi-dimensional manner, so that the driving behaviors can be used as a basis for correcting the bad driving habits of the drivers, and the safety of the urban traffic environment and the riding comfort of passengers can be guaranteed.
Disclosure of Invention
The present invention is directed to solving, at least to some extent, one of the technical problems in the art described above. Therefore, an object of the present invention is to provide a driving behavior analysis method, which can implement multidimensional comprehensive evaluation of driving behavior of each driver, so as to be used as a basis for correcting bad driving habits of the driver, thereby ensuring safety of urban traffic environment and riding comfort of passengers.
A second object of the invention is to propose a computer-readable storage medium.
A third object of the present invention is to provide a driving behavior analysis system.
A fourth object of the present invention is to provide a driving behavior analysis system.
In order to achieve the above object, an embodiment of a first aspect of the present invention provides a driving behavior analysis method, including the following steps: acquiring driving data of a driver; combining the driving process of the vehicle, and performing feature extraction on the driving data of the driver to obtain a driving behavior feature matrix; screening the driving behavior characteristic matrix to obtain a final characteristic; measuring the driving behavior characteristic similarity of each driving of the driver according to the final characteristic, establishing connecting edges according to the driving behavior characteristic similarity, and respectively clustering the driver groups by adopting a Fast Unfolding clustering algorithm and a K-means clustering algorithm based on the connecting edges to obtain a first clustering result and a second clustering result; acquiring a clustering result with high accuracy in the first clustering result and the second clustering result; the driving behavior characteristics of each driving of the driver are classified into driving behavior dimensions according to the clustering result with high accuracy, and the driving preference of the driver is subjected to user portrayal from different driving behavior dimensions by adopting a radar map so as to obtain single-dimensional scores of the driver on each driving behavior dimension and multi-dimensional comprehensive scores on different driving behavior dimensions; and analyzing factors influencing the driving behavior of the driver according to the single-dimensional score and the multi-dimensional comprehensive score.
According to the driving behavior analysis method provided by the embodiment of the invention, firstly, driving data of a driver is obtained; the driving data of the driver is subjected to feature extraction to obtain a driving behavior feature matrix in combination with the driving process of the vehicle; then, screening the driving behavior characteristic matrix to obtain a final characteristic; measuring the driving behavior characteristic similarity of each driving of the driver according to the final characteristic, establishing connecting edges according to the driving behavior characteristic similarity, and then respectively adopting Fast Unfolding clustering algorithm and K-means clustering algorithm to cluster the driver groups based on the connecting edges to obtain a first clustering result and a second clustering result; then, obtaining a clustering result with high accuracy in the first clustering result and the second clustering result; the driving behavior characteristics of each driving of the driver are classified into driving behavior dimensions according to the clustering result with high accuracy, and the driving preference of the driver is subjected to user portrayal from different driving behavior dimensions by adopting a radar map so as to obtain single-dimensional scores of the driver on each driving behavior dimension and multi-dimensional comprehensive scores on different driving behavior dimensions; then, analyzing factors influencing the driving behavior of the driver according to the single-dimensional score and the multi-dimensional comprehensive score; therefore, the driving behavior of the driver can be comprehensively evaluated in multiple dimensions, and the driving behavior can be used as a basis for correcting bad driving habits of the driver, so that the safety of the urban traffic environment and the riding comfort of passengers can be further guaranteed.
In addition, the driving behavior analysis method proposed according to the above embodiment of the present invention may further have the following additional technical features:
optionally, the driving data of the driver is acquired through a CAN bus vehicle-mounted instrument, wherein the driving data of the driver comprises information based on a driver ID, a recording date and time, a position, a speed, an uplink and a downlink of the vehicle, a motor and engine speed, a gear, electronic brake information, hand brake information, an accelerator pedal percentage, an ignition signal, brake pedal opening information and a switch state.
Optionally, screening the driving behavior feature matrix to obtain a final feature includes: acquiring a behavior feature probability distribution map based on the driving behavior feature matrix to analyze the driving behavior feature distribution condition, and deleting driving behavior features which are not obviously distinguished in the driving behavior feature matrix according to the driving behavior feature distribution condition to perform preliminary screening; sorting the driving behavior characteristics after the primary screening by adopting a maximum correlation minimum redundancy characteristic selection method based on mutual information, and performing secondary screening on the driving behavior characteristics after the primary screening according to a sorting result; performing empowerment on the driving behavior characteristics after the secondary screening; and generating a characteristic box chart according to the weighted weight of each driving behavior characteristic, and removing abnormal behavior characteristics according to the characteristic box chart to obtain the final characteristics.
Optionally, when driver group clustering is performed by adopting Fast Unfolding clustering algorithm, points and communities with improved modularity in the network are merged according to the modularity algorithm until the modularity in the network cannot be improved.
To achieve the above object, a second embodiment of the present invention provides a computer-readable storage medium, on which a driving behavior analysis program is stored, which, when executed by a processor, implements the driving behavior analysis method as described above.
In order to achieve the above object, a driving behavior analysis system according to a third aspect of the present invention includes a memory, a processor, and a driving behavior analysis program stored in the memory and executable on the processor, wherein the processor implements the driving behavior analysis method as described above when executing the driving behavior analysis program.
In order to achieve the above object, a fourth aspect of the present invention provides a driving behavior analysis system, including a data obtaining module, configured to obtain driving data of a driver; the characteristic extraction module is used for extracting the characteristics of the driving data of the driver in combination with the driving process of the vehicle to obtain a driving behavior characteristic matrix; the characteristic screening module is used for screening the driving behavior characteristic matrix to obtain final characteristics; the clustering module is used for measuring the driving behavior feature similarity of each driving of the driver according to the final feature, establishing connecting edges according to the driving behavior feature similarity, respectively adopting Fast Unfolding clustering algorithm and K-means clustering algorithm to cluster the driver groups based on the connecting edges so as to obtain a first clustering result and a second clustering result, and obtaining a high-accuracy clustering result in the first clustering result and the second clustering result; the portrait generation module is used for attributing the driving behavior characteristics of each driving of the driver to the driving behavior dimensions according to the clustering result with high accuracy, and performing user portrait on the driving preference of the driver from different driving behavior dimensions by adopting a radar map so as to obtain single-dimensional scores of the driver on each driving behavior dimension and multi-dimensional comprehensive scores on different driving behavior dimensions; and the driving behavior analysis module is used for analyzing factors influencing the driving behavior of the driver according to the single-dimensional score and the multi-dimensional comprehensive score.
According to the driving behavior analysis system provided by the embodiment of the invention, firstly, a data acquisition module acquires driving data of a driver; then, the characteristic extraction module is combined with the vehicle running process to extract the characteristics of the driving data of the driver so as to obtain a driving behavior characteristic matrix; then, the characteristic screening module screens the driving behavior characteristic matrix to obtain final characteristics; secondly, measuring the driving behavior feature similarity of each driving of the driver according to the final feature by the clustering module, establishing connecting edges according to the driving behavior feature similarity, respectively clustering the driver groups by adopting Fast Unfolding clustering algorithm and K-means clustering algorithm based on the connecting edges to obtain a first clustering result and a second clustering result, and obtaining a clustering result with high accuracy in the first clustering result and the second clustering result; then, the portrait generation module enables driving behavior characteristics of each driving of the driver to be classified into driving behavior dimensions according to the clustering result with high accuracy, and adopts a radar map to conduct user portrait on driving preference of the driver from different driving behavior dimensions so as to obtain single-dimensional scores of the driver on each driving behavior dimension and multi-dimensional comprehensive scores on different driving behavior dimensions; then, the driving behavior analysis module analyzes factors influencing the driving behavior of the driver according to the single-dimensional score and the multi-dimensional comprehensive score; therefore, the driving behavior of the driver can be comprehensively evaluated in multiple dimensions, and the driving behavior can be used as a basis for correcting bad driving habits of the driver, so that the safety of the urban traffic environment and the riding comfort of passengers can be further guaranteed.
In addition, the driving behavior analysis system proposed according to the above embodiment of the present invention may further have the following additional technical features:
optionally, the data acquisition module acquires driving data of the driver through a CAN bus vehicle-mounted instrument, wherein the driving data of the driver includes information based on a driver ID, a recording date and time, a position, a speed, an up-down movement, a motor and engine rotation speed, a gear, electronic brake information, hand brake information, an accelerator pedal percentage, an ignition signal, brake pedal opening information and switch state information.
Optionally, the feature screening module comprises: the preliminary screening unit is used for acquiring a behavior feature probability distribution map based on the driving behavior feature matrix so as to analyze the driving behavior feature distribution condition, and deleting driving behavior features which are not obviously distinguished in the driving behavior feature matrix according to the driving behavior feature distribution condition so as to perform preliminary screening; the secondary screening unit is used for sorting the driving behavior characteristics after the primary screening by adopting a maximum correlation minimum redundancy characteristic selection method based on mutual information and carrying out secondary screening on the driving behavior characteristics after the primary screening according to a sorting result; the weighting unit is used for weighting the driving behavior characteristics after the secondary screening; and the abnormality removing unit is used for generating a characteristic box chart according to the weighted weight of each driving behavior characteristic and removing the abnormal behavior characteristic according to the characteristic box chart to obtain the final characteristic.
Optionally, when the clustering module performs driver group clustering by using Fast Unfolding clustering algorithm, points and communities with improved modularity in the network are merged according to the modularity algorithm until the modularity in the network cannot be improved.
Drawings
FIG. 1 is a schematic flow chart of a driving behavior analysis method according to an embodiment of the present invention;
FIG. 2 is a schematic flow chart illustrating a process of screening a driving behavior feature matrix to obtain a final feature according to another embodiment of the present invention;
FIG. 3 is a block schematic diagram of a driving behavior analysis system according to an embodiment of the present invention;
FIG. 4 is a block diagram of a feature screening module according to another embodiment of the present invention.
Detailed Description
Reference will now be made in detail to embodiments of the present invention, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to the same or similar elements or elements having the same or similar function throughout. The embodiments described below with reference to the drawings are illustrative and intended to be illustrative of the invention and are not to be construed as limiting the invention.
In the actual process of taking a vehicle or driving the vehicle, people mostly intuitively know the modes of bad driving behaviors of drivers through a single dimension, and the modes are difficult to comprehensively reflect the driving habits of the drivers and cannot comprehensively evaluate the driving behaviors of each driver in a multi-dimension mode; the driving behavior analysis method provided by the embodiment of the invention comprises the steps of firstly obtaining driving data of a driver, extracting characteristics by combining the driving process of a vehicle to generate a driving behavior characteristic matrix, and screening the driving behavior characteristic matrix to obtain final characteristics; secondly, measuring the driving behavior characteristic similarity of each driving of the driver according to the final characteristic, connecting according to the similarity, and clustering based on a clustering algorithm to generate a clustering result; then, establishing a multi-dimensional user portrait according to the clustering result so as to obtain comprehensive evaluation of the driver in multiple dimensions; therefore, the driving behavior of the driver can be comprehensively evaluated in multiple dimensions, and the driving behavior can be used as a basis for correcting bad driving habits of the driver, so that the safety of the urban traffic environment and the riding comfort of passengers can be further guaranteed.
In order to better understand the above technical solutions, exemplary embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the invention are shown in the drawings, it should be understood that the invention can be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the invention to those skilled in the art.
In order to better understand the technical solution, the technical solution will be described in detail with reference to the drawings and the specific embodiments.
Fig. 1 is a schematic flow chart of a driving behavior analysis method according to an embodiment of the present invention, and as shown in fig. 1, the driving behavior analysis method includes the following steps:
and S101, acquiring driving data of the driver.
The method for acquiring the driving data of the driver includes various methods, for example, acquiring the driving data of the driver through an on-board terminal mounted on the vehicle; or acquiring driving data of a driver through a driving recorder; or the driving data of the driver is acquired through the mobile terminal of the driver.
As an example, the driving data of the driver CAN be acquired through a CAN bus vehicle instrument.
The driving data of the driver includes, but is not limited to, driver ID, recording date and time, position, speed, up and down, motor and engine speed, gear, electronic brake information, hand brake information, accelerator pedal percentage, ignition signal, brake pedal opening information, and switch state information.
It should be noted that after the driving data of the driver is acquired through the CAN bus vehicle-mounted instrument, the acquired driving data of the driver CAN be collated, and a CSV document corresponding to the driver and a CSV document corresponding to the vehicle are generated, so that the driving behavior characteristics of the driver CAN be extracted subsequently.
And S102, combining the driving process of the vehicle, and performing characteristic extraction on the driving data of the driver to obtain a driving behavior characteristic matrix.
That is, the driving data of the driver is subjected to feature extraction to obtain the driving behavior feature matrix in combination with the specific driving process of the vehicle (for example, the specific driving process of a starting-point vehicle to an end-point vehicle in the process of driving on a bus route, or the specific driving process of a taxi in a specified route, etc.).
It should be noted that, before generating the driving behavior feature matrix, preprocessing of the extracted features may be further included; specifically, the hot deck algorithm can be used for carrying out near completion on the missing data and the logically wrong data; the data with the logic errors can be checked through logic error detection, and the data with the logic errors refers to data obviously not conforming to the logic due to equipment recording errors or other reasons; for example, the driving speed of an urban congested road section reaches 150km/h due to the fact that longitude and latitude records are wrong; or the rotating speed of the motor reaches 16000r/min and the like; then, when the logically wrong data is found in the logical error detection process, replacing the logically wrong data by using a null value, and performing near completion by using a hot deck algorithm to finish the preprocessing of the extracted features; therefore, the feature matrix generated by the preprocessed features is more accurate and has more referential property.
S103, screening the driving behavior characteristic matrix to obtain final characteristics.
That is, after the driving behavior feature matrix is obtained, the features in the feature matrix are filtered to obtain the final features for cluster analysis.
S104, measuring the driving behavior feature similarity of each driving of the driver according to the final feature, establishing connecting edges according to the driving behavior feature similarity, and clustering the driver groups by adopting a Fast Unfolding clustering algorithm and a K-means clustering algorithm respectively based on the connecting edges to obtain a first clustering result and a second clustering result.
Measuring the driving behavior feature similarity of the driver in each driving according to the final features refers to comprehensively evaluating the similarity degree between the driving behavior features of the drivers in each driving according to the final features; the measuring mode can be various, for example, the matching coefficient between the driving behavior characteristics of each driving is measured; or measuring the consistency between the driving behavior characteristics of each driving, and the like.
As an example, when a continuous edge is established according to driving behavior feature similarity and driver group clustering is performed by adopting Fast Unfolding clustering algorithm based on the continuous edge, points and communities with improved modularity in the network are merged according to the modularity algorithm until the modularity in the network cannot be improved.
That is, each driving behavior feature is taken as an independent community, then adjacent communities are merged, whether the modularity of a network formed by all the communities is improved or not is judged after merging, and if the judgment result is yes, the communities are merged; if the judgment result is negative, the combination of the communities is cancelled; in this manner, each community is iteratively merged until the modularity of the network of all communities is no longer improved.
It should be noted that the finally formed network whose modularity cannot be improved is the first clustering result obtained by clustering the driver groups by using Fast Unfolding clustering algorithm.
The K-means clustering algorithm is a typical clustering algorithm based on distance, and the distance is used as an evaluation index of similarity, that is, the closer the distance between two objects is, the greater the similarity of the two objects is.
And S105, obtaining the clustering result with high accuracy in the first clustering result and the second clustering result.
That is to say, after the first clustering result and the second clustering result are obtained, the accuracy in the first clustering result and the accuracy in the second clustering result are compared, and the clustering result with high accuracy is selected.
For example, the classification of each driving behavior feature is determined according to a plurality of driving behavior features and the clustering result, and whether the classification is accurate is determined according to the classification result to determine the accuracy of the clustering result.
As an example, the driving behavior characteristics of each driving are taken as classification objects, multiple driving behavior characteristics of the same driver in the same travel are extracted, an average classification accuracy index is preset according to the multiple driving behavior characteristics, and classification of each driving behavior characteristic is judged according to each driving behavior characteristic and a clustering result; then, judging whether the classification of the driving behavior characteristics at each time is consistent with a preset average classification accuracy index, and if the judgment result is consistent, determining that the classification result is accurate; and then, determining the accuracy of the clustering result according to the classification result of the driving behavior characteristics each time.
And S106, the driving behavior characteristics of each driving of the driver are classified into driving behavior dimensions according to the clustering result with high accuracy, and the driving preference of the driver is subjected to user portrayal from different driving behavior dimensions by adopting a radar map, so that the single-dimensional score of the driver on each driving behavior dimension and the multi-dimensional comprehensive score on different driving behavior dimensions are obtained.
As an example, setting a driving behavior dimension corresponding to each classification in the clustering result, presetting scores corresponding to each driving behavior feature in the driving behavior dimension according to each driving behavior dimension, then, classifying the driving behavior feature of each driving of the driver into the driving behavior dimension, and connecting the driving behavior features in each dimension by adopting a radar map to form a user image corresponding to the driving of the driver; so as to obtain the single-dimensional score of the driver on each driving behavior dimension and the multi-dimensional comprehensive score on different driving behavior dimensions.
And S107, analyzing factors influencing the driving behavior of the driver according to the single-dimensional score and the multi-dimensional comprehensive score.
That is, the respective dimensional scores affecting the driving behavior of the driver are analyzed according to the single-dimensional peace and the multi-dimensional composite score to determine the factors affecting the driving behavior of the driver.
As an example, when the fuel consumption of a driver driving a vehicle is high, the fuel consumption variable is used as a dependent variable, the single-dimensional score of each driving behavior characteristic is used as an independent variable, a multiple linear regression model is constructed, and by looking up a fitting regression effect, which single-dimensional scores of the driving behavior characteristics can significantly influence the fuel consumption value is analyzed, so as to determine a factor that influences the driver driving the vehicle to generate the high fuel consumption.
As shown in fig. 2, in some embodiments, the step of screening the driving behavior feature matrix to obtain the final feature in the driving behavior analysis method according to the embodiment of the present invention may specifically include the following steps:
s201, acquiring a behavior feature probability distribution map based on the driving behavior feature matrix to analyze the driving behavior feature distribution condition, and deleting driving behavior features which are not obviously distinguished in the driving behavior feature matrix according to the driving behavior feature distribution condition to perform preliminary screening.
That is to say, a behavior feature probability distribution map is generated according to the driving behavior feature matrix, the driving behavior feature distribution situation is analyzed according to the behavior feature probability distribution map, and the driving behavior features which are not obviously distinguished are deleted according to the driving behavior feature distribution situation, so that the primary screening of the driving behavior features is completed.
S202, ranking the driving behavior characteristics after the primary screening by adopting a maximum correlation minimum redundancy characteristic selection method based on mutual information, and performing secondary screening on the driving behavior characteristics after the primary screening according to a ranking result.
Mutual information refers to the amount of information contained in one random variable with respect to another random variable, or the uncertainty of a decrease in one random variable due to the knowledge of another random variable.
As an example, after the driving behavior features that are not obviously distinguished in the driving behavior feature matrix are deleted according to the driving behavior feature distribution situation to complete the primary screening, one driving behavior feature is selected at a time by estimating the capability of each driving behavior feature after the primary screening to reduce the uncertainty of other driving behavior features except the driving behavior feature itself, the features are sorted by adopting the maximum correlation minimum redundancy based on mutual information, and the driving behavior features after the primary screening are secondarily screened according to the sorting result.
The secondary screening may be performed in various manners, for example, according to the sequence of the sorting, the driving behavior characteristics of the sorting number before the preset value are selected.
As an example, a threshold value of the average mutual information is preset, and then the driving behavior characteristics of the mutual information which are unexpected at the threshold value are deleted to complete the secondary screening.
And S203, giving weight to the driving behavior characteristics after secondary screening.
That is, the driving behavior features after the secondary screening are weighted to determine the weight of each driving behavior feature after the secondary screening.
And S204, generating a characteristic box chart according to the weighted weight of each driving behavior characteristic, and removing abnormal behavior characteristics according to the characteristic box chart to obtain final characteristics.
Wherein, the box chart is a statistical chart used for realizing a group of data dispersion conditions.
As an example, according to the sequence of each weighted driving behavior feature, determining a minimum value, a first quartile, a median, a third quartile and a maximum value, determining an inner limit value and an outer limit value according to the difference value of the first quartile and the third quartile, and determining an abnormal behavior feature according to the inner limit value and the outer limit value; then, the abnormal behavior features are removed according to the feature box chart to obtain final features.
In summary, according to the driving behavior analysis method of the embodiment of the present invention, firstly, a behavior feature probability distribution map is obtained based on a driving behavior feature matrix to analyze a driving behavior feature distribution situation, and driving behavior features that are not obviously distinguished in the driving behavior feature matrix are deleted according to the driving behavior feature distribution situation to perform a primary screening, then, a maximum correlation minimum redundancy feature selection method based on mutual information is adopted to sort the driving behavior features after the primary screening, secondary screening is performed on the driving behavior features after the primary screening according to a sorting result, and then, weighting is performed on the driving behavior features after the secondary screening; secondly, generating a characteristic box diagram according to the weighted weight of each driving behavior characteristic, and removing abnormal behavior characteristics according to the characteristic box diagram to obtain final characteristics; therefore, the accuracy and the referential performance of the final characteristics are enhanced, and the generation of a clustering result formed according to the final characteristics is facilitated.
In order to achieve the above-described embodiments, an embodiment of the present invention proposes a computer-readable storage medium having stored thereon a driving behavior analysis program that, when executed by a processor, implements the driving behavior analysis method as described above.
In order to implement the foregoing embodiment, an embodiment of the present invention provides a driving behavior analysis system, which includes a memory, a processor, and a driving behavior analysis program stored in the memory and executable on the processor, where the processor implements the driving behavior analysis method as described above when executing the driving behavior analysis program.
As shown in fig. 3, an embodiment of the present invention provides a driving behavior analysis system, including: the system comprises a data acquisition module 10, a feature extraction module 20, a feature screening module 30, a clustering module 40, an image generation module 50 and a driving behavior analysis module 60.
The data acquisition module 10 is configured to acquire driving data of a driver.
And the characteristic extraction module 20 is used for extracting the characteristics of the driving data of the driver in combination with the driving process of the vehicle so as to obtain a driving behavior characteristic matrix.
And the characteristic screening module 30 is used for screening the driving behavior characteristic matrix to obtain the final characteristics.
The clustering module 40 is used for measuring the driving behavior feature similarity of each driving of the driver according to the final feature, establishing a connecting edge according to the driving behavior feature similarity, clustering the driver groups by adopting a Fast Unfolding clustering algorithm and a K-means clustering algorithm respectively based on the connecting edge to obtain a first clustering result and a second clustering result, and obtaining a clustering result with high accuracy in the first clustering result and the second clustering result.
And the portrait generation module 50 is used for attributing the driving behavior characteristics of each driving of the driver to the driving behavior dimensions according to the clustering result with high accuracy, and performing user portrait on the driving preference of the driver from different driving behavior dimensions by adopting a radar map so as to obtain the single-dimensional score of the driver on each driving behavior dimension and the multi-dimensional comprehensive score on different driving behavior dimensions.
And the driving behavior analysis module 60 is configured to analyze factors affecting the driving behavior of the driver according to the single-dimensional score and the multi-dimensional comprehensive score.
In summary, according to the driving behavior analysis system provided by the embodiment of the present invention, first, the data acquisition module acquires driving data of a driver; then, the characteristic extraction module is combined with the vehicle running process to extract the characteristics of the driving data of the driver so as to obtain a driving behavior characteristic matrix; then, the characteristic screening module screens the driving behavior characteristic matrix to obtain final characteristics; secondly, measuring the driving behavior feature similarity of each driving of the driver according to the final feature by the clustering module, establishing connecting edges according to the driving behavior feature similarity, respectively clustering the driver groups by adopting Fast Unfolding clustering algorithm and K-means clustering algorithm based on the connecting edges to obtain a first clustering result and a second clustering result, and obtaining a clustering result with high accuracy in the first clustering result and the second clustering result; then, the portrait generation module enables driving behavior characteristics of each driving of the driver to be classified into driving behavior dimensions according to the clustering result with high accuracy, and adopts a radar map to conduct user portrait on driving preference of the driver from different driving behavior dimensions so as to obtain single-dimensional scores of the driver on each driving behavior dimension and multi-dimensional comprehensive scores on different driving behavior dimensions; then, the driving behavior analysis module analyzes factors influencing the driving behavior of the driver according to the single-dimensional score and the multi-dimensional comprehensive score; therefore, the driving behavior of the driver can be comprehensively evaluated in multiple dimensions, and the driving behavior can be used as a basis for correcting bad driving habits of the driver, so that the safety of the urban traffic environment and the riding comfort of passengers can be further guaranteed.
In some embodiments, in the driving behavior analysis system provided in the embodiments of the present invention, the data obtaining module 10 obtains driving data of the driver through a CAN bus onboard instrument, where the driving data of the driver includes information based on a driver ID, a recording date and time, a position, a speed, an up-down movement, a motor and engine rotation speed, a gear position, electronic brake information, hand brake information, an accelerator pedal percentage, an ignition signal, brake pedal opening information, and switch state information.
As shown in fig. 4, in some embodiments, in the driving behavior analysis system provided by the embodiment of the present invention, the feature screening module 30 includes:
a preliminary screening unit 70, configured to obtain a behavior feature probability distribution map based on the driving behavior feature matrix to analyze a driving behavior feature distribution situation, and delete driving behavior features that are not significantly distinguished in the driving behavior feature matrix according to the driving behavior feature distribution situation to perform preliminary screening;
a secondary screening unit 80, configured to sort the primarily screened driving behavior features by using a maximum correlation minimum redundancy feature selection method based on mutual information, and perform secondary screening on the primarily screened driving behavior features according to a sorting result;
the empowerment unit 90 is used for empowering the driving behavior characteristics after the secondary screening;
and an abnormality removing unit 100 for generating a characteristic box map from the weighted weight of each driving behavior characteristic, and removing the abnormal behavior characteristic from the characteristic box map to obtain a final characteristic.
In some embodiments, in the driving behavior analysis system provided in the embodiments of the present invention, when the clustering module 40 performs driver group clustering by using Fast Unfolding clustering algorithm, points and communities whose modularity can be improved in the network are merged according to the modularity algorithm until the modularity cannot be improved in the network.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
It should be noted that in the claims, any reference signs placed between parentheses shall not be construed as limiting the claim. The word "comprising" does not exclude the presence of elements or steps not listed in a claim. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The invention may be implemented by means of hardware comprising several distinct elements, and by means of a suitably programmed computer. In the unit claims enumerating several means, several of these means may be embodied by one and the same item of hardware. The usage of the words first, second and third, etcetera do not indicate any ordering. These words may be interpreted as names.
While preferred embodiments of the present invention have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. Therefore, it is intended that the appended claims be interpreted as including preferred embodiments and all such alterations and modifications as fall within the scope of the invention.
It will be apparent to those skilled in the art that various changes and modifications may be made in the present invention without departing from the spirit and scope of the invention. Thus, if such modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include such modifications and variations.
In the description of the present invention, it is to be understood that the terms "first", "second" and the like are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implying any number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of the present invention, "a plurality" means two or more unless specifically defined otherwise.
In the present invention, unless otherwise expressly stated or limited, the terms "mounted," "connected," "secured," and the like are to be construed broadly and can, for example, be fixedly connected, detachably connected, or integrally formed; can be mechanically or electrically connected; either directly or indirectly through intervening media, either internally or in any other relationship. The specific meanings of the above terms in the present invention can be understood by those skilled in the art according to specific situations.
In the present invention, unless otherwise expressly stated or limited, the first feature "on" or "under" the second feature may be directly contacting the first and second features or indirectly contacting the first and second features through an intermediate. Also, a first feature "on," "over," and "above" a second feature may be directly or diagonally above the second feature, or may simply indicate that the first feature is at a higher level than the second feature. A first feature being "under," "below," and "beneath" a second feature may be directly under or obliquely under the first feature, or may simply mean that the first feature is at a lesser elevation than the second feature.
In the description herein, references to the description of the term "one embodiment," "some embodiments," "an example," "a specific example," or "some examples," etc., mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the invention. In this specification, the schematic representations of the terms used above should not be understood to necessarily refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Furthermore, various embodiments or examples and features of different embodiments or examples described in this specification can be combined and combined by one skilled in the art without contradiction.
Although embodiments of the present invention have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present invention, and that variations, modifications, substitutions and alterations can be made to the above embodiments by those of ordinary skill in the art within the scope of the present invention.
Claims (10)
1. A driving behavior analysis method, characterized by comprising the steps of:
acquiring driving data of a driver;
combining the driving process of the vehicle, and performing feature extraction on the driving data of the driver to obtain a driving behavior feature matrix;
screening the driving behavior characteristic matrix to obtain a final characteristic;
measuring the driving behavior characteristic similarity of each driving of the driver according to the final characteristic, establishing connecting edges according to the driving behavior characteristic similarity, and respectively clustering the driver groups by adopting a Fast Unfolding clustering algorithm and a K-means clustering algorithm based on the connecting edges to obtain a first clustering result and a second clustering result;
acquiring a clustering result with high accuracy in the first clustering result and the second clustering result;
the driving behavior characteristics of each driving of the driver are classified into driving behavior dimensions according to the clustering result with high accuracy, and the driving preference of the driver is subjected to user portrayal from different driving behavior dimensions by adopting a radar map so as to obtain single-dimensional scores of the driver on each driving behavior dimension and multi-dimensional comprehensive scores on different driving behavior dimensions;
and analyzing factors influencing the driving behavior of the driver according to the single-dimensional score and the multi-dimensional comprehensive score.
2. The driving behavior analysis method according to claim 1, wherein the driving data of the driver is acquired through a CAN bus onboard instrument, wherein the driving data of the driver includes information based on a driver ID, a recording date and time, a position, a speed, an up-down motion, a motor and engine rotation speed, a gear position, electronic brake information, handbrake information, an accelerator pedal percentage, an ignition signal, brake pedal opening information, and switch state information.
3. The driving behavior analysis method of claim 1, wherein screening the driving behavior feature matrix to obtain final features comprises:
acquiring a behavior feature probability distribution map based on the driving behavior feature matrix to analyze the driving behavior feature distribution condition, and deleting driving behavior features which are not obviously distinguished in the driving behavior feature matrix according to the driving behavior feature distribution condition to perform preliminary screening;
sorting the driving behavior characteristics after the primary screening by adopting a maximum correlation minimum redundancy characteristic selection method based on mutual information, and performing secondary screening on the driving behavior characteristics after the primary screening according to a sorting result;
performing empowerment on the driving behavior characteristics after the secondary screening;
and generating a characteristic box chart according to the weighted weight of each driving behavior characteristic, and removing abnormal behavior characteristics according to the characteristic box chart to obtain the final characteristics.
4. The driving behavior analysis method according to any one of claims 1 to 3, wherein, when clustering of the driver group is performed by using Fast Unfolding clustering algorithm, points and communities in the network, whose modularity can be improved, are merged according to a modularity algorithm until the modularity in the network cannot be improved.
5. A computer-readable storage medium, characterized in that a driving behavior analysis program is stored thereon, which when executed by a processor implements the driving behavior analysis method according to any one of claims 1 to 4.
6. A driving behavior analysis system comprising a memory, a processor, and a driving behavior analysis program stored on the memory and executable on the processor, the processor implementing the driving behavior analysis method according to any one of claims 1 to 4 when executing the driving behavior analysis program.
7. A driving behavior analysis system, comprising:
the data acquisition module is used for acquiring driving data of a driver;
the characteristic extraction module is used for extracting the characteristics of the driving data of the driver in combination with the driving process of the vehicle to obtain a driving behavior characteristic matrix;
the characteristic screening module is used for screening the driving behavior characteristic matrix to obtain final characteristics;
the clustering module is used for measuring the driving behavior feature similarity of each driving of the driver according to the final feature, establishing connecting edges according to the driving behavior feature similarity, respectively adopting Fast Unfolding clustering algorithm and K-means clustering algorithm to cluster the driver groups based on the connecting edges so as to obtain a first clustering result and a second clustering result, and obtaining a high-accuracy clustering result in the first clustering result and the second clustering result;
the portrait generation module is used for attributing the driving behavior characteristics of each driving of the driver to the driving behavior dimensions according to the clustering result with high accuracy, and performing user portrait on the driving preference of the driver from different driving behavior dimensions by adopting a radar map so as to obtain single-dimensional scores of the driver on each driving behavior dimension and multi-dimensional comprehensive scores on different driving behavior dimensions;
and the driving behavior analysis module is used for analyzing factors influencing the driving behavior of the driver according to the single-dimensional score and the multi-dimensional comprehensive score.
8. The driving behavior analysis system of claim 7, wherein the data acquisition module acquires driving data of the driver through a CAN bus onboard instrument, wherein the driving data of the driver includes information based on a driver ID, a recording date and time, a position, a speed, an up-down movement, a motor and engine rotation speed, a gear position, electronic brake information, hand brake information, an accelerator pedal percentage, an ignition signal, brake pedal opening information, and switch state information.
9. The driving behavior analysis system of claim 7, wherein the feature screening module comprises:
the preliminary screening unit is used for acquiring a behavior feature probability distribution map based on the driving behavior feature matrix so as to analyze the driving behavior feature distribution condition, and deleting driving behavior features which are not obviously distinguished in the driving behavior feature matrix according to the driving behavior feature distribution condition so as to perform preliminary screening;
the secondary screening unit is used for sorting the driving behavior characteristics after the primary screening by adopting a maximum correlation minimum redundancy characteristic selection method based on mutual information and carrying out secondary screening on the driving behavior characteristics after the primary screening according to a sorting result;
the weighting unit is used for weighting the driving behavior characteristics after the secondary screening;
and the abnormality removing unit is used for generating a characteristic box chart according to the weighted weight of each driving behavior characteristic and removing the abnormal behavior characteristic according to the characteristic box chart to obtain the final characteristic.
10. The driving behavior analysis system according to any one of claims 7 to 9, wherein, when the clustering module performs driver group clustering using Fast Unfolding clustering algorithm, points and communities in the network, whose modularity can be improved, are merged according to the modularity algorithm until the modularity in the network cannot be improved.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810801891.9A CN109033332B (en) | 2018-07-20 | 2018-07-20 | Driving behavior analysis method, medium and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810801891.9A CN109033332B (en) | 2018-07-20 | 2018-07-20 | Driving behavior analysis method, medium and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109033332A CN109033332A (en) | 2018-12-18 |
| CN109033332B true CN109033332B (en) | 2020-12-25 |
Family
ID=64643761
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810801891.9A Active CN109033332B (en) | 2018-07-20 | 2018-07-20 | Driving behavior analysis method, medium and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109033332B (en) |
Families Citing this family (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109552338B (en) * | 2018-12-19 | 2020-04-07 | 北京理工新源信息科技有限公司 | Evaluation method and system for ecological driving behavior of pure electric vehicle |
| CN110097287B (en) * | 2019-05-07 | 2021-06-22 | 宏图物流股份有限公司 | Group portrait method for logistic drivers |
| CN110533094B (en) * | 2019-08-26 | 2022-11-15 | 汉纳森（厦门）数据股份有限公司 | Evaluation method and system for driver |
| CN113129473B (en) * | 2020-01-15 | 2023-06-27 | 北京京东振世信息技术有限公司 | Data acquisition method, device and system |
| CN111460076B (en) * | 2020-04-20 | 2023-05-26 | 亚美智联数据科技有限公司 | Driving route familiarity determination method, driving route familiarity determination device, computer device, and storage medium |
| CN112200235B (en) * | 2020-09-30 | 2022-05-27 | 蜂巢能源科技有限公司 | Method, device, medium and equipment for classifying driving behavior habits of electric vehicle |
| CN112257953B (en) * | 2020-11-03 | 2021-09-24 | 上海电力大学 | Data processing method based on polar region new energy power generation power prediction |
| CN114842571A (en) * | 2021-02-02 | 2022-08-02 | 深圳市易流科技股份有限公司 | Method and device for determining driving behavior data |
| CN113033651A (en) * | 2021-03-22 | 2021-06-25 | 上海仙塔智能科技有限公司 | Method and device for improving driving safety |
| CN113505955A (en) * | 2021-05-19 | 2021-10-15 | 辛巴网络科技(南京)有限公司 | User driving behavior scoring method based on TSP system |
| CN113379945A (en) * | 2021-07-26 | 2021-09-10 | 陕西天行健车联网信息技术有限公司 | Vehicle driving behavior analysis device, method and system |
| CN115641160A (en) * | 2022-12-26 | 2023-01-24 | 中国汽车技术研究中心有限公司 | Method, device and storage medium for improving new energy automobile |
| CN116821805A (en) * | 2023-06-28 | 2023-09-29 | 运脉云技术有限公司 | Vehicle service platform system for monitoring driving behavior and driving behavior monitoring method |
| CN116653980A (en) * | 2023-06-28 | 2023-08-29 | 运脉云技术有限公司 | Driver driving habit analysis system and driving habit analysis method |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9898759B2 (en) * | 2014-03-28 | 2018-02-20 | Joseph Khoury | Methods and systems for collecting driving information and classifying drivers and self-driving systems |
| CN105930771A (en) * | 2016-04-13 | 2016-09-07 | 乐视控股（北京）有限公司 | Driving behavior grading method and device |
| CN107153916A (en) * | 2017-04-30 | 2017-09-12 | 安徽中科美络信息技术有限公司 | A kind of driving behavior evaluation method clustered based on FCM with BP neural network |
| CN107585164B (en) * | 2017-09-04 | 2019-11-22 | 交通运输部公路科学研究所 | A kind of method and device for the driver that classifies |
-
2018
- 2018-07-20 CN CN201810801891.9A patent/CN109033332B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN109033332A (en) | 2018-12-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109033332B (en) | Driving behavior analysis method, medium and system | |
| CN109117869B (en) | User portrayal method, medium and system | |
| CN109635852B (en) | User portrait construction and clustering method based on multi-dimensional attributes | |
| CN110020797B (en) | Evaluation method of automatic driving test scene based on perception defect | |
| CN111688713B (en) | Driving behavior analysis method and device | |
| US9633490B2 (en) | System and method for testing and evaluating vehicle components | |
| CN106650157B (en) | Method, device and system for estimating fault occurrence probability of vehicle parts | |
| WO2015171397A1 (en) | Passive driver identification | |
| DE102012200671A1 (en) | Music selection system and method in a vehicle | |
| CN106649709B (en) | Vehicle stopping behavior pattern prediction and evaluation method based on data mining | |
| Abas et al. | Development of Malaysian urban drive cycle using vehicle and engine parameters | |
| CN108769104B (en) | Road condition analysis and early warning method based on vehicle-mounted diagnosis system data | |
| US20180017402A1 (en) | Method and system for vehicle speed profile generation | |
| CN111401414A (en) | Natural driving data-based dangerous scene extraction and classification method | |
| CN109886724B (en) | Robust resident travel track identification method | |
| CN113095387B (en) | Road risk identification method based on networking vehicle-mounted ADAS | |
| CN108475357B (en) | Method and system for evaluating driver's trip performance | |
| Yardy et al. | Detecting malicious driving with machine learning | |
| CN115035713B (en) | Intelligent traffic carbon emission monitoring system and method | |
| CN109376473B (en) | Vehicle controller, vehicle and method and device for calculating driving mileage of vehicle | |
| Jaworek-Korjakowska et al. | SafeSO: interpretable and explainable deep learning approach for seat occupancy classification in vehicle interior | |
| CN107867294B (en) | Apparatus and method for evaluating driving sensitivity of vehicle | |
| CN114169426A (en) | Beidou position data-based highway traffic potential safety hazard investigation method | |
| CN113192340B (en) | Method, device, equipment and storage medium for identifying highway construction vehicles | |
| CN114802264A (en) | Vehicle control method and device and electronic equipment |
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 | ||
| CB02 | Change of applicant information |
Address after: 361000 Innovation Building, Software Park, Xiamen Torch High-tech Zone, Xiamen City, Fujian Province Applicant after: Hanathan (Xiamen) data Limited by Share Ltd Applicant after: Shenzhen Pengcheng Electric Vehicle Rental Co., Ltd. Address before: 361000 5th Floor, 28 Guanri Road, Phase II Software Park, Siming District, Xiamen City, Fujian Province Applicant before: Hanathan (Xiamen) data Limited by Share Ltd Applicant before: Shenzhen Pengcheng Electric Vehicle Rental Co., Ltd. |
|
| CB02 | Change of applicant information | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |