CN115817500A - Driving style determination method and device, vehicle and storage medium - Google Patents
Driving style determination method and device, vehicle and storage medium Download PDFInfo
- Publication number
- CN115817500A CN115817500A CN202211502917.2A CN202211502917A CN115817500A CN 115817500 A CN115817500 A CN 115817500A CN 202211502917 A CN202211502917 A CN 202211502917A CN 115817500 A CN115817500 A CN 115817500A
- Authority
- CN
- China
- Prior art keywords
- driving style
- vehicle
- determining
- principal component
- driving
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Landscapes
- Control Of Driving Devices And Active Controlling Of Vehicle (AREA)
Abstract
The invention discloses a driving style determination method, a driving style determination device, a vehicle and a storage medium. The method comprises the following steps: acquiring a kinematic segment according to vehicle driving data, and acquiring a first characteristic parameter representing a transverse driving style and a second characteristic parameter representing a longitudinal driving style in the kinematic segment; respectively carrying out dimensionality reduction processing on the first characteristic parameters and the second characteristic parameters to obtain a plurality of principal component score matrixes; and clustering the kinematic segments according to each principal component score matrix to obtain a plurality of clustering centers, and determining the driving style of the driver respectively when the vehicle turns, accelerates or decelerates according to the characteristic parameters corresponding to each clustering center. In the embodiment, the parameters corresponding to the horizontal driving style and the vertical driving style are determined from the kinematic segments, and the kinematic segments are clustered by using the principal component score matrix, so that the driving styles of the driver in different dimensions are determined, and the intellectualization of the judgment of the driving style of the vehicle is improved.
Description
Technical Field
The invention relates to the technical field of automatic driving, in particular to a driving style determining method, a driving style determining device, a vehicle and a storage medium.
Background
The driving style can be an overall evaluation index for representing the inherent driving mode of the driver, and due to the difference of factors such as gender, age and personality, the driving style of the driver shows obvious difference due to the fact that a certain regular driving behavior tendency exists, and for the same driver, the driving style of the driver has certain difference when the driver drives under different working conditions or moods.
Most of the existing driving style identification and judgment methods comprehensively consider the overall performance of a driver in the driving process, including driving behavior change, control acceleration degree and the like, are lack of analysis on different dimensions, and have certain limitations.
Disclosure of Invention
The invention provides a driving style determining method, a driving style determining device, a vehicle and a storage medium, and aims to solve the problem that the driving style determination in the prior art is limited.
According to an aspect of the present invention, there is provided a driving style determination method including:
the method comprises the steps of obtaining a kinematic segment according to vehicle driving data, and obtaining a first characteristic parameter representing a transverse driving style and a second characteristic parameter representing a longitudinal driving style in the kinematic segment;
respectively carrying out dimensionality reduction processing on the first characteristic parameters and the second characteristic parameters to obtain a plurality of principal component score matrixes;
and clustering the kinematic segments according to each principal component score matrix to obtain a plurality of clustering centers, and determining the driving style of the driver respectively during steering, accelerating or decelerating of the vehicle according to the characteristic parameters corresponding to each clustering center.
According to another aspect of the present invention, there is provided a driving style determination apparatus including:
the characteristic parameter acquisition module is used for acquiring a kinematic segment according to vehicle driving data, and acquiring a first characteristic parameter representing a transverse driving style and a second characteristic parameter representing a longitudinal driving style in the kinematic segment;
the characteristic parameter dimension reduction module is used for respectively carrying out dimension reduction processing on the first characteristic parameters and the second characteristic parameters to obtain a plurality of principal component score matrixes;
and the driving style determining module is used for clustering the kinematic segments according to each principal component score matrix to obtain a plurality of clustering centers and determining the driving style of a driver respectively during steering, accelerating or decelerating of the vehicle according to the characteristic parameters corresponding to each clustering center.
According to another aspect of the present invention, there is provided a vehicle including:
the vehicle-mounted sensor is used for collecting vehicle driving data;
at least one processor; and
a memory communicatively coupled to the at least one processor; wherein the content of the first and second substances,
the memory stores a computer program executable by the at least one processor to enable the at least one processor to perform the driving style determination method of any of the embodiments of the present invention.
According to another aspect of the present invention, there is provided a computer-readable storage medium storing computer instructions for causing a processor to implement the driving style determination method according to any one of the embodiments of the present invention when executed.
According to the technical scheme of the embodiment of the invention, the driving styles of the driver in different dimensions are determined by determining the parameters corresponding to the transverse driving style and the longitudinal driving style from the kinematic segments and clustering the kinematic segments by utilizing the principal component score matrix, so that the problem of limitation in the judgment of the driving styles in the prior art is solved, and the intellectualization of the judgment of the driving styles of the vehicle is improved.
It should be understood that the statements in this section do not necessarily identify key or critical features of the embodiments of the present invention, nor do they necessarily limit the scope of the invention. Other features of the present invention will become apparent from the following description.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed to be used in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
Fig. 1 is a flowchart of a driving style determining method according to an embodiment of the present invention;
FIG. 2 is a flow chart of another driving style determination method according to a second embodiment of the present invention;
FIG. 3 is a flowchart of another driving style determination method according to the second embodiment of the present invention
Fig. 4 is a schematic structural diagram of a driving style determining apparatus according to a third embodiment of the present invention;
fig. 5 is a schematic configuration diagram of a vehicle implementing the driving style determination method of the embodiment of the invention.
Detailed Description
In order to make the technical solutions of the present invention better understood, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be obtained by a person skilled in the art without making any creative effort based on the embodiments in the present invention, shall fall within the protection scope of the present invention.
It should be noted that the terms "first," "second," and the like in the description and claims of the present invention and in the drawings described above are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the invention described herein are capable of operation in sequences other than those illustrated or described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
Example one
Fig. 1 is a flowchart of a driving style determination method provided in an embodiment of the present invention, which may be applied to a case where a driving style of a driver is obtained, and the method may be performed by a driving style determination device, which may be implemented in a form of hardware and/or software, and may be integrally configured in a vehicle. As shown in fig. 1, the method includes:
s110, a kinematic segment is obtained according to the vehicle driving data, and a first characteristic parameter representing a transverse driving style and a second characteristic parameter representing a longitudinal driving style in the kinematic segment are obtained.
The vehicle driving data may be vehicle driving data collected by various sensors when the vehicle is in a running state, and the vehicle driving data may include various data including, but not limited to, time, speed, acceleration, and ambient environment information; the kinematic segment may refer to a vehicle driving data set between the start of the idle state and the start of the next idle state of the vehicle, and specifically, the start of one idle state may be used as the start of the historical kinematic segment, and the start of the next idle state may be used as the end of the kinematic segment; the idle state may refer to an operating condition when the engine is idling.
In this embodiment, the kinematic segment may be divided according to the collected vehicle driving data, and the kinematic segment may include characteristic parameters characterizing a lateral driving style and a longitudinal driving style, where the characteristic parameters may be shown in table 1 below:
TABLE 1 kinematic fragment feature parameters Table
Some of the parameters in table 1 may be used to characterize the lateral driving style, which may be specifically shown in the lateral driving style parameter table shown in table 2 below:
TABLE 2 transverse driving style characteristic parameter table
| Characteristic parameter | (symbol) | Unit of |
| Average velocity | v a | km/h |
| Maximum speed | v max | km/h |
| Standard deviation of speed | S v | km/h |
| Average lateral acceleration | l a | m/s 2 |
| Maximum lateral acceleration | l max | m/s 2 |
| Standard deviation of lateral acceleration | S l | m/s 2 |
| Average steering wheel angular acceleration | ω a | rad/s |
| Standard deviation of angular acceleration of steering wheel | S ω | rad/s 2 |
Further, some of the parameters in table 1 may be used to characterize the longitudinal driving style, where the longitudinal driving style may be divided into a driving acceleration style and a driving deceleration style, and specifically, the driving acceleration style may be represented by an acceleration style characteristic parameter table shown in table 3 below:
TABLE 3 accelerated style characterization parameter Table
The driving deceleration style can be shown by the deceleration style characteristic parameter table shown in table 4 below:
TABLE 4 deceleration Style characteristic parameter Table
| Characteristic parameter | (symbol) | Unit of |
| Average velocity | v a | km/h |
| Maximum speed | v max | km/h |
| Standard deviation of speed | S v | km/h |
| Average longitudinal deceleration | d a | m/s 2 |
| Maximum longitudinal deceleration | d max | m/s 2 |
| Standard deviation of longitudinal deceleration | S d | m/s 2 |
| Average brake pedal opening | b a | ％ |
| Standard deviation of opening of brake pedal | S b | ％ |
It can be seen that the first characteristic parameter used to characterize the lateral driving style may be average speed, maximum speed, speed standard deviation, average lateral acceleration, maximum lateral acceleration, lateral acceleration standard deviation, average steering wheel angular acceleration, and steering wheel angular acceleration standard deviation; the first characteristic parameter characterizing the longitudinal driving style may be an average speed, a maximum speed, a speed standard deviation, an average longitudinal acceleration, a maximum longitudinal acceleration, a longitudinal acceleration standard deviation, an average accelerator pedal opening, an accelerator pedal opening standard deviation, an average longitudinal deceleration, a maximum longitudinal deceleration, a longitudinal deceleration standard deviation, an average brake pedal opening, and a brake pedal opening standard deviation.
And S120, performing dimensionality reduction processing on the first characteristic parameters and the second characteristic parameters respectively to obtain a plurality of principal component score matrixes.
The dimension reduction processing may be performed on the first characteristic parameter and the second characteristic parameter by using a principal component analysis method, and specifically, the principal component analysis method may be a statistical method for data dimension reduction. The method can extract variables which possibly have correlation in the data processing process, convert the variables into a group of variables which have fewer variables and are linearly uncorrelated through orthogonal transformation, and replace the original variables with large quantity and many types, and in the process, information contained in original data is reserved as much as possible.
In this embodiment, the principal component score matrices corresponding to the steering dimension, the acceleration dimension and the deceleration dimension can be obtained by performing dimension reduction processing on the first characteristic parameter and the second characteristic parameter respectively.
S130, clustering the kinematic segments according to each principal component score matrix to obtain a plurality of clustering centers, and determining the driving style of the driver when the vehicle turns, accelerates or decelerates respectively according to the characteristic parameters corresponding to each clustering center.
In this embodiment, the cluster center may be understood as a group of characteristic parameter data, and the driving style may reflect the severity of the driver in the acceleration/deceleration/steering operation, so that the driving style may be determined according to the steering, acceleration and deceleration behaviors of the driver.
Clustering the principal component score matrixes in each different dimension to obtain 3 clustering centers, for example, for the principal component score matrixes in the steering dimension, the clustering centers obtained after clustering can be of an aggressive type, a general type and a robust type; for the corresponding principal component score matrix under the acceleration and deceleration dimensions, the clustering centers obtained after clustering can be an aggressive type, a general type and a robust type. The characteristic parameters corresponding to each cluster center can be characteristic parameters corresponding to an aggressive type, a general type and a robust type respectively.
Optionally, the clustering algorithm adopted in this embodiment may be a K-Means clustering algorithm, which is not specifically limited in this embodiment.
In the embodiment, the parameters corresponding to the transverse driving style and the longitudinal driving style are determined from the kinematic segments, and the kinematic segments are clustered by utilizing the principal component scoring matrix, so that the driving styles of the driver in different dimensions are determined, the problem that the judgment of the driving styles is limited in the prior art is solved, and the intellectualization and humanization of the judgment of the driving styles of the vehicle are improved.
Example two
Fig. 2 is a flowchart of a driving style determining method according to a second embodiment of the present invention, and in this embodiment, the step "performing dimension reduction processing on the first characteristic parameter and the second characteristic parameter respectively to obtain a plurality of principal component score matrices" is further optimized. As shown in fig. 2, the method includes:
s210, acquiring a kinematic segment according to the vehicle driving data, and acquiring a first characteristic parameter representing a transverse driving style and a second characteristic parameter representing a longitudinal driving style in the kinematic segment.
In this embodiment, the time T for a kinematic segment is calculated as follows:
T＝N (2.1)；
where N may be used to represent the number of data within each kinematic segment, the duration of each kinematic segment may be represented by the number of data contained within the corresponding segment, since the sampling frequency is 1Hz, i.e., a set of data per second.
In the present embodiment, the average velocity v for each characteristic parameter a The calculation of (c) may be as follows:
wherein v is i The vehicle speed is used for representing the vehicle speed at each moment and collected by a vehicle sensor.
In the present embodiment, the maximum velocity v among the respective characteristic parameters max The calculation of (c) may be as follows:
v max ＝max{v i h, wherein i =1,2,3, ·, N (2.3);
in this embodiment, the calculation method of the lateral acceleration and the longitudinal acceleration in each characteristic parameter may be firstly to obtain the longitudinal acceleration a of the vehicle at each time through the vehicle sensor i And lateral acceleration l i 。
In the present embodiment, the standard deviation S of the velocity in each characteristic parameter is v The calculation of (c) may be as follows:
in the present embodiment, the average longitudinal acceleration a of each characteristic parameter is a The calculation of (c) may be as follows:
wherein, a i1 May be the instantaneous longitudinal acceleration value, T, of the vehicle at that moment a The duration of the acceleration behavior during the driving process of the vehicle can be determined (to avoid the interference of the low-speed driving road segment data to the cluster, only the longitudinal acceleration value a can be calculated i At 0.15m/s 2 Above, and T a Data for more than 3 seconds).
In the present embodiment, the maximum longitudinal acceleration a among the respective characteristic parameters is max The calculation of (c) may be as follows:
a max ＝max{a i h, wherein i =1,2,3, ·, N (2.6);
in the present embodiment, the standard deviation S of the longitudinal acceleration in each characteristic parameter is a The calculation of (c) may be as follows:
in the present embodiment, the average longitudinal deceleration d in each characteristic parameter is used a The calculation of (c) can be as follows:
wherein, a i2 The instantaneous longitudinal deceleration value, T, of the vehicle at that moment d For the duration of the deceleration behavior during the travel of the vehicle (to avoid disturbance of the low-speed travel segment data on the clusters, only the longitudinal deceleration value a is calculated i At-0.15 m/s 2 Above, and T d Data over 3 s).
In the present embodiment, the maximum longitudinal deceleration d among the respective characteristic parameters is set max The calculation of (c) can be as follows:
d max ＝min{a i h, wherein i =1,2,3, ·, N (2.9);
in the present embodiment, the standard deviation S of the longitudinal deceleration for each characteristic parameter d The calculation of (c) can be as follows:
in the present embodiment, for the average lateral acceleration l in each characteristic parameter a The calculation of (c) may be as follows:
in the present embodiment, for the maximum lateral acceleration l among the respective characteristic parameters max The calculation of (c) can be as follows:
l max ＝max{l i h, wherein i =1,2,3, · N (2.12);
in the present embodiment, the standard deviation S of the lateral acceleration in each characteristic parameter is l The calculation of (c) may be as follows:
in the present embodiment, the average accelerator pedal opening t of each characteristic parameter is a The calculation of (c) may be as follows:
wherein, t i Can be the accelerator pedal opening of the vehicle at the momentDegree, T t The total time the accelerator pedal is triggered in the kinematic segment may be the vehicle.
In the present embodiment, the standard deviation S of the accelerator pedal opening degree in each characteristic parameter t The calculation of (c) may be as follows:
in the present embodiment, the average brake pedal opening b among the respective characteristic parameters is set a The calculation of (c) may be as follows:
wherein, b i The opening degree of the brake pedal of the vehicle at that time, T b The total time for which the brake pedal is activated in this kinematic segment is referred to as the vehicle.
In the present embodiment, the standard deviation S of the opening degree of the brake pedal among the respective characteristic parameters b The calculation of (c) may be as follows:
in the present embodiment, for the average steering wheel angular acceleration ω among the respective characteristic parameters a The calculation of (c) may be as follows:
wherein, ω is i For the angular acceleration of the steering wheel of the vehicle at that moment, collected by vehicle sensors, T ω The total time for the vehicle to perform a steering operation in this kinematic segment.
In the present embodiment, the standard deviation S of the angular acceleration of the steering wheel among the respective characteristic parameters ω Can be calculated as followsThe following steps:
and S220, performing dimensionality reduction on the first characteristic parameter by adopting a principal component analysis algorithm to obtain a first principal component score matrix.
In this embodiment, the first characteristic parameter characterizing the transverse driving style and the second characteristic parameter characterizing the longitudinal driving style in the kinematic segment may be subjected to the dimension reduction processing through a principal component analysis algorithm. In the calculation process, a new variable with the largest square difference in all linear combinations formed by steering, accelerating and decelerating can be defined as a first principal component M1, if the first principal component cannot well reflect the information contained in the original data, the new variable with the largest square difference in the remaining linear combinations is continuously selected as a second principal component M2 … …, and so on, and when the cumulative contribution rate of the selected principal component exceeds 85%, the new variable can be considered to reflect the information in the original data more completely.
The principal component analysis algorithm comprises the following steps:
firstly, carrying out standardization processing on original data; since the original data have different units, if the original data are directly analyzed without processing, the result has larger discreteness, and obviously has a certain influence on the classification, and therefore, the original data are standardized to eliminate the influence, specifically, the original data matrix can be converted into a standardized matrix according to a certain method, so that the mean value of each column of the matrix is 0, and the variance is l.
Let the original data matrix be X (the elements in the matrix are characteristic parameters), where p is the number of kinematic segments; n is the number of characteristic parameters;
carrying out standardization processing on the matrix X to obtain a standardized matrix Y, wherein the standardization process is shown as the following formula:
wherein r =1,2,3 … … p, j =1,2,3 … … n;
secondly, calculating a correlation coefficient and a corresponding correlation coefficient matrix:
the present embodiment calculates the correlation coefficient using the following formula:
the correlation coefficient matrix corresponding thereto may be:
thirdly, determining an eigenvector and an eigenvalue of the correlation coefficient matrix according to the correlation coefficient matrix, specifically, obtaining an eigenvalue λ of the correlation coefficient matrix, arranging the eigenvalues in a sequence from λ 1> λ 2> λ 3> … … > λ n from large to small, and obtaining eigenvectors corresponding to the eigenvalues as ξ r, ξ rj and ξ rj respectively representing the jth component of the eigenvector ξ r.
Fourthly, calculating the contribution rate of the principal component, specifically, the contribution rate calculation formula of the jth principal component is shown as formula 2.24:
and calculating the contribution rate of each principal component in sequence according to the formula 3.24, and calculating the cumulative contribution rate of each principal component, wherein when the cumulative contribution rate of the m principal components reaches more than 85%, the information of the original data can be considered to be completely reserved, and the principal components are selected as the basis of classification.
Fifth, a principal component load matrix Z is calculated, specifically, using the following formula:
wherein j =1,2,3 … … n, q =1,2,3 … … m;
and sixthly, multiplying the normalized characteristic parameter matrix and the principal component load matrix to obtain a principal component score matrix. Specifically, the principal component score matrix is as follows:
in this embodiment, the principal component analysis algorithm may be used to perform the dimension reduction processing on the first characteristic parameter to obtain the first principal component score matrix.
And S230, performing dimensionality reduction on a second characteristic parameter for representing vehicle acceleration by adopting a principal component analysis algorithm to obtain a second principal component score matrix.
In this embodiment, the principal component analysis algorithm may be used to perform the dimension reduction processing on the second characteristic parameter for characterizing the vehicle acceleration, so as to obtain a second principal component score matrix.
And S240, performing dimensionality reduction on the second characteristic parameters for representing the vehicle deceleration by adopting a principal component analysis algorithm to obtain a third principal component score matrix.
In this embodiment, the principal component analysis algorithm may be used to perform the dimension reduction processing on the second characteristic parameter for characterizing the vehicle deceleration to obtain a third principal component score matrix.
And S250, clustering the kinematic segments according to each principal component score matrix to obtain a plurality of clustering centers, and determining the driving style of a driver respectively during steering, accelerating or decelerating of the vehicle according to the characteristic parameters corresponding to each clustering center.
In this embodiment, the processed characteristic parameters may be clustered by using a K-means clustering algorithm to obtain a plurality of clustering centers.
In this embodiment, the steps of clustering the kinematic segments according to each principal component score matrix to obtain a plurality of clustering centers are as follows:
1. according to the actual situation, the number of clusters K =2 or 3 is assumed, and an initial cluster center is randomly set for each category.
2. The euclidean distance of each kinematic segment from the cluster center is calculated using the following equation (2.26):
xik denotes the kth variable of the ith fragment, each fragment has p variables (determined by the principal component analysis algorithm), y denotes the selected cluster center, and in the first calculation, it is a randomly selected set of data that also contains p variables.
3. And classifying the data with the closer distance into one class, calculating the center position of each class, and setting the center position as a new clustering center.
4. And (4) repeating the steps 2-3 according to the new clustering center, and continuously determining the new clustering center through repeated calculation until the clustering center is not changed any more.
5. And judging the clustering centers to be aggressive type, general type and robust type from large to small according to the numerical values of the clustering centers.
In the embodiment, the driving style of the driver when the vehicle turns, accelerates or decelerates, namely an aggressive type, a general type and a robust type, is determined according to the characteristic parameters corresponding to each cluster center.
For example, determining the driving style of the driver when the vehicle turns according to the characteristic parameter corresponding to each cluster center may be determining the driving style of each first cluster center when the vehicle turns according to the numerical value of each first cluster center corresponding to the first principal component score matrix; determining the number of the kinematic segments corresponding to each driving style when the vehicle volume turns according to the driving style of each first clustering center when the vehicle turns; and determining the driving style of the driver when the vehicle turns according to the proportion of the number of the kinematic segments corresponding to each driving style in the number of the kinematic segments corresponding to the first clustering center when the vehicle turns.
Wherein, the first cluster center may be all the kinematic segments in the cluster corresponding to the cluster center, and the kinematic segments may be distributed near the first cluster center.
In this embodiment, after the numerical value of the first cluster center is determined, the specific style of the driver when performing the steering driving behavior may be determined according to the number ratio of the kinematic segments corresponding to each driving style in the steering dimension in the kinematic segments generated by the driver.
In this embodiment, if it is assumed that the number of aggressive kinematic segments is 40%, the normal kinematic segment is 30%, and the robust kinematic segment is 30%, it can be determined that the driving style of the driver when the vehicle is turning is aggressive. The present embodiment does not specifically limit this.
For example, determining the driving style of each first cluster center when the vehicle turns according to the value of each first cluster center corresponding to the first principal component score matrix may include: determining the numerical value of each first clustering center according to the average lateral acceleration, the maximum lateral acceleration and the average value of the lateral acceleration standard deviation of each first clustering center corresponding to the first principal component score matrix; and performing descending order arrangement on the first clustering centers according to the numerical values, and determining the driving style of each first clustering center when the vehicle turns according to the arrangement result.
In this embodiment, each selected index reflects the severity of the acceleration/deceleration/steering operation of the driver, so the law of each characteristic parameter should be aggressive type > general type > robust type, that is, the aggressive type value is greater than the general type value, and the general type value is greater than the robust type value.
Specifically, the average value of the average lateral acceleration, the maximum lateral acceleration and the standard deviation of the lateral acceleration can be selected for the driving style when the vehicle turns, the average values are sorted in a descending order from large to small, and the corresponding first clustering center is divided into an aggressive type, a general type and a robust type according to the rule of the characteristic parameters.
Exemplarily, determining the driving style of each second clustering center when the vehicle accelerates according to the value of each second clustering center corresponding to the second principal component score matrix; determining the number of the kinematic segments corresponding to each driving style when the vehicle accelerates according to the driving style of each second cluster center when the vehicle accelerates; and determining the driving style of the driver when the vehicle accelerates according to the ratio of the number of the kinematic segments corresponding to each driving style when the vehicle accelerates to the number of the kinematic segments corresponding to the second clustering center.
In this embodiment, it may be assumed that the number of the aggressive kinematic segments is 30% when the vehicle accelerates, the general type is 30% and the robust type is 40%, and it may be determined that the driving style of the driver when the vehicle accelerates is the robust type.
For example, determining the driving style of each second cluster center when the vehicle accelerates according to the value of each second cluster center corresponding to the second principal component score matrix may include: determining the numerical value of each second clustering center according to the average longitudinal acceleration, the maximum longitudinal acceleration and the average value of the longitudinal acceleration standard deviation of each second clustering center corresponding to the second principal component scoring matrix; and performing descending order arrangement on the second cluster centers according to the numerical values, and determining the driving style of each second cluster center when the vehicle accelerates according to the arrangement result.
The average longitudinal acceleration, the maximum longitudinal acceleration and the mean value of the standard deviation of the longitudinal acceleration of each type of data clustering center can be calculated for the accelerated driving style, and the corresponding second clustering centers are divided into an aggressive type, a general type and a robust type according to the rule of characteristic parameters from large to small according to the mean value.
For example, determining the driving style of the driver when the vehicle decelerates according to the characteristic parameter corresponding to each cluster center may include: determining the driving style of each third clustering center when the vehicle decelerates according to the numerical value of each third clustering center corresponding to the third principal component score matrix; determining the number of the kinematic segments corresponding to each driving style when the vehicle decelerates according to the driving style of each third clustering center when the vehicle decelerates; and determining the driving style of the driver during the deceleration of the vehicle according to the ratio of the number of the kinematic segments corresponding to each driving style during the deceleration of the vehicle to the number of the kinematic segments corresponding to the third clustering center.
In this embodiment, it may be assumed that the number of aggressive kinematic segments is 30% when the vehicle decelerates, the general type ratio is 30%, and the robust type ratio is 40%, and it may be determined that the driving style of the driver when the vehicle decelerates is robust.
For example, determining the driving style of each third categorical center when the vehicle decelerates according to the value of each third categorical center corresponding to the third principal component score matrix may include: determining the numerical value of each third clustering center according to the average longitudinal deceleration, the maximum longitudinal deceleration and the average value of the longitudinal deceleration standard deviation of each third clustering center corresponding to the third principal component scoring matrix; and performing descending order arrangement on the third cluster centers according to the numerical values, and determining the driving style of each third cluster center when the vehicle decelerates according to the arrangement result.
Wherein the average of the average longitudinal deceleration, the maximum longitudinal deceleration, the longitudinal deceleration standard deviation (all absolute values) can be calculated for the driving style of deceleration; and according to the average value from large to small, dividing the corresponding third cluster center into an aggressive type, a general type and a robust type according to the rule of the characteristic parameters.
For example, the present embodiment may input the driving style of the vehicle when the vehicle is steered into the steering system, and adjust the driving mode and/or the driving parameters by the steering system based on the driving style of the vehicle when the vehicle is steered; inputting the driving style of the vehicle during acceleration into a power system, and adjusting the driving mode and/or driving parameters through the power system based on the driving style of the vehicle during acceleration; and inputting the driving style of the vehicle during deceleration into a braking system, and adjusting the driving mode and/or the driving parameters through the braking system based on the driving style of the vehicle during deceleration.
In this embodiment, the determination result of the driving style may be used as an important basis for adaptive adjustment of the driving mode and/or driving parameters and related parameters of the power, brake, and steering system.
As shown in fig. 3, the driving style determining method of this embodiment may show that a kinematic segment is obtained according to vehicle driving data, and 8 feature parameters corresponding to a transverse driving style, 8 feature parameters corresponding to a longitudinal acceleration driving style, and 8 feature parameters corresponding to a longitudinal deceleration driving style are selected according to the kinematic segment; and respectively carrying out data dimension reduction processing and corresponding K-means clustering on the three types of characteristic parameters to determine each driving style type, and respectively inputting the corresponding driving styles into a steering system, a power system and a braking system, thereby realizing the self-adaptive adjustment of the driving mode and/or the driving parameters.
It should be emphasized that, in the embodiment, the timeliness and the long-term property of the classification result can be ensured by setting the driving style of three dimensions of steering, acceleration and deceleration, continuously accumulating new driving data along with the increase of the vehicle using time of the driver, and performing repeated iteration.
According to the embodiment, the parameters corresponding to the transverse driving style and the longitudinal driving style can be determined from the kinematic segments, and the kinematic segments are clustered by utilizing the principal component score matrix, so that the driving styles of the driver in different dimensions are determined, and the intellectualization and humanization of the judgment of the driving style of the vehicle are improved.
EXAMPLE III
Fig. 4 is a schematic structural diagram of a driving style determining apparatus according to a third embodiment of the present invention. As shown in fig. 4, the apparatus includes: a characteristic parameter obtaining module 401, a characteristic parameter dimension reducing module 402 and a driving style determining module 403;
the characteristic parameter acquiring module 401 is configured to acquire a kinematic segment according to vehicle driving data, and acquire a first characteristic parameter representing a transverse driving style and a second characteristic parameter representing a longitudinal driving style in the kinematic segment;
a feature parameter dimension reduction module 402, configured to perform dimension reduction processing on the first feature parameter and the second feature parameter, respectively, to obtain a plurality of principal component score matrices;
and the driving style determining module 403 is configured to cluster the kinematic segments according to each principal component score matrix to obtain a plurality of cluster centers, and determine the driving style of the driver when the vehicle turns, accelerates or decelerates according to the characteristic parameters corresponding to each cluster center.
Optionally, the feature parameter dimension reduction module 402 is specifically configured to:
performing dimensionality reduction processing on the first characteristic parameter by adopting a principal component analysis algorithm to obtain a first principal component score matrix;
performing dimensionality reduction processing on a second characteristic parameter for representing vehicle acceleration by adopting a principal component analysis algorithm to obtain a second principal component score matrix;
and performing dimensionality reduction on the second characteristic parameters for representing the vehicle deceleration by adopting a principal component analysis algorithm to obtain a third principal component score matrix.
Optionally, the feature parameter dimension reduction module 402 is specifically configured to:
determining the driving style of each first clustering center when the vehicle turns according to the numerical value of each first clustering center corresponding to the first principal component score matrix;
determining the number of the kinematic segments corresponding to each driving style when the vehicle volume turns according to the driving style of each first clustering center when the vehicle turns;
and determining the driving style of the driver during vehicle steering according to the ratio of the number of the kinematic segments corresponding to each driving style during vehicle steering to the number of the kinematic segments corresponding to the first clustering center.
Optionally, the feature parameter dimension reduction module 402 is specifically configured to:
determining the numerical value of each first clustering center according to the average transverse acceleration, the maximum transverse acceleration and the average value of the transverse acceleration standard deviation of each first clustering center corresponding to the first principal component score matrix;
and performing descending order arrangement on the first clustering centers according to the numerical values, and determining the driving style of each first clustering center when the vehicle turns according to an arrangement result.
Optionally, the feature parameter dimension reduction module 402 is specifically configured to:
determining the driving style of each second cluster center when the vehicle accelerates according to the numerical value of each second cluster center corresponding to the second principal component score matrix;
determining the number of the kinematic segments corresponding to each driving style when the vehicle accelerates according to the driving style of each second cluster center when the vehicle accelerates;
and determining the driving style of the driver when the vehicle accelerates according to the proportion of the number of the kinematic segments corresponding to each driving style when the vehicle accelerates in the number of the kinematic segments corresponding to the second clustering center.
Optionally, the feature parameter dimension reduction module 402 is specifically configured to:
determining the numerical value of each second clustering center according to the average longitudinal acceleration, the maximum longitudinal acceleration and the average value of the longitudinal acceleration standard deviation of each second clustering center corresponding to the second principal component scoring matrix;
and performing descending order arrangement on the second cluster centers according to the numerical values, and determining the driving style of each second cluster center when the vehicle accelerates according to an arrangement result.
Optionally, the feature parameter dimension reduction module 402 is specifically configured to:
determining the driving style of each third clustering center when the vehicle decelerates according to the numerical value of each third clustering center corresponding to the third principal component score matrix;
determining the number of the kinematic segments corresponding to each driving style when the vehicle decelerates according to the driving style of each third clustering center when the vehicle decelerates;
and determining the driving style of the driver during the deceleration of the vehicle according to the ratio of the number of the kinematic segments corresponding to each driving style during the deceleration of the vehicle to the number of the kinematic segments corresponding to the third clustering center.
Optionally, the feature parameter dimension reduction module 402 is specifically configured to:
determining the numerical value of each third clustering center according to the average longitudinal deceleration, the maximum longitudinal deceleration and the average value of the standard deviation of the longitudinal deceleration of each third clustering center corresponding to the third principal component scoring matrix;
and performing descending order arrangement on the third cluster centers according to the numerical values, and determining the driving style of each third cluster center when the vehicle decelerates according to the arrangement result.
Optionally, the apparatus further comprises:
the steering module is used for inputting the driving style of the vehicle during steering into a steering system, and adjusting the driving mode and/or driving parameters through the steering system based on the driving style of the vehicle during steering;
the power module is used for inputting the driving style of the accelerated vehicle into a power system, and adjusting the driving mode and/or driving parameters through the power system based on the driving style of the accelerated vehicle;
and the braking module is used for inputting the driving style of the vehicle during deceleration into a braking system, and adjusting the driving mode and/or the driving parameters through the braking system based on the driving style of the vehicle during deceleration.
The driving style determining device provided by the embodiment of the invention can execute the driving style determining method provided by any embodiment of the invention, and has corresponding functional modules and beneficial effects of the executing method.
Example four
FIG. 5 illustrates a schematic block diagram of a vehicle 10 that may be used to implement an embodiment of the present invention. The components shown herein, their connections and relationships, and their functions, are meant to be exemplary only, and are not meant to limit implementations of the inventions described and/or claimed herein.
As shown in fig. 5, the vehicle 10 includes at least one processor 11, and a memory communicatively connected to the at least one processor 11, such as a Read Only Memory (ROM) 12, a Random Access Memory (RAM) 13, and the like, wherein the memory stores a computer program executable by the at least one processor, and the processor 11 may perform various appropriate actions and processes according to the computer program stored in the Read Only Memory (ROM) 12 or the computer program loaded from a storage unit 18 into the Random Access Memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the vehicle 10 may also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other via a bus 14. An input/output (I/O) interface 15 is also connected to the bus 14.
Various components in the vehicle 10 are connected to the I/O interface 15, including: an input unit 16 such as a key and an in-vehicle sensor; the vehicle-mounted sensor is used for collecting vehicle running data. An output unit 17 such as various types of displays, speakers, and the like; a storage unit 18 such as a magnetic disk, an optical disk, or the like; and a communication unit 19 such as a network card, modem, wireless communication transceiver, etc. The communication unit 19 allows the vehicle 10 to exchange information/data with other devices via a computer network such as the internet and/or various telecommunication networks.
The processor 11 may be a variety of general and/or special purpose processing components having processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), various specialized Artificial Intelligence (AI) computing chips, various processors running machine learning model algorithms, a Digital Signal Processor (DSP), and any suitable processor, controller, microcontroller, or the like. The processor 11 performs the various methods and processes described above, such as a driving style determination method.
In some embodiments, a driving style determination method may be implemented as a computer program tangibly embodied in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and/or installed on the vehicle 10 via the ROM 12 and/or the communication unit 19. One or more steps of a driving style determination method described above may be performed when the computer program is loaded into RAM 13 and executed by processor 11. Alternatively, in other embodiments, the processor 11 may be configured to perform a driving style determination method by any other suitable means (e.g., by means of firmware).
Various implementations of the systems and techniques described here above may be implemented in digital electronic circuitry, integrated circuitry, field Programmable Gate Arrays (FPGAs), application Specific Integrated Circuits (ASICs), application Specific Standard Products (ASSPs), system on a chip (SOCs), complex Programmable Logic Devices (CPLDs), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs that are executable and/or interpretable on a programmable system including at least one programmable processor, which may be special or general purpose, receiving data and instructions from, and transmitting data and instructions to, a storage system, at least one input device, and at least one output device.
A computer program for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the computer programs, when executed by the processor, cause the functions/acts specified in the flowchart and/or block diagram block or blocks to be performed. A computer program can execute entirely on a machine, partly on a machine, as a stand-alone software package partly on a machine and partly on a remote machine or entirely on a remote machine or server.
In the context of the present invention, a computer-readable storage medium may be a tangible medium that can contain, or store a computer program for use by or in connection with an instruction execution system, apparatus, or device. A computer readable storage medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. Alternatively, the computer readable storage medium may be a machine readable signal medium. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
To provide for interaction with a user, the systems and techniques described herein may be implemented on a vehicle having: display means (e.g. a touch screen) for displaying information to a user; and buttons, which the user may provide input to the vehicle through the touch screen or buttons. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic, speech, or tactile input.
It should be understood that various forms of the flows shown above may be used, with steps reordered, added, or deleted. For example, the steps described in the present invention may be executed in parallel, sequentially, or in different orders, and are not limited herein as long as the desired result of the technical solution of the present invention can be achieved.
The above-described embodiments should not be construed as limiting the scope of the invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions may be made in accordance with design requirements and other factors. Any modification, equivalent replacement, and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (12)
1. A driving style determination method, characterized by comprising:
the method comprises the steps of obtaining a kinematic segment according to vehicle driving data, and obtaining a first characteristic parameter representing a transverse driving style and a second characteristic parameter representing a longitudinal driving style in the kinematic segment;
respectively carrying out dimensionality reduction processing on the first characteristic parameters and the second characteristic parameters to obtain a plurality of principal component score matrixes;
and clustering the kinematic segments according to each principal component score matrix to obtain a plurality of clustering centers, and determining the driving style of the driver respectively during steering, accelerating or decelerating of the vehicle according to the characteristic parameters corresponding to each clustering center.
2. The method according to claim 1, wherein performing dimension reduction processing on the first feature parameter and the second feature parameter respectively to obtain a plurality of principal component score matrices includes:
performing dimensionality reduction processing on the first characteristic parameter by adopting a principal component analysis algorithm to obtain a first principal component score matrix;
performing dimensionality reduction processing on a second characteristic parameter for representing vehicle acceleration by adopting a principal component analysis algorithm to obtain a second principal component score matrix;
and performing dimensionality reduction on the second characteristic parameters for representing the vehicle deceleration by adopting a principal component analysis algorithm to obtain a third principal component score matrix.
3. The method of claim 2, wherein determining the driving style of the driver when the vehicle turns according to the characteristic parameter corresponding to each cluster center comprises:
determining the driving style of each first clustering center when the vehicle turns according to the numerical value of each first clustering center corresponding to the first principal component score matrix;
determining the number of the kinematic segments corresponding to each driving style when the vehicle volume turns according to the driving style of each first clustering center when the vehicle turns;
and determining the driving style of the driver during vehicle steering according to the proportion of the number of the kinematic segments corresponding to each driving style during vehicle steering in the number of the kinematic segments corresponding to the first clustering center.
4. The method according to claim 3, wherein determining the driving style of each first cluster center in turning the vehicle according to the numerical value of each first cluster center corresponding to the first principal component score matrix comprises:
determining the numerical value of each first clustering center according to the average transverse acceleration, the maximum transverse acceleration and the average value of the transverse acceleration standard deviation of each first clustering center corresponding to the first principal component score matrix;
and performing descending order arrangement on the first clustering centers according to the numerical values, and determining the driving style of each first clustering center when the vehicle turns according to an arrangement result.
5. The method of claim 2, wherein determining the driving style of the driver when the vehicle accelerates according to the characteristic parameter corresponding to each cluster center comprises:
determining the driving style of each second clustering center when the vehicle accelerates according to the numerical value of each second clustering center corresponding to the second principal component score matrix;
determining the number of the kinematic segments corresponding to each driving style when the vehicle accelerates according to the driving style of each second cluster center when the vehicle accelerates;
and determining the driving style of the driver when the vehicle accelerates according to the ratio of the number of the kinematic segments corresponding to each driving style when the vehicle accelerates to the number of the kinematic segments corresponding to the second clustering center.
6. The method of claim 5, wherein determining the driving style of each second cluster center during vehicle acceleration according to the value of each second cluster center corresponding to the second principal component score matrix comprises:
determining the numerical value of each second clustering center according to the average longitudinal acceleration, the maximum longitudinal acceleration and the average value of the longitudinal acceleration standard deviation of each second clustering center corresponding to the second principal component scoring matrix;
and performing descending order on the second clustering centers according to the numerical values, and determining the driving style of each second clustering center when the vehicle accelerates according to an arrangement result.
7. The method according to claim 2, wherein determining the driving style of the driver when the vehicle decelerates according to the characteristic parameter corresponding to each cluster center comprises:
determining the driving style of each third clustering center when the vehicle decelerates according to the numerical value of each third clustering center corresponding to the third principal component score matrix;
determining the number of the kinematic segments corresponding to each driving style when the vehicle decelerates according to the driving style of each third clustering center when the vehicle decelerates;
and determining the driving style of the driver during the deceleration of the vehicle according to the ratio of the number of the kinematic segments corresponding to each driving style during the deceleration of the vehicle to the number of the kinematic segments corresponding to the third clustering center.
8. The method of claim 7, wherein determining the driving style of each third principal component score matrix during deceleration of the vehicle according to the value of each third principal component score matrix comprises:
determining the numerical value of each third clustering center according to the average longitudinal deceleration, the maximum longitudinal deceleration and the average value of the standard deviation of the longitudinal deceleration of each third clustering center corresponding to the third principal component scoring matrix;
and performing descending order on the third clustering centers according to the numerical values, and determining the driving style of each third clustering center when the vehicle decelerates according to an arrangement result.
9. The method of claim 1, further comprising:
inputting the driving style of the vehicle during steering into a steering system, and adjusting a driving mode and/or driving parameters through the steering system based on the driving style of the vehicle during steering;
inputting the driving style of the vehicle during acceleration into a power system, and adjusting the driving mode and/or driving parameters through the power system based on the driving style of the vehicle during acceleration;
and inputting the driving style of the vehicle during deceleration into a braking system, and adjusting the driving mode and/or the driving parameters through the braking system based on the driving style of the vehicle during deceleration.
10. A driving style determination apparatus, characterized by comprising:
the system comprises a characteristic parameter acquisition module, a data acquisition module and a data processing module, wherein the characteristic parameter acquisition module is used for acquiring a kinematic segment according to vehicle driving data, and acquiring a first characteristic parameter which represents a transverse driving style and a second characteristic parameter which represents a longitudinal driving style in the kinematic segment;
the characteristic parameter dimension reduction module is used for respectively carrying out dimension reduction processing on the first characteristic parameter and the second characteristic parameter to obtain a plurality of principal component score matrixes;
and the driving style determining module is used for clustering the kinematic segments according to each principal component score matrix to obtain a plurality of clustering centers, and determining the driving style of the driver respectively during steering, accelerating or decelerating of the vehicle according to the characteristic parameters corresponding to each clustering center.
11. A vehicle, characterized in that the vehicle comprises:
the vehicle-mounted sensor is used for collecting vehicle driving data;
at least one processor; and
a memory communicatively coupled to the at least one processor; wherein the content of the first and second substances,
the memory stores a computer program executable by the at least one processor to enable the at least one processor to perform the driving style determination method of any one of claims 1-9.
12. A computer-readable storage medium storing computer instructions for causing a processor to perform the driving style determination method of any one of claims 1-9 when executed.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211502917.2A CN115817500A (en) | 2022-11-28 | 2022-11-28 | Driving style determination method and device, vehicle and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211502917.2A CN115817500A (en) | 2022-11-28 | 2022-11-28 | Driving style determination method and device, vehicle and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115817500A true CN115817500A (en) | 2023-03-21 |
Family
ID=85532258
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211502917.2A Pending CN115817500A (en) | 2022-11-28 | 2022-11-28 | Driving style determination method and device, vehicle and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115817500A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116906561A (en) * | 2023-09-14 | 2023-10-20 | 北京理工大学 | Vehicle gear shifting point optimal control method and system based on short-time driving style identification |
| CN117184103A (en) * | 2023-11-08 | 2023-12-08 | 北京理工大学 | Driving style identification method, system and equipment |
| CN117584991A (en) * | 2024-01-17 | 2024-02-23 | 上海伯镭智能科技有限公司 | Mining area unmanned vehicle outside personnel safety protection method and system |
-
2022
- 2022-11-28 CN CN202211502917.2A patent/CN115817500A/en active Pending
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116906561A (en) * | 2023-09-14 | 2023-10-20 | 北京理工大学 | Vehicle gear shifting point optimal control method and system based on short-time driving style identification |
| CN116906561B (en) * | 2023-09-14 | 2023-12-08 | 北京理工大学 | Vehicle gear shifting point optimal control method and system based on short-time driving style identification |
| CN117184103A (en) * | 2023-11-08 | 2023-12-08 | 北京理工大学 | Driving style identification method, system and equipment |
| CN117184103B (en) * | 2023-11-08 | 2024-01-09 | 北京理工大学 | Driving style identification method, system and equipment |
| CN117584991A (en) * | 2024-01-17 | 2024-02-23 | 上海伯镭智能科技有限公司 | Mining area unmanned vehicle outside personnel safety protection method and system |
| CN117584991B (en) * | 2024-01-17 | 2024-03-22 | 上海伯镭智能科技有限公司 | Mining area unmanned vehicle outside personnel safety protection method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN115817500A (en) | Driving style determination method and device, vehicle and storage medium | |
| CN108108766B (en) | Driving behavior identification method and system based on multi-sensor data fusion | |
| KR100800367B1 (en) | Sensor based speech recognizer selection, adaptation and combination | |
| CN111267863B (en) | Driver driving type identification method and device, storage medium and terminal equipment | |
| CN111178452B (en) | Driving risk identification method, electronic device and readable storage medium | |
| CN109542081B (en) | Online driving danger estimation method based on offline vehicle deceleration curve | |
| CN108407814B (en) | Driver characteristic identification method | |
| CN110858312A (en) | Driver driving style classification method based on fuzzy C-means clustering algorithm | |
| CN111216736A (en) | Driving condition-based self-adaptive adjustment method and system for auxiliary driving system | |
| CN112529638B (en) | Service demand dynamic prediction method and system based on user classification and deep learning | |
| CN113239599A (en) | Intelligent tire wear life estimation method and device based on BP neural network | |
| CN113581188A (en) | Commercial vehicle driver driving style identification method based on Internet of vehicles data | |
| CN112966818A (en) | Directional guide model pruning method, system, equipment and storage medium | |
| CN115675099A (en) | Pure electric vehicle braking energy recovery method based on driver style recognition | |
| CN114897312A (en) | Driving behavior scoring method, device, equipment and storage medium | |
| CN111723206B (en) | Text classification method, apparatus, computer device and storage medium | |
| CN116380438A (en) | Fault diagnosis method and device, electronic equipment and storage medium | |
| CN115859667A (en) | Automobile cable loss prediction method and device based on neural network and storage medium | |
| CN114004143B (en) | Method and device for predicting tire life, terminal device and storage medium | |
| CN114822562A (en) | Training method of voiceprint recognition model, voiceprint recognition method and related equipment | |
| CN115736925A (en) | Monitoring operator fatigue | |
| US20220404161A1 (en) | System for generating guidance information | |
| CN114693088A (en) | Reservoir temperature field influence factor analysis method and device and storage medium | |
| Gao et al. | Driver identification based on stop-and-go events using naturalistic driving data | |
| CN116906561B (en) | Vehicle gear shifting point optimal control method and system based on short-time driving style identification |
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 |