CN118072290A

CN118072290A - Driving style recognition method, driving style recognition device, computer readable medium and electronic equipment

Info

Publication number: CN118072290A
Application number: CN202211485184.6A
Authority: CN
Inventors: 石田俊雄; 李晓波; 邓云飞; 刘学武
Original assignee: Guangzhou Automobile Group Co Ltd
Current assignee: Guangzhou Automobile Group Co Ltd
Priority date: 2022-11-24
Filing date: 2022-11-24
Publication date: 2024-05-24

Abstract

The application belongs to the technical field of vehicles, and particularly relates to a driving style identification method, a driving style identification device, a computer readable medium and electronic equipment. The method includes obtaining driving behavior data; determining corresponding driving conditions and the duty ratio of the driving conditions according to the driving behavior data, and calculating to obtain a first driving style value according to the driving conditions and the duty ratio of the driving conditions; inputting driving behavior data into a trained machine learning model to obtain a second driving style value; and carrying out fusion correction on the first driving style value and the second driving style value to obtain a final driving style result. According to the application, the first driving style value is obtained by determining different working conditions and the duty ratio of the different working conditions according to the driving behavior data, and then the first driving style value and the second driving style value obtained by machine learning analysis are subjected to fusion correction, so that the accuracy of the driving style result can be improved, and the output final driving style result meets the control requirement of a user.

Description

Driving style recognition method, driving style recognition device, computer readable medium and electronic equipment

Technical Field

The application belongs to the technical field of vehicles, and particularly relates to a driving style identification method, a driving style identification device, a computer readable medium and electronic equipment.

Background

The driving style is an overall evaluation index that characterizes the driving style inherent to the driver. The driving style study mainly divides drivers from the angles of energy-saving driving, traffic safety and the like. Existing researches show that the style of a driver is closely related to traffic safety: the aggressive driving style driver has bad driving behaviors such as frequent lane changing, rapid acceleration and deceleration, close-range following and the like, and the accident occurrence probability is easy to increase. Through driving style research, bad driving styles of daily driving of a driver are detected or fed back, supervision and education on driving behaviors of the driver can be realized, and corresponding measures are assisted to improve driving safety.

In the related technical scheme, the driving control logic of the vehicle is fixed, and cannot be adaptively adjusted according to the driving habit of the user, so that the control requirement of the user cannot be met.

It should be noted that the information disclosed in the above background section is only for enhancing understanding of the background of the application and thus may include information that does not form the prior art that is already known to those of ordinary skill in the art.

Disclosure of Invention

The application aims to provide a driving style identification method, a driving style identification device, a computer readable medium and electronic equipment, which meet the control requirements of users to a certain extent.

Other features and advantages of the application will be apparent from the following detailed description, or may be learned by the practice of the application.

According to an aspect of an embodiment of the present application, there is provided a driving style recognition method including:

Acquiring driving behavior data;

Determining a corresponding driving condition and the duty ratio of the driving condition according to the driving behavior data, and calculating to obtain a first driving style value according to the driving condition and the duty ratio of the driving condition;

Inputting the driving behavior data into a trained machine learning model to obtain a second driving style value;

And carrying out fusion correction on the first driving style value and the second driving style value to obtain a final driving style result.

According to an aspect of an embodiment of the present application, there is provided a driving style recognition apparatus including:

The acquisition module is used for acquiring driving behavior data;

The first analysis module is used for determining corresponding driving conditions and the duty ratio of the driving conditions according to the driving behavior data, and calculating to obtain a first driving style value according to the driving conditions and the duty ratio of the driving conditions;

The second analysis module is used for inputting the driving behavior data into a trained machine learning model to obtain a second driving style value;

And the fusion module is used for carrying out fusion correction on the first driving style value and the second driving style value to obtain a final driving style result.

In some embodiments of the present application, based on the above technical solution, the first analysis module is further configured to analyze the driving behavior data to obtain at least one working condition of a driving road working condition, a driving behavior working condition, and a driving manipulation event working condition; calculating the duty ratio of the driving road working condition, the driving behavior working condition and the driving control event working condition; and calculating to obtain the first driving style value according to the driving road working condition, the driving behavior working condition, the driving control event working condition and the corresponding duty ratio of each working condition.

In some embodiments of the present application, based on the above technical solution, the first analysis module is further configured to obtain a vehicle speed, an acceleration, and a braking frequency in the driving behavior data; determining a low-speed driving road and a high-speed driving road according to the relation between the vehicle speed and a set speed threshold value; and respectively determining road congestion working conditions corresponding to the low-speed driving road and the high-speed driving road according to the acceleration and the braking frequency so as to obtain the driving road working conditions.

In some embodiments of the present application, based on the above technical solution, the first analysis module is further configured to obtain control behavior data in the driving behavior data; and determining driving behavior working conditions corresponding to the control behaviors according to the control behavior data.

In some embodiments of the present application, based on the above technical solution, the first analysis module is further configured to obtain control event data in the driving behavior data; and determining driving control event working conditions corresponding to the control events according to the control event data.

In some embodiments of the present application, based on the above technical solution, the first analysis module is further configured to obtain a first correction coefficient corresponding to the driving road condition, a second correction coefficient corresponding to the driving behavior condition, and a third correction coefficient corresponding to the driving manipulation event condition; accumulating the product of the duty ratio of the driving road working condition and the first correction coefficient, the product of the duty ratio of the driving behavior working condition and the second correction coefficient and the product of the duty ratio of the driving control event working condition and the third correction coefficient to obtain driving style parameters; counting the duty ratio of each driving style parameter in a set time period; and multiplying the duty ratio of each driving style parameter by a set driving style coefficient, and accumulating to obtain a first driving style value.

In some embodiments of the present application, based on the above technical solution, the first analysis module is further configured to decompose the driving behavior condition, and determine a plurality of sub-behavior conditions corresponding to the driving behavior condition; calculating the duty ratio of a plurality of sub-behavior working conditions; multiplying the duty ratios of the sub-behavior working conditions with the corresponding set correction coefficients respectively and accumulating to obtain the second correction coefficient.

In some embodiments of the present application, based on the above technical solution, the first analysis module is further configured to decompose the driving manipulation event working condition, and determine a plurality of sub-event working conditions corresponding to the driving manipulation event working condition; calculating the duty ratio of the working conditions of a plurality of sub-events; multiplying the duty ratios of the sub-event working conditions with the corresponding set correction coefficients respectively and accumulating to obtain the third correction coefficient.

In some embodiments of the present application, based on the above technical solution, the fusion module is further configured to calculate, according to the first driving style value and the second driving style value, an accuracy of a driving style; and if the accuracy reaches the set threshold, correcting the driving style value in each period, and taking the corrected driving style value as a final driving style result.

In some embodiments of the present application, based on the above technical solution, the fusion module is further configured to obtain a first driving style value and a second driving style value corresponding to each period; correcting the first driving style value by a first setting coefficient, and correcting the second driving style value by a second setting coefficient; and accumulating and averaging the correction result of the first driving style value and the correction result of the second driving style value to obtain the driving style value of each period.

In some embodiments of the present application, based on the above technical solutions, the fusion module is further configured to count a duty ratio of each driving style value in a set time period; and multiplying the duty ratio of each driving style value by a set driving style coefficient, and accumulating to obtain a final driving style value.

In some embodiments of the present application, based on the above technical solution, the apparatus further includes a mapping module, configured to map the final driving style value with the driving road condition, the driving behavior condition, and the driving manipulation event condition, to obtain a driving style mapping table.

According to an aspect of the embodiments of the present application, there is provided a computer-readable medium having stored thereon a computer program which, when executed by a processor, implements a driving style recognition method as in the above technical solution.

According to an aspect of an embodiment of the present application, there is provided an electronic apparatus including: a processor; and a memory for storing executable instructions of the processor; wherein the processor is configured to perform the driving style recognition method as in the above technical solution via execution of the executable instructions.

According to an aspect of embodiments of the present application, there is provided a computer program product or computer program comprising computer instructions stored in a computer readable storage medium. The processor of the computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions so that the computer device performs the driving style recognition method as in the above technical solution.

In the technical scheme provided by the embodiment of the application, the corresponding driving working condition and the duty ratio of the driving working condition are determined according to the driving behavior data, and the first driving style value is obtained by calculation according to the driving working condition and the duty ratio of the driving working condition; then, driving behavior data are input into a trained machine learning model to obtain a second driving style value; and finally, carrying out fusion correction on the first driving style value and the second driving style, so that a final driving style result can be determined. In other words, the embodiment of the application considers that the driving styles under different scenes of different road conditions have differences, so that the first driving style value is obtained by determining the driving behavior data according to different working conditions and the duty ratio of the different working conditions, and then the first driving style value and the second driving style value obtained by machine learning analysis are fused and corrected, thereby improving the accuracy of the driving style result and enabling the output final driving style result to more meet the control requirement of a user.

It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the application as claimed.

Drawings

The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the application and together with the description, serve to explain the principles of the application. It is evident that the drawings in the following description are only some embodiments of the present application and that other drawings may be obtained from these drawings without inventive effort for a person of ordinary skill in the art.

Fig. 1 schematically shows a flow of steps of a driving style recognition method according to an embodiment of the present application.

Fig. 2 schematically shows a flow of steps for calculating a first driving style value from driving conditions and a duty cycle of the driving conditions.

Fig. 3 schematically shows a flow of steps for calculating a first driving style value according to driving road conditions, driving behavior conditions, driving control event conditions and corresponding duty ratios of the respective conditions.

Fig. 4 schematically illustrates driving condition and sub-condition recognition according to an embodiment of the present application.

Fig. 5 schematically illustrates driving event and sub-event recognition according to an embodiment of the present application.

Fig. 6 schematically illustrates a clustering algorithm provided by an embodiment of the present application.

Fig. 7 schematically shows a flow of steps of a driving style recognition method according to an embodiment of the present application.

Fig. 8 schematically illustrates a driving style analysis algorithm deployment diagram according to an embodiment of the present application.

Fig. 9 schematically shows a block diagram of a driving style recognition device provided by an embodiment of the present application.

Fig. 10 schematically shows a block diagram of a computer system suitable for use in implementing embodiments of the application.

Detailed Description

Example embodiments will now be described more fully with reference to the accompanying drawings. However, the exemplary embodiments may be embodied in many forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the concept of the example embodiments to those skilled in the art.

Furthermore, the described features, structures, or characteristics may be combined in any suitable manner in one or more embodiments. In the following description, numerous specific details are provided to give a thorough understanding of embodiments of the application. One skilled in the relevant art will recognize, however, that the application may be practiced without one or more of the specific details, or with other methods, components, devices, steps, etc. In other instances, well-known methods, devices, implementations, or operations are not shown or described in detail to avoid obscuring aspects of the application.

The block diagrams depicted in the figures are merely functional entities and do not necessarily correspond to physically separate entities. That is, the functional entities may be implemented in software, or in one or more hardware modules or integrated circuits, or in different networks and/or processor devices and/or microcontroller devices.

The flow diagrams depicted in the figures are exemplary only, and do not necessarily include all of the elements and operations/steps, nor must they be performed in the order described. For example, some operations/steps may be decomposed, and some operations/steps may be combined or partially combined, so that the order of actual execution may be changed according to actual situations.

The driving style recognition method, the driving style recognition device, the computer readable medium and the electronic equipment provided by the application are described in detail below with reference to the specific embodiments.

Referring to fig. 1, fig. 1 schematically shows a step flow of a driving style recognition method according to an embodiment of the present application. The driving style recognition method may be performed by a controller, and may mainly include steps S101 to S104 as follows.

Step S101, driving behavior data is acquired.

In step S101, driving behavior data may be acquired from a server or a database. The driving behavior data may include, for example, vehicle speed, acceleration, braking frequency, and other data related to driving behavior. Therefore, the driving behavior data are acquired, so that the road condition and the driving style conditions corresponding to different road conditions can be obtained through analysis.

Step S102, determining corresponding driving conditions and the duty ratio of the driving conditions according to the driving behavior data, and calculating to obtain a first driving style value according to the driving conditions and the duty ratio of the driving conditions.

After the driving behavior data is obtained, the driving behavior data is analyzed to determine the corresponding driving conditions and the corresponding duty ratio of the driving conditions in the whole driving time period. For example, the speed and the acceleration in the driving behavior data may be used to determine whether the road on which the vehicle is traveling is a low-speed road condition or a high-speed road condition, and thus the driving road condition may be obtained. After determining whether the driving road is under the low-speed road condition or the high-speed road condition, the ratio of the low-speed road condition to the whole time period is further determined, for example, the ratio of the low-speed road condition to the high-speed road condition is 20%, and the ratio of the high-speed road condition to the low-speed road condition is 80%. The driving conditions may include driving behavior conditions and driving control event conditions besides driving road conditions, the driving behavior conditions may include starting conditions, accelerating conditions, rapid acceleration conditions, steady-state driving conditions, decelerating conditions, rapid deceleration conditions, sliding conditions, and the like, and the driving control event conditions may include over-bending events, overtaking/lane changing events, following vehicles, and the like. By analyzing the driving behavior data, a plurality of driving conditions and corresponding duty ratios of the driving conditions can be determined. And finally, calculating to obtain a first driving style value according to the driving condition and the duty ratio of the driving condition so as to obtain driving styles under different scenes of different road conditions.

Therefore, based on the analysis of the running condition of the whole vehicle, the control behavior of the user on the vehicle, the proportion of the event and the preference are analyzed in a targeted manner, so that the accurate driving style under different road conditions is obtained.

Step S103, driving behavior data are input into the trained machine learning model, and a second driving style value is obtained.

After the driving behavior data is obtained, the driving behavior data can be directly input into a trained machine learning model, and a driving style data classification result based on machine learning can be obtained, namely, a second driving style value can be obtained.

And step S104, carrying out fusion correction on the first driving style value and the second driving style value to obtain a final driving style result.

And after the first driving style value and the second driving style value are obtained, carrying out fusion correction on the first driving style value and the second driving style value to obtain a final driving style result. Compared with the scheme that the driving behavior data is analyzed only through machine learning to obtain the driving style result, the driving style result obtained through machine learning is more accurate because the driving behavior data of the user are comprehensively considered, namely, the driving style difference in different scenes of different road conditions is considered, the driving behavior data are analyzed to obtain the first driving style value, the second driving style value is obtained through machine learning, and finally the first driving style value and the second driving style value are subjected to fusion correction.

In one embodiment of the present application, referring to fig. 2, fig. 2 schematically illustrates a flow of steps for calculating a first driving style value based on a driving condition and a duty cycle of the driving condition. According to the driving behavior data, determining the corresponding driving working condition and the duty ratio of the driving working condition, and calculating to obtain the first driving style value according to the driving working condition and the duty ratio of the driving working condition, the method mainly comprises the following steps S201 to S203.

Step S201, analyzing the driving behavior data to obtain at least one of a driving road condition, a driving behavior condition and a driving manipulation event condition.

After the driving behavior data is obtained, the driving behavior data is analyzed to determine the corresponding driving conditions. For example, the speed and the acceleration in the driving behavior data may be used to determine whether the road on which the vehicle is traveling is a low-speed road condition or a high-speed road condition, and thus the driving road condition may be obtained. The low-speed road condition may be, for example, a city road segment, and the high-speed road condition may include, for example, a national road or a high-speed road segment. The driving working conditions comprise driving behavior working conditions and driving control event working conditions besides driving road working conditions, wherein the driving behavior working conditions comprise starting working conditions, accelerating working conditions, rapid accelerating working conditions, steady-state driving working conditions, decelerating working conditions, rapid decelerating working conditions, sliding working conditions and the like, and the driving control event working conditions comprise passing-over events, overtaking/lane changing events, following and the like.

Step S202, calculating the duty ratio of the driving road working condition, the driving behavior working condition and the driving control event working condition.

After the driving behavior data are analyzed to obtain each working condition, the duty ratio of each working condition in the whole driving time period needs to be calculated, so that the driving style under different working conditions is determined. For example, after determining that the road being traveled is a low-speed road condition or a high-speed road condition, a further determination is made as to how much of the low-speed road condition occupies the entire time period, e.g., 20% for the low-speed road condition and 80% for the high-speed road condition. Likewise, the driving behavior conditions and the driving control event conditions are treated similarly, and are not described in detail herein. Therefore, based on the analysis of the running condition of the whole vehicle, the control behavior of the user on the vehicle, the proportion of the event and the preference are analyzed in a targeted manner, so that the accurate driving style under different road conditions is obtained.

Step S203, a first driving style value is calculated according to the driving road working condition, the driving behavior working condition, the driving control event working condition and the corresponding duty ratio of each working condition.

By analyzing the driving behavior data, a plurality of driving conditions and corresponding duty ratios of the driving conditions can be determined. And finally, calculating to obtain a first driving style value according to the driving condition and the duty ratio of the driving condition so as to obtain driving styles under different scenes of different road conditions.

In this way, at least one working condition of driving road working conditions, driving behavior working conditions and driving control event working conditions is obtained by analyzing the driving behavior data, and the duty ratio of each working condition is calculated so as to analyze and obtain driving styles under different road conditions and different scenes, thereby being beneficial to accurately analyzing and obtaining a final driving style result.

In one embodiment of the present application, analyzing driving behavior data to obtain driving road conditions includes:

acquiring the speed, acceleration and braking frequency of the driving behavior data;

Determining a low-speed driving road and a high-speed driving road according to the relation between the vehicle speed and the set speed threshold value;

and respectively determining road congestion working conditions corresponding to the low-speed driving road and the high-speed driving road according to the acceleration and the braking frequency so as to obtain driving road working conditions.

When the driving road working condition is obtained, specifically, the road driving working condition is analyzed by combining signals such as the vehicle speed, the acceleration, the braking frequency and the like, and the low-speed driving road and the high-speed driving road are obtained.

The working condition of the low-speed driving road meets the following conditions: { v _max≤V_low、v_ave≤V_lowave, }; specifically, the maximum vehicle speed V _max for low speed conditions is below a set threshold V _low, such as V _max < 80, and the average vehicle speed V _ave is less than or equal to a defined low speed condition threshold V _lowave, such as V _ave < 60.

For highway driving conditions, highway driving conditions satisfy: { V _low＜v_max、V_lowave＜v_ave, … }; i.e. the maximum vehicle speed V _max for high speed operation is higher than the set threshold V _low, while the average vehicle speed V _ave is greater than the defined threshold V _lowave for low speed operation.

After the working conditions of the low-speed driving road and the high-speed driving road are determined, the road running working conditions are analyzed by combining signals such as vehicle speed, braking and acceleration to obtain the road smooth working conditions and the road congestion working conditions, and the data of the vehicle in the road congestion working conditions are removed without data analysis.

Road unobstructed condition: { F _brk＜F_jam、A_jam＜a_ave, … }, i.e. the braking frequency F _brk when the road is clear is less than the set congestion threshold F _jam, and the acceleration a _ave when the road is clear is greater than the set congestion threshold a _jam.

Road congestion conditions: { F _jam≤f_jambrk、a_ave≤A_jam, … }, namely, the braking frequency F _jambrk during congestion is more than or equal to the set congestion threshold value F _jam, and the acceleration a _ave during road unblocking is less than or equal to the set congestion threshold value A _jam.

And analyzing the road running working conditions by combining signals such as vehicle speed, braking, acceleration and the like to obtain road smooth working conditions and road congestion working conditions, removing data of the vehicle in the road congestion working conditions, and not analyzing the data.

Therefore, the driving behavior data are analyzed, so that the specific condition of the driving road working condition can be obtained.

In one embodiment of the present application, the driving behavior data is analyzed to obtain driving behavior conditions, including:

acquiring control behavior data in driving behavior data;

and determining driving behavior working conditions corresponding to the control behaviors according to the control behavior data.

The driving behavior working conditions comprise a starting working condition, an accelerating working condition, a sudden acceleration working condition, a steady-state driving working condition, a decelerating working condition, a sudden deceleration working condition, a sliding working condition and the like. And (3) carrying out comprehensive control behavior analysis by combining signals such as an accelerator pedal, braking, acceleration, vehicle speed, rotating speed, torque and the like and the front and rear vehicle states so as to obtain driving behavior working conditions corresponding to the control behavior data.

If the control behavior data in the driving behavior data meets the following conditions corresponding to the various working conditions, the driving behavior data can be determined to be the driving behavior working condition corresponding to the control behavior data.

For example, start-up conditions: { v _before≤V_launch、a_before≤A_launch、accpedal≥accpedal_launch, … }; i.e., the previous vehicle speed V _before is below the start speed threshold V _launch, the previous acceleration a _before is below the start acceleration threshold a _launch, the accelerator pedal opening accpedal is above the start pedal threshold accpedal _launch, etc.

Acceleration conditions: { v _before＞V_launch、accpedal≥accpedal_acc、t_acc≥T_acc, }; i.e., the previous vehicle speed V _before is higher than the start speed threshold V _launch, the accelerator pedal opening accpedal is higher than the accelerator pedal threshold accpedal _acc, the acceleration time T _acc is higher than the acceleration time threshold T _acc, etc.

Sudden acceleration condition: { v _before＞V_launch、accpedal≥accpedal_urgacc、t_acc≥T_acc, }; i.e., the previous vehicle speed V _before is higher than the start speed threshold V _launch, the accelerator pedal opening accpedal is higher than the quick pedal threshold accpedal _urgacc, the acceleration time T _acc is higher than the acceleration time threshold T _acc, etc.

The steady-state running condition ：{Δv＜ΔV_sta、accpedal＜accpedal_acc、Δaccpedal＜Δaccpedal_sta、t_sta≥T_sta,...}; is that the vehicle speed change rate Deltav is lower than the vehicle speed change rate threshold DeltaV _sta, the accelerator pedal opening accpedal is higher than the accelerator pedal threshold accpedal _acc, the accelerator pedal change rate Delta accpedal is lower than the change rate threshold Delta accpedal _sta, the steady-state running time T _sta is greater than the set steady-state running time threshold T _sta, and the like. It should be noted that only a part of the data is listed here, and those skilled in the art can obtain the data in the driving behavior data according to actual needs to analyze and obtain each driving condition.

Therefore, through analyzing the driving behavior data, if the data in the driving behavior data meet the conditions corresponding to the working conditions, the corresponding driving behavior working conditions can be determined.

In one embodiment of the present application, analyzing driving behavior data to obtain driving control event conditions includes:

acquiring control event data in driving behavior data;

and determining driving control event working conditions corresponding to the control events according to the control event data.

The driving maneuver event analysis includes a turn-over event, a cut-in/lane change event, a follow-up, etc. And carrying out control behavior analysis by combining signals such as an accelerator pedal, braking, acceleration, vehicle speed, rotating speed, torque and the like. If the control event data in the driving behavior data satisfies the following conditions corresponding to the respective working conditions, the driving behavior working condition corresponding to the control event data may be determined.

For example, an over-bend event: { θ _cor≥Θ_cor、v_cor≥V_cor、t_cor≥T_cor, }; i.e. the over-bending angle theta _cor is higher than the set angle threshold theta _cor, the over-bending speed V _cor is higher than the set over-bending speed threshold V _cor, the over-bending time T _cor is higher than the set time threshold T _cor, etc.

Overtaking/lane change event: { Θ _over≤θ_over＜Θ_cor、v_over≥V_over、t_acc≥T_acc, … }; that is, the overtaking angle θ _over is within the set section range, the overtaking speed V _over is higher than the set overtaking speed threshold V _over, the acceleration time T _acc is higher than the acceleration time threshold T _acc, and the like. . It should be noted that only a part of the data is listed here, and a person skilled in the art may obtain the data in the driving behavior data according to actual needs to analyze and obtain the working condition of each driving control event.

Therefore, by analyzing the driving behavior data, if the data in the driving behavior data meet the conditions corresponding to the working conditions of each event, the specific situation of the working conditions of the driving control event can be obtained.

In one embodiment of the present application, referring to fig. 3, fig. 3 schematically illustrates a step flow of calculating a first driving style value according to a driving road condition, a driving behavior condition, a driving manipulation event condition, and a corresponding duty ratio of each condition. According to the driving road working condition, the driving behavior working condition, the driving control event working condition and the corresponding duty ratio of each working condition, the first driving style value is calculated, and the method mainly comprises the following steps S301 to S304.

Step S301, obtaining a first correction coefficient corresponding to a driving road condition, a second correction coefficient corresponding to a driving behavior condition, and a third correction coefficient corresponding to a driving manipulation event condition.

Different working conditions are corrected corresponding to different correction coefficients, so that the control behavior and the control event of the vehicle by the user are fully obtained, and the preference of the control behavior and the control event of the user is obtained. The first correction coefficient can be preset, and the second correction coefficient and the third correction coefficient can be determined through sub-working conditions corresponding to the working conditions.

Step S302, the product of the duty ratio of the driving road working condition and the first correction coefficient, the product of the duty ratio of the driving behavior working condition and the second correction coefficient and the product of the duty ratio of the driving control event working condition and the third correction coefficient are accumulated to obtain driving style parameters.

For example, road driving condition duty ratio: { f _low、f_high };

road driving condition coefficient: { a _low、a_high };

Driving control behavior ratio under low-speed working condition: { f _launchlow、f_acclow、f_urgacclow、f_stalow, … };

driving control behavior coefficient under low-speed working condition: { a _launchlow、a_acclow、a_urgacclow、a_stalow, … };

driving control behavior ratio under high-speed working condition: { f _launchhigh、f_acchigh、f_urgacchigh、f_stahigh, … };

driving control behavior coefficient under high-speed working condition: { a _launchlow、a_acclow、a_urgacclow、a_stalow, … };

driving control event duty ratio under low speed working condition: { f _corlow、f_overlow, … };

driving control event coefficient under low speed working condition: { a _corlow、a_overlow, … };

Driving control event duty ratio under high-speed working condition: { f _corhigh、f_overhigh, … };

Driving control event coefficient under high-speed working condition: { a _corhigh、a_overhigh, … };

Low speed operating mode driving style coefficient:

x_low＝(a_launchlow*f_launchlow+a_acclow*f_acclow+a_urgacclow*f_urgacclow+a_stalow*f_stalow+…)+(a_corlow*f_corlow+a_overlow*f_overlow+…);

high speed operating mode driving style coefficient:

x_high＝(a_launchhigh*f_launchhigh+a_acchigh*f_acchigh+a_urgacchigh*f_urgacchigh+a_stahigh*f_stahigh+…)+(a_corhigh*f_corhigh+a_ovorhigh*f_overhigh+…);

Comprehensive driving style: x _i＝a_low*x_low+a_higgh*x_higgh. Driving style during driving cycle: { x ₁、x₂、x₃、x₄、x₅...、x_n }.

Step S303, the duty ratio of each driving style parameter in the set time period is counted.

According to signals such as different road conditions and congestion conditions, relevant data preprocessing is carried out, the driving operation and control action proportion, the driving operation and control event proportion, the driving operation and control action and event habit proportion under the road conditions are analyzed, the driving style analysis result based on the driving operation and control analysis under the road conditions is comprehensively obtained, and then the driving styles under various road conditions are counted to obtain the final driving style analysis result based on the driving operation and control analysis.

The duty ratio of each driving style in the driving period: { a ₁、a₂、a₃、a₄、a₅ }, where a ₁、a₂、a₃、a₄、a₅ represents the duty cycle of each driving style over the entire driving time period, respectively.

Step S304, the duty ratio of each driving style parameter is multiplied by the set driving style coefficient, and the first driving style value is obtained through accumulation.

Total driving style: Where i represents a driving style coefficient corresponding to various driving styles, for example, i=1, i=2, i=3 represents that the driving style is aggressive, i=4 represents that the driving style is aggressive, and i=5 represents that the driving style is aggressive. The total driving style can be determined by counting the duty ratio of each driving style in the driving period and the corresponding driving style coefficient.

For the convenience of understanding the technical solution of the embodiment of the present application, for example, the user opens an hour, and the driving style is analyzed every 10 minutes, and then 6 times. Firstly, respectively calculating the style within each 10 minutes, and assuming that each driving style in the driving period is as follows: { x ₁、x₂、x₃、x₄、x₅、x₆ }, the duty cycle of each driving style is calculated again, for example, 6 styles are found within one hour, 3 times 10 minutes are mild, 2 times 10 minutes are aggressive, and 10 minutes are normal, so that the mild duty cycle is 3/6, the aggressive duty cycle is 2/6, and the normal duty cycle is 1/6. And finally, multiplying the duty ratio of each driving style parameter by a set driving style coefficient, and accumulating to obtain a first driving style value.

In one embodiment of the present application, the second correction coefficient corresponding to the driving behavior condition includes:

Decomposing the driving behavior working conditions, and determining a plurality of sub-behavior working conditions corresponding to the driving behavior working conditions;

calculating the duty ratio of a plurality of sub-behavior working conditions;

Multiplying the duty ratios of the sub-behavior conditions with the corresponding set correction coefficients respectively and accumulating the multiplied duty ratios to obtain a second correction coefficient.

After the starting working condition, the accelerating working condition, the rapid accelerating working condition, the steady-state driving working condition, the decelerating working condition, the rapid decelerating working condition, the sliding working condition and the like are identified and analyzed. The working conditions are required to be further analyzed, several typical sub-working conditions of the working conditions are defined in the algorithm model, and the sub-working conditions are defined as sub-working conditions when the sub-working condition boundary threshold requirements are met by combining the characteristic parameters. The starting working conditions are exemplified, and characteristic parameters such as accelerator pedal position and change rate, brake pedal position and exit time, starting vehicle speed and the like are combined, so that the starting working conditions are analyzed, different types of sub-working conditions and driving styles are also closely related, and the duty ratio and correction coefficient of the sub-working conditions have decisive effect on driving style identification.

Referring to fig. 4, fig. 4 schematically illustrates a driving condition and sub-condition recognition schematic provided by an embodiment of the present application. Taking a starting working condition as an example, the starting working condition corresponds to 4 starting sub-working conditions, and the 4 starting sub-working conditions have the following proportion: { f _launch1、f_launch2、f_launch3、f_launch4 }; and the set correction coefficients corresponding to the 4 starting sub-working conditions are as follows: { a _launch1、a_launch2、a_launch3、a_launch4 }; the overall starting condition coefficient can be obtained as:

the identification of other working conditions is consistent with the identification of starting working conditions, and is not repeated here.

In one embodiment of the present application, the third correction factor corresponding to the driving maneuver event condition includes:

Decomposing the driving control event working condition, and determining a plurality of sub-event working conditions corresponding to the driving control event working condition;

Calculating the duty ratio of the working conditions of a plurality of sub-events;

Multiplying the duty ratios of the sub-event working conditions with the corresponding set correction coefficients respectively and accumulating to obtain a third correction coefficient.

The driving maneuver event analysis includes a turn-over event, a cut-in/lane change event, a follow-up, etc. And carrying out control behavior analysis by combining signals such as an accelerator pedal, braking, acceleration, vehicle speed, rotating speed, torque and the like. Further analysis of each event is required, and several typical sub-events of each working condition are defined in the algorithm model, and the sub-events are defined as sub-events when the sub-event boundary threshold requirements are met by combining the characteristic parameters. The lane change event is exemplified, and the characteristic parameters such as steering angle, steering speed, transverse acceleration, vehicle speed, accelerator pedal and the like are combined to analyze which sub-event in the lane change event is changed, so that different types of sub-events and driving styles are also closely related, and the duty ratio and correction coefficient of the sub-events have decisive effect on driving style identification.

Referring to fig. 5, fig. 5 schematically illustrates a driving event and sub-event recognition schematic diagram according to an embodiment of the present application. Taking a lane change event as an example, the lane change event corresponds to 3 lane change sub-events, and the 3 lane change sub-events have the following proportion: { f _over1、f_over2、f_over3 }; correction coefficients corresponding to 3 lane change sub-events: { a _over1、a_over2、a_over3 }; the overall lane change event coefficients may be obtained as:

The identification of other events is consistent with the identification of lane change events, and will not be described in detail herein.

In one embodiment of the present application, performing fusion correction on the first driving style value and the second driving style value to obtain a final driving style result, including:

according to the first driving style value and the second driving style value, calculating to obtain the accuracy of the driving style;

and if the accuracy reaches the set threshold, correcting the driving style value in each period, and taking the corrected driving style value as a final driving style result.

After the first driving style value and the second driving style value are obtained, when the driving style analysis result based on driving control analysis and the driving style analysis result based on machine learning are corrected, firstly, the accuracy delta of the driving styles of the data pieces obtained by the two driving style calculation methods is calculated, and whether the driving style calculation needs to be carried out again is judged according to whether the value of delta reaches a threshold value or not. If the value of delta reaches the threshold value, correcting to obtain the driving style and the total driving style of each data sheet, and forming a mapping relation table of the driving style and the driving working condition.

Therefore, the accuracy of the first driving style value and the second driving style value is calculated, so that more accurate driving style values can be obtained, and then correction and fusion are carried out based on the more accurate driving style values, so that more accurate final driving style results can be obtained.

In one embodiment of the present application, correcting the driving style value in each period includes:

and acquiring a first driving style value and a second driving style value corresponding to each period.

The first driving style value corresponding to each period is obtained through calculation in the mode. While referring to fig. 6, fig. 6 schematically illustrates a clustering algorithm provided in an embodiment of the present application when calculating the second driving style value. And (3) performing machine learning of driving style based on the maximum value, the minimum value, the average value, the root mean square, the variance and the standard deviation of various signals (such as vehicle speed, transverse acceleration, longitudinal acceleration, an accelerator pedal, a brake pedal, steering wheel rotation angle, vehicle power and the like) of the whole vehicle, performing correlation analysis of characteristic parameters before performing machine learning, and eliminating the characteristic parameters with the correlation coefficient larger than 0.8.

Wherein, the calculation formula of the correlation parameter is: n represents the number of features in each sample point, i represents each feature constituting point x, x _i、y_i represents a sample point,/> Representing the centroid in the cluster.

And carrying out principal component analysis on the extracted characteristic parameters, and carrying out dimension reduction treatment on the data set. And then calculating the data set based on a Kmeans clustering algorithm to obtain a driving style data classification result based on machine learning.

Driving style during driving cycle: { y ₁、y₂、y₃、y₄、y₅…、y_n };

the duty ratio of each driving style in the driving period: { b ₁、b₂、b₃、b₄、b₅ };

Total driving style:

The first driving style value is corrected by the first setting coefficient, and the second driving style value is corrected by the second setting coefficient.

Driving style of each data sheet in driving period: Wherein c _i is a first set coefficient, x _i is a first driving style value, d _i is a second set coefficient, and y _i is a second driving style value.

And accumulating and averaging the correction result of the first driving style value and the correction result of the second driving style value to obtain the driving style value of each period.

In this way, the most accurate driving style classification is finally output by performing algorithm correction by combining driving style analysis based on user driving manipulation analysis and driving style analysis based on machine learning.

In one embodiment of the application, taking the corrected driving style value as the final driving style result comprises:

counting the duty ratio of each driving style value in a set time period;

and multiplying the duty ratio of each driving style value by a set driving style coefficient, and accumulating to obtain a final driving style value.

Assume that each driving style duty ratio in the driving cycle: { e ₁、e₂、e₃、e₄、e₅ };

then the final overall driving style is obtained:

in this way, the duty ratio of each driving style value in the set time period is counted, then the duty ratio of each driving style value is multiplied by the set driving style coefficient, and the final driving style value is obtained through accumulation.

In one embodiment of the application, the method further comprises:

And mapping the final driving style value with the driving road working condition, the driving behavior working condition and the driving control event working condition to obtain a driving style mapping table.

The driving style mapping table is referred to in the following table, and the driving style can be mapped with road working conditions, driving events, driving scenes and the like to form a full-scene full-working-condition driving style mapping table, which is used for representing the driving style and the control preference of a user in a specific scene and under a specific working condition, the longer the use time of the user vehicle, the more complete the driving style mapping table, and when the vehicle recognizes the current scene or working condition, the control logic of the controller adjusts according to the driving style of the user.

/>

In this way, the full-scene full-working condition driving style mapping table is used for representing the driving style and the control preference of the user under the specific scene and the specific working condition, the longer the user vehicle use time is, the more complete the driving style mapping table is, and when the vehicle recognizes the current scene or working condition, the control logic of the controller adjusts according to the driving style of the user. When the user drives, the control logic is executed according to the driving style and the control preference of the user. And when the driver is automatically driven, driving control is carried out according to the current scene, the driving style and the control preference of the user, so that the automatic driving personification is realized.

In one embodiment of the present application, referring to fig. 7, fig. 7 schematically illustrates a step flow of a driving style recognition method provided in one embodiment of the present application. The driving style identification method comprises the following steps:

step S701, road information analysis, including road driving condition analysis and road congestion analysis.

Step S702, driving manipulation behavior analysis. And (3) carrying out comprehensive control behavior analysis by combining signals such as an accelerator pedal, braking, acceleration, vehicle speed, rotating speed, torque and the like and front and rear vehicle states. The driving control behavior analysis comprises a starting working condition, an accelerating working condition, a sudden acceleration working condition, a steady-state running working condition, a decelerating working condition, a sudden deceleration working condition, a sliding working condition and the like, and the duty ratio of each working condition is counted. And analyzing the duty ratio and preference of the sub-working conditions under each working condition.

Step S703, driving manipulation event analysis. And carrying out control behavior analysis by combining signals such as an accelerator pedal, braking, acceleration, vehicle speed, rotating speed, torque and the like. The driving control event analysis comprises a bending event, a overtaking/lane changing event, a following event and the like, and the duty ratio of each event is counted. The sub-event duty cycle and preference for each event is then analyzed.

Step S704, outputting a driving style analysis result based on the driving style analysis. According to different road conditions, relevant data preprocessing is carried out according to signals such as congestion working conditions, the driving operation behavior proportion, the driving operation event proportion, the driving operation behavior and the event preference proportion under the road conditions are analyzed, the driving style analysis result based on the driving operation analysis under the road conditions is comprehensively obtained, and then the driving styles under various road conditions are counted to obtain the final driving style analysis result based on the driving operation analysis.

Step S705, driving style analysis based on machine learning. Machine learning of driving style is carried out based on the maximum value, the minimum value, the average value, the root mean square, the variance and the standard deviation of various signals (such as vehicle speed, transverse acceleration, longitudinal acceleration, an accelerator pedal, a brake pedal, steering wheel rotation angle, vehicle power and the like) of the whole vehicle, correlation analysis of characteristic parameters is carried out before machine learning is carried out, principal component analysis is carried out on the extracted characteristic parameters, and dimension reduction processing is carried out on a data set. And then calculating the data set based on a Kmeans clustering algorithm to obtain a driving style data classification result based on machine learning.

Step S706, driving style correction is performed, and a final driving style result is output. Correcting a driving style analysis result based on driving control analysis and a driving style analysis result based on machine learning, firstly calculating the accuracy delta of the driving styles of the data sheets obtained by the two driving style calculation methods, and judging whether the driving style calculation needs to be carried out again according to whether the value of delta reaches a threshold value. And if the value of delta reaches the threshold value, correcting according to the following formula to obtain the driving style and the total driving style of each data sheet, and forming a mapping relation table of the driving style and the driving working condition.

Referring to fig. 8, fig. 8 schematically illustrates a driving style analysis algorithm deployment schematic provided by an embodiment of the present application. When a user drives the vehicle, according to signals of the controllers and the sensors, an algorithm deployed in the central domain controller calculates the current driving style, the previous driving style, the current road condition and the driving style of the current scene of the user, and sends driving style command signals to the controllers, and the controllers adjust control logic according to the user styles, so that the vehicle performs control according to the driving style of the user when the user drives.

When a user uses an automatic driving mode, according to signals of each controller and each sensor, an algorithm deployed in the central domain controller calculates the current driving style, the previous driving style, the current road condition and the driving style of the current scene of the user, and sends driving style instruction signals, sub-working conditions and event control preferences to each controller, and each controller adjusts control logic according to the user styles, so that the control of the vehicle when the user drives automatically is consistent with the self driving of the user.

It should be noted that although the steps of the methods of the present application are depicted in the accompanying drawings in a particular order, this does not require or imply that the steps must be performed in that particular order, or that all illustrated steps be performed, to achieve desirable results. Additionally or alternatively, certain steps may be omitted, multiple steps combined into one step to perform, and/or one step decomposed into multiple steps to perform, etc.

The following describes embodiments of the apparatus of the present application that may be used to perform the driving style recognition method in the above-described embodiments of the present application. Fig. 9 schematically shows a block diagram of a driving style recognition device provided by an embodiment of the present application. As shown in fig. 9, the driving style recognition device 900 includes:

an acquisition module 901, configured to acquire driving behavior data;

The first analysis module 902 is configured to determine a corresponding driving condition and a duty ratio of the driving condition according to the driving behavior data, and calculate a first driving style value according to the driving condition and the duty ratio of the driving condition;

A second analysis module 903, configured to input driving behavior data into the trained machine learning model, to obtain a second driving style value;

And the fusion module 904 is used for carrying out fusion correction on the first driving style value and the second driving style value to obtain a final driving style result.

In some embodiments of the present application, based on the above technical solution, the first analysis module 902 is further configured to analyze driving behavior data to obtain at least one of a driving road condition, a driving behavior condition, and a driving manipulation event condition; calculating the duty ratio of driving road working conditions, driving behavior working conditions and driving control event working conditions; and calculating to obtain a first driving style value according to the driving road working condition, the driving behavior working condition, the driving control event working condition and the corresponding duty ratio of each working condition.

In some embodiments of the present application, based on the above technical solution, the first analysis module 902 is further configured to obtain a vehicle speed, an acceleration, and a braking frequency in the driving behavior data; determining a low-speed driving road and a high-speed driving road according to the relation between the vehicle speed and the set speed threshold value; and respectively determining road congestion working conditions corresponding to the low-speed driving road and the high-speed driving road according to the acceleration and the braking frequency so as to obtain driving road working conditions.

In some embodiments of the present application, based on the above technical solutions, the first analysis module 902 is further configured to obtain control behavior data in the driving behavior data; and determining driving behavior working conditions corresponding to the control behaviors according to the control behavior data.

In some embodiments of the present application, based on the above technical solutions, the first analysis module 902 is further configured to obtain control event data in driving behavior data; and determining driving control event working conditions corresponding to the control events according to the control event data.

In some embodiments of the present application, based on the above technical solution, the first analysis module 902 is further configured to obtain a first correction coefficient corresponding to a driving road condition, a second correction coefficient corresponding to a driving behavior condition, and a third correction coefficient corresponding to a driving manipulation event condition; accumulating the product of the duty ratio of the driving road working condition and the first correction coefficient, the product of the duty ratio of the driving behavior working condition and the second correction coefficient and the product of the duty ratio of the driving control event working condition and the third correction coefficient to obtain driving style parameters; counting the duty ratio of each driving style parameter in a set time period; the duty ratio of each driving style parameter is multiplied by the set driving style coefficient, and the first driving style value is obtained through accumulation.

In some embodiments of the present application, based on the above technical solutions, the first analysis module 902 is further configured to decompose a driving behavior condition, and determine a plurality of sub-behavior conditions corresponding to the driving behavior condition; calculating the duty ratio of a plurality of sub-behavior working conditions; multiplying the duty ratios of the sub-behavior conditions with the corresponding set correction coefficients respectively and accumulating the multiplied duty ratios to obtain a second correction coefficient.

In some embodiments of the present application, based on the above technical solutions, the first analysis module 902 is further configured to decompose a driving manipulation event condition, and determine a plurality of sub-event conditions corresponding to the driving manipulation event condition; calculating the duty ratio of the working conditions of a plurality of sub-events; multiplying the duty ratios of the sub-event working conditions with the corresponding set correction coefficients respectively and accumulating to obtain a third correction coefficient.

In some embodiments of the present application, based on the above technical solution, the fusion module 904 is further configured to calculate, according to the first driving style value and the second driving style value, an accuracy of the driving style; and if the accuracy reaches the set threshold, correcting the driving style value in each period, and taking the corrected driving style value as a final driving style result.

In some embodiments of the present application, based on the above technical solution, the fusion module 904 is further configured to obtain a first driving style value and a second driving style value corresponding to each period; correcting the first driving style value by the first setting coefficient and correcting the second driving style value by the second setting coefficient; and accumulating and averaging the correction result of the first driving style value and the correction result of the second driving style value to obtain the driving style value of each period.

In some embodiments of the present application, based on the above technical solution, the fusion module 904 is further configured to count the duty ratio of each driving style value in the set time period; and multiplying the duty ratio of each driving style value by a set driving style coefficient, and accumulating to obtain a final driving style value.

In some embodiments of the present application, based on the above technical solution, the apparatus further includes a mapping module, configured to map the final driving style value with a driving road condition, a driving behavior condition, and a driving control event condition, to obtain a driving style mapping table.

Specific details of the driving style recognition device provided in each embodiment of the present application have been described in the corresponding method embodiments, and are not described herein.

Fig. 10 schematically shows a block diagram of a computer system of an electronic device for implementing an embodiment of the application.

It should be noted that, the computer system 1000 of the electronic device shown in fig. 10 is only an example, and should not impose any limitation on the functions and the application scope of the embodiments of the present application.

As shown in fig. 10, the computer system 1000 includes a central processing unit 1001 (Central Processing Unit, CPU) which can execute various appropriate actions and processes according to a program stored in a Read-Only Memory 1002 (ROM) or a program loaded from a storage portion 1008 into a random access Memory 1003 (Random Access Memory, RAM). In the random access memory 1003, various programs and data necessary for the system operation are also stored. The cpu 1001, the rom 1002, and the ram 1003 are connected to each other via a bus 1004. An Input/Output interface 1005 (i.e., an I/O interface) is also connected to bus 1004.

The following components are connected to the input/output interface 1005: an input section 1006 including a keyboard, a mouse, and the like; an output portion 1007 including a Cathode Ray Tube (CRT), a Liquid crystal display (Liquid CRYSTAL DISPLAY, LCD), and a speaker, etc.; a storage portion 1008 including a hard disk or the like; and a communication section 1009 including a network interface card such as a local area network card, a modem, or the like. The communication section 1009 performs communication processing via a network such as the internet. The drive 1010 is also connected to the input/output interface 1005 as needed. A removable medium 1011, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, or the like, is installed as needed in the drive 1010, so that a computer program read out therefrom is installed as needed in the storage section 1008.

In particular, the processes described in the various method flowcharts may be implemented as computer software programs according to embodiments of the application. For example, embodiments of the present application include a computer program product comprising a computer program embodied on a computer readable medium, the computer program comprising program code for performing the method shown in the flowcharts. In such an embodiment, the computer program may be downloaded and installed from a network via the communication portion 1009, and/or installed from the removable medium 1011. The computer programs, when executed by the central processor 1001, perform the various functions defined in the system of the present application.

It should be noted that, the computer readable medium shown in the embodiments of the present application may be a computer readable signal medium or a computer readable storage medium, or any combination of the two. The computer readable storage medium can be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or a combination of any of the foregoing. More specific examples of the computer-readable storage medium may include, but are not limited to: an electrical connection having 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 (Erasable Programmable Read Only Memory, EPROM), a flash Memory, an optical fiber, a portable compact disc read-Only Memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the context of this document, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In the present application, however, the computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, with the computer-readable program code embodied therein. Such a propagated data signal may take any of a variety of forms, including, but not limited to, electro-magnetic, optical, or any suitable combination of the foregoing. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wired, etc., or any suitable combination of the foregoing.

The flowcharts and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present application. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams or flowchart illustration, and combinations of blocks in the block diagrams or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.

It should be noted that although in the above detailed description several modules or units of a device for action execution are mentioned, such a division is not mandatory. Indeed, the features and functions of two or more modules or units described above may be embodied in one module or unit in accordance with embodiments of the application. Conversely, the features and functions of one module or unit described above may be further divided into a plurality of modules or units to be embodied.

From the above description of embodiments, those skilled in the art will readily appreciate that the example embodiments described herein may be implemented in software, or may be implemented in software in combination with the necessary hardware. Thus, the technical solution according to the embodiments of the present application may be embodied in the form of a software product, which may be stored in a non-volatile storage medium (may be a CD-ROM, a U-disk, a mobile hard disk, etc.) or on a network, and includes several instructions to cause a computing device (may be a personal computer, a server, a touch terminal, or a network device, etc.) to perform the method according to the embodiments of the present application.

Other embodiments of the application will be apparent to those skilled in the art from consideration of the specification and practice of the application disclosed herein. This application is intended to cover any variations, uses, or adaptations of the application following, in general, the principles of the application and including such departures from the present disclosure as come within known or customary practice within the art to which the application pertains.

It is to be understood that the application is not limited to the precise arrangements and instrumentalities shown in the drawings, which have been described above, and that various modifications and changes may be effected without departing from the scope thereof. The scope of the application is limited only by the appended claims.

Claims

1. A driving style recognition method, characterized in that the method comprises:

Acquiring driving behavior data;

2. The driving style recognition method according to claim 1, wherein the determining the corresponding driving condition and the duty ratio of the driving condition according to the driving behavior data, and calculating the first driving style value according to the driving condition and the duty ratio of the driving condition, includes:

analyzing the driving behavior data to obtain at least one working condition of a driving road working condition, a driving behavior working condition and a driving control event working condition;

Calculating the duty ratio of the driving road working condition, the driving behavior working condition and the driving control event working condition;

And calculating to obtain the first driving style value according to the driving road working condition, the driving behavior working condition, the driving control event working condition and the corresponding duty ratio of each working condition.

3. The driving style recognition method according to claim 2, wherein the analyzing the driving behavior data to obtain driving road conditions includes:

Determining a low-speed driving road and a high-speed driving road according to the relation between the vehicle speed and a set speed threshold value;

And respectively determining road congestion working conditions corresponding to the low-speed driving road and the high-speed driving road according to the acceleration and the braking frequency so as to obtain the driving road working conditions.

4. The driving style recognition method according to claim 2, wherein the analyzing the driving behavior data to obtain driving behavior conditions includes:

Acquiring control behavior data in the driving behavior data;

5. The driving style recognition method according to claim 2, wherein the analyzing the driving behavior data to obtain driving control event conditions includes:

acquiring control event data in the driving behavior data;

6. The driving style recognition method according to claim 2, wherein the calculating the first driving style value according to the driving road condition, the driving behavior condition, the driving manipulation event condition, and the corresponding duty ratio of each condition includes:

Acquiring a first correction coefficient corresponding to the driving road working condition, a second correction coefficient corresponding to the driving behavior working condition and a third correction coefficient corresponding to the driving control event working condition;

Accumulating the product of the duty ratio of the driving road working condition and the first correction coefficient, the product of the duty ratio of the driving behavior working condition and the second correction coefficient and the product of the duty ratio of the driving control event working condition and the third correction coefficient to obtain driving style parameters;

counting the duty ratio of each driving style parameter in a set time period;

and multiplying the duty ratio of each driving style parameter by a set driving style coefficient, and accumulating to obtain a first driving style value.

7. The driving style recognition method according to claim 6, wherein the second correction coefficient corresponding to the driving behavior condition includes:

calculating the duty ratio of a plurality of sub-behavior working conditions;

Multiplying the duty ratios of the sub-behavior working conditions with the corresponding set correction coefficients respectively and accumulating to obtain the second correction coefficient.

8. The driving style identification method according to claim 6, wherein the third correction coefficient corresponding to the driving manipulation event condition includes:

Multiplying the duty ratios of the sub-event working conditions with the corresponding set correction coefficients respectively and accumulating to obtain the third correction coefficient.

9. The driving style recognition method according to claim 1, wherein the performing fusion correction on the first driving style value and the second driving style value to obtain a final driving style result includes:

10. The driving style recognition method according to claim 9, wherein the correcting the driving style value in each period includes:

acquiring a first driving style value and a second driving style value corresponding to each period;

Correcting the first driving style value by a first setting coefficient, and correcting the second driving style value by a second setting coefficient;

11. The driving style recognition method according to claim 10, wherein the taking the corrected driving style value as the final driving style result includes:

counting the duty ratio of each driving style value in a set time period;

12. The driving style identification method according to claim 2, characterized in that the method further comprises:

13. A driving style recognition device, characterized in that the device comprises:

The acquisition module is used for acquiring driving behavior data;

14. A computer readable medium, characterized in that the computer readable medium has stored thereon a computer program which, when executed by a processor, implements the driving style recognition method according to any one of claims 1 to 12.

15. An electronic device, comprising:

A processor; and

A memory for storing executable instructions of the processor;

Wherein the processor is configured to perform the driving style identification method of any one of claims 1 to 12 via execution of the executable instructions.