Driver driving style identification method, system and device and storage medium

Abstract

The invention discloses a driver driving style identification method, system and device and a storage medium, and the method comprises the steps: obtaining a first driving data set and second driving data of a target vehicle, the second driving data being driving data of the target vehicle at the current moment, and the first driving data set being a first driving data set; the first driving data set comprises historical driving data of the target vehicle, and part of the first driving data in the first driving data set further comprises historical driving working condition category label values and historical driving style category label values; constructing an initial driving style recognition model, and inputting the first driving data set into the initial driving style recognition model for model training to obtain a trained driving style recognition model; and inputting the second driving data into the trained driving style recognition model to obtain a driver driving style recognition result of the target vehicle, thereby improving the accuracy of driving style recognition.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of driver driving style recognition, and in particular to a driver driving style recognition method, system, device and storage medium. BACKGROUND

[0002] In order to better apply advanced driving assistance and automatic driving, it is necessary to analyze the behavior of the driver. The driving habits of the driver are very complex and complicated, and the driving habits of each person are dynamically changing. With the requirement of consumers for the performance of the car, the car has become a trend to adapt to people, so the driving assistance system and other functions need to be changed to adapt to the requirements of different drivers.

[0003] In the prior art, the driving style is mainly recognized by the age, personality, driving age and driving proficiency of the driver, resulting in low accuracy of driving style recognition. SUMMARY

[0004] The present application aims to at least solve the technical problems existing in the prior art. To this end, the present application provides a driver driving style recognition method, system, device and storage medium, which can recognize the driving style of the driver in combination with different driving conditions, and improve the accuracy of driving style recognition.

[0005] The first aspect of the present application provides a driver driving style recognition method, comprising the following steps: obtaining a first driving data set and a second driving data of a target vehicle, wherein the second driving data is the driving data of the target vehicle at the current time, the first driving data set includes the historical driving data of the target vehicle, and part of the first driving data in the first driving data set further includes a historical driving condition category label value and a historical driving style category label value; constructing an initial driving style recognition model, inputting the first driving data set into the initial driving style recognition model for model training, and obtaining a trained driving style recognition model; inputting the second driving data into the trained driving style recognition model to obtain a driver driving style recognition result of the target vehicle.

[0006] The control method according to the embodiments of the present application has at least the following beneficial effects: The method comprises the following steps: acquiring a first driving data set of a target vehicle and second driving data, wherein the second driving data is driving data of the target vehicle at a current time, the first driving data set comprises historical driving data of the target vehicle, and part of the first driving data in the first driving data set further comprises a historical driving condition category label value and a historical driving style category label value; an initial driving style recognition model is constructed, the first driving data set is input into the initial driving style recognition model for model training, and a trained driving style recognition model is obtained; the second driving data is input into the trained driving style recognition model, and a driving style recognition result of a driver of the target vehicle is obtained, so that the driving style recognition accuracy is improved by recognizing the driving style of the driver in combination with different driving conditions.

[0007] According to some embodiments of the present application, the first driving data set of the target vehicle is acquired by: acquiring historical longitudinal acceleration, historical lateral acceleration, historical longitudinal speed, historical lateral speed, historical longitudinal acceleration change rate, historical yaw rate, historical accelerator pedal position and historical braking force of the target vehicle in a plurality of preset historical time periods; The first driving data set is constructed by data preprocessing based on the historical longitudinal acceleration, historical lateral acceleration, historical longitudinal speed, historical lateral speed, historical longitudinal acceleration change rate, historical yaw rate, historical accelerator pedal position and historical braking force of the target vehicle in the plurality of preset historical time periods.

[0008] According to some embodiments of the present application, the first driving data set is constructed by data preprocessing based on the historical longitudinal acceleration, historical lateral acceleration, historical longitudinal speed, historical lateral speed, historical longitudinal acceleration change rate, historical yaw rate, historical accelerator pedal position and historical braking force of the target vehicle in the plurality of preset historical time periods, comprising: The historical longitudinal acceleration, historical lateral acceleration, historical longitudinal speed, historical lateral speed, historical longitudinal acceleration change rate, historical yaw rate, historical accelerator pedal position and historical braking force of the target vehicle in the plurality of preset historical time periods are taken as a driving data set, and the driving data set is uploaded to a cloud control platform to filter the driving data set by the cloud control platform to obtain a filtered driving data set; extracting feature parameters in the filtered driving data set; The first driving data set is constructed based on the feature parameters, the historical driving condition category label value of part of the first driving data in the first driving data set in the plurality of preset historical time periods, and the historical driving style category label value of part of the first driving data in the first driving data set in the plurality of preset historical time periods.

[0009] According to some embodiments of the present application, the extracting the feature parameters in the filtered driving data set comprises: confirming maximum, minimum, mean, standard deviation, root mean square, coefficient of variation and median of all the historical longitudinal accelerations; confirming maximum, minimum, mean, standard deviation, root mean square, coefficient of variation and median of all the historical lateral accelerations; confirming maximum, minimum, mean, standard deviation, root mean square, coefficient of variation and median of all the historical longitudinal velocities; confirming maximum, minimum, mean, standard deviation, root mean square, coefficient of variation and median of all the historical lateral velocities; confirming maximum, minimum, mean, standard deviation, root mean square, coefficient of variation and median of all the historical longitudinal acceleration rates; confirming maximum, minimum, mean, standard deviation, root mean square, coefficient of variation and median of all the historical yaw rates; confirming maximum, minimum, mean, standard deviation, root mean square, coefficient of variation and median of all the historical acceleration pedal positions; confirming maximum, minimum, mean, standard deviation, root mean square, coefficient of variation and median of all the historical braking forces; confirming maximum, minimum, mean, standard deviation, root mean square, coefficient of variation and median of all the historical longitudinal accelerations, maximum, minimum, mean, standard deviation, root mean square, coefficient of variation and median of all the historical lateral accelerations, maximum, minimum, mean, standard deviation, root mean square, coefficient of variation and median of all the historical longitudinal velocities, maximum, minimum, mean, standard deviation, root mean square, coefficient of variation and median of all the historical lateral velocities, maximum, minimum, mean, standard deviation, root mean square, coefficient of variation and median of all the historical longitudinal acceleration rates, maximum, minimum, mean, standard deviation, root mean square, coefficient of variation and median of all the historical yaw rates, maximum, minimum, mean, standard deviation, root mean square, coefficient of variation and median of all the historical longitudinal acceleration rates, maximum, minimum, mean, standard deviation, root mean square, coefficient of variation and median of all the historical acceleration pedal positions, and maximum, minimum, mean, standard deviation, root mean square, coefficient of variation and median of all the historical braking forces as the feature parameters in the filtered driving data set.

[0010] According to some embodiments of the present application, the method further comprises: inputting the second driving data into the trained driving style recognition model to obtain a driving condition prediction category and a driving style prediction category, wherein the driving condition prediction category comprises city, suburb, and highway, and the driving style prediction category comprises aggressive type, moderate type, and ordinary type; combining the driving condition prediction category and the driving style prediction category to obtain the driver driving style recognition result of the target vehicle.

[0011] According to some embodiments of the present application, the method further comprises: updating the driver driving style recognition result of the target vehicle to the target vehicle, so that the target vehicle determines a driving style strategy based on the driver driving style recognition result; incorporating the driving style strategy into the vehicle control system of the target vehicle without affecting the normal driving needs of the driver; in the case that the driver ends the current driving trip, generating driver revisit information, so that the driver replies to the driver revisit information to obtain a revisit result.

[0012] According to some embodiments of the present application, the method further comprises: constructing an initial driving style recognition model through a cloud control platform.

[0013] In a second aspect, the present application provides a driver driving style recognition system, comprising: a data acquisition module configured to acquire a first driving data set and second driving data of a target vehicle, wherein the second driving data is driving data of the target vehicle at a current time, the first driving data set comprises historical driving data of the target vehicle, and part of the first driving data in the first driving data set further comprises a historical driving condition category label value and a historical driving style category label value; a model training module configured to construct an initial driving style recognition model, input the first driving data set into the initial driving style recognition model for model training, and obtain a trained driving style recognition model; a result output module configured to input the second driving data into the trained driving style recognition model to obtain a driver driving style recognition result of the target vehicle.

[0014] The system obtains a first driving data set and second driving data of a target vehicle, the second driving data is driving data of the target vehicle at a current time, the first driving data set includes historical driving data of the target vehicle, and part of the first driving data in the first driving data set further includes a historical driving condition category label value and a historical driving style category label value; an initial driving style recognition model is constructed, the first driving data set is input into the initial driving style recognition model for model training, and a trained driving style recognition model is obtained; the second driving data is input into the trained driving style recognition model, and a driving style recognition result of a driver of the target vehicle is obtained, the driving style of the driver is recognized by combining different driving conditions, and the accuracy of driving style recognition is improved.

[0015] In a third aspect, the present application provides a driver driving style recognition electronic device, comprising at least one control processor and a memory connected in communication with the at least one control processor; the memory stores instructions executable by the at least one control processor, and the instructions are executed by the at least one control processor to enable the at least one control processor to perform the driver driving style recognition method described above.

[0016] In a fourth aspect, the present application provides a computer-readable storage medium, which stores computer-executable instructions for causing a computer to perform the driver driving style recognition method described above.

[0017] It should be noted that the beneficial effects between the second aspect to the fourth aspect of the present application and the prior art are the same as the beneficial effects between the driver driving style recognition system described above and the prior art, which will not be described here.

[0018] Additional aspects and advantages of the present application will be in part apparent and in part pointed out hereinafter. BRIEF DESCRIPTION OF DRAWINGS

[0019] The above and / or additional aspects and advantages of the present application will become apparent and be readily appreciated from the following description, including the accompanying drawings, in which: Figure 1 is a flowchart of the driver driving style recognition method provided by the present application; Figure 2 is a structural schematic diagram of an embodiment of the driver driving style recognition system provided by the present application; Figure 3 is a structural schematic diagram of an embodiment of the electronic device provided by the present application. DETAILED DESCRIPTION

[0020] Embodiments of the present application are described below in detail, examples of the embodiments are shown in the drawings, wherein the same or similar notations represent the same or similar elements or elements having the same or similar functions throughout. The embodiments described below by referring to the drawings are exemplary only, for the purpose of explaining the present application, and should not be understood as a limitation of the present application.

[0021] In the description of the present application, if there is a description to first, second, etc., it is only for the purpose of distinguishing technical features, and cannot be understood as indicating or implying relative importance or implicitly indicating the number of indicated technical features or the sequence of indicated technical features.

[0022] In the description of the present application, it is to be understood that the orientation description, such as up, down, etc., indicates the orientation or first positional relationship based on the orientation or first positional relationship shown in the drawings, only for the purpose of describing the present application and simplifying the description, and therefore cannot be understood as indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation of the present application.

[0023] In the description of the present application, it is to be understood that, unless otherwise explicitly limited, the words such as setting, installing, connecting, etc. should be broadly understood, and the person skilled in the art can reasonably determine the specific meaning of the above words in the present application in combination with the specific content of the technical solution.

[0024] In order to better apply advanced driving assistance and automatic driving, it is necessary to analyze the behavior of the driver. The driving habits of the driver are very complex and complicated, and the driving habits of each person are dynamically changing. With the requirement of consumers for the performance of the car, the car has become a trend to adapt to people, so the driving assistance system and other functions need to be changed to adapt to the requirements of different drivers.

[0025] In the prior art, driving style recognition is mainly performed by the age, personality, driving age and driving proficiency of the driver, resulting in low driving style recognition accuracy.

[0026] In order to solve the above technical defects, the embodiments of the present application provide a driver driving style recognition method, system, device and storage medium.

[0027] Please refer to Figure 1 , which is a flowchart of a driver driving style recognition method provided by the embodiments of the present application, as shown in Figure 1 , the driver driving style recognition method comprises: In step S101, a first driving data set and second driving data of a target vehicle are acquired, the second driving data being driving data of the target vehicle at a current time, the first driving data set including historical driving data of the target vehicle, and part of the first driving data in the first driving data set further including a historical driving condition category label value and a historical driving style category label value. In step S102, an initial driving style recognition model is constructed, the first driving data set is input into the initial driving style recognition model for model training, and a trained driving style recognition model is obtained. In step S103, the second driving data is input into the trained driving style recognition model, and a driving style recognition result of a driver of the target vehicle is obtained.

[0028] The initial driving style recognition model can be trained by a supervised learning method or an unsupervised learning method.

[0029] In step S102, the initial driving style recognition model can be constructed based on a back propagation neural network model.

[0030] The method acquires a first driving data set and second driving data of a target vehicle, the second driving data being driving data of the target vehicle at a current time, the first driving data set including historical driving data of the target vehicle, and part of the first driving data in the first driving data set further including a historical driving condition category label value and a historical driving style category label value; an initial driving style recognition model is constructed, the first driving data set is input into the initial driving style recognition model for model training, and a trained driving style recognition model is obtained; and the second driving data is input into the trained driving style recognition model, and a driving style recognition result of a driver of the target vehicle is obtained. The driving style of the driver is recognized by combining different driving conditions, and the accuracy of driving style recognition is improved.

[0031] In some embodiments, the first driving data set of the target vehicle is acquired by: In step S201, historical longitudinal acceleration, historical lateral acceleration, historical longitudinal speed, historical lateral speed, historical longitudinal acceleration change rate, historical yaw rate, historical accelerator pedal position, and historical braking force in a plurality of preset historical time periods of the target vehicle are acquired. In step S202, the first driving data set is constructed based on the historical longitudinal acceleration, the historical lateral acceleration, the historical longitudinal speed, the historical lateral speed, the historical longitudinal acceleration change rate, the historical yaw rate, the historical accelerator pedal position, and the historical braking force in the plurality of preset historical time periods of the target vehicle through data preprocessing.

[0032] The application constructs a first driving data set through data preprocessing, provides more accurate data basis for subsequent model training, and improves the accuracy and efficiency of model training.

[0033] In some embodiments, based on the historical longitudinal acceleration, historical lateral acceleration, historical longitudinal speed, historical lateral speed, historical longitudinal acceleration change rate, historical yaw rate, historical accelerator pedal position and historical braking force of the target vehicle within a plurality of preset historical time periods, a first driving data set is constructed through data preprocessing, comprising: Step S301, the historical longitudinal acceleration, historical lateral acceleration, historical longitudinal speed, historical lateral speed, historical longitudinal acceleration change rate, historical yaw rate, historical accelerator pedal position and historical braking force of the target vehicle within a plurality of preset historical time periods are taken as a driving data set, and the driving data set is uploaded to a cloud control platform to filter the driving data set through the cloud control platform to obtain a filtered driving data set; Step S302, extracting feature parameters in the filtered driving data set; Step S303, based on the feature parameters, the historical driving condition category label value of part of the first driving data in the first driving data set within a plurality of preset historical time periods and the historical driving style category label value of part of the first driving data in the first driving data set within a plurality of preset historical time periods, constructing the first driving data set.

[0034] The above-mentioned preset historical time period can be a value set in advance according to actual needs.

[0035] In some embodiments, the feature parameters in the filtered driving data set are extracted, comprising: Step S401, confirming the maximum value, minimum value, mean value, standard deviation, root mean square, coefficient of variation and median of all historical longitudinal accelerations; Step S402, confirming the maximum value, minimum value, mean value, standard deviation, root mean square, coefficient of variation and median of all historical lateral accelerations; Step S403, confirming the maximum value, minimum value, mean value, standard deviation, root mean square, coefficient of variation and median of all historical longitudinal speeds; Step S404, confirming the maximum value, minimum value, mean value, standard deviation, root mean square, coefficient of variation and median of all historical lateral speeds; Step S405, confirming the maximum value, minimum value, mean value, standard deviation, root mean square, coefficient of variation and median of all historical longitudinal acceleration change rates; Step S406, confirming the maximum value, minimum value, mean value, standard deviation, root mean square, coefficient of variation and median of all historical yaw rates; Step S407, confirming the maximum value, minimum value, mean value, standard deviation, root mean square, coefficient of variation and median of all historical accelerator pedal positions; Step S408, confirming the maximum value, minimum value, mean value, standard deviation, root mean square, coefficient of variation and median of all historical braking forces; Step S409, taking the maximum value, minimum value, mean value, standard deviation, root mean square, coefficient of variation and median of all historical longitudinal accelerations, the maximum value, minimum value, mean value, standard deviation, root mean square, coefficient of variation and median of all historical lateral accelerations, the maximum value, minimum value, mean value, standard deviation, root mean square, coefficient of variation and median of all historical longitudinal velocities, the maximum value, minimum value, mean value, standard deviation, root mean square, coefficient of variation and median of all historical lateral velocities, the maximum value, minimum value, mean value, standard deviation, root mean square, coefficient of variation and median of all historical longitudinal acceleration rates, the maximum value, minimum value, mean value, standard deviation, root mean square, coefficient of variation and median of all historical yaw rates, the maximum value, minimum value, mean value, standard deviation, root mean square, coefficient of variation and median of all historical longitudinal acceleration rates, the maximum value, minimum value, mean value, standard deviation, root mean square, coefficient of variation and median of all historical accelerator pedal positions and the maximum value, minimum value, mean value, standard deviation, root mean square, coefficient of variation and median of all historical braking forces as the characteristic parameters in the filtered driving data set.

[0036] In the above step S401, confirming the maximum value, minimum value, mean value, standard deviation, root mean square, coefficient of variation and median of all historical longitudinal accelerations can be screening out the maximum value, minimum value and median of all historical longitudinal accelerations, and calculating the mean value, standard deviation, root mean square and coefficient of variation of all historical longitudinal accelerations.

[0037] In the above step S402, the confirmation process of confirming the maximum value, minimum value, mean value, standard deviation, root mean square, coefficient of variation and median of all historical lateral accelerations is similar to the confirmation process of step S401, which will not be repeated here.

[0038] In the above step S403, the confirmation process of confirming the maximum value, minimum value, mean value, standard deviation, root mean square, coefficient of variation and median of all historical longitudinal velocities is similar to the confirmation process of step S401, which will not be repeated here.

[0039] In the above step S404, the confirmation process of confirming the maximum value, minimum value, mean value, standard deviation, root mean square, coefficient of variation and median of all historical lateral velocities is similar to the confirmation process of step S401, which will not be repeated here.

[0040] The confirmation process of the maximum value, the minimum value, the average value, the standard deviation, the root mean square, the coefficient of variation and the median of all historical longitudinal acceleration changes in step S405 is similar to that of step S401, and will not be repeated here.

[0041] The confirmation process of the maximum value, the minimum value, the average value, the standard deviation, the root mean square, the coefficient of variation and the median of all historical yaw rate in step S406 is similar to that of step S401, and will not be repeated here.

[0042] The confirmation process of the maximum value, the minimum value, the average value, the standard deviation, the root mean square, the coefficient of variation and the median of all historical acceleration pedal positions in step S407 is similar to that of step S401, and will not be repeated here.

[0043] The confirmation process of the maximum value, the minimum value, the average value, the standard deviation, the root mean square, the coefficient of variation and the median of all historical braking force in step S408 is similar to that of step S401, and will not be repeated here.

[0044] The characteristic parameters can also include the impact degree.

[0045] The present application provides more accurate and comprehensive data basis for subsequent model training by extracting the characteristic parameters in the filtered driving data set, and improves the accuracy and efficiency of model training.

[0046] In some embodiments, the second driving data is input into the trained driving style recognition model to obtain a driver driving style recognition result of the target vehicle, including: Step S501, input the second driving data into the trained driving style recognition model to obtain a driving condition prediction category and a driving style prediction category, wherein the driving condition prediction category includes city, suburb and highway, and the driving style prediction category includes aggressive type, moderate type and ordinary type; Step S502, combine the driving condition prediction category and the driving style prediction category to obtain the driver driving style recognition result of the target vehicle.

[0047] In the step S501, the second driving data is input into the trained driving style recognition model to obtain the driving condition prediction category and the driving style prediction category. The n-dimensional feature parameter representing the driving condition and the m-dimensional feature parameter representing the driving style can be extracted from the second driving data. The correlation analysis of the n-dimensional feature parameter and the driving condition category and the correlation analysis of the m-dimensional feature parameter and the driving style category are performed. Based on the n-dimensional feature parameter and the m-dimensional feature parameter, the driving condition prediction category and the driving style prediction category are obtained through the trained driving style recognition model. The n can be a value pre-set according to actual requirements, and the m can be a value pre-set according to actual requirements.

[0048] The application improves the accuracy of driving style recognition by identifying the driving style of the driver under different driving conditions.

[0049] In some embodiments, the method further comprises: In step S601, the driving style recognition result of the driver of the target vehicle is updated to the target vehicle, so that the target vehicle determines the driving style strategy based on the driving style recognition result of the driver; In step S602, the driving style strategy is integrated into the vehicle control system of the target vehicle without affecting the normal driving demand of the driver. In step S603, the driver's feedback information is generated when the driver ends the current driving trip, so that the driver replies to the driver's feedback information to obtain the feedback result.

[0050] The normal driving demand can be maintaining a safe distance from the front and side vehicles, not violating the lane change or overtaking, and complying with the traffic regulations, including not exceeding the speed limit, not running a red light, not reversing, driving in the designated lane, and parking according to the law.

[0051] Specifically, in some embodiments, the driving style strategy is integrated into the vehicle control system without affecting the normal driving demand of the driver, thereby completing the multi-objective collaborative optimization. The application can also extract important vehicle parameters (such as the driving range, the state of charge of the battery, and the energy consumption rate) when the driver ends the current driving trip, evaluate the personalized driving control strategy, and combine the driving condition and the driving style recognition result with the driver's feedback information to form a data set for evaluation. The data set is uploaded to the cloud as data support for subsequent iterative optimization of the driving style recognition model.

[0052] In some embodiments, the initial driving style recognition model is constructed, including: In step S701, the initial driving style recognition model is constructed through the cloud control platform.

[0053] The application can improve the efficiency of subsequent model training by constructing an initial driving style recognition model through a cloud control platform.

[0054] In addition, with reference to Figure 2 An embodiment of the application provides a driver driving style recognition system, which comprises a data acquisition module 1100, a model training module 1200 and a result output module 1300. The data acquisition module 1100 is used for acquiring a first driving data set and second driving data of a target vehicle, wherein the second driving data is driving data of the target vehicle at a current time, the first driving data set comprises historical driving data of the target vehicle, and part of the first driving data in the first driving data set further comprises a historical driving condition category label value and a historical driving style category label value. The model training module 1200 is used for constructing an initial driving style recognition model, inputting the first driving data set into the initial driving style recognition model for model training, and obtaining a trained driving style recognition model. The result output module 1300 is used for inputting the second driving data into the trained driving style recognition model, and obtaining a driver driving style recognition result of the target vehicle.

[0055] The system acquires a first driving data set and second driving data of a target vehicle, wherein the second driving data is driving data of the target vehicle at a current time, the first driving data set comprises historical driving data of the target vehicle, and part of the first driving data in the first driving data set further comprises a historical driving condition category label value and a historical driving style category label value; an initial driving style recognition model is constructed, the first driving data set is input into the initial driving style recognition model for model training, and a trained driving style recognition model is obtained; and the second driving data is input into the trained driving style recognition model, and a driver driving style recognition result of the target vehicle is obtained.

[0056] It should be noted that the system embodiment and the method embodiment described above are based on the same inventive concept, and therefore the related content of the method embodiment described above is also applicable to the system embodiment, which will not be described here again.

[0057] Figure 3 A hardware structure schematic diagram of driver driving style recognition provided by an embodiment of the application is shown.

[0058] The driver driving style recognition device can comprise a processor 301 and a memory 302 in which computer program instructions are stored.

[0059] In particular, the processor 301 can include a central processing unit (CPU), or an application-specific integrated circuit (ASIC), or one or more integrated circuits configured to perform the operations of the embodiments of the application.

[0060] The memory 302 can include mass storage for data or instructions. As an example and not by way of limitation, the memory 302 can include a hard disk drive (HDD), a floppy disk drive, flash memory, an optical disc (e.g., a compact disc (CD) or DVD), a tape drive, a USB drive, or a combination of two or more of these. The memory 302 can include removable or non-removable (or fixed) media, where appropriate. The memory 302 can be internal or external to the integrated gateway disaster recovery device, where appropriate. In particular embodiments, the memory 302 is non-volatile, solid-state memory.

[0061] In some implementations, the memory 302 includes read-only memory (ROM), random access memory (RAM), a magnetic disk storage medium, an optical storage medium, a flash memory device, electrical, optical, or other physical / tangible memory storage device. Thus, in general, the memory includes one or more tangible (non-transitory) computer-readable storage media (e.g., a memory device) encoded with software that, when executed (by one or more processors), is operable to perform operations described with reference to the methods according to an aspect of the present disclosure.

[0062] The processor 301 implements any one of the driver driving style recognition methods in the above embodiments by reading and executing computer program instructions stored in the memory 302.

[0063] In one example, the driver driving style recognition device can further include a communication interface 303 and a bus 310. As shown, the processor 301, the memory 302, and the communication interface 303 are connected through the bus 310 and complete communication with each other. Figure 3

[0064] The communication interface 303 is mainly used to realize the communication between the modules, devices, units and / or equipment in the embodiments of the application.

[0065] ​Bus 310 includes hardware, software, or both, to couple components of the driver driving style recognition device to each other in communication. While the application is not limited to particular bus structures, in this application, bus 310 can be a system bus, a peripheral component interconnect (PCI) bus, a HyperTransport® bus, MicroChannel Architecture (MSA) bus, proprietary instrument bus, industry standard architecture (ISA) bus, Advanced Technology Attachment (ATA) bus, Small Computer System Interface (SCSI) bus, FIrewire bus, Universal Serial Bus (USB), Audio Video Interleaved (AVI) bus, Video Electronics Standards Association (VESA) local bus, improved Video Electronics Standards Association local bus (VL), or a suitable bus structure for use with the drives of the application. In this application, bus 310 can be a bus implementing a communication protocol with the driver driving style recognition device. While bus 310 is shown in this application as a single bus, alternative embodiments can feature two or more buses. Although the application is described and shown in this application with respect to a particular bus configuration, the application contemplates any suitable bus or interconnect.

[0066] The driver driving style recognition device can perform the driver driving style recognition method in the embodiments of the application based on the three-dimensional design model, thereby realizing the driver driving style recognition method and system described in the embodiments of the application. Figure 1 and Figure 2 The driver driving style recognition method and system described in the embodiments of the application.

[0067] In addition, in combination with the driver driving style recognition method in the above embodiments, the embodiments of the application can provide a computer storage medium to realize. The computer storage medium has computer program instructions stored thereon; the computer program instructions are executed by a processor to realize any one of the driver driving style recognition methods in the above embodiments.

[0068] It needs to be clear that the application is not limited to the specific configurations and processes described above and shown in the drawings. For the sake of brevity, detailed descriptions of known methods are omitted here. In the above embodiments, several specific steps are described and shown as examples. However, the method process of the application is not limited to the specific steps described and shown, and those skilled in the art can make various changes, modifications and additions, or change the order between steps, after understanding the spirit of the application.

[0069] The functional blocks shown in the structural block diagrams above can be implemented as hardware, software, firmware, or a combination thereof. When implemented in hardware, they can be, for example, electronic circuits, application specific integrated circuits (ASICs), appropriate firmware, plug-ins, function cards, and the like. When implemented in software, the elements of the present application are program or code segments that are used to perform the required tasks. The program or code segments can be stored in a machine-readable medium, or transmitted through a data signal carried in a carrier wave over a transmission medium or communication link. A "machine-readable medium" includes any medium that can store or transport information. Examples of machine-readable media include electronic circuits, semiconductor memory devices, ROMs, flash memory, erasable ROMs (EROMs), floppy disks, CD-ROMs, optical disks, hard disks, optical fiber media, radio frequency (RF) links, and the like. The code segments can be downloaded via computer networks such as the Internet, intranets, and the like.

[0070] It is also important to note that the examples in the present application are described based on a series of steps or units for performing some methods or systems. However, the present application is not limited to the order of the above steps, that is, the steps can be performed in the order mentioned in the examples, or in an order different from the examples, or several steps can be performed simultaneously.

[0071] The above describes the aspects of the present application with reference to the flowcharts and / or block diagrams of the methods, apparatuses (systems) and computer program products according to the embodiments of the present application. It should be understood that each block in the flowcharts and / or block diagrams, and the combination of the blocks in the flowcharts and / or block diagrams can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, or other programmable data processing apparatus, to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing apparatus enable the implementation of the functions / actions specified in one or more blocks of the flowcharts and / or block diagrams. Such a processor can be, but is not limited to, a general-purpose processor, a special-purpose processor, a special application processor, or a field programmable logic circuit. It should also be understood that each block in the block diagrams and / or flowcharts, and the combination of the blocks in the block diagrams and / or flowcharts, can also be implemented by special hardware that performs the specified functions or actions, or can be implemented by a combination of special hardware and computer instructions.

[0072] The above is only a specific implementation of the present application, and those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described systems, modules and units can refer to the corresponding processes in the foregoing method embodiments, which will not be described here. It should be understood that the protection scope of the present application is not limited thereto, and any person skilled in the art can easily think of various equivalent modifications or replacements within the technical scope disclosed in the present application, and these modifications or replacements should be covered within the protection scope of the present application.

Claims

1. A driver driving style recognition method characterized by, The driver driving style recognition method comprises: obtaining a first driving data set and a second driving data of a target vehicle, wherein the second driving data is the driving data of the target vehicle at the current time, the first driving data set comprises historical driving data of the target vehicle, and part of the first driving data in the first driving data set further comprises a historical driving condition category label value and a historical driving style category label value; constructing an initial driving style recognition model, inputting the first driving data set into the initial driving style recognition model for model training, and obtaining a trained driving style recognition model; inputting the second driving data into the trained driving style recognition model to obtain a driver driving style recognition result of the target vehicle.

2. The method of claim 1, wherein The first driving data set of the target vehicle is obtained, comprising: obtaining historical longitudinal acceleration, historical lateral acceleration, historical longitudinal speed, historical lateral speed, historical longitudinal acceleration change rate, historical yaw rate, historical accelerator pedal position and historical braking force of the target vehicle in a plurality of preset historical time periods; based on the historical longitudinal acceleration, historical lateral acceleration, historical longitudinal speed, historical lateral speed, historical longitudinal acceleration change rate, historical yaw rate, historical accelerator pedal position and historical braking force of the target vehicle in a plurality of preset historical time periods, the first driving data set is constructed through data preprocessing.

3. The method of claim 2, wherein The first driving data set is constructed through data preprocessing based on the historical longitudinal acceleration, historical lateral acceleration, historical longitudinal speed, historical lateral speed, historical longitudinal acceleration change rate, historical yaw rate, historical accelerator pedal position and historical braking force of the target vehicle in a plurality of preset historical time periods, comprising: the historical longitudinal acceleration, historical lateral acceleration, historical longitudinal speed, historical lateral speed, historical longitudinal acceleration change rate, historical yaw rate, historical accelerator pedal position and historical braking force of the target vehicle in a plurality of preset historical time periods are taken as a driving data set, and the driving data set is uploaded to a cloud control platform to filter the driving data set through the cloud control platform to obtain a filtered driving data set; extracting feature parameters in the filtered driving data set; based on the feature parameters, the historical driving condition category label value of part of the first driving data in the first driving data set in the plurality of preset historical time periods, and the historical driving style category label value of part of the first driving data in the first driving data set in the plurality of preset historical time periods, the first driving data set is constructed.

4. The method of claim 3, wherein The feature parameters in the filtered driving data set are extracted, comprising: confirming the maximum value, minimum value, mean value, standard deviation, root mean square, coefficient of variation and median of all the historical longitudinal acceleration; confirming the maximum value, minimum value, mean value, standard deviation, root mean square, coefficient of variation and median of all the historical lateral acceleration; confirming the maximum value, minimum value, mean value, standard deviation, root mean square, coefficient of variation and median of all the historical longitudinal speed; confirming maximum, minimum, mean, standard deviation, root mean square, coefficient of variation and median of all the historical lateral velocities; confirming maximum, minimum, mean, standard deviation, root mean square, coefficient of variation and median of all the historical longitudinal acceleration rates; confirming maximum, minimum, mean, standard deviation, root mean square, coefficient of variation and median of all the historical yaw rates; confirming maximum, minimum, mean, standard deviation, root mean square, coefficient of variation and median of all the historical acceleration pedal positions; confirming maximum, minimum, mean, standard deviation, root mean square, coefficient of variation and median of all the historical braking forces; confirming maximum, minimum, mean, standard deviation, root mean square, coefficient of variation and median of all the historical longitudinal accelerations, maximum, minimum, mean, standard deviation, root mean square, coefficient of variation and median of all the historical lateral accelerations, maximum, minimum, mean, standard deviation, root mean square, coefficient of variation and median of all the historical longitudinal velocities, maximum, minimum, mean, standard deviation, root mean square, coefficient of variation and median of all the historical lateral velocities, maximum, minimum, mean, standard deviation, root mean square, coefficient of variation and median of all the historical longitudinal acceleration rates, maximum, minimum, mean, standard deviation, root mean square, coefficient of variation and median of all the historical yaw rates, maximum, minimum, mean, standard deviation, root mean square, coefficient of variation and median of all the historical longitudinal acceleration rates, maximum, minimum, mean, standard deviation, root mean square, coefficient of variation and median of all the historical acceleration pedal positions, and maximum, minimum, mean, standard deviation, root mean square, coefficient of variation and median of all the historical braking forces as the characteristic parameters in the filtered driving data set.

5. The method of claim 4, wherein The method further comprises: updating the driver driving style recognition result of the target vehicle to the target vehicle, so that the target vehicle determines a driving style strategy based on the driver driving style recognition result; without affecting the normal driving needs of the driver, the driving style strategy is integrated into the vehicle control system of the target vehicle; 6. The method of claim 5, wherein in the case that the driver ends the current driving trip, generating a revisit information of the driver, so that the driver replies to the revisit information of the driver to obtain a revisit result. ​ ​ ​ 7. The method of claim 1, wherein The initial driving style recognition model is constructed, comprising: An initial driving style recognition model is constructed through a cloud control platform.

8. A driver driving style recognition system characterized by, The driver driving style recognition system comprises: A data acquisition module configured to acquire a first driving data set and second driving data of a target vehicle, wherein the second driving data is driving data of the target vehicle at a current time, the first driving data set comprises historical driving data of the target vehicle, and part of the first driving data in the first driving data set further comprises a historical driving condition category label value and a historical driving style category label value; A model training module configured to construct an initial driving style recognition model, input the first driving data set into the initial driving style recognition model for model training, and obtain a trained driving style recognition model; A result output module configured to input the second driving data into the trained driving style recognition model, and obtain a driver driving style recognition result of the target vehicle.

9. A driver driving style recognition apparatus characterized by comprising: The computer readable storage medium stores computer executable instructions for causing a computer to execute a driver driving style recognition method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer readable storage medium stores computer executable instructions for causing a computer to execute a driver driving style recognition method according to any one of claims 1 to 7.

Images