A driving mode configuration method, electronic device, and computer storage medium

Abstract

The application discloses a driving mode configuration method, an electronic device and a computer storage medium. The method comprises the following steps: in response to the starting of a vehicle, collecting the identity information of a driver, and determining whether the driving mode matching the identity information is not stored; if so, obtaining driving habit feature information, inputting the driving habit feature information into a preset neural network model to fit the driving mode matching the identity information; and configuring the driving mode as the current driving mode of the vehicle. In the application, after the starting of the vehicle, the identity information of the driver is collected, and when the vehicle does not store the driving mode matching the identity information, the driving habit feature information of the driver is obtained, and then the driving habit feature information is input into the preset neural network model to fit the driving mode matching the identity information. In this way, the controllability of the driver on the vehicle is improved, and the personal safety and the driving safety are effectively ensured.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of driving mode configuration, in particular to a driving mode configuration method, an electronic device and a computer storage medium. BACKGROUND

[0002] The existing vehicles are often configured with multiple driving modes set when leaving the factory, and each driving mode is calibrated by chassis calibration experts according to the configuration of the vehicle. For example, the common driving modes include gentle, standard and sport.

[0003] However, different drivers have different driving habits, and the driving mode set by the vehicle when leaving the factory may not be adapted to the driving habits of the driver, which affects the controllability of the driver to the vehicle, and causes the personal safety and driving safety to be unable to be effectively guaranteed. SUMMARY

[0004] In view of the above technical problems, the present application provides a driving mode configuration method, an electronic device and a computer storage medium, aiming at solving the problem that the driving mode provided by the existing vehicle when leaving the factory is relatively limited, and cannot be adaptively configured according to different drivers, resulting in the personal safety and driving safety being unable to be effectively guaranteed.

[0005] To solve the above technical problems, the present application provides a driving mode configuration method, which comprises:

[0006] In response to the start of the vehicle, the identity information of the driver is collected, and it is judged whether the driving mode matched with the identity information is not stored;

[0007] If yes, the driving habit feature information is obtained, and the driving habit feature information is input into a preset neural network model to fit the driving mode matched with the identity information;

[0008] The driving mode is configured as the current driving mode of the vehicle.

[0009] Optionally, the input of the driving habit feature information into the preset neural network model to fit the driving mode matched with the identity information comprises:

[0010] At least two of the pedal stroke information, the steering amplitude information and the seat position information are obtained from the driving habit feature information, and at least two of the pedal stroke information, the steering amplitude information and the seat position information are fused by the preset neural network model to fit the driving mode matched with the identity information.

[0011] Optionally, the obtaining at least two of the pedal stroke information, the steering amplitude information and the seat position information from the driving habit feature information comprises:

[0012] According to a preset sampling frequency, collecting brake data obtained when the driver steps on the brake pedal, and obtaining the pedal stroke information according to the brake data;

[0013] According to a preset sampling frequency, collecting steering data obtained when the driver turns the steering wheel, and obtaining the steering amplitude information according to the steering data;

[0014] According to a preset sampling frequency, collecting seat adjustment data obtained when the driver adjusts the seat, and obtaining the seat position information according to the seat adjustment data.

[0015] Optionally, the obtaining the pedal stroke information according to the brake data comprises:

[0016] According to the brake data, a first corresponding relationship between deceleration and pedal force and a second corresponding relationship between deceleration and pedal stroke are constructed respectively;

[0017] The first corresponding relationship and the second corresponding relationship are fused by the preset neural network model to fit the pedal stroke information.

[0018] Optionally, the obtaining the steering amplitude information according to the steering data comprises:

[0019] According to a preset torque threshold interval, first sub-steering data conforming to steering behavior and second sub-steering data conforming to U-turn behavior are screened from the steering data;

[0020] The first sub-steering data and the second sub-steering data are fused by the preset neural network model to fit the steering amplitude information.

[0021] Optionally, the obtaining the seat position information according to the seat adjustment data comprises:

[0022] The seat adjustment data is divided to obtain seat height data, seat front and back data, backrest angle data, lumbar protrusion data, seat corner data and backrest corner data;

[0023] At least two of the seat height data, the seat front and back data, the backrest angle data, the lumbar protrusion data, the seat corner data and the backrest corner data are fused by the preset neural network model to fit the seat position information.

[0024] Optionally, before the at least two of the pedal stroke information, the steering amplitude information and the seat position information are fused by the preset neural network model, the method further comprises:

[0025] When the vehicle is turned off, it is determined whether the number of the pedal stroke information, the steering amplitude information and the seat position information all reach a preset number threshold;

[0026] If yes, the at least two of the pedal stroke information, the steering amplitude information and the seat position information are fused by the preset neural network model;

[0027] If no, when the vehicle is started next time, the step of acquiring the driving habit feature information is continuously executed until the number of the pedal stroke information, the steering amplitude information and the seat position information all reach the preset number threshold.

[0028] Optionally, the identity information of the driver is collected by:

[0029] collecting facial feature information and / or voice feature information of the driver, and integrating the facial feature information and / or the voice feature information to acquire the identity information.

[0030] The application further provides an electronic device, comprising a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the driving mode configuration method as described above when executing the computer program.

[0031] The application further provides a computer storage medium, which stores a computer program, wherein the computer program is executed by the processor to implement the steps of the driving mode configuration method as described above.

[0032] In the application, after the vehicle is started, the identity information of the driver is collected, and when the vehicle does not store a driving mode matching the identity information, the driving habit feature information of the driver is acquired, and the driving habit feature information is input into a preset neural network model to fit a driving mode matching the identity information, so that the controllability of the driver to the vehicle is improved, and the personal safety and the driving safety are effectively ensured. BRIEF DESCRIPTION OF DRAWINGS

[0033] In order to more clearly illustrate the technical solutions of the embodiments of the application, the following will briefly introduce the drawings needed to be used in the embodiments. It should be understood that the following drawings only show some of the embodiments of the application, and therefore should not be considered as a limitation to the scope. For those skilled in the art, other related drawings can also be obtained without creative labor.

[0034] Figure 1 is a module schematic diagram of a driving mode configuration method according to an embodiment of the present application.

[0035] Figure 2 is a fitting curve schematic diagram of a first corresponding relationship according to an embodiment of the present application.

[0036] Figure 3 is a fitting curve schematic diagram of a second corresponding relationship according to an embodiment of the present application.

[0037] Figure 4 is a fitting curve schematic diagram of a steering assist style according to an embodiment of the present application.

[0038] Figure 5 is a module schematic diagram of a driving mode configuration system according to an embodiment of the present application.

[0039] Figure 6 is a structure schematic diagram of an electronic device according to an embodiment of the present application.

[0040] Legend of reference signs:

[0041] 10, brake pedal sensor; 20, steering assist sensor; 30, seat position memory module; 40, camera module; 50, storage module.

[0042] 310, processor; 311, memory; 312, network interface; 313, bus system. DETAILED DESCRIPTION

[0043] The implementation of the present application will be described by specific embodiments hereinafter, and those skilled in the art can easily understand other advantages and effects of the present application from the content disclosed in the specification.

[0044] In the following description, reference is made to the accompanying drawings, which form a part hereof, and in which are shown, by way of illustration, several embodiments of the present application. It is understood that other embodiments can be utilized and mechanical, structural, electrical, and operational changes can be made without departing from the spirit and scope of the present application. The following detailed description is, therefore, not to be taken in a limiting sense, as the sole purpose of the description is to describe the particular embodiments, and not to describe every possible embodiment.

[0045] Although the terms first, second, etc. can be used herein to describe various elements, these elements should not be limited by these terms. These terms are only used to distinguish one element from another.

[0046] Also, as used herein, the singular forms "a", "an" and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will be further understood that the terms "comprises", "comprising", "includes" and / or "including", when used herein, specify the presence of stated features, steps, operations, elements, components, items, and / or groups but do not preclude the presence or addition of one or more other features, steps, operations, elements, components, items, and / or groups thereof. As used herein, the terms "or" and "and / or" are to be interpreted as inclusive, i.e., as meaning one or any combination of the items. Thus, "A, B or C" or "A, B and / or C" means any of the following: A; B; C; A and B; A and C; B and C; A, B and C. Exceptions to this definition will only occur when the combination of elements, functions, steps or acts are mutually exclusive as a matter of some significance.

[0047] The following first explains the terms that may be involved in the present application, as follows:

[0048] A BP neural network, also known as a Back Propagation neural network, is a multi-layer feedforward neural network that can perform nonlinear transformation on input data and adjust the weights and biases in the network through a learning process to minimize prediction errors. The BP neural network is one of the most fundamental and important models in the field of deep learning and machine learning.

[0049] Please refer to Figure 1 , Figure 1 A module flowchart illustrating a driving mode configuration method is shown, and the method comprises:

[0050] S1, in response to the start of the vehicle, the identity information of the driver is collected, and it is determined whether the driving mode matching the identity information is not stored. Specifically, in an embodiment, when the driver sits in the driver's seat of the vehicle and starts the vehicle, the camera module carried by the vehicle will collect the identity information of the driver. Then, the system will automatically perform the step of searching in the storage module to determine whether the driving mode matching the identity information is not stored in the storage module. Wherein, for different drivers, the identity information of each driver will be stored in the storage module of the vehicle after being collected.

[0051] S2, if so, the driving habit feature information is obtained. Specifically, in an embodiment, if it is determined that the driving mode matching the identity information of the current driver is not stored in the storage module of the vehicle, the system will automatically perform the step of obtaining the driving habit feature information.

[0052] The driving habit feature information may be, for example, pedal stroke information, steering amplitude information, seat position information, vehicle body height information, steering wheel height information, tire hub size information, engine output horsepower information, and the like, without being limited thereto.

[0053] Further, the system will automatically input the driving habit feature information into a preset neural network model, and then fit a driving mode matching the identity information.

[0054] The preset neural network model uses a quintic polynomial to fit the driving habit feature information, and then fits a driving mode that conforms to the driving habit of the driver. After fitting a driving mode matching the identity information for different drivers, the driving mode corresponding to the identity information of each driver is stored in the storage module of the vehicle and is bound with the identity information. Thereafter, when the driver is identified by the camera module while driving the vehicle, the vehicle can automatically switch to a driving mode that conforms to the driving habit of the driver according to the identity information.

[0055] S3, configure the driving mode as the current driving mode of the vehicle. Specifically, after fitting the driving mode that conforms to the driving habit of the driver in step S2, the vehicle will automatically configure the driving mode as the current driving mode, and the entire process can be completed without manual operation by the driver, providing a good user experience.

[0056] By executing the driving mode configuration method of steps S1-S3, first, the identity information of the driver is collected after the vehicle is started. Second, when the vehicle does not store a driving mode matching the identity information, the driving habit feature information is obtained, and finally, it is input into a preset neural network model to fit a driving mode matching the identity information, and configure it as the current driving mode.

[0057] In this way, the driver can more intuitively perceive the response state of the vehicle performance system, thereby accurately controlling the braking force and steering force. Not only does it enhance the driver's grasp of the vehicle dynamics, but it also helps the driver quickly respond correctly in emergency situations, effectively shortens the braking distance and controls the steering angle, significantly reduces the probability of traffic accidents, improves the driver's control of the vehicle, and effectively ensures personal safety and driving safety.

[0058] In addition, the driving mode obtained by executing the driving mode configuration method of steps S1-S3 can also improve the overall driving experience. Especially in high-speed driving or complex road conditions, it can effectively help the driver to make early judgments and adjust the speed in a timely manner, ensuring driving safety while improving ride comfort and driving experience.

[0059] Optionally, the input of the driving habit feature information into the preset neural network model to fit the driving mode matching the identity information in step S2 comprises:

[0060] At least two of the pedal stroke information, the steering amplitude information and the seat position information are obtained from the driving habit feature information, and the at least two of the pedal stroke information, the steering amplitude information and the seat position information are fused by the preset neural network model to fit the driving mode matching the identity information. Specifically, in the embodiment, the driving habit feature information is preferably at least two of the pedal stroke information, the steering amplitude information and the seat position information, and it can be known by enumeration that the driving habit feature information can comprise:

[0061] (1) the pedal stroke information and the steering amplitude information; (2) the pedal stroke information and the seat position information; (3) the steering amplitude information and the seat position information; (4) the pedal stroke information, the steering amplitude information and the seat position information.

[0062] Further, the at least two of the pedal stroke information, the steering amplitude information and the seat position information are fused by the preset neural network model to fit the driving mode matching the identity information.

[0063] Optionally, the obtaining of the at least two of the pedal stroke information, the steering amplitude information and the seat position information from the driving habit feature information in the above step comprises:

[0064] S21, according to the preset sampling frequency, the brake data obtained when the driver steps on the brake pedal is collected, and the pedal stroke information is obtained according to the brake data. Specifically, in the embodiment, in the process of driving the vehicle, the system will automatically collect the brake data obtained by the brake pedal sensor when the driver steps on the brake pedal according to the preset sampling frequency. Wherein, the time node of the driver stepping on the brake pedal is the initial node of a cycle, and the time node of the driver releasing the brake pedal is the termination node of the cycle. Then, the pedal stroke information is obtained according to the obtained brake data. It can be understood that the brake data will be obtained at the preset sampling frequency in each cycle, and will be continuously performed before the number of brake data reaches enough to ensure the accuracy of the fitting result.

[0065] S22, collect steering data obtained when the driver rotates the steering wheel according to a preset sampling frequency, and obtain steering amplitude information according to the steering data. Specifically, in this embodiment, during the driving of the vehicle, the system will automatically collect the steering data obtained by the steering assist sensor when the driver rotates the steering wheel according to a preset sampling frequency. Wherein, the time node of the driver controlling the steering wheel to steer, turn around, change lanes and the like is taken as an initial node of a cycle, and the time node of the driver returning the steering wheel to the normal position is taken as a termination node of the cycle. Then, the steering amplitude information is obtained according to the obtained steering data. It can be understood that the steering data will be obtained at a preset sampling frequency in each cycle, and will be continuously performed before the number of steering data reaches a sufficient accuracy of fitting result.

[0066] S23, collect seat adjustment data when the driver adjusts the seat according to a preset sampling frequency, and obtain seat position information according to the seat adjustment data. Specifically, in this embodiment, after the vehicle is started, the system will automatically collect the seat adjustment data obtained by the seat position memory module when the driver adjusts the seat according to a preset sampling frequency. Wherein, the time node at which the driver starts to adjust the seat is taken as an initial node of a cycle, and the time node at which the driver stops adjusting the seat is taken as a termination node. Then, the seat position information is obtained according to the obtained seat adjustment data. It can be understood that the seat adjustment data will be obtained at a preset sampling frequency in each cycle, and will be continuously performed before the number of seat adjustment data reaches a sufficient accuracy of fitting result.

[0067] Optionally, in steps S21-S23, the preset sampling frequency is preferably 2000Hz, and a data set is recorded every 50Hz, and a data set is composed of 10 samples. In other words, 40 data sets, i.e. 400 samples, can be recorded per second.

[0068] Please refer to Figure 2 and Figure 3 In step S21, the pedal stroke information obtained according to the braking data includes:

[0069] S211, construct a first corresponding relationship between deceleration and pedal force, and a second corresponding relationship between deceleration and pedal stroke according to the braking data. Specifically, as shown in Figure 2 The pedal force that the vehicle can support has factory-set pedal force design target upper and lower limits, as shown in Figure 3 The vehicle has factory-set pedal stroke design target upper and lower limits. In this embodiment, the fitting between deceleration and pedal force, and the fitting between deceleration and pedal stroke are performed according to the collected braking data, so that Figure 2 and Figure 3The first corresponding relationship fitting curve (as shown in the blue curve in Figure 2 The second corresponding relationship fitting curve (as shown in the blue curve in Figure 3 It can be understood that the larger the sample size of the braking data is, the more matched the fitting curve fitted is with the driving habits of the driver.

[0070] In an embodiment, when the driver steps on the brake pedal, braking data of deep stepping and light stepping on the brake pedal is recorded respectively, which is the first corresponding relationship between deceleration and pedal force, and the second corresponding relationship between deceleration and pedal stroke. Wherein, deep stepping on the brake pedal means reaching the effective stroke limit of the brake pedal, and light stepping on the brake pedal means reaching within 50% of the effective stroke of the brake pedal.

[0071] S212, the first corresponding relationship and the second corresponding relationship are fused by a preset neural network model to fit the pedal stroke information. Specifically, in the embodiment, the first corresponding relationship and the second corresponding relationship obtained in step S211 are fused as input by the BP neural network model, and then the stepping brake pedal style conforming to the driving habits of the current driver is fitted, that is, the pedal stroke information is output.

[0072] It can be understood that gravity is the attraction of the earth to the object, and acceleration (deceleration) is the measure of the change in speed of the object under the action of gravity. On the surface of the earth, the acceleration of the object is equal to the acceleration of gravity. Therefore, as shown in Figure 2 And Figure 3 The unit of the ordinate is gravity acceleration (G).

[0073] Please refer to Figure 4 In step S22, the steering amplitude information obtained according to the steering data includes:

[0074] S221, according to the preset torque threshold interval, the first sub-steering data conforming to the steering behavior and the second sub-steering data conforming to the U-turn behavior are screened out from the steering data. Specifically, as shown in Figure 4 The steering torque that the vehicle can support has a factory-set upper and lower torque limit. In this embodiment, by setting the preset torque threshold interval, the first sub-steering data conforming to the steering behavior and the second sub-steering data conforming to the U-turn behavior in the torque threshold interval are screened out from the steering data obtained in step S22, and then the data of the driver in the process of driving the vehicle, small amplitude and large amplitude of the steering wheel are accurately divided. Wherein, the preset torque threshold interval can be set to different values according to different vehicles, which is not limited here.

[0075] S222, fitting out steering amplitude information by fusing the first sub-steering data and the second sub-steering data through a preset neural network model. Specifically, in the embodiment, the first sub-steering data and the second sub-steering data obtained in step S221 are fused as input through a BP neural network model, and then a steering assist style fitting curve conforming to the driving habit of the current driver is fitted, that is, the steering amplitude information (such as the middle red curve shown in FIG. 6) is output. Figure 4 It can be understood that in step S221, the steering behavior may, for example, include lane changing, left and right turning, and small amplitude steering behaviors such as avoiding obstacles, and the U-turn behavior is a vehicle U-turn behavior that requires the driver to steer the steering wheel at a large amplitude, for example, the steering wheel is fully turned to achieve the U-turn behavior.

[0076] Optionally, the seat position information obtained according to the seat adjustment data in step S23 includes:

[0077] S231, dividing the seat adjustment data to obtain seat height data, seat front and rear data, chair back angle data, lumbar support data, seat corner data, and chair back corner data. Specifically, in the embodiment, the seat adjustment data obtained in step S23 is divided to obtain seat height data, which means the vertical distance from the seat bottom to the chassis, seat front and rear data, which means the seat depth, chair back angle data, which means the included angle between the chair back and the cushion, lumbar support data, which means the protrusion of the seat waist support, seat corner data, which means the inward bending of the two sides of the cushion, and chair back corner data, which means the inward bending of the two sides of the chair back.

[0078] S232, fusing at least two of the seat height data, the seat front and rear data, the chair back angle data, the lumbar support data, the seat corner data, and the chair back corner data through a preset neural network model to fit out the seat position information. Specifically, in the embodiment, at least two of the seat height data, the seat front and rear data, the chair back angle data, the lumbar support data, the seat corner data, and the chair back corner data obtained in step S231 are fused as input through a BP neural network model, and then a seat adjustment style conforming to the seat adjustment habit of the current driver is fitted, that is, the seat position information is output.

[0079] Optionally, before the step of fusing at least two of the pedal stroke information, the steering amplitude information and the seat position information through the preset neural network model to fit the driving mode matched with the identity information, the method further comprises:

[0080] Optionally, before the step of fusing at least two of the pedal stroke information, the steering amplitude information and the seat position information through the preset neural network model, the method further comprises:

[0081] When the vehicle is turned off, it is determined whether the number of the pedal stroke information, the steering amplitude information and the seat position information all reaches a preset number threshold. If yes, at least two of the pedal stroke information, the steering amplitude information and the seat position information are fused through the preset neural network model. If no, the step of obtaining the driving habit feature information is continued to be executed when the vehicle is started next time until the number of the pedal stroke information, the steering amplitude information and the seat position information all reaches the preset number threshold.

[0082] Specifically, in the embodiment, when the driver turns off the vehicle, the system will automatically execute the step of determining whether the number of the pedal stroke information, the steering amplitude information and the seat position information all reaches the preset number threshold. It can be understood that the more the number of samples, the more the BP neural network model can learn the general characteristics of the data, thereby achieving the purpose of improving the prediction accuracy of the model and reducing the risk of overfitting.

[0083] The preset number threshold is preferably 10000. As described above, the preset sampling frequency is preferably 2000Hz, 40 data sets can be recorded per second, i.e. 400 samples. In other words, the collection time of 10000 samples is 25 seconds.

[0084] When the number of the pedal stroke information, the steering amplitude information and the seat position information all reaches the preset number threshold, at least two of the pedal stroke information, the steering amplitude information and the seat position information are fused through the BP neural network model, and then the driving mode matched with the identity information is fitted.

[0085] When the number of the pedal stroke information, the steering amplitude information and the seat position information does not reach the preset number threshold, the step of obtaining the driving habit feature information will be continued to be executed when the vehicle is started next time until the number of the pedal stroke information, the steering amplitude information and the seat position information all reach the preset number threshold.

[0086] For example, there is a driver Zhang and a first vehicle which has not been driven by Zhang. When Zhang sits in the driver's cabin of the first vehicle and starts, the camera module of the vehicle will execute the step of collecting the identity information of Zhang. Since Zhang has not driven the first vehicle, the driving mode matching the identity information of Zhang is not necessarily stored in the first vehicle. Then, the pedal stroke information, the steering amplitude information and the seat position information will be recorded respectively during the process that Zhang steps on / releases the brake pedal, angles / straightens the steering wheel and adjusts / stops adjusting the seat. According to the foregoing, 10000 sample quantities can be obtained for the pedal stroke information, the steering amplitude information and the seat position information within 25s. It can be understood that during a driving cycle from starting to shutting down of the first vehicle, there is a situation that some information samples of the driver Zhang are not completely collected. Therefore, when Zhang starts the first vehicle for the second time, the data whose sample quantity does not reach the preset number threshold will be continued to be collected, and the cycle will be repeated until the number of the pedal stroke information, the steering amplitude information and the seat position information all reach the preset number threshold.

[0087] Optionally, the collecting the identity information of the driver in the step S1 comprises:

[0088] The face feature information and / or the voice feature information of the driver are collected, and the face feature information and / or the voice feature information are integrated to obtain the identity information. Specifically, in the embodiment, after the vehicle is started, the face feature information (such as the shape and position of the eyes, nose and mouth) and / or the voice feature information (such as the tone, rhythm and pronunciation manner) of the driver are collected. For example, a face feature template belonging to the driver can be created by using a face recognition module which is electrically connected with the camera module. The voice feature information is captured by using a voiceprint recognition module which is electrically connected with the camera module, and a voiceprint template belonging to the driver can also be created by analyzing the frequency spectrum, rhythm and tone of the voice. In an implementation manner, the face feature information and the voice feature information can be integrated to generate the identity information which is exclusive to the driver.

[0089] Optionally, the judging whether the driving mode matching the identity information is not stored in the step S1 further comprises:

[0090] If not, the driving mode matching the identity information is configured as the current driving mode of the vehicle. Specifically, in this embodiment, after the driver sits in the driver's seat and starts the vehicle, the camera module of the vehicle will collect the identity information of the driver. At this time, when the driving mode matching the identity information of the driver can be obtained in the storage module, the vehicle will automatically configure the driving mode matching the identity information as the current driving mode of the vehicle. It can be understood that for the driver, the vehicle has generated a driving mode matching the driving habits of the driver before this start, so when the driver starts the vehicle every time subsequently, after the identity information authentication is passed, the vehicle will automatically configure the exclusive driving mode of the driver.

[0091] Please refer to Figure 5 , Figure 5 A module flowchart of a driving mode configuration system is shown, which is applied to a vehicle and includes a brake pedal sensor 10, a steering assist sensor 20, a seat position memory module 30, a camera module 40, and a storage module 50. In actual implementation, first, when the driver sits in the driver's seat of the vehicle and starts the vehicle, the camera module 40 will collect the identity information of the driver. Then, the system will automatically perform the step of searching the identity information from the storage module 50 to determine whether the driving mode matching the identity information is stored in the storage module 50. Among them, for different drivers, the identity information of each driver will be stored in the storage module 50 of the vehicle after being collected.

[0092] Secondly, if the driving mode matching the identity information is not stored in the storage module 50, the system will automatically obtain the pedal stroke information, the steering amplitude information, and the seat position information from the brake pedal sensor 10, the steering assist sensor 20, and the seat position memory module 30 according to a preset sampling frequency.

[0093] Thirdly, the system will automatically use a preset neural network model (such as a BP neural network model) to fit the pedal stroke information, the steering amplitude information, and the seat position information using a quintic polynomial, and then fit the driving mode matching the driving habits of the driver. Among them, for different drivers, the driving mode corresponding to the identity information of each driver will be stored in the storage module 50 of the vehicle after being fitted to match the identity information, and will be bound with the identity information. After that, when the driver drives the vehicle is recognized by the camera module 40, the vehicle can be automatically configured to the driving mode matching the driving habits of the driver according to the identity information.

[0094] Finally, the system configures the driving mode as the current driving mode of the vehicle, and the whole process is completed without manual operation of the driver, improves the controllability of the driver to the vehicle, and effectively guarantees the safety of the driver and the driving safety.

[0095] Based on the same inventive concept as the foregoing embodiments, the embodiments of the present application provide an electronic device, such as Figure 6 as shown, the device comprises a processor 310 and a memory 311 storing a computer program; wherein, Figure 6 The processor 310 illustrated in the specification is not used to refer to the number of processors 310 being one, but is only used to refer to the positional relationship of the processor 310 relative to other devices. In actual application, the number of processors 310 can be one or more; similarly, Figure 6 The memory 311 illustrated in the specification also has the same meaning, that is, it is only used to refer to the positional relationship of the memory 311 relative to other devices. In actual application, the number of memories 311 can be one or more. When the processor 310 runs the computer program, the method applied to the above-mentioned device is realized.

[0096] The device can further comprise at least one network interface 312. Various components in the device are coupled together through a bus system 313. It can be understood that the bus system 313 is used to realize the connection and communication between the components. The bus system 313 includes not only a data bus, but also a power supply bus, a control bus and a status signal bus. However, for the purpose of clear illustration, all kinds of buses are marked as the bus system 313 in the specification. Figure 6

[0097] ​The memory 311 can be a volatile memory or a nonvolatile memory, and can include both a volatile and a nonvolatile memory. The nonvolatile memory can be a Read Only Memory (ROM), a Programmable Read-Only Memory (PROM), an Erasable Programmable Read-Only Memory (EPROM), an Electrically Erasable Programmable Read-Only Memory (EEPROM), a ferroelectric random access memory (FRAM), a flash memory, a magnetic memory, an optical memory, or a compact disc read-only memory (CD-ROM). The magnetic memory can be a magnetic disk memory or a magnetic tape memory. The volatile memory can be a random access memory (RAM) used as an external cache. By way of example, but not limitation, many forms of RAM can be used, such as a Static Random Access Memory (SRAM), a Synchronous Static Random Access Memory (SSRAM), a Dynamic Random Access Memory (DRAM), a Synchronous Dynamic Random Access Memory (SDRAM), a Double Data Rate Synchronous Dynamic Random Access Memory (DDR SDRAM), an Enhanced Synchronous Dynamic Random Access Memory (ESDRAM), a Sync Link Dynamic Random Access Memory (SLDRAM), or a Direct Rambus Random Access Memory (DRRAM).The memory 311 described in the embodiments of the present application is intended to include, but not limited to, these and any other suitable type of memory.

[0098] The memory 311 in the embodiments of the present application is configured to store various types of data to support the operation of the device. Examples of the data include: any computer programs for operating on the device, such as operating systems and application programs; contact data; phonebook data; messages; pictures; videos; and the like. The operating system contains various system programs, such as a framework layer, a core library layer, a driver layer, and the like, for implementing various basic services and processing hardware-based tasks. The application programs can contain various application programs, such as a Media Player, a Browser, and the like, for implementing various application services. Here, the program for implementing the method of the embodiments of the present application can be contained in the application programs.

[0099] Based on the same inventive concept as the foregoing embodiments, the present embodiment also provides a computer readable storage medium, wherein the computer readable storage medium stores a computer program, and the computer readable storage medium can be a ferromagnetic random access memory (FRAM), a read only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), a flash memory, a magnetic surface memory, an optical disc, a compact disc read-only memory (CD-ROM), or the like. The computer readable storage medium can also be various devices including one or any combination of the above memories, such as a mobile phone, a computer, a tablet device, a personal digital assistant, or the like. The computer program stored in the computer readable storage medium is run by a processor to implement the above method. The specific step flow implemented by the computer program when executed by the processor will be described in the embodiments of the present application shown in the description, which will not be described here again. Figure 1 The description of the embodiments shown in the foregoing description will not be described here again.

[0100] Each of the technical features of the above-described embodiments can be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above-described embodiments are described, however, as long as the combinations of the technical features do not exist contradictions, it should be considered that they are within the scope of the present application.

[0101] In this document, the terms "comprise", "comprising", or any other variation thereof are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but can include other elements not expressly listed or inherent to such process, method, article, or apparatus.

[0102] All the above examples are only specific embodiments of the present application, which are used to illustrate the technical solutions of the present application, but not to limit the present application, the protection scope of the present application is not limited to this, any person skilled in the art can make equivalent transformation or replacement to the technical solutions recorded in the foregoing examples, which is included in the scope defined by the claims of the present application.

Claims

1. A driving mode configuration method, characterized in that, The method includes: In response to vehicle startup, the system collects the driver's identity information and determines whether a driving mode matching the identity information is not stored. If so, then obtain driving habit feature information and input the driving habit feature information into a preset neural network model to fit a driving mode that matches the identity information; Configure the driving mode to the current driving mode of the vehicle; The step of inputting the driving habit feature information into a preset neural network model to fit a driving pattern that matches the identity information includes: Obtain at least two of the following from the driving habit feature information: pedal travel information, steering amplitude information, and seat position information. When the vehicle is turned off, determine whether the number of the pedal travel information, steering amplitude information, and seat position information all reach a preset number threshold. If not, when the vehicle is started again, the step of obtaining driving habit feature information will continue to be executed until the number of pedal travel information, steering amplitude information and seat position information all reach the preset number threshold. If so, at least two of the pedal travel information, steering amplitude information, and seat position information are fused using a preset neural network model to fit a driving mode that matches the identity information.

2. The method according to claim 1, characterized in that, The step of obtaining at least two of the following from the driving habit feature information: pedal travel information, steering angle information, and seat position information: Braking data is collected when the driver depresses the brake pedal according to a preset sampling frequency, and the pedal travel information is obtained based on the braking data. Steering data is collected when the driver turns the steering wheel according to a preset sampling frequency, and the steering amplitude information is obtained based on the steering data. The seat adjustment data is collected according to the preset sampling frequency when the driver adjusts the seat, and the seat position information is obtained based on the seat adjustment data.

3. The method according to claim 2, characterized in that, The step of obtaining the pedal travel information based on the braking data includes: Based on the braking data, a first correspondence between deceleration and pedal force, and a second correspondence between deceleration and pedal travel are constructed respectively. The first correspondence and the second correspondence are fused using the preset neural network model to fit the pedal travel information.

4. The method according to claim 2, characterized in that, The step of obtaining the steering angle information based on the steering data includes: Based on a preset torque threshold range, the first sub-steering data that conforms to the steering behavior and the second sub-steering data that conforms to the U-turn behavior are selected from the steering data. The first sub-steering data and the second sub-steering data are fused using the preset neural network model to fit the steering amplitude information.

5. The method according to claim 2, characterized in that, The step of obtaining the seat position information based on the seat adjustment data includes: The seat adjustment data is divided to obtain seat height data, seat fore-aft data, backrest angle data, lumbar support protrusion data, seat corner protection data, and backrest corner protection data; The preset neural network model fuses at least two of the following data: seat height, seat fore-aft data, backrest angle data, lumbar support protrusion data, seat corner protector data, and backrest corner protector data, in order to fit the seat position information.

6. The method according to claim 1, characterized in that, The collected driver identity information includes: Collect the driver's facial features and / or voice features, and integrate the facial features and / or voice features to obtain the identity information.

7. An electronic device, characterized in that, It includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the driving mode configuration method as described in any one of claims 1 to 6.

8. A computer storage medium, characterized in that, The computer storage medium stores a computer program that, when executed by a processor, implements the steps of the driving mode configuration method as described in any one of claims 1 to 6.

Images