Driving mode switching method and device and storage medium

Through the automated driving mode switching method, using scene working conditions and pedal control feature data, the problem of low application rate caused by manual driving mode switching in the prior art is solved, and the accuracy of driving experience and pattern matching is improved.

CN118928412APending Publication Date: 2024-11-12YUXIN INTELLIGENT CHASSIS SYSTEM (HUBEI) CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411323277.8
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-09-20
Publication Date
2024-11-12

AI Technical Summary

Technical Problem

Switching driving modes in existing cars requires manual operation by the driver, which leads to low application rates and is difficult to choose a suitable driving mode, affecting the driving experience.

Method used

By determining the scene working conditions of the vehicle, and using a pre-trained classification model to predict the mode switching decision results based on the pedal control feature data, the driving mode is automatically adjusted to realize automatic switching of the driving mode.

Benefits of technology

Without analyzing the correlation between driving style and mode, it can deeply analyze driving habits and preferences, automatically provide drivers with the most suitable operating conditions in the scenario, improve driving experience and improve the application rate of driving modes.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118928412A_ABST
    Figure CN118928412A_ABST
Patent Text Reader

Abstract

The embodiment of the invention provides a driving mode switching method and device and a storage medium, and the method comprises the steps: determining the scene working condition of a road section where a vehicle runs; acquiring pedal control characteristic data acquired by the vehicle in the previous acquisition period; predicting a mode switching decision result of the vehicle under the scene working condition based on the pedal control characteristic data through a pre-trained classification model matched with the scene working condition; according to the mode switching decision result, the driving mode of the vehicle is adjusted, and through the driving mode switching method and device, the problem that the application rate of the driving mode is low due to manual switching of the driving mode in a driving mode switching method in the related technology is solved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The embodiments of the present application relate to the field of automobile intelligent assisted driving technology, and more specifically, to a method, device and storage medium for switching driving modes. Background Art

[0002] Many mass-produced models on the market are equipped with the function of manually selecting driving modes to meet the driving style of each driver and different driving scenarios. The operation of the accelerator pedal is different in different driving modes.

[0003] Currently, there is little research on optimal driving mode recognition for drivers. Drivers' driving styles are generally divided into three categories: aggressive, steady, and conservative, and the data lacks objectivity. Current mass-produced models require direct operation by the driver to change the driving mode. The driver may not have enough understanding of each mode, and it is inconvenient to switch modes, resulting in low frequency of use of this function and the driver cannot choose a driving mode that suits him well. Summary of the invention

[0004] The embodiments of the present application provide a driving mode switching method, device and storage medium to at least solve the problem of low application rate of driving mode due to manual switching of driving mode in the driving mode switching method in the related art.

[0005] According to one embodiment of the present application, a method for switching a driving mode is provided, comprising: determining a scenario condition of a road section on which a vehicle is traveling; acquiring pedal manipulation feature data collected by the vehicle in a previous collection cycle; predicting a mode switching decision result of the vehicle under the scenario condition based on the pedal manipulation feature data through a pre-trained classification model that matches the scenario condition; and adjusting the driving mode of the vehicle according to the mode switching decision result.

[0006] According to another embodiment of the present application, a driving mode switching device is provided, including: a working condition determination module, used to determine the scene working condition of the road section on which the vehicle is traveling; a data acquisition module, used to obtain pedal operation feature data collected by the vehicle in the previous acquisition cycle; a prediction module, used to predict the mode switching decision result of the vehicle under the scene working condition based on the pedal operation feature data through a pre-trained classification model matching the scene working condition; and a mode switching module, used to adjust the driving mode of the vehicle according to the mode switching decision result.

[0007] According to another aspect of an embodiment of the present application, a computer-readable storage medium is provided, in which a computer program is stored, wherein the computer program is configured to execute the above-mentioned driving mode switching method when running.

[0008] According to another aspect of an embodiment of the present application, an electronic device is also provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the driving mode switching method through the computer program.

[0009] According to another embodiment of the present application, a computer program product is provided, including a computer program, and when the computer program is executed by a processor, the steps in any of the above-mentioned driving mode switching method embodiments are implemented.

[0010] Through the embodiments of the present application, a pre-trained classification model that matches the scene conditions of the road section on which the vehicle is traveling is used, and based on the pedal operation feature data collected by the vehicle in the previous collection cycle, the mode switching decision result of the vehicle under the scene conditions is predicted. According to the mode switching decision result, the vehicle's driving mode is adjusted, thereby realizing automatic switching of driving modes. There is no need to analyze the correlation between the driver's driving style and the driving mode. The driver's driving habits and driving preferences can be deeply analyzed based on the pedal operation feature data, and the driver is automatically provided with the most suitable scene conditions for the vehicle at present, thereby improving the driver's driving experience and increasing the application rate of the driving mode. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] Figure 1 It is a hardware structure block diagram of an optional driving mode switching method of an embodiment of the present application;

[0012] Figure 2 is a flow chart of an optional method for switching driving modes according to an embodiment of the present application;

[0013] Figure 3 is a schematic diagram of an application of an optional classification model according to an embodiment of the present application;

[0014] Figure 4 is a schematic diagram of an optional method of obtaining training samples according to an embodiment of the present application;

[0015] Figure 5 is a schematic diagram of training an optional classification model according to an embodiment of the present application;

[0016] Figure 6 is a structural block diagram of an optional driving mode switching device according to an embodiment of the present application;

[0017] Figure 7 It is a structural block diagram of an optional electronic device according to an embodiment of the present application. DETAILED DESCRIPTION

[0018] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present application.

[0019] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0020] According to one aspect of an embodiment of the present application, a method for switching a driving mode is provided. Optionally, in this embodiment, the method for switching a driving mode can be applied to Figure 1 In the hardware environment composed of the vehicle terminal 102 and the server 104 shown in FIG. Figure 1 As shown, the server 104 is connected to the vehicle-mounted terminal 102 via a network, and can be used to provide services (such as application services, etc.) for the terminal or a client installed on the terminal. A database can be set up on the server or independently of the server to provide data storage services for the server 104. Cloud computing and / or edge computing services can be configured on the server or independently of the server to provide data computing services for the server 104.

[0021] The above network may include but is not limited to at least one of the following: wired network, wireless network. The above wired network may include but is not limited to at least one of the following: wide area network, metropolitan area network, local area network, and the above wireless network may include but is not limited to at least one of the following: WIFI, Bluetooth.

[0022] The driving mode switching method of the embodiment of the present application can be executed by the vehicle terminal 102, or can be executed by the server 104 and the vehicle terminal 102 together. Taking the vehicle terminal 102 executing the driving mode switching method of the embodiment as an example, Figure 2 is a flow chart of an optional method for switching driving modes according to an embodiment of the present application, such as Figure 2As shown, the process of the method may include the following steps:

[0023] Step S202, determining the scene conditions of the road section on which the vehicle is traveling.

[0024] Among them, scenario conditions refer to the combination of various specific road and environmental conditions that a vehicle may encounter during actual driving. For example, scenario conditions may include urban conditions, suburban conditions, and highway conditions. Among them, urban conditions refer to the road conditions and environmental conditions that a vehicle faces when driving in an urban area; urban conditions usually include features such as congested traffic, frequent starts and stops, low-speed driving, complex intersections, and interference from pedestrians and non-motor vehicles. Suburban conditions refer to the road conditions and environmental conditions encountered by a vehicle when driving in the suburbs of a city or in the urban-rural fringe. Suburban conditions are usually between cities and rural areas, with some characteristics of cities (such as traffic signals and pedestrian flow) and open roads and less traffic in rural areas. Highway conditions refer to the road conditions and environmental conditions in which a vehicle is traveling on a highway or expressway. Under this high-speed condition, the vehicle can usually maintain a relatively high and stable speed, and the traffic flow is relatively stable with less traffic interference.

[0025] Specifically, the electronic control unit of the vehicle-mounted terminal obtains the scene conditions corresponding to the current driving section of the vehicle based on the high-precision map.

[0026] Step S204, acquiring pedal manipulation characteristic data collected by the vehicle in the previous collection cycle.

[0027] The collection cycle refers to the time interval at which the sensors or data collection systems on the vehicle record the vehicle status or operation data at regular intervals (such as a few seconds, tens of seconds or minutes). For example, a driving mode online matching cycle is 3 minutes, so the pedal operation feature data is collected every 3 minutes, and the current driving mode of the vehicle is matched according to the pedal operation feature data.

[0028] Pedal operation characteristic data refers to data related to the operation of vehicle pedals (such as accelerator pedal, brake pedal, etc.). Pedal operation characteristic data can reflect the driver's control intention of the vehicle and the actual response of the vehicle. Pedal operation characteristic data is obtained from the CAN bus, usually including the pedal opening (i.e. the depth or angle of the pedal being stepped on), the pedal operation speed (i.e. the speed of the pedal opening change), the pedal operation frequency (i.e. the number of times the pedal is operated per unit time), etc. The sampling frequency is 100Hz.

[0029] Specifically, the vehicle-mounted terminal collects pedal operation characteristic data according to a set collection cycle, determines the collection cycle of the vehicle after determining the scene conditions of the road section on which the vehicle is traveling, and obtains the pedal operation characteristic data collected in the previous collection cycle.

[0030] Step S206 , predicting the mode switching decision result of the vehicle under the scenario conditions based on the pedal operation feature data through a pre-trained classification model that matches the scenario conditions.

[0031] Among them, the classification model is a machine learning model. In the vehicle driving system, the classification model can predict the state the vehicle should be in or the operation it should perform based on the input features (such as pedal operation feature data). The classification model is usually pre-trained based on a large amount of historical data so that it can accurately classify new and unseen data. In the vehicle system, the classification model can be applied to a variety of scenarios, including driving mode recognition, gear shifting decisions, etc. By learning and identifying the mode switching rules in different driving scenarios, the classification model can help the vehicle terminal make more reasonable and intelligent decisions.

[0032] The mode switching decision result refers to the decision made on how the vehicle should adjust its operating mode based on factors such as the current state of the vehicle, the driver's intention, and the external environment. In the vehicle power management system, the mode switching decision result usually refers to the decision result of the gear shift decision (such as upshift, downshift) or the driving mode switch (such as economy mode, comfort mode, sports mode, etc.). The mode switching decision result is used to control the controller of the driving mode switch to complete the switching of the driving mode. For example, if the initial driving mode is comfort mode, and the output result of the previous online matching cycle (ie, the acquisition cycle) is a mode upshift, the corresponding driving mode will be switched to sports mode.

[0033] Specifically, the vehicle terminal establishes corresponding classification models for different scene conditions, and trains the classification models corresponding to the scene conditions based on a large amount of historical data under the corresponding scene conditions to obtain a pre-trained classification model that matches the scene conditions. After determining the scene conditions of the road section where the vehicle is traveling, the pre-trained classification model that matches the scene conditions is called, and the pedal operation feature data collected by the vehicle in the previous collection cycle is input into the classification model. The classification model analyzes the pedal operation feature data to obtain the mode switching decision result of the vehicle under the scene conditions.

[0034] Step S208, adjusting the driving mode of the vehicle according to the mode switching decision result.

[0035] Among them, driving mode refers to a setting that allows the vehicle to provide different driving experiences and performances by adjusting the working status of key components such as the engine, transmission, suspension system, and steering system according to different driving needs and environmental conditions. Each driving mode provides a unique driving experience and performance characteristics by adjusting the working parameters of the vehicle's key systems (such as the engine, transmission, suspension system, etc.). For example, considering the individual differences of drivers and the changing driving scenarios, many mass-produced models on the market are currently equipped with manual selection functions for driving modes, covering multiple modes such as economic mode, comfort mode, and sports mode. The accelerator pedal operation in each mode has different responses. For example, when the driver steps on the same pedal stroke, the sports mode will produce greater torque and faster response, which can allow the driver to feel the vehicle's handling performance more deeply and improve driving pleasure and satisfaction. Since each driving mode has its own characteristics, different drivers will prefer different driving modes when dealing with different driving scenarios. If the driver is not provided with a suitable driving mode, the driver may feel that the vehicle response is insufficient or excessive.

[0036] Generally, different driving modes correspond to different gears. In different driving modes, when the driver steps on the same pedal stroke, the longitudinal response of different driving modes is different, that is, the same accelerator pedal operation in each mode has a different response. This is because the rate limit of the base torque and torque gain (the system between the accelerator pedal and the traction torque) will change according to the change of the driving mode. As the torque gain increases, the traction torque will increase under the same pedal input; as the rate limit becomes larger, the traction torque response becomes faster under the same base torque change, that is, when the driver performs the same pedal operation in different driving modes, the vehicle's longitudinal performance is also different. For example, when the driver steps on the same pedal stroke, the sports mode will produce greater torque and faster response, which can allow the driver to feel the vehicle's handling performance more deeply and improve driving pleasure and satisfaction.

[0037] Specifically, the vehicle terminal determines whether the mode switching conditions are met based on the vehicle's current driving mode. If so, the vehicle's current driving mode is adjusted based on the mode switching decision result so that the vehicle's current driving mode matches the current scene conditions.

[0038] In some embodiments, the mode switching condition may be that the current driving environment of the vehicle meets the requirements for mode switching, for example, the current driving environment is not suitable for adjustment to a driving mode with higher longitudinal responsiveness, and the current driving mode will not be adjusted even if the mode switching decision result indicates an upshift. Alternatively, the current gear of the vehicle can be further adjusted.

[0039] In the above-mentioned driving mode switching method, a pre-trained classification model that matches the scene conditions of the road section on which the vehicle is traveling is used to predict the mode switching decision result of the vehicle under the scene conditions based on the pedal operation feature data collected by the vehicle in the previous collection cycle. According to the mode switching decision result, the vehicle's driving mode is adjusted to achieve automatic switching of driving modes. There is no need to analyze the correlation between the driver's driving style and the driving mode. The driver's driving habits and driving preferences can be deeply analyzed based on the pedal operation feature data, and the driver can be automatically provided with the most suitable scene conditions for the vehicle, thereby improving the driver's driving experience and increasing the application rate of the driving mode.

[0040] In an exemplary embodiment, a pre-trained classification model matching the scene condition is used to predict the mode switching decision result of the vehicle under the scene condition based on the pedal operation feature data, including:

[0041] 1. Determine a pre-trained classification model that matches the scenario conditions.

[0042] Among them, each scenario condition corresponds to a different classification model.

[0043] Specifically, after the vehicle-mounted terminal determines the current scene condition of the vehicle, it calls a pre-trained classification model that matches the current scene condition locally.

[0044] Second, the pedal manipulation feature data is subjected to dimensionality reduction processing through a classification model to obtain a plurality of feature common factors; the plurality of feature common factors are used to characterize a plurality of pedal manipulation features that are unrelated to each other.

[0045] The collected pedal manipulation characteristic data includes multiple data. Taking the pedal manipulation characteristic data under urban working conditions as an example, the pedal manipulation characteristic data includes the maximum value of the accelerator pedal opening, the average value of the accelerator pedal opening, the standard deviation of the accelerator pedal opening, the maximum value of the accelerator pedal opening change rate, the average value of the accelerator pedal opening change rate, the standard deviation of the accelerator pedal opening change rate, the non-zero time proportion of the accelerator pedal opening, the maximum value of the accelerator pedal pressure, the average value of the accelerator pedal pressure, and the standard deviation of the accelerator pedal pressure. For the convenience of representation, as shown in Table 1, these characteristic parameters are respectively expressed as P 1 , P 2 , P 3 ,…,P 10 express.

[0046] Table 1

[0047] <![CDATA[P 1 ]]> Maximum accelerator pedal opening <![CDATA[P 6 ]]> Standard deviation of the accelerator pedal opening rate <![CDATA[P 2 ]]> Average value of accelerator pedal opening <![CDATA[P 7 ]]> The proportion of non-zero time of the accelerator pedal opening <![CDATA[P 3 ]]> Standard deviation of accelerator pedal opening <![CDATA[P 8 ]]> Maximum accelerator pedal pressure <![CDATA[P 4 ]]> Maximum value of the accelerator pedal opening rate <![CDATA[P 9 ]]> Average accelerator pedal pressure <![CDATA[P 5 ]]> The average value of the accelerator pedal opening rate <![CDATA[P 10 ]]> Standard deviation of accelerator pedal pressure

[0048] The 10 characteristic parameters extracted above can more comprehensively reflect the driver's operating characteristics of the accelerator pedal, but there is information redundancy between the parameters. In order to improve the calculation efficiency and accuracy, the classification model of this embodiment performs dimensionality reduction processing on the pedal operation characteristic data. Dimensionality reduction aims to reduce the dimension of the data while retaining the important information in the pedal operation characteristic data as much as possible. The specific dimensionality reduction method can be set according to actual needs. For example, factor analysis can be used to reduce the dimensionality of the pedal operation characteristic data.

[0049] The feature common factors are extracted from the pedal manipulation feature data through dimensionality reduction technology, and are used to represent the common variation patterns of multiple features in the pedal manipulation feature data. The feature common factors are not directly observed from the pedal manipulation feature data, but are constructed from the pedal manipulation feature data through linear combination or other methods. They are intended to capture the common variation patterns or potential structures in the pedal manipulation feature data. The feature common factors are mutually uncorrelated, that is, multiple feature common factors are as uncorrelated as possible, and each represents an independent source of information in the data.

[0050] Specifically, Figure 3 FIG. 1 is a schematic diagram of an application of a classification model in an embodiment. Figure 3 As shown, the vehicle-mounted terminal inputs the pedal operation feature data collected in the previous collection cycle into a pre-trained classification model that matches the scene working conditions. The classification model performs dimensionality reduction processing on the pedal operation feature data through factor analysis or principal component analysis to obtain a factor score coefficient matrix. According to the factor score coefficient matrix, multiple feature common factors are constructed; wherein each row of the factor score coefficient matrix represents a pedal operation feature data, and each column represents a feature common factor. The numerical value in the factor score coefficient matrix represents the score coefficient of each pedal operation feature data on the corresponding feature common factor, that is, it characterizes the contribution of the pedal operation feature data to the corresponding feature common factor score.

[0051] In some embodiments, taking the 10 pedal manipulation feature data in Table 1 as an example, the factor analysis method is used to perform dimensionality reduction processing on the 10 pedal manipulation feature data to obtain the factor score coefficient matrix A: 3×10 , according to the factor score coefficient matrix A 3×10 Three characteristic common factors F can be obtained 1 , F 2 , F 3 , the three characteristic common factors can be expressed as:

[0052]

[0053] Where a i,j Represents the factor score coefficient matrix A 3×10For the elements in , i represents the row and j represents the column.

[0054] 3. Through the classification model, supervised learning and classification of multiple feature common factors are performed to obtain the mode switching decision results of the vehicle under the scenario conditions.

[0055] Specifically, the vehicle-mounted terminal performs supervised learning classification based on multiple feature common factors through a classification model, and makes a mode switching decision result of the vehicle under the scenario conditions according to the classification result.

[0056] Through this embodiment, a classification model is used to perform dimensionality reduction processing on the pedal manipulation feature data to obtain multiple feature common factors. A large number of features in the pedal manipulation feature data can be approximately represented by a small number of feature common factors. The important information in the pedal manipulation feature data can be retained as much as possible while reducing the dimension of the pedal manipulation feature data, which helps to simplify the classification model, improve calculation efficiency and may improve the classification model performance.

[0057] In an exemplary embodiment, adjusting the driving mode of the vehicle according to the mode switching decision result includes:

[0058] Determine the gear position corresponding to the current driving mode of the vehicle; and when the mode switching decision result indicates that the mode is maintained, keep the gear position corresponding to the current driving mode of the vehicle unchanged.

[0059] Different driving modes correspond to different gears. For example, the driving modes include an economic mode, a comfort mode, and a sports mode, wherein the economic mode corresponds to the first gear, the comfort mode corresponds to the second gear, and the sports mode corresponds to the third gear.

[0060] The mode switching decision result represents mode retention, which means that the current driving mode matches the current scene condition, and therefore, there is no need to switch the current driving mode.

[0061] Specifically, the vehicle-mounted terminal determines the current driving mode and the gear corresponding to the current driving mode, and obtains the mode switching decision result output by the classification model. When the mode switching decision result indicates that the mode is maintained, the gear corresponding to the current driving mode of the vehicle is kept unchanged.

[0062] Through this embodiment, when the mode switching decision result represents mode retention, it means that the current driving mode matches the current scene condition. At this time, the gear corresponding to the current driving mode of the vehicle is kept unchanged, so that online matching of the driving mode can be achieved.

[0063] In an exemplary embodiment, after determining the gear position corresponding to the current driving mode of the vehicle, the method further includes:

[0064] When the mode switching decision result indicates a mode downshift and the current driving mode of the vehicle is not in the lowest gear, the gear corresponding to the current driving mode of the vehicle is lowered.

[0065] Among them, the mode switching decision result represents a mode downshift, which means that the current driving mode does not match the current scene condition, and the longitudinal response of the vehicle in the current driving mode is too large, and the gear corresponding to the current driving mode needs to be lowered. For example, when the driver is driving in the sports mode, he feels that the longitudinal response of the vehicle is excessive. In order to ensure safe driving and the matching of the driving mode with the scene condition, the sports mode needs to be adjusted to the comfort mode, that is, the third gear corresponding to the sports mode is reduced to the second gear corresponding to the comfort mode.

[0066] The lowest gear is the vehicle's lowest gear. When the vehicle is in the lowest gear, it cannot be lowered further. For example, when the vehicle is in economy mode, the vehicle is in first gear, which is the lowest gear.

[0067] Specifically, after the vehicle-mounted terminal determines the gear corresponding to the vehicle's current driving mode, when the mode switching decision result represents a mode downshift, it determines whether the current driving mode corresponds to the lowest gear. If the vehicle's current driving mode is not in the lowest gear, the gear corresponding to the vehicle's current driving mode is lowered.

[0068] Through this embodiment, when the mode switching decision result represents a mode downshift and the current driving mode of the vehicle is not in the lowest gear, it means that the current driving mode does not match the current scene condition, and the longitudinal response degree of the vehicle in the current driving mode is too large. At this time, lowering the gear corresponding to the current driving mode of the vehicle can achieve online matching of the driving mode.

[0069] In an exemplary embodiment, after determining the gear position corresponding to the current driving mode of the vehicle, the method further includes:

[0070] When the mode switching decision result indicates a mode downshift and the vehicle's current driving mode is in the lowest gear, the gear corresponding to the vehicle's current driving mode is kept unchanged.

[0071] When the vehicle's current driving mode is in the lowest gear, it is no longer possible to lower the gear. For example, if the vehicle's current driving mode is the economic mode, and the mode switching decision result of the previous online matching cycle represents a mode downshift, the vehicle terminal still performs the mode hold operation, that is, keeps the gear corresponding to the vehicle's current driving mode unchanged.

[0072] Specifically, after the on-board terminal determines the gear corresponding to the vehicle's current driving mode, when the mode switching decision result represents a mode downshift, it determines whether the current driving mode corresponds to the lowest gear. If the vehicle's current driving mode is in the lowest gear, the gear corresponding to the vehicle's current driving mode remains unchanged.

[0073] Through this embodiment, when the mode switching decision result represents a mode downshift, and the vehicle's current driving mode is in the lowest gear, it means that the current driving mode does not match the current scene conditions. However, the vehicle is already in the lowest gear and cannot continue to downshift. The only thing it can do is to keep the gear corresponding to the vehicle's current driving mode unchanged to ensure the vehicle's driving safety.

[0074] In an exemplary embodiment, after determining the gear position corresponding to the current driving mode of the vehicle, the method further includes:

[0075] When the mode switching decision result indicates a mode upshift and the current driving mode of the vehicle is not at the highest gear, the gear corresponding to the current driving mode of the vehicle is increased.

[0076] Among them, the mode switching decision result represents a mode upshift, which means that the current driving mode does not match the current scene condition, and the longitudinal responsiveness of the vehicle in the current driving mode is not sensitive enough, and the gear corresponding to the current driving mode needs to be increased. For example, when the driver is driving in the comfort mode, he feels that the longitudinal response of the vehicle is not sensitive enough. In order to ensure safe driving and the matching of the driving mode with the scene condition, the sport mode needs to be adjusted to the sport mode, that is, the second gear corresponding to the comfort mode is upgraded to the third gear corresponding to the sport mode.

[0077] Top gear refers to the highest gear of the vehicle. When the vehicle is in top gear, it is not possible to increase the gear further. For example, when the vehicle is in sport mode, the vehicle is in third gear, which is the highest gear, and it is not possible to increase the gear further.

[0078] Specifically, after the vehicle-mounted terminal determines the gear corresponding to the vehicle's current driving mode, when the mode switching decision result represents a mode upshift, it determines whether the current driving mode corresponds to the highest gear. If the vehicle's current driving mode is not at the highest gear, the gear corresponding to the vehicle's current driving mode is increased.

[0079] Through this embodiment, when the mode switching decision result represents a mode upshift and the vehicle's current driving mode is in the highest gear, it means that the current driving mode does not match the current scene conditions and the longitudinal responsiveness of the vehicle in the current driving mode is not sensitive enough. At this time, increasing the gear corresponding to the vehicle's current driving mode can achieve online matching of the driving mode.

[0080] In an exemplary embodiment, after determining the gear position corresponding to the current driving mode of the vehicle, the method further includes:

[0081] When the mode switching decision result indicates a mode upshift and the vehicle's current driving mode is at the highest gear, the gear corresponding to the vehicle's current driving mode is kept unchanged.

[0082] When the vehicle's current driving mode is in the highest gear, the gear cannot be increased. For example, if the vehicle's current driving mode is the sports mode, and the mode switching decision result of the previous online matching cycle represents a mode upshift, the vehicle terminal still performs the mode hold operation, that is, keeps the gear corresponding to the vehicle's current driving mode unchanged.

[0083] Specifically, after the vehicle-mounted terminal determines the gear corresponding to the vehicle's current driving mode, when the mode switching decision result represents a mode upshift, it determines whether the current driving mode corresponds to the highest gear. If the vehicle's current driving mode is in the highest gear, the gear corresponding to the vehicle's current driving mode remains unchanged.

[0084] Through this embodiment, when the mode switching decision result represents a mode upshift and the vehicle's current driving mode is in the highest gear, it means that the current driving mode does not match the current scenario conditions. However, the vehicle is already in the highest gear and cannot continue to increase the gear. The only thing it can do is to keep the gear corresponding to the vehicle's current driving mode unchanged to ensure the vehicle's driving safety.

[0085] In an exemplary embodiment, the training method of the classification model includes the following steps:

[0086] 1. Obtain multiple training samples; each of the multiple training samples includes historical pedal operation characteristic data collected when the vehicle is driving in a driving mode under a scenario, and a sample label; the sample label represents the historical mode switching decision result when the vehicle is driving in a driving mode under a scenario.

[0087] Among them, a training sample refers to a single instance in the data set used to train the machine learning model. In the scenario of vehicle driving mode switching, each training sample contains the driving data of the vehicle under certain conditions (such as a specific road type, traffic flow, weather conditions, etc.) and the decision information related to it. These training samples are used to train the model so that the model can learn and predict the best driving mode or decision in similar situations in the future.

[0088] Historical pedal operation characteristic data refers to the driver's operation record of the accelerator pedal, brake pedal and other control pedals during the historical driving process of the vehicle. The historical pedal operation characteristic data includes the pedal's stepping depth, stepping speed, duration, etc., which reflects the driver's driving habits and preferences in different scenarios and driving modes. In this embodiment, the driver's satisfaction with the driving mode can be expressed through the control of the pedal. Usually, if the driver feels that the vehicle's longitudinal response is not sensitive enough, the driver will apply more pressure to the pedal and the frequency of stepping on the accelerator pedal will be higher; on the contrary, if the driver feels that the vehicle's longitudinal response is excessive, the driver will be surprised and adjust the pedal more carefully, and the frequency of stepping on the accelerator pedal will be lower.

[0089] The sample label is associated with each training sample and represents the recommended mode switching decision result (such as whether to switch from economy mode to sports mode) based on the historical pedal operation characteristic data in this specific scenario and driving mode. The sample label is the goal of model learning. The model learns how to predict the sample label (i.e. the mode switching decision result) based on the input data (such as historical pedal operation characteristic data). The labeling process of the sample label can be done manually or automatically.

[0090] Historical mode switching decision results refer to the record of recommended mode switching decisions based on the current scene conditions, driving mode and historical pedal operation characteristic data during the vehicle's past driving process. When training machine learning models, historical mode switching decision results are used as sample labels to guide the model to learn how to make correct driving mode switching decisions in similar situations.

[0091] Specifically, each of the multiple scenario conditions is used as the current scenario condition to perform the following sample construction operations to obtain multiple training samples: multiple test personnel complete a driving task of preset duration in different driving modes under the current scenario condition, collect historical pedal operation characteristic data collected when the vehicle is driving in a driving mode under the current scenario condition, and obtain a questionnaire form corresponding to the test personnel's use of a driving mode under the current scenario condition; according to the questionnaire results, determine the most satisfactory driving mode corresponding to the use of a driving mode under the current condition; determine the sample label based on the most satisfactory driving mode; and use the historical pedal operation characteristic data collected when driving in a driving mode under the current scenario condition and the corresponding sample label as a training sample.

[0092] For example, Figure 4 FIG. 1 is a schematic diagram of obtaining training samples in an embodiment. Figure 4As shown in the figure, for three different scenarios of urban conditions, suburban conditions, and highway conditions, the economic mode, comfort mode, and sports mode are used for driving in each scenario, where the economic mode corresponds to the first gear, the comfort mode corresponds to the second gear, and the sports mode corresponds to the third gear. Each tester is arranged to perform driving tasks in urban conditions, suburban conditions, and highway conditions, and completes the driving tasks for about five minutes in the economic mode, comfort mode, and sports mode in each driving condition. In order to ensure driving safety and improve the credibility of driving data, the driver has five minutes to familiarize himself with the driving mode before each driving task. After the driving tasks in the three driving modes of each condition are completed, combined with the video information recorded by the on-board camera (including the in-car camera that records the driver's facial expression and the front-view camera that records the driving environment) (to help the tester recall the driving experience at the time), the tester is asked to fill in a questionnaire about the feelings of the three modes. According to the questionnaire results, the driver's most satisfactory driving mode is recorded, and the data under different driving modes are marked. For example, if the test subject is most satisfied with the comfort mode, the sample label corresponding to the driving data of the corresponding driver in the comfort mode is Mode Stay; when the driver drives in the economy mode, he will feel that the longitudinal response of the vehicle is not sensitive enough, and the driver will apply more pressure to the pedal and the frequency of pressing the accelerator pedal will be higher. The sample label corresponding to such driving data is Mode Upgrade; when the driver drives in the sports mode, he will feel that the longitudinal response of the vehicle is excessive, adjust the pedal more carefully, and the frequency of pressing the accelerator pedal will be lower. The sample label corresponding to such driving data is Mode Degrade.

[0093] 2. Obtain the initial model.

[0094] Among them, the initial model refers to a model built based on a certain architecture and has not been trained.

[0095] Specifically, the vehicle terminal builds an untrained initial model.

[0096] 3. Through the initial model, the historical pedal operation feature data in each training sample is reduced in dimension to obtain multiple historical feature common factors corresponding to each training sample.

[0097] Among them, the historical feature common factor is extracted from the historical pedal operation feature data through dimensionality reduction technology, and is used to represent the common change pattern of multiple features in the historical pedal operation feature data.

[0098] Specifically, Figure 5 FIG. 1 is a schematic diagram of training a classification model in an embodiment, such as Figure 5As shown, the on-board terminal inputs the historical pedal operation feature data in a training sample into the initial model. The initial model performs dimensionality reduction processing on the historical pedal operation feature data through factor analysis or principal component analysis to obtain a historical factor score coefficient matrix. According to the historical factor score coefficient matrix, multiple historical feature common factors are constructed; wherein each row of the historical factor score coefficient matrix represents a historical pedal operation feature data, and each column represents a historical feature common factor. The numerical value in the historical factor score coefficient matrix represents the score coefficient of each historical pedal operation feature data on the corresponding historical feature common factor, that is, it characterizes the contribution degree of the historical pedal operation feature data to the corresponding historical feature common factor score.

[0099] Fourth, supervised learning and classification are performed on multiple historical feature common factors corresponding to each training sample through the initial model to obtain the prediction model decision result corresponding to each training sample; according to the difference between the prediction model decision result corresponding to each training sample and the corresponding sample label, the parameters of the initial model are adjusted, and the training is stopped when the training stop condition is reached to obtain a trained classification model.

[0100] The training stop condition refers to the condition for stopping the iterative training of the model. Generally, the training stop condition can be that the model parameter reaches the target value or the number of iterations reaches the maximum value.

[0101] At present, there are few studies on the optimal driving mode identification of drivers. Many scholars divide the driving styles of drivers into aggressive, robust and conservative types through cluster learning methods. This identification method requires drivers or experts to classify driving styles first to label the data, which lacks objectivity. In addition, the mapping and matching relationship between driving mode and driving style is also worth discussing. It is not considered to directly mark the data of aggressive drivers as driving data that prefers sports mode. This embodiment is based on the online matching of driving modes based on pedal operation characteristics. There is no need to analyze the correlation between driving style and driving mode. It can deeply analyze the driver's driving habits and behaviors based on driving data, and automatically provide the driver with the most suitable driving mode for the current scenario, thereby improving the driver's driving experience.

[0102] Specifically, Figure 5 As shown, for each training sample, the vehicle terminal performs supervised learning classification based on multiple historical feature common factors of the training sample through the initial model, obtains the prediction mode decision result corresponding to the sample according to the classification result, and calculates the difference between the prediction mode decision result corresponding to each training sample and the corresponding sample label. If the difference is greater than the preset value, the parameters of the initial model are adjusted, and the iterative training process is continued until the training stop condition is reached to stop the training and obtain a trained classification model.

[0103] Through this embodiment, multiple training samples are obtained, covering historical data of the vehicle driving in different driving modes under different scene conditions, which can ensure that the model learns rich driving experience and the diversity of mode switching. These diverse data enable the model to more accurately predict and decide which driving mode to adopt in a specific scenario, thereby improving the accuracy and reliability of decision-making; because the training samples cover a variety of scene conditions and driving modes, the trained model can better adapt to and respond to unknown or complex environmental changes.

[0104] In a detailed embodiment, a method for switching a driving mode includes the following steps:

[0105] 1. Obtain multiple training samples; each of the multiple training samples includes historical pedal operation characteristic data collected when the vehicle is driving in a driving mode under a scenario, and a sample label; the sample label represents the historical mode switching decision result when the vehicle is driving in a driving mode under a scenario.

[0106] 2. Obtain the initial model.

[0107] 3. Through the initial model, the historical pedal operation feature data in each training sample is reduced in dimension to obtain multiple historical feature common factors corresponding to each training sample.

[0108] Fourth, supervised learning and classification are performed on multiple historical feature common factors corresponding to each training sample through the initial model to obtain the prediction model decision result corresponding to each training sample; according to the difference between the prediction model decision result corresponding to each training sample and the corresponding sample label, the parameters of the initial model are adjusted, and the training is stopped when the training stop condition is reached to obtain a trained classification model.

[0109] 5. Determine the scenario conditions of the road section on which the vehicle is traveling.

[0110] 6. Obtain the pedal operation characteristic data collected by the vehicle in the previous collection cycle.

[0111] 7. Determine a pre-trained classification model that matches the scenario conditions.

[0112] 8. Through the classification model, the pedal operation feature data is subjected to dimensionality reduction processing to obtain multiple feature common factors; the multiple feature common factors are used to characterize multiple pedal operation features that are unrelated to each other.

[0113] 9. Through the classification model, supervised learning classification is performed on multiple feature common factors to obtain the mode switching decision results of the vehicle under the scenario conditions.

[0114] 10. Determine the gear position that corresponds to the vehicle's current driving mode.

[0115] 11. When the mode switching decision result indicates that the mode is maintained, or when the mode switching decision result indicates that the mode is downshifted and the vehicle's current driving mode is in the lowest gear, or when the mode switching decision result indicates that the mode is upshifted and the vehicle's current driving mode is in the highest gear, execute step 12; when the mode switching decision result indicates that the mode is downshifted and the vehicle's current driving mode is not in the lowest gear, execute step 13; when the mode switching decision result indicates that the mode is upshifted and the vehicle's current driving mode is not in the highest gear, execute step 14.

[0116] 12. Keep the gear corresponding to the vehicle's current driving mode unchanged.

[0117] 13. Reduce the gear corresponding to the vehicle's current driving mode.

[0118] 14. Increase the gear corresponding to the vehicle's current driving mode.

[0119] In this embodiment, a pre-trained classification model that matches the scene conditions of the road section on which the vehicle is traveling is used to predict the mode switching decision results of the vehicle under the scene conditions based on the pedal operation feature data collected by the vehicle in the previous collection cycle. According to the mode switching decision results, the vehicle's driving mode is adjusted to achieve automatic switching of driving modes. There is no need to analyze the correlation between the driver's driving style and the driving mode. The driver's driving habits and driving preferences can be deeply analyzed based on the pedal operation feature data, and the driver can be automatically provided with the most suitable scene conditions for the vehicle at present, thereby improving the driver's driving experience and increasing the application rate of the driving mode.

[0120] It should be noted that, for the aforementioned method embodiments, for the sake of simplicity, they are all expressed as a series of action combinations, but those skilled in the art should be aware that the present application is not limited by the described order of actions, because according to the present application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the present application.

[0121] Through the description of the above implementation methods, those skilled in the art can clearly understand that the method according to the above embodiment can be implemented by means of software plus a necessary general hardware server, and of course it can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art can be embodied in the form of a software product, which is stored in a storage medium (such as ROM (Read-Only Memory) / RAM (Random Access Memory), a disk, or an optical disk), and includes a number of instructions for a terminal device (which can be a mobile phone, a computer, a server, or a network device, etc.) to execute the methods of each embodiment of the present application.

[0122] According to another aspect of the embodiment of the present application, a driving mode switching device is also provided, which is used to implement the driving mode switching method provided in the above embodiment, which has been described and will not be repeated. As used below, the term "module" can implement a combination of software and / or hardware for a predetermined function. Although the device described in the following embodiments is preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceivable.

[0123] Figure 6 is a structural block diagram of an optional driving mode switching device according to an embodiment of the present application, such as Figure 6 As shown, the device may include:

[0124] The working condition determination module 601 is used to determine the scene working condition of the road section where the vehicle is traveling;

[0125] The data collection module 602 is used to obtain the pedal operation characteristic data collected by the vehicle in the previous collection cycle;

[0126] A prediction module 603 is used to predict the mode switching decision result of the vehicle under the scenario condition based on the pedal operation feature data by using a pre-trained classification model that matches the scenario condition;

[0127] The mode switching module 604 is used to adjust the driving mode of the vehicle according to the mode switching decision result.

[0128] Through the embodiments of the present application, a pre-trained classification model that matches the scene conditions of the road section on which the vehicle is traveling is used, and based on the pedal operation feature data collected by the vehicle in the previous collection cycle, the mode switching decision result of the vehicle under the scene conditions is predicted. According to the mode switching decision result, the vehicle's driving mode is adjusted, thereby realizing automatic switching of driving modes. There is no need to analyze the correlation between the driver's driving style and the driving mode. The driver's driving habits and driving preferences can be deeply analyzed based on the pedal operation feature data, and the driver is automatically provided with the most suitable scene conditions for the vehicle at present, thereby improving the driver's driving experience and increasing the application rate of the driving mode.

[0129] The working condition determination module 601 is used to determine the scene working condition of the road section where the vehicle is traveling;

[0130] The data collection module 602 is used to obtain the pedal operation characteristic data collected by the vehicle in the previous collection cycle;

[0131] A prediction module 603 is used to predict the mode switching decision result of the vehicle under the scenario condition based on the pedal operation feature data by using a pre-trained classification model that matches the scenario condition;

[0132] The mode switching module 604 is used to adjust the driving mode of the vehicle according to the mode switching decision result.

[0133] In an exemplary embodiment, the prediction module 603 is also used to determine a pre-trained classification model that matches the scenario conditions; the pedal operation feature data is subjected to dimensionality reduction processing through the classification model to obtain multiple feature common factors; the multiple feature common factors are used to characterize multiple unrelated pedal operation features; the multiple feature common factors are subjected to supervised learning classification through the classification model to obtain a mode switching decision result of the vehicle under the scenario conditions.

[0134] In an exemplary embodiment, the mode switching module 604 is further used to determine the gear position corresponding to the current driving mode of the vehicle; when the mode switching decision result indicates that the mode is maintained, the gear position corresponding to the current driving mode of the vehicle is maintained unchanged.

[0135] In an exemplary embodiment, the mode switching module 604 is further configured to reduce the gear corresponding to the current driving mode of the vehicle when the mode switching decision result indicates a mode downshift and the current driving mode of the vehicle is not in the lowest gear.

[0136] In an exemplary embodiment, the mode switching module 604 is further configured to keep the gear corresponding to the current driving mode of the vehicle unchanged when the mode switching decision result indicates a mode downshift and the current driving mode of the vehicle is in the lowest gear.

[0137] In an exemplary embodiment, the mode switching module 604 is further configured to increase the gear corresponding to the current driving mode of the vehicle when the mode switching decision result indicates a mode upshift and the current driving mode of the vehicle is not at the highest gear.

[0138] In an exemplary embodiment, the mode switching module 604 is further configured to keep the gear corresponding to the current driving mode of the vehicle unchanged when the mode switching decision result indicates a mode upshift and the current driving mode of the vehicle is at the highest gear.

[0139] In an exemplary embodiment, the prediction module 603 is also used to obtain multiple training samples; each of the multiple training samples includes historical pedal operation characteristic data collected when the vehicle is traveling in a driving mode under a scenario, and a sample label; the sample label represents the historical mode switching decision result when the vehicle is traveling in a driving mode under a scenario; an initial model is obtained; through the initial model, the historical pedal operation feature data in each training sample is subjected to dimensionality reduction processing to obtain multiple historical feature common factors corresponding to each training sample; the multiple historical feature common factors corresponding to each training sample are subjected to supervised learning classification through the initial model to obtain the prediction mode decision result corresponding to each training sample; according to the difference between the prediction mode decision result corresponding to each training sample and the corresponding sample label, the parameters of the initial model are adjusted, and the training is stopped when the training stop condition is reached to obtain a trained classification model.

[0140] It should be noted that the examples and application scenarios implemented by the above modules and corresponding steps are the same, but are not limited to the contents disclosed in the above embodiments. It should be noted that the above modules as part of the device can be run in Figure 1 In the hardware environment shown, it can be implemented by software or by hardware, wherein the hardware environment includes a network environment.

[0141] According to another aspect of the embodiment of the present application, a storage medium is further provided. Optionally, in this embodiment, the storage medium can be used to execute the program code of any of the driving mode switching methods in the embodiment of the present application.

[0142] Optionally, in this embodiment, the storage medium may be located on at least one network device among a plurality of network devices in the network shown in the above embodiment.

[0143] Optionally, in this embodiment, the storage medium is configured to store program codes for executing the following steps:

[0144] S1. Determine the scene working condition of the road section where the vehicle is traveling;

[0145] S2, acquiring pedal manipulation characteristic data collected by the vehicle in a previous collection cycle;

[0146] S3, predicting the mode switching decision result of the vehicle under the scenario based on the pedal operation feature data by using a pre-trained classification model that matches the scenario;

[0147] S4. Adjusting the driving mode of the vehicle according to the mode switching decision result.

[0148] Optionally, the specific examples in this embodiment may refer to the examples described in the above embodiments, which will not be described in detail in this embodiment.

[0149] Optionally, in this embodiment, the storage medium may include but is not limited to: a U disk, a ROM, a RAM, a mobile hard disk, a magnetic disk or an optical disk, and other media that can store program codes.

[0150] According to another aspect of an embodiment of the present application, an electronic device for implementing the above-mentioned driving mode switching method is also provided. The electronic device may be a smart device, a server, a terminal, or a combination thereof.

[0151] Figure 7 is a structural block diagram of an optional electronic device according to an embodiment of the present application, such as Figure 7 As shown, it includes a processor 702, a communication interface 704, a memory 706 and a communication bus 708, wherein the processor 702, the communication interface 704 and the memory 706 communicate with each other through the communication bus 708, wherein,

[0152] Memory 706, used to store computer programs;

[0153] The processor 702 is used to implement the following steps when executing the computer program stored in the memory 706:

[0154] S1. Determine the scene working condition of the road section where the vehicle is traveling;

[0155] S2, acquiring pedal manipulation characteristic data collected by the vehicle in a previous collection cycle;

[0156] S3, predicting the mode switching decision result of the vehicle under the scenario based on the pedal operation feature data by using a pre-trained classification model that matches the scenario;

[0157] S4. Adjusting the driving mode of the vehicle according to the mode switching decision result.

[0158] Optionally, the communication bus may be a PCI (Peripheral Component Interconnect) bus, or an EISA (Extended Industry Standard Architecture) bus, etc. The communication bus may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 7 The communication interface is used for communication between the above electronic device and other devices.

[0159] The memory may include RAM, or may include non-volatile memory, such as at least one disk memory. Optionally, the memory may also be at least one storage device located away from the aforementioned processor.

[0160] As an example, the memory 706 may include, but is not limited to, the operating condition determination module 601, the data acquisition module 602, the prediction module 603, and the mode switching module 604 in the driving mode switching device. In addition, it may also include, but is not limited to, other module units in the driving mode switching device, which will not be described in detail in this example.

[0161] The above-mentioned processor can be a general-purpose processor, which can include but not be limited to: CPU (Central Processing Unit), NP (Network Processor), etc.; it can also be DSP (Digital Signal Processing), ASIC (Application Specific Integrated Circuit), FPGA (Field-Programmable Gate Array) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components.

[0162] Optionally, the specific examples in this embodiment may refer to the examples described in the above embodiments, and this embodiment will not be described in detail here.

[0163] It can be understood by those skilled in the art that Figure 7 The structure shown is for illustration only. The device for implementing the above-mentioned driving mode switching method may be a vehicle-mounted terminal, which may be a smart phone (such as an Android phone, an iOS phone, etc.), a tablet computer, a PDA, a mobile Internet device (Mobile Internet Devices, MID), a PAD, or other vehicle-mounted terminals. Figure 7 The structure of the electronic device is not limited. Figure 7 More or fewer components (such as network interfaces, display devices, etc.) shown in, or having Figure 7 Different configurations shown.

[0164] An embodiment of the present application further provides a computer program product, which includes a computer program. When the computer program is executed by a processor, the steps in any of the above method embodiments are implemented.

[0165] An embodiment of the present application further provides another computer program product, including a non-volatile computer-readable storage medium, wherein the non-volatile computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps in any of the above method embodiments are implemented.

[0166] The embodiments of the present application also provide a computer program, which includes computer instructions, which are stored in a computer-readable storage medium; a processor of a computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes the steps in any one of the above method embodiments.

[0167] A person of ordinary skill in the art may understand that all or part of the steps in the various methods of the above-mentioned embodiments may be completed by instructing the hardware related to the vehicle terminal through a program, and the program may be stored in a computer-readable storage medium, which may include: a flash drive, ROM, RAM, a magnetic disk or an optical disk, etc.

[0168] The serial numbers of the above-mentioned embodiments of the present application are for description only and do not represent the advantages or disadvantages of the embodiments.

[0169] If the integrated units in the above embodiments are implemented in the form of software functional units and sold or used as independent products, they can be stored in the above computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for enabling one or more computer devices (which may be personal computers, servers, or network devices, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present application.

[0170] In the above embodiments of the present application, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, please refer to the relevant description of other embodiments.

[0171] In the several embodiments provided in the present application, it should be understood that the disclosed client can be implemented in other ways. Among them, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0172] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution provided in this embodiment.

[0173] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, each unit may exist physically separately, or at least two units may be integrated into one unit. The above integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0174] The above is only a preferred implementation of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. A method for switching a driving mode, characterized in that: include: Determine the scene conditions of the road section where the vehicle is traveling; Acquiring pedal manipulation characteristic data collected by the vehicle in a previous collection cycle; Predicting a mode switching decision result of the vehicle under the scenario based on the pedal manipulation feature data by using a pre-trained classification model that matches the scenario; The driving mode of the vehicle is adjusted according to the mode switching decision result.

2. The method according to claim 1, characterized in that: The method of predicting the mode switching decision result of the vehicle under the scenario condition based on the pedal manipulation feature data by using a pre-trained classification model that matches the scenario condition includes: Determining a pre-trained classification model that matches the scenario; By using the classification model, the pedal operation feature data is subjected to dimensionality reduction processing to obtain a plurality of feature common factors; the plurality of feature common factors are used to characterize a plurality of pedal operation features that are unrelated to each other; The classification model is used to perform supervised learning classification on the multiple characteristic common factors to obtain a mode switching decision result of the vehicle under the scenario condition.

3. The method according to claim 1, characterized in that The adjusting the driving mode of the vehicle according to the mode switching decision result includes: Determining a gear position corresponding to a current driving mode of the vehicle; When the mode switching decision result indicates that the mode is maintained, the gear position corresponding to the current driving mode of the vehicle is maintained unchanged.

4. The method according to claim 3, characterized in that The method further comprises: When the mode switching decision result indicates a mode downshift and the current driving mode of the vehicle is not in the lowest gear, the gear corresponding to the current driving mode of the vehicle is reduced.

5. The method according to claim 3, characterized in that: The method further comprises: When the mode switching decision result indicates a mode downshift and the current driving mode of the vehicle is in the lowest gear, the gear corresponding to the current driving mode of the vehicle is kept unchanged.

6. The method according to claim 3, characterized in that The method further comprises: When the mode switching decision result indicates a mode upshift and the current driving mode of the vehicle is not at a highest gear, the gear corresponding to the current driving mode of the vehicle is increased.

7. The method according to claim 3, characterized in that The method further comprises: When the mode switching decision result indicates a mode upshift and the current driving mode of the vehicle is at the highest gear, the gear corresponding to the current driving mode of the vehicle is kept unchanged.

8. The method according to claim 1, characterized in that The method further comprises: Acquire multiple training samples; each of the multiple training samples includes historical pedal operation characteristic data collected when the vehicle is traveling in a driving mode under a scenario, and a sample label; the sample label represents a historical mode switching decision result when the vehicle is traveling in a driving mode under a scenario; Get the initial model; Through the initial model, the historical pedal manipulation feature data in each training sample is subjected to dimensionality reduction processing to obtain a plurality of historical feature common factors corresponding to each training sample; The initial model is used to perform supervised learning classification on multiple historical feature common factors corresponding to each training sample to obtain a prediction mode decision result corresponding to each training sample; according to the difference between the prediction mode decision result corresponding to each training sample and the corresponding sample label, the parameters of the initial model are adjusted, and the training is stopped when the training stop condition is reached to obtain a trained classification model.

9. A driving mode switching device, characterized in that: include: A working condition determination module, used to determine the scene working condition of the road section on which the vehicle is traveling; A data acquisition module, used to acquire pedal manipulation characteristic data collected by the vehicle in a previous acquisition cycle; A prediction module, configured to predict a mode switching decision result of the vehicle under the scenario based on the pedal manipulation feature data by using a pre-trained classification model that matches the scenario; A mode switching module is used to adjust the driving mode of the vehicle according to the mode switching decision result.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, wherein the computer program implements the steps of any one of the methods of claims 1 to 8 when executed by a processor.