Driving mode switching method and device, electronic equipment and storage medium

Abstract

The embodiment of the invention provides a driving mode switching method and device, electronic equipment and a storage medium, and relates to the technical field of vehicle control. The method comprises the following steps: acquiring a congestion level of a road in a future time period based on navigation information; driving style values of the driver under different congestion levels are called; and performing power configuration according to the driving style numerical value so as to switch to corresponding power configuration based on different congestion levels in the driving process. According to the method, power configuration can be carried out according to the driving style values of the user under different congestion levels, the driving mode which fits the driving habit of the user and adapts to future road conditions is provided for the user, and the problem that an existing driving mode cannot cover diversified driving requirements of the user is solved.

Description

Technical Field

[0001] This application relates to the field of vehicle control technology, and more specifically, to a driving mode switching method, device, electronic device, and storage medium. Background Technology

[0002] Existing vehicles generally offer four driving modes: Eco, Comfort, Sport, and Custom. Eco mode provides the least power, while Sport mode provides the most. However, novice drivers may find Eco mode to be quite powerful, while off-road enthusiasts may find Sport mode relatively weak. Custom mode also offers limited power options. These issues mean that existing driving modes cannot meet the diverse driving needs of users. Summary of the Invention

[0003] The purpose of this application is to provide a driving mode switching method, device, electronic device, and storage medium that can configure power according to the user's driving style values ​​under different congestion levels, providing the user with a driving mode that fits their own driving habits and adapts to future road conditions, thus solving the problem that existing driving modes cannot cover the diverse driving needs of users.

[0004] In a first aspect, this application provides a driving mode switching method, which includes: obtaining the road congestion level in a future time period based on navigation information; retrieving the driver's driving style values ​​under different congestion levels; and configuring the power according to the driving style values, so as to switch to the corresponding power configuration based on different congestion levels during driving.

[0005] In the technical solution of this application embodiment, the road congestion level for a future period of time can be obtained based on navigation information, and the driving style value corresponding to the congestion level can be obtained. Then, the power configuration is configured according to the congestion level and the driving style value. During subsequent driving, the corresponding power configuration can be switched according to different road congestion conditions, so that the vehicle can drive according to the power configuration that meets the user's driving habits, meet the user's diverse driving needs, and enable the driver to have a good driving experience. At the same time, the power configuration can adapt to the road congestion level, which is conducive to extending the driving range.

[0006] In some embodiments, prior to the step of retrieving the driver's driving style values ​​under different congestion levels, the method further includes: obtaining the driver's driving style values ​​under different congestion levels based on online driving data. In the initial stage, the driver's driving style values ​​under different congestion levels are obtained using the driver's online driving data, so that the obtained driving style values ​​can be used subsequently for powertrain configuration.

[0007] In some embodiments, obtaining driving style values ​​for drivers under different congestion levels based on online driving data includes: cyclically acquiring online driving data corresponding to the driver's current congestion level; inputting the online driving data into a pre-trained driving style self-learning model to obtain the driver's driving style value under the current congestion level; and adjusting the driving style value after multiple cyclic inputs until the driving style value tends to stabilize. Utilizing a pre-trained driving style self-learning model for multiple cyclic inputs and driving style value adjustments ensures that the obtained driving style values ​​are more accurate.

[0008] In some embodiments, the driving style value is adjusted through multiple iterations of input until it stabilizes. This includes: averaging the current driving style value with the previously obtained driving style value and storing the average; averaging the next obtained driving style value with the average again; and repeating this averaging process multiple times until the variation in the obtained driving style value is within a set range, at which point the driving style value is determined to be stable. Averaging the current driving style value with the previously obtained driving style value, and then averaging the next obtained driving style value with the average again, repeating this averaging process multiple times until a stable driving style value is obtained, provides a stable and accurate driving style value result.

[0009] In some embodiments, before the step of inputting the online driving data into a pre-trained driving style self-learning model to obtain the driver's driving style value based on the congestion level, the method further includes training the driving style self-learning model: normalizing the offline driving data for each congestion level to obtain normalized offline driving data; and inputting the normalized offline driving data into a backpropagation neural network model based on a genetic algorithm for training. Using offline driving data as input for training of the backpropagation neural network model based on a genetic algorithm can improve convergence speed and enhance robustness.

[0010] In some embodiments, the normalized offline driving data is input into a backpropagation neural network model based on a genetic algorithm for training, including: obtaining the optimal initial parameters of the backpropagation neural network model based on the genetic algorithm; and training the backpropagation neural network model based on the optimal initial parameters and the normalized offline driving data until convergence. Using a genetic algorithm to obtain the optimal initial parameters and then training the backpropagation neural network model based on these parameters can improve the convergence speed, reduce the risk of overfitting, obtain stable driving style values, and enhance the robustness of the output results.

[0011] In some embodiments, the method further includes: periodically calculating new driving style values ​​for the driver under different congestion levels using online driving data; and updating the original driving style values ​​based on the new driving style values. By using the driver's online driving data to obtain new driving style values ​​and updating the original driving style values, the driving style values ​​are always aligned with the user's driving habits.

[0012] In some embodiments, configuring the powertrain based on the driving style values ​​includes: generating a new accelerator pedal characteristic curve based on the driving style values; and determining the torque corresponding to different vehicle speeds at different pedal openings based on the new accelerator pedal characteristic curve. Generating a new accelerator pedal characteristic curve based on the driving style values ​​and configuring the powertrain based on this curve satisfies the user's driving needs.

[0013] Secondly, this application provides a driving mode switching device, which includes: a congestion level acquisition module for acquiring the road congestion level within a future time period based on navigation information; a driving style data retrieval module for retrieving the driver's driving style values ​​under different congestion levels; and a power configuration module for configuring the power according to the driving style values, so as to switch to the corresponding power configuration based on different congestion levels during driving. Using the user's driving style values ​​under different congestion levels for power configuration not only conforms to the user's driving habits but also adapts to changes in road conditions, solving the problem that existing driving modes cannot cover the diverse driving needs of users.

[0014] Thirdly, this application provides a vehicle that performs the aforementioned driving mode switching method. Fourthly, this application provides an electronic device, which includes a memory and a processor. The memory stores a computer program, and the processor runs the computer program to cause the electronic device to perform the driving mode switching method described above.

[0015] Fifthly, this application provides a readable storage medium storing computer program instructions, which are read and executed by a processor to perform the aforementioned driving mode switching method. Attached Figure Description

[0016] To more clearly illustrate the technical solutions of the embodiments of this application, the accompanying drawings used in the embodiments of this application will be briefly introduced below. It should be understood that the following drawings only show some embodiments of this application and should not be regarded as a limitation of the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0017] Figure 1A flowchart illustrating a driving mode switching method provided in this application embodiment; Figure 2 This application provides a specific implementation process for adaptive driving mode switching in its embodiments. Figure 3 A flowchart for obtaining driving style values ​​provided in this application embodiment; Figure 4 A flowchart illustrating the adjustment of driving style values ​​provided in an embodiment of this application; Figure 5 A flowchart of the model training process provided in this application embodiment; Figure 6 A flowchart illustrating the training process of a backpropagation neural network model based on a genetic algorithm, provided in an embodiment of this application. Figure 7 This is a flowchart illustrating the driving style numerical update process provided in an embodiment of this application. Figure 8 A power configuration flowchart provided for an embodiment of this application; Figure 9 A detailed block diagram illustrating the method for implementing driving mode switching provided in this application embodiment; Figure 10 This is a structural block diagram of a driving mode switching device provided in an embodiment of this application.

[0018] icon: 110 - Congestion level acquisition module; 120 - Driving style data retrieval module; 130 - Power configuration module; 140 - Driving style value acquisition module; 150 - Model training module. Detailed Implementation

[0019] The technical solutions in the embodiments of this application will now be described with reference to the accompanying drawings.

[0020] It should be noted that similar reference numerals and letters in the following figures indicate similar items; therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures. Furthermore, in the description of this application, terms such as "first," "second," etc., are used only to distinguish descriptions and should not be construed as indicating or implying relative importance.

[0021] With the rapid development of intelligent vehicles, people's demands for driving modes are becoming increasingly diverse to meet their power needs. Even in the custom driving mode, the options for power options are limited, making it impossible for existing driving modes to meet the diverse driving needs of users.

[0022] To address the aforementioned technical issues, this application provides a driving mode switching method. This method combines road congestion levels with driving style values, using the driving style values ​​to configure the power supply. During subsequent driving, the vehicle can switch to the corresponding power supply configuration based on the road congestion level, enabling the vehicle to drive according to the power supply configuration that meets the user's driving habits, satisfying diverse driving needs, and providing the driver with a good driving experience. At the same time, this power supply configuration can adapt to the road congestion level, providing the user with a driving mode that fits their own driving habits and is adaptable to future road conditions.

[0023] Please refer to Figure 1 , Figure 1 A flowchart of a driving mode switching method provided in this application embodiment, the method including the following steps: S110: Obtain the road congestion level for a future time period based on navigation information; S120: Retrieves driver's driving style values ​​under different congestion levels; S130: Power configuration is adjusted based on driving style values ​​to switch to the appropriate power configuration during driving based on different congestion levels.

[0024] Navigation information can provide the road congestion level for a future period. For example, a congestion level of 0 means that the road will be unobstructed for a period of time, a congestion level of 1 means that the road will be moderately congested for a period of time, and a congestion level of 2 means that the road will be very congested.

[0025] Driving style values, for example, can be expressed as percentages to characterize a user's driving style, such as aggressive or gentle, or can be expressed as specific numerical values ​​to quantify the driving style.

[0026] Regarding powertrain configuration, each congestion level corresponds to a driving style value; therefore, each congestion level requires powertrain configuration based on the corresponding driving style value. As for the specific configuration method, drivers can either use the system's recommended powertrain configuration based on the driving style value for one-click configuration, or manually configure it according to the needs set for each congestion level. There are no restrictions on the form of powertrain configuration. For the specific configuration mode, the method described in this application can be used based on the vehicle's existing custom modes, offering good adaptability while reducing costs.

[0027] Based on navigation information, the system can determine the road congestion level for a future period and obtain the corresponding driving style value. The system then adjusts the power configuration based on the congestion level and driving style value. During subsequent driving, the system can switch to the appropriate power configuration according to different road congestion conditions, providing users with a driving mode that suits their driving habits and adapts to future road conditions. This satisfies diverse driving needs and provides drivers with a good driving experience. Furthermore, the system's adaptability to road congestion levels helps extend the driving range.

[0028] In some embodiments, prior to retrieving the driver's driving style values ​​under different congestion levels, the method further includes: obtaining the driver's driving style values ​​under different congestion levels based on online driving data.

[0029] like Figure 2 The diagram illustrates the specific implementation process of adaptive driving mode switching. Online driving data refers to real-time driving data generated by the vehicle during operation, including but not limited to average longitudinal acceleration, maximum master cylinder pressure, average vehicle speed, steering wheel angle, and accelerator pedal change rate. By using online driving data to identify the driver's driving style, numerical values ​​of the driver's driving style under different congestion levels can be obtained, providing a basis for powertrain configuration. Furthermore, based on future road congestion levels, powertrain configuration can be adjusted to enable adaptive driving mode switching.

[0030] Please refer to Figure 3 , Figure 3 The flowchart for obtaining driving style values ​​shows that, in some embodiments, driving style values ​​for drivers at different congestion levels are obtained based on online driving data, including: S140: Loop through online driving data corresponding to the driver's current congestion level; S150: Input online driving data into a pre-trained self-learning model of driving style to obtain the driver's driving style value under the current congestion level; S160: After multiple cycles of input, the driving style value is adjusted until it stabilizes.

[0031] Online driving data is acquired multiple times to ensure coverage of all congestion levels. For each congestion level, the corresponding online driving data is acquired and adjusted repeatedly until the driving style value for that congestion level stabilizes, ensuring that the obtained driving style value matches the driver's driving preferences for the current time period.

[0032] Please refer to Figure 4 , Figure 4This is a flowchart for adjusting driving style values. In some embodiments, the driving style values ​​are adjusted through multiple iterations of input until they stabilize, including: S161: Take the average value of the driving style value obtained in the current operation and the driving style value obtained in the previous operation, and store the average value; S162: Take the average value again between the next obtained driving style value and the average value; S163: After taking the average value multiple times until the change range of the obtained driving style value is within the set range, the driving style value is determined to be stable.

[0033] The driving style value tends to stabilize, which means the driving style value converges. The criterion for judgment is that the change in the driving style value is within the set range, such as 2%.

[0034] In addition to adjusting using the mean, adjustments can also be made based on the fluctuation range. For example, if the driving style value obtained this time is smaller than the previously stored driving style value, the stored driving style value will be slightly adjusted downward and re-stored, with the adjustment range not exceeding 2%. After multiple cycles of adjustment, the driving style value will converge.

[0035] By employing a multi-cycle adjustment method, the obtained driving style values ​​are made to match the driver's driving style and preferences in the current time period, so that the subsequent power configuration can meet the driver's driving needs.

[0036] Please refer to Figure 5 , Figure 5 The flowchart illustrates the model training process. In some embodiments, before the step of inputting online driving data into a pre-trained self-learning model of driving style to obtain a driver's driving style value based on the congestion level, the method further includes training the self-learning model of driving style: S111: Normalize the offline driving data for each congestion level to obtain normalized offline driving data; S112: Input the normalized offline driving data into the backpropagation neural network model based on the genetic algorithm for training.

[0037] For example, a CAN (Controller Area Network) device can be used to collect offline driving data from the driver. Offline driving data refers to historical driving data. A self-learning model of driving style can be built based on the offline driving data and machine learning algorithms. The trained self-learning model of driving style is deployed in the vehicle controller. During the user's driving process, the driver's driving style value is obtained based on the driver's current online driving data, and the power configuration under several different congestion conditions is adaptively recommended to the user according to the driver's driving style.

[0038] The offline driving data includes the mean longitudinal acceleration signal, the maximum master cylinder pressure signal, the mean vehicle speed signal, the steering wheel angle signal, and the accelerator pedal rate of change signal. Within the required time range, the mean longitudinal acceleration, mean vehicle speed, maximum master cylinder pressure, and accelerator pedal rate of change signals needed for model training are calculated and normalized using the min-max normalization method, as follows: ; in, Indicates the first One characteristic, Indicates the first The first feature Each feature value.

[0039] The backpropagation neural network model uses a three-layer structure: the input layer contains 5 neurons, the hidden layer has 9 neurons, and the output layer has 1 neuron.

[0040] The driving style self-learning model adopts a genetic algorithm-based backpropagation neural network model (GA-BP model). Offline driving data under different congestion levels are input into the genetic algorithm-based backpropagation neural network model for training, so that driving style values ​​under different congestion levels can be obtained by using the genetic algorithm-based backpropagation neural network model in the future.

[0041] Please refer to Figure 6 , Figure 6 This is a flowchart illustrating the training process of a backpropagation neural network model based on a genetic algorithm. In some embodiments, normalized offline driving data is input into the backpropagation neural network model based on a genetic algorithm for training, including: S121: Obtaining the optimal initial parameters of the backpropagation neural network model based on the genetic algorithm; S122: The backpropagation neural network model is trained based on the optimal initial parameters and normalized offline driving data until convergence.

[0042] The genetic algorithm used here to obtain the optimal initial parameters specifically includes the following steps: S1211: Encode the chromosome to obtain the individual fitness of the normalized offline driving data. The fitness is represented by the absolute value of the error between the output value of the predicted sample and the true value. S1212: After crossover, selection, and mutation operations, calculate the fitness and find a set of individuals with the best fitness as the current solution; The crossing method is the real number crossing method, specifically expressed as follows: ; in, Indicates the first Individuals in position Intersection, Indicates the first Individuals in position Intersection, Represents a random number.

[0043] Individual selection is implemented using a roulette wheel algorithm. The higher an individual's fitness, the greater its probability of being selected. In other words, the probability of each individual being selected is directly proportional to its fitness. The probability of an individual being selected is expressed as: ; in, Indicates the first Individual fitness represents the total number of individuals.

[0044] S1213: Determine whether the current solution meets the convergence condition. If it does, output the optimal weight threshold. If it does not meet the condition, return to the previous step and recalculate the fitness by selecting an operator until convergence. The convergence condition is that after 100 iterations of the population, the solution with the highest fitness is selected as the optimal solution.

[0045] The optimal weight threshold obtained by the genetic algorithm is used as the optimal initial parameter to train the backpropagation neural network model until it converges.

[0046] By using a genetic algorithm to obtain the optimal initial parameters of the backpropagation neural network model and then performing iterative training based on these parameters, the number of iterations is significantly reduced, improving the convergence speed. At the same time, global optimization using a genetic algorithm can improve the accuracy of the output driving style values, reduce the impact of noisy data on the model, and improve the robustness of the output driving style values.

[0047] Please refer to Figure 7 , Figure 7 A flowchart for updating driving style values. In some embodiments, the method further includes: S141: Periodically calculate the driver's new driving style values ​​under different congestion levels using online driving data; S142: Update the original driving style values ​​based on the new driving style values.

[0048] Considering changes in drivers' driving habits, the driving style values ​​can be updated periodically to better align with these habits. Specifically, during driving, the system stores and updates the corresponding driving style values ​​based on different congestion levels indicated by the navigation. If the current congestion level is 1, the current driving style value will be updated to the stored value corresponding to congestion level 1; the same applies to congestion levels 0 and 2.

[0049] The driving style values ​​are updated regularly so that even if the driver's driving habits change over time, the driving style values ​​will always match the driver's driving habits.

[0050] Please refer to Figure 8 , Figure 8 This is a flowchart of the powertrain configuration process. In some embodiments, powertrain configuration is performed based on driving style values, including: S131: Generate a new accelerator pedal characteristic curve based on driving style values; S132: Determine the torque corresponding to different vehicle speeds at different pedal openings based on the new accelerator pedal characteristic curve.

[0051] Based on the existing throttle pedal characteristic curves corresponding to driving modes such as Eco, Comfort, and Sport, a new throttle pedal characteristic curve is generated based on driving style values. The torque corresponding to the vehicle speed is adjusted according to the new throttle pedal characteristic curve to achieve power configuration.

[0052] Based on the power configuration and the future road congestion level, the system automatically switches to the appropriate power configuration under different operating conditions, so that the driver can have a good driving experience. At the same time, the power configuration is adapted to congested road conditions, which helps to extend the vehicle's driving range and manage energy.

[0053] To make the objectives, technical solutions, and advantages of this application clearer, the technical solutions in this application will be clearly and completely described below. In some embodiments, please refer to... Figure 9 , Figure 9 To illustrate the specific block diagram of the driving mode switching method, the driving mode switching method includes: S201: The first stage is model training. Offline driving data is used to train the self-learning model of driving style to obtain the self-learning model of driving style. S202: The second stage is the self-learning of driving style values. Online driving data is input into the driving style self-learning model, and driving style values ​​are obtained through multiple iterations and adjustments. S203: The third stage is driving mode configuration. It uses driving style values ​​and road navigation information to configure the power to obtain an adaptive driving mode, which switches to the corresponding power configuration based on different congestion levels during driving.

[0054] Please refer to Figure 10 , Figure 10 The structural block diagram of a driving mode switching device provided in this application should be understood to be related to... Figure 1 The method embodiment executed in this document corresponds to the method described above, and is capable of performing the steps involved in the aforementioned method. The specific functions of this device can be found in the description above; to avoid repetition, detailed descriptions are appropriately omitted here. This device includes, but is not limited to: The congestion level acquisition module 110 is used to obtain the road congestion level for a future time period based on navigation information; The driving style data retrieval module 120 is used to retrieve the driver's driving style values ​​under different congestion levels. The power configuration module 130 is used to configure the power according to the driving style value, so as to switch to the corresponding power configuration based on different congestion levels during driving.

[0055] In the technical solution of this application embodiment, the road congestion level for a future period of time can be obtained based on navigation information, and the driving style value corresponding to the congestion level can be obtained. Then, the power configuration is configured according to the congestion level and the driving style value. During subsequent driving, the corresponding power configuration can be switched according to different road congestion conditions, so that the vehicle can drive according to the power configuration that meets the user's driving habits, meet the diverse driving needs of the user, and enable the driver to have a good driving experience. At the same time, the power configuration can adapt to the congestion level of the road conditions, which is conducive to extending the driving range.

[0056] According to some embodiments of this application, the device further includes a driving style value acquisition module 140, which is used to acquire driving style values ​​of the driver under different congestion levels based on online driving data.

[0057] According to some embodiments of this application, the specific process of obtaining the driving style value includes: cyclically acquiring online driving data corresponding to the driver's current congestion level; inputting the online driving data into a pre-trained driving style self-learning model to obtain the driver's driving style value under the current congestion level; and adjusting the driving style value after multiple cyclic inputs until the driving style value tends to stabilize. According to some embodiments of this application, the specific adjustment process of the driving style value includes: taking the average of the driving style value obtained in the current time and the driving style value obtained in the previous time, and storing the average value; taking the average of the driving style value obtained in the next time and the average value again; after taking the average multiple times, until the change range of the obtained driving style value is within the set range, it is determined that the driving style value tends to be stable. According to some embodiments of this application, the device further includes a model training module 150 for: training a self-learning model of driving style.

[0058] According to some embodiments of this application, the specific training process of the driving style self-learning model includes: normalizing the offline driving data under each congestion level to obtain normalized offline driving data; and inputting the normalized offline driving data into a backpropagation neural network model based on a genetic algorithm for training.

[0059] According to some embodiments of this application, the specific process of training the backpropagation neural network model based on the genetic algorithm is as follows: obtaining the optimal initial parameters of the backpropagation neural network model based on the genetic algorithm; training the backpropagation neural network model based on the optimal initial parameters and normalized offline driving data until convergence.

[0060] According to some embodiments of this application, the device further includes a driving style value update module, specifically used for: The system periodically calculates new driving style values ​​for drivers under different congestion levels using online driving data; and updates the original driving style values ​​based on these new values.

[0061] According to some embodiments of this application, the power configuration module 130 is specifically used for: A new accelerator pedal characteristic curve is generated based on driving style values; the torque corresponding to different vehicle speeds at different pedal openings is determined based on the new accelerator pedal characteristic curve.

[0062] This application provides a vehicle, which is implemented using any of the aforementioned alternative methods.

[0063] This application provides an electronic device including a memory and a processor. The memory stores a computer program, and the processor runs the computer program to cause the electronic device to perform the methods in any of the aforementioned optional implementations.

[0064] This application provides a readable storage medium storing computer program instructions, which, when read and executed by a processor, perform the methods in any of the aforementioned optional implementations.

[0065] The storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as Static Random Access Memory (SRAM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Erasable Programmable Read Only Memory (EPROM), Programmable Red-Only Memory (PROM), Read-Only Memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk.

[0066] In the several embodiments provided in this application, it should be understood that the disclosed apparatus and methods can also be implemented in other ways. The apparatus embodiments described above are merely illustrative. For example, the flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of apparatus, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order than those marked in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in a block diagram and / or flowchart, and combinations of blocks in block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or action, or using a combination of dedicated hardware and computer instructions.

[0067] In addition, the functional modules in the various embodiments of this application can be integrated together to form an independent part, or each module can exist independently, or two or more modules can be integrated to form an independent part.

[0068] If the aforementioned functions are implemented as software functional modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0069] The above description is merely an embodiment of this application and is not intended to limit the scope of protection of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of protection of this application. It should be noted that similar reference numerals and letters in the following figures indicate similar items; therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures.

[0070] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

[0071] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

Claims

1. A method for switching driving modes, characterized in that, The method includes: The congestion level of roads in the future time period is obtained based on navigation information; Retrieve driver's driving style values ​​under different congestion levels; The power configuration is adjusted based on the driving style value, and the appropriate power configuration is switched during driving based on different congestion levels.

2. The driving mode switching method according to claim 1, characterized in that, Before the step of retrieving the driver's driving style values ​​under different congestion levels, the method further includes: The driving style values ​​of drivers under different congestion levels are obtained based on online driving data.

3. The driving mode switching method according to claim 2, characterized in that, The method of obtaining driver style values ​​under different congestion levels based on online driving data includes: Loop through and retrieve online driving data corresponding to the driver's current congestion level; The online driving data is input into a pre-trained driving style self-learning model to obtain the driver's driving style value under the current congestion level; After multiple cycles of input, the driving style value is adjusted until it stabilizes.

4. The driving mode switching method according to claim 3, characterized in that, The process of adjusting the driving style value through multiple cycles of input until the driving style value stabilizes includes: The average value of the driving style obtained in the current instance is taken with the average value of the driving style obtained in the previous instance, and the average value is stored. The next obtained driving style value will be averaged again with the aforementioned average value; After taking the average value multiple times until the change range of the obtained driving style value is within the set range, it is determined that the driving style value tends to be stable.

5. The driving mode switching method according to claim 3, characterized in that, Before the step of inputting the online driving data into a pre-trained driving style self-learning model to obtain the driver's driving style value based on the congestion level, the method further includes training the driving style self-learning model: The offline driving data under each congestion level is normalized to obtain normalized offline driving data; The normalized offline driving data is input into a backpropagation neural network model based on a genetic algorithm for training.

6. The driving mode switching method according to claim 5, characterized in that, The step of inputting the normalized offline driving data into a backpropagation neural network model based on a genetic algorithm for training includes: The optimal initial parameters of the backpropagation neural network model are obtained based on the genetic algorithm. The backpropagation neural network model is trained based on the optimal initial parameters and the normalized offline driving data until it converges.

7. The driving mode switching method according to claim 1, characterized in that, The method further includes: The system uses online driving data to periodically calculate the driver's new driving style values ​​under different congestion levels. The original driving style values ​​are updated based on the new driving style values.

8. The driving mode switching method according to claim 1, characterized in that, The process of configuring the powertrain based on the driving style values ​​includes: A new accelerator pedal characteristic curve is generated based on driving style values; The torque corresponding to different vehicle speeds at different pedal openings is determined based on the new accelerator pedal characteristic curve.

9. A driving mode switching device, characterized in that, The device includes: The congestion level acquisition module is used to obtain the road congestion level for a future time period based on navigation information; The driving style data retrieval module is used to retrieve the driver's driving style values ​​under different congestion levels; The power configuration module is used to configure the power according to the driving style value, so as to switch to the corresponding power configuration based on different congestion levels during driving.

10. A vehicle, characterized in that, Perform the driving mode switching method according to any one of claims 1 to 8.

11. An electronic device, characterized in that, The electronic device includes a memory and a processor, the memory being used to store a computer program, and the processor running the computer program to cause the electronic device to perform the driving mode switching method according to any one of claims 1 to 8.

12. A readable storage medium, characterized in that, The readable storage medium stores computer program instructions, which, when read and executed by a processor, perform the driving mode switching method according to any one of claims 1 to 8.

Images