Driving mode recommendation method, electronic device, storage medium and program product

Abstract

The invention relates to a driving mode recommendation method, electronic equipment, a storage medium and a program product. In response to the fact that the current driving style is the target style, target prompt information is output, and the target prompt information is used for recommending a user to start a target mode; wherein the current driving style is obtained based on driving data. On the basis that the current driving style is the target style, the target mode is intelligently recommended, and therefore the personalized driving requirement of a driver of the target style can be met.

Description

Technical Field

[0001] The present disclosure relates to the field of vehicle control technology, and in particular, to a driving mode recommendation method, electronic device, storage medium, and program product. Background Art

[0002] Currently, with the increasing popularity of smart cars, users' demands for driving experience and vehicle performance are also increasing. Different driving modes can provide users with different vehicle performance and driving experience.

[0003] The driving modes provided in the related art are mostly fixed function switches, which cannot provide personalized recommendations for driving modes for users with different driving needs. Summary of the Invention

[0004] The present disclosure aims to provide a driving mode recommendation method, electronic device, storage medium and program product.

[0005] To achieve the above objectives, the present disclosure provides a driving mode recommendation method, the method comprising:

[0006] In response to the current driving style being the target style, target prompt information is output, where the target prompt information is used to recommend the user to turn on the target mode; wherein the current driving style is obtained based on the driving data.

[0007] Optionally, the current driving style is obtained based on driving data, specifically including:

[0008] determining a driving behavior characteristic based on the driving data;

[0009] The current driving style is determined according to the driving behavior characteristics.

[0010] Optionally, determining the current driving style according to the driving behavior characteristics includes:

[0011] According to the driving behavior characteristics, the current driving style corresponding to the driving behavior characteristics is determined by a pre-trained target classification model.

[0012] Optionally, the target classification model includes a K-means clustering model, and the K-means clustering model is pre-trained in the following manner:

[0013] Obtaining an initialized clustering model, wherein the initialization parameters of the clustering model include the number of classification clusters and the centroid corresponding to each cluster; wherein different clusters correspond to different driving styles, and for each cluster, the centroid of the cluster represents the driving behavior characteristics of the driving style corresponding to the cluster;

[0014] Acquire training sample data, wherein the training sample data includes driving behavior feature sample data corresponding to multiple time periods;

[0015] updating the centroid corresponding to each cluster according to the driving behavior feature sample data corresponding to the multiple time periods to obtain a target centroid;

[0016] The K-means clustering model is determined according to the target centroid corresponding to each cluster.

[0017] Optionally, the driving data includes driving data corresponding to at least one preset time period, and the driving data corresponding to each preset time period includes driving data collected at at least one moment within the preset time period;

[0018] Determining the driving behavior characteristics according to the driving data includes:

[0019] Data processing is performed on the driving data collected at at least one moment within the preset time period to obtain the driving behavior characteristics corresponding to the preset time period.

[0020] Optionally, the driving behavior characteristics include at least one of the following:

[0021] Vehicle speed standard deviation, average deceleration, average accelerator pedal position, average acceleration, average acceleration jerk, accelerator pedal position standard deviation, average vehicle speed, and maximum speed.

[0022] Optionally, the method further includes:

[0023] In response to the current driving style not being the target style, an operation switch of the target mode on the preset prompt interface is controlled to be in an inoperable state.

[0024] Optionally, the target style includes an aggressive driving style, and in response to the current driving style being the target style, outputting the target prompt information includes: in response to the aggressive driving style, the target prompt information is used to recommend the user to turn on the racing mode.

[0025] Optionally, the target prompt information includes the operation switch of the racing mode and / or path information of the operation switch of the racing mode.

[0026] Optionally, the method further includes:

[0027] In response to the user turning on the racing mode, the racing mode is added to the driving mode options of the vehicle.

[0028] In order to achieve the above objectives, the present disclosure provides an electronic device, comprising:

[0029] memory for storing computer programs;

[0030] A processor is configured to execute the computer program stored in the memory so as to enable the device to perform the steps of the driving mode recommendation method described above.

[0031] In order to achieve the above objectives, the present disclosure provides a computer-readable storage medium having a computer program stored thereon, which implements the steps of the driving mode recommendation method described above when executed by a processor.

[0032] In order to achieve the above objectives, the present disclosure provides a computer program product, including a computer program, which implements the steps of the driving mode recommendation method described above when executed by a processor.

[0033] The above technical solution determines the current driving style based on driving data. If the current driving style matches the target style, target prompt information is output. This target prompt information is used to recommend that the user activate the target mode. In this way, the driver's current driving style is analyzed based on the vehicle's driving data. If the current driving style matches the target style, the target mode is intelligently recommended. This can meet the personalized driving needs of drivers with the target style and enhance the user's driving experience.

[0034] Other features and advantages of the present disclosure will be described in detail in the following detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] The accompanying drawings are used to provide a further understanding of the present disclosure and constitute a part of the specification. Together with the following detailed description, they are used to explain the present disclosure but do not constitute a limitation of the present disclosure. In the accompanying drawings:

[0036] Figure 1 The figure is a flowchart of a driving mode recommendation method according to an exemplary embodiment.

[0037] Figure 2 is based on Figure 1 The illustrated embodiment shows a flow chart of a driving mode recommendation method.

[0038] Figure 3 is based on Figure 2 The illustrated embodiment shows a flowchart of a model training method.

[0039] Figure 4 The figure is a schematic diagram of a racing mode recommendation window according to an exemplary embodiment.

[0040] Figure 5 The present invention is a driving mode display interface for an aggressive user according to an exemplary embodiment.

[0041] Figure 6 The present invention is a driving mode display interface for a conservative user according to an exemplary embodiment.

[0042] Figure 7 The figure is a block diagram of a driving mode recommendation device according to an exemplary embodiment.

[0043] Figure 8 is based on Figure 7 A block diagram of a driving mode recommendation device is shown in the illustrated embodiment.

[0044] Figure 9 is based on Figure 8 A block diagram of a driving mode recommendation device is shown in the illustrated embodiment.

[0045] Figure 10 It is a block diagram of an electronic device according to an exemplary embodiment. DETAILED DESCRIPTION

[0046] The following describes the specific embodiments of the present disclosure in detail with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are only used to illustrate and explain the present disclosure and are not intended to limit the present disclosure.

[0047] The present disclosure is mainly used in scenarios where vehicle driving mode recommendations are made. Driving modes may include racing mode and non-racing mode. Racing mode is a mode that enhances vehicle power output and is designed to improve vehicle performance and enhance the driving experience. For example, users with an aggressive driving style are more suitable for choosing racing mode to drive the vehicle, while users with a conservative or average driving style are more suitable for driving the vehicle in non-racing mode. In actual application scenarios, the vehicle's launch function has certain similarities with the racing mode.

[0048] A related technology provides a vehicle launch control method and device, a vehicle, and a storage medium. Upon determining that the vehicle meets the conditions for entering launch preparation mode, the method controls the vehicle to enter launch preparation mode and activates the vehicle's torque oscillation randomizer to randomly generate oscillating torque, giving the vehicle a strong sense of individuality. However, while random torque oscillation enhances the personalized driving experience, this complex torque variation is impractical in daily life. For users who do not pursue extreme driving experiences, such a design may seem unnecessary.

[0049] Another related technology provides a method for controlling a vehicle's launch control. This method uses vehicle status and surrounding environment information to determine whether to enable launch control. A major drawback of this method is the risk of information overload. During the launch control process, information displayed includes 0-100 km / h acceleration time, remaining battery life, driving mode, gear position, real-time vehicle speed, readiness status, throttle depth, brake depth, and text reminders. In a high-intensity driving environment, excessive information display can distract the driver and compromise safe driving.

[0050] In summary, existing driving modes are mostly fixed switches, lacking intelligent recognition and recommendations for driver style. While some existing technologies, such as Launch Control, share similarities with Racing Mode, they fail to intelligently recommend Racing Mode usage scenarios through data analysis. This leads to limitations such as limited usage conditions and an inability to personalize driving styles. Furthermore, existing solutions for making driving recommendations based on interface prompts suffer from information overload, potentially distracting the driver and compromising safe driving.

[0051] To solve the above problems, the present disclosure provides a driving mode recommendation method, electronic device, storage medium, and program product. The specific implementation methods of the present disclosure are described in detail below with reference to the accompanying drawings.

[0052] Figure 1 is a flow chart of a driving mode recommendation method according to an exemplary embodiment. Figure 1 As shown, the method includes the following steps:

[0053] In step S101 , in response to the current driving style being a target style, target prompt information is output, where the target prompt information is used to recommend the user to turn on the target mode; wherein the current driving style is obtained based on driving data.

[0054] The target mode is a vehicle driving mode that matches the target driving style. For example, the target style may include aggressive, conservative, or normal. If the current driving style is aggressive, the target mode may be a racing mode that matches the aggressive driving style; if the current driving style is conservative, the target mode may be an economy mode that matches the conservative driving style; and if the current driving style is normal, the target mode may be a normal mode that matches the normal driving style.

[0055] In a possible embodiment, driving data of the vehicle may be acquired, the current driving style may be identified based on the driving data, and the target prompt information may be output when the current driving style is a target style.

[0056] In actual application scenarios, the data acquisition module can collect real-time driving data of the vehicle. This driving data can represent the driver's real-time driving behavior, and the driver's driving style can be analyzed based on this driving data. This driving style can include, for example, aggressive, conservative, and normal.

[0057] The driving data may include, for example, the vehicle's acceleration, the accelerator and brake pedal force and response time, the steering wheel angle, and the vehicle's speed. The vehicle's acceleration can be used to monitor the vehicle's acceleration and deceleration, including the frequency and intensity of sudden acceleration and braking. The accelerator and brake pedal force and response time can be used to determine whether the driver is driving smoothly or aggressively. The steering wheel angle is used to record the driver's steering movements, especially sharp turns or high-speed cornering. The vehicle's speed can be used to detect the vehicle's instantaneous speed, average speed, and the frequency and magnitude of speeding.

[0058] After acquiring the driving data, data cleaning can be performed to eliminate unnecessary noise or abnormal data, ensuring the validity and accuracy of the collected data. For example, it is possible to identify whether there are missing values in the collected driving data set and fill in the missing values if so. It is also possible to identify and delete abnormal data based on statistical methods (such as the Z-score or IQR method).

[0059] The vehicle driver's driving style can be pre-set based on actual needs or experience. For example, the driver's driving style can be set to include three styles: aggressive, conservative, and normal. The current driving style can be any of these three styles.

[0060] It is understandable that users with different driving styles will have different characteristics of driving data when driving a vehicle. For example, for aggressive users, the characteristics of their driving data (which can be understood as driving behavior) are: violent speed fluctuations, large average acceleration and acceleration impact, large throttle depth, and intense throttle use. Among them, acceleration impact refers to the rate of change of acceleration per unit time. For ordinary users, the characteristics of their driving data are: moderate speed fluctuations, moderate average acceleration and acceleration impact, and moderate throttle depth. For conservative users, the characteristics of their driving data are: small speed fluctuations, small average acceleration and acceleration impact, and small throttle depth.

[0061] When using specific data sizes to characterize users with different driving styles, for aggressive users, the acceleration of their vehicle is greater than or equal to a first preset acceleration threshold (characterizing drastic speed fluctuations); the average acceleration is greater than or equal to the first preset average acceleration threshold, the acceleration impact is greater than or equal to the first acceleration impact threshold; and the vehicle's throttle depth is greater than or equal to the first preset throttle depth.

[0062] For ordinary users, the acceleration of their vehicle is greater than or equal to the second preset acceleration threshold and less than the first preset acceleration threshold (indicating moderate vehicle speed fluctuation), wherein the second preset acceleration threshold is less than the first preset acceleration threshold; the average acceleration is greater than or equal to the second preset average acceleration threshold and less than the first preset average acceleration threshold, the acceleration impact degree is greater than or equal to the second acceleration impact degree threshold and less than the first acceleration impact degree threshold, wherein the second preset average acceleration threshold is less than the first preset average acceleration threshold, and the second acceleration impact degree threshold is less than the first acceleration impact degree threshold; the vehicle's throttle depth is greater than or equal to the second preset throttle depth and less than the first preset throttle depth, wherein the second preset throttle depth is less than the first preset throttle depth.

[0063] For conservative users, the acceleration of their vehicle is less than the second preset acceleration threshold (indicating small speed fluctuations); the average acceleration is less than the second preset average acceleration threshold, and the acceleration impact is less than the second acceleration impact threshold; the vehicle's throttle depth is less than the second preset throttle depth.

[0064] The above examples are merely illustrative and are not intended to be limiting.

[0065] Because users with different driving styles generate different characteristics of driving data when driving a vehicle, the current driving style of the driver can be determined based on the currently collected driving data. Target prompt information can then be output based on the current driving style, and this target prompt information is used to recommend that the user activate the target mode.

[0066] The target prompt information may be in text form. For example, the target prompt information may be displayed to the user in text form on the vehicle computer interface and / or the interface of a terminal communicating with the vehicle. The target prompt information may also be in voice form, for example, the target prompt information may be played to the user via a player on the vehicle computer system.

[0067] By executing this step, a personalized driving mode recommendation can be made to the driver through target prompt information based on the current driving style. In one embodiment, in response to the current driving style being the target style, the vehicle can be controlled to output the target prompt information. For example, the target style includes an aggressive driving style. In response to the current driving style being the aggressive driving style, the vehicle is controlled to output target prompt information for recommending the user to turn on the racing mode. For example, when it is determined that the current driving style is the aggressive type, the target prompt information can be, for example: "The system recognizes that your driving habits are aggressive, and recommends that you turn on the racing mode" or "The system recognizes that your driving habits are aggressive, and recommends that you click the following switch to turn on the racing mode." This is just an example, and the present disclosure is not limited to this.

[0068] The target style may further include a normal driving style. In response to the current driving style being the normal driving style, the vehicle is controlled to output target prompt information for recommending the user to turn on the normal mode.

[0069] In addition, the target style may further include a conservative driving style. In response to the current driving style being the conservative driving style, the vehicle is controlled to output target prompt information for recommending the user to activate the economy mode.

[0070] That is, different target styles may have different target modes recommended to users. The target modes corresponding to different styles may be arbitrarily set according to actual needs. The above is only an example and is not limited in this disclosure.

[0071] In addition, when it is determined that the current driving style is not the target style, it indicates that the current driver's driving style does not match the target mode, and in this case, there is no need to recommend the target mode to the driver.

[0072] For example, if the driver's driving style is not an aggressive driving style (for example, the driver's driving style is conservative), for this type of user, turning on the racing mode may have an adverse effect on the user's driving safety, thereby affecting the user experience. Therefore, when the present disclosure determines that the current driving style is not the target style, the target mode may not be recommended to the driver, and in this scenario, the soft switch of the target mode may not be displayed on the interface of the vehicle computer, thereby avoiding the driver from mistakenly starting the target mode.

[0073] The above method uses driving data to determine the current driving style. In response to the current driving style being the target style, target prompt information is output, which is used to recommend that the user activate the target mode. In this way, the driver's current driving style is analyzed using the vehicle's driving data. If the current driving style is the target style, the target mode is intelligently recommended, thereby meeting the personalized driving needs of drivers with the target style and improving the user's driving experience.

[0074] Figure 2 is based on Figure 1 The embodiment shown is a flow chart of a driving mode recommendation method. Figure 2 As shown, the current driving style can be obtained based on the driving data by executing the following sub-steps:

[0075] In step S1021 , driving behavior characteristics are determined based on the driving data.

[0076] The driving data includes driving data corresponding to at least one preset time period, and the driving data corresponding to each preset time period includes driving data collected at at least one moment within the preset time period.

[0077] The preset time period refers to a time period of a preset length. For example, if the preset length is 10 seconds, then the driving data collected every 10 seconds (a set of time series data) can be considered as the driving data corresponding to one preset time period. Taking one of the preset time periods as an example, the driving data collected within these 10 seconds constitutes a time series data, which includes driving data collected at multiple time points.

[0078] During the execution of this step, for each preset time period, the driving data collected at at least one moment within the preset time period may be processed to obtain the driving behavior characteristics corresponding to the preset time period.

[0079] Among them, the driving behavior characteristics are characteristic data that characterize the driver's driving behavior. For example, the driving behavior characteristics may include at least one of the following: vehicle speed standard deviation, average deceleration, average accelerator pedal position, average acceleration, average acceleration impact, accelerator pedal position standard deviation, average vehicle speed and maximum speed.

[0080] For example, the vehicle speed standard deviation, average vehicle speed, and maximum vehicle speed for the preset time period can be calculated based on the driving speed collected at multiple moments in the preset time period. The average deceleration, average acceleration, and average acceleration jerk for the preset time period can be calculated based on the acceleration collected at multiple moments in the preset time period. The average accelerator pedal position and accelerator pedal position standard deviation corresponding to the preset time period can be calculated based on the throttle force collected at multiple moments in the preset time period.

[0081] In step S1022, the current driving style is determined according to the driving behavior characteristics.

[0082] In this step, the current driving style corresponding to the driving behavior feature can be determined based on the driving behavior feature through a pre-trained target classification model.

[0083] The target classification model may include a K-means clustering model.

[0084] For example, for one or more consecutive preset time periods, the driving behavior characteristics corresponding to the preset time periods can be input into the K-means clustering model, and then the K-means clustering model can output the current driving style that matches the driving behavior characteristics.

[0085] It should be noted that in one implementation, the target classification model can be pre-deployed on the vehicle. In this way, the current driving style corresponding to the driving behavior characteristics can be identified in real time locally on the vehicle based on the target classification model. In another implementation, the target classification model can also be deployed in the cloud (i.e., a server communicating with the vehicle computer). In this way, the vehicle can upload the driving behavior characteristics to the cloud, and then the cloud outputs the current driving style based on the target classification model, and transmits the current driving style back to the vehicle computer.

[0086] It's also important to note that this target classification model is pre-trained based on a massive amount of collected driving data from the same vehicle model. In other words, it's a classification model learned through big data and capable of identifying a driver's driving style. Therefore, by inputting driving behavior characteristics into this target classification model, the present disclosure can accurately identify a vehicle's current driving style through big data and driving behavior analysis, and then intelligently recommend a racing mode based on that current driving style, providing a better user experience.

[0087] The following takes the K-means clustering model as an example to illustrate the model training process.

[0088] Figure 3 is based on Figure 2 The embodiment shown is a flow chart of a model training method, as shown in FIG. Figure 3 As shown, the K-means clustering model can be pre-trained by the following steps:

[0089] In step S301, an initialized clustering model is obtained. The initialization parameters of the clustering model include the number of classification clusters and the centroid corresponding to each cluster. Different clusters correspond to different driving styles. For each cluster, the centroid of the cluster represents the driving behavior characteristics of the driving style corresponding to the cluster.

[0090] When initializing the clustering model to be trained, it is necessary to set the number of classification clusters corresponding to the clustering model and the center point (i.e., centroid) of each cluster. The number of classification clusters can be set based on actual business needs. For example, if the driver's driving style is divided into three styles: aggressive, ordinary, and conservative, the number of classification clusters K can be set to K=3. Therefore, in the present disclosure, the number of classification clusters is the number of types of driving styles. The centroid corresponding to each cluster can be randomly selected based on the training sample data. For example, the training sample data includes driving behavior feature sample data corresponding to multiple time periods. For each cluster, a time period can be randomly selected from multiple time periods, and the driving behavior feature sample data corresponding to the randomly selected time period is used as the data corresponding to the centroid of the cluster.

[0091] In step S302 , training sample data is obtained, where the training sample data includes driving behavior feature sample data corresponding to multiple time periods.

[0092] During this step, driving data for model training can first be extracted from the massive amount of driving data for the same vehicle model, and invalid data can be removed. This massive amount of driving data can then be broken down into data from the total operating time of a single vehicle. For example, the massive amount of driving data can first be divided into driving data corresponding to different vehicles. Then, for each vehicle, the driving data corresponding to that vehicle is sorted in chronological order of the driving data collection time to obtain the data from the total operating time corresponding to that vehicle. The driving data corresponding to each vehicle is then segmented into multiple sets of segmented data according to preset time segments (preset time segments correspond to time periods one-to-one). These multiple sets of segmented data represent the collected driving behavior data representing the driver of the vehicle during different time periods. For each set of segmented data, feature extraction is performed on the segmented data to convert the driver behavior data into feature data (i.e., driving behavior feature sample data, such as vehicle speed standard deviation, average deceleration, average accelerator pedal position, average acceleration, average acceleration impact, accelerator pedal position standard deviation, average vehicle speed, maximum speed, etc.). This allows the generation of driving behavior feature sample data corresponding to each of the multiple time periods.

[0093] In step S303, the centroid corresponding to each cluster is updated according to the driving behavior feature sample data corresponding to the multiple time periods to obtain a target centroid.

[0094] Among them, the basic principle of the K-means clustering algorithm is to divide the data points into the clusters where the nearest centroid is located through continuous iteration, and then recalculate the centroid of each cluster until the centroid of the cluster no longer changes or the maximum number of iterations is reached.

[0095] In this step, the driving behavior feature sample data corresponding to the multiple time periods can be input into the clustering model to be trained. The clustering model can calculate the distance (e.g., Euclidean distance) between the driving behavior feature sample data corresponding to each time period and the centroid of each cluster. Based on this distance, the driving behavior feature sample data corresponding to each time period can be divided into the clusters with the closest distance. In this way, the driving behavior feature sample data corresponding to each time period can be divided into its corresponding cluster. Afterwards, for each cluster, the centroid of the cluster can be recalculated based on the driving behavior feature sample data corresponding to the multiple time periods within the cluster until the centroid of each cluster no longer changes or the maximum number of iterations is reached, at which point the target centroid corresponding to each cluster can be obtained.

[0096] It can be understood that for each cluster, the driving behavior feature sample data corresponding to the cluster's target centroid best represents the driving behavior characteristics of the driving style corresponding to that cluster. Thus, during the model inference phase, after inputting the driving behavior features calculated after real-time vehicle driving data collection into the trained K-means clustering model, the K-means clustering model can calculate the distance between the input driving behavior features and the target centroid of each cluster and then assign the driving behavior features to the target cluster with the closest distance. The driving style corresponding to this target cluster is the current driving style that matches the driving behavior features.

[0097] In step S304, the K-means clustering model is determined according to the target centroid corresponding to each cluster.

[0098] After obtaining the target centroid of each cluster through model training, the trained K-means clustering model can be obtained.

[0099] As described above, during step S101, in response to the current driving style being the target style, target prompt information may be output. The target style includes an aggressive driving style. In response to the target style being the aggressive driving style, the target prompt information is used to recommend that the user enable the racing mode. The target prompt information may include the racing mode operation switch and / or path information for the racing mode operation switch. In this way, the racing mode operation switch can be displayed to the user only when the current driving style is identified as the aggressive driving style, thereby improving the user experience.

[0100] For example, Figure 4 FIG. 1 is a schematic diagram of a racing mode recommendation window according to an exemplary embodiment. Figure 4As shown, the target prompt information can be output on the vehicle interface or the user's terminal interface. The target prompt information can include the operation switch of the racing mode (for example, it can be a soft switch), and can also include the path information of the racing mode operation switch, so that the target prompt information can provide clear interface guidance on the location of the racing mode operation switch, so that the user can easily find the racing mode switch, improve the convenience of user operation, and thus improve the user experience. Figure 4 As shown, the target prompt message may be "The system recognizes that your driving habits are aggressive. It is recommended that you turn on the racing mode. In this mode, you can enjoy the ultimate acceleration experience. You can also turn it on in Driving Settings → Driving Mode → Racing Mode." This example is for illustrative purposes only and is not limited to this disclosure.

[0101] It should be noted that if Figure 4 As shown, the UI interface design for outputting the target prompt information in the present disclosure should be simple to avoid redundant display of unnecessary information, thereby solving the problem of information overload displayed on the interface and improving user convenience in operation.

[0102] It should also be noted that the target styles that match the racing mode may also include multiple types. For example, when the current driving style is identified as an aggressive driving style or a normal driving style, the operation switch of the racing mode is displayed to the user.

[0103] In addition, in response to the user turning on the racing mode, the present disclosure can add the racing mode to the driving mode options of the vehicle. In response to the user not turning on the racing mode, the driving mode of the vehicle does not include the racing mode.

[0104] In one possible implementation, in response to a user triggering Figure 4 The soft switch "Enable Racing Mode" in the target prompt information of the interface shown can add the Racing Mode to the driving mode options. Alternatively, in response to identifying that the user's current driving style belongs to the target style, the Racing Mode is added to the driving mode options. For example, Figure 5 This is a driving mode display interface for an aggressive user according to an exemplary embodiment. Figure 5 As shown, for a user with an aggressive driving style, the driving mode displayed to the user includes the racing mode. In addition, if it is determined that the user has not enabled the racing mode (e.g., if the user has not triggered the "enable racing mode" soft switch within a preset time period), the vehicle's driving mode may be controlled to exclude the racing mode.

[0105] In another possible implementation, when the racing mode is recommended to the user multiple times, if it is determined that the user has not activated the recommended racing mode for a preset number of times (such as 2 consecutive times or 3 consecutive times), the racing mode may no longer be recommended to the user.

[0106] Furthermore, in response to the current driving style not being the target style, the present disclosure can disable the target mode's operating switch on a preset prompt interface. The preset prompt interface can be a display interface for the target prompt information (such as a vehicle-mounted interface or a user's terminal interface). Thus, by disabling the target mode's operating switch on the preset prompt interface when the current driving style is identified as not being the target style, users with non-target driving styles can be prevented from accidentally activating the target mode, thereby improving driving safety. It can also prevent unnecessary activation of driving modes, achieving the dual benefits of energy conservation and safe driving.

[0107] Among them, when the operation switch of the target mode on the preset prompt interface is in an inoperable state, the operation switch of the target mode can be controlled to be locked (such as in a gray state), or the driving mode of the vehicle can be controlled so that the target mode is not included.

[0108] For example, Figure 6 This is a driving mode display interface for a conservative user according to an exemplary embodiment. When recommending a racing mode to a user based on the current driving style, the target style is an aggressive driving style, such as Figure 6 As shown, for a user whose driving style is conservative rather than aggressive, the driving modes displayed to the user do not include the racing mode.

[0109] Using this method, the interface display of the target mode's operating switch can be personalized based on the user's driving style. Only when the user's current driving style matches the target mode is the target mode recommended to the user, and the target mode's operating switch and / or path information for the target mode's operating switch are displayed. If the user's current driving style is not the target style, the target mode's operating switch is set to an inoperable state on the interface. Therefore, the present disclosure provides a method for intelligently identifying a driver's driving style based on driving data (traffic data representing driving behavior) and reminding the driver to activate the target mode at the appropriate time, thereby improving vehicle usability and providing a personalized driving experience for the user.

[0110] In addition, when the present disclosure determines that the current driving style is the target style, it recommends the target mode to the user instead of forcing the user to directly enter the target mode, which increases the user's autonomy.

[0111] Compared with related technologies that mostly rely on hardware devices (such as random torque generators, linked optical devices, etc.) to enhance the driving experience, the present invention recommends target modes through intelligent driving behavior analysis, avoiding excessive hardware dependence, reducing costs, and simplifying the complexity of the system.

[0112] Figure 7 is a block diagram of a driving mode recommendation device according to an exemplary embodiment. Figure 7 As shown, the device includes:

[0113] The recommendation module 701 is configured to output target prompt information in response to the current driving style being the target style, wherein the target prompt information is used to recommend the user to activate the target mode; wherein the current driving style is obtained based on the driving data.

[0114] Optionally, Figure 8 is based on Figure 7 The embodiment shown is a block diagram of a driving mode recommendation device, as shown in FIG. Figure 8 As shown, the device also includes:

[0115] The driving style recognition module 702 is configured to determine driving behavior characteristics based on the driving data; and determine the current driving style based on the driving behavior characteristics.

[0116] Optionally, the driving style recognition module 702 is configured to determine the current driving style corresponding to the driving behavior characteristics through a pre-trained target classification model according to the driving behavior characteristics.

[0117] Optionally, the target classification model includes a K-means clustering model. Figure 9 is based on Figure 8 The embodiment shown is a block diagram of a driving mode recommendation device, as shown in FIG. Figure 9 As shown, the device also includes:

[0118] The model training module 703 is used to pre-train the K-means clustering model in the following manner: obtaining an initialized clustering model, wherein the initialization parameters of the clustering model include the number of classification clusters and the centroid corresponding to each cluster; wherein different clusters correspond to different driving styles, and for each cluster, the centroid of the cluster represents the driving behavior characteristics of the driving style corresponding to the cluster; obtaining training sample data, wherein the training sample data includes driving behavior characteristic sample data corresponding to multiple time periods; updating the centroid corresponding to each cluster according to the driving behavior characteristic sample data corresponding to the multiple time periods to obtain a target centroid; and determining the K-means clustering model according to the target centroid corresponding to each cluster.

[0119] Optionally, the driving data includes driving data corresponding to at least one preset time period, and the driving data corresponding to each preset time period includes driving data collected at at least one moment within the preset time period; the driving style recognition module 702 is used to process the driving data collected at at least one moment within the preset time period to obtain the driving behavior characteristics corresponding to the preset time period.

[0120] Optionally, the driving behavior characteristics include at least one of the following:

[0121] Vehicle speed standard deviation, average deceleration, average accelerator pedal position, average acceleration, average acceleration jerk, accelerator pedal position standard deviation, average vehicle speed, and maximum speed.

[0122] Optionally, the recommendation module 701 is further configured to, in response to the current driving style not being the target style, control an operation switch of the target mode on a preset prompt interface to be in an inoperable state.

[0123] Optionally, the target style includes an aggressive driving style, and in response to the aggressive driving style, the target prompt information is used to recommend the user to turn on a racing mode.

[0124] Optionally, the target prompt information includes the operation switch of the racing mode and / or path information of the operation switch of the racing mode.

[0125] Optionally, the recommendation module 701 is further configured to add the racing mode to the driving mode options of the vehicle in response to the user turning on the racing mode.

[0126] Regarding the apparatus in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.

[0127] Figure 10 FIG. 1 is a block diagram of an electronic device according to an exemplary embodiment. Figure 10 As shown, the electronic device 1000 may include: a processor 1001 , a memory 1002 , and may further include one or more of a multimedia component 1003 , an input / output (I / O) interface 1004 , and a communication component 1005 .

[0128] The processor 1001 is used to control the overall operation of the electronic device 1000 to complete all or part of the steps in the driving mode recommendation method described above. The memory 1002 is used to store various types of data to support the operation of the electronic device 1000. Such data may include, for example, instructions for any application or method operating on the electronic device 1000, as well as application-related data, such as contact information, sent and received messages, images, audio, video, etc. The memory 1002 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 read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk. The multimedia component 1003 may include a screen and an audio component. The screen may be, for example, a touch screen, and the audio component is used to output and / or input audio signals. For example, the audio component may include a microphone for receiving external audio signals. The received audio signals may be further stored in the memory 1002 or transmitted via the communication component 1005. The audio component also includes at least one speaker for outputting audio signals. The I / O interface 1004 provides an interface between the processor 1001 and other interface modules. The aforementioned other interface modules may be a keyboard, a mouse, buttons, etc. These buttons may be virtual buttons or physical buttons. The communication component 1005 is used for wired or wireless communication between the electronic device 1000 and other devices. Wireless communication, such as Wi-Fi, Bluetooth, Near Field Communication (NFC), 2G, 3G, 4G, NB-IOT, eMTC, or other 5G, etc., or a combination of one or more thereof, is not limited here. Therefore, the corresponding communication component 1005 may include: a Wi-Fi module, a Bluetooth module, an NFC module, etc.

[0129] In an exemplary embodiment, the electronic device 1000 may be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components to execute the above-mentioned driving mode recommendation method.

[0130] The present disclosure also provides a computer-readable storage medium having computer program instructions stored thereon. When the program instructions are executed by a processor, the steps of the driving mode recommendation method provided by the present disclosure are implemented.

[0131] In another exemplary embodiment, a computer program product is further provided. The computer program product includes a computer program executable by a programmable device, and the computer program has a code portion for executing the above-mentioned driving mode recommendation method when executed by the programmable device.

[0132] The preferred embodiments of the present disclosure are described in detail above in conjunction with the accompanying drawings. However, the present disclosure is not limited to the specific details of the above embodiments. Within the technical concept of the present disclosure, various simple modifications can be made to the technical solutions of the present disclosure, and these simple modifications all fall within the scope of protection of the present disclosure.

[0133] It should also be noted that the various specific technical features described in the above specific embodiments can be combined in any appropriate manner without contradiction. In order to avoid unnecessary repetition, the present disclosure will not further describe various possible combinations.

[0134] In addition, the various embodiments of the present disclosure may be arbitrarily combined, and as long as they do not violate the concept of the present disclosure, they should also be regarded as the contents disclosed by the present disclosure.

Claims

1. A driving mode recommendation method, characterized in that: The method comprises: In response to the current driving style being the target style, outputting target prompt information, wherein the target prompt information is used to recommend the user to turn on the target mode; The current driving style is obtained based on driving data.

2. The method according to claim 1, characterized in that The current driving style is obtained based on driving data, specifically including: determining a driving behavior characteristic based on the driving data; The current driving style is determined according to the driving behavior characteristics.

3. The method according to claim 2, characterized in that Determining the current driving style according to the driving behavior characteristics includes: According to the driving behavior characteristics, the current driving style corresponding to the driving behavior characteristics is determined by a pre-trained target classification model.

4. The method according to claim 3, characterized in that The target classification model includes a K-means clustering model, which is pre-trained in the following manner: Obtaining an initialized clustering model, wherein the initialization parameters of the clustering model include the number of classification clusters and the centroid corresponding to each cluster; wherein different clusters correspond to different driving styles, and for each cluster, the centroid of the cluster represents the driving behavior characteristics of the driving style corresponding to the cluster; Acquire training sample data, wherein the training sample data includes driving behavior feature sample data corresponding to multiple time periods; updating the centroid corresponding to each cluster according to the driving behavior feature sample data corresponding to the multiple time periods to obtain a target centroid; The K-means clustering model is determined according to the target centroid corresponding to each cluster.

5. The method according to claim 2, characterized in that The driving data includes driving data corresponding to at least one preset time period, and the driving data corresponding to each preset time period includes driving data collected at at least one moment within the preset time period; Determining the driving behavior characteristics according to the driving data includes: Data processing is performed on the driving data collected at at least one moment within the preset time period to obtain the driving behavior characteristics corresponding to the preset time period.

6. The method according to claim 5, characterized in that The driving behavior characteristics include at least one of the following: Vehicle speed standard deviation, average deceleration, average accelerator pedal position, average acceleration, average acceleration jerk, accelerator pedal position standard deviation, average vehicle speed, and maximum speed.

7. The method according to claim 1, characterized in that The method further comprises: In response to the current driving style not being the target style, an operation switch of the target mode on the preset prompt interface is controlled to be in an inoperable state.

8. The method according to claim 1 or 7, characterized in that The target style includes an aggressive driving style, and in response to the current driving style being the target style, outputting the target prompt information includes: In response to the aggressive driving style, the target prompt information is used to recommend the user to turn on the racing mode.

9. The method according to claim 8, characterized in that The target prompt information includes the operation switch of the racing mode and / or the path information of the operation switch of the racing mode.

10. The method according to claim 8, characterized in that The method further comprises: In response to the user turning on the racing mode, the racing mode is added to the driving mode options of the vehicle.

11. An electronic device, characterized in that: include: memory for storing computer programs; A processor, configured to execute the computer program stored in the memory, so that the device performs the steps of the method according to any one of claims 1 to 10.

12. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 10 are implemented.

13. A computer program product, characterized in that The invention comprises a computer program, which implements the steps of the method according to any one of claims 1 to 10 when the computer program is executed by a processor.

Images