Driving mode control method and device of vehicle, vehicle and storage medium

Abstract

The application relates to a driving mode control method and device of a vehicle, the vehicle and a storage medium, and comprises the following steps: determining current vehicle data of a target vehicle and historical behavior data of a driver; based on a preset working condition library, determining a current driving working condition of the target vehicle according to the current vehicle data, and determining a driving style of the driver according to the current driving working condition and the historical behavior data; determining final demand parameters according to working condition demand parameters corresponding to the current driving working condition and style demand parameters corresponding to the driving style, and adjusting whole-vehicle driving parameters of the target vehicle according to the final demand parameters. Therefore, through real-time analysis of vehicle working conditions and driving preferences, the embodiment of the application solves the problem that a static parameter mode cannot be dynamically adapted to working conditions and driving habits, which easily causes the whole-vehicle energy consumption to increase, the driving experience to be poor, and in serious cases, the driving safety to be affected, and the driving mode can be self-adaptively adjusted, the whole-vehicle energy consumption can be balanced, the driving experience can be optimized, and the driving safety of the vehicle can be ensured.

Description

Technical Field

[0001] This application relates to the field of vehicle technology, and in particular to a method, device, vehicle, and storage medium for controlling the driving mode of a vehicle. Background Technology

[0002] In related technologies, electric vehicle driving modes generally adopt a fixed parameter setting method. The vehicle controller pre-stores multiple sets of calibrated static parameter tables. Each driving mode, such as Economy, Sport, and Comfort, corresponds to a fixed set of control parameters, including torque response coefficient, motor power limit, pedal opening-torque mapping curve, energy feedback intensity, pedal filtering, and power delay. After receiving the mode switching command, the vehicle directly loads the corresponding parameter set and converts the pedal signal into a driving demand according to the preset mapping relationship, thus completing the vehicle's driving mode control.

[0003] However, actual driving scenarios are complex, encompassing various road conditions and weather environments, and drivers exhibit significant differences in their driving styles. Static parameter modes cannot dynamically adapt to changing operating conditions and driving habits, easily leading to increased vehicle energy consumption, a poor driving experience, and in severe cases, even affecting driving safety, which urgently needs to be addressed. Summary of the Invention

[0004] This application provides a driving mode control method, device, vehicle, and storage medium for a vehicle, in order to solve the problem that static parameter modes cannot be dynamically adapted to operating conditions and driving habits, which can easily lead to increased vehicle energy consumption, poor driving experience, and even affect driving safety in severe cases. The method can adaptively adjust the driving mode, balance vehicle energy consumption, optimize driving experience, and ensure vehicle driving safety.

[0005] The first aspect of this application provides a method for controlling the driving mode of a vehicle, comprising the following steps: Determine the current vehicle data of the target vehicle and the driver's historical behavior data; Based on a pre-set operating condition database, the current driving condition of the target vehicle is determined according to the current vehicle data, and the driver's driving style is determined according to the current driving condition and historical behavior data. The final requirement parameters are determined based on the operating condition requirement parameters corresponding to the current driving conditions and the style requirement parameters corresponding to the driving style, and the overall vehicle driving parameters of the target vehicle are adjusted according to the final requirement parameters.

[0006] Optionally, in some embodiments, before determining the current driving condition of the target vehicle based on the current vehicle data according to a preset operating condition database, the method further includes: Obtain full vehicle data for the target vehicle's corresponding model; The entire vehicle data is cleaned to obtain cleaned vehicle data, and the cleaned vehicle data is segmented according to a preset time interval to obtain multiple vehicle driving segments. Extract multi-dimensional feature parameters corresponding to each vehicle driving segment, and construct a preset working condition library based on multiple vehicle driving segments and the multi-dimensional feature parameters corresponding to each vehicle driving segment.

[0007] Optionally, in some embodiments, the driver's driving style is determined based on current driving conditions and historical behavior data, including: Input the current driving conditions and historical behavior data into the preset driving style classification model; The driver's driving style is obtained based on the output of the preset driving style classification model.

[0008] Optionally, in some embodiments, before inputting the current driving conditions and historical behavior data into a preset driving style classification model, the method further includes: Construct a driving style feature dataset; Based on a pre-defined working condition database, the driving style label corresponding to each driving style feature data under each working condition is obtained by clustering the driving style feature dataset. Based on the driving style label corresponding to each driving style feature data under each working condition, a preset neural network is trained to obtain a preset driving style classification model.

[0009] Optionally, in some embodiments, a driving style feature dataset is constructed, including: Collect historical driving behavior data from multiple target users; Based on historical driving data from multiple target users, multi-dimensional driving style representation parameters are extracted, and a driving style feature dataset is constructed based on these parameters.

[0010] Optionally, in some embodiments, before adjusting the overall driving parameters of the target vehicle according to the final demand parameters, the method further includes: Identify whether the target vehicle meets the preset adjustment conditions; If the target vehicle does not meet the preset adjustment conditions, the current driving parameters of the target vehicle will be maintained.

[0011] A second aspect of this application provides a driving mode control device for a vehicle, comprising: The acquisition module is used to determine the current vehicle data of the target vehicle and the driver's historical behavior data; The identification module is used to determine the current driving condition of the target vehicle based on the current vehicle data according to the preset driving condition database, and to determine the driver's driving style based on the current driving condition and historical behavior data. The adjustment module is used to determine the final requirement parameters based on the operating condition requirement parameters corresponding to the current driving conditions and the style requirement parameters corresponding to the driving style, and to adjust the overall vehicle driving parameters of the target vehicle based on the final requirement parameters.

[0012] Optionally, in some embodiments, before determining the current driving condition of the target vehicle based on the current vehicle data according to a preset operating condition database, the identification module is further configured to: Obtain full vehicle data for the target vehicle's corresponding model; The entire vehicle data is cleaned to obtain cleaned vehicle data, and the cleaned vehicle data is segmented according to a preset time interval to obtain multiple vehicle driving segments. Extract multi-dimensional feature parameters corresponding to each vehicle driving segment, and construct a preset working condition library based on multiple vehicle driving segments and the multi-dimensional feature parameters corresponding to each vehicle driving segment.

[0013] Optionally, in some embodiments, the identification module is specifically used for: Input the current driving conditions and historical behavior data into the preset driving style classification model; The driver's driving style is obtained based on the output of the preset driving style classification model.

[0014] Optionally, in some embodiments, before inputting the current driving conditions and historical behavior data into a preset driving style classification model, the identification module is further configured to: Construct a driving style feature dataset; Based on a pre-defined working condition database, the driving style label corresponding to each driving style feature data under each working condition is obtained by clustering the driving style feature dataset. Based on the driving style label corresponding to each driving style feature data under each working condition, a preset neural network is trained to obtain a preset driving style classification model.

[0015] Optionally, in some embodiments, the identification module is specifically used for: Collect historical driving behavior data from multiple target users; Based on historical driving data from multiple target users, multi-dimensional driving style representation parameters are extracted, and a driving style feature dataset is constructed based on these parameters.

[0016] Optionally, in some embodiments, before adjusting the overall driving parameters of the target vehicle according to the final demand parameters, the adjustment module is further configured to: Identify whether the target vehicle meets the preset adjustment conditions; If the target vehicle does not meet the preset adjustment conditions, the current driving parameters of the target vehicle will be maintained.

[0017] A third aspect of this application provides a vehicle, including: a memory, a processor, and a computer program stored in the memory and executable on the processor. The processor executes the program to implement the driving mode control method for the vehicle described in the first aspect embodiment.

[0018] A fourth aspect of this application provides a computer-readable storage medium having a computer program stored thereon, which is executed by a processor to implement the vehicle driving mode control method described in the first aspect embodiment.

[0019] Therefore, the embodiments of this application have at least the following beneficial effects: (1) By constructing a multi-dimensional working condition library and integrating real-time data such as congestion information, weather, and road surface adhesion coefficient, this application embodiment can accurately identify the current driving scenario at a frequency of minutes or hours, respond in real time to the ever-changing road conditions, environment and driver intentions, and make dynamic adjustments to driving parameters accordingly, realizing the leap from "static preset" to "dynamic adaptive", effectively improving vehicle driving performance and energy utilization efficiency.

[0020] (2) This application embodiment combines operating conditions with driving style for analysis. First, it identifies macro driving scenarios such as evening rush hour congestion, and then analyzes the driver's micro-operation behaviors such as acceleration, deceleration, and braking habits under these scenarios. Finally, it synthesizes a combination of control parameters consisting of "scenario baseline parameters + style offset". This solves the problem of isolated scenarios in related technologies. Through multi-dimensional coupling, it achieves global optimal control, which can match the common needs of corresponding scenarios, such as prioritizing driving smoothness in congested conditions, while also taking into account the driver's personalized operating preferences, such as satisfying the demand of aggressive drivers for rapid start-up response. Thus, it achieves more accurate and humanized global optimal control under complex coupled operating conditions, effectively improving user satisfaction.

[0021] (3) The embodiments of this application adopt a hierarchical decision-making architecture: the vehicle end undertakes low-latency real-time control tasks to ensure driving safety; the cloud gathers massive amounts of driving data to complete complex model training and strategy optimization such as driving style clustering and energy consumption prediction. This division of labor enables a single vehicle to instantly call upon the "collective intelligence" trained in the cloud, while the data generated by the vehicle end supports the iteration of the cloud model, forming a data closed loop for continuous learning and optimization. Based on the online learning mechanism, it can adapt to long-term changes in user driving habits and new driving scenarios, and improve itself with the growth of the user group and changes in the driving environment. Through the "end-cloud collaboration" architecture, it takes into account both real-time response capabilities and global optimization capabilities, and realizes continuous system evolution.

[0022] (4) The embodiments of this application mainly rely on software algorithms and existing vehicle sensors. Over-the-Air (OTA) technology can be used to upgrade existing models, which can enable functions with low hardware modification costs and high return on investment. It supports scene adaptation and personalized power parameter calibration capabilities. Through dynamic parameter optimization, it can reduce vehicle energy consumption, improve driving stability, and enhance driving quality and ride comfort. At the same time, it can be used as a core selling point of the product to create an image of an intelligent electric vehicle that "understands you better and adapts to the environment." This distinguishes it from similar competing products that have rich modes but poor adaptability, effectively enhancing the product's differentiated competitiveness and brand technological sense, strengthening user stickiness, and combining functional performance improvement with commercial application value.

[0023] Additional aspects and advantages of this application will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of this application. Attached Figure Description

[0024] The above and / or additional aspects and advantages of this application will become apparent and readily understood from the following description of the embodiments taken in conjunction with the accompanying drawings, wherein: Figure 1 This is a flowchart of a vehicle driving mode control method according to an embodiment of this application; Figure 2 This is a flowchart of a vehicle driving mode control method according to an embodiment of this application; Figure 3 This is a block diagram of a vehicle driving mode control device according to an embodiment of this application; Figure 4 This is a schematic diagram of the structure of a vehicle according to an embodiment of this application. Detailed Implementation

[0025] The embodiments of this application are described in detail below. Examples of these embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and intended to explain this application, and should not be construed as limiting this application.

[0026] The following description, with reference to the accompanying drawings, describes a vehicle driving mode control method, apparatus, vehicle, and storage medium according to embodiments of this application.

[0027] Before introducing the vehicle driving mode control method of this application, let me briefly introduce the vehicle control methods in related technologies.

[0028] Specifically, the related art proposes a vehicle-wide multi-mode cooperative control system based on driving habit recognition, which integrates a driving style analysis module through a multi-mode ECU, and links the powertrain, braking, steering, suspension and Human-Machine Interface (HMI) systems to realize global switching of preset modes such as standard, sport, and comfort. Its core feature is the use of the Controller Area Network (CAN) to realize unified mode adaptation of the entire vehicle system, so that the driver can clearly perceive the changes in vehicle state under different modes.

[0029] However, the vehicle control method in the related art relies on fixed preset driving modes, and only completes mode switching based on historical driving habits, lacking fusion processing of real-time road conditions, environmental conditions and cloud data, resulting in insufficient adaptability. On the one hand, the control strategy tends to be static, the driving mode parameters are fixed, and the collaborative optimization of energy efficiency and scenarios is not considered. Most of the processing is only carried out for a single dimension of driving style or road conditions, making it difficult to achieve multi-scenario linkage optimization, resulting in isolation of each scenario; on the other hand, the division of labor between the vehicle end and the cloud end is ambiguous, real-time control and global optimization cannot be effectively coordinated, the matching between energy efficiency and actual driving scenarios cannot be considered, and environmental changes cannot be dynamically responded to.

[0030] Based on the above problems, the present application provides a driving mode control method for a vehicle, which can determine the current driving condition of the target vehicle according to the current vehicle data of the target vehicle based on a preset working condition library, and determine the driving style of the driver in combination with the historical behavior data of the driver; determine the final demand parameter according to the working condition demand parameter corresponding to the current driving condition and the style demand parameter corresponding to the driving style, so as to adjust the entire vehicle driving parameter of the target vehicle. This solves the problem that the static parameter mode cannot be dynamically adapted to working conditions and driving habits, which easily causes increased vehicle energy consumption, poor driving experience, and even affects driving safety in severe cases, and can adaptively adjust the driving mode, balance vehicle energy consumption, optimize driving and riding experience, and ensure vehicle driving safety.

[0031] Specifically, Figure 1 is a flowchart of a driving mode control method for a vehicle provided by an embodiment of the present application.

[0032] As Figure 1 shown, the driving mode control method for the vehicle includes the following steps: In step S101, current vehicle data of the target vehicle and historical behavior data of the driver are determined.

[0033] Specifically, in this embodiment, the driving status and operating parameters of the target vehicle can be collected in real time using onboard sensors and vehicle controllers as current vehicle data. Simultaneously, the driver's operation records from multiple past trips are retrieved from the vehicle-side storage unit and the cloud-based backend database as historical behavior data. Next, data cleaning, outlier removal, and time alignment are performed on both types of data to eliminate invalid samples caused by signal loss and interference noise, thereby obtaining standardized current vehicle data and driver historical behavior data.

[0034] In step S102, based on a preset operating condition database, the current driving condition of the target vehicle is determined according to the current vehicle data, and the driver's driving style is determined according to the current driving condition and historical behavior data.

[0035] In some embodiments, determining the driver's driving style based on current driving conditions and historical behavior data includes: inputting the current driving conditions and historical behavior data into a preset driving style classification model; and obtaining the driver's driving style based on the output of the preset driving style classification model.

[0036] Specifically, this embodiment of the application can input current driving conditions and historical behavior data into a preset driving style classification model based on a preset driving condition database. The preset driving style classification model then matches the coupled driving condition samples corresponding to the current driving condition with these samples. It performs feature comparison and category probability calculation on multi-dimensional input features of throttle, braking, steering, and vehicle assistance settings, and outputs the corresponding driving style label. Finally, the driver's driving style is obtained based on the output of the preset driving style classification model. This avoids recognition bias caused by detachment from the actual driving environment, making the recognition results more consistent with the driver's real driving habits and providing a reliable decision-making basis for the dynamic adjustment of the vehicle's subsequent adaptive driving strategy.

[0037] In step S103, the final requirement parameters are determined based on the working condition requirement parameters corresponding to the current driving condition and the style requirement parameters corresponding to the driving style, and the overall vehicle driving parameters of the target vehicle are adjusted based on the final requirement parameters.

[0038] Specifically, after obtaining the current driving condition classification and driving style classification, this embodiment first needs to mine the vehicle driving parameter requirements under complex scenarios. It can extract the corresponding driving condition requirement parameters (i.e., optimal vehicle parameter settings) based on the group behavior under this condition. Then, combined with the driver's individual habits, the driving condition requirement parameters are fine-tuned to obtain the final requirement parameters, thereby completing the analysis of the driver's driving parameter requirements under specific conditions. This embodiment can define the vehicle requirements as: ; It should be understood that the aforementioned operating condition requirements refer to the demands imposed on operating condition parameters (i.e., vehicle drivability parameters) by external factors such as time, climate, and road conditions, while driving style requirements refer to the demands imposed on style parameters by the individualized habit differences of the target driver. After the above two parts of the requirements analysis are completed, the embodiments of this application can be superimposed to form the final vehicle requirements.

[0039] Furthermore, the process of determining the final demand parameters described above can be broken down into the following three steps: Step 1: This application embodiment can perform operating condition demand mining. Based on the historical behavior of a large number of users in the same scenario, the operating condition demand parameters corresponding to the current driving condition are statistically derived (i.e., the parameter preferences of most users in this scenario). For example, by comparing the difference between the user's pedal opening in a specific scenario and the global average, it can be determined whether the power response should be increased, or by statistically analyzing the frequency of suspension height adjustments in a certain geographical location, it can be inferred whether the vehicle body needs to be raised for that road section.

[0040] Step Two: This application embodiment can perform driving style demand mining. Based on the operating condition demand parameters (i.e., common parameters), fine-tuning is performed by combining the current driver's clustering style to obtain the style demand parameters corresponding to the driving style. For example, an aggressive driver may expect a more direct pedal mapping and a suspension performance with higher damping in high-speed scenarios, while a gentle driver prefers a chassis tuning that is linear acceleration and comfort-oriented.

[0041] Step 3: This embodiment of the application can perform optimal parameter synthesis. The final requirement parameters are determined based on the operating condition requirement parameters corresponding to the current driving conditions and the style requirement parameters corresponding to the driving style. The final output is a combination of "operating condition requirement parameters (i.e., scenario baseline parameters) + style requirement parameters (i.e., style offset)," which reflects both scenario consensus and individual differences. Furthermore, this embodiment of the application can introduce statistical inference and regression models in the above process to ensure the reliability and stability of parameter settings.

[0042] Furthermore, after determining the final required parameters, this embodiment of the application requires individualized dynamic control of driving parameters. The overall driving parameters of the target vehicle are adjusted according to the final required parameters, that is, the above analysis results are transformed into specific vehicle actuator parameters to achieve closed-loop control. Specifically, this embodiment of the application first needs to establish a parameter mapping mechanism, that is, to establish a functional relationship from behavioral characteristics to overall vehicle control parameters. For example: adjusting the Pedal-map curve shape based on the median accelerator pedal opening, thereby affecting torque response; adjusting the energy recovery level and comfort braking intervention timing based on braking frequency and intensity; dynamically switching the steering assist mode (e.g., light, standard, sport) based on the average steering wheel speed; and adjusting the shock absorber damping and suspension height based on the number of occupants and the degree of road bumps.

[0043] It should be understood that, in the process of adjusting the overall driving parameters of the target vehicle according to the final demand parameters, the embodiments of this application can also specify a multi-layer adjustment strategy, namely, adopting a layered adjustment mechanism: the first layer switches the basic mode according to the scenario type; the second layer completes a secondary fine-tuning based on the driving style obtained in real time; and the third layer further enables a personalized calibration mechanism on the premise that sufficient user data has been accumulated.

[0044] Furthermore, the embodiments of this application can also perform cloud-based collaborative optimization. The cloud is responsible for model training and policy generation, while the vehicle is responsible for real-time perception and lightweight inference. Both utilize over-the-air (OTA) updates to achieve model iteration and parameter updates, jointly constructing a continuously evolving driving intelligence system.

[0045] Therefore, this application proposes an edge-cloud collaborative dynamic adaptive driving mode control method. Through data interaction between the vehicle and the cloud, it dynamically integrates multi-dimensional information such as environment, user preferences, and vehicle status to achieve autonomous optimization of driving parameters, thereby improving vehicle driving adaptability and energy utilization efficiency. Specifically, this application integrates multi-source data fusion, combining vehicle-side sensors, user habits, and cloud-based traffic and meteorological data to construct a dynamic driving parameter optimization model. Through a hierarchical decision-making architecture, the vehicle handles low-latency real-time control such as torque response, while the cloud processes high-dimensional computational tasks such as energy consumption prediction, achieving efficient collaboration with edge nodes. Furthermore, through an online learning mechanism, the control strategy is iteratively updated based on reinforcement learning to adapt to long-term user preferences and short-term environmental changes. Driving parameters are dynamically adjusted according to multi-source information to achieve real-time adaptive control driven by edge-cloud collaboration, effectively improving vehicle driving performance, energy efficiency, and user experience in various complex scenarios.

[0046] Furthermore, to enable those skilled in the art to better understand how the preset operating condition library is constructed in the vehicle driving mode control method of this application, the following description is provided in conjunction with specific embodiments.

[0047] As one possible implementation, in some embodiments, before determining the current driving condition of the target vehicle based on the current vehicle data according to the preset operating condition library, the method further includes: acquiring full vehicle data of the target vehicle's corresponding model; cleaning the full vehicle data to obtain cleaned vehicle data, and segmenting the cleaned vehicle data into multiple vehicle driving segments according to a preset time interval; extracting multi-dimensional feature parameters corresponding to each vehicle driving segment, and constructing a preset operating condition library based on the multiple vehicle driving segments and the multi-dimensional feature parameters corresponding to each vehicle driving segment.

[0048] The preset time interval can be a time interval pre-set by the user, a time interval obtained through a limited number of experiments, or a time interval obtained through a limited number of computer simulations; no specific limitation is made here.

[0049] Specifically, since the foundation for building the preset operating condition database is the statistical analysis of a large amount of vehicle data, the embodiments of this application can extract the full vehicle data of the target vehicle corresponding to the vehicle model from the cloud data platform, and perform data cleaning work such as data filtering, data interpolation, data conversion, and outlier processing to obtain cleaned vehicle data.

[0050] Furthermore, in this embodiment, vehicle driving segments can be extracted from vehicle status messages, combined with message parameters such as vehicle speed and current. These segments are then divided and cleaned according to a preset time interval to obtain multiple vehicle driving segments. The length of the preset time interval depends on the desired timeliness of the driving mode control; it can be long or short, but is recommended to be set between 10 minutes and 1 hour.

[0051] Furthermore, embodiments of this application can perform statistical analysis on the parameters within each vehicle driving segment, extract multi-dimensional feature parameters corresponding to each vehicle driving segment, and construct a preset driving condition library based on multiple vehicle driving segments and the multi-dimensional feature parameters corresponding to each vehicle driving segment. This preset driving condition library not only provides a structured expression for scene coupling but also provides semantic support for subsequent driving style clustering and parameter decision-making. The preset driving condition library, as the basis for identifying and classifying driving scenarios, can be constructed using a multi-dimensional, multi-source data fusion approach, including but not limited to the following dimensions: (1) Time attributes: can be divided by hour, including: morning peak 7:00-9:00, evening peak 17:00-20:00, daytime off-peak 9:00-17:00, nighttime 20:00-7:00 the next day, and further subdivided into each time period by combining weekday, holiday and other date types.

[0052] (2) Climate and environmental parameters: can be divided according to ambient temperature, including: high temperature > 30℃, medium temperature 10~30℃, low temperature < 10℃, or according to weather conditions, including: rain, snow, fog, sunny, etc.

[0053] (3) Real-time traffic information: The degree of congestion can be identified by indicators such as average vehicle speed, vehicle speed variance, and acceleration and deceleration frequency, and the road specifications (such as urban roads, expressways, ring roads, etc.) and road surface adhesion coefficient can be determined by combining high-precision map data.

[0054] (4) Vehicle energy status: including battery state of charge (SOC), maximum allowable discharge power, historical energy consumption data, etc.

[0055] (5) Passenger information: The current driver's identity can be identified through the account system, and whether there are passengers in the back row can be detected by in-vehicle sensors or seat pressure.

[0056] (6) Driving behavior intention recognition: It can help visual perception or vehicle dynamic signals to infer and recognize behaviors such as overtaking, sudden changes in following distance, and switching between high-speed / congested road sections.

[0057] (7) Energy management mode: such as whether it is in an energy-saving state or a high-performance demand state.

[0058] It should be understood that when constructing the preset working condition database, the embodiments of this application are not limited to the feature parameters listed above. They can also combine the characteristics of the vehicle itself to add environmental perception dimension information such as lane lines and surrounding vehicles to achieve a comprehensive judgment of the current working condition.

[0059] Therefore, this application embodiment constructs a multi-dimensional, structured driving condition database. By integrating multi-source heterogeneous data such as time attributes (e.g., peak hours), climate environment (e.g., temperature, weather), real-time road conditions (e.g., congestion level, road type), vehicle energy state (e.g., SOC), occupant information, and driving behavior intentions, vehicle driving segments are divided and features are extracted. Complex coupled conditions such as "heavy rain + evening rush hour" are identified and labeled, providing a precise data foundation for subsequent scenario-based analysis.

[0060] Furthermore, to enable those skilled in the art to better understand how the preset driving style classification model in the vehicle driving mode control method of this application is constructed, the following description is provided in conjunction with specific embodiments.

[0061] As one possible implementation, in some embodiments, before inputting the current driving conditions and historical behavior data into the preset driving style classification model, the method further includes: constructing a driving style feature dataset; clustering the driving style feature dataset according to a preset driving condition database to obtain the driving style label corresponding to each driving style feature data under each driving condition; and training a preset neural network to obtain the preset driving style classification model based on the driving style label corresponding to each driving style feature data under each driving condition.

[0062] In some embodiments, constructing a driving style feature dataset includes: collecting historical driving behavior data from multiple target users; extracting multi-dimensional driving style representation parameters based on the historical driving data from multiple target users; and constructing a driving style feature dataset based on the multi-dimensional driving style representation parameters.

[0063] Specifically, in this embodiment, it is first necessary to collect historical driving behavior data of multiple target users, and then mine driving style representation parameters of the historical driving data of multiple target users to obtain multi-dimensional driving style representation parameters, and construct a driving style feature dataset based on the multi-dimensional driving style representation parameters.

[0064] It should be understood that the aforementioned driving style characterization parameters refer to statistical parameters or calculated values ​​that characterize the user's driving behavior, also known as driving style factors. A driver's driving behavior mainly consists of four parts: accelerator pedal, brake pedal, steering wheel, and driver assistance settings. Accelerator pedal style can be characterized by parameters such as the median and average accelerator pedal opening over a given time period; brake pedal style can be characterized by parameters such as the frequency of brake pedal presses, the median and average pedal opening; steering wheel style can be characterized by parameters such as average engine speed and average steering angle; and driver assistance settings mainly include user-defined driving mode settings, whether comfort braking is enabled, and gear selection.

[0065] Furthermore, embodiments of this application can perform feature clustering on the aforementioned driving style feature dataset based on a pre-defined operating condition database to obtain driving style labels corresponding to each driving style feature data under each operating condition. Specifically, for various coupled operating conditions such as "morning rush hour + high temperature + low speed," K-Means clustering algorithm, Gaussian Mixture Model (GMM), or noisy density-based spatial clustering algorithm can be used. Based on unsupervised learning algorithms such as Spatial Clustering of Applications with Noise (DBSCAN), driver behavior characteristics are clustered using the aforementioned driving style representation parameters. The number of clusters can be dynamically determined (e.g., 3-5). Typical driving style labels include: aggressive, normal, and mild, and can be further subdivided into labels such as extremely aggressive and extremely fuel-efficient. The coupled operating conditions are formed by the intersection of different types of operating conditions.

[0066] Furthermore, embodiments of this application can train a preset neural network to obtain a preset driving style classification model based on the driving style label corresponding to each driving style feature data under each working condition. Specifically, after the unsupervised clustering model is trained, for complex working conditions such as "heavy rain + evening rush hour + highway section", intelligent classification algorithms such as rule-based tree models or lightweight neural networks can be used to classify the driver's driving style under this working condition for subsequent driving parameter determination.

[0067] It should be understood that the above-mentioned driving style clustering and classification analysis is based on a pre-built, pre-defined working condition database, and is implemented by selecting differentiated AI methods according to actual business needs, aiming to capture drivers' behavioral preferences under different working conditions.

[0068] Therefore, this application proposes a driving style clustering and classification method that takes into account driving conditions. It binds driving style analysis to specific driving conditions. For each identified specific driving condition, driving style factors are extracted from operation data such as acceleration, braking, and steering wheel. An unsupervised learning algorithm is used to cluster the driver's behavioral characteristics under the driving condition, defining style categories such as aggressive and gentle. The trained classification model is then used to determine the style of real-time driving behavior, providing a direct basis for personalized driving parameter adjustment.

[0069] Furthermore, to enable those skilled in the art to better understand how the vehicle driving mode control method of this application ensures operational stability and reliability, the following description is provided in conjunction with specific embodiments.

[0070] As one possible implementation, in some embodiments, before adjusting the overall driving parameters of the target vehicle according to the final demand parameters, the method further includes: identifying whether the target vehicle meets preset adjustment conditions; if the target vehicle does not meet the preset adjustment conditions, then maintaining the current driving parameters of the target vehicle.

[0071] The preset adjustment conditions can be conditions set by the user, conditions obtained through a limited number of experiments, or conditions obtained through a limited number of computer simulations; no specific limitations are made here.

[0072] Specifically, to avoid the discomfort caused by frequent switching of driving modes, this application embodiment needs to construct a decision smoothness and stability guarantee mechanism. This is achieved by adopting a time window mechanism (such as triggering a switch only after two consecutive cycles of stable operating conditions) and supporting gradual parameter transitions, thereby ensuring a natural and consistent user experience. The time window can be flexibly adjusted according to vehicle characteristics and real-time control requirements, adaptively extending or shortening it.

[0073] Furthermore, the aforementioned preset adjustment conditions can also be operating condition determination conditions, vehicle operating condition conditions, and user interaction condition conditions. The operating condition determination condition verifies that the current driving condition has entered a stable state, eliminating false triggers caused by instantaneous disturbances. The vehicle operating condition verifies that vehicle speed, power load, and other overall vehicle operating parameters are within a reasonable range for adjustment. The user interaction condition identifies whether the user is actively interfering with driving; when active user intervention is detected, the parameter adjustment request is blocked. Only when all of the above conditions are met is the adjustment of the vehicle driving parameters allowed, thereby avoiding invalid adjustments and mode switching issues from the source and ensuring the safety and smoothness of driving control.

[0074] Therefore, the embodiments of this application can, while taking into account scene adaptation and personalized adjustment of driving style, avoid parameter misadjustment and frequent mode jumps caused by instantaneous operating condition disturbances based on the pre-adjustment condition verification and smooth decision-making mechanism. On the basis of ensuring the safety and stability of vehicle control, the smoothness of the driving mode switching process and the driving experience are improved.

[0075] Furthermore, to enable those skilled in the art to better understand the vehicle driving mode control method of this application, the following is combined with... Figure 2 The illustrated embodiments will be used for explanation.

[0076] Figure 2 A flowchart of a vehicle driving mode control method provided in an embodiment of this application.

[0077] like Figure 2 As shown, the driving mode control method for this vehicle includes the following steps: S201 completes the construction of the preset working condition library (i.e., multi-dimensional working condition library) through data cleaning and preprocessing, data segmentation and working condition construction.

[0078] S202 completes driving style classification through driving style factor extraction, feature clustering, and style classification.

[0079] S203 completes the mining of requirements for complex scenarios through working condition requirements mining, driving style requirements mining, and optimal parameter synthesis.

[0080] S204 achieves dynamic control of driving parameters through parameter mapping, multi-layer adjustment, parameter stabilization control, and cloud-based collaborative optimization.

[0081] Specifically, this application proposes a vehicle dynamic adaptive driving mode control method. This method utilizes edge-cloud collaborative computing, combining the vehicle's current driving conditions and driver preferences, to dynamically adjust the vehicle's power and chassis parameters in real time, enabling the vehicle's output characteristics to adapt to the current driving conditions and the corresponding driver's driving needs. The method mainly includes: constructing a multi-dimensional driving condition database, clustering driving styles considering driving condition differences, mining vehicle driving parameter requirements in complex scenarios, and integrated dynamic control of driving parameters. This application is implemented based on massive cloud-based vehicle data and artificial intelligence machine learning algorithms. The specific execution process is as follows: First, multi-vehicle data is fused, and historical vehicle data is segmented into single driving segments. The driving condition distribution of each segment is analyzed, and the main driving condition categories are extracted and classified. Second, for each driving condition, driver acceleration, braking, and steering operation data are extracted to obtain driving style factor features, and clustering algorithms are used to distinguish the driving style types of different drivers. Next, driving condition information and driving style information are fused to analyze scenario requirements. Finally, based on the analyzed scenario requirements, the vehicle's power-related parameters are adjusted to complete the adaptive adjustment of the driving mode. This application's embodiments utilize an edge-cloud collaborative architecture, based on multi-dimensional scene recognition, and combined with driver behavior clustering and vehicle parameter optimization strategies. It can dynamically optimize driving modes at minute-level or hour-level update frequencies, solving the shortcomings of related technologies where fixed driving modes cannot dynamically adjust according to operating conditions and driver habits. It enables vehicles to autonomously, smoothly, and efficiently adjust under different driving conditions and user habits, taking into account vehicle power, economy, and driving stability, and effectively improving the overall driving experience.

[0082] Furthermore, this application proposes a method for mining and synthesizing vehicle parameter requirements in complex scenarios. The core decision-making step of this application lies in proposing a parameter synthesis model of "vehicle requirements = operating condition requirements + driving style requirements". First, based on historical data of a large number of users under the same operating conditions, the common parameter preferences of the group in this scenario are statistically obtained as operating condition requirements; then, combined with the real-time style classification results of the current driver, the above common parameters are individually fine-tuned to generate driving style requirements; finally, the fusion method of "operating condition requirement parameters + style requirement parameters" is adopted to output the final requirement parameters (i.e., optimal vehicle driving parameters) that take into account both the consensus of the scenario group and the individual differences of the driver.

[0083] Furthermore, this application proposes an integrated dynamic control and execution scheme for driving parameters, achieving dynamic parameter execution through a closed-loop control mechanism involving both end and cloud. Specifically, this application constructs a mapping relationship from behavioral features to vehicle actuator parameters (such as Pedal-map curves, energy recovery levels, and steering assist modes), and employs a multi-layered adjustment strategy of "basic mode switching - style fine-tuning - personalized calibration." To ensure a smooth driving experience, a time window judgment and parameter gradual transition mechanism are introduced to avoid frequent switching. The cloud is responsible for model training and strategy distribution, while the vehicle is responsible for real-time perception and lightweight inference, jointly achieving adaptive and smooth optimization of the driving mode.

[0084] Furthermore, embodiments of this application can also integrate the above-described driving mode control method into a driving mode control system. In the cloud, model pre-training is performed using data and computing power from a big data platform, and the trained model is integrated into the vehicle controller. At the vehicle end, CAN bus data is downsampled and calculated using the on-board controller model to control the vehicle parameters.

[0085] In summary, this application, through its edge-cloud collaborative architecture design, fully leverages the advantages of big data in driving behavior analysis and scenario understanding, combined with the vehicle's low-latency response capabilities, to achieve efficient, intelligent, and personalized adjustment of driving modes. This is not only suitable for upgrading and iterating existing models, but also provides a solid technical foundation for the global energy management and driving experience optimization of future intelligent electric vehicles.

[0086] The vehicle driving mode control method proposed in this application can determine the current driving condition based on the current vehicle data of the target vehicle according to a preset operating condition library, and determine the driver's driving style by combining the driver's historical behavior data; the final demand parameters are determined based on the operating condition demand parameters corresponding to the current driving condition and the style demand parameters corresponding to the driving style, thereby adjusting the overall driving parameters of the target vehicle. This solves the problem that static parameter modes cannot dynamically adapt to operating conditions and driving habits, easily leading to increased vehicle energy consumption, poor driving experience, and in severe cases, affecting driving safety. It can adaptively adjust the driving mode, balance vehicle energy consumption, optimize driving experience, and ensure vehicle driving safety.

[0087] Next, referring to the accompanying drawings, an embodiment of the present application provides a vehicle driving mode control device.

[0088] Figure 3 This is a block diagram of a vehicle driving mode control device according to an embodiment of this application.

[0089] like Figure 3As shown, the driving mode control device 10 of the vehicle includes: an acquisition module 100, an identification module 200, and an adjustment module 300.

[0090] The acquisition module 100 is used to determine the current vehicle data of the target vehicle and the driver's historical behavior data; the identification module 200 is used to determine the current driving condition of the target vehicle based on the current vehicle data according to a preset working condition library, and to determine the driver's driving style based on the current driving condition and historical behavior data; the adjustment module 300 is used to determine the final requirement parameters based on the working condition requirement parameters corresponding to the current driving condition and the style requirement parameters corresponding to the driving style, and to adjust the overall driving parameters of the target vehicle based on the final requirement parameters.

[0091] Optionally, in some embodiments, before determining the current driving condition of the target vehicle based on the current vehicle data according to the preset operating condition library, the identification module 200 is further configured to: acquire full vehicle data of the target vehicle's corresponding model; perform data cleaning on the full vehicle data to obtain cleaned vehicle data, and divide the cleaned vehicle data into multiple vehicle driving segments according to a preset time interval; extract multi-dimensional feature parameters corresponding to each vehicle driving segment, and construct a preset operating condition library based on the multiple vehicle driving segments and the multi-dimensional feature parameters corresponding to each vehicle driving segment.

[0092] Optionally, in some embodiments, the identification module 200 is specifically used to: input the current driving conditions and historical behavior data into a preset driving style classification model; and obtain the driver's driving style based on the output of the preset driving style classification model.

[0093] Optionally, in some embodiments, before inputting the current driving conditions and historical behavior data into the preset driving style classification model, the identification module 200 is further configured to: construct a driving style feature dataset; based on a preset driving condition database, cluster the driving style feature dataset to obtain the driving style label corresponding to each driving style feature data under each driving condition; and train a preset neural network to obtain a preset driving style classification model based on the driving style label corresponding to each driving style feature data under each driving condition.

[0094] Optionally, in some embodiments, the identification module 200 is specifically used to: collect historical driving behavior data of multiple target users; extract multi-dimensional driving style representation parameters based on the historical driving data of multiple target users, and construct a driving style feature dataset based on the multi-dimensional driving style representation parameters.

[0095] Optionally, in some embodiments, before adjusting the overall driving parameters of the target vehicle according to the final demand parameters, the adjustment module 300 is further configured to: identify whether the target vehicle meets the preset adjustment conditions; if the target vehicle does not meet the preset adjustment conditions, then maintain the current driving parameters of the target vehicle.

[0096] It should be noted that the foregoing explanation of the vehicle driving mode control method embodiment also applies to the vehicle driving mode control device of this embodiment, and will not be repeated here.

[0097] The vehicle driving mode control device proposed in this application can determine the current driving condition based on a preset operating condition database and the current vehicle data of the target vehicle, and determine the driver's driving style by combining the driver's historical behavior data; it then determines the final requirement parameters based on the operating condition requirement parameters corresponding to the current driving condition and the style requirement parameters corresponding to the driving style, thereby adjusting the overall driving parameters of the target vehicle. This solves the problem that static parameter modes cannot dynamically adapt to operating conditions and driving habits, easily leading to increased vehicle energy consumption, poor driving experience, and in severe cases, affecting driving safety. The device can adaptively adjust the driving mode, balance vehicle energy consumption, optimize driving experience, and ensure vehicle driving safety.

[0098] Figure 4 A schematic diagram of the structure of a vehicle provided in an embodiment of this application. The vehicle may include: The memory 401, the processor 402, and the computer program stored on the memory 401 and capable of running on the processor 402.

[0099] When the processor 402 executes the program, it implements the vehicle driving mode control method provided in the above embodiments.

[0100] Furthermore, the vehicle also includes: Communication interface 403 is used for communication between memory 401 and processor 402.

[0101] The memory 401 is used to store computer programs that can run on the processor 402.

[0102] Memory 401 may include high-speed RAM memory, and may also include non-volatile memory, such as at least one disk storage device.

[0103] If the memory 401, processor 402, and communication interface 403 are implemented independently, then the communication interface 403, memory 401, and processor 402 can be interconnected via a bus to complete communication between them. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. Buses can be categorized as address buses, data buses, control buses, etc. For ease of representation, Figure 4 The bus is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.

[0104] Optionally, in a specific implementation, if the memory 401, processor 402, and communication interface 403 are integrated on a single chip, then the memory 401, processor 402, and communication interface 403 can communicate with each other through an internal interface.

[0105] Processor 402 may be a central processing unit (CPU), an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of this application.

[0106] This application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the following... Figure 1 The driving mode control method of the vehicle shown.

[0107] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0108] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this application, "N" means at least two, such as two, three, etc., unless otherwise explicitly specified.

[0109] Any process or method described in the flowchart or otherwise herein can be understood as representing a module, segment, or portion of code comprising one or more N executable instructions for implementing custom logic functions or processes, and the scope of the preferred embodiments of this application includes additional implementations in which functions may be performed not in the order shown or discussed, including substantially simultaneously or in reverse order depending on the functions involved, as should be understood by those skilled in the art to which embodiments of this application pertain.

[0110] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-included system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of computer-readable media include: an electrical connection having one or more wires (electronic device), a portable computer disk drive (magnetic device), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Alternatively, the computer-readable medium may be paper or other suitable media on which the program can be printed, since the program can be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, interpreting, or otherwise processing as necessary, and then stored in a computer memory.

[0111] It should be understood that the various parts of this application can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiments, the N steps or methods can be implemented using software or firmware stored in memory and executed by a suitable instruction execution system. If implemented in hardware, as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0112] Those skilled in the art will understand that all or part of the steps of the methods in the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, the program includes one or a combination of the steps of the method embodiments.

[0113] Furthermore, the functional units in the various embodiments of this application can be integrated into a processing module, or each unit can exist physically separately, or two or more units can be integrated into a module. The integrated module can be implemented in hardware or as a software functional module. If the integrated module is implemented as a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium.

[0114] The storage medium mentioned above can be a read-only memory, a disk, or an optical disk, etc. Although embodiments of this application have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting this application. Those skilled in the art can make changes, modifications, substitutions, and variations to the above embodiments within the scope of this application.

Claims

1. A method for controlling the driving mode of a vehicle, characterized in that, include: Determine the current vehicle data of the target vehicle and the driver's historical behavior data; Based on a preset operating condition database, the current driving condition of the target vehicle is determined according to the current vehicle data, and the driver's driving style is determined according to the current driving condition and the historical behavior data. The final requirement parameters are determined based on the operating condition requirement parameters corresponding to the current driving condition and the style requirement parameters corresponding to the driving style, and the overall vehicle driving parameters of the target vehicle are adjusted based on the final requirement parameters.

2. The method according to claim 1, characterized in that, Before determining the current driving condition of the target vehicle based on the current vehicle data according to the preset operating condition database, the method further includes: Obtain full vehicle data for the model corresponding to the target vehicle; The full vehicle data is cleaned to obtain cleaned vehicle data, and the cleaned vehicle data is segmented according to a preset time interval to obtain multiple vehicle driving segments. Extract the multi-dimensional feature parameters corresponding to each vehicle driving segment, and construct the preset working condition library based on the multiple vehicle driving segments and the multi-dimensional feature parameters corresponding to each vehicle driving segment.

3. The method according to claim 1, characterized in that, Determining the driver's driving style based on the current driving conditions and the historical behavior data includes: The current driving conditions and the historical behavior data are input into a preset driving style classification model; The driver's driving style is obtained based on the output of the preset driving style classification model.

4. The method according to claim 3, characterized in that, Before inputting the current driving conditions and the historical behavior data into the preset driving style classification model, the method further includes: Construct a driving style feature dataset; Based on the preset working condition database, the driving style label corresponding to each driving style feature data under each working condition is obtained by clustering according to the driving style feature dataset. Based on the driving style label corresponding to each driving style feature data under each working condition, a preset neural network is trained to obtain the preset driving style classification model.

5. The method according to claim 4, characterized in that, The construction of the driving style feature dataset includes: Collect historical driving behavior data from multiple target users; Based on the historical driving data of the multiple target users, multi-dimensional driving style representation parameters are extracted, and a driving style feature dataset is constructed according to the multi-dimensional driving style representation parameters.

6. The method according to claim 1, characterized in that, Before adjusting the target vehicle's overall driving parameters according to the final required parameters, the process also includes: Identify whether the target vehicle meets the preset adjustment conditions; If the target vehicle does not meet the preset adjustment conditions, the current driving parameters of the target vehicle shall be maintained.

7. A driving mode control device for a vehicle, characterized in that, include: The acquisition module is used to determine the current vehicle data of the target vehicle and the driver's historical behavior data; The identification module is used to determine the current driving condition of the target vehicle based on the current vehicle data according to a preset working condition database, and to determine the driver's driving style based on the current driving condition and the historical behavior data. The adjustment module is used to determine the final requirement parameters based on the operating condition requirement parameters corresponding to the current driving condition and the style requirement parameters corresponding to the driving style, and to adjust the overall driving parameters of the target vehicle based on the final requirement parameters.

8. The apparatus according to claim 7, characterized in that, Before determining the current driving condition of the target vehicle based on the preset operating condition database and the current vehicle data, the identification module is further configured to: Obtain full vehicle data for the model corresponding to the target vehicle; The full vehicle data is cleaned to obtain cleaned vehicle data, and the cleaned vehicle data is segmented according to a preset time interval to obtain multiple vehicle driving segments. Extract the multi-dimensional feature parameters corresponding to each vehicle driving segment, and construct the preset working condition library based on the multiple vehicle driving segments and the multi-dimensional feature parameters corresponding to each vehicle driving segment.

9. A vehicle, characterized in that, include: A memory, a processor, and a computer program stored in the memory and executable on the processor, the processor executing the program to implement the driving mode control method for a vehicle as described in any one of claims 1-6.

10. A computer-readable storage medium storing a computer program, characterized in that, When the program is executed by the processor, it implements the driving mode control method for the vehicle as described in any one of claims 1-6.

Images