Vehicle driving mode control method, device, equipment and storage medium

Abstract

The application relates to the technical field of intelligent automobiles, in particular to a vehicle driving mode control method and device, equipment and a storage medium, aiming to solve the problem that in the prior art, driving mode switching is strongly dependent on single information, it is difficult to accurately determine the driver's concentration degree, the switching timing is not accurate and it is easy to interfere with driving. The scheme comprehensively collects the driver's visual performance, vehicle operation behavior and road environment related information, analyzes and fuses to form concentration information for representing the driving concentration degree, and selects a target driving mode suitable for the current state based on the concentration information, and controls the vehicle to complete mode switching. By using the scheme, the accuracy of driver concentration state recognition can be improved, the timeliness and adaptability of driving mode switching can be improved, the inappropriate interactive interference can be reduced, and the driving continuity, stability and driving safety can be improved.

Description

Technical Field

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

[0002] In the field of smart cockpits, existing vehicles typically use preset driving mode switching, driver status monitoring, and in-vehicle information push control to improve driving assistance and interactive experience.

[0003] However, existing solutions mostly rely on manual switching by the driver or state judgment based on single data, resulting in insufficient adaptability to switching timing under complex working conditions and easy interference with driving continuity. At the same time, information push, cabin environment and vehicle response lack control that is coordinated with the driver's level of focus, which limits recognition stability and actual experience.

[0004] Therefore, how to improve the accuracy of focus state recognition and mode switching adaptability during driving, while taking into account driving interference control and information synchronization, has become a technical problem that needs to be solved. Summary of the Invention

[0005] This application provides a method, apparatus, device, and storage medium for controlling vehicle driving modes to solve the aforementioned technical problems. This solution addresses the needs for attention state recognition and adaptive driving mode control during vehicle driving. It integrates driver state information and vehicle scene information to determine the driver's current level of focus and dynamically adjusts the vehicle driving mode based on this determination, thereby improving the matching between driving mode switching and the driver's actual state and road conditions.

[0006] In a first aspect, embodiments of this application provide a method for controlling a vehicle driving mode, including:

[0007] Acquire driver's visual data, driver's control behavior data, and road environment data of the vehicle;

[0008] Based on the visual data, the control behavior data, and the road environment data, focus information is determined; the focus information represents the driver's level of focus while driving the vehicle.

[0009] Based on the focus information, a target driving mode is determined, and the vehicle is controlled to switch to the target driving mode.

[0010] In one possible implementation, determining focus information based on the visual data, the manipulation behavior data, and the road environment data includes:

[0011] Based on the visual data, first evaluation information is determined; the first evaluation information represents the driver's level of focus.

[0012] Based on the aforementioned control behavior data, second evaluation information is determined; the second evaluation information characterizes the stability of vehicle control.

[0013] Based on the road environment data, a third evaluation information is determined; the third evaluation information characterizes the complexity of the vehicle driving environment.

[0014] The first evaluation information, the second evaluation information, and the third evaluation information are weighted and fused to obtain focus information.

[0015] In one possible implementation, the visual data includes driver gaze fixation information and saccade information. The gaze fixation information represents the duration for which the driver's gaze remains within a preset visual field area within a preset time period, and the saccade information represents the shifting of the driver's gaze between different visual fields of the vehicle within a preset time period.

[0016] Based on the visual data, the first evaluation information is determined, including:

[0017] The gaze lingering information and the scanning information are weighted and fused to obtain the first evaluation information.

[0018] In one possible implementation, the control behavior data includes information on the undulation of the vehicle steering wheel and the undulation of the vehicle pedals.

[0019] Based on the aforementioned manipulation behavior data, second evaluation information is determined, including:

[0020] The fluctuation information of the vehicle steering wheel and the fluctuation information of the vehicle pedal are weighted and fused to obtain the second evaluation information.

[0021] In one possible implementation, the road environment data includes road complexity information and traffic flow density information;

[0022] Based on the road environment data, the third evaluation information is determined, including:

[0023] The road complexity information and the traffic flow density information are weighted and fused to obtain the third evaluation information.

[0024] In one possible implementation, if the target driving mode is a preset focus mode, after controlling the vehicle to switch to the target driving mode, if it is detected that the driver actively triggers a preset operation behavior, then exit flag information is determined based on the first evaluation information, the second evaluation information, and the preset operation behavior; the exit flag information represents the possibility of exiting the preset focus mode.

[0025] If the exit indicator information meets the preset conditions, the vehicle is controlled to exit the target driving mode.

[0026] In one possible implementation, determining the target driving mode based on the attention information includes:

[0027] The focus information is compared with a preset threshold, and the target driving mode is determined based on the comparison result. The preset threshold is determined based on a preset update cycle, historical thresholds, actual thresholds, and predicted thresholds. The actual threshold is a threshold generated based on the driver's actual operation of the vehicle. The predicted threshold is a threshold generated based on the user's focus state.

[0028] In one possible implementation, controlling the vehicle to switch to the target driving mode includes:

[0029] Based on the focus information, the preset base value is adjusted to generate a target value; the target value represents the value that the control parameters of the vehicle functional domain need to be set in the target driving mode.

[0030] Based on a preset smooth transition algorithm, the values ​​of each control parameter are adjusted until the value of each control parameter equals the corresponding target value; the preset smooth transition algorithm is used to gradually change the value of each control parameter to the corresponding target value within a preset time period.

[0031] In one possible implementation, if the target driving mode is a preset focus mode, the vehicle is controlled to silently receive preset notification messages and adjust the vehicle cabin environment to a preset environmental state.

[0032] Secondly, embodiments of this application provide a vehicle driving mode control device, comprising:

[0033] The acquisition module is used to acquire: the driver's visual data, the driver's control behavior data, and the road environment data in which the vehicle is located;

[0034] The determination module is used to: determine focus information based on the visual data, the control behavior data, and the road environment data; the focus information represents the driver's level of focus while driving the vehicle;

[0035] The control module is used to: determine the target driving mode based on the attention information, and control the vehicle to switch to the target driving mode.

[0036] Thirdly, embodiments of this application provide a vehicle driving mode control device, including: a memory and a processor;

[0037] The memory stores computer-executed instructions;

[0038] The processor executes computer execution instructions stored in the memory, causing the processor to perform the first aspect and / or various possible implementations of the first aspect as described above.

[0039] Fourthly, embodiments of this application provide a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, are used to implement the first aspect and / or various possible implementations of the first aspect.

[0040] Fifthly, embodiments of this application provide a computer program product, including a computer program that, when executed by a processor, implements the first aspect and / or various possible implementations of the first aspect.

[0041] The vehicle driving mode control method, device, equipment, and storage medium provided in this application acquire the driver's visual data, control behavior data, and road environment data of the vehicle, and determine the focus information that characterizes the driver's level of focus while driving based on the above multi-dimensional information. This can more comprehensively reflect the driver's current driving state, improve the accuracy and stability of focus state recognition, and then determine the target driving mode based on the focus information and control the vehicle to switch to the target driving mode. This improves the adaptability of the timing and result of driving mode switching to the driver's state and road environment, and reduces interference with driving continuity. Attached Figure Description

[0042] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0043] Figure 1 Flowchart of the vehicle driving mode control method provided in this application Figure 1 ;

[0044] Figure 2 Flowchart of the vehicle driving mode control method provided in this application Figure 2 ;

[0045] Figure 3 A schematic diagram of the control device for the vehicle driving mode provided in this application;

[0046] Figure 4 A schematic diagram of the structure of the vehicle driving mode control device provided in this application.

[0047] The accompanying drawings illustrate specific embodiments of this application, which will be described in more detail below. These drawings and descriptions are not intended to limit the scope of the concept in any way, but rather to illustrate the concept of this application to those skilled in the art through reference to particular embodiments. Detailed Implementation

[0048] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this application.

[0049] In vehicle intelligent cockpit and driver assistance control technologies, driving mode management is typically used in conjunction with driver status monitoring, in-vehicle information interaction, and vehicle driving environment perception. Related solutions are mostly deployed within a vehicle system equipped with cameras, in-vehicle buses, environmental perception units, and cockpit control units to adjust vehicle response and human-machine interaction methods during driving.

[0050] In existing technologies, vehicles generally employ preset driving modes such as Comfort, Sport, or Eco, which are switched by the driver via physical buttons, touch interfaces, or voice commands. Some solutions also make simple judgments about the driving status based on single sensor information and trigger corresponding mode adjustments or information push controls. The basic idea is to switch power response, cabin prompts, or interaction strategies after detecting specific driving behaviors or specific operating conditions.

[0051] However, in complex conditions such as continuous curves, merging zones, or high-speed cruising, the above-mentioned solutions are relatively crude in their grasp of the timing of switching. Especially when relying on a single visual data or a single operational data, they are difficult to accurately reflect the driver's true level of concentration and are prone to misjudgment, omission, or delayed switching.

[0052] Meanwhile, the lack of coordination between driving mode switching, message reminders, and cockpit interaction often results in sudden prompts or inappropriate mode adjustments even when the driver is highly focused, affecting driving continuity and stability.

[0053] Furthermore, since changes in road conditions are not fully incorporated into the judgment criteria, existing solutions struggle to produce consistent and reliable control results under different road conditions. This not only reduces the adaptability of driving mode control but may also cause additional interference to drivers when they need to maintain focus, thereby affecting driving safety and user satisfaction.

[0054] Therefore, how to more accurately judge the driver's level of concentration during driving and accordingly switch driving modes has become an urgent technical problem to be solved.

[0055] To address the aforementioned issues, a method for controlling vehicle driving modes is provided. This method acquires the driver's visual data, the driver's operational behavior data, and the road environment data in which the vehicle is located. Based on the data, it determines focus information that characterizes the driver's level of concentration while driving the vehicle. Then, based on this focus information, it determines the target driving mode and controls the vehicle to switch to the target driving mode, thereby improving the adaptability of mode switching and taking into account the control of interference during the driving process.

[0056] The technical solution of this application and how the technical solution of this application solves the above-mentioned technical problems are described in detail below with specific embodiments. These specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments. The embodiments of this application will now be described with reference to the accompanying drawings.

[0057] Figure 1 Flowchart of the vehicle driving mode control method provided in this application Figure 1 ,like Figure 1 As shown, the method includes:

[0058] S101: Acquire driver's visual data, driver's control behavior data, and road environment data of the vehicle.

[0059] In this embodiment, visual data is used to characterize the driver's gaze-related state during driving, serving as the input basis for determining focus information. Control behavior data is used to characterize the driver's control over the vehicle. Road environment data is used to characterize the current driving environment of the vehicle.

[0060] For example, the vehicle controller can serve as the execution subject of this method, and the vehicle controller is communicatively connected to the driver monitoring system, the vehicle network, and the environmental perception system.

[0061] When acquiring visual data, control behavior data, and road environment data, the corresponding data can be obtained through the vehicle-mounted perception and control system, and synchronized and preprocessed as needed to form input data that can be directly used within the same analysis cycle.

[0062] Based on the above analysis, this step, by simultaneously acquiring the driver's line of sight, driving control status, and external road scene status, forms a joint description of the driver's current driving behavior and environmental status, providing input for subsequent attention level calculation.

[0063] S102: Based on visual data, control behavior data, and road environment data, determine attention information; attention information represents the driver's level of focus while driving the vehicle.

[0064] In this embodiment, focus information is used to characterize the driver's level of focus during the current time period and serves as the basis for subsequently determining the target driving mode.

[0065] Visual data, driving behavior data, and road environment data can be comprehensively analyzed to determine focus information, reflecting the match between the driver's current state and the environment.

[0066] For example, the vehicle controller can process visual data, control behavior data, and road environment data, and output attention information by combining preset judgment rules or models. The preset judgment rules or models are used to comprehensively analyze visual data, control behavior data, and road environment data to extract attention information that characterizes the driver's level of focus while driving the vehicle.

[0067] In some implementations, to improve the stability of the results, the focus information can be subjected to necessary stability processing. For example, the focus information can be standardized or normalized and mapped to a fixed numerical range. Alternatively, it can be output in the form of scores, grades, or other forms suitable for representing the degree of focus, as needed.

[0068] Based on the above analysis, this step converts multi-source data into unified attention information, so that the judgment of the driver's attention level does not depend on a single information source, thus making the attention recognition results in complex road scenarios more consistent with the actual driving state.

[0069] S103: Based on focus information, determine the target driving mode and control the vehicle to switch to the target driving mode.

[0070] In this embodiment, the target driving mode is used to represent the vehicle operating mode that matches the current focus information. In this step, the vehicle controller determines the target driving mode corresponding to the current analysis cycle based on the correspondence between the focus information and preset rules, and sends a mode switching command to the vehicle control system to switch the vehicle to the target driving mode.

[0071] For example, the vehicle controller can pre-store the correspondence between attention information and driving modes. Once the target driving mode is determined, the vehicle controller can determine whether the current driving mode is consistent with the target driving mode; if they are consistent, the current driving mode is maintained; if they are inconsistent, mode switching control is executed to adapt the vehicle's operating state to the driver's current level of attention.

[0072] After the switch is completed, the vehicle controller records the current mode status and enters the next data collection and evaluation cycle to achieve continuous updates.

[0073] As an example, the target driving mode can be any of the following: deep focus mode, normal driving mode, and distracted driving mode. In deep focus mode, the driver has a high level of concentration; in normal driving mode, the driver's concentration requirement is slightly lower than that of deep focus mode; and in distracted driving mode, the driver's concentration requirement is even lower.

[0074] Assuming focus information is represented by a score, for example, a value ranging from 0 to 1, with higher values ​​indicating higher driver focus. To make the mapping between focus information and driving modes more accurate, a time constraint rule is introduced based on focus information. For example, if the focus information is greater than or equal to 0.8, and the result is consistently greater than or equal to 0.8 for 5 minutes, the target mode is determined to be the deep focus mode. By imposing a 5-minute time limit, instantaneous high scores caused by factors such as brief driver lapses in concentration or glancing at road signs can be eliminated. If the focus information is less than 0.8 but greater than or equal to 0.5, or greater than or equal to 0.8 but lasting less than 5 minutes, the target mode is determined to be the normal driving mode. If the focus information is less than 0.5, the target mode is determined to be the distracted driving mode.

[0075] Based on the above analysis, this application provides a method for controlling a vehicle driving mode, including: acquiring the driver's visual data, the driver's operational behavior data, and the road environment data of the vehicle; determining attention information based on the visual data, operational behavior data, and road environment data; the attention information characterizing the driver's level of focus while driving the vehicle; determining a target driving mode based on the attention information, and controlling the vehicle to switch to the target driving mode. In this application, by jointly analyzing the driver's visual state, operational state, and road environment state, attention information reflecting the driver's current level of focus is generated, and then the determination and switching of the target driving mode are performed based on this attention information, so that the timing of mode switching corresponds to the driver's state and the road environment.

[0076] Figure 2 Flowchart of the vehicle driving mode control method provided in this application Figure 2 ,like Figure 2 As shown, the focus information determined above based on visual data, maneuver behavior data, and road environment data includes:

[0077] Based on visual data, a first evaluation information is determined; the first evaluation information represents the driver's focus. Based on control behavior data, a second evaluation information is determined; the second evaluation information represents the stability of vehicle control. Based on road environment data, a third evaluation information is determined; the third evaluation information represents the complexity of the vehicle's driving environment. The first, second, and third evaluation information are weighted and fused to obtain focus information.

[0078] Based on the focus information, the target driving mode is determined, including:

[0079] Attention information is compared with preset thresholds, and the target driving mode is determined based on the comparison results. The preset thresholds are determined based on historical thresholds, actual thresholds, and predicted thresholds, according to a preset update cycle. The actual thresholds are generated based on the driver's actual operation of the vehicle, and the predicted thresholds are generated based on the user's attention state.

[0080] The above-mentioned control of the vehicle to switch to the target driving mode includes:

[0081] Based on the focus information, the preset base values ​​are adjusted to generate target values; the target values ​​represent the values ​​that the control parameters of the vehicle's functional domains need to be set in the target driving mode.

[0082] Based on a preset smooth transition algorithm, the values ​​of each control parameter are adjusted until the values ​​of each control parameter are equal to the corresponding target values. The preset smooth transition algorithm is used to gradually change the values ​​of each control parameter to the corresponding target values ​​within a preset time period.

[0083] The above methods include:

[0084] S201. Acquire driver's visual data, driver's control behavior data, and road environment data of the vehicle.

[0085] For example, visual data includes driver gaze fixation information and scanning information. The gaze fixation information represents the duration for which the driver's gaze remains within a preset visual field within a preset time period, while the scanning information represents the shifting of the driver's gaze between different visual fields of the vehicle within a preset time period. The control behavior data includes information on the movement of the vehicle's steering wheel and the movement of the vehicle's pedals. The road environment data includes information on road complexity and traffic flow density.

[0086] For example, an enhanced infrared binocular camera can capture the driver's eye movements and head posture in real time, and calculate the coordinates of the gaze point in real time. The gaze point coordinates can be divided into areas such as the windshield, instrument panel, center console screen, side windows, and rearview mirror.

[0087] The preset time period is defined as a unit of time (e.g., one second), the preset field of vision is defined as the area of ​​the windshield in front, and the total proportion of time that the driver's gaze is focused on the area of ​​the windshield in front is defined as visual data.

[0088] For example, the proportion of time a driver's gaze is focused on the windshield area can be equal to the ratio of the number of frames focused on the windshield area to the total number of monitored frames per unit time. The higher the ratio, the more focused the driver is on observing the road conditions.

[0089] The system can also track sudden changes in the driver's gaze (displacement speed and acceleration) using an enhanced infrared binocular camera. When the gaze jumps instantly from one area to another, it is counted as a scan. Using a 5-minute preset time period, the number of times the driver's gaze jumps between different areas within 5 minutes is counted, and the counted number is used as scan information.

[0090] Steering wheel fluctuation information can be defined as the quantified value of the steering wheel fluctuation corresponding to small-amplitude high-frequency corrections and minute vibrations after deducting effective large-angle low-frequency steering actions such as turning and lane changing, based on the actual steering wheel angle collected by the vehicle's CAN bus within a unit sampling time. This indicator only reflects the degree of vibration caused by the driver's unconscious and frequent small-amplitude corrections to the steering wheel, and does not include angle changes caused by normal steering operations.

[0091] The raw steering wheel angle signal can be read in real time via the CAN bus. A digital filtering algorithm is used to separate the low-frequency effective steering component from the high-frequency micro-jitter component. The root mean square of the high-frequency jitter signal is taken as the calculation result of the steering wheel fluctuation amplitude. This is then used as the steering wheel fluctuation information.

[0092] The steering wheel fluctuation information can be compared with the benchmark threshold (such as 5 degrees per second) to judge the smoothness of the driver's operation.

[0093] When the steering wheel fluctuation value is less than 5, it means that there is little vibration when the steering wheel is slightly corrected and the operation is smooth. When the fluctuation value is greater than or equal to 5, it means that the driver frequently shakes and corrects the steering wheel, resulting in poor driving stability.

[0094] The fluctuation information of the vehicle pedals is used to characterize the instantaneous change in the opening of the accelerator pedal and brake pedal per unit time. It only judges the smoothness of the foot's subtle control, does not distinguish between large and stable pedaling actions such as normal acceleration and deceleration, and focuses on reflecting the operating vibration caused by frequent small pedaling and releasing.

[0095] The output signal of the pedal position sensor can be acquired via the CAN bus. The differential operation is performed on the continuously sampled pedal opening value to obtain the opening change rate. The average value of the absolute value of the change rate at each sampling point is taken as the final calculated value of the vehicle pedal fluctuation amplitude, and this value is used as the vehicle pedal fluctuation information.

[0096] The fluctuation information of the vehicle pedal can be compared with the benchmark threshold (such as 20% opening per second). For example, when the pedal fluctuation amplitude is less than 20, it means that the foot control is delicate and stable; when the pedal fluctuation amplitude is greater than or equal to 20, it indicates that there is frequent hard pressing and sudden release of the pedal, and the driving control stability is poor.

[0097] Road complexity information is used to characterize the objective requirements that road geometry, road surface undulation, and road topology place on the driver's control precision and attention allocation. The value range is 0 to 1. The larger the value, the more complex the road driving conditions are, and the higher the requirements for the driver's observation, steering, and speed change.

[0098] For example, two types of data sources can be combined to comprehensively determine road complexity: one is navigation map data, which can predict road conditions 1 kilometer in advance; the other is vehicle-mounted forward-facing cameras, which collect real-time road scene information to complete condition verification and confirmation, and combine multi-dimensional road physical parameters to calculate a standardized complexity value in the range of 0 to 1, which is then used as road complexity information.

[0099] Specifically, for straight roads, the radius of curvature approaches infinity, and the road complexity approaches 0; for curves, the smaller the radius of curvature, the sharper the curve, and when the radius of curvature is less than 100 meters, the road complexity approaches 1; steep inclines and declines compress the driver's field of vision and increase blind spots, and the greater the slope undulation, the higher the road complexity increases; ramps, highway entrances and exits, lane forks, and areas where multiple vehicles converge require drivers to continuously observe the rearview mirror and pay attention to blind spots, and these road sections are directly classified as high-complexity conditions, with a complexity value close to 1.

[0100] Traffic flow density information refers to the density of dynamic targets such as vehicles on the road within a fixed detection range ahead of the vehicle (e.g., a detection distance of 100 meters forward). Vehicle-mounted millimeter-wave radar can be used as the primary sensing device, simultaneously paired with a forward-facing camera to complete target identification and verification, and to count the total number of moving vehicles within a 100-meter forward detection range; the unit of measurement is vehicles / 100 meters, representing the number of vehicles present in every 100-meter road section.

[0101] S202. Based on visual data, determine the first evaluation information; the first evaluation information represents the driver's level of focus.

[0102] For example, the gaze lingering information and the scanning information can be weighted and fused to obtain the first evaluation information.

[0103] For example, the first evaluation information can be calculated according to the following formula (1):

[0104] (1);

[0105] In the formula, This indicates the first evaluation information; Indicates where the gaze lingers; The expression represents saccade information; min represents the minimum value function; 0.8 and 0.6 are the weights of gaze persistence information and saccade information, respectively. In specific implementations, these weights can be dynamically adjusted according to actual needs, and this embodiment does not impose any limitations on this. The higher the gaze persistence information and the lower the saccade information, the higher the first evaluation information.

[0106] In this step, by incorporating both sustained attention features and gaze shift features into the first evaluation information, the first evaluation information can simultaneously reflect the driver's gaze stability on the current road and their switching behavior towards key information inside and outside the vehicle. This makes the subsequent construction of attention information more closely resemble real driving conditions. Based on this first evaluation information, subsequent attention information fusion calculations can be performed more accurately, providing a reliable basis for driving mode switching. Using this method, the visual data representation is more complete, reducing bias caused by relying solely on a single gaze feature and improving the accuracy of characterizing the driver's gaze focus.

[0107] S203. Based on the handling behavior data, determine the second evaluation information; the second evaluation information characterizes the stability of vehicle handling.

[0108] For example, the fluctuation information of the vehicle's steering wheel and the fluctuation information of the vehicle's pedals can be weighted and fused to obtain the second evaluation information.

[0109] For example, the second evaluation information can be calculated according to the following formula (2):

[0110] (2);

[0111] In the formula, This indicates the second evaluation information; This indicates information about the movement of the vehicle's steering wheel; This represents the fluctuation information of the vehicle pedals; 0.6 and 0.4 are the respective weights of the fluctuation information of the vehicle steering wheel and the fluctuation information of the vehicle pedals. In specific implementations, these weights can be dynamically adjusted according to actual needs, and this embodiment does not impose any limitations on this. The smoother the vehicle handling, the higher the second evaluation information.

[0112] After acquiring the two types of control features, steering wheel and pedal, this method forms a second evaluation information through weighted fusion, which enables the fluctuation effect of a single control action to be comprehensively expressed, and makes the evaluation results simultaneously reflect the synergy of steering and acceleration / deceleration operations, thus making the second evaluation information a more complete reflection of the vehicle's handling stability.

[0113] This second evaluation information no longer relies on a single control quantity, and can more accurately characterize the driver's overall stability in steering and pedal control, providing a more reliable input for determining subsequent focus information and improving the accuracy of driving status judgment based on control behavior data.

[0114] S204. Based on road environment data, determine the third evaluation information; the third evaluation information characterizes the complexity of the vehicle driving environment.

[0115] For example, road complexity information and traffic flow density information can be weighted and fused to obtain third evaluation information.

[0116] For example, the third evaluation information can be calculated according to the following formula (3):

[0117] (3);

[0118] In the formula, This indicates the third evaluation information; Indicates road complexity information; This represents traffic flow density information; 0.7 and 0.3 are the weights corresponding to road complexity information and traffic flow density information, respectively. In specific implementation, these weights can be dynamically adjusted according to actual needs, and this embodiment does not impose any limitations on this. The more complex the road and the more moderate the traffic flow, the higher the third evaluation information.

[0119] This third evaluation information is used to characterize the comprehensive impact of the road environment on driver focus during vehicle driving mode control. It is also input into subsequent judgment modules in conjunction with other evaluation information to form a unified evaluation result of the current driving environment. By weightedly fusing road complexity information with traffic flow density information, road environment evaluation can move beyond relying on a single feature, thereby improving the completeness and consistency of environmental representation.

[0120] By adopting the above method, the third evaluation information can more accurately reflect the overall complexity of the current road environment of the vehicle, making the determination of subsequent focus information closer to the actual driving load, thereby improving the matching degree of driving mode switching and reducing control inconsistency caused by road environment judgment deviation.

[0121] S205. The first evaluation information, the second evaluation information, and the third evaluation information are weighted and fused to obtain the focus information.

[0122] For example, the first evaluation information, the second evaluation information, and the third evaluation information can be weighted and fused according to the following formula (4) to obtain the focus information:

[0123] (4);

[0124] In the formula, This indicates a focus on information; , , These are the weights corresponding to the first evaluation information, the second evaluation information, and the third evaluation information, respectively. , , The sum of these values ​​equals 1. However, in practice, this can be dynamically adjusted based on actual needs; this embodiment does not impose any limitations on this. In one specific implementation, The value is 0.35. The value is 0.4. The value is 0.25. The higher the focus information, the higher the driver's level of focus.

[0125] The above processing allows eye focus, handling stability, and environmental complexity to work together to construct focus information. Focus information is less dependent on a single sensor, can more completely reflect the driver's focus in the current road scenario, and provides a consistent basis for subsequent driving mode switching.

[0126] S206. Compare the focus information with a preset threshold, and determine the target driving mode based on the comparison result.

[0127] In this embodiment, the preset threshold is determined based on a preset update cycle, according to historical thresholds, actual thresholds, and predicted thresholds; the actual threshold is generated based on the driver's actual operation of the vehicle; and the predicted threshold is generated based on the user's concentration state.

[0128] The comparison process between focus information and preset thresholds is as follows: if the focus information is greater than or equal to 0.8, and the result is greater than or equal to 0.8 every time within 5 minutes, the target mode is determined to be deep focus mode; if the focus information is less than 0.8, but greater than or equal to 0.5, or if the focus information is greater than or equal to 0.8 but the duration is less than 5 minutes, the target mode is determined to be normal driving mode; if the focus information is less than 0.5, the target mode is determined to be distracted driving mode.

[0129] At this point, the preset thresholds include 0.8 and 0.5, which are the initial thresholds. In specific implementation, the preset thresholds can be determined by fusing the historical thresholds retained by the threshold fusion unit based on the previous update cycle (such as every 7 days), the actual thresholds obtained by the control and acquisition unit, and the predicted thresholds calculated by the focus evaluation unit. The fusion method can be weighted summation, moving average, or weighted correction.

[0130] The actual threshold is a threshold generated based on the driver's actual operation of the vehicle. For example, it may be a threshold set based on the driver's behavior over the past 7 days. For instance, if the driver manually exits the deep focus mode after it is automatically switched to deep focus mode, it means that the current threshold is too low and needs to be increased. If the driver frequently exits deep focus mode, the current threshold will be increased by a larger value as the actual threshold. If the driver exits deep focus mode less often, the current threshold will be increased by a smaller value as the actual threshold.

[0131] The prediction threshold is a threshold generated based on the driver's attention level; for example, the prediction threshold is based on the current... and historical calculations The threshold is set based on the driver's level of concentration.

[0132] For example, for any preset threshold, the threshold in the current update cycle can be calculated according to the following formula (5):

[0133] (5);

[0134] In the formula, This represents the updated threshold. This indicates the historical threshold retained from the previous update cycle; Indicates the actual threshold; Indicates the prediction threshold; The learning rate is used to ensure smoother threshold updates and avoid abrupt changes. In one specific implementation... The value is 0.03.

[0135] In this approach, the threshold update is synchronously linked to the driver's actual operation and focus state. The mode determination does not rely on a fixed constant, but is dynamically corrected with the update cycle, so that the determination result of the target driving mode is consistent with the current driving state, and the stability and adaptability of mode switching are improved.

[0136] S207. Based on the focus information, adjust the preset base value to generate the target value.

[0137] In this embodiment, the preset baseline value is the reference value of the control parameters of the vehicle functional domain when the vehicle is driving in normal driving mode. The target value represents the value that the control parameters of the vehicle functional domain need to be set in the target driving mode. Among them, the control parameters of the vehicle functional domain include, for example, throttle response linearity, transmission shift delay time, and suspension stiffness coefficient.

[0138] For example, after determining the target driving mode, the control system first reads the set of basic values ​​corresponding to the mode, maps the focus information into correction coefficients or offsets, and then calculates the basic values ​​accordingly to form the target values ​​of each control parameter.

[0139] In practice, after determining the target driving mode, the control system first reads the set of basic values ​​corresponding to the mode, maps the focus information into correction coefficients or offsets, and then calculates the basic values ​​to form the target values ​​of each control parameter.

[0140] For example, assuming the target driving mode is the deep focus mode, the target value of throttle response linearity can be calculated according to the following formula (6):

[0141] (6);

[0142] In the formula, This represents the target value for throttle response linearity; The basic value representing the linearity of throttle response; The adjustment coefficient representing the linearity of the throttle response can be set according to actual conditions. The value of is greater than or equal to 0.7 and less than or equal to 1. The higher the focus, the higher the linearity of the throttle response.

[0143] The target value of the gearbox shift delay time can be calculated using the following formula (7):

[0144] (7);

[0145] In the formula, This represents the target value for the gearbox shift delay time; The base value representing the gearbox shift delay time; This represents the adjustment coefficient for the gearbox shift delay time, which can be set according to actual conditions. The value is greater than or equal to 200 milliseconds and less than or equal to 500 milliseconds. The higher the focus, the lower the gearbox shift delay.

[0146] The target value of the suspension stiffness coefficient can be calculated according to the following formula (8):

[0147] (8);

[0148] In the formula, This indicates the target value of the suspension stiffness coefficient; This represents the basic value of the suspension stiffness coefficient; This represents the adjustment coefficient for the suspension stiffness, which can be set according to actual conditions. The value is greater than or equal to 0.8 and less than or equal to 1.15. The higher the focus, the higher the suspension stiffness coefficient.

[0149] In one specific implementation method The value is 0.2. The value is 200. The value is 0.15.

[0150] S208. Based on a preset smooth transition algorithm, adjust the values ​​of each control parameter until the value of each control parameter is equal to the corresponding target value.

[0151] In this embodiment, a preset smooth transition algorithm is used to gradually change the values ​​of each control parameter to the corresponding target values ​​within a preset time period.

[0152] For example, the control system continuously updates the parameters according to a preset smooth transition algorithm. The parameter update amount decreases over time or converges according to a preset curve, so that each control parameter smoothly transitions from its current value to its target value within a preset time period. This preset time period can be pre-set according to the target driving mode type and the current driving scenario.

[0153] For example, the value of any control parameter can be adjusted according to the following formula (9) until the value of the control parameter gradually changes to the corresponding target value:

[0154] (9);

[0155] In the formula, This indicates the value of the control parameter at time t; This indicates the value of the control parameter before adjustment; This represents the target value corresponding to the control parameter; e represents the natural constant. Represents the transition time constant. The value is greater than or equal to 10 seconds, thus ensuring a smooth transition of the control parameters so that the user does not perceive anything.

[0156] This method first transforms the focus information into target values, and then uses a smooth transition algorithm to drive the control parameters to gradually converge to the target values, thus maintaining the continuity of the mode switching process. Because the control parameters do not change instantaneously, but gradually over a preset time period, the state changes of the vehicle's functional domains when switching to the target driving mode are more consistent.

[0157] By adopting this implementation method, the vehicle can maintain a gradual transition of control parameters during mode switching, reduce the abruptness of vehicle functional domain output, and keep the parameter settings in the target driving mode consistent with the current driving state, thereby improving the smoothness of the switching process and control adaptability.

[0158] In some specific implementations, when the target driving mode is a preset focus mode, that is, a deep focus mode, after the vehicle is switched to the target driving mode, the vehicle silently receives preset notification messages and adjusts the vehicle cabin environment to a preset environmental state.

[0159] For example, after the vehicle switches to the preset focus mode, that is, when the vehicle is controlled to switch to the deep focus mode, the cockpit control unit receives message events from the vehicle communication module and the human-machine interaction module, and processes the preset notification messages by receiving them in the background, delaying the prompts, or not displaying them immediately, so that when the messages arrive, they do not form sudden pop-ups, voice broadcasts, or obvious sound and light prompts in the foreground.

[0160] At the same time, the cabin control unit generates control commands based on preset environmental conditions and sends linkage control signals to the air conditioning system, ambient lighting system, audio system and seat adjustment unit to coordinate and adjust the in-vehicle temperature, air volume, air direction, lighting brightness, warning sound intensity and seat support posture.

[0161] The preset environmental state can be set to a combination of states that reduce interfering environmental factors, such as reducing the cabin alert volume, reducing the ambient lighting brightness, and maintaining a constant air conditioning venting state to create a stable and focused driving environment; in practical applications, other models of this component can also be selected, and this application does not limit them.

[0162] In this way, when the vehicle is in focus mode, notification messages are processed silently without directly interfering with the driver's attention, and the vehicle cabin environment is switched to a preset state in sync, so that the information receiving method and the environmental control method are consistent. This allows the vehicle to maintain a more stable cabin interaction and control state in focus driving scenarios, thereby improving the overall adaptability and driving continuity after mode switching.

[0163] In some specific implementations, if the target driving mode is a preset focus mode, after the vehicle is switched to the target driving mode, if the driver is detected to have actively triggered a preset operation, the exit indicator information is determined based on the first evaluation information, the second evaluation information, and the preset operation. The exit indicator information represents the possibility of exiting the preset focus mode. If the exit indicator information meets the preset conditions, the vehicle is controlled to exit the target driving mode.

[0164] For example, the aforementioned preset focus mode is a deep focus mode. After the vehicle switches to the preset driving mode, that is, after the vehicle switches to the deep focus mode, it continuously monitors the active operation signals in the cabin. When it is detected that the driver has actively triggered the seat, door, window, air conditioner, in-vehicle equipment or other in-vehicle components, the behavior is converted into a preset operation behavior and written into the risk judgment module.

[0165] The risk assessment module combines the first evaluation information, the second evaluation information, and the preset operation behavior to perform a comprehensive calculation, and outputs the comprehensive calculation result as an exit identifier.

[0166] The comprehensive calculation can be achieved by weighted fusion, rule-based judgment, or a combination of both. The weights and thresholds are preset by the vehicle control strategy. In practical applications, this module can also be selected from other models, which is not limited in this application.

[0167] For example, when a driver is detected to have actively triggered actions on the seat, doors, windows, air conditioning, in-vehicle equipment, or other in-vehicle components, such as actively adjusting the seat, changing music, or setting navigation, the operation flag for any of these actions is set to 1; otherwise, the operation flag is set to 0. Then, the first evaluation information, the second evaluation information, and the operation flag are weighted and fused according to the following formula (10) to obtain the exit flag information:

[0168] (10);

[0169] In the formula, This indicates the exit indicator information. The higher the exit indicator information, the greater the likelihood of exiting the current driving mode. Indicates the operation identifier; , , The weights corresponding to the first evaluation information, the second evaluation information, and the operation identifier are respectively, among which, , , The sum of these values ​​equals 1. In one specific implementation, The value of is equal to 0.3. The value of is equal to 0.3. The value of is 0.4.

[0170] The exit sign information can be compared with a preset threshold to determine whether the exit sign information meets the preset conditions. When the preset conditions are met, the vehicle is controlled to exit the target driving mode.

[0171] For example, when the exit indicator value is less than 0.3, it means that the possibility of exiting the deep focus mode is low, and the current driving mode can be maintained and driving can continue; when the exit indicator value is greater than or equal to 0.3 and less than 0.6, it means that the possibility of exiting the deep focus mode is moderate, and the monitoring of the vehicle status can be strengthened to maintain the current driving mode and continue driving; when the exit indicator value is greater than or equal to 0.6, it means that the possibility of exiting the deep focus mode is high. At this time, the exit indicator value meets the preset conditions, and the vehicle is controlled to exit the deep focus mode.

[0172] In one specific implementation, time can also be used to determine whether to exit the deep focus mode. For example, if the exit indicator value is detected to be greater than or equal to 0.6, and the exit indicator value is calculated to be greater than or equal to 0.6 in each of the multiple monitoring processes within 1 minute, then it is determined that the exit indicator value meets the preset conditions, and the vehicle is controlled to exit the target driving mode.

[0173] When the exit indicator information meets preset conditions, the vehicle control unit sends an exit command to the mode management module, switching the vehicle from deep focus mode to another driving mode. Simultaneously, the corresponding human-machine interaction and message prompt strategies are restored. At the same time, silently received notification messages are delayed by 30 seconds and are instead announced to the driver in a gentle voice. By linking driver actions with vehicle control status and road environment status, the system can complete mode exit when it detects a driver's tendency to exit focus mode and the current environment is suitable for switching, thus ensuring consistency between control results and driving status.

[0174] By adopting the above method, the determination of exiting the focus mode no longer relies solely on a single operation signal, but rather on a combined judgment based on vehicle handling stability and environmental complexity. This ensures that mode exit matches the driver's true intentions and current driving conditions, thereby improving the accuracy and consistency of mode switching and reducing the occurrence of situations where it is not appropriate to continue maintaining the focus mode.

[0175] Figure 3 This is a schematic diagram of the structure of the vehicle driving mode control device provided in this application, as shown below. Figure 3 As shown, the vehicle driving mode control device 30 provided in this embodiment includes:

[0176] The acquisition module 301 is used to: acquire the driver's visual data, the driver's control behavior data, and the road environment data in which the vehicle is located;

[0177] The determination module 302 is used to: determine attention information based on visual data, control behavior data, and road environment data; the attention information represents the driver's level of focus while driving the vehicle;

[0178] The control module 303 is used to: determine the target driving mode based on attention information and control the vehicle to switch to the target driving mode.

[0179] In one possible implementation, the determining module 302 is further configured to:

[0180] Based on visual data, the first evaluation information is determined; the first evaluation information represents the driver's level of focus.

[0181] Based on the handling behavior data, a second evaluation information is determined; the second evaluation information characterizes the stability of vehicle handling.

[0182] Based on road environment data, a third evaluation information is determined; the third evaluation information characterizes the complexity of the vehicle driving environment.

[0183] The first, second, and third evaluation information are weighted and fused to obtain focused information.

[0184] In one possible implementation, the visual data includes the driver's gaze fixation information and saccade information. The gaze fixation information represents the duration for which the driver's gaze remains within a preset visual field within a preset time period, and the saccade information represents the movement of the driver's gaze between different visual fields of the vehicle within a preset time period. The determining module 302 is further configured to:

[0185] The gaze lingering information and the scanning information are weighted and fused to obtain the first evaluation information.

[0186] In one possible implementation, the control behavior data includes steering wheel undulation information and vehicle pedal undulation information; the determination module 302 is further configured to:

[0187] The fluctuation information of the vehicle steering wheel and the fluctuation information of the vehicle pedal are weighted and fused to obtain the second evaluation information.

[0188] In one possible implementation, the road environment data includes road complexity information and traffic flow density information; the determination module 302 is further used for:

[0189] The road complexity information and traffic flow density information are weighted and fused to obtain the third evaluation information.

[0190] In one possible implementation, the control module 303 is further used for:

[0191] If the target driving mode is the preset focus mode, after the vehicle is switched to the target driving mode, if the driver actively triggers the preset operation behavior, the exit sign information is determined based on the first evaluation information, the second evaluation information, and the preset operation behavior; the exit sign information indicates the possibility of exiting the preset focus mode.

[0192] If the exit sign information meets the preset conditions, the vehicle will exit the target driving mode.

[0193] In one possible implementation, the control module 303 is further used for:

[0194] Attention information is compared with preset thresholds, and the target driving mode is determined based on the comparison results. The preset thresholds are determined based on historical thresholds, actual thresholds, and predicted thresholds, according to a preset update cycle. The actual thresholds are generated based on the driver's actual operation of the vehicle, and the predicted thresholds are generated based on the user's attention state.

[0195] In one possible implementation, the control module 303 is further used for:

[0196] Based on the focus information, the preset base values ​​are adjusted to generate target values; the target values ​​represent the values ​​that the control parameters of the vehicle's functional domains need to be set in the target driving mode.

[0197] Based on a preset smooth transition algorithm, the values ​​of each control parameter are adjusted until the values ​​of each control parameter are equal to the corresponding target values. The preset smooth transition algorithm is used to gradually change the values ​​of each control parameter to the corresponding target values ​​within a preset time period.

[0198] In one possible implementation, the control module 303 is further used for:

[0199] If the target driving mode is the preset focus mode, the vehicle will be controlled to silently receive preset notification messages and adjust the vehicle cabin environment to the preset environmental state.

[0200] The vehicle driving mode control device provided in this embodiment can execute the method provided in the above method embodiment. Its implementation principle and technical effect are similar, and will not be described in detail here.

[0201] Figure 4 This is a schematic diagram of the control device for the vehicle driving mode provided in this application. Figure 4As shown, the vehicle driving mode control device 40 provided in this embodiment includes at least one processor 401 and a memory 402. Optionally, the vehicle driving mode control device 40 further includes a communication component 403. The processor 401, memory 402, and communication component 403 are connected via a bus.

[0202] In the specific implementation process, at least one processor 401 executes computer execution instructions stored in memory 402, causing at least one processor 401 to execute the above-described vehicle driving mode control method.

[0203] The specific implementation process of processor 401 can be found in the above method embodiments, and its implementation principle and technical effect are similar. It will not be repeated here.

[0204] In the above embodiments, it should be understood that the processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), etc. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the method disclosed in this invention can be directly implemented by a hardware processor, or implemented by a combination of hardware and software modules within the processor.

[0205] The memory may include random access memory (RAM) and may also include non-volatile memory (NVM), such as at least one disk storage device.

[0206] 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 illustration, the buses shown in the accompanying drawings are not limited to a single bus or a single type of bus.

[0207] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the above-described vehicle driving mode control method.

[0208] This application also provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the above-described vehicle driving mode control method.

[0209] The aforementioned readable storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk. The readable storage medium can be any available medium accessible to a general-purpose or special-purpose computer.

[0210] An exemplary readable storage medium is coupled to a processor, enabling the processor to read information from and write information to the readable storage medium. Of course, the readable storage medium can also be a component of the processor. The processor and the readable storage medium can reside in an Application Specific Integrated Circuit (ASIC). Alternatively, the processor and the readable storage medium can exist as discrete components in the device.

[0211] The division of units is merely a logical functional division; in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be indirect coupling or communication connection through some interfaces, devices, or units, and may be electrical, mechanical, or other forms.

[0212] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0213] In addition, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0214] If a function is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0215] Those skilled in the art will understand that all or part of the steps of the above-described method embodiments can be implemented by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When executed, the program performs the steps of the above-described method embodiments; and the aforementioned storage medium includes various media capable of storing program code, such as ROM, RAM, magnetic disks, or optical disks.

[0216] Finally, it should be noted that other embodiments of the invention will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This invention is intended to cover any variations, uses, or adaptations of the invention that follow the general principles of the invention and include common knowledge or customary techniques in the art not disclosed herein, and is not limited to the precise structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope.

Claims

1. A method for controlling a vehicle driving mode, characterized in that, include: Acquire driver's visual data, driver's control behavior data, and road environment data of the vehicle; Based on the visual data, the control behavior data, and the road environment data, focus information is determined; the focus information represents the driver's level of focus while driving the vehicle. Based on the focus information, a target driving mode is determined, and the vehicle is controlled to switch to the target driving mode.

2. The method according to claim 1, characterized in that, Based on the visual data, the manipulation behavior data, and the road environment data, focus information is determined, including: Based on the visual data, first evaluation information is determined; the first evaluation information represents the driver's level of focus. Based on the aforementioned control behavior data, second evaluation information is determined; the second evaluation information characterizes the stability of vehicle control. Based on the road environment data, a third evaluation information is determined; the third evaluation information characterizes the complexity of the vehicle driving environment. The first evaluation information, the second evaluation information, and the third evaluation information are weighted and fused to obtain focus information.

3. The method according to claim 2, characterized in that, The visual data includes the driver's gaze fixation information and scanning information. The gaze fixation information represents the duration for which the driver's gaze remains within a preset visual field area within a preset time period. The scanning information represents the shifting of the driver's gaze between different visual fields of the vehicle within a preset time period. Based on the visual data, the first evaluation information is determined, including: The gaze lingering information and the scanning information are weighted and fused to obtain the first evaluation information.

4. The method according to claim 2, characterized in that, The control behavior data includes information on the fluctuations of the vehicle's steering wheel and the vehicle's pedals. Based on the aforementioned manipulation behavior data, second evaluation information is determined, including: The fluctuation information of the vehicle steering wheel and the fluctuation information of the vehicle pedal are weighted and fused to obtain the second evaluation information.

5. The method according to claim 2, characterized in that, The road environment data includes road complexity information and traffic flow density information; Based on the road environment data, the third evaluation information is determined, including: The road complexity information and the traffic flow density information are weighted and fused to obtain the third evaluation information.

6. The method according to claim 2, characterized in that, If the target driving mode is a preset focus mode, after controlling the vehicle to switch to the target driving mode, if it is detected that the driver actively triggers a preset operation behavior, then exit flag information is determined based on the first evaluation information, the second evaluation information, and the preset operation behavior. The exit identifier information indicates the likelihood of exiting the preset focus mode; If the exit indicator information meets the preset conditions, the vehicle is controlled to exit the target driving mode.

7. The method according to claim 1, characterized in that, Based on the attention information, the target driving mode is determined, including: The focus information is compared with a preset threshold, and the target driving mode is determined based on the comparison result. The preset threshold is determined based on a preset update cycle, historical thresholds, actual thresholds, and predicted thresholds. The actual threshold is a threshold generated based on the driver's actual operation of the vehicle. The predicted threshold is a threshold generated based on the user's focus state.

8. The method according to claim 1, characterized in that, Controlling the vehicle to switch to the target driving mode includes: Based on the focus information, the preset base value is adjusted to generate a target value; the target value represents the value that the control parameters of the vehicle functional domain need to be set in the target driving mode. Based on a preset smooth transition algorithm, the values ​​of each control parameter are adjusted until the value of each control parameter equals the corresponding target value; the preset smooth transition algorithm is used to gradually change the value of each control parameter to the corresponding target value within a preset time period.

9. The method according to any one of claims 1-8, characterized in that, If the target driving mode is the preset focus mode, the vehicle will be controlled to silently receive preset notification messages and adjust the vehicle cabin environment to the preset environmental state.

10. A control device for a vehicle driving mode, characterized in that, include: The acquisition module is used to acquire: the driver's visual data, the driver's control behavior data, and the road environment data in which the vehicle is located; The determination module is used to: determine focus information based on the visual data, the control behavior data, and the road environment data; the focus information represents the driver's level of focus while driving the vehicle; The control module is used to: determine the target driving mode based on the attention information, and control the vehicle to switch to the target driving mode.

11. A control device for a vehicle driving mode, characterized in that, include: Memory, processor; The memory stores computer-executed instructions; The processor executes computer execution instructions stored in the memory, causing the processor to perform the method as described in any one of claims 1-9.

12. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions, which, when executed by a processor, are used to implement the method as described in any one of claims 1-9.

13. A computer program product, characterized in that, Includes a computer program that, when executed by a processor, implements the method of any one of claims 1-9.

Images