In-vehicle screen rotation control methods, electronic devices and vehicles

Abstract

This application provides a method for controlling the rotation of an in-vehicle screen, an electronic device, and a vehicle, relating to the field of smart cockpit technology. The method involves acquiring vehicle-related data, determining the driving safety level and current driving scenario based on the vehicle-related data, the current driving scenario, and the driving safety level, determining a target angle, and determining a target rotation speed based on the driving safety level and the target angle. This ensures that the determined target angle is related not only to the current driving scenario but also to the vehicle-related data and the driving safety level, making the process of determining the target angle more intelligent and more in line with the actual situation of the vehicle. This allows the in-vehicle screen to ultimately rotate to the target angle that best suits the actual situation, improving the intelligence of screen rotation and making the screen rotation more in line with the user's actual needs.

Description

Technical Field

[0001] This application relates to the field of smart cockpit technology, and more particularly to an in-vehicle screen rotation control method, electronic equipment, and vehicle. Background Technology

[0002] With the development of automotive intelligence, the smart cockpit has become the core interaction center of the vehicle. As the primary interface for user interaction with the vehicle, the display method and interactive experience of the in-vehicle screen directly impact the user experience. To improve the user experience, rotating screen technology is increasingly being applied to high-end models, enabling the in-vehicle screen to adjust its angle according to usage scenarios to adapt to the viewing and operation needs of different users. However, the current level of intelligence in in-vehicle screen rotation is low and cannot meet user needs. Summary of the Invention

[0003] In view of this, the purpose of this application is to provide an in-vehicle screen rotation control method, electronic device and vehicle to solve or partially solve the problems raised in the prior art.

[0004] To achieve the above objectives, the first aspect of this application provides a method for controlling the rotation of an in-vehicle screen, comprising:

[0005] Acquire vehicle-related data and determine the driving safety level and current driving scenario based on the vehicle-related data; The target angle is determined based on the vehicle-related data, the current driving scenario, and the driving safety level. Based on the driving safety level and the target angle, determine the target rotation speed; Control the vehicle screen to rotate to the target angle at the target rotation speed.

[0006] In some embodiments, determining the driving safety level based on vehicle-related data includes: Based on the vehicle-related data, a driving risk index, a driver status index, a traffic environment index, and a vehicle status index are determined. The driving safety index is determined based on the driving risk index, driver status index, traffic environment index, and vehicle status index. The driving safety level is determined based on the driving safety index.

[0007] In some embodiments, the driving safety level includes a no-rotation level or a rotation-permitted level; Determining the target angle based on the vehicle-related data, the current driving scenario, and the driving safety level includes: In response to the driving safety level being a no-rotation level, the preset default angle is determined as the target angle; In response to the driving safety level being a permissible rotation level, a current scene reference angle is determined based on the current driving scenario; a current correction angle is determined based on the current scene reference angle, the vehicle-related data, and the driving safety level; and a target angle is determined based on the current scene reference angle and the current correction angle.

[0008] In some embodiments, the vehicle-related data includes driver identity information, light intensity, noise information, current ambient temperature, and current screen angle; The process of determining the current correction angle based on the current scene reference angle, the vehicle-related data, and the driving safety level includes: Determine the safety correction angle based on the aforementioned driving safety level; Based on the driver's identity information and preset driver preference information, the driver's correction angle is determined; Based on the light intensity, noise information, and current ambient temperature, determine the environmental correction angle; Based on the current scene reference angle, safety correction angle, driver correction angle, environment correction angle, and current screen angle, determine the smooth correction angle; The sum of the safety correction angle, driver correction angle, environmental correction angle, and smoothness correction angle is determined as the current correction angle.

[0009] In some embodiments, the vehicle-related data includes the current screen angle; Determining the target rotation speed based on the driving safety level and the target angle includes: The maximum rotational speed is determined based on the aforementioned driving safety level; The target rotation speed is determined based on the maximum rotation speed, the current screen angle, and the target angle.

[0010] In some embodiments, determining the target rotation speed based on the maximum rotation speed, the current screen angle, and the target angle includes: The absolute value of the difference between the target angle and the current screen angle is determined as the first difference; The ratio of the first difference to the preset adjustment parameter is determined as the smooth rotation speed; The smaller of the smooth rotational speed and the maximum rotational speed is determined as the target rotational speed.

[0011] In some embodiments, after the vehicle screen is rotated to the target angle at the target rotation speed, the method further includes: Obtain vehicle's upcoming driving data; The next driving scenario for the vehicle and the distance the vehicle is traveling from the next driving scenario are determined based on the upcoming driving data. Determine the reference angle for the next driving scenario based on the next driving scenario; In response to the fact that the category difference between the next driving scenario and the current driving scenario is greater than or equal to a preset difference, and the driving distance is less than or equal to a preset distance, the vehicle screen is controlled to rotate to the reference angle of the next scenario.

[0012] In some embodiments, the method further includes: In response to the vehicle entering the next driving scenario, real-time data information of the vehicle is acquired; The scene correction angle is determined based on the next scene reference angle and the real-time data information; The target angle of the scene is determined based on the next scene reference angle and the scene correction angle. The scene rotation speed is determined based on the real-time data information and the scene target angle. Control the in-vehicle screen to rotate to the target angle of the scene at the scene rotation speed.

[0013] Based on the same inventive concept, a second aspect of this application provides an electronic device, including a memory, a processor, and a computer program stored in the memory and running on the processor, wherein the processor executes the computer program to implement the method as described in any of the first aspects above.

[0014] Based on the same inventive concept, a second aspect of this application provides a vehicle including the electronic equipment described in the second aspect above.

[0015] As can be seen from the above, the in-vehicle screen rotation control method, electronic device, and vehicle provided in this application acquire vehicle-related data, determine the driving safety level and current driving scenario based on the vehicle-related data, determine the target angle based on the vehicle-related data, current driving scenario, and driving safety level, and determine the target rotation speed based on the driving safety level and the target angle. This ensures that the determined target angle is not only related to the current driving scenario but also to the vehicle-related data and driving safety level, making the process of determining the target angle more intelligent and more in line with the actual situation of the vehicle. Simultaneously, the determined target rotation speed is also related to the driving safety level, making the determined target rotation speed more in line with the actual situation of the vehicle, ensuring the safety of rotating the in-vehicle screen, and ultimately controlling the in-vehicle screen to rotate to the target angle at the target rotation speed, so that the in-vehicle screen can ultimately rotate to the target angle that best reflects the actual situation, improving the intelligence level of rotating the in-vehicle screen and making the rotation of the in-vehicle screen more in line with the actual needs of the user. Attached Figure Description

[0016] To more clearly illustrate the technical solutions in this application or related technologies, the drawings used in the description of the embodiments or related technologies will be briefly introduced below. Obviously, the drawings described below are only embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0017] Figure 1 This is an exemplary flowchart of an in-vehicle screen rotation control method according to an embodiment of this application; Figure 2 This is a schematic diagram illustrating the process of determining the safety level and whether rotation is allowed in the vehicle screen rotation control method according to an embodiment of this application; Figure 3 This is an exemplary scene-angle mapping table for embodiments of this application; Figure 4 This is a flowchart illustrating the process of determining the target angle in the vehicle screen rotation control method according to an embodiment of this application. Figure 5 This is another exemplary flowchart illustrating the vehicle screen rotation control method according to an embodiment of this application; Figure 6 This is a schematic diagram of an in-vehicle screen rotation control device according to an embodiment of this application; Figure 7 This is a schematic diagram of an electronic device according to an embodiment of this application. Detailed Implementation

[0018] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with specific embodiments and the accompanying drawings.

[0019] It should be noted that, unless otherwise defined, the technical or scientific terms used in the embodiments of this application should have the ordinary meaning understood by one of ordinary skill in the art to which this application pertains. The terms "first," "second," and similar terms used in the embodiments of this application do not indicate any order, quantity, or importance, but are merely used to distinguish different components. Terms such as "comprising" or "including" mean that the element or object preceding the word encompasses the elements or objects listed after the word and their equivalents, without excluding other elements or objects. Terms such as "connected" or "linked" are not limited to physical or mechanical connections, but can include electrical connections, whether direct or indirect. Terms such as "upper," "lower," "left," and "right" are only used to indicate relative positional relationships; when the absolute position of the described object changes, the relative positional relationship may also change accordingly.

[0020] With the development of automotive intelligence, the smart cockpit has become the core interaction center of the vehicle. In-vehicle screens (such as the central control screen, entertainment screens above or in front of the second-row seats, etc.) serve as the main interface for user interaction with the vehicle, and their display methods and interactive experiences directly impact user experience. To improve user experience, rotating screen technology is increasingly being applied to high-end models, enabling in-vehicle screens to adjust their angle according to usage scenarios to adapt to the viewing and operation needs of different users.

[0021] Most existing in-vehicle screen rotation operations rely on manual adjustment by the user. This adjustment method can easily distract the driver, pose safety hazards, and lacks intelligence.

[0022] Some in-vehicle screens are automatically adjustable, mostly with preset fixed scenarios such as navigation mode, entertainment mode, and reversing mode, and a fixed screen angle for each scenario. When a specific scenario is detected, the screen rotates to the corresponding preset angle. This adjustment method solves the safety hazards caused by manual user adjustment. However, its shortcomings are that the preset scenarios are too simple and cannot meet the many complex scenarios that occur during driving. Furthermore, the adjustment of the in-vehicle screen depends only on the driving scenario and cannot be flexibly adjusted based on the user and environmental conditions, making it difficult to meet the actual needs of users.

[0023] Therefore, how to improve the intelligence level of rotating in-vehicle screens so that the rotation of in-vehicle screens can better meet the actual needs of users is an urgent problem to be solved.

[0024] Based on this, see Figure 1 This application provides a method for controlling the rotation of an in-vehicle screen, executed by an in-vehicle screen controller, the method specifically including the following steps: Step S100: Obtain vehicle-related data, and determine the driving safety level and current driving scenario based on the vehicle-related data; Step S200: Determine the target angle based on the vehicle-related data, the current driving scenario, and the driving safety level; Step S300: Determine the target rotation speed based on the driving safety level and the target angle; Step S400: Control the vehicle screen to rotate to the target angle at the target rotation speed.

[0025] Specifically, in this application, the in-vehicle screen may be an in-vehicle central control screen, an in-vehicle entertainment screen installed above or in front of the second-row seats, etc.

[0026] The vehicle-related data may include driving status data, environmental perception data, user behavior data, vehicle status data, and cabin environment data, which are collected in real time by various sensors.

[0027] Driving status data is collected via the vehicle bus and may include vehicle speed, steering angle, braking status, throttle opening, gear information, etc.

[0028] Environmental perception data is collected through cameras, including road scenes, traffic signs, light intensity, rainfall and other weather conditions, as well as geographical location information.

[0029] User behavior data is collected through facial cameras, including the driver's line of sight, facial expressions, head posture, seat position, height and weight, etc.; it can also be collected through touch screens and microphones to collect users' voice commands and operation records.

[0030] Vehicle status data is collected through body sensors and can include door status, window status, air conditioning status, and light status.

[0031] The cabin environment data is collected by infrared sensors and may include cabin temperature and humidity.

[0032] In practice, the collected raw data can be preprocessed, including data cleaning, time synchronization, format conversion, and feature extraction to obtain vehicle-related data. Data cleaning removes outliers and noisy data; time synchronization ensures the alignment of timestamps from multiple data sources; feature extraction extracts key features from the raw data, such as extracting gaze direction as angle values ​​and facial expressions as emotion tags (happy, focused, tired, etc.).

[0033] The preprocessed data can be stored in the feature database as multimodal feature vectors. A time window mechanism is used to retain data from the most recent 60 seconds to support scene recognition and predictive analysis.

[0034] Based on vehicle-related data, the driving safety level and current driving scenario can be determined. The driving safety level is used to assess the current safety level of the vehicle, and it is related to factors such as vehicle driving conditions, driver behavior, and environmental conditions.

[0035] When determining the current driving scenario based on vehicle-related data, it can be based on environmental perception data and / or driving status data within the vehicle-related data. For example, when the environmental perception data includes parking space information, garage information, or underground parking information, the current driving scenario is determined to be a parking scenario; when the environmental perception data includes urban road information, vehicles are all around the vehicle, and the vehicle speed is less than or equal to a preset speed, the current driving scenario is determined to be an urban congestion scenario; when the environmental perception data includes highway information and the vehicle speed is greater than or equal to a preset minimum speed, the current driving scenario is determined to be a highway driving scenario; when the environmental perception data includes tunnel information, the current driving scenario is determined to be a tunnel driving scenario, and so on.

[0036] When determining the current driving scenario based on vehicle-related data, a multi-dimensional scene recognition model can be constructed, and deep learning algorithms can be used to integrate multi-source features for scene recognition and semantic understanding.

[0037] The scene recognition model adopts a layered architecture: The first layer is a basic scene classifier that uses a lightweight convolutional neural network (CNN) to quickly identify basic scene types, including six major categories: navigation scene, entertainment scene, call scene, reversing scene, parking scene, and rest scene.

[0038] The second layer is a refined scene understander, which uses an attention-enhanced recurrent neural network (RNN) to perform refined analysis of the basic scene and identify sub-scenes (such as navigation scenes being subdivided into highway navigation, city navigation, and congestion navigation).

[0039] The third layer is the scene semantic parser, which uses a graph neural network (GNN) to build a scene knowledge graph and understand the semantic relationships and transformation logic between scenes (such as user interaction intent: viewing navigation, adjusting volume, making or receiving phone calls, etc.).

[0040] The scene recognition model takes a multimodal feature vector as input and outputs a scene category probability distribution and a scene semantic description. Based on the scene category probability distribution and scene semantic description, the current driving scene can be determined. Model training utilizes large-scale real-world driving data, including over 1 million labeled data points, covering various driving scenarios and user behaviors. The scene recognition frequency is 10 times per second to ensure real-time performance. The recognition results include information such as the current scene category, confidence level, scene duration, and scene change trend.

[0041] Then, based on the vehicle-related data, the current driving scenario, and the driving safety level, a target angle is determined. This target angle is the final angle to which the in-vehicle screen needs to be rotated. In this application, the target angle is not only related to the current driving scenario but also to the vehicle-related data and the driving safety level. That is, even in the same driving scenario, different vehicle-related data and driving safety levels will determine different target angles. This makes the determined target angle more consistent with the actual situation of the vehicle and more accurate, thereby making the final angle of the in-vehicle screen after adjustment more consistent with the actual situation and user needs.

[0042] Then, based on the driving safety level and the target angle, the target rotation speed is determined. The target rotation speed is the optimal rotation speed of the in-vehicle screen, which ensures that the screen can rotate to the target angle while ensuring that the rotation speed is moderate and will not have an adverse effect on the driver, thereby improving the user experience.

[0043] In this application, the target rotation speed is related not only to the target angle but also to the driving safety level. That is to say, even with the same target angle, different driving safety levels will determine different target angles, thus making the determined target rotation speed more consistent with the current actual situation of the vehicle.

[0044] Finally, the vehicle screen is controlled to rotate to the target angle at the target rotation speed, so that the vehicle screen can eventually rotate to the target angle that best reflects the actual situation, thereby improving the user experience.

[0045] In this application, vehicle-related data is acquired, and a driving safety level and current driving scenario are determined based on this data. A target angle is determined based on the vehicle-related data, the current driving scenario, and the driving safety level. A target rotation speed is determined based on the driving safety level and the target angle. This ensures that the determined target angle is related not only to the current driving scenario but also to the vehicle-related data and the driving safety level, making the target angle determination process more intelligent and more consistent with the vehicle's current situation. Simultaneously, the determined target rotation speed is also related to the driving safety level, making it more consistent with the vehicle's current situation and ensuring safety when rotating the screen. Finally, the in-vehicle screen is controlled to rotate to the target angle at the target rotation speed, so that the in-vehicle screen can ultimately rotate to the target angle that best reflects the actual situation, improving the intelligence of screen rotation and making the screen rotation more in line with the user's actual needs.

[0046] In some embodiments, see Figure 2 As shown, determining the driving safety level based on vehicle-related data includes: Based on the vehicle-related data, a driving risk index, a driver status index, a traffic environment index, and a vehicle status index are determined. The driving safety index is determined based on the driving risk index, driver status index, traffic environment index, and vehicle status index. The driving safety level is determined based on the driving safety index.

[0047] Specifically, vehicle-related data includes current vehicle speed, road speed limit, longitudinal acceleration, maximum comfort acceleration, lateral acceleration, maximum comfort lateral acceleration, rainfall information, maximum rainfall, visibility, minimum safe visibility, wind speed, and maximum safe wind speed.

[0048] Assessing the dynamic risks of vehicle movement primarily considers speed, acceleration, and weather factors. Therefore, the driving risk index is determined based on the vehicle-related data, including determining the speed risk index, acceleration risk index, and weather risk index based on the vehicle-related data.

[0049] Specifically, the Driving Risk Index is calculated as follows: Driving_Risk_Index = w1×Speed_Risk + w2×Acceleration_Risk + w3×Weather_Risk.

[0050] Among them, the speed risk index Speed_Risk = (Current_Speed ​​ / Speed_Limit) k1 Current_Speed ​​is the current vehicle speed; Speed_Limit is the road speed limit; k1 is the first exponential factor, which sharply increases the risk of speeding and truncates the speed limit to 1 when exceeding the limit. The first exponential factor is a preset parameter, for example, k1=2.

[0051] Among them, the speed risk uses a square function, which makes the risk of speeding increase sharply.

[0052] Acceleration risk index Acceleration_Risk = w_a×Long_Accel_Risk + w_t×Trans_Accel_Risk.

[0053] The longitudinal acceleration risk index, Long_Accel_Risk, is calculated as: Long_Accel_Risk = (|Long_Accel| / Max_Long_Accel) k2 Where Long_Accel is the longitudinal acceleration, Max_Long_Accel is the maximum comfort acceleration, and k2 is the second exponential factor, exemplarily k2=2. The maximum comfort acceleration is obtained based on historical testing experience; exemplarily, the maximum comfort acceleration can be 2.5 m / s². The lateral acceleration risk index, Trans_Accel_Risk, is calculated as: (|Trans_Accel| / Max_Trans_Accel) k3 Where Trans_Accel is the lateral acceleration, Max_Trans_Accel is the maximum comfortable lateral acceleration, and k3 is the third exponential factor, for example, k3=2. The maximum comfortable lateral acceleration is obtained based on historical testing experience, for example, the maximum comfortable lateral acceleration can be 3m / s².

[0054] Weather Risk Index: Weather_Risk = w_w1×Rain_Risk + w_w2×Visibility_Risk + w_w3×Wind_Risk.

[0055] The rain and snow risk index is calculated as Rain_Risk = Rain_Intensity / Max_Rain_Intensity, where Rain_Intensity is the rain sensor reading (i.e., rainfall information), and Max_Rain_Intensity is the maximum rainfall, which is obtained based on historical testing experience or determined based on factory settings. For example, the maximum rainfall is 50 mm / h.

[0056] The visibility risk index, Visibility_Risk, is calculated as 1 - min(Visibility / Min_Safe_Visibility, 1), where Visibility is the visibility level, and Min_Safe_Visibility is the minimum safe visibility level, which is determined based on historical testing experience or factory settings. For example, the minimum safe visibility level is 100m.

[0057] The wind resistance risk index Wind_Risk = Wind_Speed ​​ / Max_Safe_Wind_Speed, where Wind_Speed ​​is the wind speed and Max_Safe_Wind_Speed ​​is the maximum safe wind speed, which is obtained based on historical testing experience or determined based on factory settings. For example, the maximum safe wind speed is 20 m / s.

[0058] Among them, w1 (vehicle speed risk weight), w2 (acceleration risk weight), w3 (weather risk weight), w_a (longitudinal acceleration weight), w_t (lateral acceleration weight), w_w1 (rain and snow risk weight), w_w2 (visibility risk weight), and w_w3 (wind resistance risk weight) are all weight values ​​obtained based on historical test experience.

[0059] For example, w1 (vehicle speed risk weight) = 0.5, w2 (acceleration risk weight) = 0.3, w3 (weather risk weight) = 0.2, w_a (longitudinal acceleration weight) = 0.6, w_t (lateral acceleration weight) = 0.4, w_w1 (rain / snow risk weight) = 0.5, w_w2 (visibility risk weight) = 0.4, and w_w3 (wind resistance risk weight) = 0.1.

[0060] Specifically, the Driver State Index is mainly used to assess the driver's physiological and psychological state, primarily considering focus and fatigue levels. The formula is as follows: Driver State Index = v1 × Attention_Index + v2 × Fatigue_Index, where v1 (attention weight) and v2 (fatigue weight) are obtained based on historical testing experience. For example, v1 (attention weight) = 0.6 and v2 (fatigue weight) = 0.4.

[0061] The attention index is calculated as: Attention_Index = v_a1×Gaze_Stability + v_a2×Head_Stability + v_a3×Interaction_Frequency. The values ​​of v_a1 (gaze stability weight), v_a2 (head stability weight), and v_a3 (interaction frequency weight) are derived from historical testing experience. For example, v_a1 (gaze stability weight) = 0.5, v_a2 (head stability weight) = 0.3, and v_a3 (interaction frequency weight) = 0.2.

[0062] The gaze stability index Gaze_Stability = 1 - (Gaze_Angle_Variance / Max_Variance), where Gaze_Angle_Variance is the variance of the gaze angle (the variance of the angle by which the driver's gaze direction, i.e., the viewpoint, deviates from the preset gaze direction, i.e., directly in front, within a preset time), and Max_Variance is the maximum variance threshold. For example, the maximum variance threshold can be 25 degrees².

[0063] The head posture stability index is Head_Stability = 1 - (Head_Pose_Angle_Variance / Max_Variance), where Head_Pose_Angle_Variance is the head posture variance (the variance of the angle by which the driver's head deviates from the preset direction, i.e., directly in front, within a preset time), and Max_Variance is the maximum variance threshold. For example, the maximum variance threshold can be 25 degrees².

[0064] Interaction frequency = 1 - min(Interaction_Count / Max_Safe_Interaction, 1), where Interaction_Count is the number of screen interactions in the past 30 seconds, and Max_Safe_Interaction is the maximum number of safe interactions (for example, 5 times).

[0065] The Fatigue Index is calculated as: Fatigue_Index = v_f1×Blink_Frequency + v_f2×Head_Nod_Frequency + v_f3×Yawn_Duration, where v_f1 (blink frequency weight), v_f2 (nodding frequency weight), and v_f3 (yawn duration weight) are obtained based on historical testing experience. For example, v_f1 (blink frequency weight) = 0.5, v_f2 (nodding frequency weight) = 0.3, and v_f3 (yawn duration weight) = 0.2.

[0066] Blink_Frequency = (Blink_Count - Normal_Blink_Count) / Max_Excess_Blink, where Blink_Count is the number of blinks in 1 minute, Normal_Blink_Count is the number of normal blinks (for example, based on historical testing experience, the number of normal blinks is 15 times / minute), and Max_Excess_Blink is the maximum number of excessive blinks (for example, based on historical testing experience, the maximum number of excessive blinks is 30 times / minute).

[0067] Head nod frequency = (Head_Nod_Count - Normal_Nod_Count) / Max_Excess_Nod, where Head_Nod_Count is the number of nods in 1 minute, Normal_Nod_Count is the number of normal nods (for example, based on historical testing experience, the number of normal nods is 0 times / minute), and Max_Excess_Nod is the maximum number of excessive nods (for example, based on historical testing experience, the maximum number of excessive nods is 5 times / minute).

[0068] Yawn duration Yawn_Duration = Yawn_Duration_Per_Minute / Max_Yawn_Duration, where Yawn_Duration_Per_Minute is the total yawn duration within 1 minute, and Max_Yawn_Duration is the maximum yawn duration (for example, based on historical testing experience, the maximum yawn duration is 10 seconds / minute).

[0069] The focus index takes into account the stability of the gaze, the stability of the head posture, and the frequency of interaction; the fatigue index takes into account the frequency of blinking, the frequency of nodding, and the duration of yawning.

[0070] Specifically, the Traffic Environment Index is used to assess traffic density, road complexity, and intersection conditions. The formula is as follows: The Traffic Environment Index is calculated as follows: Traffic_Environment_Index = u1×Traffic_Density_Factor + u2×Road_Complexity_Factor + u3×Intersection_Factor, where u1 (traffic density weight), u2 (road complexity weight), and u3 (intersection weight) are obtained based on historical testing experience. For example, u1 (traffic density weight) = 0.4, u2 (road complexity weight) = 0.4, and u3 (intersection weight) = 0.2.

[0071] Traffic density factor = (Vehicle_Count / Max_Vehicle_Count) k4 Where Vehicle_Count is the number of vehicles within 100 meters, Max_Vehicle_Count is the maximum number of vehicles (for example, based on historical testing experience, the maximum number of vehicles is 10), and k4 is the fourth exponential factor (the fourth exponential factor is obtained based on historical testing experience, for example, k4=1.5).

[0072] The road complexity factor is calculated as: Road_Complexity_Factor = w_r1×Lane_Complexity + w_r2×Sign_Density + w_r3×Road_Type_Risk, where w_r1 (lane complexity weight), w_r2 (sign density weight), and w_r3 (road type risk weight) are obtained based on historical testing experience. For example, w_r1 (lane complexity weight) = 0.3, w_r2 (sign density weight) = 0.2, and w_r3 (road type risk weight) = 0.5.

[0073] Lane complexity = Lane_Count / Max_Lane_Count, where Lane_Count is the current number of lanes and Max_Lane_Count is the maximum number of lanes (for example, based on historical testing experience, the maximum number of lanes can be 6 lanes).

[0074] Sign density: Sign_Density = Sign_Count_Per_Km / Max_Sign_Count_Per_Km, where Sign_Count_Per_Km is the number of traffic signs per kilometer, and Max_Sign_Count_Per_Km is the maximum sign density (for example, based on historical testing experience, the maximum sign density can be 20 signs / km).

[0075] The Road Type Risk (Road_Type_Risk) is 0.2 for highways, 0.5 for urban arterial roads, 0.7 for urban secondary roads, 0.9 for rural roads, and 1.0 for mountain roads.

[0076] Intersection_Factor = w_i1×Intersection_Type+w_i2×Upcoming_Distance_Factor, where w_i1 (intersection type weight) and w_i2 (distance weight to the upcoming intersection) are obtained based on historical testing experience. For example, w_i1 (intersection type weight) = 0.7 and w_i2 (distance weight to the upcoming intersection) = 0.3.

[0077] Intersection_Type: 0.0 for no intersection, 0.4 for simple intersections (T-junctions), 0.7 for complex intersections (crossroads), 0.6 for roundabouts, and 0.3 for grade-separated interchanges.

[0078] The Upcoming Distance Factor is calculated as 1 - min(Distance_To_Intersection / Safe_Following_Distance, 1), where Distance_To_Intersection is the distance to the next intersection, and Safe_Following_Distance is the safe following distance (for example, based on historical test experience, the safe following distance can be 50m).

[0079] Traffic density is calculated based on the number of surrounding vehicles; road complexity takes into account the number of lanes, signage density, and road type; intersection factor takes into account intersection type and distance to the intersection.

[0080] Specifically, the Vehicle State Index is used to assess the technical condition of a vehicle, primarily considering tire pressure, braking system, and battery condition. The formula is as follows: Vehicle State Index = z1×Tire_Status_Factor + z2×Brake_Status_Factor + z3×Battery_Status_Factor, where z1 (tire pressure status weight), z2 (brake status weight), and z3 (battery status weight) are obtained based on historical testing experience. For example, z1 (tire pressure status weight) = 0.5, z2 (brake status weight) = 0.3, and z3 (battery status weight) = 0.2.

[0081] Tire pressure status factor Tire_Status_Factor = 1 - max(|Tire_Pressure_i - Nominal_Pressure| / Max_Allowable_Deviation), where Tire_Pressure_i is the tire pressure of the i-th tire, Nominal_Pressure is the standard tire pressure (for example, the standard tire pressure is 250 kPa), Max_Allowable_Deviation is the maximum allowable deviation (for example, the maximum allowable deviation is 50 kPa based on historical testing experience), and max is the maximum deviation among all tires.

[0082] Brake_Status_Factor = 1 - (Brake_Warning_Level / Max_Warning_Level), where Brake_Warning_Level is the braking system warning level (0-10) and Max_Warning_Level is the maximum warning level (10).

[0083] The brake warning levels are as follows: 0-2 is normal with no warning, 3-5 is a minor abnormality (such as brake pad wear), 6-8 is a moderate abnormality (such as low brake fluid level), and 9-10 is a serious abnormality (such as brake failure).

[0084] Battery Status Factor = w_b1×SOC_Factor + w_b2×Health_Factor, where w_b1 (SOC factor weight) and w_b2 (health factor weight) are obtained based on historical testing experience. For example, w_b1 (SOC factor weight) = 0.7 and w_b2 (health factor weight) = 0.3.

[0085] Remaining capacity factor SOC_Factor = SOC / 100, where SOC is the remaining battery capacity (%). Health factor Health_Factor = SOH / 100, where SOH is the battery health status (%).

[0086] Among them, tire pressure status is calculated based on the tire pressure deviation of all tires, and the maximum deviation is taken; braking status is calculated based on the braking system warning level; battery status takes into account both SOC and SOH.

[0087] Then, the driving safety index is determined based on the driving risk index, driver state index, traffic environment index, and vehicle state index.

[0088] Specifically, the driving safety index Safety_Score = (1-Driving_Risk_Index)×Driver_State_Index×(1 - Traffic_Environment_Index)×Vehicle_State_Index, where Safety_Score ranges from [0, 1], and a higher value indicates a safer driving condition.

[0089] Among them, the driving risk index and traffic environment index are negative indicators, with higher values ​​indicating greater danger; they are converted to positive indicators using (1 - Index). The driver state index and vehicle state index are positive indicators, with higher values ​​indicating greater safety. The four indices are multiplied together; any index that is too low will lead to a decrease in the overall safety score, reflecting the "weakest link effect."

[0090] Finally, the driving safety level is determined based on the driving safety index. In this way, the driving safety level can be accurately determined based on the quantified value, thereby determining the safety of the current driving state.

[0091] In this application, driving risk factors, driver state factors, traffic environment factors, and vehicle state factors during the driving process are quantified based on driving risk index, driver state index, traffic environment index, and vehicle state index. Then, the driving safety level is accurately determined based on the driving risk index, driver state index, traffic environment index, and vehicle state index. In this way, the driving safety level can be accurately determined based on the quantified values, thereby improving the accuracy of determining the current driving state.

[0092] In some embodiments, determining the driving safety level based on the driving safety index includes: In response to the driving safety index being greater than a preset minimum value and less than or equal to a first preset index, the driving safety level is determined to be the "rotation prohibited and reset" level. Alternatively, in response to the driving safety index being greater than a first preset index and less than or equal to a second preset index, the driving safety level is determined to be prohibited from rotation and the level is adjusted. Alternatively, in response to the driving safety index being greater than the second preset index and less than or equal to the third preset index, the driving safety level is determined to be the level that allows slow rotation. Alternatively, in response to the driving safety index being greater than a third preset index and less than or equal to a fourth preset index, the driving safety level is determined to be a level that allows slightly slower rotation. Alternatively, in response to the driving safety index being greater than the fourth preset index and less than or equal to the fifth preset index, the driving safety level is determined to be the level that allows normal rotation. The preset minimum value, the first preset index, the second preset index, the third preset index, the fourth preset index, and the fifth preset index increase sequentially.

[0093] Specifically, the preset minimum value, first preset index, second preset index, third preset index, fourth preset index, and fifth preset index are obtained based on historical testing experience. For example, the preset minimum value can be 0, the first preset index can be 0.4, the second preset index can be 0.55, the third preset index can be 0.7, the fourth preset index can be 0.85, and the fifth preset index can be 1.0.

[0094] When the driving safety index is greater than a preset minimum value but less than or equal to a first preset index, the driving safety index is very low, indicating that the driving state is extremely unsafe. Therefore, in order to ensure driving safety, screen rotation is prohibited, the screen is immediately reset to the default position, and an alarm is triggered. The default position is the factory setting where the screen is not rotated at all, i.e., the screen is perpendicular to the driver's line of sight and faces directly in front of the driver, with a screen angle of 0 degrees. Therefore, the driving safety level is determined to be the "prohibit rotation and reset" level.

[0095] When the driving safety index is greater than the first preset index and less than or equal to the second preset index, the driving safety index is low, indicating that the driving state is unsafe. Therefore, in order to ensure driving safety, the screen rotation is prohibited and the screen is slowly reset to the default position. This can ensure safety without reducing the driver's user experience due to excessively fast screen rotation. Therefore, the driving safety level is determined to be "prohibit rotation and adjust level".

[0096] When the driving safety index is greater than the second preset index and less than or equal to the third preset index, the driving safety index is in the middle, indicating that the driving state is relatively safe. At this time, screen rotation is allowed, but the rotation speed must be slow to ensure safety. Therefore, the driving safety level is determined to be the slow rotation level.

[0097] When the driving safety index is greater than the third preset index and less than or equal to the fourth preset index, the driving safety index is relatively high, indicating that the driving state is relatively safe. At this time, screen rotation is allowed, and the rotation speed can be appropriately increased to rotate the screen to the designated position as quickly as possible while ensuring safety. Therefore, the driving safety level is determined to be the level that allows slightly slower rotation.

[0098] When the driving safety index is greater than the fourth preset index and less than or equal to the fifth preset index, the driving safety index is very high, indicating that the driving state is very safe. At this time, screen rotation is allowed, and the rotation speed can be very fast, so as to rotate the screen to the designated position as soon as possible while ensuring safety. Therefore, the driving safety level is determined to be the level that allows normal rotation.

[0099] In this application, the driving safety level can be accurately determined by comparing different values ​​of the driving safety index with preset indices. Then, the target angle can be determined based on the accurate driving safety level, thereby improving the safety of the determined target angle.

[0100] In some embodiments, the driving safety level includes a prohibited rotation level or a slightly slower rotation level, wherein the prohibited rotation level includes a prohibited rotation and reset level and a prohibited rotation and adjustment level. The permitted rotation level includes a permitted slow rotation level, a permitted slightly slower rotation level, and a permitted normal rotation level.

[0101] Determining the target angle based on the vehicle-related data, the current driving scenario, and the driving safety level includes: In response to the driving safety level being a no-rotation level, the preset default angle is determined as the target angle; In response to the driving safety level being a permissible rotation level, a current scene reference angle is determined based on the current driving scenario; a current correction angle is determined based on the current scene reference angle, the vehicle-related data, and the driving safety level; and a target angle is determined based on the current scene reference angle and the current correction angle.

[0102] Specifically, when the driving safety level is the prohibited rotation level, the driving state is unsafe, the screen is not allowed to rotate automatically, and the screen is only allowed to reset, that is, the screen is only allowed to rotate to the default position. Therefore, the preset default angle corresponding to the default position is determined as the target angle. The preset default angle is 0 degrees, which means that the screen faces directly in front of the driver, that is, the screen is perpendicular to the driver's line of sight.

[0103] When the driving safety level is at the rotation-permissible level, the driving state is safe, and automatic screen rotation is allowed. Therefore, it is necessary to first determine the current scenario reference angle based on the current driving scenario. The current scenario reference angle is the optimal screen angle corresponding to the current driving scenario, determined based on historical testing experience. Different current driving scenarios will correspond to different current scenario reference angles.

[0104] For example, see Figure 3 The aforementioned is a scene-angle mapping table determined based on historical testing experience. Based on the barrier driving scenario, the corresponding current scene reference angle can be determined from this scene-angle mapping table.

[0105] Figure 3 In this context, 0 degrees refers to the default preset angle, meaning the screen faces directly in front of the driver, i.e., the screen is perpendicular to the driver's line of sight. When the scene reference angle is negative, it means the screen is tilted towards the passenger side; when the scene reference angle is positive, it means the screen is tilted towards the driver's side.

[0106] After determining the current scene reference angle, the current correction angle is determined based on the current scene reference angle, the vehicle-related data, and the driving safety level. The current correction angle is the angle that needs to be corrected based on the current vehicle-related data and the driving safety level. Finally, the target angle is determined based on the current scene reference angle and the current correction angle.

[0107] Specifically, when determining the target angle based on the current scene reference angle and the current correction angle, the target angle is the sum of the current scene reference angle and the current correction angle.

[0108] It is important to note that after determining the target angle, it is also necessary to determine whether the target angle meets the hardware limitations, that is, whether the target angle is within the range allowed by the screen rotation. The range allowed by the screen rotation is the angle interval formed by the maximum rotation angle and the minimum rotation angle. For example, the range allowed by the screen rotation can be the angle interval formed by -30° to +30°.

[0109] When the target angle is within this angle range, the target angle is the final executable target angle.

[0110] When the target angle is less than the minimum rotation angle, the minimum rotation angle is determined as the final executable target angle.

[0111] When the target angle is greater than the maximum rotation angle, the maximum rotation angle is determined as the final executable target angle.

[0112] In this application, the target angle is determined not only based on the current driving scenario, but also based on the current vehicle-related data and driving safety level. This makes the final target angle not just a specific angle related to the current driving scenario, but an angle that is more in line with the actual situation of the vehicle. As a result, the final angle after the in-vehicle screen is adjusted is more in line with the actual situation and user needs.

[0113] In some embodiments, see Figure 4 The vehicle-related data includes driver identity information, light intensity, noise information, current ambient temperature, and current screen angle; The process of determining the current correction angle based on the current scene reference angle, the vehicle-related data, and the driving safety level includes: Determine the safety correction angle based on the aforementioned driving safety level; Based on the driver's identity information and preset driver preference information, the driver's correction angle is determined; Based on the light intensity, noise information, and current ambient temperature, determine the environmental correction angle; Based on the current scene reference angle, safety correction angle, driver correction angle, environment correction angle, and current screen angle, determine the smooth correction angle; The sum of the safety correction angle, driver correction angle, environmental correction angle, and smoothness correction angle is determined as the current correction angle.

[0114] Specifically, the safety correction angle is determined based on the driving safety level, including: when the driving safety level is the level that allows normal rotation, the safety correction angle is 0°; when the driving safety level is the level that allows slightly slower rotation, the safety correction angle is -2°; when the driving safety level is the level that allows slow rotation, the safety correction angle is -5°; when the driving safety level is the level that prohibits rotation and requires adjustment, the safety correction angle is -10°; and when the driving safety level is the level that prohibits rotation and requires adjustment, the safety correction angle is -∞ (prohibits rotation).

[0115] Specifically, the driver's correction angle is determined based on the driver's identity information and preset driver preference information. The preset driver preference information includes a preset driver tilt preference index (Driver_Orient, exemplarily -1 to 1), a preset passenger tilt preference index (Passenger_Orient, exemplarily -1 to 1), a preset centering preference index (Center_Preference, exemplarily 0 to 1), and the average of the user's historical tilt angles (User_History).

[0116] The preset driver-oriented preference index (Example, -1 to 1), the preset passenger-oriented preference index (Example, -1 to 1), and the preset center-oriented preference index (Example, 0 to 1) can be obtained based on historical test data. Different users may have different preset driver-oriented preference indices, preset passenger-oriented preference indices, and preset center-oriented preference indices.

[0117] For example, a user personalization model trained through reinforcement learning can also be used. The feature words of the current driving scenario, driver identity information (such as user ID), and preset driver preference information (such as user preference features) are input into the personalization model, and the driver correction angle is output.

[0118] Personalized models are models built for specific users, learning their preferences and usage habits to achieve personalized recommendations. In this application, reinforcement learning algorithms are used to continuously learn user behavior patterns, constructing a personalized user model and implementing a personalized recommendation strategy for each user.

[0119] Model inputs: scene semantics, user ID, user preference features (height, driving habits, etc.).

[0120] Model output: Personalized correction angle, i.e., the correction angle (range -5° to +5°) for a specific user's driver, and the angle calculation weight set.

[0121] The model can also be updated by regularly collecting new data and using online learning algorithms to update the model. It can also be updated immediately when the user makes manual adjustments, with a convergence time of 2-4 weeks.

[0122] Among them, user preference features are feature vectors used to describe user preferences and usage habits. User preference features serve as input to the personalization model and are used to calculate the personalization correction angle.

[0123] Feature dimensions: Driver tilt preference: -1 to 1 (-1 means no tilt towards the driver at all, 1 means tilt towards the driver at all). Passenger tilt preference: -1 to 1 (-1 means no tilt towards the passenger, 1 means full tilt towards the passenger). Centering preference: 0 to 1 (0 means no preference for centering, 1 means strong preference for centering); User historical angle mean: The average tilt angle of a user in this scenario throughout history.

[0124] Wherein, the driver correction angle ΔAngle_User = β1×Driver_Orient + β2×Passenger_Orient + β3×Center_Preference + β4×User_History, where β1, β2, β3, and β4 are driver weighting coefficients determined based on historical testing experience. For example, β1=0.4, β2=-0.4, β3=0.2, and β4=0.2.

[0125] Specifically, based on the light intensity, noise information, and current ambient temperature, an environmental correction angle is determined, that is, the angle is corrected according to environmental factors such as lighting conditions and in-vehicle temperature.

[0126] Specifically, the environmental correction angle ΔAngle_Environment = γ1×Light_Correction + γ2×Noise_Correction + γ3×Temperature_Correction, where γ1, γ2, and γ3 are temperature weighting coefficients obtained based on historical testing experience. For example, γ1=0.5, γ2=0.3, and γ3=0.2.

[0127] Wherein, Light_Correction is the light correction angle, Light_Correction = (LightIntensity / Max Light) × 5°, where Light Intensity is the light intensity, and Max Light is the maximum allowable light intensity (the maximum allowable light intensity is obtained based on historical test experience or based on factory settings).

[0128] Noise_Correction is the noise correction angle, Noise_Correction = (Noise Level / MaxNoise) ×3°, where Noise Level is the noise information, that is, the noise level, and Max Noise is the maximum noise level (the maximum noise level is obtained based on historical test experience or based on factory settings).

[0129] Temperature_Correction is the temperature correction angle, Temperature_Correction = -(Temperature - Comfort_Temp) / 10°, where Temperature is the current ambient temperature and Comfort_Temp is the optimal temperature (the optimal temperature is obtained based on historical testing experience; for example, the optimal temperature can be 25℃±3℃).

[0130] Then, the current scene reference angle, safety correction angle, driver correction angle, environment correction angle, and current screen angle are used to determine the smoothing correction angle. The smoothing correction angle ΔAngle_Smooth = Δ0 × (1 / (1 + e)) (-k × |Δ|) )), where Δ0 = Angle Target - Angle Current, where Angle Target is the sum of the current scene baseline angle, safety correction angle, driver correction angle and environment correction angle, Angle Current is the current screen angle, and k is the curve steepness parameter, which is obtained based on historical test experience. For example, k can be 5-10.

[0131] Finally, the sum of the safety correction angle, driver correction angle, environmental correction angle, and smoothness correction angle is determined as the current correction angle.

[0132] In this application, the current correction angle is the final correction angle obtained by combining driving safety level, driver preference habits, environmental influencing factors and smoothing correction factors. By quantifying each factor, a more accurate and realistic current correction angle is finally obtained.

[0133] In some embodiments, the vehicle-related data includes the current screen angle; Determining the target rotation speed based on the driving safety level and the target angle includes: The maximum rotational speed is determined based on the aforementioned driving safety level; The target rotation speed is determined based on the maximum rotation speed, the current screen angle, and the target angle.

[0134] Specifically, since the driving safety level is closely related to the safety of the driving state, different maximum rotational speeds need to be limited under different driving safety levels to ensure driving safety. Therefore, determining the maximum rotational speed based on the driving safety level includes: In response to the driving safety level being set to prohibit rotation and reset, the maximum rotation speed is determined to be a preset maximum rotation speed; Alternatively, in response to the driving safety level being set to prohibit rotation and adjusting the level, the maximum rotation speed is determined to be a preset minimum rotation speed; Alternatively, in response to the driving safety level being a level that allows slow rotation, the maximum rotation speed is determined to be a first preset speed; Alternatively, in response to the driving safety level being a level that allows for slightly slower rotation, the maximum rotation speed is determined to be a second preset speed; Alternatively, in response to the driving safety level being a permissible normal rotation level, the maximum rotation speed is determined to be a preset normal speed; The preset minimum rotational speed, the first preset speed, the second preset speed, the preset normal high speed, and the preset maximum rotational speed increase sequentially. For example, the second preset speed can be half of the preset normal speed, and the first preset speed can be half of the second preset speed.

[0135] That is, when the driving safety level is the prohibited rotation and reset level, the corresponding maximum rotation speed is the preset maximum speed. This is because the driving state at this time is very unsafe. Therefore, in order to ensure driving safety, the screen needs to be immediately reset to the default position at the preset maximum speed to ensure that the position of the screen does not affect driving safety.

[0136] When the driving safety level is set to prohibit rotation and adjust level, the corresponding maximum rotation speed is the preset minimum rotation speed. This is because the driving state at this time is unsafe, but not urgent. Therefore, in order to ensure driving safety and take into account the driver's driving experience, the screen is slowly reset to the default position at the preset minimum rotation speed. This ensures safety without reducing the driver's user experience due to excessively fast screen rotation.

[0137] When the driving safety level is the level that allows slow rotation, the corresponding maximum rotation speed is the first preset speed, which is a slightly slower speed. This is because the driving state at this time is relatively safe, but not absolutely safe. Therefore, the rotation speed of the screen should be slow to ensure safety.

[0138] When the driving safety level is the level that allows slightly slower rotation, the corresponding maximum rotation speed is the second preset speed, which is a relatively fast but slow speed. This is because the driving state is safer at this time. At this time, the screen can be rotated and the rotation speed can be appropriately increased so as to rotate the screen to the designated position as soon as possible while ensuring safety.

[0139] When the driving safety level is the level that allows normal rotation, the corresponding maximum rotation speed is the preset normal speed. This is because the driving state is very safe at this time, and the screen can be rotated quickly so as to rotate the screen to the designated position as soon as possible while ensuring safety.

[0140] To ensure safety during screen rotation and prevent it from affecting vehicle driving safety, this application further enhances the smoothness of screen rotation, allowing the screen to rotate more smoothly to the target angle, thereby improving the user experience. Therefore, based on the maximum rotation speed, the current screen angle, and the target angle, a target rotation speed needs to be determined to achieve the optimal rotation speed while ensuring safety.

[0141] In this application, when determining the target rotation speed, not only are safety factors considered and the maximum rotation speed is limited, but also the user experience is considered. Therefore, the target rotation speed is determined based on the maximum rotation speed, the current screen angle, and the target angle, so that the determined target rotation speed is more in line with the actual situation of the vehicle, ensuring safety when rotating the screen and improving the user experience.

[0142] In some embodiments, determining the target rotation speed based on the maximum rotation speed, the current screen angle, and the target angle includes: The absolute value of the difference between the target angle and the current screen angle is determined as the first difference; The ratio of the first difference to the preset adjustment parameter is determined as the smooth rotation speed; The smaller of the smooth rotational speed and the maximum rotational speed is determined as the target rotational speed.

[0143] Specifically, the absolute value of the difference between the target angle and the current screen angle is determined as a first difference, which characterizes the magnitude of the difference between the current screen angle and the target angle. Then, the ratio of the first difference to a preset adjustment parameter is determined as the smooth rotation speed. The preset adjustment parameter is a preset parameter used to adjust the smooth rotation; for example, the preset adjustment parameter can be 2 or 3.

[0144] The smaller of the smoothed rotation speed and the maximum rotation speed is determined as the target rotation speed. For example, if the smoothed rotation speed is less than the maximum rotation speed, then the smoothed rotation speed is determined as the target rotation speed; if the smoothed rotation speed is greater than the maximum rotation speed, then the maximum rotation speed is determined as the target rotation speed; if the smoothed rotation speed is equal to the maximum rotation speed, then either the maximum rotation speed or the smoothed rotation speed is determined as the target rotation speed.

[0145] In this application, the final target rotation speed is determined to meet the requirements of rotation safety without being too high, thereby enabling the screen to rotate smoothly under safe and fast conditions, thus improving the user experience.

[0146] In some embodiments, after the vehicle screen is rotated to the target angle at the target rotation speed, the method further includes: Obtain vehicle's upcoming driving data; The next driving scenario for the vehicle and the distance the vehicle is traveling from the next driving scenario are determined based on the upcoming driving data. Determine the reference angle for the next driving scenario based on the next driving scenario; In response to the fact that the category difference between the next driving scenario and the current driving scenario is greater than or equal to a preset difference, and the driving distance is less than or equal to a preset distance, the vehicle screen is controlled to rotate to the reference angle of the next scenario.

[0147] Specifically, after the vehicle screen rotates to the target angle at the target rotation speed, vehicle driving data is acquired as the vehicle continues to travel. This driving data refers to the relevant data of the route the vehicle will take next on its current driving trajectory. The driving data can be obtained based on navigation information or image information of the surrounding environment acquired by the vehicle's camera. For example, the driving data may include the road to be traveled, the environment to be traveled, and the speed limit to be reached.

[0148] Based on the upcoming driving data, the next driving scenario for the vehicle and the distance the vehicle is traveling from the next driving scenario are determined. For example, if the upcoming driving data includes a tunnel environment, then the next driving scenario is determined to be a tunnel scenario. If the upcoming driving data includes rural roads, then the next driving scenario is determined to be a rural road scenario.

[0149] The distance of the vehicle from the next driving scenario can also be determined based on driving data, such as determining the distance of the vehicle from the next driving scenario based on navigation information.

[0150] After determining the next driving scenario, the reference angle for the next scenario is determined based on the next driving scenario. This process is the same as the process of "determining the reference angle for the current scenario based on the current driving scenario", and will not be described in detail here.

[0151] Next, the category difference between the next driving scenario and the current driving scenario is determined. In historical testing, a category difference was set for each pair of driving scenarios; this category difference characterizes the degree of difference between the two scenarios. When the category difference is greater than or equal to a preset difference, it indicates a significant difference between the two driving scenarios, thus requiring pre-adjustment of the screen angle to better adapt to the next driving scenario. When the category difference is less than the preset difference, it indicates a less significant difference between the two driving scenarios, thus requiring no pre-adjustment of the screen angle.

[0152] The preset difference is a difference benchmark pre-set based on historical testing experience.

[0153] Therefore, when the category difference between the next driving scenario and the current driving scenario is greater than or equal to a preset difference, and the driving distance is less than or equal to a preset distance, it indicates that the difference between the next driving scenario and the current driving scenario is significant, and the driving distance for the vehicle to enter the next driving scenario is relatively short. In this case, the in-vehicle screen can be rotated to the reference angle of the next scenario. That is, before the vehicle enters the next driving scenario, the in-vehicle screen is rotated to the reference angle of the next scenario in advance, so that the in-vehicle screen can be adapted to the significantly changed next driving scenario in advance, solving the problem of inconsistency in use caused by the screen angle remaining unchanged due to a sudden change in scenario.

[0154] Furthermore, the process of determining whether to rotate the in-vehicle screen to the reference angle corresponding to the next driving scenario based on the above steps involves very little computation, making it easy to adjust the screen quickly and simply, thereby improving the user experience.

[0155] For example, if it is predicted that the vehicle is about to enter a tunnel (when the light will drop sharply), the screen angle is adjusted in advance to reduce glare; if it is predicted that a parking operation is about to be performed (when the vehicle speed will decrease and the steering wheel angle will increase), the screen angle is adjusted in advance to make it easier to observe the surrounding environment; if it is predicted that the destination is about to be reached (when navigation is about to end), the screen angle is adjusted in advance to make it easier to view parking information.

[0156] In this application, before the vehicle is about to enter the next driving scenario that is significantly different from the current driving scenario, the in-vehicle screen is rotated to the reference angle of the next driving scenario in advance, so that the in-vehicle screen can be adapted to the next driving scenario that has changed significantly in advance, thus solving the problem of inconsistency in use caused by the screen angle not changing due to the sudden change of scenario.

[0157] In some embodiments, the method further includes: In response to the vehicle entering the next driving scenario, real-time data information of the vehicle is acquired; The scene correction angle is determined based on the next scene reference angle and the real-time data information; The target angle of the scene is determined based on the next scene reference angle and the scene correction angle. The scene rotation speed is determined based on the real-time data information and the scene target angle. Control the in-vehicle screen to rotate to the target angle of the scene at the scene rotation speed.

[0158] Specifically, when the vehicle enters the next driving scenario, real-time data information of the vehicle is obtained. The content of the real-time data information is the same as the data category of the vehicle-related data, which will not be elaborated here.

[0159] Then, the scene correction angle is determined based on the next scene reference angle and the real-time data information. This process is almost the same as the process of "determining the current correction angle based on the current scene reference angle, the vehicle-related data and the driving safety level", and will not be described in detail here.

[0160] Then, the sum of the next scene reference angle and the scene correction angle is determined as the scene target angle.

[0161] Then, the scene rotation speed is determined based on the real-time data information and the scene target angle. This process is almost the same as the process of "determining the target rotation speed based on the driving safety level and the target angle", and will not be described in detail here.

[0162] Finally, control the in-vehicle screen to rotate to the target angle of the scene at the scene rotation speed.

[0163] Thus, in this application, before the vehicle is about to enter the next driving scenario that is significantly different from the current driving scenario, the in-vehicle screen is rotated to the reference angle of the next driving scenario in advance, so as to quickly adjust the angle of the in-vehicle screen and make the in-vehicle screen adaptable to the next driving scenario that has changed significantly in advance, thus solving the problem of inconsistency in use caused by the screen angle not changing due to the sudden change of scenario.

[0164] Then, after the vehicle enters the next driving scenario, the target angle of the scenario that is more in line with the actual situation is determined based on the real-time data information actually acquired. The in-vehicle screen is then rotated to the target angle of the scenario so that the final angle of the in-vehicle screen is more in line with the actual situation and more accurate.

[0165] That is, the in-vehicle screen rotates twice. The first rotation is a quick rotation to the reference angle of the next scene, and then a lot of fine calculations are performed to finally rotate to a more accurate target angle of the scene. The first rotation can meet the needs of rapid adjustment, and the second rotation can meet the needs of accuracy and adaptability.

[0166] In some embodiments, see Figure 5 It can perform personalized learning optimization regularly, and continuously optimize the user's personalized model through reinforcement learning.

[0167] Step 1: Learning Data Collection The system continuously collects the following user data: User's manual screen angle adjustment operation records in different scenarios.

[0168] User satisfaction feedback on different rotation angles (through implicit feedback such as voice, gestures, and facial expressions).

[0169] User driving habit data (such as typical driving speed, frequently traveled routes, and usage time periods).

[0170] Users' personal preferences (such as preference to look at the driver, preference to look at the passenger seat, preference to be in the center, etc.).

[0171] Step 2: Personalized Model Building A reinforcement learning algorithm is used, with user satisfaction as the reward signal, to optimize the weight coefficients of the user personalization model.

[0172] The reinforcement learning model employs a deep Q-network (DQN) architecture: State space: Scene feature vector S and user preference feature vector U Action space: The set of weight coefficients W = {w1user, w2user, ..., wk_user} in the user personalization model, where w1user, w2user, ..., wk_user are the weight coefficients corresponding to each user.

[0173] Reward function: User satisfaction (Reward).

[0174] Reward function design: Reward = α1×Retention_Time - α2×Manual_Adjust_Frequency + α3×User_Feedback_Score, where α1, α2, and α3 are reward coefficients obtained based on historical tests. For example, α1=0.5, α2=0.3, and α3=0.2.

[0175] Among them, Retention_Time is the duration (in seconds) that the user stays at the current angle, Manual_Adjust_Frequency is the frequency of manual adjustment by the user (times / hour), and User_Feedback_Score is the user feedback score (voice evaluation, facial expression recognition, 0-100 points).

[0176] Model update mechanism: The system collects new data periodically (e.g., daily) and uses online learning algorithms to update the personalized model. Update model parameters: User_Model = User_Model + α×Reward× User_Model, where α is the learning rate (exemplarily 0.01), and User_Model is the set of parameters of the existing model, representing the system's understanding of user habits and preferences. `User_Model` is the gradient vector of the model parameters, representing the partial derivatives of the model parameters with respect to the objective function. It indicates how the model parameters should be adjusted to improve performance. The gradient vector points in the direction of the fastest growth of the objective function and is commonly used in machine learning to find the minimum (or maximum) value of the objective function. In online learning, we use gradients to adjust model parameters so that the model can better fit new data. The objective function is a pre-defined loss function.

[0177] Furthermore, different weights can be applied to different users and their preferences, thereby training a more accurate user personalization model.

[0178] In addition, user feedback can be collected to optimize scene recognition and personalization models. For example, it can record whether the user manually adjusted the angle and the adjustment range, and record the user's satisfaction with the current angle. This feedback data can then be sent to the personalized learning module for model updates.

[0179] In some embodiments, see continue to see Figure 5 It can predict the next driving scenario based on the model.

[0180] Specifically, Long Short-Term Memory (LSTM) networks can be used to predict scene changes in the next 10-30 seconds.

[0181] Prediction model input: Time series of multi-source data over the past Δt time period (e.g., vehicle-related data over the past 60 seconds). Current scene feature vector S; Navigation route information (road type ahead, intersection information, distance to destination).

[0182] Predictive model architecture: Long Short-Term Memory (LSTM) network is used as the time series prediction model: Scene_Future = LSTM_Predictor(Scene_Sequence, 10-30s), where Scene_Sequence is the scene sequence data of the past 30 seconds.

[0183] The LSTM network consists of 2-3 layers, with 128-256 hidden units per layer. The model input is a time series data sequence X = [x(t-Δt), x(t-Δt+1), ..., x(t)], where the input vector x at each time step contains features from multiple data sources.

[0184] Prediction model output: Predict scene categories P_predict = [p1, p2, ..., pn]; The predicted scene feature vector is S_predict = [s1, s2, ..., sm]. Scene change trend Trend = [t1, t2, ..., tk].

[0185] Scene change detection: Calculate the Euclidean distance between the predicted scene feature vector and the current scene feature vector: D = ||S_predict - S||_2, where S_predict is the predicted scene feature vector and S is the current scene feature vector. When D exceeds a preset change threshold ΔP_threshold (e.g., 0.3), it is determined that the scene will change significantly, triggering a pre-adjustment mechanism.

[0186] Pre-adjustment strategy: When a significant change in the scene is predicted, the screen angle is adjusted in advance to match the screen state with the predicted scene. The advance time t_advance for pre-adjustment is dynamically adjusted according to the severity of the prediction.

[0187] Pre-adjustment trigger conditions: The change in the confidence level of the predicted scene category exceeds a threshold (e.g., 0.3). The Euclidean distance between the predicted scene and the current scene exceeds a threshold (e.g., 0.3). High-risk scenarios were predicted to emerge.

[0188] In some embodiments, security prompts and exception handling can also be provided: When the driving safety level is set to the "no rotation" level, a safety warning can be issued to the user: Voice prompt: "The current driving environment is complex. We recommend that you temporarily adjust the screen angle." Screen flickering: A yellow warning light flashes at the edge of the screen; Touch feedback: Touchscreen vibration alert.

[0189] Exception handling mechanism: Sensor failure: When data from a certain type of sensor is abnormal, reduce the weight of that type of data and increase the weight of other data.

[0190] Missing data: When a certain type of data is missing, historical data or default values ​​are used to fill the gap.

[0191] Angle Exceeds Limit: When the calculated angle exceeds the hardware limit, the calculation is truncated to the nearest boundary value.

[0192] Rotation fault: When the rotation mechanism malfunctions, a fault alarm is issued and an attempt is made to reset it.

[0193] This application significantly improves the accuracy and intelligence of scene recognition, achieving a technological leap from "signal level classification" to "multi-level scene understanding". The basic scene classifier can identify major categories of scenes such as driving, entertainment, navigation, and safety. The refined scene understander can further identify sub-scenes under each major category (such as normal cruising on highways, overtaking and changing lanes, following in traffic jams, and rainy / foggy weather). The scene semantic parser can extract semantic information such as driver attention, interaction intent, and scene priority.

[0194] Establish a driving safety assessment mechanism to ensure driving safety is a priority. This mechanism utilizes a four-dimensional driving safety assessment system (driving risk index, driver state index, traffic environment index, and vehicle state index) to comprehensively evaluate driving safety conditions and calculate a driving safety level as a prerequisite for rotation decisions. When the driving safety level is below a threshold (e.g., 0.7), rotation actions are prohibited or a safety warning is issued to the user, effectively reducing the risk of driver distraction.

[0195] To achieve predictive control and enhance user experience smoothness, the system predicts scene changes 10-30 seconds in advance based on historical data and current state, adjusting the screen angle accordingly for a seamless user experience. For example, when it predicts a vehicle is about to enter a tunnel, the screen angle is adjusted in advance to reduce glare; when it predicts an upcoming parking maneuver, the screen angle is adjusted in advance to facilitate observation of the surrounding environment.

[0196] A personalized learning model is constructed to achieve a unique control strategy for each user. This is achieved through reinforcement learning algorithms that continuously learn user behavior patterns and optimize strategies based on user satisfaction as a reward signal. The system collects data on user manual adjustments, satisfaction feedback, driving habits, and personal preferences to build a personalized user model.

[0197] Through multi-factor dynamic angle calculation, refined control is achieved. The target angle is obtained by using a multi-factor angle correction method, and the optimal angle is calculated by comprehensively considering multiple factors such as scenario, safety, user, environment, and smooth transition.

[0198] Make full use of multi-source sensor data to improve data utilization. Collect five categories of multi-source sensor data: driving status, environmental perception, user behavior, vehicle status, and cabin environment. Use timestamp synchronization and data cleaning technology for preprocessing to construct multi-dimensional feature vectors for scene recognition and decision-making.

[0199] Closed-loop control ensures rotational accuracy and stability. A PID closed-loop control system can be used, with real-time feedback of the actual angle from an angle sensor, dynamically adjusting the control output to achieve precise rotation. The rotational speed is dynamically adjusted based on the angle difference, with a maximum speed limit of 10° / second to prevent discomfort caused by excessively fast rotation.

[0200] The system's robustness is enhanced. The multi-source data fusion and outlier handling mechanism enable the system to maintain an accuracy rate of over 85% even in the event of sensor failure or data loss, which is 60% more robust than the single signal source solution.

[0201] It should be noted that the method in this embodiment can be executed by a single device, such as a computer or server. The method can also be applied in a distributed scenario, where multiple devices cooperate to complete the task. In such a distributed scenario, one of these devices may execute only one or more steps of the method in this embodiment, and the multiple devices will interact with each other to complete the method described.

[0202] It should be noted that some embodiments of this application have been described above. In some cases, the actions or steps described in the above embodiments can be performed in a different order than that shown in the above embodiments and the desired result can still be achieved. In addition, the processes depicted in the accompanying drawings do not necessarily require a specific or sequential order to achieve the desired result. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0203] Based on the same inventive concept, and corresponding to any of the above embodiments, this application also provides a vehicle screen rotation control device.

[0204] refer to Figure 6 The vehicle-mounted screen rotation control device includes: The acquisition module 100 is configured to acquire vehicle-related data and determine the driving safety level and current driving scenario based on the vehicle-related data. Angle determination module 200 is configured to determine the target angle based on the vehicle-related data, the current driving scenario, and the driving safety level. The speed determination module 200 is configured to determine the target rotation speed based on the driving safety level and the target angle; The control module 400 is configured to control the vehicle screen to rotate to the target angle at the target rotation speed.

[0205] In some embodiments, the acquisition module 100 is further configured to: Based on the vehicle-related data, a driving risk index, a driver status index, a traffic environment index, and a vehicle status index are determined. The driving safety index is determined based on the driving risk index, driver status index, traffic environment index, and vehicle status index. The driving safety level is determined based on the driving safety index.

[0206] In some embodiments, the driving safety level includes a no-rotation level or a rotation-permitted level.

[0207] In some embodiments, the angle determination module 200 is further configured to: In response to the driving safety level being a no-rotation level, the preset default angle is determined as the target angle; In response to the driving safety level being a permissible rotation level, a current scene reference angle is determined based on the current driving scenario; a current correction angle is determined based on the current scene reference angle, the vehicle-related data, and the driving safety level; and a target angle is determined based on the current scene reference angle and the current correction angle.

[0208] In some embodiments, the vehicle-related data includes driver identification information, light intensity, noise information, current ambient temperature, and current screen angle.

[0209] In some embodiments, the angle determination module 200 is further configured to: Determine the safety correction angle based on the aforementioned driving safety level; Based on the driver's identity information and preset driver preference information, the driver's correction angle is determined; Based on the light intensity, noise information, and current ambient temperature, determine the environmental correction angle; Based on the current scene reference angle, safety correction angle, driver correction angle, environment correction angle, and current screen angle, determine the smooth correction angle; The sum of the safety correction angle, driver correction angle, environmental correction angle, and smoothness correction angle is determined as the current correction angle.

[0210] In some embodiments, the vehicle-related data includes the current screen angle.

[0211] In some embodiments, the speed determination module 200 is further configured to: The maximum rotational speed is determined based on the aforementioned driving safety level; The target rotation speed is determined based on the maximum rotation speed, the current screen angle, and the target angle.

[0212] In some embodiments, the speed determination module 200 is further configured to: The absolute value of the difference between the target angle and the current screen angle is determined as the first difference; The ratio of the first difference to the preset adjustment parameter is determined as the smooth rotation speed; The smaller of the smooth rotational speed and the maximum rotational speed is determined as the target rotational speed.

[0213] In some embodiments, the control module 400 is further configured to: Obtain vehicle's upcoming driving data; The next driving scenario for the vehicle and the distance the vehicle is traveling from the next driving scenario are determined based on the upcoming driving data. Determine the reference angle for the next driving scenario based on the next driving scenario; In response to the fact that the category difference between the next driving scenario and the current driving scenario is greater than or equal to a preset difference, and the driving distance is less than or equal to a preset distance, the vehicle screen is controlled to rotate to the reference angle of the next scenario.

[0214] In some embodiments, the control module 400 is further configured to: In response to the vehicle entering the next driving scenario, real-time data information of the vehicle is acquired; The scene correction angle is determined based on the next scene reference angle and the real-time data information; The target angle of the scene is determined based on the next scene reference angle and the scene correction angle. The scene rotation speed is determined based on the real-time data information and the scene target angle. Control the in-vehicle screen to rotate to the target angle of the scene at the scene rotation speed.

[0215] For ease of description, the above devices are described in terms of function, divided into various modules. Of course, in implementing this application, the functions of each module can be implemented in one or more software and / or hardware.

[0216] The apparatus described above is used to implement the corresponding vehicle screen rotation control method in any of the foregoing embodiments, and has the beneficial effects of the corresponding method embodiments, which will not be repeated here.

[0217] Based on the same inventive concept, corresponding to the methods of any of the above embodiments, this application also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the vehicle screen rotation control method described in any of the above embodiments.

[0218] Figure 7 This embodiment illustrates a more specific hardware structure of an electronic device. The device may include a processor 1010, a memory 1020, an input / output interface 1030, a communication interface 1040, and a bus 1050. The processor 1010, memory 1020, input / output interface 1030, and communication interface 1040 are interconnected internally via the bus 1050.

[0219] The processor 1010 can be implemented using a general-purpose CPU (Central Processing Unit), microprocessor, application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of this specification.

[0220] The memory 1020 can be implemented in the form of ROM (Read Only Memory), RAM (Random Access Memory), static storage device, dynamic storage device, etc. The memory 1020 can store the operating system and other applications. When the technical solutions provided in the embodiments of this specification are implemented by software or firmware, the relevant program code is stored in the memory 1020 and is called and executed by the processor 1010.

[0221] The input / output interface 1030 is used to connect input / output modules to realize information input and output. Input / output modules can be configured as components within the device (not shown in the figure) or externally connected to the device to provide corresponding functions. Input devices may include keyboards, mice, touchscreens, microphones, various sensors, etc., while output devices may include displays, speakers, vibrators, indicator lights, etc.

[0222] The communication interface 1040 is used to connect a communication module (not shown in the figure) to enable communication between this device and other devices. The communication module can communicate via wired means (such as USB, Ethernet cable, etc.) or wireless means (such as mobile network, WIFI, Bluetooth, etc.).

[0223] Bus 1050 includes a pathway for transmitting information between various components of the device, such as processor 1010, memory 1020, input / output interface 1030, and communication interface 1040.

[0224] It should be noted that although the above-described device only shows the processor 1010, memory 1020, input / output interface 1030, communication interface 1040, and bus 1050, in specific implementations, the device may also include other components necessary for normal operation. Furthermore, those skilled in the art will understand that the above-described device may only include the components necessary for implementing the embodiments of this specification, and not necessarily all the components shown in the figures.

[0225] The electronic devices described above are used to implement the corresponding vehicle screen rotation control methods in any of the foregoing embodiments, and have the beneficial effects of the corresponding method embodiments, which will not be repeated here.

[0226] Based on the same inventive concept, corresponding to the methods of any of the above embodiments, this application also provides a non-transitory computer-readable storage medium that stores computer instructions for causing the computer to execute the vehicle screen rotation control method as described in any of the above embodiments.

[0227] The computer-readable medium of this embodiment includes permanent and non-permanent, removable and non-removable media, and information storage can be implemented by any method or technology. Information can be computer-readable instructions, data structures, program modules, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transfer medium that can be used to store information accessible by a computing device.

[0228] The computer instructions stored in the storage medium of the above embodiments are used to cause the computer to execute the vehicle screen rotation control method as described in any of the above embodiments, and have the beneficial effects of the corresponding method embodiments, which will not be repeated here.

[0229] Based on the same inventive concept, corresponding to any of the above embodiments, this application also provides a computer program product, including computer program instructions. When the computer program instructions are run on a computer, the computer causes the computer to execute the vehicle screen rotation control method as described in any of the above embodiments, which has the beneficial effects of the corresponding method embodiments, and will not be repeated here.

[0230] Based on the same inventive concept, and corresponding to the methods of any of the above embodiments, this application also provides a vehicle, which includes the in-vehicle screen rotation control device, electronic device, computer-readable storage medium, or computer program product described in any of the above embodiments. The vehicle possesses the technical effects corresponding to any of the above embodiments, which will not be elaborated further here.

[0231] It is understood that before using the technical solutions of the various embodiments in this application, users will be informed of the type, scope of use, and usage scenarios of the personal information involved in an appropriate manner, and user authorization will be obtained.

[0232] For example, upon receiving a user's active request, a prompt message is sent to the user to explicitly inform them that the requested operation will require the acquisition and use of the user's personal information. This allows the user to independently choose, based on the prompt message, whether to provide personal information to the software or hardware such as electronic devices, applications, servers, or storage media performing the operations described in this application.

[0233] As an optional but not limited implementation, in response to a user's active request, sending a prompt message to the user can be done via a pop-up window, where the prompt message can be presented in text format. Furthermore, the pop-up window can also include a selection control allowing the user to choose "agree" or "disagree" to provide personal information to the electronic device.

[0234] It is understood that the above notification and user authorization process is merely illustrative and does not limit the implementation of this application. Other methods that comply with relevant laws and regulations may also be applied to the implementation of this application.

[0235] Those skilled in the art should understand that the discussion of any of the above embodiments is merely exemplary and is not intended to imply that the scope of this application is limited to these examples; under the concept of this application, the technical features of the above embodiments or different embodiments can also be combined, the steps can be implemented in any order, and there are many other variations of different aspects of the embodiments of this application as described above, which are not provided in detail for the sake of brevity.

[0236] Additionally, to simplify the description and discussion, and to avoid obscuring the embodiments of this application, the well-known power / ground connections to integrated circuit (IC) chips and other components may or may not be shown in the provided drawings. Furthermore, the apparatus may be shown in block diagram form to avoid obscuring the embodiments of this application, and this also takes into account the fact that the details of the implementation of these block diagram apparatuses are highly dependent on the platform on which the embodiments of this application will be implemented (i.e., these details should be fully understood by those skilled in the art). While specific details (e.g., circuits) have been set forth to describe exemplary embodiments of this application, it will be apparent to those skilled in the art that the embodiments of this application can be implemented without these specific details or with variations thereof. Therefore, these descriptions should be considered illustrative rather than restrictive.

[0237] Although this application has been described in conjunction with specific embodiments thereof, many substitutions, modifications, and variations of these embodiments will be apparent to those skilled in the art from the foregoing description. For example, other memory architectures (e.g., dynamic RAM (DRAM)) may be used with the embodiments discussed.

[0238] The embodiments of this application are intended to cover all such substitutions, modifications, and variations that fall within the broad scope of this application. Therefore, any omissions, modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the embodiments of this application should be included within the protection scope of this application.

Claims

1. A method for controlling the rotation of an in-vehicle screen, characterized in that, include: Acquire vehicle-related data and determine the driving safety level and current driving scenario based on the vehicle-related data; The target angle is determined based on the vehicle-related data, the current driving scenario, and the driving safety level. Based on the driving safety level and the target angle, determine the target rotation speed; Control the vehicle screen to rotate to the target angle at the target rotation speed.

2. The method according to claim 1, characterized in that, The method of determining the driving safety level based on vehicle-related data includes: Based on the vehicle-related data, a driving risk index, a driver status index, a traffic environment index, and a vehicle status index are determined. The driving safety index is determined based on the driving risk index, driver status index, traffic environment index, and vehicle status index. The driving safety level is determined based on the driving safety index.

3. The method according to claim 1, characterized in that, The driving safety level includes a prohibited rotation level or a permitted rotation level; Determining the target angle based on the vehicle-related data, the current driving scenario, and the driving safety level includes: In response to the driving safety level being a no-rotation level, the preset default angle is determined as the target angle; In response to the driving safety level being a permissible rotation level, a current scene reference angle is determined based on the current driving scenario; a current correction angle is determined based on the current scene reference angle, the vehicle-related data, and the driving safety level; and a target angle is determined based on the current scene reference angle and the current correction angle.

4. The method according to claim 3, characterized in that, The vehicle-related data includes driver identity information, light intensity, noise information, current ambient temperature, and current screen angle; The process of determining the current correction angle based on the current scene reference angle, the vehicle-related data, and the driving safety level includes: Determine the safety correction angle based on the aforementioned driving safety level; Based on the driver's identity information and preset driver preference information, the driver's correction angle is determined; Based on the light intensity, noise information, and current ambient temperature, determine the environmental correction angle; Based on the current scene reference angle, safety correction angle, driver correction angle, environment correction angle, and current screen angle, determine the smooth correction angle; The sum of the safety correction angle, driver correction angle, environmental correction angle, and smoothness correction angle is determined as the current correction angle.

5. The method according to claim 1, characterized in that, The vehicle-related data includes the current screen angle; Determining the target rotation speed based on the driving safety level and the target angle includes: The maximum rotational speed is determined based on the aforementioned driving safety level; The target rotation speed is determined based on the maximum rotation speed, the current screen angle, and the target angle.

6. The method according to claim 5, characterized in that, Determining the target rotation speed based on the maximum rotation speed, the current screen angle, and the target angle includes: The absolute value of the difference between the target angle and the current screen angle is determined as the first difference; The ratio of the first difference to the preset adjustment parameter is determined as the smooth rotation speed; The smaller of the smooth rotational speed and the maximum rotational speed is determined as the target rotational speed.

7. The method according to claim 1, characterized in that, After the vehicle control screen rotates to the target angle at the target rotation speed, the process further includes: Obtain vehicle's upcoming driving data; The next driving scenario for the vehicle and the distance the vehicle is traveling from the next driving scenario are determined based on the upcoming driving data. Determine the reference angle for the next driving scenario based on the next driving scenario; In response to the fact that the category difference between the next driving scenario and the current driving scenario is greater than or equal to a preset difference, and the driving distance is less than or equal to a preset distance, the vehicle screen is controlled to rotate to the reference angle of the next scenario.

8. The method according to claim 7, characterized in that, The method further includes: In response to the vehicle entering the next driving scenario, real-time data information of the vehicle is acquired; The scene correction angle is determined based on the next scene reference angle and the real-time data information; The target angle of the scene is determined based on the next scene reference angle and the scene correction angle. The scene rotation speed is determined based on the real-time data information and the scene target angle. Control the in-vehicle screen to rotate to the target angle of the scene at the scene rotation speed.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that, When the processor executes the computer program, it implements the method as described in any one of claims 1 to 8.

10. A vehicle, characterized in that, Includes the electronic device as described in claim 9.

Images