Vehicle cabin screen information display state adjusting method and device, medium and vehicle
By quantifying the driver's stress load index using multi-source sensors and machine learning algorithms, and dynamically adjusting the display status of the cabin screen, the problem of overly complex and distracting information on the cabin screen is solved, thus improving driving safety and experience.
Patent Information
- Application Number
- CN202511945072.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-12-22
- Publication Date
- 2026-03-03
Smart Images
Figure CN121597155A_ABST
Abstract
Description
Technical Field
[0001] This application belongs to the field of vehicle cockpit technology, and particularly relates to a method, device, medium and vehicle for adjusting the information display status of a vehicle cockpit screen. Background Technology
[0002] With the rapid development of automotive intelligence and connectivity, the functions of in-car screens have become increasingly diverse, expanding from traditional navigation and music playback to include social interaction, video conferencing, and streaming media playback, undoubtedly enhancing the driver's experience. However, this continuous addition of functions has also led to problems such as larger screen sizes, increased information density, and more complex menu hierarchies. This information-overloaded interface can significantly distract drivers, posing a potential threat to driving safety.
[0003] Therefore, improving driver safety has become an urgent technical problem to be solved. Summary of the Invention
[0004] The embodiments of this application provide a method, apparatus, computer program product, computer-readable storage medium, and vehicle for adjusting the information display status of a vehicle cabin screen, thereby improving the safety of the driver at least to a certain extent.
[0005] Other features and advantages of this application will become apparent from the following detailed description, or may be learned in part from practice of this application.
[0006] According to a first aspect of the present application, a method for adjusting the display state of information on a vehicle cabin screen is provided. The method includes: acquiring perception data of the driver in at least one state representation dimension among visual attention, physiological tension, and behavioral actions, collected by multi-source sensors in the vehicle cabin; performing fusion analysis on the perception data to quantify the perception data into a stress load index of the driver, the stress load index being used to characterize the driver's current level of attention resource occupancy; and dynamically adjusting the display state of the vehicle cabin screen in at least one display dimension among interface element layout, information presentation density, and menu hierarchy structure based on the stress load index, wherein the complexity of the display state is negatively correlated with the stress load index.
[0007] In some embodiments of this application, based on the foregoing scheme, the step of fusing and analyzing the perceived data to quantify the perceived data into the driver's stress load index includes: aligning the perceived data of at least one state representation dimension based on the timestamp when the perceived data was collected to obtain a set of perceived data corresponding to at least one timestamp; extracting at least one state feature value of the driver from the set of perceived data corresponding to each timestamp; and performing weighted fusion of the at least one state feature value using a machine learning algorithm to obtain the driver's stress load index.
[0008] In some embodiments of this application, based on the foregoing scheme, the step of weighted fusion of the at least one state feature value using a machine learning algorithm to obtain the driver's stress load index includes: using a one-dimensional convolutional neural network to extract the short-term dependency relationship between at least one state feature value corresponding to the same timestamp; learning the long-term evolution pattern of the same state feature value corresponding to at least one timestamp in the time series using a long short-term memory network; and combining the short-term dependency relationship and the long-term evolution pattern to determine the driver's stress load index.
[0009] In some embodiments of this application, based on the foregoing scheme, the method further includes: if one or more of the at least one state characteristic values exceed a preset state characteristic value threshold, then the upper limit value of the pressure load index is determined as the driver's pressure load index.
[0010] In some embodiments of this application, based on the foregoing scheme, the step of dynamically adjusting the display state of the cabin screen in at least one display dimension of interface element layout, information presentation density, and menu hierarchy structure based on the stress load index includes: obtaining at least two sequentially adjacent index intervals and determining the target index interval into which the stress load index falls; determining the driver's stress load level based on the interval number of the target index interval; and dynamically adjusting the display state of the cabin screen in at least one display dimension of interface element layout, information presentation density, and menu hierarchy structure based on the stress load level.
[0011] In some embodiments of this application, based on the foregoing scheme, obtaining at least two sequentially adjacent index intervals includes: obtaining the current driving environment data of the vehicle driven by the driver, and determining the endpoint values of the index intervals that match the driving environment data; and determining at least two sequentially adjacent index intervals based on the endpoint values of the index intervals.
[0012] In some embodiments of this application, based on the aforementioned scheme, the pressure load level includes a first level, a second level, and a third level, wherein the third level is greater than the second level, and the second level is greater than the first level. The step of dynamically adjusting the display state of the cabin screen in at least one display dimension—interface element layout, information presentation density, and menu hierarchy—based on the pressure load level includes: if the pressure load level is the first level, controlling the cabin screen to adopt a full display state, displaying all information and supporting deep-level menus; if the pressure load level is the second level, controlling the cabin screen to adopt a simplified display state, hiding low-priority information, reducing the display ratio of the passenger entertainment area to a first ratio of the screen width, and compressing the menu hierarchy to a mid-level menu; if the pressure load level is the third level, controlling the cabin screen to adopt a minimalist display state, displaying only high-priority information, reducing the display ratio of the passenger entertainment area to a second ratio of the screen width, and compressing the menu hierarchy to a low-level menu, where the second ratio is less than the first ratio.
[0013] According to a second aspect of the present application, a device for adjusting the display state of information on a vehicle cabin screen is provided. The device includes: an acquisition unit, configured to acquire perception data of the driver in at least one state representation dimension among visual attention, physiological tension, and behavioral actions, collected by multi-source sensors in the vehicle cabin; an analysis unit, configured to perform fusion analysis on the perception data to quantify the perception data into a stress load index of the driver, the stress load index being used to characterize the driver's current level of attention resource occupancy; and an adjustment unit, configured to dynamically adjust the display state of the vehicle cabin screen in at least one display dimension among interface element layout, information presentation density, and menu hierarchy structure based on the stress load index, wherein the complexity of the display state is negatively correlated with the stress load index.
[0014] According to a third aspect of the embodiments of this application, a computer program product is provided, the computer program product including computer instructions stored in a computer-readable storage medium and adapted to be read and executed by a processor to cause a computer device having the processor to perform an operation as described in any of the first aspects above.
[0015] According to a fourth aspect of the embodiments of this application, a computer-readable storage medium is provided, the computer-readable storage medium storing at least one computer program instruction, the at least one computer program instruction being loaded and executed by a processor to perform the operation as described in any of the first aspects above.
[0016] According to a fifth aspect of the embodiments of this application, a vehicle is provided, the vehicle including one or more processors and one or more memories, the one or more memories storing at least one computer program instruction, the at least one computer program instruction being loaded and executed by the one or more processors to perform the operation as described in any of the first aspects above.
[0017] Based on the technical solution proposed in this application, the safety of drivers can be improved to a certain extent. Specifically, firstly, by collecting perception data from at least one dimension of state representation through multi-source sensors, the driver's current state can be captured comprehensively and from multiple perspectives. Compared with single-dimensional data collection, this effectively avoids misjudgments of driver state caused by data bias, laying the foundation for the accurate quantification of the stress load index. Secondly, quantifying the perception data into a stress load index enables an intuitive and accurate representation of the driver's attention resource occupancy, solving the problem of difficulty in quantifying and assessing driver state in traditional methods, and providing a clear and operable basis for adjusting the display state. Finally, dynamically adjusting the screen display state based on the stress load index, with the display complexity being negatively correlated with the stress load index, ensures that the information presented on the screen is adapted to the driver's attention resources. When the driver's attention resources are abundant, rich information is provided to meet diverse needs; when the driver's attention resources are strained, information presentation is simplified to reduce attention distraction, fundamentally improving driving safety while also taking into account the functional diversity and user experience of the cabin screen.
[0018] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and do not limit this application. Attached Figure Description
[0019] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application. It is obvious that the drawings described below are merely some embodiments of this application, and those skilled in the art can obtain other drawings based on these drawings without any inventive effort. In the drawings: Figure 1 A flowchart illustrating the method for adjusting the display status of cabin screen information in an embodiment of this application is shown; Figure 2 A block diagram of an adjustment device for the display status of cabin screen information in an embodiment of this application is shown; Figure 3 A schematic diagram of the vehicle structure in an embodiment of this application is shown. Detailed Implementation
[0020] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.
[0021] Furthermore, the described features, structures, or characteristics can be combined in any suitable manner in one or more embodiments. Numerous specific details are provided in the following description to give a thorough understanding of embodiments of this application. However, those skilled in the art will recognize that the technical solutions of this application can be practiced without one or more of the specific details, or other methods, components, apparatuses, steps, etc., can be employed. In other instances, well-known methods, apparatuses, implementations, or operations are not shown or described in detail to avoid obscuring various aspects of this application.
[0022] The block diagrams shown in the accompanying drawings are merely functional entities and do not necessarily correspond to physically independent entities. That is, these functional entities can be implemented in software, in one or more hardware modules or integrated circuits, or in different network and / or processor devices and / or microcontroller devices. It should also be noted that, for the sake of simplicity, certain components in the drawings that do not affect the interpretation of the technical solution of this application have been appropriately omitted.
[0023] The flowchart shown in the attached diagram is for illustrative purposes only and does not necessarily include all content and operations / steps, nor does it necessarily have to be performed in the described order. For example, some operations / steps can be broken down, while others can be combined or partially combined. Therefore, the actual execution order may change depending on the actual situation.
[0024] In the description of this application, it should be understood that the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of this application, unless otherwise stated, "multiple" means two or more.
[0025] With the rapid development of automotive intelligence and connectivity, the functions of in-car screens have become increasingly diverse, expanding from traditional navigation and music playback to include social interaction, video conferencing, and streaming media playback, undoubtedly enhancing the driver's experience. However, this continuous addition of functions has also led to problems such as larger screen sizes, increased information density, and more complex menu hierarchies. This information-overloaded interface can significantly distract drivers, posing a potential threat to driving safety.
[0026] The inventors of this application have discovered that drivers have limited attentional resources while driving. When the information displayed on the vehicle's screen is too complex, drivers need to spend more time and energy sifting through a large amount of information to select key driving-related information, such as vehicle speed and navigation turn prompts. This causes drivers' visual attention to be shifted from the road environment to the vehicle's screen for extended periods, increasing "look-down time" and significantly increasing the risk of traffic accidents. For example, while driving on urban roads, if the vehicle's screen displays multiple pieces of information simultaneously, such as navigation maps, music playback interfaces, social media notifications, and vehicle status parameters, drivers may need to search through multiple interface elements when they need to check navigation turn prompts. During this process, they are very likely to overlook pedestrians or non-motorized vehicles at intersections ahead, leading to safety accidents. In this regard, this application proposes a scheme for adjusting the information display status of the vehicle's screen to improve driver safety.
[0027] Next, this application will elaborate on the proposed adjustment scheme for the display status of information on the vehicle cabin screens. (Refer to...) Figure 1 The flowchart illustrates a method for adjusting the display state of cabin screen information according to an embodiment of this application. This method for adjusting the display state of cabin screen information can be executed by a device with computing processing capabilities, such as... Figure 1 As shown, the method for adjusting the information display status of the cabin screen includes at least steps 110 to 130, which are detailed below: In step 110, the driver's perception data in at least one state representation dimension among visual attention, physiological tension, and behavioral actions is acquired by multi-source sensors in the vehicle cabin.
[0028] In step 120, the perceived data is fused and analyzed to quantify the perceived data into the driver's stress load index, which is used to characterize the driver's current level of attention resource utilization.
[0029] In step 130, based on the pressure load index, the display status of the cabin screen in at least one display dimension, including interface element layout, information presentation density, and menu hierarchy structure, is dynamically adjusted. The complexity of the display status is negatively correlated with the pressure load index.
[0030] In this application, the state representation dimensions may include at least one of three core dimensions: visual attention, physiological tension, and behavioral actions. These dimensions can comprehensively reflect the driver's current state and thus accurately determine the driver's attention resource usage.
[0031] The visual attention dimension focuses on the driver's visual behavior characteristics, such as gaze distribution and pupil changes. Visual attention data can be collected through a visual attention monitoring module, specifically including fixation point distribution data, pupil diameter change data, blink frequency data, and eye closure duration data. The physiological stress dimension focuses on the driver's internal physiological state, such as heart rate and skin conductivity. Physiological stress data is collected through a physiological stress monitoring module, specifically including heart rate data, heart rate variability data, and skin conductance response data. The behavioral action dimension focuses on the driver's external behavioral performance, such as grip strength and body posture. Behavioral action data is collected through a behavioral action recognition module, specifically including steering wheel grip strength data, steering wheel micro-operation data, and driver body posture data. In this application, collecting perception data from at least one dimension using multi-source sensors avoids the one-sidedness of single-dimensional data and provides data support for the accurate quantification of the subsequent stress load index.
[0032] In this application, the stress load index is a quantitative representation of the degree of driver attention resource occupancy. Its value directly reflects how much attention resource the driver can currently allocate to receiving information from the cabin screens. For example, a stress load index of 0.2 indicates that the driver's attention resources are relatively abundant and can receive a lot of screen information; a stress load index of 0.8 indicates that the driver's attention resources are highly occupied and can only receive a small amount of key information.
[0033] In this application, the complexity of the displayed state is negatively correlated with the pressure load index; that is, the higher the pressure load index, the lower the complexity of the displayed state on the cabin screen, and vice versa. This dynamic correlation ensures that the information presented on the cabin screen matches the driver's attentional resources.
[0034] For example, in a specific scenario, when a driver is cruising smoothly on a highway, visual attention sensors (such as infrared eye trackers) in the vehicle cabin collect data showing that the driver's gaze is mainly focused on the road ahead, with low frequency and short duration of eye contact with the cabin screen (visual attention dimension perception data); physiological sensors (such as a steering wheel capacitive heart rate sensor) collect data showing that the driver's heart rate is stable and heart rate variability is normal (physiological tension dimension perception data); and behavioral motion sensors (such as a steering wheel pressure sensor) collect data showing that the driver's grip is even and there are no frequent steering wheel fine-tuning movements (behavioral motion dimension perception data). After fusing and analyzing these perception data, a pressure load index of 0.2 (low load) is obtained. At this time, the cabin screen adopts a more complex display state, fully displaying navigation maps, music playback interfaces, vehicle fuel consumption information, social media notifications, etc., supporting deep menu operations to meet the driver's information acquisition needs.
[0035] For example, in another specific scenario, when a driver is driving in congested urban traffic, the visual attention sensor detects that the driver's gaze frequently switches between the road ahead, the in-vehicle screen, and surrounding vehicles, with relatively long single periods of focusing on the in-vehicle screen (visual attention dimension perception data); the physiological sensor detects that the driver's heart rate is elevated and heart rate variability is reduced (physiological stress dimension perception data); and the behavioral motion sensor detects that the driver's grip strength is increased and frequent micro-adjustments to the steering wheel (behavioral motion dimension perception data). After fusion analysis, the stress load index is found to be 0.7 (high load). At this time, the in-vehicle screen automatically reduces the complexity of the display, retaining only key information such as navigation arrows, current speed, and traffic congestion warnings, while hiding non-critical information such as fuel consumption and social notifications, simplifying the menu hierarchy and reducing the driver's information processing burden.
[0036] Based on the technical solution proposed in this application, the safety of drivers can be improved to a certain extent. Specifically, firstly, by collecting perception data from at least one dimension of state representation through multi-source sensors, the driver's current state can be captured comprehensively and from multiple perspectives. Compared with single-dimensional data collection, this effectively avoids misjudgments of driver state caused by data bias, laying the foundation for the accurate quantification of the stress load index. Secondly, quantifying the perception data into a stress load index enables an intuitive and accurate representation of the driver's attention resource occupancy, solving the problem of difficulty in quantifying and assessing driver state in traditional methods, and providing a clear and operable basis for adjusting the display state. Finally, dynamically adjusting the screen display state based on the stress load index, with the display complexity being negatively correlated with the stress load index, ensures that the information presented on the screen is adapted to the driver's attention resources. When the driver's attention resources are abundant, rich information is provided to meet diverse needs; when the driver's attention resources are strained, information presentation is simplified to reduce attention distraction, fundamentally improving driving safety while also taking into account the functional diversity and user experience of the cabin screen.
[0037] Next, this application will provide a more detailed explanation of the various technical details in the above-mentioned scheme for adjusting the display status of information on the cabin screen.
[0038] In such Figure 1 In step 120, the fusion analysis of the perceived data to quantify the perceived data into the driver's stress load index can be performed according to steps 121 to 123 as follows: Step 121: Based on the timestamp of the sensing data when it was collected, align the sensing data of the at least one state representation dimension to obtain a set of sensing data corresponding to at least one timestamp.
[0039] Step 122: Extract at least one state feature value of the driver from the perception data set corresponding to each timestamp.
[0040] Step 123: The driver's stress load index is obtained by weighted fusion of the at least one state feature value through a machine learning algorithm.
[0041] In this application, considering the potential differences in acquisition frequency and response speed among multi-source sensors, the acquisition times of perception data representing different state dimensions may be asynchronous. Therefore, by aligning timestamps, perception data collected at the same time point from different dimensions can be categorized into a single perception data set. This ensures that subsequent feature extraction and fusion analysis are based on driver state data at the same time point, avoiding analysis errors caused by asynchronous data timing. For example, if a visual attention sensor collects data at a sampling rate of 100Hz and a physiological sensor collects data at a sampling rate of 250Hz, timestamp alignment can group visual attention data and physiological data at the same millisecond into a single perception data set.
[0042] In this application, state feature values are extracted from the sensing data set. Specifically, key parameters that reflect the driver's state are selected and calculated from the raw sensing data. Raw sensing data is usually quite complex, and direct fusion analysis is difficult and inefficient. State feature values, on the other hand, are a refinement and condensation of the raw data, which can accurately reflect the driver's state at a specific point in time.
[0043] For example, features extracted from visual attention data can include the interface fixation ratio, the standard deviation of saccade speed, the PERCLOS value, and the pupil diameter change rate. The interface fixation ratio is the ratio of the total time spent continuously focusing on the screen for a duration longer than a set time (e.g., 500ms) to the total time of the sampling window. The PERCLOS value is the proportion of time during which eyelid closure exceeds a set percentage (e.g., 80%). Similarly, features extracted from physiological tension data can include heart rate variability frequency domain analysis values and peak frequency of skin conductance response. The heart rate variability frequency domain analysis values can be low-frequency power (0.04 to 0.15 Hz) and high-frequency power (0.15 to 0.4 Hz). Furthermore, features extracted from behavioral motion data can include steering wheel micro-correction entropy, average grip pressure, and shoulder tilt angle variance. The steering wheel micro-correction entropy is the standard deviation of the steering wheel angle within a set time (e.g., 3 seconds).
[0044] In this application, a weighted fusion of state feature values is performed using a machine learning algorithm. Specifically, this involves using a machine learning algorithm to learn the weights of different state feature values on the driver's stress load, and then fusing the feature values according to these weights to obtain the final stress load index. Different state feature values contribute differently to stress load. For example, in emergency scenarios, behavioral action feature values (such as a sudden increase in grip strength) may have a higher weight; in fatigue driving scenarios, visual attention feature values (such as PERCLOS values) may have a higher weight. Automatically learning the weights through machine learning algorithms can improve the quantitative accuracy of the stress load index.
[0045] Based on the technical solutions in steps 121 to 123 above, aligning multi-dimensional sensing data using timestamps ensures that the data used for fusion analysis reflects driver status data from the same time point, effectively eliminating data analysis errors caused by asynchronous sensor sampling and improving the accuracy of stress load index quantification. Secondly, extracting state feature values from the sensing data set simplifies and refines the original complex data, highlighting key information reflecting driver status, reducing the computational complexity of subsequent fusion analysis, and improving data processing efficiency. Finally, using machine learning algorithms to weightedly fuse state feature values automatically learns the influence weights of different feature values on stress load. Compared to fixed-weight fusion methods, this approach is more adaptable to different driving scenarios and individual differences among drivers, further improving the quantification accuracy of the stress load index and providing a reliable guarantee for accurate adjustment of the displayed status.
[0046] Furthermore, in step 123 above, the step of weighted fusion of the at least one state feature value using a machine learning algorithm to obtain the driver's stress load index can be performed according to steps 1231 to 1233 as follows: Step 1231: Use a one-dimensional convolutional neural network (1D-CNN) to extract short-term dependencies between at least one state feature value corresponding to the same timestamp.
[0047] Step 1232: Learn the long-term evolution pattern of the same state feature value corresponding to at least one timestamp on the time series through a Long Short-Term Memory (LSTM) network.
[0048] Step 1233: Combine the short-term dependency relationship and the long-term evolution pattern to determine the driver's stress load index.
[0049] In this application, one-dimensional convolutional neural networks excel at processing sequential data. They can extract local features from multiple state feature values corresponding to the same timestamp by sliding the convolutional kernel, capturing potential correlations (i.e., short-term dependencies) between different feature values. For example, at the same time point, there may be a cooperative relationship between visual attention feature values (such as the interface gaze ratio), physiological feature values (such as the heart rate LF / HF ratio), and behavioral action feature values (such as grip strength variance). One-dimensional convolutional neural networks can effectively mine such correlations and form more representative local features.
[0050] In this application, the Long Short-Term Memory (LSTM) network has the ability to remember long-term information and can perform time series analysis on the same state feature values corresponding to multiple timestamps, learning the pattern of change of these feature values over time (i.e., long-term evolution patterns). For example, if the PERCLOS values for 10 consecutive timestamps are 0.05, 0.06, 0.08, 0.12, 0.18, 0.25, 0.32, 0.38, 0.45, and 0.50, the LTM network can capture the evolution pattern of a continuously rising PERCLOS value, thereby determining that the driver's fatigue level is gradually increasing.
[0051] Furthermore, the local features extracted by the one-dimensional convolutional neural network (reflecting the correlation between different features at the same point in time) and the time series features learned by the LSTM network (reflecting the time variation pattern of the same feature) can be fused together to combine the advantages of both and obtain a more comprehensive and accurate pressure load index.
[0052] Based on the technical solutions in steps 121 to 123 above, a one-dimensional convolutional neural network can effectively capture the short-term dependencies between different state feature values at the same time point and uncover the collaborative change patterns between feature values. Compared with analyzing a single feature value alone, it can obtain more comprehensive local state information, providing richer evidence for stress load assessment. Furthermore, by using a long short-term memory network, the gradient vanishing problem of traditional recurrent neural networks can be overcome, effectively learning the long-term evolution patterns of the same state feature value over time. This allows for accurate capture of the dynamic changing trends of the driver's state (such as gradually increasing fatigue and gradually easing tension), avoiding the static and one-sided problems caused by assessment based solely on data from a single time point. In this application, by further combining short-term dependencies and long-term evolution patterns to determine the stress load index, it is possible to integrate multi-feature correlation information at the same time point and the time-varying information of the same feature, achieving dynamic and accurate quantification of the driver's stress load. Compared with a single neural network model, the accuracy and reliability of the quantification results are significantly improved, providing stronger support for the refined adjustment of the cabin screen display status.
[0053] In this application, step 124 may also be performed: Step 124: If one or more of the at least one state characteristic values exceed a preset state characteristic value threshold, then the upper limit of the pressure load index is determined as the driver's pressure load index.
[0054] In this application, the preset state characteristic value thresholds can be set based on actual driving safety needs. Different state characteristic values correspond to different thresholds, and can be fine-tuned according to vehicle model and driving scenario. These thresholds typically correspond to extreme states such as extreme fatigue, high tension, or sudden danger for the driver. At this time, the driver's attention resources are completely occupied by the driving task, and they can no longer process additional information on the cabin screen, so the screen display status needs to be adjusted to the simplest state immediately.
[0055] In this application, the upper limit of the stress load index can be a pre-set maximum value, such as 0.9 or 1.0, representing that the driver's attention resources are fully utilized and in an extremely high-load state. When this mechanism is triggered, the upper limit value is directly used as the stress load index, which can quickly activate the highest level of screen display simplification strategy and avoid response delays caused by complex calculations.
[0056] Based on the technical solution in step 124 above, by setting a state characteristic value threshold triggering mechanism, it is possible to quickly identify extreme high-load states such as extreme fatigue, high tension, and severe distraction of the driver. Compared with conventional quantification methods that rely on complex neural network calculations, the response speed is faster, avoiding untimely adjustment of display status due to calculation delays, and effectively responding to sudden dangerous scenarios. When the state characteristic value exceeds the preset state characteristic value threshold, the pressure load index is directly set to the upper limit, ensuring that the cabin screen immediately activates the highest level of display simplification strategy. This minimizes the occupation of the driver's attention by screen information, reserving sufficient attention resources for the driver to deal with extreme situations, and significantly improving driving safety.
[0057] In such Figure 1 In step 130, the dynamic adjustment of the display status of the cabin screen in at least one display dimension, including interface element layout, information presentation density, and menu hierarchy structure, based on the pressure load index, can be performed according to steps 131 to 133 as follows: Step 131: Obtain at least two consecutively adjacent index intervals and determine the target index interval into which the pressure load index falls.
[0058] Step 132: Determine the driver's stress load level based on the interval number of the target index interval.
[0059] Step 133: Based on the pressure load level, dynamically adjust the display status of the cabin screen in at least one display dimension among interface element layout, information presentation density, and menu hierarchy structure.
[0060] In this application, the range of the pressure load index (e.g., 0-1) can be divided into multiple continuous and non-overlapping intervals. The number of intervals and the endpoint values of each interval can be set according to the actual application scenario. For example, dividing it into two intervals could include [0, 0.5] and (0.5, 1.0], or dividing it into three intervals could include [0, 0.3], (0.3, 0.7], (0.7, 1.0], or more intervals. The core principle of interval division is to ensure that there are significant differences in the degree of driver attention resource occupancy corresponding to different intervals, so as to correspond to different screen information display states.
[0061] In this application, determining the stress load level based on the interval number means assigning a corresponding load level to each index interval. The larger the interval number, the higher the corresponding stress load level, which represents a higher degree of driver attention resource consumption.
[0062] In this application, a corresponding display adjustment strategy can be preset for each load level. The adjusted display dimensions may include at least one of interface element layout, information presentation density, and menu hierarchy structure. The display strategies corresponding to different load levels are significantly different; the higher the load level, the simpler the display state.
[0063] In one embodiment of this application, the pressure load level may include a first level (low load), a second level (medium load), and a third level (high load), wherein the third level is greater than the second level, and the second level is greater than the first level.
[0064] Furthermore, in this embodiment, the dynamic adjustment of the display status of the cabin screen in at least one display dimension among interface element layout, information presentation density, and menu hierarchy structure based on the pressure load level can be performed according to the following steps 1331 to 1333: Step 1331: If the pressure load level is the first level, the control cabin screen adopts a full display state, displays all information and supports deep menus.
[0065] Step 1332: If the pressure load level is the second level, the control cabin screen adopts a simplified display state, hides low priority information, reduces the display ratio of the passenger entertainment area to the first ratio of the screen width, and compresses the menu level to the middle level menu.
[0066] Step 1333: If the pressure load level is the third level, the control cabin screen adopts a simplified display state, only displaying high priority information, reducing the display ratio of the passenger entertainment area to the second ratio of the screen width, and compressing the menu level to a low-level menu, where the second ratio is smaller than the first ratio.
[0067] In this application, the full display state is a display strategy for the first level (low load), at which time the driver has sufficient attention resources and can process more information. Therefore, the screen displays all information corresponding to the installed functions, including driving-related information (vehicle speed, navigation, vehicle status) and entertainment interaction information (music, video, social notifications), and supports deep menus (such as 3 levels and above), allowing the driver to perform complex function settings and operations.
[0068] In this application, the simplified display status is a display strategy for the second level (medium load), at which point the driver's attention resources are partially occupied, and the amount of information processed needs to be appropriately reduced. Therefore, low-priority information (such as general social media notifications, vehicle maintenance reminders, historical fuel consumption statistics, etc.) is hidden on the screen, and only medium- and high-priority information is retained; the display ratio of the passenger-side entertainment area is reduced to the first ratio (such as 1 / 3 or 1 / 2, which can be preset according to the screen size of the vehicle model) to reduce interference with the driver's line of sight; the menu hierarchy is compressed to a medium level (such as 2 levels) to simplify the operation process and enable the driver to quickly find the functions they need.
[0069] In this application, the minimalist display state is a display strategy for the third level (high load), at which point the driver's attention resources are highly occupied and can only process core driving information. Therefore, the screen only displays high-priority information (such as vehicle speed, core navigation guidance, collision warning, abnormal tire pressure, and other information that directly affects driving safety); the display ratio of the passenger entertainment area is further reduced to a second ratio (e.g., 1 / 4, hidden, the second ratio is smaller than the first ratio) to minimize interference; the menu hierarchy is compressed to a low level (e.g., 1 level), retaining only emergency functions and core function buttons to avoid driver misoperation.
[0070] For example, in a specific embodiment, the pressure load index range (0-1) can be divided into three consecutive adjacent index intervals: [0,0.3] (first interval), (0.3,0.7] (second interval), and (0.7,1.0] (third interval), corresponding to the pressure load levels of the first level (low load), the second level (medium load), and the third level (high load), respectively.
[0071] If the driver is driving smoothly on suburban roads, and the calculated pressure load index is 0.2, falling into the first interval, it is determined to be the first level. At this time, the cabin screen is in full display mode, with the navigation map displayed in full screen on the left, the music playback interface (including lyrics) displayed on the right, fuel consumption, driving range, and tire pressure information displayed in the upper right corner, and social media notifications popping up in the lower right corner; the menu supports 3-level operation, such as entering the detailed air conditioning settings interface by clicking 3 times.
[0072] If the driver is driving on city roads in rainy weather, the pressure load index is 0.5, falling into the second range and thus classified as Level 2. At this time, the screen switches to a simplified display state, hiding low-priority information such as social notifications and music lyrics, while retaining medium-to-high-priority information such as navigation maps, vehicle speed, fuel consumption, and lane keeping prompts; the passenger entertainment area (original music playback interface) is reduced to 1 / 3 of the screen width (first ratio), displaying only the play / pause button and song titles; the menu is compressed to two layers, allowing access to the detailed air conditioning settings interface with two clicks, eliminating the need to navigate to deeper settings.
[0073] If a driver is driving on a highway in foggy weather, the pressure load index is 0.8, falling into the third range and thus classified as Level 3. At this time, the screen switches to a minimalist display mode, showing only enlarged vehicle speed, navigation core arrows, collision warning icons, and other high-priority information; the passenger entertainment area is reduced to 1 / 4 of the screen width (second ratio), displaying only audio waveforms and no other content; the menu is compressed to one layer, with only "Emergency Call" and "Navigation Switch" buttons remaining at the bottom of the screen, and all other functions are hidden.
[0074] Based on the technical solutions in steps 131 to 133 above, firstly, dividing the stress load index into at least two consecutively adjacent index intervals allows for the discretization of continuous indices, avoiding frequent switching of display states due to minor changes in the index, and improving the stability of display adjustments and user experience. Secondly, determining the stress load level based on the interval number makes the driver's attention resource occupancy more intuitive and easier to determine, providing a clear grading basis for display state adjustments and simplifying the adjustment logic. Finally, grading the display state based on stress load levels enables the development of precise display strategies for different load levels, ensuring both information richness under low load and information simplicity under high load, achieving a dynamic balance between driving safety and information needs. Furthermore, the grading adjustment method makes changes in display state smoother and more predictable, improving driver satisfaction with the cabin screen.
[0075] In step 131 above, obtaining at least two consecutively adjacent exponential intervals can be performed according to steps 1311 to 1312 as follows: Step 1311: Obtain the current driving environment data of the vehicle driven by the driver, and determine the endpoint values of the index interval that match the driving environment data.
[0076] Step 1312: Determine at least two sequentially adjacent exponential intervals based on the endpoint values of the exponential intervals.
[0077] In this application, driving environment data refers to external environmental information related to the driving process, which may include road type (e.g., urban roads, highways, rural roads), traffic conditions (e.g., congestion, smooth traffic, construction), weather conditions (e.g., sunny, rainy, snowy, foggy), time of day (e.g., daytime, nighttime, early morning), and road segment characteristics (e.g., densely intersectioned road sections, long downhill sections, tunnels), etc. These environmental factors directly affect the driver's driving difficulty and attention resource consumption. For example, in a smooth highway scenario, the driver's attention resource consumption is low. In congested urban scenarios or rainy nighttime scenarios, the driver's attention resource consumption is high.
[0078] In this application, a correspondence between driving environment data and index interval endpoint values can be pre-established. Based on the currently collected driving environment data, the corresponding endpoint values can be queried or calculated. For example, in a smooth highway scenario, the endpoint values for low and medium loads are set to 0.4. In a congested urban scenario, the endpoint values for low and medium loads can be adjusted to 0.3. After obtaining the endpoint values adapted to the current driving environment, the corresponding index intervals can be defined, and subsequent pressure load level determination and display status adjustments can be made based on these intervals.
[0079] Based on the technical solutions in steps 131 to 133 above, by dynamically adjusting the endpoint values of the index interval using driving environment data, the division of the index interval can be adapted to different driving environments, avoiding the problem of insufficient adaptability of fixed intervals in different environments. For example, in high-difficulty driving environments (such as foggy highways), drivers need more attention resources to cope with driving tasks. By reducing the endpoint values of the low-load interval, the display simplification strategy can be triggered earlier, ensuring driving safety. In low-difficulty driving environments (such as rural roads), by increasing the endpoint values, display simplification can be delayed, retaining more information to meet the driver's needs. Determining the index interval based on endpoint values adapted to the current driving environment makes the determination of stress load level more in line with the difficulty of actual driving scenarios, which can improve the accuracy of load level determination. In addition, the dynamic adjustment of the index interval can further optimize the adjustment accuracy of the display status, enabling the information presentation on the cabin screen to simultaneously match the driver's own state and the external driving environment, achieving dual adaptation of driver state and driving environment, further improving driving safety and interactive experience.
[0080] In step 131 above, obtaining at least two consecutively adjacent exponential intervals can also be performed according to steps 1313 to 1314 below: Step 1313: Establish a personal baseline profile for each driver, which includes average grip strength, resting heart rate, and gaze habits data under normal conditions.
[0081] Step 1313: Based on the personal baseline profile, make personalized fine-tuning of the preset threshold.
[0082] This application provides a personalized approach to obtaining index intervals. Its core is to fine-tune preset thresholds based on individual driver differences to make interval division more accurate. Specifically, a personal baseline profile is first established for each driver, including their average grip strength, resting heart rate, and gaze habits under normal conditions (data must be collected when the driver is not fatigued, not stressed, and the driving scenario is stable to ensure it reflects their basic state characteristics). Then, based on this profile, the interval endpoints are optimized according to the physiological characteristics and driving ability differences of different drivers. For example, experienced drivers with strong stress resistance can have their thresholds raised to reduce unnecessary screen simplification, while novice or elderly drivers with weaker information processing abilities can have their thresholds lowered to trigger simplification earlier. After fine-tuning, the index intervals are divided using the new thresholds, which avoids misjudgments using universal standards, allowing screen display adjustments to better match the driver's actual state, balancing safety and experience while improving system adaptability.
[0083] In this application, steps 141 to 143 may also be performed: Step 141: After adjusting the information display status of the cabin screen, continuously monitor the changes in the driver's stress load index.
[0084] Step 142: If the pressure load index does not decrease or continues to increase, then completely retract the passenger entertainment interface.
[0085] Step 143: If the pressure load index drops rapidly, maintain the current information display status on the screen.
[0086] This application further proposes a closed-loop feedback mechanism after adjusting the cockpit screen display status. Its core purpose is to verify the effectiveness of the initial display adjustment strategy and dynamically optimize it based on real-time changes in the driver's stress load index, ensuring that the screen display always matches the driver's attention resources. After the initial screen display status adjustment, monitoring does not stop; instead, multi-source sensors continuously collect the driver's perception data, update the stress load index in real time, and continuously track the impact of the adjustment strategy on the driver's load. For scenarios where the adjustment is ineffective, if the stress load index does not decrease or even continues to rise, it indicates that the initial simplification strategy has failed to effectively reduce the driver's information processing pressure. In this case, more aggressive optimization measures need to be initiated, namely, completely retracting the passenger-side entertainment interface to completely eliminate interference with the driver's vision and attention, maximizing the reserve of attention resources for driving tasks. If the stress load index decreases rapidly, it indicates that the current screen display status matches the driver's load level well, and no further adjustment is needed; maintaining the existing status is sufficient to avoid over-simplification affecting the driver's information acquisition needs.
[0087] The following describes an embodiment of the apparatus described in this application, which can be used to execute the method for adjusting the display state of the vehicle cabin screen information in the above embodiments of this application. For details not disclosed in the apparatus embodiments of this application, please refer to the embodiments of the method for adjusting the display state of the vehicle cabin screen information described above in this application.
[0088] See Figure 2 The diagram shows a block diagram of the device for adjusting the display status of cabin screen information in an embodiment of this application.
[0089] like Figure 2 As shown, the vehicle cabin screen information display status adjustment device 200 according to an embodiment of this application includes: an acquisition unit 201, an analysis unit 202, and an adjustment unit 203.
[0090] The acquisition unit 201 is used to acquire perception data of the driver in at least one state representation dimension among visual attention, physiological tension, and behavioral actions, collected by multi-source sensors in the vehicle cabin; the analysis unit 202 is used to perform fusion analysis on the perception data to quantify the perception data into the driver's stress load index, which is used to characterize the driver's current level of attention resource occupancy; the adjustment unit 203 is used to dynamically adjust the display state of the vehicle cabin screen in at least one display dimension among interface element layout, information presentation density, and menu hierarchy structure based on the stress load index, wherein the complexity of the display state is negatively correlated with the stress load index.
[0091] In some embodiments of this application, based on the foregoing scheme, the analysis unit 202 is configured to: align the sensing data of the at least one state representation dimension based on the timestamp when the sensing data is collected, to obtain a sensing data set corresponding to at least one timestamp; extract at least one state feature value of the driver from the sensing data set corresponding to each timestamp; and perform weighted fusion of the at least one state feature value using a machine learning algorithm to obtain the driver's stress load index.
[0092] In some embodiments of this application, based on the foregoing scheme, the analysis unit 202 is configured to: use a one-dimensional convolutional neural network to extract the short-term dependency relationship between at least one state feature value corresponding to the same timestamp; learn the long-term evolution pattern of the same state feature value corresponding to at least one timestamp in the time series through a long short-term memory network; and combine the short-term dependency relationship and the long-term evolution pattern to determine the driver's stress load index.
[0093] In some embodiments of this application, based on the foregoing scheme, the analysis unit 202 is configured to: if one or more of the at least one state feature values exceed a preset state feature value threshold, then the upper limit value of the pressure load index is determined as the driver's pressure load index.
[0094] In some embodiments of this application, based on the foregoing scheme, the adjustment unit 203 is configured to: acquire at least two sequentially adjacent index intervals and determine the target index interval into which the stress load index falls; determine the driver's stress load level based on the interval number of the target index interval; and dynamically adjust the display status of the cabin screen in at least one display dimension among interface element layout, information presentation density, and menu hierarchy structure based on the stress load level.
[0095] In some embodiments of this application, based on the foregoing scheme, the adjustment unit 203 is configured to: acquire the current driving environment data of the vehicle driven by the driver, and determine the endpoint values of the index interval that match the driving environment data; and determine at least two sequentially adjacent index intervals based on the endpoint values of the index interval.
[0096] In some embodiments of this application, based on the aforementioned scheme, the pressure load level includes a first level, a second level, and a third level, wherein the third level is greater than the second level, and the second level is greater than the first level. The adjustment unit 203 is configured as follows: if the pressure load level is the first level, the cabin screen is controlled to adopt a full display state, displaying all information and supporting deep-level menus; if the pressure load level is the second level, the cabin screen is controlled to adopt a simplified display state, hiding low-priority information, reducing the display ratio of the passenger entertainment area to a first ratio of the screen width, and compressing the menu level to a mid-level menu; if the pressure load level is the third level, the cabin screen is controlled to adopt a minimalist display state, displaying only high-priority information, reducing the display ratio of the passenger entertainment area to a second ratio of the screen width, and compressing the menu level to a low-level menu, wherein the second ratio is less than the first ratio.
[0097] Based on the same inventive concept, this application provides a computer program product, which includes computer instructions stored in a computer-readable storage medium and adapted to be read and executed by a processor to cause a computer device having the processor to perform operations performed by the method for adjusting the display state of cabin screen information as described above.
[0098] Based on the same inventive concept, embodiments of this application provide a computer-readable storage medium storing at least one computer program instruction, which is loaded and executed by a processor to perform the operations performed by the method for adjusting the display state of cabin screen information as described above.
[0099] Based on the same inventive concept, this application also provides a vehicle, see reference. Figure 3 The diagram shows a structural schematic of a vehicle according to an embodiment of this application. The vehicle includes one or more memories 304, one or more processors 302, and at least one computer program (computer program instruction) stored in the memory 304 and executable on the processor 302. When the processor 302 executes the computer program, it implements the method for adjusting the display status of the cabin screen information as described above.
[0100] Among them, Figure 3 In this document, a bus architecture (represented by bus 300) is used. Bus 300 may include any number of interconnected buses and bridges, linking various circuits including one or more processors represented by processor 302 and memory represented by memory 304. Bus 300 may also link various other circuits such as peripheral devices, voltage regulators, and power management circuits, which are well known in the art and therefore will not be described further herein. Bus interface 305 provides an interface between bus 300 and receiver 301 and transmitter 303. Receiver 301 and transmitter 303 may be the same element, i.e., a transceiver, providing a unit for communicating with various other devices over a transmission medium. Processor 302 is responsible for managing bus 300 and general processing, while memory 304 can be used to store data used by processor 302 during operation.
[0101] The functions described herein can be implemented in hardware, software executed by a processor, firmware, or any combination thereof. When implemented in software executed by a processor, the functions can be stored as one or more instructions or codes on or transmitted via a computer-readable medium. Other examples and embodiments are within the scope and spirit of this application and the appended claims. For example, due to the nature of software, the functions described above can be implemented using software executed by a processor, hardware, firmware, hardwired, or any combination thereof. Furthermore, the functional units can be integrated into a single processing unit, or each unit can exist physically separately, or two or more units can be integrated into a single unit.
[0102] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. The device embodiments described above are merely illustrative; for example, the division of units can be a logical functional division, and in actual implementation, there may be other division methods. For instance, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the displayed or discussed mutual coupling, direct coupling, or communication connection may be through some interfaces; the indirect coupling or communication connection between units or modules may be electrical or other forms.
[0103] The units described as separate components may or may not be physically separate. Similarly, the components of the control device may or may not be physical units; they may be located in one place or distributed across multiple units. Some or all of the units can be selected to achieve the purpose of this embodiment, depending on actual needs.
[0104] When the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing computer program instructions, such as USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, or optical disks.
[0105] The above description is merely an embodiment of this application and is not intended to limit this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of the claims of this application.
Claims
1. A method for adjusting the information display status of a vehicle cabin screen, characterized in that, The method includes: Acquire perceptual data of the driver in at least one state representation dimension among visual attention, physiological tension, and behavioral actions, collected by multi-source sensors in the vehicle cabin; The perceived data is fused and analyzed to quantify the perceived data into the driver's stress load index, which is used to characterize the driver's current level of attention resource utilization. Based on the pressure load index, the display status of the cabin screen in at least one display dimension, including interface element layout, information presentation density, and menu hierarchy structure, is dynamically adjusted. The complexity of the display status is negatively correlated with the pressure load index.
2. The method according to claim 1, characterized in that, The process of fusing and analyzing the sensed data to quantify it into the driver's stress load index includes: Based on the timestamp of the sensing data when it was collected, the sensing data of the at least one state representation dimension are aligned to obtain a set of sensing data corresponding to at least one timestamp. Extract at least one state feature value of the driver from the sensing data set corresponding to each timestamp; The driver's stress load index is obtained by weighting and fusing the at least one state feature value using a machine learning algorithm.
3. The method according to claim 2, characterized in that, The step of weighted fusion of the at least one state feature value using a machine learning algorithm to obtain the driver's stress load index includes: A one-dimensional convolutional neural network is used to extract short-term dependencies between at least one state feature value corresponding to the same timestamp; Learn the long-term evolution pattern of the same state feature value corresponding to at least one timestamp in the time series by using a long short-term memory network; The driver's stress load index is determined by combining the short-term dependency relationship and the long-term evolution pattern.
4. The method according to claim 3, characterized in that, The method further includes: If one or more of the at least one state characteristic values exceed a preset state characteristic value threshold, then the upper limit of the pressure load index is determined as the driver's pressure load index.
5. The method according to claim 1, characterized in that, The method of dynamically adjusting the display status of the cabin screen in at least one display dimension, including interface element layout, information presentation density, and menu hierarchy structure, based on the pressure load index, includes: Obtain at least two consecutively adjacent index intervals and determine the target index interval into which the pressure load index falls; The driver's stress load level is determined based on the interval number of the target index interval; Based on the aforementioned pressure load level, the display status of the cabin screen in at least one display dimension, including interface element layout, information presentation density, and menu hierarchy structure, is dynamically adjusted.
6. The method according to claim 5, characterized in that, Obtaining at least two consecutively adjacent exponential intervals includes: Obtain the current driving environment data of the vehicle driven by the driver, and determine the endpoint values of the index interval that match the driving environment data; Based on the endpoint values of the exponential intervals, at least two consecutively adjacent exponential intervals are determined.
7. The method according to claim 5, characterized in that, The pressure load level includes a first level, a second level, and a third level, wherein the third level is greater than the second level, and the second level is greater than the first level. The step of dynamically adjusting the display state of the cabin screen in at least one display dimension—interface element layout, information presentation density, and menu hierarchy—based on the pressure load level includes: If the pressure load level is the first level, the control cabin screen will be in full display mode, displaying all information and supporting deep menus; If the pressure load level is the second level, the control cabin screen adopts a simplified display state, hides low priority information, reduces the display ratio of the passenger entertainment area to the first ratio of the screen width, and compresses the menu level to the middle level menu. If the pressure load level is level three, the control cabin screen adopts a simplified display state, only displaying high-priority information, reducing the display ratio of the passenger entertainment area to the second ratio of the screen width, and compressing the menu level to a low-level menu, with the second ratio being smaller than the first ratio.
8. A device for adjusting the information display status of a vehicle cabin screen, characterized in that, The device includes: The acquisition unit is used to acquire perception data of the driver in at least one state representation dimension among visual attention, physiological tension and behavioral actions, collected by multi-source sensors in the vehicle cabin. The analysis unit is used to perform fusion analysis on the perceived data to quantify the perceived data into the driver's stress load index, which is used to characterize the driver's current level of attention resource utilization. The adjustment unit is used to dynamically adjust the display status of the cabin screen in at least one display dimension, including interface element layout, information presentation density, and menu hierarchy structure, based on the pressure load index. The complexity of the display status is negatively correlated with the pressure load index.
9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores at least one piece of program code, which is loaded and executed by a processor to perform the operations performed by the method as described in any one of claims 1 to 7.
10. A vehicle, characterized in that, The vehicle includes one or more processors and one or more memories, wherein at least one piece of program code is stored in the one or more memories, and the at least one piece of program code is loaded and executed by the one or more processors to implement the method as described in any one of claims 1 to 7.