Display adjustment method of vehicle-mounted interaction equipment, electronic equipment and storage medium

Abstract

The invention provides a display adjustment method of a vehicle-mounted interaction device, an electronic device and a storage medium, and relates to the technical field of automotive electronics and intelligent man-machine interaction, and the method comprises the steps: obtaining an eye image of a driver and light data of an environment where a vehicle is located; extracting pupil state data based on the eye image, and predicting a pupil reaction range by adopting a pupil comfort model based on the pupil state data and the ambient light data; if the pupil state data continuously deviates from the pupil reaction range, current display parameters of the vehicle-mounted interaction equipment are optimized to obtain target display parameters; and performing display adjustment on the vehicle-mounted interaction equipment according to the target display parameter. According to the method, the response smoothness and visibility in complex scenes such as illumination dramatic change are remarkably enhanced, instantaneous glare or black screen is avoided, and therefore the driving safety and the interaction comfort are improved.

Description

Technical Field

[0001] This application relates to the fields of automotive electronics and intelligent human-machine interaction technology, and in particular to a display adjustment method, electronic device and storage medium for an in-vehicle interactive device. Background Technology

[0002] Current in-vehicle display adjustment technologies primarily rely on ambient light sensors for unidirectional brightness adjustment, or combine driver monitoring for attention detection and energy-saving control. However, these solutions employ fixed adjustment strategies, failing to adapt to the individual visual needs of different drivers. Especially in transient scenarios with drastic lighting changes, they exhibit slow or excessive response, easily resulting in screens that are too dark or too bright, creating blind spots and compromising driving safety. Furthermore, existing systems are mostly open-loop controls, lacking feedback verification of the adjustment effect, making it difficult to ensure actual visual comfort. Additionally, display adjustment is limited to the brightness dimension, resulting in limited overall intelligence. Summary of the Invention

[0003] The purpose of this application is to provide a display adjustment method, electronic device and storage medium for an in-vehicle interactive device, so as to alleviate the above-mentioned technical problems existing in the prior art.

[0004] In a first aspect, the present invention provides a display adjustment method for an in-vehicle interactive device, comprising: Acquire images of the driver's eyes and ambient light data of the vehicle's location; Pupil state data is extracted from eye images, and pupil comfort model is used to predict pupil response range based on pupil state data and ambient light data. If the pupil state data continues to deviate from the pupil response range, the current display parameters of the in-vehicle interactive device will be optimized to obtain the target display parameters; Adjust the display of the in-vehicle interactive device according to the target display parameters.

[0005] In an optional implementation, acquiring the driver's eye image and ambient light data of the vehicle's location includes: The driver's eye video stream is acquired by an imaging device installed in the vehicle's cockpit under preset trigger conditions; the preset trigger conditions include at least one of the following: vehicle start-up, engaging a driving gear, or entering an assisted driving mode. An ambient light sensor installed on the top of the dashboard collects real-time information on the light intensity and color temperature of the current environment, and timestamps the eye video stream with the ambient light data.

[0006] In an optional implementation, pupil state data is extracted based on eye images, including: Each frame of the eye video stream is preprocessed to remove ambient light interference and enhance the contrast in the eye area; The center position of the pupils of both eyes is located by edge detection and circle fitting algorithm, and the pupil diameter of the current frame is calculated to determine the pupil state data.

[0007] In an optional implementation, based on pupil state data and ambient light data, a pupil comfort model is used to predict the pupillary response range, including: Input the light intensity and color temperature information into the pupil comfort model; By using the mapping relationship between pre-configured ambient light data and physiological response in the pupil comfort model, the pupil response range corresponding to the pupil state data under the corresponding ambient light data is determined.

[0008] In an optional implementation, if the pupil state data continuously deviates from the pupil response range, the current display parameters of the in-vehicle interactive device are optimized to obtain target display parameters, including: Compare pupil state data with pupil reaction range to determine whether pupil state data is higher than the upper limit of pupil reaction range or lower than the lower limit of pupil reaction range; If the deviation of the pupil state data from the pupil reaction range continues to exceed a preset time threshold, the display adjustment strategy library is matched to optimize the current display parameters of the in-vehicle interactive device based on the preset adjustment strategies in the display adjustment strategy library to obtain the target display parameters.

[0009] In an optional implementation, the display of the in-vehicle interactive device is adjusted according to the target display parameters, including one or more of the following adjustment strategies: The system controls the in-vehicle interactive device to adjust the backlight brightness and color temperature output value according to the target display parameters, so that the screen's luminous characteristics match the current lighting conditions of the driving environment. When a vehicle is detected to be rapidly transitioning from a bright environment to a dark environment, the brightness transition curve is adjusted based on the dynamic rate of change of pupil state data to achieve smooth visual adaptation. Trigger the user interface rendering engine of the in-vehicle interactive device to switch the display mode, and switch the display theme and / or information layout of the user interface.

[0010] In an optional implementation, it further includes: Establish a personal visual preference profile for identified drivers and record pupil state data that has reached a stable state after adjustment under different ambient light data; When the driver logs into the system again, under the same or similar ambient light data, the system directly retrieves the target pupil state data corresponding to the ambient light data from the historical records. When adjusting the display, the target pupil state data is used as the adjustment reference, and the adjustment is stabilized at the adjustment reference, or optimized based on the adjustment reference.

[0011] In an optional implementation, it further includes: After completing one display adjustment, continuously monitor changes in the driver's pupil state data; If the adjusted pupil state data still does not fall within the corresponding pupil response range, a second fine-tuning is performed to recalculate the degree of deviation between the current pupil state data and the pupil response range. Based on the degree of deviation, the current display parameters of the in-vehicle interactive device are updated and optimized to obtain the updated target display parameters until the pupil state data stabilizes within the pupil response range.

[0012] In a second aspect, the present invention provides an electronic device including a processor and a memory, wherein the memory stores computer-executable instructions that can be executed by the processor, and the processor executes the computer-executable instructions to implement the display adjustment method of the in-vehicle interactive device according to any of the foregoing embodiments.

[0013] Thirdly, the present invention provides a computer-readable storage medium storing computer-executable instructions. When the computer-executable instructions are invoked and executed by a processor, the computer-executable instructions cause the processor to implement the display adjustment method of the in-vehicle interactive device according to any of the foregoing embodiments.

[0014] The display adjustment method, electronic device, and storage medium of the in-vehicle interactive device provided in this application achieve dual perception of individual physiological state and external lighting environment by acquiring driver eye images and ambient light data, solving the problem of rigid adjustment caused by traditional systems relying solely on fixed environmental parameters; a comfort model is constructed based on pupil state data and ambient light data to predict the reaction range, introducing personalized physiological benchmarks and improving the adaptability to different drivers' visual characteristics; when the pupil state continuously deviates from the predicted range, an adjustment mechanism is triggered, forming a closed-loop control based on real physiological feedback, effectively overcoming the deficiency of open-loop systems lacking effect verification; by dynamically optimizing and adjusting display parameters, the smoothness of response and visibility in complex scenarios such as drastic changes in lighting are significantly enhanced, avoiding instantaneous glare or black screen, thereby improving driving safety and interactive comfort. Attached Figure Description

[0015] To more clearly illustrate the technical solutions in the specific embodiments of this application or the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this application. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0016] Figure 1 A flowchart illustrating a display adjustment method for an in-vehicle interactive device provided in this application embodiment; Figure 2 A hardware module diagram of a display adjustment system for an in-vehicle interactive device provided in an embodiment of this application; Figure 3 A flowchart illustrating an in-vehicle human-machine interaction adjustment strategy that integrates ambient light and pupil dynamics, provided as an embodiment of this application; Figure 4 A logical diagram illustrating data fusion and decision-making for a comfort model provided in an embodiment of this application; Figure 5 A schematic diagram comparing the brightness adjustment curves of the present invention and a conventional solution in a tunnel entry / exit scenario, provided as an embodiment of this application; Figure 6 A structural diagram of a display adjustment device for an in-vehicle interactive device provided in an embodiment of this application; Figure 7 This is a structural diagram of an electronic device provided in an embodiment of this application. Detailed Implementation

[0017] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, 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. The components of the embodiments of this application described and shown in the accompanying drawings can generally be arranged and designed in various different configurations.

[0018] Therefore, the following detailed description of the embodiments of this application provided in the accompanying drawings is not intended to limit the scope of the claimed application, but merely to illustrate selected embodiments of the application. All other embodiments obtained by those skilled in the art based on the embodiments of this application without inventive effort are within the scope of protection of this application.

[0019] It should be noted that similar labels and letters in the following figures indicate similar items. Therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures.

[0020] This application provides a display adjustment method for an in-vehicle interactive device. See also... Figure 1 As shown, the method mainly includes the following steps: S110 acquires the driver's eye image and the ambient light data of the vehicle's location.

[0021] In one implementation, when the vehicle is activated or enters a preset trigger condition such as city NOA or highway NOA, a near-infrared camera installed in the vehicle's cockpit captures real-time video streams of the driver's eyes, ensuring stable capture of eye images under different lighting conditions (including nighttime or strong light) and even when wearing sunglasses. Simultaneously, an ambient light sensor located at the top of the dashboard near the windshield continuously collects information on the current ambient light intensity and color temperature. To achieve synchronized data analysis, the captured eye video frames and ambient light data can be timestamped to ensure the accuracy and timeliness of subsequent fusion and judgment.

[0022] S120 extracts pupil state data based on eye images, and uses a pupil comfort model to predict the pupil response range based on pupil state data and ambient light data.

[0023] When extracting pupil state data, preprocessing operations such as Gaussian blur denoising and histogram equalization to enhance contrast can be performed sequentially on each frame of the eye image to reduce interference from complex lighting. Subsequently, Canny edge detection combined with Hough circle transform algorithm is used to accurately locate the center of both pupils and calculate the current pupil diameter as pupil state data. This pupil state data, along with synchronously acquired ambient light data, is input into a pre-constructed pupil comfort model. This model embeds a mapping relationship between ambient light data (light intensity, color temperature) and the expected pupil diameter range under normal physiological conditions (e.g., in a 50,000 Lux strong light environment, the comfortable pupil diameter range for healthy adults is 1.9–2.4 mm), thereby dynamically predicting the pupil response range that should be presented in the current environment.

[0024] S130, if the pupil state data continues to deviate from the pupil reaction range, the current display parameters of the in-vehicle interactive device are optimized to obtain the target display parameters.

[0025] The real-time extracted pupil state data is compared with the pupil response range output by the model to determine if there is a significant deviation. For example, the measured pupil diameter may be higher than the upper limit of the comfortable range (indicating the screen is too dark) or lower than the lower limit (indicating the screen is too bright). If such deviations persist for more than a preset time threshold (e.g., 1.5 seconds), it is determined that the current display settings are causing visual discomfort, triggering the adjustment mechanism. When adjusting the display, the built-in adjustment strategy library can be consulted to match the optimal adjustment strategy based on the current environmental change trend (e.g., a sudden drop in light) and the dynamic response characteristics of the pupil (e.g., dilation rate), generating a set of target display parameters including target brightness, color temperature, UI mode, and other dimensions.

[0026] S140 adjusts the display of the in-vehicle interactive device according to the target display parameters.

[0027] Based on the aforementioned target display parameters, the control system performs multi-dimensional coordinated adjustments: First, it adjusts the backlight brightness and color temperature output of the vehicle display screen to better match its luminous characteristics with the current ambient lighting conditions; second, in scenarios with drastic lighting changes (such as entering a tunnel), it combines the dynamic change rate of the pupils to adjust the brightness transition curve, achieving a smooth adjustment that is initially fast and then slows down, avoiding instantaneous glare or visibility interruption; simultaneously, the UI rendering engine, upon receiving instructions, switches the interface theme, such as enabling dark mode or a high-contrast layout, and appropriately enlarges the font size of key information to further improve readability. After adjustment, the system continuously monitors pupil state feedback; if it still has not entered a comfortable range, it initiates a fine-tuning mechanism for iterative optimization until a stable and comfortable visual state is achieved.

[0028] For ease of understanding, the display adjustment method of the in-vehicle interactive device provided in the embodiments of this application will be described in detail below.

[0029] In one embodiment, the driver's eye image can be acquired by an imaging device installed in the vehicle's cockpit, which acquires the driver's eye video stream under preset trigger conditions; the preset trigger conditions include at least one of vehicle start-up, engaging a driving gear, or entering an assisted driving mode.

[0030] The aforementioned imaging device can be an imaging unit for acquiring visual information about the driver's eye area, such as a near-infrared camera. This camera is capable of penetrating sunglasses and stably capturing clear eye images under different lighting conditions for dynamic monitoring of pupil status. Its installation location is typically inside the instrument panel behind the steering wheel or above the center console, ensuring that the field of view covers both eyes of the driver, and the field of view is adapted to the range of human eye movement (e.g., 40°–70°), with a resolution of 720P to 5MP and a frame rate of no less than 30fps to meet real-time requirements.

[0031] After the vehicle starts, the system enters standby mode. When a preset trigger condition is met—that is, when the vehicle is ignited, engaged in drive (D or R), or when an assisted driving function (such as city NOA or highway NOA) is activated—the system receives a vehicle status signal via the vehicle communication bus (such as CAN or Ethernet) and activates the imaging device accordingly. The imaging device then switches to near-infrared mode, using an infrared fill light to illuminate the driver's face, enabling the acquisition of a high-contrast eye video stream even under limited visible light conditions. This video stream is transmitted in consecutive frames to the subsequent processing module for extracting the pupil diameter and its changing trends.

[0032] Furthermore, the ambient light data of the vehicle's location is obtained. In specific implementation, an ambient light sensor installed on the top of the dashboard collects the current ambient light intensity and color temperature information in real time, and timestamps the eye video stream and the ambient light data.

[0033] An ambient light sensor is a photoelectric detection device that can sense external lighting conditions and output digital ambient light data. Models such as the APDS-9301 or other digital sensors with illuminance (in lux) and color temperature (in Kelvin, K) measurement capabilities can be selected. Its installation position is located at the top of the dashboard near the windshield to avoid obstruction and ensure accurate reflection of the incident light intensity and spectral characteristics of the vehicle's main external light sources.

[0034] An ambient light sensor operates continuously, sampling the ambient light intensity and color temperature multiple times per second, and converting the raw data into standard physical quantities for output. For example, under midday sunlight, the ambient illuminance can reach 80,000 Lux, with a color temperature of approximately 6500 K; while on city roads at night, it may only be 100 Lux, with a lower color temperature. This data is used as background reference information to predict the physiological response baseline that a driver should have under specific lighting conditions.

[0035] During the data acquisition process, precise timestamps can be added to each frame of the eye image and each ambient light sample value. Based on these timestamps, pupil observations at the same or similar times can be matched with the corresponding ambient light data to generate a set of spatiotemporally synchronized multimodal input data pairs. For example, when a frame of an image shows a pupil diameter of 3.0 mm, it can be simultaneously associated with the 50,000 Lux illuminance and 6000 K color temperature information recorded by the ambient light sensor during that period, thereby supporting subsequent comfort model judgments.

[0036] Furthermore, the extraction of pupil state data based on eye images, in its specific implementation, may include the following steps 1.1 and 1.2: Step 1.1: Preprocess each frame of the eye video stream to remove ambient light interference and enhance the contrast of the eye area.

[0037] To eliminate noise interference caused by factors such as changes in in-vehicle lighting, drivers wearing sunglasses, or external strong light reflection, and to highlight the boundary features between the pupil and iris, the original image is preprocessed to improve the recognition of the eye area.

[0038] In one specific implementation, upon receiving each frame of eye video image, a Gaussian blur filter is used to smooth and denoise the image, reducing random pixel noise. Subsequently, histogram equalization is performed to expand the grayscale dynamic range, making the grayscale difference between the pupil area and surrounding tissues more pronounced. For areas with local overexposure or underexposure, adaptive gamma correction is used for compensation. The image processed in this way significantly improves the clarity of the eye structure, especially the contrast between the black part of the eye (pupil) and the white sclera and eyelid edges, which is beneficial for subsequent edge detection processing.

[0039] Step 1.2: Locate the center position of the pupils of both eyes using edge detection and circle fitting algorithm, and calculate the pupil diameter of the current frame to determine the pupil state data.

[0040] The edge detection method described above is used to identify contour lines with abrupt changes in grayscale in an image, thus recognizing the closed boundary of the outer edge of the pupil. Circular fitting, on the other hand, uses mathematical methods to fit the optimal circumference based on the detected edge point set, thereby accurately locating the pupil center coordinates and calculating its diameter. This method exhibits high robustness and is applicable to real-world driving scenarios involving different pupil sizes and partial occlusion (such as eyelashes or eyeglass frames).

[0041] In practical implementation, after image preprocessing, the Canny edge detection algorithm can be used to extract edge information of the eye region. For image regions containing both eyes, the system initially segments the left and right eye ROIs (Regions of Interest) using facial keypoint localization, and performs edge detection independently within the left and right eye regions respectively. Subsequently, the Hough Circle Transform is used to fit a circle to the edge points, searching for the optimal circular contour that conforms to the pupil morphological characteristics (diameter typically in the range of 2.0mm–5.0mm, located in the central region of the eyeball). The center of the fitted circle is taken as the pupil center position, and the radius of the circle multiplied by 2 is the pupil diameter of the current frame. The results for the left and right eyes are averaged after consistency verification, and this average is taken as the pupil state data corresponding to the current frame image, i.e., the pupil diameter data.

[0042] The above methods enable the stable and accurate extraction of driver pupil state data from raw eye video streams. The image preprocessing effectively overcomes the image quality degradation caused by complex lighting conditions, enhancing the discriminability of key features. The combination of edge detection and circular fitting ensures high-precision pupil location and size quantification even under various real-world interference factors. The entire extraction process is fully automated and low-latency, continuously outputting reliable pupil diameter data during vehicle operation, significantly enhancing the safety and comfort of human-computer interaction.

[0043] Furthermore, the above-mentioned prediction of pupillary response range based on pupillary state data and ambient light data using a pupillary comfort model may include the following steps 2.1 and 2.2 in practical implementation: Step 2.1: Input the light intensity and color temperature information into the pupil comfort model.

[0044] The pupil comfort model is an algorithmic model integrated into the data processing and decision-making module for evaluating the visual comfort of drivers. This model uses ambient light data (including light intensity and color temperature) as input variables and, through the mapping relationship between these data and the physiological response of the human eye, determines the expected range of pupil diameter variation, i.e., the pupil response range, under the current environment.

[0045] After ambient light data acquisition, the real-time acquired illuminance (lux) and color temperature (Kelvin, K) values ​​are input into the pupil comfort model. For example, when a vehicle is in a midday bright light environment, the system detects an illuminance of 80,000 Lux and a color temperature of approximately 6500 K; these values ​​are simultaneously fed into the model for processing. Upon receiving the input, the model performs data queries or calculations to determine the normal degree of pupil constriction expected by a healthy adult under such lighting conditions. This process does not rely on a single brightness dimension but comprehensively considers the combined effects of illuminance and color temperature on human eye light sensitivity, improving the scientific rigor and accuracy of the predictions.

[0046] Step 2.2: By using the mapping relationship between pre-configured ambient light data and physiological response in the pupil comfort model, determine the pupil response range corresponding to the pupil state data under the corresponding ambient light data.

[0047] A mapping relationship refers to a pre-defined data structure within a pupil comfort model that reflects the correlation between ambient light data and the physiological response of the human pupil. It is typically stored as a look-up table or piecewise function. This mapping relationship is determined based on extensive experimental observation data and is used to characterize the comfortable range within which most drivers' pupil diameters should fall under specific combinations of light intensity and color temperature. For example, under 50,000 Lux illumination, the expected comfortable pupil diameter range is 2.0 mm to 2.5 mm.

[0048] The pupil comfort model matches and searches its internally stored mapping relationships based on the input light intensity and color temperature information to locate the corresponding pupil response range. For example, when the ambient light intensity is 50,000 Lux, the model calls a preset entry to determine that a normal pupil should be in a significantly constricted state, with its diameter falling between 2.0 mm and 2.5 mm. This range is the expected comfortable pupil range in the current environment. If the actual measured pupil diameter is consistently higher than the upper limit of this range (e.g., 3.0 mm), it indicates that the driver is not producing the expected constriction response, possibly due to insufficient screen brightness leading to an overall darker visual experience. Conversely, if it is much lower than the lower limit, there may be excessive brightness stimulation. This prediction result will serve as the basis for subsequent comparative analysis to determine whether the current display settings are suitable for the driver's actual physiological experience. The mapping relationship can be set with multiple sets of baseline curves according to different population characteristics (e.g., age, visual status) and dynamically optimized in conjunction with personalized learning functions to further improve individual adaptability.

[0049] Through the above steps, not only can external lighting conditions be identified, but also the pupil behavior of the driver in that environment can be inferred based on a preset physiological law model. Compared with the traditional open-loop adjustment method that only relies on a fixed brightness mapping table, this introduces the predictive ability that combines the real physiological response of the human eye, which significantly enhances the accuracy of adaptive adjustment of in-vehicle displays in complex lighting environments and improves visual comfort and safety during driving.

[0050] In practical applications, to further improve visual comfort, if the pupil state data continuously deviates from the pupil response range, the current display parameters of the in-vehicle interactive device are optimized to obtain the target display parameters. In specific implementation, this may include the following steps 3.1 and 3.2: Step 3.1: Compare the pupil state data with the pupil reaction range to determine whether the pupil state data is higher than the upper limit of the pupil reaction range or lower than the lower limit of the pupil reaction range.

[0051] Pupil state data refers to the driver's pupil diameter value extracted in real time from the eye video stream using image processing algorithms. Pupil response range is the range of normal pupil diameters that should appear under certain lighting conditions, predicted by the pupil comfort model based on ambient light data, and is used to characterize the expected ideal physiological response of the driver.

[0052] After obtaining the pupil diameter of the current frame, it is numerically compared with the pupil response range under corresponding environmental conditions output by the pupil comfort model. For example, when the ambient light intensity is 50,000 Lux, the model's preset comfortable pupil range is 2.0 mm to 2.5 mm. If the measured pupil diameter is 3.0 mm, which is higher than the upper limit of the range, it is judged as "the pupil does not constrict normally," indicating that the current overall visual environment may be too dark, and the screen brightness is insufficient, so the human eye does not need to adjust further to avoid light. Conversely, if the measured value is 1.8 mm, which is lower than the lower limit of the range, it indicates that the pupil constricts excessively, and there may be a risk of glare caused by an overly bright screen or strong external light reflection.

[0053] Step 3.2: If the deviation of the pupil state data from the pupil reaction range continues to exceed a preset time threshold, then the display adjustment strategy library is matched to optimize the current display parameters of the in-vehicle interactive device based on the preset adjustment strategies in the display adjustment strategy library to obtain the target display parameters.

[0054] The preset time threshold is a time filtering mechanism set to avoid misjudgments caused by momentary interference (such as blinking, brief occlusion, sensor fluctuations). For example, it can be set to 1 to 3 seconds to ensure that adjustment is only initiated when the deviation is persistent and stable. The display adjustment strategy library is a set of rules stored in the data processing and decision-making module, containing a variety of predefined adjustment schemes for different scenarios, such as strong light comfort strategy, low light comfort strategy, and transient smoothing strategy. Each strategy corresponds to a set of callable display parameter combinations.

[0055] When the detected pupil state data continuously exceeds the pupil response range for a period of time equal to or exceeding a preset time threshold (e.g., more than 2 consecutive seconds), the deviation is confirmed as a genuine and effective discomfort state, rather than random noise. At this point, based on the current environmental change trend and pupil dynamic characteristics, the most suitable adjustment strategy is matched from the display adjustment strategy library. For example, in a bright light environment with persistently dilated pupils, the bright light comfort strategy is invoked, generating instructions to increase brightness, raise the color temperature to a cool white temperature (e.g., 6500K), and switch the UI to a high contrast mode. In scenarios with sudden drops in light, such as entering a tunnel, if the pupils dilate rapidly, a transient smoothing strategy is activated, controlling the screen brightness to first decrease rapidly and then slowly stabilize, while simultaneously switching to a dark theme interface. In low-light environments at night, when the pupils naturally dilate but are close to the lower limit of the comfort range, a dark light comfort strategy is invoked, moderately reducing brightness and adjusting the color temperature to a warm tone (e.g., below 4000K) to reduce visual stimulation. The optimized display parameters are sent as target display parameters to the display execution module to drive the in-vehicle display and UI rendering engine to complete the adjustments.

[0056] The above approach, combined with multi-dimensional preset strategies, achieves coordinated optimization of brightness, color temperature, and user interface layout, enabling the display output to more accurately match the current environment and individual perceptual needs. This improves visual comfort and information readability in complex lighting scenarios, effectively reduces driver distraction and visual fatigue caused by screen discomfort, and enhances the level of intelligence in driving safety and human-computer interaction.

[0057] Furthermore, the display of the in-vehicle interactive device is adjusted according to the target display parameters, including one or more of the following adjustment strategies: Strategy 1: Adjust the backlight brightness and color temperature output values ​​of the in-vehicle interactive device according to the target display parameters so that the screen's luminous characteristics match the current driving environment's lighting conditions.

[0058] Backlight brightness refers to the light intensity level emitted by the backlight system of an in-vehicle display screen (such as an LCD instrument panel or central control screen), used to achieve stepless adjustment within the range of 0 to 1000 nits. Color temperature output value indicates the warmth or coolness of the screen's white light, continuously adjusted between 3000K (warm yellow light) and 7500K (cool white light). By dynamically controlling these two optical parameters, the screen's own luminous properties are kept in harmony with the intensity and hue of the external ambient light, reducing visual contrast.

[0059] Once the decision-making module generates the target display parameters, it sends the brightness and color temperature instructions to the display execution module. For example, under midday sunlight, with ambient light reaching 80,000 Lux and a cool color temperature, the system automatically increases the screen brightness to nearly 1000 nits and sets the color temperature to above 6500K to ensure that information is clearly visible and not drowned out by ambient light due to excessive darkness. In low-light environments at night, the system proactively reduces the brightness to the 100–200 nits range and switches to a warm color temperature output of 3000–4000K to avoid glaring blue light interfering with the driver's night vision. This adjustment method not only improves readability but also reduces eye fatigue caused by frequent adaptation between ambient light and screen light, achieving visual fusion between the screen light source and natural / artificial lighting environments.

[0060] Strategy 2: When a vehicle is detected to be rapidly transitioning from a bright environment to a dark environment, the brightness transition curve is adjusted based on the dynamic rate of change of pupil state data to achieve smooth visual adaptation.

[0061] The dynamic rate of change of pupil state data refers to the amount of change in pupil diameter per unit time (e.g., mm / s), used to characterize the physiological response speed of the human eye to sudden changes in light intensity. The brightness transition curve refers to the adjustment path of screen brightness over time. Traditional solutions often use linear or fixed exponential decay methods, while this strategy dynamically adjusts the shape of this curve based on actual physiological feedback, thereby improving the personalization and adaptability of display adjustment.

[0062] In typical scenarios, such as when a vehicle enters a tunnel, ambient light drops abruptly from tens of thousands of lux to hundreds of lux within seconds, causing the human pupil to dilate rapidly to enhance light sensitivity. At this time, the rate of pupil dilation (e.g., increasing from 2.2 mm at approximately 1.5 mm / s) is monitored in real time. If the screen brightness is directly and rapidly reduced to an extremely low level using traditional methods, drivers entering a dark area may be unable to see the screen content due to insufficient pupil adaptation; conversely, if the reduction is too slow, it may cause temporary glare. Therefore, this embodiment employs a transient smoothing strategy, dynamically planning the brightness reduction trajectory based on the current pupil dilation rate. Initially, a relatively rapid reduction in brightness is allowed to avoid overexposure. Subsequently, as the pupil adaptation process slows down, the slope of the brightness reduction gradually decreases, eventually stabilizing at an adaptation value that ensures visibility without irritating the vision (e.g., 22% brightness). This process achieves a high degree of synchronization between brightness adjustment and physiological adaptation rhythm, significantly improving visual continuity and comfort in transient scenarios.

[0063] Strategy 3 triggers the user interface rendering engine of the in-vehicle interactive device to switch display modes, changing the display theme and / or information layout of the user interface.

[0064] Display modes include, but are not limited to, day mode, night mode, and high contrast mode. Each display mode corresponds to a specific theme style (such as background color and text color) and information organization logic (such as font size and element density).

[0065] When a deep visual adaptation is deemed necessary, in addition to physical layer adjustments, the UI rendering engine is instructed to switch modes. For example, in bright light environments with high brightness output, the system automatically activates a high-contrast mode. In this mode, the speedometer numbers on the dashboard become bold white characters, the background turns dark gray or black, the borders are thickened, unnecessary icons are minimized, and core driving information is highlighted. In low-light environments, a dark theme is switched to, with the overall interface using black and dark gray as the main colors to reduce scattered light, while key numbers are enlarged for easier long-distance visibility. During periods of heightened attention or fatigue warnings, the information layout is simplified, entertainment controls are hidden, and navigation and safety prompts are focused. This synergistic effect of interface-level adjustments and optical parameters generates a multi-dimensional human-centric optimization system, comprehensively improving the effectiveness of information delivery and the user-friendliness of interaction.

[0066] By applying or combining the above three adjustment strategies independently, a closed-loop human-machine interaction system with the driver's physiological state as the core feedback source is constructed, which significantly enhances visual comfort, information readability and driving safety in complex driving environments.

[0067] Optionally, to improve the accuracy and efficiency of adjustments, a personal visual preference profile can be created for identified drivers, recording pupil state data that has reached a stable state after adjustments under different ambient light conditions. When the driver logs into the system again, under the same or similar ambient light conditions, the target pupil state data corresponding to the ambient light data in the historical records can be directly retrieved. When adjusting the display, the target pupil state data is used as the adjustment reference benchmark, and the system stabilizes at the adjustment reference benchmark, or the adjustment is optimized based on the adjustment reference benchmark.

[0068] For example, after the vehicle starts and driver facial recognition is completed, the system searches the database to see if the user's personal visual preference profile exists. If it exists, the profile is activated; if it is the first time using the system, a new profile is created and the system enters the learning phase. During daily driving, whenever the system executes a complete closed-loop adjustment process and confirms that the current pupil state has stabilized within a comfortable range (e.g., changes less than 0.1 mm within 3 consecutive seconds), and the ambient light data remains relatively constant (fluctuations less than ±10%), the system determines that the adjustment result is valid and stores the ambient light data (e.g., illuminance 50,000 Lux, color temperature 6000 K) and the corresponding stable pupil diameter value (e.g., 3.0 mm) as a set of correlated data points in the driver's personal profile. Through repeated recording, the system gradually constructs the driver's personal comfort baseline under multiple typical lighting scenarios.

[0069] When the same driver drives the vehicle again, and the system detects that the current ambient light data is similar to a record in the system's archive (e.g., again under illumination conditions of approximately 50,000 Lux), the system no longer starts from the default adjustment curve. Instead, it directly extracts the driver's historical target pupil state data (e.g., 3.0 mm) under this environment and uses it as the adjustment reference benchmark. Subsequent adjustments aim to bring the measured pupil diameter close to and stabilize at this benchmark, dynamically outputting matching brightness, color temperature, and UI mode commands. For older drivers and other groups with weaker pupil adjustment abilities, their archives typically record larger stable pupil diameter values. Based on this, the system proactively provides a higher initial brightness setting, thus achieving a comfortable state more quickly. Furthermore, the system can fine-tune and update the benchmark based on newly acquired data, achieving a continuous optimization learning mechanism.

[0070] To further improve the accuracy of this adjustment strategy, the driver's pupil state data can be continuously monitored after each display adjustment. If the adjusted pupil state data still does not fall within the corresponding pupil response range, a second fine-tuning is performed, and the deviation between the current pupil state data and the pupil response range is recalculated. Based on the deviation, the current display parameters of the in-vehicle interactive device are updated and optimized to obtain the updated target display parameters until the pupil state data stabilizes within the pupil response range.

[0071] In one implementation, after completing the initial adjustment based on the target display parameters (such as increasing brightness or switching UI modes), the control process does not immediately end. Instead, it continues to acquire the latest pupil state data at a high frequency (e.g., once every 100 milliseconds) and compare it with the pupil response range corresponding to the current ambient light conditions. For example, in a strong light scene adjustment, the system increases the screen brightness to 95%, but monitoring reveals that the driver's pupil diameter remains at 2.8 mm, higher than the preset comfort range upper limit (2.5 mm), indicating that the screen brightness is still insufficient or there is glare interference, and the human eye has not produced a sufficient contraction response.

[0072] At this point, it is determined that the first round of adjustment did not achieve the expected results, and a second fine-tuning process is initiated. First, the deviation between the current pupil state data and the pupil response range is recalculated. For example, if the measured value is 2.8 mm, while the target range is 2.0–2.5 mm, the deviation is more than 0.3 mm, which is considered significant. Based on this deviation, a more aggressive or refined supplementary strategy is selected from the adjustment strategy library, such as further increasing the brightness to 100%, enhancing the contrast, or locally darkening non-critical areas to reduce overall visual stimulation. The newly generated updated target display parameters are then sent back to the display execution module, driving the display screen and UI rendering engine to complete the parameter refresh.

[0073] This process can be repeated multiple times, with each iteration dynamically assessed and corrected based on the latest physiological feedback, until the pupil diameter is continuously monitored and stabilized within the pupillary response range of the corresponding environment (e.g., maintaining 2.3mm for 2 seconds). Only then is the adjustment confirmed as successful and the process transitions to a maintenance state. Throughout the entire process, the driver's actual physiological response is used as the sole criterion for evaluation, ensuring that the final display truly matches the driver's visual comfort needs and guaranteeing safety, continuity, and comfort during human-computer interaction.

[0074] In summary, this application achieves multi-dimensional adaptive adjustment of in-vehicle displays by integrating ambient light perception and dynamic monitoring of the driver's pupils. Using pupil diameter as a physiological feedback benchmark, the system dynamically optimizes screen brightness, color temperature, and interface layout by combining personalized profiles and a real-time fine-tuning mechanism, significantly improving visual comfort and information readability in complex lighting scenarios. Compared to traditional open-loop adjustment methods, this solution offers advantages such as personalized adaptation, smooth transient response, and verifiable adjustment results, effectively eliminating glare and blind spots, reducing driver fatigue and distraction risks, and comprehensively enhancing driving safety and the intelligent cockpit interaction experience.

[0075] Furthermore, this application embodiment provides a specific display adjustment method for an in-vehicle interactive device, the implementation of which can be found in [reference needed]. Figure 2As shown, the hardware configuration is as follows: Multimodal perception module 101: Ambient light sensor (101a): Employs a digital ambient light sensor, installed at the top of the instrument panel near the windshield, used to detect ambient illuminance in lux and color temperature in Kelvin (K). Driver status monitoring camera (101b): Employs a CMOS image sensor supporting near-infrared imaging, with a resolution of 720P and a frame rate of 30fps, installed inside the instrument panel cover behind the steering wheel to ensure its field of view stably covers the driver's eyes.

[0076] Data Processing and Decision Module 102: This module's functions are handled by the vehicle's main domain controller. The system software running on this controller implements a data fusion and comfort model (102a). This model defines the mapping relationship between ambient light intensity and the expected comfortable pupil diameter range through a pre-defined lookup table. For example, when the ambient light is 50,000 Lux, the expected comfortable pupil diameter range is 2.0 mm to 2.5 mm. Adjustment Strategy Library (102b): This is stored in memory as a data structure; some entries are shown below.

[0077] Display Execution Module 103: In-vehicle Display Screen (103a): Refers to the vehicle's LCD instrument panel, whose backlight system supports stepless brightness adjustment from 0-1000 nits and continuous color temperature adjustment from 3000K-7500K. UI Rendering Engine (103b): Developed based on the QtAutomotive framework, it can dynamically switch the interface between "daytime mode," "nighttime mode," and "high contrast mode" based on received commands, and can adjust the font size of the virtual instrument panel numbers.

[0078] Taking the implementation of this method in a car equipped with a smart cockpit as an example, see [link to relevant documentation]. Figure 3 The flowchart shown illustrates the system's operation process as follows: After the vehicle starts, the system begins to synchronously collect ambient light data and eye video. Ambient light data is captured in real time by a light sensor inside the vehicle cabin, capturing the current ambient brightness value (unit: Lux). Eye video is recorded via an infrared mode activated by a camera directly in front of the driver (supporting penetration through sunglasses), recording detailed images of the eyes at a resolution of 1MP-5MP and a field of view of 40°–70°. The synchronous trigger mechanism automatically activates dual-channel acquisition when the vehicle starts or enters an assisted driving mode (such as city NOA / highway NOA). The trigger signal originates from the vehicle status bus (such as turn signals, reverse gear shifting).

[0079] The driver's real-time pupil diameter was extracted from the video stream using a pupil localization algorithm based on Canny edge detection (steps include Gaussian blur, gradient calculation, non-maximum suppression, double threshold detection, and edge connection) and Hough circle transform. Assuming the ambient light level is 50,000 Lux, the measured pupil diameter is 3.0 mm.

[0080] Input the data into the comfort model; see the comfort model section. Figure 4 As shown. The comfort model indicates that the expected comfortable pupil range at 50,000 Lux is 1.9mm-2.4mm. Since the measured value of 3.0mm is higher than the upper limit of the comfortable range, the model determines the current condition as "too dark" and uncomfortable.

[0081] The decision module then queries the adjustment strategy library and generates the instruction: {Brightness: +35%, Color Temperature: 6500K, UI Mode: High Contrast}.

[0082] The display execution module received the instruction, and the instrument panel backlight brightness was increased from the current 70% to approximately 95%. The color temperature was set to cool white. The UI rendering engine switched the interface to "high contrast mode," at which point the speedometer numbers became bold and white, and the background became dark gray.

[0083] After adjustment, the system continuously monitored the driver's pupil diameter, which contracted from 3.0 mm to 2.3 mm within 2 seconds and then stabilized. This value fell within the current comfortable range, indicating that the adjustment was effective, and the system would maintain this setting. If the pupil failed to enter the comfortable range, the system would initiate a new round of fine-tuning, forming a closed loop.

[0084] A schematic diagram comparing the brightness adjustment curves of this application and conventional solutions in a tunnel scenario is shown below. Figure 5 ,in: Initial state: The vehicle is driving under midday sunlight with an ambient light level of 80,000 Lux and a screen brightness of 100% (1000 nits). The measured pupil diameter is 2.2 mm (in a comfortable state). Upon entering the tunnel (time t0): The vehicle enters the tunnel, and the ambient light level drops sharply to 100 Lux within 2 seconds.

[0085] Traditional solution (dashed line): The ambient light sensor triggers a linear drop in screen brightness to 10% (100 nits) within a short period. This process is abrupt, and after time t1, the screen is too dark for a driver who has just entered a dark environment, making it difficult to read information.

[0086] In this application (solid line): the ambient light sensor also triggers a rapid decrease in brightness. The key difference is that the system simultaneously detects the pupil starting to dilate (e.g., expanding from 2.1mm at a rate of approximately 1.5mm / s). The comfort model determines that the pupil is rapidly dilating to adapt to the dark environment, and visual sensitivity is increasing. If the brightness drops too low at this time, it will result in poor visibility because the pupil has not fully adapted. Therefore, the decision module invokes a transient smoothing strategy to control the brightness curve to decrease rapidly at first and then slowly. The brightness first drops to 30% within 1 second, and then, in the next second, it slowly drops to 22% and stabilizes as the pupil dilation rate slows down. This final value is calculated by the model based on the dynamic response of the pupil, ensuring a smooth transition and optimal visibility. In dark environments, the screen can be seen clearly without internal glare caused by excessively high initial brightness. At the same time, the UI automatically switches to dark mode to further optimize the visual experience.

[0087] In summary, this application employs a personalized learning module to create a profile for each driver who logs in via facial recognition. When driver "User A" repeatedly drives in ambient light around 20,000 Lux, and the system stabilizes their pupil at 2.8 mm through closed-loop adjustment, the system determines this as "User A's" personal comfort baseline in that environment and records it. When "User A" drives the vehicle again in ambient light of 20,000 Lux, the system will no longer start from the default brightness curve, but will directly preload a higher brightness setting that is closer to their personal comfort baseline (pupil 2.8 mm), thus achieving their comfort state faster and more accurately, resulting in a smoother personalized comfort experience. Furthermore, the system can create independent personal profiles for different drivers (login via facial recognition), recording their typical pupil response baseline under different ambient light conditions. For example: Driver A (young): In an environment of 50,000 Lux, their comfortable pupil diameter is 2.2 mm. Driver B (older, with weaker pupil accommodation): In the same environment, their comfortable pupil diameter is 3.0 mm. When the system recognizes driver B, in a 50,000 Lux environment, it will actively set the brightness higher than that of driver A in order to reduce the pupil stimulation of driver B to near his personal comfort baseline (3.0 mm), thereby achieving true personalized comfort.

[0088] In summary, compared with existing technologies, the technical solution provided in this application introduces the driver's own pupillary physiological response as direct feedback, enabling the system to adapt to the visual characteristics of different drivers and improve individual visual comfort. Through precise and smooth response to transient lighting scenarios, it effectively eliminates glare and sudden drops in visibility during screen adjustment, reducing driver distraction and temporary blind spots caused by display discomfort, thus improving driving safety in complex lighting environments. Furthermore, by expanding the adjustment range from single brightness to a multi-dimensional system that coordinates brightness, color temperature, and UI adjustment, the display output can more intelligently and precisely match the current environment and driver's state, enhancing the driver's interactive experience.

[0089] Based on the above method embodiments, this application also provides a display adjustment device for an in-vehicle interactive device, see [link to relevant documentation]. Figure 6 As shown, the device includes the following parts: The acquisition module 610 is used to acquire the driver's eye image and the ambient light data of the vehicle. The data processing module 620 is used to extract pupil state data based on eye images, and to predict the pupil response range based on the pupil state data and ambient light data using a pupil comfort model. The optimization module 630 is used to optimize the current display parameters of the in-vehicle interactive device to obtain the target display parameters if the pupil state data continues to deviate from the pupil reaction range. The display adjustment module 640 is used to adjust the display of the in-vehicle interactive device according to the target display parameters.

[0090] In one feasible implementation, the acquisition module 610 is specifically used for: The driver's eye video stream is acquired by an imaging device installed in the vehicle's cockpit under preset trigger conditions; the preset trigger conditions include at least one of the following: vehicle start-up, engaging a driving gear, or entering an assisted driving mode. An ambient light sensor installed on the top of the dashboard collects real-time information on the light intensity and color temperature of the current environment, and timestamps the eye video stream with the ambient light data.

[0091] In one feasible implementation, the data processing module 620 is specifically used for: Each frame of the eye video stream is preprocessed to remove ambient light interference and enhance the contrast in the eye area; The center position of the pupils of both eyes is located by edge detection and circle fitting algorithm, and the pupil diameter of the current frame is calculated to determine the pupil state data.

[0092] In one feasible implementation, the data processing module 620 is specifically used for: Input the light intensity and color temperature information into the pupil comfort model; By using the mapping relationship between pre-configured ambient light data and physiological response in the pupil comfort model, the pupil response range corresponding to the pupil state data under the corresponding ambient light data is determined.

[0093] In one feasible implementation, the optimization module 630 is specifically used for: Compare pupil state data with pupil reaction range to determine whether pupil state data is higher than the upper limit of pupil reaction range or lower than the lower limit of pupil reaction range; If the deviation of the pupil state data from the pupil reaction range continues to exceed a preset time threshold, the display adjustment strategy library is matched to optimize the current display parameters of the in-vehicle interactive device based on the preset adjustment strategies in the display adjustment strategy library to obtain the target display parameters.

[0094] In one feasible implementation, the above-mentioned display adjustment module 640 is specifically used for: The system controls the in-vehicle interactive device to adjust the backlight brightness and color temperature output value according to the target display parameters, so that the screen's luminous characteristics match the current lighting conditions of the driving environment. When a vehicle is detected to be rapidly transitioning from a bright environment to a dark environment, the brightness transition curve is adjusted based on the dynamic rate of change of pupil state data to achieve smooth visual adaptation. Trigger the user interface rendering engine of the in-vehicle interactive device to switch the display mode, and switch the display theme and / or information layout of the user interface.

[0095] In one feasible embodiment, the above-mentioned device further includes an information recording and recall module, used for: Establish a personal visual preference profile for identified drivers and record pupil state data that has reached a stable state after adjustment under different ambient light data; When the driver logs into the system again, under the same or similar ambient light data, the system directly retrieves the target pupil state data corresponding to the ambient light data from the historical records. When adjusting the display, the target pupil state data is used as the adjustment reference, and the adjustment is stabilized at the adjustment reference, or optimized based on the adjustment reference.

[0096] In one feasible implementation, the above-described apparatus further includes a deviation optimization module, used for: After completing one display adjustment, continuously monitor changes in the driver's pupil state data; If the adjusted pupil state data still does not fall within the corresponding pupil response range, a second fine-tuning is performed to recalculate the degree of deviation between the current pupil state data and the pupil response range. Based on the degree of deviation, the current display parameters of the in-vehicle interactive device are updated and optimized to obtain the updated target display parameters until the pupil state data stabilizes within the pupil response range.

[0097] The display adjustment device for in-vehicle interactive devices provided in this application has the same implementation principle and technical effect as the aforementioned method embodiment. For the sake of brevity, any parts of the display adjustment device for in-vehicle interactive devices not mentioned in the embodiment can be referred to the corresponding content in the aforementioned display adjustment method embodiment for in-vehicle interactive devices.

[0098] This application also provides an electronic device, such as... Figure 7 The diagram shows the structure of the electronic device 100, which includes a processor 71 and a memory 70. The memory 70 stores computer-executable instructions that can be executed by the processor 71. The processor 71 executes the computer-executable instructions to implement any of the above-mentioned display adjustment methods for in-vehicle interactive devices.

[0099] exist Figure 7 In the illustrated embodiment, the electronic device further includes a bus 72 and a communication interface 73, wherein the processor 71, the communication interface 73, and the memory 70 are connected via the bus 72.

[0100] The memory 70 may include high-speed random access memory (RAM) and may also include non-volatile memory, such as at least one disk storage device. Communication between this system network element and at least one other network element is achieved through at least one communication interface 73 (which can be wired or wireless), such as the Internet, wide area network, local area network, metropolitan area network, etc. The bus 72 may be an ISA (Industry Standard Architecture) bus, a PCI (Peripheral Component Interconnect) bus, or an EISA (Extended Industry Standard Architecture) bus, etc. The bus 72 can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 7 The symbol is represented by a single double-headed arrow, but this does not mean that there is only one bus or one type of bus.

[0101] The processor 71 may be an integrated circuit chip with signal processing capabilities. In implementation, each step of the above method can be completed by the integrated logic circuitry in the hardware of the processor 71 or by instructions in software form. The processor 71 can be a general-purpose processor, including a Central Processing Unit (CPU), a Network Processor (NP), etc.; it can also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field-Programmable Gate Array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the method disclosed in the embodiments of this application can be directly embodied in the execution of a hardware decoding processor, or can be executed by a combination of hardware and software modules in the decoding processor. The software modules can reside in random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, registers, or other mature storage media in the art. The storage medium is located in the memory. The processor 71 reads the information in the memory and, in conjunction with its hardware, completes the steps of the display adjustment method of the in-vehicle interactive device in the aforementioned embodiment.

[0102] This application also provides a computer-readable storage medium storing computer-executable instructions. When the computer-executable instructions are called and executed by a processor, the computer-executable instructions cause the processor to implement the above-described display adjustment method for the in-vehicle interactive device. For specific implementation, please refer to the foregoing method embodiments, which will not be repeated here.

[0103] The computer program product of the display adjustment method, electronic device and storage medium of the vehicle interactive device provided in the embodiments of this application includes a computer-readable storage medium storing program code. The instructions included in the program code can be used to execute the methods described in the preceding method embodiments. For specific implementation, please refer to the method embodiments, which will not be repeated here.

[0104] Unless otherwise specifically stated, the relative steps, numerical expressions, and values ​​of the components and steps described in these embodiments do not limit the scope of this application.

[0105] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a processor-executable, non-volatile, 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 a portion 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 program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0106] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some or all of the technical features therein. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of this application.

Claims

1. A display adjustment method for an in-vehicle interactive device, characterized in that, include: Acquire images of the driver's eyes and ambient light data of the vehicle's location; Pupil state data is extracted based on the eye images, and pupil response range is predicted using a pupil comfort model based on the pupil state data and the ambient light data. If the pupil state data continues to deviate from the pupil reaction range, the current display parameters of the in-vehicle interactive device are optimized to obtain the target display parameters; The display of the in-vehicle interactive device is adjusted according to the target display parameters.

2. The display adjustment method for an in-vehicle interactive device according to claim 1, characterized in that, Acquire images of the driver's eyes and ambient light data of the vehicle's location, including: The driver's eye video stream is acquired by an imaging device installed in the vehicle's cockpit under preset trigger conditions; the preset trigger conditions include at least one of vehicle start-up, engaging a driving gear, or entering an assisted driving mode. An ambient light sensor installed on the top of the dashboard collects real-time information on the light intensity and color temperature of the current environment, and timestamps the eye video stream with the ambient light data.

3. The display adjustment method for an in-vehicle interactive device according to claim 2, characterized in that, Pupil state data is extracted based on the eye image, including: Each frame of the eye video stream is preprocessed to remove ambient light interference and enhance the contrast of the eye area; The center position of the pupils of both eyes is located by edge detection and circle fitting algorithm, and the pupil diameter of the current frame is calculated to determine the pupil state data.

4. The display adjustment method for an in-vehicle interactive device according to claim 2, characterized in that, Based on the pupil state data and the ambient light data, a pupil comfort model is used to predict the pupil response range, including: The light intensity and color temperature information are input into the pupil comfort model; By using the mapping relationship between pre-configured ambient light data and physiological response in the pupil comfort model, the pupil response range corresponding to the pupil state data under the corresponding ambient light data is determined.

5. The display adjustment method for an in-vehicle interactive device according to claim 3, characterized in that, If the pupil state data continues to deviate from the pupil response range, the current display parameters of the in-vehicle interactive device are optimized to obtain target display parameters, including: The pupil state data is compared with the pupil reaction range to determine whether the pupil state data is higher than the upper limit of the pupil reaction range or lower than the lower limit of the pupil reaction range. If the deviation of the pupil state data from the pupil reaction range continues to exceed a preset time threshold, a display adjustment strategy library is matched to optimize the current display parameters of the in-vehicle interactive device based on the preset adjustment strategies in the display adjustment strategy library to obtain the target display parameters.

6. The display adjustment method for an in-vehicle interactive device according to claim 4, characterized in that, The display of the in-vehicle interactive device is adjusted according to the target display parameters, including one or more of the following adjustment strategies: Based on the target display parameters, the in-vehicle interactive device is controlled to adjust the backlight brightness and color temperature output values ​​so that the screen's luminous characteristics match the current driving environment's lighting conditions. When a vehicle is detected to be rapidly transitioning from a bright environment to a dark environment, the brightness transition curve is adjusted based on the dynamic rate of change of pupil state data to achieve smooth visual adaptation. The user interface rendering engine of the in-vehicle interactive device is triggered to switch the display mode, and the display theme and / or information layout of the user interface are switched.

7. The display adjustment method for an in-vehicle interactive device according to claim 1, characterized in that, Also includes: Establish a personal visual preference profile for identified drivers and record pupil state data that has reached a stable state after adjustment under different ambient light data; When the driver logs into the system again, under the same or similar ambient light data, the system directly retrieves the target pupil state data corresponding to the ambient light data from the historical records. When adjusting the display, the target pupil state data is determined as the adjustment reference benchmark, and the adjustment is stabilized at the adjustment reference benchmark, or optimized based on the adjustment reference benchmark.

8. The display adjustment method for an in-vehicle interactive device according to claim 1, characterized in that, Also includes: After completing one display adjustment, continuously monitor changes in the driver's pupil state data; If the pupil state data still does not fall within the corresponding pupil reaction range after adjustment, a second fine-tuning is performed, and the deviation between the current pupil state data and the pupil reaction range is recalculated. Based on the degree of deviation, the current display parameters of the in-vehicle interactive device are updated and optimized to obtain the updated target display parameters until the pupil state data is stable within the pupil reaction range.

9. An electronic device, characterized in that, The device includes a processor and a memory, the memory storing computer-executable instructions that can be executed by the processor, the processor executing the computer-executable instructions to implement the display adjustment method of the in-vehicle interactive device according to any one of claims 1 to 8.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions, which, when invoked and executed by a processor, cause the processor to implement the display adjustment method of the in-vehicle interactive device according to any one of claims 1 to 9.

Images