Display screen dynamic control method and system

Abstract

The invention provides a display screen dynamic control method and system, and relates to the technical field of data processing, the method comprises the following steps: constructing a space coordinate system comprising a plurality of entity nodes, the entity nodes comprising a display screen preset angular point, a user binocular vision center and a handheld interaction device; analyzing a relative pose relationship among the nodes by calculating a projection dot product of a space vector corresponding to each node; constructing a dynamic topology network based on the relative pose relationship, and synchronously collecting environment illumination intensity, user fixation point coordinates and user pose data; performing time sequence synchronization and Kalman filtering preprocessing on the acquired multi-modal data to obtain an initial feature set; and generating a spatial calibration coefficient according to the distribution characteristics of the dynamic topology network, and performing normalization compensation on the initial feature set through the calibration coefficient to obtain a calibrated multi-modal sensing feature vector. According to the invention, accurate and intelligent dynamic control is realized.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of data processing, in particular to a display screen dynamic control method and system. BACKGROUND

[0002] With the popularization of intelligent display scenarios, display screen brightness adjustment needs to meet the requirements of visibility and low power consumption at the same time, and the existing technology mainly focuses on dynamic control based on environmental light perception or a single user behavior parameter.

[0003] For example, a certain vehicle-mounted display screen automatic brightness adjustment system collects real-time light intensity through a front-mounted environmental light sensor, combines the light and dark distribution of the current display content of the screen, linearly adjusts the overall backlight brightness according to the preset threshold interval, and adapts to the visual requirements under different road conditions. There are obvious technical defects, which do not consider the relative pose, gaze focus and motion state differences between the user and the display screen, only adjust in a single dimension based on the global environmental light and image content, which leads to insufficient brightness when the user looks down to view the core area of the navigation, brightness mutation affects visual stability during high-speed driving, and cannot differentiate control between the navigation information area and the background area, making it difficult to achieve dynamic balance between power consumption and core information visibility. SUMMARY

[0004] The technical problem to be solved by the present application is to provide a display screen dynamic control method and system, which realizes accurate and intelligent dynamic control.

[0005] To solve the above technical problems, the technical solution of the present application is as follows: In a first aspect, a display screen dynamic control method, the method comprising: Constructing a spatial coordinate system containing a plurality of entity nodes, the entity nodes including display screen preset corner points, user binocular vision centers and handheld interaction devices; analyzing the relative pose relationship between the nodes by calculating the projection dot product of the space vectors corresponding to each node; Based on the relative pose relationship, a dynamic topology network is constructed, and environmental light intensity, user gaze point coordinates and user posture data are synchronously collected; the collected multi-modal data is subjected to time sequence synchronization and Kalman filter preprocessing to obtain an initial feature set; a spatial calibration coefficient is generated according to the distribution characteristics of the dynamic topology network, and the initial feature set is normalized and compensated by the calibration coefficient to obtain a calibrated multi-modal perception feature vector; Based on the multi-modal perception feature vector, the screen focus state is determined according to the user's line of sight focus, and the visual stability requirement is evaluated in combination with the user's motion state; the environmental light intensity data is weighted processed based on the screen focus state and the visual stability requirement to obtain the brightness adjustment urgency and the adjustment instruction of the partition brightness target value; According to the brightness adjustment urgency in the adjustment instruction, the brightness change mode is selected to obtain the backlight control strategy and the partition control strategy; Based on the backlight control strategy and the partition control strategy, differential brightness adjustment is performed on the navigation information area and the background area of the display screen according to the partition brightness target value and the corresponding brightness change mode, so as to realize dynamic balance between power consumption and visibility.

[0006] Further, a spatial coordinate system including a plurality of entity nodes is constructed, the entity nodes including display screen preset corner points, user binocular vision centers and handheld interaction devices; by calculating the projection dot product of the spatial vectors corresponding to each node, the relative pose relationship between each node is analyzed, including: A unified spatial coordinate system is constructed and maintained, and the display screen preset corner points, user binocular vision centers and handheld interaction devices are registered as entity nodes in the coordinate system; Based on the registered entity nodes, a first group of spatial vectors pointing from the user binocular vision center to each display screen preset corner point is defined, and a second group of spatial vectors pointing from the user binocular vision center to the handheld interaction device is defined; By defining the first group and the second group of spatial vectors, the projection dot product of the vectors on the preset coordinate plane is calculated to quantify the spatial geometric relationship between the entity nodes; The obtained projection dot product result is analyzed and converted into the relative orientation and distance between the user and the display screen, and the pointing direction and position of the handheld interaction device relative to the display screen, to obtain the real-time relative pose relationship between each node.

[0007] Further, based on the relative pose relationship, a dynamic topology network is constructed, and environmental light intensity, user gaze point coordinates and user posture data are synchronously collected; the collected multi-modal data is time-synchronized and Kalman filtered for preprocessing to obtain an initial feature set, including: Based on the obtained real-time relative pose relationship, a topology network describing the dynamic connection relationship between each entity node is constructed; Synchronously with the construction process of the dynamic topology network, environmental light intensity, user gaze point coordinates and user posture data are coordinated and collected; The multi-modal raw data is time-synchronized and aligned and Kalman filtered for preprocessing to eliminate time jitter and measurement noise between the data, to obtain an initial feature set.

[0008] Further, a spatial calibration coefficient is generated according to the distribution characteristics of the dynamic topology network, and the initial feature set is normalized and compensated by the calibration coefficient to obtain a calibrated multi-modal perception feature vector, including: According to the real-time distribution characteristics of the constructed dynamic topology network, the corresponding spatial calibration coefficient is obtained; The obtained initial feature set is normalized and compensated by the spatial calibration coefficient to obtain a calibrated multi-modal perception feature vector.

[0009] Furthermore, based on multimodal perception feature vectors, the screen attention state is determined according to the user's gaze focus, and the visual stability requirement is assessed in conjunction with the user's motion state. Based on the screen attention state and visual stability requirements, the ambient light intensity data is weighted to obtain adjustment instructions for brightness adjustment urgency and zone brightness target values, including: Based on the multimodal perception feature vector, user gaze focus data is extracted from the multimodal perception feature vector, and the user's current attention state to the screen is determined. Based on the screen attention status determination, and combined with the user motion state data in the multimodal perception feature vector, the user's visual stability needs are comprehensively evaluated. Based on the determined screen attention state and the assessed visual stability requirements, the ambient light intensity data in the multimodal perception feature vector is weighted and fused to obtain the brightness adjustment urgency. Based on the urgency of brightness adjustment and the determined screen attention status, target brightness values ​​for different functional areas of the display screen are obtained, ultimately forming a complete adjustment command for brightness adjustment urgency and target brightness values ​​for each area.

[0010] Furthermore, based on the urgency of brightness adjustment in the adjustment command, a brightness change mode is selected to obtain the backlight control strategy and zone control strategy, including: Receive and parse the output adjustment command, and extract the brightness adjustment urgency parameter; Receive and parse adjustment commands, and select a matching brightness change curve from multiple predefined brightness change modes; Based on the selected brightness change curve, a global backlight control strategy is obtained, which defines the overall law of brightness change over time. By combining the target brightness values ​​of the zones contained in the adjustment instructions with the selected brightness change curves, a zone control strategy is formulated for the navigation information area and the background area, ultimately resulting in a complete combination of backlight control strategy and zone control strategy.

[0011] Furthermore, based on backlight control and zone control strategies, and according to the zone brightness target values ​​and corresponding brightness change patterns, differentiated brightness adjustments are performed on the navigation information area and background area of ​​the display screen to achieve a dynamic balance between power consumption and visibility, including: Based on the backlight control strategy and the zone control strategy, a first set of brightness control parameters corresponding to the navigation information area and a second set of brightness control parameters corresponding to the background area are obtained, wherein the parameter set includes the target brightness value and the corresponding change mode; Based on the obtained first set of brightness control parameters, a control signal is sent to the navigation information area driving unit of the display screen to drive the area backlight to transition to the target brightness value according to the specified brightness change mode, so as to prioritize the visibility of core information. Based on the obtained second set of brightness control parameters, an independent control signal is sent to the background area driving unit of the display screen to drive the area backlight to adjust to the target brightness value according to the specified brightness change mode, so as to achieve energy saving optimization. By performing parallel and differentiated brightness adjustment operations on the navigation information area and the background area of ​​the display screen, a dynamic balance between the overall power consumption of the display screen and the user's visibility is achieved.

[0012] Secondly, a dynamic control system for a display screen includes: The acquisition module is used to construct a spatial coordinate system containing multiple entity nodes, including preset corner points of the display screen, the user's binocular visual center, and the handheld interactive device; by calculating the projected dot product of the spatial vectors corresponding to each node, the relative pose relationship between each node is analyzed. The calibration module is used to construct a dynamic topology network based on relative pose relationships and simultaneously collect ambient light intensity, user gaze point coordinates, and user pose data; it performs temporal synchronization and Kalman filtering preprocessing on the collected multimodal data to obtain an initial feature set; it generates spatial calibration coefficients based on the distribution characteristics of the dynamic topology network, and normalizes and compensates the initial feature set using the calibration coefficients to obtain the calibrated multimodal perception feature vector. The adjustment module is used to determine the screen attention state based on the user's gaze focus according to the multimodal perception feature vector, and to evaluate the visual stability requirements in combination with the user's motion state; it performs weighted processing on the ambient light intensity data based on the screen attention state and visual stability requirements to obtain adjustment instructions for brightness adjustment urgency and zone brightness target values; it is used to select the brightness change mode according to the brightness adjustment urgency in the adjustment instructions to obtain the backlight control strategy and zone control strategy. The processing module is used to perform differentiated brightness adjustment on the navigation information area and background area of ​​the display screen based on the backlight control strategy and the zoning control strategy, according to the target brightness value of the zoning area and the corresponding brightness change mode, so as to achieve a dynamic balance between power consumption and visibility.

[0013] Thirdly, a computing device includes: One or more processors; A storage device for storing one or more programs that, when executed by one or more processors, cause the one or more processors to implement the method.

[0014] Fourthly, a computer-readable storage medium storing a program that, when executed by a processor, implements the method.

[0015] The above-described solution of the present invention has at least the following beneficial effects: By employing a spatial coordinate system that includes preset corner points of the display screen, the user's binocular visual center, and the handheld interactive device, and resolving relative pose relationships through spatial vector projection dot product, combined with a dynamic topology network to perform temporal synchronization, Kalman filtering preprocessing, and spatial calibration coefficient normalization compensation of ambient light intensity, user gaze point coordinates, and user posture multimodal data, and then generating brightness adjustment urgency and zone brightness target values ​​based on user attention state and visual stability requirements, selecting brightness change modes according to urgency, and formulating backlight control strategies and zone control strategies to perform differentiated brightness adjustment for navigation information areas and background areas, this technology overcomes the technical problems of existing display screen brightness adjustment that rely only on single-dimensional parameters, do not integrate user spatial pose and multimodal behavior data, have insufficient adjustment accuracy, and cannot balance the visibility of core information with power consumption. This results in more precise and intelligent dynamic control of the display screen, prioritizing clear visibility of core information, effectively reducing power consumption in non-core areas, achieving a dynamic balance between power consumption and visibility, and improving the user experience. Attached Figure Description

[0016] Figure 1 This is a flowchart illustrating a dynamic control method for a display screen provided in an embodiment of the present invention.

[0017] Figure 2 This is a schematic diagram of a dynamic control system for a display screen provided in an embodiment of the present invention. Detailed Implementation

[0018] Exemplary embodiments of the present disclosure will now be described in more detail with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be implemented in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.

[0019] like Figure 1 As shown, an embodiment of the present invention proposes a dynamic control method for a display screen, the method comprising the following steps: Step 1: Construct a spatial coordinate system containing multiple entity nodes, including the preset corner points of the display screen, the user's binocular visual center, and the handheld interactive device; analyze the relative pose relationship between the nodes by calculating the projected dot product of the spatial vectors corresponding to each node. Step 2: Construct a dynamic topology network based on relative pose relationships, and simultaneously collect ambient light intensity, user gaze point coordinates, and user pose data; perform temporal synchronization and Kalman filtering preprocessing on the collected multimodal data to obtain an initial feature set; generate spatial calibration coefficients based on the distribution characteristics of the dynamic topology network, and normalize and compensate the initial feature set using the calibration coefficients to obtain the calibrated multimodal perception feature vector. Step 3: Based on the multimodal perception feature vector, determine the screen attention state according to the user's gaze focus, and assess the visual stability requirement in combination with the user's motion state; based on the screen attention state and visual stability requirement, perform weighted processing on the ambient light intensity data to obtain the adjustment instructions for brightness adjustment urgency and zone brightness target value. Step 4: Select the brightness change mode according to the brightness adjustment urgency in the adjustment command to obtain the backlight control strategy and zone control strategy. Step 5: Based on the backlight control strategy and the zone control strategy, perform differentiated brightness adjustment on the navigation information area and the background area of ​​the display screen according to the zone brightness target value and the corresponding brightness change mode, so as to achieve a dynamic balance between power consumption and visibility.

[0020] In this embodiment of the invention, the invention overcomes the technical problems of existing display screen brightness adjustment relying on a single parameter, not integrating user spatial pose and multimodal behavior data, lacking precision in adjustment, and being difficult to balance the visibility of core information with overall power consumption. This results in improved intelligence and precision in dynamic control of the display screen, priority protection for the visibility of core information, effective reduction of power consumption in non-core areas, dynamic balance between power consumption and visibility, and improved user comfort and scene adaptability. The invention also employs a spatial coordinate system that includes preset corner points of the display screen, user binocular visual center, and handheld interactive device. Based on this pose relationship, a dynamic topology network is constructed and multimodal data is collected synchronously. After time synchronization and Kalman filtering preprocessing, normalization compensation is performed using spatial calibration coefficients. Furthermore, the urgency of brightness adjustment and target values ​​for different zones are generated by combining user attention state and visual stability requirements. Brightness change modes are selected according to urgency, and backlight and zone control strategies are formulated.

[0021] In a preferred embodiment of the present invention, step 1 above may include: Step 1.1 involves constructing and maintaining a unified spatial coordinate system, and registering the display screen's preset corner points, the user's binocular visual center, and the handheld interactive device as entity nodes within this coordinate system. Specifically, this includes: establishing a unified three-dimensional spatial coordinate system based on the installation position of the vehicle-mounted display screen; setting the plane where the display screen is located as the reference plane; determining the X, Y, and Z axis directions of the coordinate system and fixing the origin; locking the physical positions of the four corners using the display screen's hardware-preset position recognition module, and using these four positions as the display screen's preset corner points; capturing the user's binocular visual center in real-time using the vehicle-mounted camera to capture the three-dimensional coordinates of both eyes; obtaining the real-time positioning data of the handheld interactive device through the vehicle-mounted Bluetooth or wireless communication module, and using the position corresponding to this positioning data as the reference point for the handheld interactive device; and finally, recording these three types of position information into the three-dimensional spatial coordinate system one by one to complete the registration of all entity nodes.

[0022] Step 1.2: Based on the registered entity nodes, define a first set of spatial vectors pointing from the user's binocular visual center to preset corner points of each display screen, and a second set of spatial vectors pointing from the user's binocular visual center to the handheld interactive device. Specifically, this includes: extracting the coordinates of the user's binocular visual center as the starting point coordinates in the 3D spatial coordinate system where entity nodes have been registered; extracting the coordinates of the four preset corner points of each display screen as the ending point coordinates; and generating four spatial vectors from the user's binocular visual center to the preset corner points of each display screen based on the numerical differences between the starting point coordinates and each ending point coordinate, forming the first set of spatial vectors; and extracting the reference point coordinates of the handheld interactive device as the ending point coordinates; and again, generating a spatial vector from the user's binocular visual center to the handheld interactive device based on the numerical differences between the starting point coordinates and the ending point coordinates, forming the second set of spatial vectors.

[0023] Step 1.3: Using the defined first and second sets of spatial vectors, calculate the projection dot product of the vectors on the preset coordinate planes to quantify the spatial geometric relationship between the entity nodes. Specifically, this includes: pre-setting an XY coordinate plane parallel to the display screen reference plane and an XZ coordinate plane perpendicular to the display screen reference plane as preset coordinate planes; projecting the first and second sets of spatial vectors onto these two preset coordinate planes respectively to obtain the projection vectors of each set of spatial vectors on different planes; calculating the dot product values ​​between each projection vector in the first set and between the projection vectors in the second set and each projection vector in the first set according to the calculation logic of the spatial vector projection dot product; determining the directional relationship between vectors by the sign of the dot product value, and reflecting the angle between vectors by the magnitude of the dot product value, thereby quantifying the relative geometric position association of all entity nodes in space.

[0024] Step 1.4 involves parsing the obtained projection dot product results and converting them into the relative orientation and distance between the user and the display screen, as well as the pointing direction and position of the handheld interactive device relative to the display screen, to obtain the real-time relative pose relationships between each node. Specifically, this includes: comprehensively analyzing all obtained projection dot product results; determining the orientation of the user's binocular visual center relative to the display screen based on the dot product values ​​corresponding to the first set of spatial vectors; calculating the straight-line distance between the user and the display screen by combining the dot product values ​​with the coordinate system scale; determining the approximate direction of the handheld interactive device relative to the display screen based on the dot product results of the second set of spatial vectors and the first set of spatial vectors; and then accurately locating its specific orientation and physical position relative to the display screen by combining the coordinate data of the handheld interactive device's reference point in the coordinate system. By continuously updating the dot product results and coordinate data, the relative pose relationships between the user and the display screen, and between the handheld interactive device and the display screen, are obtained and updated in real time.

[0025] In this embodiment of the invention, by constructing a unified spatial coordinate system and registering the preset corner point of the display screen, the user's binocular visual center, and the handheld interactive device as entity nodes, defining a spatial vector pointing from the user's binocular center to the corner point of the display screen and the handheld device, and quantifying the spatial geometric relationship by calculating the dot product of the vector's projection on the preset coordinate plane, and parsing and converting it into the relative orientation and distance between the user and the display screen, and the orientation and position of the handheld device relative to the display screen to obtain the real-time relative pose relationship, the technical problem in the prior art of being unable to accurately analyze the dynamic spatial pose relationship between the user, the display screen, and the interactive device, resulting in a lack of accurate spatial reference for subsequent adjustments, is overcome. Thus, the technical effect of capturing the relative pose between each entity node in real time and accurately is achieved, providing a reliable spatial basis for the dynamic control of the display screen, and improving the adaptability and accuracy of the overall adjustment strategy is achieved.

[0026] In a preferred embodiment of the present invention, step 2 above may include: Step 2.1: Based on the obtained real-time relative pose relationships, construct a topology network describing the dynamic connection relationships between each entity node. Specifically, this includes: based on the obtained real-time relative pose relationships between the user and the display screen, and between the handheld interactive device and the display screen, determine the dynamic positional associations of each entity node in space. The preset corner point of the display screen, the user's binocular visual center, and the handheld interactive device are respectively regarded as independent nodes of the topology network. Initial connection relationships are established based on the relative distance and the degree of fit of the relative orientation between each node. As the user's head rotates, body moves, or the position of the handheld interactive device changes, the connection strength and connection status between each node are updated in real time, so that the topology network can dynamically reflect the spatial association of entity nodes at different times, forming a complete dynamic topology network.

[0027] Step 2.2, synchronized with the construction process of the dynamic topology network, coordinates and collects ambient light intensity, user gaze coordinates, and user posture data. Specifically, this includes: while the dynamic topology network begins construction and is continuously updated, a multi-device collaborative acquisition mechanism is initiated. Real-time ambient light intensity data inside and outside the vehicle is captured using an onboard ambient light sensor; the user's eye movement trajectory is tracked using an onboard high-definition camera to obtain the coordinates of the gaze point on the display screen; and the user's posture data, such as sitting posture, head rotation angle, and body sway amplitude, is collected using an onboard posture sensor. A unified acquisition time interval is set to ensure that the acquisition rhythm of the three types of data is consistent with the update frequency of the dynamic topology network, achieving synchronous acquisition of spatial correlation information and multimodal data.

[0028] Step 2.3 involves performing temporal synchronization alignment and Kalman filtering preprocessing on the multimodal raw data to eliminate temporal jitter and measurement noise between data, obtaining an initial feature set. Specifically, this includes: collecting all raw data on ambient light intensity, user gaze coordinates, and user posture; extracting the acquisition timestamp corresponding to each data point; sorting the three types of data according to chronological order; matching and aligning data with the same or adjacent timestamps to eliminate temporal jitter caused by acquisition delays from different devices; processing the aligned multimodal data using the Kalman filtering method to filter out interference factors such as instantaneous fluctuations in ambient light intensity, slight drifts in gaze coordinates, and measurement errors in posture data, retaining effective feature information in the data; and finally integrating and summarizing the processed data to form a well-structured and reliable initial feature set.

[0029] In this embodiment of the invention, a topological network describing the dynamic connection relationship between various entity nodes is constructed based on real-time relative pose relationships. This network synchronously and coordinately collects multimodal data on ambient light intensity, user gaze coordinates, and user posture. Furthermore, the original multimodal data undergoes temporal synchronization alignment and Kalman filtering preprocessing to eliminate time jitter and measurement noise. This overcomes the technical problems in existing technologies where multimodal data acquisition lacks synchronous support with the spatial association of entity nodes, data exhibits temporal deviations and measurement interference, resulting in insufficient reliability of feature data and an inability to provide accurate input for subsequent adjustments. Consequently, this invention achieves the technical effect of establishing dynamic linkage between the spatial association of entity nodes and multimodal data, obtaining a high-quality initial feature set with consistent timing and noise elimination. This lays a solid data foundation for the accurate generation of subsequent brightness adjustment commands, improving the robustness and accuracy of dynamic control of the display screen.

[0030] In a preferred embodiment of the present invention, step 2 above may include: Step 2.4: Based on the real-time distribution characteristics of the constructed dynamic topology network, obtain the corresponding spatial calibration coefficients. Specifically, this includes: continuously monitoring the real-time distribution status of each entity node in the dynamic topology network, analyzing the range of changes in relative distances between nodes, the stability of relative orientations, and the density characteristics of connection relationships. Combining the positional variation patterns of the user and display screen in the vehicle scenario and the usage trajectory of handheld interactive devices, establish the correspondence between distribution characteristics and spatial calibration coefficients; based on the node distribution density, spatial span, and dynamic change rate of the current topology network, dynamically calculate spatial calibration coefficients adapted to the current spatial scenario to ensure that the coefficients accurately reflect the real-time spatial association characteristics of entity nodes.

[0031] Step 2.5 involves normalizing and compensating the initial feature set using spatial calibration coefficients to obtain a calibrated multimodal perception feature vector. This includes extracting various data from the initial feature set, such as ambient light intensity, user gaze coordinates, and user posture. For different types of data, the obtained spatial calibration coefficients are applied for normalization and compensation. For example, the effective weights of ambient light intensity data at different spatial locations are adjusted based on the calibration coefficients, the gaze coordinate deviation caused by changes in the relative pose between the user and the display screen is corrected, the adaptability of user posture data to the current spatial scene is calibrated, and the compensated data are integrated and sorted to form a multimodal perception feature vector that can accurately match the real-time spatial scene and eliminate spatial difference interference.

[0032] In this embodiment of the invention, by employing a technique of obtaining corresponding spatial calibration coefficients based on the real-time distribution characteristics of the constructed dynamic topology network, and then normalizing and compensating the initial feature set using these spatial calibration coefficients, the technical problem of insufficient spatial adaptability and limited feature accuracy of multimodal data, which is caused by the initial feature set not being specifically calibrated in conjunction with the spatial distribution differences of entity nodes, thus failing to accurately reflect the dynamic changes of the scene, is overcome. This achieves the technical effect of enabling multimodal perception feature vectors to fit the real-time spatial scene, improving data accuracy and reliability, providing high-quality feature input for the accurate generation of brightness adjustment commands, and further enhancing the dynamic control adaptability and intelligence level of the display screen.

[0033] In a preferred embodiment of the present invention, step 3 above may include: Step 3.1: Based on the multimodal perception feature vector, extract the user's gaze focus data from the multimodal perception feature vector and determine the user's current attention state to the screen. Specifically, this includes: extracting gaze focus-related data such as the coordinates of the user's gaze point, gaze duration, and gaze movement trajectory from the calibrated multimodal perception feature vector; setting gaze focus determination criteria; if the user's gaze point continuously falls on the navigation information area of ​​the display screen and the duration of the gaze exceeds a preset threshold, it is determined to be a high attention state; if the gaze point briefly switches between different areas of the display screen without a fixed area of ​​stay, it is determined to be a general attention state; if the gaze point is out of the display screen range for a long time or does not form an effective stay, it is determined to be an unattended state, thereby clarifying the user's current attention state to the screen.

[0034] Step 3.2: Based on the determined screen attention state, and combined with user motion state data from the multimodal perception feature vector, comprehensively evaluate the user's visual stability requirements. Specifically, this includes: based on the determined screen attention state, extracting motion state data such as the user's body swaying amplitude, head turning frequency, and degree of posture change from the multimodal perception feature vector; and combining this with the driving speed information in the in-vehicle scenario to comprehensively evaluate the visual stability requirements: if the user is in a highly attentive state and the driving speed is relatively fast, with frequent body swaying or head turning, it is determined to have high visual stability requirements; if the user is in a generally attentive state and the driving speed is relatively slow, with a relatively stable body posture, it is determined to have medium visual stability requirements; if the user is in an unattended state, regardless of the motion state, it is determined to have low visual stability requirements.

[0035] Step 3.3: Based on the determined screen attention state and the assessed visual stability requirements, the ambient light intensity data in the multimodal perception feature vector is weighted and fused to obtain the brightness adjustment urgency. Specifically, this includes: setting corresponding weight coefficients according to different screen attention states and visual stability requirements: high attention state and high visual stability requirements correspond to higher weights, general attention state and medium visual stability requirements correspond to medium weights, and no attention state and low visual stability requirements correspond to lower weights. The set weight coefficients are then weighted and fused with the ambient light intensity data in the multimodal perception feature vector. Combined with the real-time change amplitude of ambient light intensity, the brightness adjustment urgency is comprehensively obtained. The urgency is divided into three levels: high, medium, and low. High urgency occurs when there is a sudden change in ambient light and the user's need is urgent, while low urgency occurs when the ambient light is stable and the user's need is low.

[0036] Step 3.4: Based on the urgency of brightness adjustment and the determined screen attention state, obtain the target brightness values ​​for different functional areas of the display screen, ultimately forming a complete adjustment instruction for brightness adjustment urgency and target brightness values ​​for each area. Specifically, this includes: setting target brightness values ​​for the navigation information area and the background area of ​​the display screen according to the urgency of brightness adjustment and the user's attention state; under high urgency and high attention state, setting a higher target brightness for the navigation information area to ensure clear visibility, and setting a moderate target brightness for the background area to balance energy saving; under medium urgency and general attention state, setting a medium target brightness for the navigation information area, and appropriately reducing the target brightness for the background area; under low urgency and no attention state, maintaining basic visible brightness for the navigation information area, and setting a lower target brightness for the background area to maximize energy saving; integrating the brightness adjustment urgency level with the target brightness values ​​for the two areas to form a complete brightness adjustment instruction.

[0037] In this embodiment of the invention, the technical means of extracting user gaze focus data based on multimodal perception feature vectors to determine screen attention status, combining attention status with user motion status to assess visual stability requirements, and then weighting and fusing ambient light intensity data based on both to obtain brightness adjustment urgency, and finally generating partitioned brightness target values ​​for different functional areas based on urgency and attention status to form complete adjustment instructions, overcomes the technical problems of existing technologies that do not combine real-time user attention and motion status, lack targeted processing of ambient light data, resulting in brightness adjustment failing to match actual user visual needs, insufficient visibility of core areas, and difficulty in achieving precise partitioned control. This achieves the technical effect of accurately capturing user visual focus and stability requirements, generating brightness adjustment urgency and partitioned target values ​​adapted to the scene, ensuring brightness adaptation of core information areas, reducing the impact of brightness abrupt changes on visual stability, realizing precise matching of dynamic display adjustment with user needs, and improving the balance between visibility and power consumption.

[0038] In a preferred embodiment of the present invention, step 4 above may include: Step 4.1: Receive and parse the adjustment command and extract the brightness adjustment urgency parameter. Specifically, this includes: receiving the complete output adjustment command, which contains the brightness adjustment urgency level and the target brightness values ​​for the navigation information area and the background area; parsing the command to separate the brightness adjustment urgency parameter and clarify the urgency level of the current adjustment requirement, such as identifying the urgency level as high, medium, or low.

[0039] Step 4.2: Based on the extracted brightness adjustment urgency, select a matching brightness change curve from multiple predefined brightness change modes. Specifically, this includes: based on multiple predefined brightness change modes, each mode corresponds to a specific brightness change curve. The high urgency mode corresponds to a fast and smooth rising or falling curve to ensure that the brightness adjustment is completed in a short time; the medium urgency mode corresponds to a moderately gradual curve to balance the adjustment speed and visual comfort; and the low urgency mode corresponds to a slowly changing curve to reduce the interference of brightness fluctuations on the user. Based on the extracted brightness adjustment urgency parameter, select a matching brightness change curve from the predefined modes. For example, a fast and smooth curve is selected for high urgency, and a slowly changing curve is selected for low urgency.

[0040] Step 4.3: Based on the selected brightness change curve, a global backlight control strategy is obtained. The strategy defines the overall pattern of brightness change over time, specifically including: based on the selected brightness change curve, a global backlight control strategy is formulated. The strategy clarifies the pattern of overall brightness change of the display screen over time, including the time point when brightness adjustment begins, the brightness change amplitude within each time period, the total time to reach the target brightness, and the smoothing process during the transition. For example, if a fast smoothing curve corresponding to high urgency is selected, the strategy will stipulate that the brightness will transition from the current brightness to the target brightness range within 3 seconds, and the brightness change amplitude per second will be uniform to avoid sudden increases and decreases.

[0041] Step 4.4: Combining the target brightness values ​​for each zone in the adjustment command with the selected brightness change curve, formulate zone control strategies for the navigation information area and the background area. This results in a complete combination of backlight control and zone control strategies. Specifically, this includes: extracting the target brightness values ​​for each zone in the adjustment command for the navigation information area and the background area; and, based on the selected brightness change curve, formulating zone control strategies for each area. For the navigation information area, determine the brightness starting point, the rate of change at each time period, and the final stable value based on its target brightness value and curve, ensuring that the core information area reaches the target brightness at an appropriate pace. For the background area, similarly, formulate independent change parameters based on its target brightness value and curve. For example, while ensuring navigation visibility is not affected, adjust the brightness at a rate slightly slower than that of the navigation area. Integrate the global backlight control strategy with the zone control strategies for both areas to obtain a complete control strategy combination.

[0042] In this embodiment of the invention, by receiving and parsing adjustment commands to extract brightness adjustment urgency parameters, selecting matching brightness change curves from predefined modes based on the urgency, generating a global backlight control strategy, and then combining the partitioned brightness target values ​​in the adjustment commands with the selected brightness change curves to formulate partitioned control strategies for navigation information areas and background areas, a complete strategy combination is formed. Therefore, this overcomes the technical problems in the prior art, such as the lack of brightness adjustment change modes adapted to the urgency of demand, the failure of global adjustment to take into account partition differences, resulting in brightness abrupt changes affecting visual stability, and insufficient precision of partitioned control. This achieves smooth brightness changes to adapt to scene requirements, with global and partitioned strategies working together to avoid brightness abrupt changes in scenarios such as high-speed driving, and can specifically ensure the visibility of core areas and energy saving of non-core areas, further optimizing the dynamic balance between power consumption and visibility, and improving the precision and intelligence of display control.

[0043] In a preferred embodiment of the present invention, step 5 above may include: Step 5.1: Based on the backlight control strategy and the zone control strategy, obtain a first set of brightness control parameters corresponding to the navigation information area and a second set of brightness control parameters corresponding to the background area. The parameter sets include target brightness values ​​and corresponding change patterns. Specifically, based on the determined global backlight control strategy and the zone control strategies for the navigation information area and the background area, decompose the specific control parameters adapted to the two areas respectively. For the navigation information area, extract the target brightness value that ensures the visibility of core information and the corresponding brightness change pattern to form the first set of brightness control parameters. For the background area, extract the target brightness value with energy saving as the core and the corresponding brightness change pattern to form the second set of brightness control parameters. Both parameter sets include specific numerical standards and change rhythm requirements.

[0044] Step 5.2: Based on the obtained first brightness control parameter set, a control signal is sent to the navigation information area driving unit of the display screen to drive the area backlight to transition to the target brightness value according to the specified brightness change mode, so as to prioritize the visibility of core information. Specifically, this includes: converting the first brightness control parameter set into a control signal that the navigation information area driving unit can recognize; after receiving the signal, the driving unit starts the area backlight adjustment mechanism and strictly follows the brightness change mode specified in the parameter set to control the backlight source to transition from the current brightness to the target brightness value. The entire transition process remains smooth and stable, avoiding sudden increases or decreases in brightness, ensuring that users can clearly identify the core content when viewing navigation information and meeting the visibility requirements.

[0045] Step 5.3: Based on the obtained second brightness control parameter set, send an independent control signal to the background area driving unit of the display screen to drive the area backlight to adjust to the target brightness value according to the specified brightness change mode, so as to achieve energy saving optimization. Specifically, this includes: simultaneously sending an independent control signal to the background area driving unit of the display screen. This signal is converted from the second brightness control parameter set and does not interfere with the control signal of the navigation information area. The background area driving unit adjusts the backlight brightness of the background area to the target brightness value according to the instructions in the signal and the specified brightness change mode. The adjustment process is based on the premise of not affecting the visibility of navigation information. By reducing the brightness consumption of non-core areas, the overall energy saving optimization of the display screen is achieved.

[0046] Step 5.4 involves performing parallel and differentiated brightness adjustment operations on the navigation information area and the background area of ​​the display screen to achieve a dynamic balance between the overall power consumption of the display screen and user visibility. Specifically, the driving units of the navigation information area and the background area synchronously perform their respective brightness adjustment operations. The two areas operate independently and in parallel according to differentiated parameters. The navigation information area is maintained at a brightness level that meets the visibility requirements, while the background area is maintained at a low-power brightness level. At the same time, the brightness transition of both areas follows a preset mode to avoid impacting the user's vision. Through the parallel and differentiated adjustment method, the clear presentation of core information is ensured, unnecessary power consumption is minimized, and ultimately a dynamic balance between the overall power consumption of the display screen and user visibility is achieved.

[0047] In this embodiment of the invention, by employing a backlight control strategy and a zone control strategy, the brightness control parameter sets containing the target brightness value and corresponding change mode of the navigation information area and the background area are obtained respectively, and independent control signals are sent to the driving units of the two areas to drive the two areas to perform differentiated brightness adjustment in parallel according to their respective specified modes. Therefore, the technical problems of existing technologies, such as the inability to perform targeted brightness control on different areas of the display screen, the difficulty in ensuring the visibility of core information areas, the easy sudden changes in brightness adjustment, and the imbalance between overall power consumption and visibility, are overcome. This achieves the technical effect of prioritizing the clear visibility of core areas such as navigation information, while realizing energy-saving optimization of the background area, smooth brightness transition without affecting visual stability, and ultimately achieving a dynamic balance between the overall power consumption of the display screen and user visibility, thereby improving the user experience in complex scenarios.

[0048] like Figure 2 As shown, embodiments of the present invention also provide a dynamic control system for a display screen, comprising: The acquisition module is used to construct a spatial coordinate system containing multiple entity nodes, including preset corner points of the display screen, the user's binocular visual center, and the handheld interactive device; by calculating the projected dot product of the spatial vectors corresponding to each node, the relative pose relationship between each node is analyzed. The calibration module is used to construct a dynamic topology network based on relative pose relationships and simultaneously collect ambient light intensity, user gaze point coordinates, and user pose data; it performs temporal synchronization and Kalman filtering preprocessing on the collected multimodal data to obtain an initial feature set; it generates spatial calibration coefficients based on the distribution characteristics of the dynamic topology network, and normalizes and compensates the initial feature set using the calibration coefficients to obtain the calibrated multimodal perception feature vector. The adjustment module is used to determine the screen attention state based on the user's gaze focus according to the multimodal perception feature vector, and to evaluate the visual stability requirements in combination with the user's motion state; it performs weighted processing on the ambient light intensity data based on the screen attention state and visual stability requirements to obtain adjustment instructions for brightness adjustment urgency and zone brightness target values; it is used to select the brightness change mode according to the brightness adjustment urgency in the adjustment instructions to obtain the backlight control strategy and zone control strategy. The processing module is used to perform differentiated brightness adjustment on the navigation information area and background area of ​​the display screen based on the backlight control strategy and the zoning control strategy, according to the target brightness value of the zoning area and the corresponding brightness change mode, so as to achieve a dynamic balance between power consumption and visibility.

[0049] The above description represents the preferred embodiments of the present invention. It should be noted that those skilled in the art can make various improvements and modifications without departing from the principles of the present invention, and these improvements and modifications should also be considered within the scope of protection of the present invention.

Claims

1. A dynamic control method for a display screen, characterized in that, The method includes: A spatial coordinate system containing multiple entity nodes is constructed, including the preset corner points of the display screen, the user's binocular visual center, and the handheld interactive device; the relative pose relationship between the nodes is analyzed by calculating the projected dot product of the spatial vectors corresponding to each node. A dynamic topology network is constructed based on relative pose relationships, and ambient light intensity, user gaze point coordinates, and user pose data are collected synchronously. The collected multimodal data are subjected to temporal synchronization and Kalman filtering preprocessing to obtain an initial feature set. Spatial calibration coefficients are generated according to the distribution characteristics of the dynamic topology network, and the initial feature set is normalized and compensated by the calibration coefficients to obtain the calibrated multimodal perception feature vector. Based on multimodal perception feature vectors, the screen attention state is determined according to the user's gaze focus, and the visual stability requirement is evaluated in combination with the user's motion state. Based on the screen attention state and visual stability requirements, the ambient light intensity data is weighted to obtain the adjustment instructions for brightness adjustment urgency and zone brightness target values. Select the brightness change mode according to the urgency of brightness adjustment in the adjustment command to obtain the backlight control strategy and zone control strategy; Based on backlight control and zone control strategies, differentiated brightness adjustments are performed on the navigation information area and background area of ​​the display screen according to the zone brightness target value and the corresponding brightness change mode, so as to achieve a dynamic balance between power consumption and visibility.

2. The dynamic control method for the display screen according to claim 1, characterized in that, A spatial coordinate system is constructed containing multiple entity nodes, including preset corner points of the display screen, the user's binocular visual center, and the handheld interactive device. The relative pose relationships between the nodes are analyzed by calculating the projected dot product of the spatial vectors corresponding to each node, including: Construct and maintain a unified spatial coordinate system, and register the preset corner points of the display screen, the user's binocular visual center, and the handheld interactive device as entity nodes in this coordinate system; Based on the registered entity nodes, define a first set of spatial vectors pointing from the user's binocular visual center to the preset corner points of each display screen, and a second set of spatial vectors pointing from the user's binocular visual center to the handheld interactive device; By defining the first and second sets of spatial vectors, the dot product of the vector projections on the preset coordinate plane is calculated to quantify the spatial geometric relationship between the entity nodes. The obtained projection dot product results are analyzed and converted into the relative orientation and distance between the user and the display screen, as well as the pointing orientation and position of the handheld interactive device relative to the display screen, so as to obtain the real-time relative pose relationship between each node.

3. The dynamic control method for the display screen according to claim 2, characterized in that, A dynamic topology network is constructed based on relative pose relationships, and ambient light intensity, user gaze point coordinates, and user pose data are collected simultaneously. The acquired multimodal data is time-synchronized and preprocessed using Kalman filtering to obtain an initial feature set, including: Based on the obtained real-time relative pose relationship, a topological network describing the dynamic connection relationship between each entity node is constructed. Synchronized with the construction process of the dynamic topology network, it coordinates and collects ambient light intensity, user gaze point coordinates, and user posture data; The original multimodal data were preprocessed by time synchronization alignment and Kalman filtering to eliminate time jitter and measurement noise between data, and an initial feature set was obtained.

4. The dynamic control method for the display screen according to claim 3, characterized in that, Spatial calibration coefficients are generated based on the distribution characteristics of the dynamic topology network, and the initial feature set is normalized and compensated using these calibration coefficients to obtain the calibrated multimodal sensing feature vector, including: Based on the real-time distribution characteristics of the constructed dynamic topology network, the corresponding spatial calibration coefficients are obtained; By using spatial calibration coefficients, the initial feature set is normalized and compensated to obtain the calibrated multimodal sensing feature vector.

5. The dynamic control method for the display screen according to claim 4, characterized in that, Based on multimodal perception feature vectors, the screen attention status is determined according to the user's gaze focus, and the visual stability requirements are evaluated in combination with the user's motion status. Based on screen attention status and visual stability requirements, ambient light intensity data is weighted to obtain adjustment instructions for brightness adjustment urgency and zone brightness target values, including: Based on the multimodal perception feature vector, user gaze focus data is extracted from the multimodal perception feature vector, and the user's current attention state to the screen is determined. Based on the screen attention status determination, and combined with the user motion state data in the multimodal perception feature vector, the user's visual stability needs are comprehensively evaluated. Based on the determined screen attention state and the assessed visual stability requirements, the ambient light intensity data in the multimodal perception feature vector is weighted and fused to obtain the brightness adjustment urgency. Based on the urgency of brightness adjustment and the determined screen attention status, target brightness values ​​for different functional areas of the display screen are obtained, ultimately forming a complete adjustment command for brightness adjustment urgency and target brightness values ​​for each area.

6. The dynamic control method for a display screen according to claim 5, characterized in that, The brightness adjustment urgency in the adjustment command is used to select the brightness change mode, resulting in a backlight control strategy and a zone control strategy, including: Receive and parse the adjustment command, and extract the brightness adjustment urgency parameter; Based on the extracted urgency of brightness adjustment, a brightness change curve matching it is selected from multiple predefined brightness change modes; Based on the selected brightness change curve, a global backlight control strategy is obtained, which defines the overall law of brightness change over time. By combining the target brightness values ​​of the zones contained in the adjustment instructions with the selected brightness change curves, a zone control strategy is formulated for the navigation information area and the background area, ultimately resulting in a complete combination of backlight control strategy and zone control strategy.

7. The dynamic control method for a display screen according to claim 6, characterized in that, Based on backlight control and zone control strategies, and according to the zone brightness target values ​​and corresponding brightness change patterns, differentiated brightness adjustments are performed on the navigation information area and background area of ​​the display screen to achieve a dynamic balance between power consumption and visibility, including: Based on the backlight control strategy and the zone control strategy, a first set of brightness control parameters corresponding to the navigation information area and a second set of brightness control parameters corresponding to the background area are obtained, wherein the parameter set includes the target brightness value and the corresponding change mode; Based on the obtained first set of brightness control parameters, a control signal is sent to the navigation information area driving unit of the display screen to drive the area backlight to transition to the target brightness value according to the specified brightness change mode, so as to prioritize the visibility of core information. Based on the obtained second set of brightness control parameters, an independent control signal is sent to the background area driving unit of the display screen to drive the area backlight to adjust to the target brightness value according to the specified brightness change mode, so as to achieve energy saving optimization. By performing parallel and differentiated brightness adjustment operations on the navigation information area and the background area of ​​the display screen, a dynamic balance between the overall power consumption of the display screen and the user's visibility is achieved.

8. A dynamic control system for a display screen, the system implementing the method as described in any one of claims 1 to 7, characterized in that, include: The acquisition module is used to construct a spatial coordinate system containing multiple entity nodes, including preset corner points of the display screen, the user's binocular visual center, and the handheld interactive device; by calculating the projected dot product of the spatial vectors corresponding to each node, the relative pose relationship between each node is analyzed. The calibration module is used to construct a dynamic topology network based on relative pose relationships and simultaneously collect ambient light intensity, user gaze point coordinates, and user pose data; it performs temporal synchronization and Kalman filtering preprocessing on the collected multimodal data to obtain an initial feature set. Spatial calibration coefficients are generated based on the distribution characteristics of the dynamic topology network, and the initial feature set is normalized and compensated using the calibration coefficients to obtain the calibrated multimodal sensing feature vector. The adjustment module is used to determine the screen attention state based on the user's gaze focus and to evaluate the visual stability requirements in combination with the user's motion state, based on the multimodal perception feature vector. Based on screen attention status and visual stability requirements, ambient light intensity data is weighted to obtain adjustment instructions for brightness adjustment urgency and zone brightness target values; these instructions are used to select brightness change modes according to the brightness adjustment urgency in the adjustment instructions to obtain backlight control strategies and zone control strategies. The processing module is used to perform differentiated brightness adjustment on the navigation information area and background area of ​​the display screen based on the backlight control strategy and the zoning control strategy, according to the target brightness value of the zoning area and the corresponding brightness change mode, so as to achieve a dynamic balance between power consumption and visibility.

9. A computing device, characterized in that, include: One or more processors; A storage device for storing one or more programs, which, when executed by one or more processors, cause the one or more processors to implement the method as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a program that, when executed by a processor, implements the method as described in any one of claims 1 to 7.

Images