Liquid crystal display screen self-adaptive image adjusting method and device based on ambient light induction

Abstract

The invention provides a liquid crystal display screen self-adaptive image adjusting method and device based on ambient light induction, and relates to the technical field of display screens, and the method comprises the steps: carrying out ambient light field perception, and building light field emotion perception through 3D light field distribution; the display content of the liquid crystal display screen is extracted, and adjustment tolerance constraints are constructed based on the display content; activating the linkage acquisition equipment, executing multi-dimensional data perception of the user based on the linkage acquisition equipment, and establishing a user emotion vector by utilizing a multi-dimensional data perception result; after an adjustment decision vector is established, light field emotion perception, adjustment tolerance constraint and a user emotion vector serve as input data and are sent to a multi-target cooperative adjustment controller to execute adjustment decision vector optimization; and rendering the display image of the liquid crystal display screen according to the optimization result of the adjustment decision vector. According to the method and the device, the technical target of multi-dimensional intelligent collaborative optimization of ambient light-user emotion-display content can be realized, and the technical effect of improving scene adaptability is achieved.

Description

Technical Field

[0001] This application relates to the technical field of display screens, and particularly to an adaptive image adjustment method and device for a liquid crystal display screen based on ambient light sensing. Background Art

[0002] With the rapid development of display technology and the continuous improvement of users' demand for visual experience, the ambient light adaptive adjustment technology of liquid crystal display screens has become a research hotspot. However, there are still many deficiencies in the existing technologies, making it difficult to meet the intelligent and personalized needs in complex scenarios.

[0003] Currently, existing solutions mostly rely on a single light sensor or a simple RGB camera, and can only obtain the average brightness and color temperature of ambient light, unable to accurately reconstruct the three-dimensional light field distribution (such as multi-light source superposition, dynamic light and shadow changes, etc.). For example, in a scene with dappled tree shade or flashing neon lights, existing systems often fail to accurately capture key parameters such as the light direction and intensity gradient, resulting in lag or overshoot in screen adjustment (such as the brightness mutation problem of in-vehicle display screens when entering and exiting tunnels). Secondly, there is a lack of an emotional coordination mechanism. Current technologies only perform mechanical adjustment based on physical lighting parameters, and fail to dynamically adapt in combination with the user's emotional state (such as relaxation, concentration, excitement, etc.). For example, a low-color-temperature environment on a rainy day may require a soothing display tone to match the user's mood, but existing systems still use a fixed color temperature mapping, resulting in a fragmented visual experience. In addition, the multi-objective optimization ability is weak. Among the display content fidelity (such as the color accuracy requirements of medical images), the user's emotional needs (such as the high-contrast preference in entertainment scenarios), and the ambient light fusion (such as the natural tone coordination in the setting sun), existing technologies lack an intelligent trade-off mechanism, often resulting in parameter conflicts (such as oversaturation or detail loss during outdoor reading).

[0004] In summary, there is a technical problem in the existing technologies that due to the lack of an emotional coordination mechanism, the screen adjustment strategy is out of touch with the user's real needs, further affecting visual comfort, emotional interaction experience, and scene adaptability. Summary of the Invention

[0005] The purpose of this application is to provide an adaptive image adjustment method and device for a liquid crystal display screen based on ambient light sensing, so as to solve the technical problem in the existing technologies that due to the lack of an emotional coordination mechanism, the screen adjustment strategy is out of touch with the user's real needs, further affecting visual comfort, emotional interaction experience, and scene adaptability.

[0006] In view of the above problems, this application provides an adaptive image adjustment method and device for a liquid crystal display screen based on ambient light sensing.

[0007] In a first aspect, the present application provides a method for adaptively adjusting images of a liquid crystal display based on ambient light sensing, which is implemented through a device for adaptively adjusting images of a liquid crystal display based on ambient light sensing, and includes: calling an RGB camera and an ambient light sensor to sense the ambient light field, reconstructing the ambient 3D light field distribution, and establishing light field emotion perception using the 3D light field distribution; extracting the display content of the liquid crystal display, and constructing an adjustment tolerance constraint based on the display content; activating a linked acquisition device, performing multi-dimensional data perception of the user based on the linked acquisition device, and establishing a user emotion vector using the multi-dimensional data perception result; after establishing an adjustment decision vector, taking the light field emotion perception, the adjustment tolerance constraint, and the user emotion vector as input data, and sending them to a multi-objective collaborative adjustment controller to perform optimization of the adjustment decision vector. The collaborative objectives of the multi-objective collaborative adjustment controller include a user emotion resonance objective, a violation degree objective of the adjustment tolerance, and a light field emotion fusion matching degree objective; rendering the display image of the liquid crystal display according to the optimization result of the adjustment decision vector.

[0008] Preferably, the method for adaptively adjusting images of a liquid crystal display based on ambient light sensing further includes: executing a call of historical environment data to obtain a historical environment data set; performing weather similarity clustering on the historical environment data set, and predicting a mutation time point according to the time identifier of the similarity clustering to establish a mutation node prediction result; obtaining the positioning data of the liquid crystal display, and reading the network weather according to the positioning data to establish a network weather reading result; using the mutation node prediction result and the network weather reading result to compensate the light field emotion perception.

[0009] Preferably, the method for adaptively adjusting images of a liquid crystal display based on ambient light sensing further includes: performing time series extraction on the ambient light field perception to establish a time series distribution data set of the ambient 3D light field distribution; performing time series prediction using the time series distribution data set to establish light field emotion perception; performing conflict recognition of time series prediction according to the mutation node prediction result, and establishing a first compensation feedback using the conflict recognition result; performing impact analysis of time series prediction using the network weather reading result, and establishing a second compensation feedback; compensating the light field emotion perception using the first compensation feedback and the second compensation feedback.

[0010] Preferably, the method for adaptively adjusting images of a liquid crystal display based on ambient light sensing further includes: the adjustment decision vector includes a hue offset, a color temperature adjustment amount, a contrast adjustment factor, a sharpness adjustment factor, and an emotion style transfer factor.

[0011] Preferably, the adaptive image adjustment method for a liquid crystal display screen based on ambient light sensing further includes: performing scene recognition according to the display content, multi-dimensional data perception results, and ambient 3D light field distribution, and establishing a scene recognition result; using the scene recognition result to crop the search space, and performing optimization management of the adjustment decision vector based on the cropped search space.

[0012] Preferably, the adaptive image adjustment method for a liquid crystal display screen based on ambient light sensing further includes: in each iteration process, after initializing the current adjustment decision vector, performing iterative optimization through a lightweight gradient descent optimizer; executing multi-round iteration records and evaluations to generate continuous iteration evaluation results; if the continuous iteration evaluation results do not meet the preset convergence threshold, generating an auxiliary optimization instruction; using the auxiliary optimization instruction to call the historical scenario adjustment template for reinforcement optimization.

[0013] Preferably, the adaptive image adjustment method for a liquid crystal display screen based on ambient light sensing further includes: using the 3D light field distribution for feature extraction to establish a feature set, and the extracted features include light color distribution, brightness gradient, saturation distribution, incident azimuth and elevation angles, spot mottling degree, and color temperature estimation; establishing an emotion label mapping based on the existing emotion environment image data set; performing sliding time window aggregation matching of the feature set according to the emotion label mapping to establish light field emotion perception.

[0014] Preferably, the adaptive image adjustment method for a liquid crystal display screen based on ambient light sensing further includes: establishing an emotion data set of the user, and configuring an energy-saving tolerance factor for each emotion state; using the energy-saving tolerance factor to construct an energy-saving optimization function, and performing energy-saving optimization on the optimization result of the adjustment decision vector based on the energy-saving optimization function; using the energy-saving optimization result to render the display image of the liquid crystal display screen.

[0015] Preferably, the adaptive image adjustment method for a liquid crystal display screen based on ambient light sensing further includes: the linkage acquisition device includes an acquisition camera, a microphone, and a wearable physiological data acquisition device.

[0016] Second aspect, the present application also provides a liquid crystal display adaptive image adjustment device based on ambient light sensing, which is used to execute the liquid crystal display adaptive image adjustment method based on ambient light sensing as described in the first aspect, including: an ambient light field perception module, which is used to call an RGB camera and an ambient light sensor to perform ambient light field perception, reconstruct the ambient 3D light field distribution, and establish a light field emotion perception using the 3D light field distribution; a constraint construction module, which is used to extract the display content of the liquid crystal display and construct an adjustment tolerance constraint based on the display content; a multi-dimensional data perception module, which is used to activate a linkage acquisition device, perform multi-dimensional data perception of the user based on the linkage acquisition device, and establish a user emotion vector using the multi-dimensional data perception result; an adjustment decision vector optimization module, which is used to, after establishing an adjustment decision vector, use the light field emotion perception, the adjustment tolerance constraint, and the user emotion vector as input data and send them to a multi-objective collaborative adjustment controller to perform adjustment decision vector optimization. The collaborative objectives of the multi-objective collaborative adjustment controller include a user emotion resonance objective, a violation degree objective of the adjustment tolerance, and a light field emotion fusion matching degree objective; a display image rendering module, which is used to perform display image rendering of the liquid crystal display according to the adjustment decision vector optimization result.

[0017] The technical solutions provided in the present application have at least the following technical effects or advantages: By achieving the technical goal of multi-dimensional intelligent collaborative optimization of ambient light - user emotion - display content, the technical effects of improving visual comfort, enhancing emotional resonance, and adapting to dynamic scenarios are achieved.

[0018] The above description is only an overview of the technical solutions of the present application. In order to be able to understand the technical means of the present application more clearly, it can be implemented according to the content of the specification. And in order to make the above and other purposes, features, and advantages of the present application more obvious and understandable, the specific implementation manners of the present application are specifically given below. It should be understood that the content described in this part is not intended to identify the key or important features of the embodiments of the present application, nor is it used to limit the scope of the present application. Other features of the present application will become easily understood through the following description. Brief Description of the Drawings

[0019] In order to more clearly illustrate the technical solutions in the present application or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the drawings described below are only exemplary, and for those of ordinary skill in the art, other drawings can be obtained according to the provided drawings without creative efforts.

[0020] Figure 1 It is a flowchart of the liquid crystal display adaptive image adjustment method based on ambient light sensing of the present application; Figure 2This is a schematic structural diagram of the adaptive image adjustment device for a liquid crystal display based on ambient light sensing in the present application.

[0021] Explanation of reference numerals in the drawings: Ambient light field perception module 11, constraint construction module 12, multi-dimensional data perception module 13, adjustment decision vector optimization module 14, display image rendering module 15. Detailed implementation manners

[0022] By providing the adaptive image adjustment method and device for a liquid crystal display based on ambient light sensing in the present application, the technical problem in the prior art that due to the lack of an emotional collaboration mechanism, the screen adjustment strategy is out of touch with the real needs of users, further affecting visual comfort, emotional interaction experience and scene adaptability is solved. The technical goal of multi-dimensional intelligent collaboration optimization of ambient light - user emotion - display content is realized, and the technical effects of improving visual comfort, enhancing emotional resonance and adapting to dynamic scenes are achieved.

[0023] Next, the technical solutions in the present application will be described clearly and completely with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments of the present application. It should be understood that the present application is not limited by the exemplary embodiments described herein. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present application without creative efforts shall fall within the scope of protection of the present application. Additionally, it should be noted that for the sake of description, only the parts related to the present application are shown in the accompanying drawings rather than all of them.

[0024] Embodiment 1, please refer to the attached Figure 1 , the present application provides an adaptive image adjustment method for a liquid crystal display based on ambient light sensing, which is applied to the adaptive image adjustment device for a liquid crystal display based on ambient light sensing, and specifically includes the following steps: S1: Invoke an RGB camera and an ambient light sensor to perform ambient light field perception, reconstruct the ambient 3D light field distribution, and establish light field emotion perception using the 3D light field distribution.

[0025] Specifically, by invoking an RGB camera and an ambient light sensor, the illumination information of the current surrounding environment can be obtained. Among them, the RGB camera is used to capture color information, and the ambient light sensor is responsible for measuring the overall illumination intensity. After fusing and processing the two types of perception data, a three-dimensional light field distribution with spatial depth information can be restored, that is, the ambient 3D light field distribution, which can present the direction and intensity of the light source and also includes information such as color distribution, laying a foundation for subsequent emotion perception and image adjustment.

[0026] Using the 3D light field distribution to establish light field emotion perception, extracting various characteristic parameters of light and comparing them with the existing emotion label system, and then identifying the user emotion state that the current light environment may stimulate to establish light field emotion perception. Among them, the 3D light field distribution refers to the complete expression of information such as the color, brightness, direction, and change trend of light at different position points in space.

[0027] S2: Extract the display content of the liquid crystal display screen and construct an adjustment tolerance constraint based on the display content.

[0028] Specifically, extract the display content of the liquid crystal display screen, actively read and analyze the image or video information presented on the current screen, and understand the content type and its visual characteristics. The display content can include static images, dynamic images, text interfaces, game screens, or user interfaces. Each type of content has different sensitivities and adjustment requirements for image parameters such as brightness, color, and contrast. Construct an adjustment tolerance constraint based on the attributes of the display content. The adjustment tolerance constraint is the definition of the acceptable variation range of image parameters and is used to adjust the parameters without affecting the viewing experience.

[0029] S3: Activate the linked acquisition device, perform multi-dimensional data perception of the user based on the linked acquisition device, and establish a user emotion vector using the multi-dimensional data perception result.

[0030] Specifically, activate the linked acquisition device and start external or embedded sensing devices that work in coordination with the liquid crystal display screen, which may include cameras, microphones, wearable physiological monitoring devices, etc. Each device undertakes different types of data acquisition tasks. For example, a camera can analyze the user's facial expressions and eye movement trajectories, a microphone can monitor intonation changes, and wearable devices such as smart bracelets can collect physiological parameters such as heart rate, skin conductance response, and body temperature.

[0031] Perform multi-dimensional data perception of the user based on the linked acquisition device, and synchronously perceive the user's current psychological and physiological states from multiple dimensions. Multi-dimensional data perception means that the user data obtained is not limited to a single type, but integrates visual, auditory, tactile, and even physiological signals. For example, it may be possible to simultaneously perceive that the user's voice pitch rises, heart rate accelerates, and expression becomes tense, making the understanding of the user's state more comprehensive and accurate. Then, establish a user emotion vector using the multi-dimensional data perception result, and convert the original data into a quantifiable and inputtable structured representation form. The user emotion vector is a multi-dimensional vector, and each dimension represents an emotion feature or state index, such as pleasure, concentration, tension, anxiety value, etc. The emotion vector can be obtained through model mapping and data training. According to the learning experience of past data, the input signals such as facial features, voice frequencies, and heart rates are combined and then mapped to specific emotion states.

[0032] S4: After establishing the adjustment decision vector, use the light field emotion perception, the adjustment tolerance constraint, and the user emotion vector as input data, and send them to the multi-objective collaborative adjustment controller to perform optimization of the adjustment decision vector. The collaborative objectives of the multi-objective collaborative adjustment controller include the user emotion resonance objective, the violation degree objective of the adjustment tolerance, and the light field emotion fusion matching degree objective.

[0033] Specifically, after establishing the adjustment decision vector, collect the light field emotion state in the current environment, the allowable adjustment range of the display content, and the current multi-dimensional emotion state of the user at the same time. Use the light field emotion perception, the adjustment tolerance constraint, and the user emotion vector as input data and send them to the multi-objective collaborative adjustment controller to perform optimization of the adjustment decision vector, and finely adjust the adjustment vector through the multi-objective collaborative adjustment controller. For example, weighted linear programming or evolutionary optimization is used to find the comprehensive optimal solution among multiple objectives. The collaborative objectives of the multi-objective collaborative adjustment controller include the user emotion resonance objective, the violation degree objective of the adjustment tolerance, and the light field emotion fusion matching degree objective. The user emotion resonance objective means that the adjustment result needs to have a positive response to the user's current emotion state. For example, when the user is in a low mood, soft and warm color tone adjustments should be preferentially matched to evoke a sense of comfort. The violation degree objective of the adjustment tolerance is used to limit that the optimization process cannot break through the constraint boundary of the display content on the image parameters. For example, it is not allowed that the sharpness reduction exceeds 20%. The light field emotion fusion matching degree objective emphasizes that the adjustment result should be naturally integrated with the ambient light emotion to avoid a sense of incongruity. For example, it is not appropriate to output a high-saturation warm light image in an environment with strong fluctuations of cold light.

[0034] S5: Render the display image of the liquid crystal display according to the optimization result of the adjustment decision vector.

[0035] Specifically, render the display image of the liquid crystal display according to the optimization result of the adjustment decision vector, and reprocess and present the image content finally displayed on the liquid crystal screen based on the optimal adjustment parameter combination. Among them, the optimization result of the adjustment decision vector is a set of parameter value sets obtained through multiple rounds of optimization algorithms, which are used to control multiple aspects of the image, such as hue, brightness, contrast, sharpness, etc., so that the screen display effect not only conforms to the current ambient light field but also is coordinated with the user's emotion state. Display image rendering refers to applying these parameters to the image processing engine to perform real-time adjustment on the original picture to form an image that is visually more comfortable or more in line with the target emotion atmosphere. For example, when the color temperature adjustment amount in the optimization result is to decrease by 300 Kelvin, the overall image will be more inclined to the warm color tone; when the contrast adjustment factor is 1.2, the light and dark boundaries of the image will be clearer, thereby enhancing the visual tension.

[0036] Furthermore, this application also includes: performing a call to historical environmental data to obtain a historical environmental data set; after performing weather similarity clustering on the historical environmental data set, predicting mutation time points based on the time identifiers of the similarity clustering to establish a mutation node prediction result; obtaining the positioning data of the liquid crystal display screen, performing networked weather reading based on the positioning data to establish a networked weather reading result; and compensating the light field emotion perception using the mutation node prediction result and the networked weather reading result.

[0037] Specifically, relevant environmental light data for a past period of time is retrieved to obtain historical environmental data, which includes illumination patterns and characteristics under different times and weather conditions. By performing cluster analysis on the historical environmental data, data segments with similar weather conditions can be identified, such as characteristics like cloudy days, high humidity, and low brightness, thereby constructing a grouping structure based on weather similarity.

[0038] Subsequently, based on the time identifiers of the weather similarity clustering, the changing trend of the illumination pattern is analyzed, and then the possible mutation nodes are predicted. A mutation node refers to the time point when the characteristics of the environmental light change sharply, such as sudden rain, sunset, or light switching. Establishing the mutation node prediction result can thus predict in advance the drastic changes in the environmental light field and prepare a warning for the image adjustment strategy. Among them, Table 1 shows partial records of the most recent mutation node prediction result.

[0039] Table 1: Partial records of the most recent mutation node prediction result ; ; Collect the real-time positioning data of the location where the liquid crystal display screen is located, and rely on the network to obtain the latest weather information corresponding to the positioning data, and then use it to predict and provide an environmental reference for the real world.

[0040] Finally, combine the predicted mutation node prediction result with the networked weather reading result obtained through the network to compensate and optimize the light field emotion perception initially established based on real-time perception, thereby improving the stability and emotion matching degree of the overall image adjustment.

[0041] Furthermore, this application also includes: performing temporal extraction on the environmental light field perception to establish a temporal distribution data set of the environmental 3D light field distribution; using the temporal distribution data set for temporal prediction to establish light field emotion perception; performing conflict identification for temporal prediction based on the mutation node prediction result, and establishing a first compensation feedback using the conflict identification result; performing impact analysis for temporal prediction using the networked weather reading result, and establishing a second compensation feedback; and compensating the light field emotion perception using the first compensation feedback and the second compensation feedback.

[0042] Specifically, in the process of extracting the time series of the ambient light field perception, the ambient light data continuously acquired within a period of time are organized in chronological order to form a series of light field snapshots with time stamps, thereby constructing a time series distribution data set of the ambient 3D light field distribution, which can obtain the dynamic trend of the light field changing over time and provides a basis for subsequent analysis.

[0043] Next, use the time series distribution data set for time series prediction, that is, use time series analysis algorithms to predict the evolution of the ambient light in the future period of time and establish light field emotion perception. For example, when the ambient light field presents a combination of high brightness, high color temperature and drastic changes, identify the light field characteristics with strong irritation and dynamic sense. Users may receive more visual and physiological activation signals, thus evoking positive and focused emotions. When the light field presents a visual performance with lower brightness and medium humidity, and the light change speed is relatively fast, it is judged as a potential trigger factor for anxiety or uneasiness, and the discomfort of the user may be alleviated by increasing the contrast and adding smooth transition effects. When the ambient light is mainly in warm tones, and the light source changes smoothly and in the same direction, it is identified as an emotional pattern that triggers relaxation and a sense of security. When the ambient light is cold, there are multiple incident directions, and at the same time accompanied by small-amplitude fluctuations with high frequency, it will be marked as having a sense of pressure or coldness.

[0044] Furthermore, combining the prediction results of the mutation nodes, identify whether there are inconsistencies between the current time series prediction and the mutation warning, that is, perform conflict identification, which can reveal the deviation between the model prediction and the sudden environmental changes. For example, the time series prediction believes that the light will gradually brighten, but the mutation node prediction shows that it is about to rain, resulting in a darker environment. At this time, establish the first compensation feedback as the basis for correcting the light field emotion perception.

[0045] At the same time, use the results of the network weather reading to analyze its potential impact on the light field emotion perception. For example, the network weather data shows that there will be strong winds and cooling within 30 minutes, and the external real data may affect the local light field changes. Based on this, form the second compensation feedback to correct the time series prediction so that it can be closer to the actual environmental changes.

[0046] Finally, combine the first compensation feedback and the second compensation feedback to perform final compensation optimization on the established light field emotion perception, making the light field emotion judgment more accurate and making the displayed content more adaptable to the environment.

[0047] Furthermore, the present application further includes: the adjustment decision vector includes a hue offset, a color temperature adjustment amount, a contrast adjustment factor, a sharpness adjustment factor, and an emotion style migration factor.

[0048] Specifically, the adjustment decision vector is a set of multi-dimensional parameters used to guide the image adjustment of the liquid crystal display screen. Each dimension represents the adjustment direction and amplitude of an image attribute. Among them, the hue offset refers to the degree of deviation of the main color system of the overall color of the image. For example, a picture that was originally bluish can be adjusted to shift towards green or red to adapt to different light environments or emotional needs. The color temperature adjustment amount refers to the adjustment degree of the warm and cold tones of the picture. A higher color temperature makes the picture cooler, while a lower color temperature makes it warmer, which is used to adjust the atmosphere of the picture. The contrast adjustment factor determines the difference degree between light and dark in the image. The larger the value, the brighter the bright part and the darker the dark part in the image, which is beneficial to enhancing the visual impact and clear boundaries of the picture. The sharpness adjustment factor is used to enhance the sharpness of the image edge and make the details more prominent. The emotional style transfer factor is a parameter that reflects the matching degree between the overall visual style of the image and the user's current emotional state. It combines the light field emotion perception and the analysis result of the user's emotional vector to inject a specific emotional tendency into the image, such as tranquility, enthusiasm or tension, etc.

[0049] Furthermore, this application also includes: performing scene recognition based on the display content, multi-dimensional data perception result, and environmental 3D light field distribution to establish a scene recognition result; using the scene recognition result to crop the search space and performing optimization management of the adjustment decision vector based on the cropped search space.

[0050] Specifically, performing scene recognition based on the display content, multi-dimensional data perception result, and environmental 3D light field distribution, analyzing the picture information currently displayed on the liquid crystal display screen, the physiological and emotional states of the user, and the three-dimensional lighting characteristics of the surrounding environment to determine the type of the current application scene. The display content includes the main category, color composition, dynamic characteristics, etc. of the image, such as whether it is a video, static text or graphic interface; the multi-dimensional data perception result involves psychological state indicators such as the user's emotional vector and attention level; the environmental 3D light field distribution is a three-dimensional modeling of the propagation of light in space, including parameters such as light intensity, color, and direction. Then, it can be recognized whether it is in different scenes such as office, leisure, gaming or night reading, etc., and further establish a scene recognition result to provide a basis for subsequent decisions.

[0051] Using the scene recognition result to crop the search space, restricting the range of feasible image adjustment parameters based on this scene, thereby reducing the calculation space required for parameter optimization. The search space refers to the set of all possible parameter combinations when performing adjustment decision optimization. Cropping the search space means only retaining the adjustment parameter range that is most relevant to the current scene and most likely to be adopted to improve the operation efficiency and adjustment accuracy. For example, in the reading mode, the parameter combinations with a lower color temperature, softer brightness, and moderate contrast are preferentially retained, and the overly bright or highlighted candidates are excluded.

[0052] Optimize the search for the adjustment decision vector based on the cropped search space, and perform the search for the optimal image adjustment strategy within a limited and precise parameter range. The adjustment decision vector consists of multiple dimensions, including hue shift, color temperature adjustment, contrast, sharpness, mood style, etc., and each dimension has specific candidate values or variation ranges. Search for the parameter combination that best suits the current scene and user mood in multiple rounds of calculations.

[0053] Furthermore, this application also includes: in each iteration process, after initializing the current adjustment decision vector, perform iterative optimization through a lightweight gradient descent optimizer; execute multiple rounds of iterative record evaluation to generate continuous iterative evaluation results; if the continuous iterative evaluation results do not meet the preset convergence threshold, generate an auxiliary optimization instruction; use the auxiliary optimization instruction to call the historical scenario adjustment template for enhanced optimization.

[0054] Specifically, in each iteration process, after initializing the current adjustment decision vector, set an initial adjustment parameter combination that covers adjustment factors such as hue, color temperature, contrast, and sharpness, and then perform iterative optimization through a lightweight gradient descent optimizer. The lightweight gradient descent optimizer is a simplified gradient descent method with the characteristics of high computational efficiency and small resource occupancy, and is suitable for deployment in devices with high real-time requirements. The lightweight gradient descent optimizer will calculate the effect of the current adjustment parameter combination according to the target evaluation function in each iteration, and gradually approach the optimum by continuously fine-tuning the parameters.

[0055] Next, execute multiple rounds of iterative record evaluation, record the corresponding effect scores each time, such as image comfort score, user emotion feedback value, or visual contrast index, to generate continuous iterative evaluation results. For example, combine the continuous evaluation values into an iterative optimization curve for real-time judgment of the current adjustment and provide a trend reference for subsequent optimization.

[0056] If the continuous iterative evaluation results do not meet the preset convergence threshold, it is determined that the current parameter path cannot converge to a satisfactory result, and an auxiliary optimization instruction is generated to guide the subsequent adjustment process. The convergence threshold is custom-set by those skilled in the art according to the actual situation.

[0057] Finally, use the auxiliary optimization instruction to call the historical scenario adjustment template for enhanced optimization. Combine the currently recognized scene information and the adjustment templates stored in previous similar scenarios, directly borrow the parameter combinations with known good effects, jump out of the current local optimum, and re-attempt optimization. The historical scenario adjustment template is derived from past user interaction records or expert system recommendations. For example, for the "night reading" scenario, there may already be an adjustment combination with a color temperature of 3500 Kelvin, a brightness of 60%, and a contrast of 0.5, which has been verified to have good effects.

[0058] Furthermore, this application also includes: extracting features using the 3D light field distribution to establish a feature set, where the extracted features include illumination color distribution, brightness gradient, saturation distribution, incident azimuth angle and elevation angle, spot mottling degree, and color temperature estimation; establishing an emotion label mapping based on the existing emotion environment image dataset; and performing sliding time window aggregation fitting matching on the feature set according to the emotion label mapping to establish light field emotion perception.

[0059] Specifically, extracting features using the 3D light field distribution to extract key attributes that can reflect emotion characteristics, and establishing a feature set for subsequent analysis. Among them, the illumination color distribution describes the proportion and spatial variation of colors such as red, green, and blue in the ambient light, the brightness gradient represents the degree of change in light intensity from one area to another, the saturation distribution is used to measure the purity and vividness of colors, the incident azimuth angle and elevation angle refer to the angles of the light irradiation direction in the horizontal and vertical directions, the spot mottling degree reflects the uniformity or speckle degree of the light on the surface, and the color temperature estimation is the color temperature of the ambient light calculated through physical calculations or sensors, used to determine whether the light is warm or cold.

[0060] Next, establishing an emotion label mapping based on the existing emotion environment image dataset, using a data resource containing a large number of environment images with emotion labels to establish a one-to-one correspondence between specific optical features and emotion states. For example, sample images of emotion states such as relaxation, concentration, anxiety, and pleasure, each image is pre-labeled with an emotion type, and a model is trained through statistical or machine learning algorithms so that given a set of light field features, an emotion label that is most likely to correspond can be mapped.

[0061] Then, performing sliding time window aggregation fitting matching on the feature set according to the emotion label mapping, slicing the continuous light field features in the time dimension by time, and performing step-by-step aggregation analysis to establish light field emotion perception, detect the change trend of the emotion state over time, and avoid emotion judgment deviations caused by accidental illumination changes. Through the sliding window technique, within a time period of, for example, every 5 seconds, the continuously changing illumination features can be grouped together and matched with the emotion labels, and finally a stable light field emotion judgment within a certain time period can be formed.

[0062] Furthermore, this application also includes: establishing an emotion dataset of the user and configuring an energy-saving tolerance factor for each emotion state; constructing an energy-saving optimization function using the energy-saving tolerance factor, and performing energy-saving optimization on the optimization result of the adjustment decision vector based on the energy-saving optimization function; and rendering the display image of the liquid crystal display with the energy-saving optimization result.

[0063] Specifically, physiological or behavioral characteristics of the user in different emotional states are collected through multi-dimensional perception devices, such as heart rate, facial expressions, voice tones, etc., and aggregated to form an emotional sample library for algorithm training. An energy-saving tolerance factor is assigned to each emotional state, which is used to represent the acceptable degree of the user for the screen energy-saving strategy in that emotional state. For example, when the user is in a relaxed state, they may be more tolerant of a slightly lower brightness and a slightly off-color display effect. At this time, the tolerance factor can be set relatively high, such as 0.8. When the user is in a focused state, the sensitivity to image details increases, and the tolerance for the reduction in image quality caused by energy saving is lower, and the tolerance factor can be set to 0.3.

[0064] Subsequently, an energy-saving optimization function is constructed using the energy-saving tolerance factor to evaluate the balance between energy-saving effects and user experience under different display adjustment schemes. The energy-saving optimization function comprehensively considers the trade-off between the degree of power consumption reduction and the decline in emotional experience quality, so as to maximize the energy-saving effect on the premise of ensuring no obvious interference with the user experience. If a certain adjustment scheme can reduce energy consumption by 30%, but the experience of users in a relaxed state is hardly affected, the energy-saving optimization function will give a high score to this scheme.

[0065] Next, based on the energy-saving optimization function, energy-saving optimization of the optimization result of the adjustment decision vector is carried out, and its energy efficiency performance is further analyzed. If the energy-saving expectation is not met, the adjustment vector is refined and adjusted in combination with the emotional tolerance factor, such as appropriately reducing the brightness or reducing the high-power consumption color distribution, to ensure further optimization of the overall energy consumption.

[0066] Finally, the display image of the liquid crystal display is rendered with the energy-saving optimization result, that is, the optimized adjustment decision is applied to the actual image output, and parameters such as the color temperature, contrast, and clarity of the display are controlled, so that the finally rendered image significantly reduces power consumption while the visual effect is acceptable, for example, reducing the average brightness by 20%, but the change is not obvious in human eye perception.

[0067] Furthermore, this application also includes: the linkage acquisition device includes an acquisition camera, a microphone, and a wearable physiological data acquisition device.

[0068] Specifically, the acquisition camera included in the linkage acquisition device refers to a visual sensing device that can work in coordination with other devices, and is used to capture image information such as the user's facial expressions, action postures, and gaze directions in real time. The resolution, frame rate, and photosensitivity of the acquisition camera determine its sensitivity to detail changes. For example, a camera with a resolution of 1920 pixels × 1080 pixels can clearly identify subtle changes in facial expressions, and a frame rate of 30 frames per second can ensure the capture of continuous expression transitions.

[0069] Subsequently, the microphone undertakes the function of sound acquisition and can be used to obtain sound characteristics such as the user's voice, intonation, and breathing frequency, and further infer the user's emotional state. For example, when the microphone detects a voice signal with an increased speech rate and volume, it may correspond to the user's excited or nervous emotion, while a low speech rate and low volume may characterize the user's tired or calm state. Microphone devices with different sampling rates have different degrees of restoration of sound details to ensure accurate capture of emotional details.

[0070] In addition, wearable physiological data acquisition devices refer to sensors worn on the user's body to collect their physiological parameters, such as heart rate, skin conductance response, body temperature, and exercise volume, etc., including smart bracelets, watches, and body patches, etc., which can achieve continuous and high-frequency data acquisition. For example, the rate of change of heart rate can reflect the user's level of tension. If the heart rate increases by more than 20 times per minute within 10 seconds, it may indicate high emotions or anxiety.

[0071] In summary, the method for adaptively adjusting the image of a liquid crystal display based on ambient light sensing provided in this application has the following technical effects: by achieving the technical goal of multi-dimensional intelligent collaborative optimization of ambient light - user emotion - display content, it achieves the technical effects of improving visual comfort, enhancing emotional resonance, and adapting to dynamic scenarios.

[0072] Embodiment 2, based on the same inventive concept as the method for adaptively adjusting the image of a liquid crystal display based on ambient light sensing in the foregoing embodiment, this application also provides an apparatus for adaptively adjusting the image of a liquid crystal display based on ambient light sensing. Please refer to the attached Figure 2 , including: an ambient light field perception module 11, which is used to call an RGB camera and an ambient light sensor for ambient light field perception, reconstruct the ambient 3D light field distribution, and establish light field emotion perception using the 3D light field distribution; a constraint construction module 12, which is used to extract the display content of the liquid crystal display and construct an adjustment tolerance constraint based on the display content; a multi-dimensional data perception module 13, which is used to activate the linkage acquisition device, perform multi-dimensional data perception of the user based on the linkage acquisition device, and establish a user emotion vector using the multi-dimensional data perception result; an adjustment decision vector optimization module 14, which is used to send the light field emotion perception, the adjustment tolerance constraint, and the user emotion vector as input data to a multi-objective collaborative adjustment controller to perform adjustment decision vector optimization after establishing the adjustment decision vector. The collaborative objectives of the multi-objective collaborative adjustment controller include a user emotion resonance objective, a violation degree objective of the adjustment tolerance, and a light field emotion fusion matching degree objective; a display image rendering module 15, which is used to perform display image rendering of the liquid crystal display according to the adjustment decision vector optimization result.

[0073] Further, the liquid crystal display adaptive image adjustment device based on ambient light sensing is further configured to: execute historical environment data call to obtain a historical environment data set; perform weather similarity clustering on the historical environment data set, predict mutation time points according to the time identifiers of the similarity clustering, and establish a mutation node prediction result; obtain the positioning data of the liquid crystal display, perform networked weather reading according to the positioning data, and establish a networked weather reading result; use the mutation node prediction result and the networked weather reading result to compensate for light field emotion perception.

[0074] Further, the liquid crystal display adaptive image adjustment device based on ambient light sensing is further configured to: perform timing extraction on the ambient light field perception to establish a timing distribution data set of the ambient 3D light field distribution; perform timing prediction using the timing distribution data set to establish light field emotion perception; perform conflict recognition of the timing prediction according to the mutation node prediction result, and establish a first compensation feedback using the conflict recognition result; perform impact analysis of the timing prediction using the networked weather reading result to establish a second compensation feedback; use the first compensation feedback and the second compensation feedback to compensate for the light field emotion perception.

[0075] Further, the liquid crystal display adaptive image adjustment device based on ambient light sensing is further configured to: the adjustment decision vector includes a hue offset, a color temperature adjustment amount, a contrast adjustment factor, a sharpness adjustment factor, and an emotion style migration factor.

[0076] Further, the liquid crystal display adaptive image adjustment device based on ambient light sensing is further configured to: perform scene recognition according to the display content, the multi-dimensional data perception result, and the ambient 3D light field distribution to establish a scene recognition result; use the scene recognition result to crop the search space, and perform optimization management of the adjustment decision vector based on the cropped search space.

[0077] Further, the liquid crystal display adaptive image adjustment device based on ambient light sensing is further configured to: in each round of iteration process, after initializing the current adjustment decision vector, perform iterative optimization through a lightweight gradient descent optimizer; execute multi-round iteration records and evaluations to generate a continuous iteration evaluation result; if the continuous iteration evaluation result does not meet the preset convergence threshold, generate an auxiliary optimization instruction; use the auxiliary optimization instruction to call the historical scenario adjustment template for reinforcement optimization.

[0078] Further, the liquid crystal display adaptive image adjustment device based on ambient light sensing is further configured to: extract features using the 3D light field distribution, establish a feature set, and the extracted features include illumination color distribution, brightness gradient, saturation distribution, incident azimuth angle and elevation angle, spot mottling degree, and color temperature estimation; establish an emotion label mapping based on the existing emotion environment image data set; perform sliding time window aggregation fitting matching on the feature set according to the emotion label mapping, and establish light field emotion perception.

[0079] Further, the liquid crystal display adaptive image adjustment device based on ambient light sensing is further configured to: establish an emotion data set of the user, and configure an energy-saving tolerance factor for each emotion state; construct an energy-saving optimization function using the energy-saving tolerance factor, and perform energy-saving optimization on the optimization result of the adjustment decision vector based on the energy-saving optimization function; perform display image rendering of the liquid crystal display with the energy-saving optimization result.

[0080] Further, the liquid crystal display adaptive image adjustment device based on ambient light sensing is further configured to: the linkage acquisition device includes an acquisition camera, a microphone, and a wearable physiological data acquisition device.

[0081] The various embodiments in this specification are described in a progressive manner, and the key points of each embodiment are the differences from other embodiments. The liquid crystal display adaptive image adjustment method and specific examples in the foregoing Embodiment 1 are equally applicable to the liquid crystal display adaptive image adjustment device in this embodiment. Through the foregoing detailed description of the liquid crystal display adaptive image adjustment method based on ambient light sensing, those skilled in the art can clearly know the liquid crystal display adaptive image adjustment device in this embodiment. Therefore, for the sake of brevity of the specification, it will not be elaborated herein.

[0082] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will be accorded the widest scope consistent with the principles and novel features disclosed herein.

[0083] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalent technologies, the present application is also intended to include these changes and modifications.

Claims

1. An adaptive image adjustment method for a liquid crystal display based on ambient light sensing, characterized in that, The method includes: Invoking an RGB camera and an ambient light sensor to perform ambient light field perception, reconstructing the ambient 3D light field distribution, and establishing light field emotion perception using the 3D light field distribution; Extracting the display content of the liquid crystal display screen, and constructing an adjustment tolerance constraint based on the display content; Activating the linked acquisition device, performing multi-dimensional data perception of the user based on the linked acquisition device, and establishing a user emotion vector using the multi-dimensional data perception result; After establishing the adjustment decision vector, taking the light field emotion perception, the adjustment tolerance constraint, and the user emotion vector as input data, and sending them to a multi-objective collaborative adjustment controller to perform optimization of the adjustment decision vector. The collaborative objectives of the multi-objective collaborative adjustment controller include a user emotion resonance objective, a violation degree objective of the adjustment tolerance, and a light field emotion fusion matching degree objective; Performing display image rendering of the liquid crystal display screen according to the optimization result of the adjustment decision vector.

2. The adaptive image adjustment method for a liquid crystal display based on ambient light sensing according to claim 1, wherein, The establishing of the light field emotion perception using the 3D light field distribution includes: Performing a call of historical environment data to obtain a historical environment data set; After performing weather similarity clustering on the historical environment data set, predicting the mutation time point according to the time identifier of the similarity clustering, and establishing a mutation node prediction result; Obtaining the positioning data of the liquid crystal display screen, reading the networked weather according to the positioning data, and establishing a networked weather reading result; Compensating the light field emotion perception using the mutation node prediction result and the networked weather reading result.

3. The adaptive image adjustment method for a liquid crystal display based on ambient light sensing according to claim 2, wherein, The compensating of the light field emotion perception using the mutation node prediction result and the networked weather reading result includes: Performing temporal extraction on the ambient light field perception to establish a temporal distribution data set of the ambient 3D light field distribution; Performing temporal prediction using the temporal distribution data set to establish light field emotion perception; Performing conflict identification of the temporal prediction according to the mutation node prediction result, and establishing a first compensation feedback using the conflict identification result; Performing impact analysis of the temporal prediction using the networked weather reading result, and establishing a second compensation feedback; Compensating the light field emotion perception using the first compensation feedback and the second compensation feedback.

4. The adaptive image adjustment method for a liquid crystal display based on ambient light sensing according to claim 1, wherein, The adjustment decision vector includes a hue offset, a color temperature adjustment amount, a contrast adjustment factor, a sharpness adjustment factor, and an emotion style migration factor.

5. The method for adaptively adjusting an image of a liquid crystal display based on ambient light sensing according to claim 1, wherein The sending to the multi-objective collaborative adjustment controller to perform optimization of the adjustment decision vector includes: Performing scene recognition according to the display content, the multi-dimensional data perception result, and the ambient 3D light field distribution, and establishing a scene recognition result; Using the scene recognition result to crop the search space, and performing optimization management of the adjustment decision vector based on the cropped search space.

6. The method for adaptively adjusting an image of a liquid crystal display based on ambient light sensing according to claim 5, wherein, The performing of the optimization management of the adjustment decision vector based on the cropped search space includes: In each iteration process, after initializing the current adjustment decision vector, performing iterative optimization through a lightweight gradient descent optimizer; Performing multi-round iteration records and evaluations to generate a continuous iteration evaluation result; If the continuous iteration evaluation result does not meet the preset convergence threshold, generating an auxiliary optimization instruction; Using the auxiliary optimization instruction to call a historical situation adjustment template for reinforcement optimization.

7. The adaptive image adjustment method for a liquid crystal display based on ambient light sensing according to claim 1, wherein The establishing of the light field emotion perception using the 3D light field distribution includes: Feature extraction is performed using the 3D light field distribution to establish a feature set. The extracted features include illumination color distribution, brightness gradient, saturation distribution, incident azimuth angle and elevation angle, spot mottling degree, and color temperature estimation; An emotion label mapping is established based on the existing emotion environment image dataset; According to the emotion label mapping, sliding time window aggregation fitting matching of the feature set is performed to establish light field emotion perception.

8. The method for adaptively adjusting an image of a liquid crystal display based on ambient light sensing according to claim 1, wherein The display image rendering of the liquid crystal display screen according to the optimization result of the adjustment decision vector search includes: Establish a user emotion dataset and configure an energy-saving tolerance factor for each emotion state; Use the energy-saving tolerance factor to construct an energy-saving optimization function, and perform energy-saving optimization based on the optimization result of the adjustment decision vector search using the energy-saving optimization function; Perform display image rendering of the liquid crystal display screen with the energy-saving optimization result.

9. The adaptive image adjustment method for a liquid crystal display based on ambient light sensing according to claim 1, wherein, The linked acquisition device includes an acquisition camera, a microphone, and a wearable physiological data acquisition device.

10. An adaptive image adjustment device for a liquid crystal display based on ambient light sensing, characterized in that, For performing the steps of the liquid crystal display screen adaptive image adjustment method based on ambient light sensing according to any one of claims 1 to 9, including: An ambient light field perception module, configured to call an RGB camera and an ambient light sensor to perform ambient light field perception, reconstruct an ambient 3D light field distribution, and establish light field emotion perception using the 3D light field distribution; A constraint construction module, configured to extract the display content of the liquid crystal display screen and construct an adjustment tolerance constraint based on the display content; A multi-dimensional data perception module, configured to activate the linked acquisition device, perform multi-dimensional data perception of the user based on the linked acquisition device, and establish a user emotion vector using the multi-dimensional data perception result; An adjustment decision vector search optimization module, configured to, after establishing an adjustment decision vector, use the light field emotion perception, the adjustment tolerance constraint, and the user emotion vector as input data, and send them to a multi-objective collaborative adjustment controller to perform adjustment decision vector search optimization. The collaborative objectives of the multi-objective collaborative adjustment controller include a user emotion resonance objective, a violation degree objective of the adjustment tolerance, and a light field emotion fusion matching degree objective; A display image rendering module, configured to perform display image rendering of the liquid crystal display screen according to the optimization result of the adjustment decision vector search.

Images