Color temperature adjustment method and system for display

Abstract

The present invention discloses a method and system for adjusting the color temperature of a display. The method includes: collecting spectral data of an ambient light source in an environment in which the display is located, performing multi-scale decomposition on the spectral data, and extracting spectral characteristic information of the ambient light source; identifying the current ambient light source type based on the spectral characteristic information, and obtaining the color temperature information and intensity distribution of the ambient light source; obtaining the user's historical ambient light source information and color temperature adjustment information, and adjusting the current color temperature of the display in combination with the current ambient light source type, the intensity distribution of the ambient light source, and the color temperature information; receiving user feedback on the adjusted color temperature, and dynamically adjusting the color temperature adjustment strategy based on the feedback information. Utilizing embodiments of the present invention, it is possible to integrate the spectral characteristic information of the ambient light source, accurately identify the light source type, and dynamically adjust the color temperature of the display based on the user's historical information and real-time feedback to achieve optimal user experience and visual comfort.

Description

Technical Field

[0001] The present invention belongs to the technical field of displays, and in particular to a method and system for adjusting the color temperature of a display. Background Art

[0002] With the rapid development of modern technology, monitors have become an indispensable electronic device in our daily lives and work. Whether it's smartphones, tablets, TVs, or computer monitors, excellent display quality and user experience are widely valued. When using a monitor, color temperature is a key factor affecting image quality and viewing comfort.

[0003] Color temperature refers to the warm or cool properties of the color of a light source, and is usually quantified in Kelvin (K). Lower color temperatures (such as 2700K-3000K) typically exhibit warm yellow and red tones, making them suitable for use at night or in low-light environments; while higher color temperatures (such as 5000K-6500K) typically appear as clear and bright white or blue, making them suitable for use during the day or in brightly lit environments. Changes in color temperature not only affect the presentation of images, but also have a significant impact on the user's visual comfort and health. For example, prolonged use of high-color temperature displays may lead to visual fatigue, dry eyes, and other problems. Existing methods for adjusting the color temperature of displays are mainly manual adjustments. Many displays provide a manual color temperature adjustment function, allowing users to adjust the color temperature according to their personal preferences through menu options. Although this method is simple and intuitive, it often lacks flexibility and is not smart or convenient enough. Summary of the Invention

[0004] The purpose of the present invention is to provide a method and system for adjusting the color temperature of a display to address the deficiencies in the prior art. The method and system can integrate the spectral characteristic information of the ambient light source, accurately identify the light source type, and dynamically adjust the color temperature of the display based on the user's historical information and real-time feedback to achieve the best user experience and visual comfort.

[0005] An embodiment of the present application provides a method for adjusting the color temperature of a display, the method comprising:

[0006] Collecting spectral data of the ambient light source in the environment where the display is located, performing multi-scale decomposition on the spectral data, and extracting spectral characteristic information of the ambient light source;

[0007] According to the spectral characteristic information, identify the current ambient light type and obtain the color temperature information and intensity distribution of the ambient light;

[0008] Obtain the user's historical ambient light source information and color temperature adjustment information, and adjust the current color temperature of the display based on the current ambient light source type, intensity distribution, and color temperature information;

[0009] Receive user feedback on the adjusted color temperature, and dynamically adjust the color temperature adjustment strategy based on the feedback information.

[0010] Optionally, performing multi-scale decomposition on the spectral data to extract spectral feature information of the ambient light source includes:

[0011] The spectral data is subjected to multi-scale decomposition, spectral features at a specific scale are extracted, and a spectral feature vector is generated, wherein the spectral feature vector includes: spectral intensity, wavelength, and color temperature-related characteristic indicators of the feature point.

[0012] Optionally, identifying the type of ambient light source according to spectral characteristic information includes:

[0013] Performing fuzzy reasoning based on the spectral feature vector to identify multiple possible light source types of the ambient light source;

[0014] Calculating confidence between the spectral feature vector and feature vectors of each possible light source type;

[0015] Calculating a weighted score for each possible light source type based on the confidence level;

[0016] The light source type with the highest weighted score is determined as the final ambient light source type.

[0017] Optionally, acquiring the user's historical ambient light source information and color temperature adjustment information, and adjusting the current color temperature of the display in combination with the ambient light source type, the intensity distribution of the ambient light source, and the color temperature information, includes:

[0018] Obtain the user's historical ambient light source information and color temperature adjustment information, and search for the historical color temperature adjustment information corresponding to the historical ambient light source of the same type as the current ambient light source;

[0019] Determine the user's desired color temperature based on the retrieved historical color temperature adjustment information;

[0020] Based on the intensity distribution and color temperature information of the current ambient light source, calculate the impact of the ambient light source on the current color temperature;

[0021] According to the user desired color temperature and the impact value, the current color temperature of the display is adjusted through a preset state equation.

[0022] Optionally, receiving user feedback on the adjusted color temperature and dynamically adjusting the color temperature adjustment strategy according to the feedback information includes:

[0023] The Q-Learning algorithm based on reinforcement learning is used to dynamically adjust the color temperature adjustment strategy based on the user's satisfaction rating of the current color temperature. The difference between the user's satisfaction rating and the average of the historical satisfaction ratings is used as the reward value. The corresponding action is selected for color temperature adjustment based on the current Q value. The action selected is the one that maximizes the Q value.

[0024] Another embodiment of the present application provides a color temperature adjustment system for a display, the system comprising:

[0025] An extraction module is used to collect spectral data of the ambient light source in the environment where the display is located, perform multi-scale decomposition on the spectral data, and extract spectral characteristic information of the ambient light source;

[0026] The identification module is used to identify the type of the current ambient light source based on the spectral characteristic information and obtain the color temperature information and intensity distribution of the ambient light source;

[0027] An adjustment module is used to obtain the user's historical ambient light source information and color temperature adjustment information, and adjust the current color temperature of the display in combination with the current ambient light source type, intensity distribution of the ambient light source and color temperature information;

[0028] The adjustment module is used to receive user feedback on the adjusted color temperature and dynamically adjust the color temperature adjustment strategy based on the feedback information.

[0029] Yet another embodiment of the present application provides a storage medium, wherein the storage medium stores a computer program, wherein the computer program is configured to execute any of the above methods when run.

[0030] Yet another embodiment of the present application provides an electronic device, comprising a memory and a processor, wherein the memory stores a computer program, and the processor is configured to run the computer program to execute any of the above methods.

[0031] Compared with the prior art, the present invention provides a method for adjusting the color temperature of a display. The method collects spectral data of the ambient light source in the environment in which the display is located, performs multi-scale decomposition on the spectral data, and extracts spectral characteristic information of the ambient light source; identifies the current ambient light source type based on the spectral characteristic information, and obtains the color temperature information and intensity distribution of the ambient light source; obtains the user's historical ambient light source information and color temperature adjustment information, and adjusts the current color temperature of the display in combination with the current ambient light source type, intensity distribution and color temperature information; receives user feedback on the adjusted color temperature, and dynamically adjusts the color temperature adjustment strategy based on the feedback information, thereby being able to integrate the spectral characteristic information of the ambient light source, accurately identify the light source type, and dynamically adjust the color temperature of the display based on the user's historical information and real-time feedback to achieve optimal user experience and visual comfort. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] Figure 1 A hardware structure block diagram of a computer terminal for a method for adjusting the color temperature of a display provided by an embodiment of the present invention;

[0033] Figure 2 A schematic flow chart of a method for adjusting the color temperature of a display provided by an embodiment of the present invention;

[0034] Figure 3 A schematic structural diagram of a color temperature adjustment system for a display provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0035] The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present invention, and are not to be construed as limiting the present invention.

[0036] The embodiment of the present invention first provides a method for adjusting the color temperature of a display. The method can be applied to electronic devices such as computer terminals, specifically ordinary computers.

[0037] The following describes it in detail by taking running on a computer terminal as an example. Figure 1 The hardware structure block diagram of a computer terminal for a method for adjusting the color temperature of a display provided by an embodiment of the present invention. Figure 1 As shown, the computer terminal may include one or more ( Figure 1 Only one is shown) a processor 102 (the processor 102 may include but is not limited to a microprocessor MCU or a programmable logic device FPGA) and a memory 104 for storing data. Optionally, the computer terminal may also include a transmission device 106 for communication functions and an input and output device 108. It will be understood by those skilled in the art that Figure 1 The structure shown is only for illustration and does not limit the structure of the above-mentioned computer terminal. For example, the computer terminal may also include Figure 1 More or fewer components than shown, or with Figure 1 Different configurations shown.

[0038] The memory 104 can be used to store software programs and modules of application software, such as the program instructions / modules corresponding to the color temperature adjustment method of the display in the embodiment of the present application. The processor 102 executes various functional applications and data processing by running the software programs and modules stored in the memory 104, that is, implementing the above-mentioned method. The memory 104 may include a high-speed random access memory and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 104 may further include a memory remotely located relative to the processor 102, and these remote memories can be connected to the computer terminal via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0039] Transmission device 106 is used to receive or transmit data via a network. A specific example of such a network may include a wireless network provided by a computer terminal's communications provider. In one embodiment, transmission device 106 includes a network interface controller (NIC), which can be connected to other network devices via a base station to enable communication with the Internet. In another embodiment, transmission device 106 may be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0040] See also Figure 2 , an embodiment of the present invention provides a method for adjusting the color temperature of a display, which may include the following steps:

[0041] S201, collecting spectral data of an ambient light source in an environment where a display is located, performing multi-scale decomposition on the spectral data, and extracting spectral characteristic information of the ambient light source;

[0042] The first step involves collecting and analyzing spectral data from the ambient light source. The core goal of this process is to obtain the spectral characteristics of different light sources in the environment. This characteristic information can be used to identify the light source type and provide basic data for subsequent color temperature adjustment. Specifically, the spectral characteristics of the ambient light source include information such as its light intensity distribution and color temperature. They can reflect the nature of the light source (such as natural light, incandescent lamp, fluorescent lamp, etc.), thus laying an important foundation for color temperature adjustment of the display. By accurately acquiring and analyzing the spectral data of the ambient light source, the display can intelligently adapt to different environments, improving user visual comfort and reducing visual fatigue. At the same time, personalized color temperature adjustment can be achieved to best meet user preferences and needs.

[0043] A multi-channel spectral sensor can be installed near the display to periodically (e.g., every second) collect spectral data of ambient light. This sensor should be highly sensitive and perform in real time to ensure the acquisition of high-quality spectral signals. The spectral signals are then processed and filtered to eliminate high-frequency noise, ensuring data accuracy.

[0044] The collected raw spectral data is preprocessed, such as normalization and mean shift compensation, to eliminate possible environmental interference and sensor bias. The light intensity corresponding to each wavelength is calculated and mapped to a certain color temperature range (such as CCT value calculation).

[0045] Specifically, the spectral data is decomposed at multiple scales to extract spectral feature information of the ambient light source. The spectral data can be decomposed at multiple scales to extract spectral features at a specific scale to generate a spectral feature vector, wherein the spectral feature vector includes: spectral intensity, wavelength, and color temperature-related feature indicators of the feature point.

[0046] In the second step, the spectral data extracted in the first step undergoes multi-scale decomposition to extract spectral features at specific scales and generate a spectral feature vector. This feature vector not only includes the spectral intensity and wavelength of the feature points but also incorporates color temperature-related characteristic indicators. This processing provides richer information for identifying the type of ambient light source, further improving the accuracy of light source identification. The construction of the feature vector combines information compression and information extraction, ensuring a high signal-to-noise ratio during the classification and analysis of ambient light sources while avoiding interference from redundant information, providing a more effective basis for subsequent decision-making.

[0047] The spectral data obtained in the first step can be subjected to a wavelet transform. An appropriate wavelet basis is selected, the number of wavelet decomposition layers is set, and the spectral data is decomposed at different scales. At each decomposition scale, high- and low-frequency components are extracted to obtain spectral characteristics of different frequency components.

[0048] At each scale, the mean, variance, and peak of the spectral features are calculated to ensure that the potentially important features in the spectral data can be quantified. Signal processing techniques (such as thresholding) are used to extract significant feature points from the decomposition at multiple scales, which will serve as the basis for subsequent processing.

[0049] Based on the features extracted at each scale, a spectral feature vector is constructed. Each feature vector can reflect the spectral characteristics at that specific scale and characteristic indicators such as spectral intensity, wavelength, and color temperature.

[0050] The generated spectral feature vectors are normalized to ensure that the features are in the same dimension, which improves the sensitivity and accuracy of subsequent algorithms. Z-score normalization is used to make the mean of each feature 0 and the standard deviation 1.

[0051] If the generated feature vector has a high dimensionality, dimensionality reduction techniques such as principal component analysis (PCA) or linear discriminant analysis (LDA) can be used to further extract important features and reduce data redundancy. Selecting the most discriminative features provides more efficient data support for subsequent recognition.

[0052] Through the above steps, the spectral feature vector is successfully extracted and generated, which provides a rich information basis for the subsequent step of light source type identification and improves the accuracy and intelligence level of the entire color temperature adjustment method.

[0053] S202, identifying the type of the current ambient light source based on the spectral characteristic information, and obtaining the color temperature information and intensity distribution of the ambient light source;

[0054] In this step, the collected spectral signature information is analyzed to identify the type of light source in the current environment, and simultaneously obtain information about the color temperature and intensity distribution of these light sources. Specifically, the spectral signature information provides the intensity distribution of the light waves emitted by the ambient light source at different wavelengths. Combined with this information, the nature of the light source can be inferred, such as whether it is a light-emitting diode, incandescent lamp, or fluorescent lamp. The identified light source type and its characteristics will help the system understand the light source's color temperature and intensity distribution, which are relevant to human visual perception.

[0055] Accurate light source identification and acquisition of color temperature and intensity information provide the necessary basis for subsequent color temperature adjustment. Furthermore, adapting to the characteristics of different light sources enables displays to intelligently adjust color temperature, optimizing visual comfort, reducing visual fatigue, and enhancing the user experience. Furthermore, accurate acquisition of color temperature and intensity distribution lays the foundation for personalized settings and more precise environmental management, driving the development of intelligent display technology.

[0056] Specifically, the type of the ambient light source is identified based on the spectral feature information, and fuzzy reasoning can be performed based on the spectral feature vector to identify multiple possible light source types of the ambient light source;

[0057] Based on pre-extracted spectral feature vectors, a fuzzy inference algorithm is used to identify the possible light source types in the current environment. Fuzzy inference utilizes fuzzy logic to process uncertain information. By defining fuzzy sets and inference rules, spectral feature information is mapped to possible light source types. This process ensures rapid identification of multiple potential light source types, enabling rapid response and decision-making under uncertain environmental conditions. Fuzzy inference significantly enhances the system's adaptability and recognition capabilities in complex environments, laying the foundation for subsequent light source type determination.

[0058] A deep learning-based fuzzy inference network can be used to first train the historical light source spectral characteristics to generate a classifier. After receiving a new spectral feature vector, the classifier can combine historical data to dynamically generate fuzzy rules, identifying the possible light source type with higher accuracy.

[0059] Calculating confidence between the spectral feature vector and feature vectors of each possible light source type;

[0060] The confidence level for each light source type is determined by calculating the similarity between the spectral feature vector and the feature vectors of multiple possible light source types. This similarity can be measured using metrics such as cosine similarity and Euclidean distance to reflect the degree of spectral feature matching. The confidence level calculation provides a quantitative basis for the decision-making process, allowing the system to clearly identify the likelihood of each ambient light source type. By comparing the confidence level for each possible light source, recognition errors can be effectively reduced, thereby improving the accuracy of light source identification.

[0061] A multidimensional model can be established to map the eigenvectors of possible light sources to the eigenvector of the current spectrum. By weightedly combining different similarity calculation methods (such as cosine similarity and Manhattan distance), a comprehensive confidence scoring system is formed. This system dynamically adjusts weights based on changes in the eigenvectors, ensuring efficient recognition even in complex lighting environments. For example, similarity can be mapped to the interval [0, 1] to obtain the corresponding confidence level. High similarity results in a high confidence level (close to 1), while low similarity results in a low confidence level (close to 0).

[0062] Based on the confidence level, a weighted score is calculated for each possible light source type; wherein one weighted score may be:

[0063]

[0064] in, is the weighted score of the i-th light source, is the weight of the i-th light source, is the confidence level of the i-th light source. This formula is used to calculate a weighted score for each possible ambient light source type. By comprehensively considering the light source confidence level and the corresponding weight, it helps determine the true type of the current ambient light source.

[0065] Based on the calculated confidence level, each possible light source type is assigned a weighted score using preset weights. This weighted score allows the system to quickly identify the most likely light source type. This weighted scoring mechanism not only enables the system to identify light source types but also effectively rank the likelihood of different light sources. This allows the system to quickly determine the most likely light source type, even when multiple light sources are present, providing a crucial basis for subsequent color temperature adjustments.

[0066] Fuzzy logic controllers can be used to dynamically adjust the weights and confidence levels of each light source type. For example, based on user feedback and environmental changes, the weight of each light source can be adjusted to achieve a more flexible weighted scoring calculation. This approach enables the system to continuously optimize light source recognition as user habits and environmental conditions change.

[0067] The light source type with the highest weighted score is determined as the final ambient light source type.

[0068] Ultimately, the light source type with the highest weighted score is selected and determined as the current environment's light source type. This process ensures the system has clear decision-making capabilities and can quickly respond to changes in the environment. By determining the optimal light source type, the system not only provides accurate basic information for the next step of color temperature adjustment, but also further enhances the user experience, ensuring that the display presents the best visual effects under various environmental conditions. Furthermore, the final determination of the light source type facilitates effective optimization and adjustment of the system during subsequent operations.

[0069] An ensemble learning model can be used to vote on the outputs of multiple recognizers. Each recognizer performs a weighted score based on different feature sets, ultimately outputting the most likely light source type through weighted voting, thereby enhancing recognition accuracy and robustness. This approach combines the strengths of multiple models and maintains stable recognition performance under varying light sources and in complex environments.

[0070] Specifically, to obtain the color temperature and intensity distribution of the ambient light source, raw spectral data can be obtained from a multi-channel spectral sensor, recording the light intensity at each wavelength. The spectral data is converted into corresponding chromaticity coordinates (such as the CIE 1931 chromaticity diagram) and the corresponding color temperature value is calculated (e.g., using blackbody radiation theory).

[0071] Using a color temperature model, the color temperature of the ambient light source is calculated by substituting spectral data into a specific color temperature formula (such as Planckian Locus). Taking into account the color temperature fluctuations of the ambient light source, a sliding average method is used to smooth the color temperature to reduce the interference of instantaneous changes.

[0072] Based on the acquired spectral data, the light intensity distribution of the light source is calculated to determine how the intensity varies at different wavelengths. By constructing an intensity distribution model (such as a Gaussian function), the intensity distribution is fitted to extract features and generate an intensity distribution curve for the ambient light source within the visible light range.

[0073] S203, obtaining the user's historical ambient light source information and color temperature adjustment information, and adjusting the current color temperature of the display in combination with the current ambient light source type, the intensity distribution of the ambient light source, and the color temperature information;

[0074] First, the system obtains the user's past color temperature adjustment history and ambient light information to optimize the adjustment in the current environment. By combining historical data with the current environmental characteristics, the system can accurately determine and implement the user's color temperature preference, thereby improving the user experience.

[0075] This adjustment step improves the intelligence and adaptability of color temperature adjustment, allowing the display's color temperature to better match user needs and environmental changes, thereby enhancing the visual experience and comfort. Furthermore, integrating historical data eliminates the need to start from scratch each time, significantly improving efficiency.

[0076] Specifically, the user's historical ambient light source information and color temperature adjustment information may be obtained, and the historical color temperature adjustment information corresponding to the historical ambient light source of the same type as the current ambient light source may be searched;

[0077] During this step, the system leverages historical data to identify the current ambient light source type, ensuring it understands the user's adjustment habits in similar environments. By mining this historical data, the system can more accurately reflect the user's preferences and recommend color temperature settings that best meet their expectations.

[0078] A multi-dimensional database can be built, containing user color temperature adjustment information under different lighting environments. Using clustering algorithms (such as K-means clustering), historical light source types can be classified to help quickly locate and match similar historical records.

[0079] Determine the user's desired color temperature based on the retrieved historical color temperature adjustment information;

[0080] After verifying historical environmental information, the system extracts the user's adjustment preferences under similar conditions and forms the user's current desired color temperature. This determination guides subsequent adjustments and avoids negative user experiences caused by ineffective adjustments.

[0081] Time series analysis can be used to evaluate the color temperature changes of users under similar lighting conditions and identify the central trend of user preferences (e.g., using a sliding average to smooth the color temperature data to obtain the user's desired color temperature). Alternatively, the average of the adjusted color temperatures found can be directly taken as the user's desired color temperature.

[0082] Based on the intensity distribution and color temperature information of the current ambient light source, the influence value of the ambient light source on the current color temperature is calculated. One influence value may be:

[0083]

[0084] in, The color temperature of the current ambient light directly affects the decision of the display adjustment strategy. A higher ambient color temperature may mean that the display needs to lower the corresponding color temperature to maintain visual comfort. It provides a reference framework for the preset benchmark color temperature, so that the adjustment strategy can be appropriately modified relative to the standard. The current ambient light intensity indicates the illumination level of the current ambient light source. The higher the intensity, the stronger the response of the display to adjust the color temperature may be. The maximum ambient light intensity value provides a normalized standard for calculations, enabling comparison of impacts under different environmental conditions and enhancing the adaptability of adjustment strategies. This formula is used to calculate the impact of the current ambient light source on the display's color temperature. By considering the current ambient light intensity and color temperature and comparing it with a preset baseline color temperature, the quantitative impact on the display's color temperature adjustment is determined.

[0085] This step quantifies the impact of the current ambient light source on the display's color temperature for easier adjustment. By clarifying the extent of the ambient light's influence, we ensure that color temperature adjustments are appropriate, avoiding discomfort caused by an unsuitable external lighting environment.

[0086] According to the user's desired color temperature and the impact value, the current color temperature of the display is adjusted by a preset state equation. One of the preset state equations may be:

[0087]

[0088] in, is the color temperature of the display after adjustment, The current color temperature of the display serves as the basis for adjustment and affects the starting point of adjustment. The color temperature is the difference between the user's desired color temperature and the current color temperature, reflecting the user's needs and enabling the adjustment strategy to accurately meet user needs. The impact value reflects the specific impact of changes in ambient light sources on the color temperature of the display. The larger the impact value, the greater the adjustment range required for the display. 、 is the corresponding influence coefficient. This formula is used to calculate the adjusted color temperature of the display. By combining the user's desired color temperature, the current color temperature, and the environmental influence, the final color temperature adjustment is ensured to meet the user's expectations and environmental influences.

[0089] This step uses a formula to calculate a new color temperature setting, effectively adjusting the display's color temperature to the user's expectations. This ensures comfortable viewing in all environments, improving overall user satisfaction and overall experience.

[0090] S204: Receive user feedback on the adjusted color temperature, and dynamically adjust the color temperature adjustment strategy based on the feedback.

[0091] This step aims to collect real-time user feedback on the adjusted color temperature to guide subsequent color temperature adjustment strategies. This feedback can be in various forms, such as user satisfaction ratings, the frequency of manual adjustments, etc. The system will use this feedback to judge the effectiveness of the current adjustment and dynamically adjust future adjustment strategies.

[0092] 1. Personalized experience: Through user feedback, the system can better understand user preferences and needs, achieve personalized color temperature adjustment, and thus enhance the user experience.

[0093] 2. Adaptive learning: The system continuously learns through user feedback, optimizes the adjustment strategy so that it can adapt to user changes, and ultimately forms an intelligent adjustment mechanism.

[0094] 3. Reduce discomfort: Timely adjustments based on user feedback can reduce visual fatigue and discomfort caused by inappropriate color temperature and improve user comfort.

[0095] 4. Enhance user participation: By actively collecting user feedback, enhance user participation in the system, and make users more trusting and dependent on the intelligent system.

[0096] Specifically, the Q-Learning algorithm of reinforcement learning can be used to dynamically adjust the color temperature adjustment strategy based on the user's satisfaction rating information for the current color temperature feedback. The difference between the user's satisfaction rating and the average of the historical satisfaction ratings is used as the reward value, and the corresponding action is selected for color temperature adjustment based on the current Q value. The action selected is the action that maximizes the Q value.

[0097] A set of initial Q-value matrices can be randomly generated to represent the expected utility of each possible color temperature adjustment strategy in each state; information such as the display's color temperature setting, user satisfaction, and ambient light intensity is defined as a state space S; a set of adjustable color temperature ranges and their corresponding action sets A are defined, for example, increasing, decreasing, or maintaining the current color temperature; an experience replay pool is set up to store past state-action-reward combinations, and historical data is randomly selected periodically to update the Q-value to avoid adjustment strategy deviations caused by overfitting current user feedback; an ε-greedy strategy is adopted to select the action with the highest current Q-value in most cases, but randomly select actions in low-probability cases to maintain exploratory nature; a Q-value convergence threshold is set, and when the Q-value change is within the set range, the learning process is stopped to confirm that the strategy is stable; user satisfaction is regularly evaluated, and if satisfaction drops significantly, the strategy is triggered to reinitialize to cope with new environments and user needs.

[0098] In practical applications, we first collect user satisfaction ratings for the current color temperature. These ratings reflect the user's direct experience with the adjustment effect. The reward value is calculated as the difference between the user's satisfaction rating and the average of historical satisfaction ratings. This difference represents the user's satisfaction with the current adjustment effect.

[0099] Update the Q value according to the Q-Learning update formula:

[0100]

[0101] Where s is the current state, a is the selected action (color temperature adjustment strategy), R is the reward value fed back by the user, alpha is the learning rate, gamma is the discount factor, s' is the new state transferred to after executing the action, and a' is the selectable action in the new state.

[0102] An action is selected based on the current Q value, with the goal of maximizing the final Q value. This means that when adjusting the color temperature, the system will prioritize the strategy that was previously evaluated as the most effective. Based on the selected action, the system adjusts the color temperature accordingly and provides the user with the adjusted color temperature.

[0103] 1. Enhanced adaptability: Through dynamic adjustments based on user feedback, the system can continuously adapt to the changing needs of users and improve user satisfaction.

[0104] 2. Real-time optimization: This algorithm enables the system to optimize adjustment strategies in real time, effectively respond to different environmental changes and user preferences, and form a closed-loop feedback mechanism.

[0105] 3. Improved intelligence: Utilizing the Q-Learning algorithm, the system has self-learning capabilities and can more accurately grasp user preferences as usage frequency increases.

[0106] 4. Improve user satisfaction: By continuously optimizing and adjusting strategies, we can ultimately improve overall user satisfaction and comfort, and enhance user experience.

[0107] By implementing the above steps, an intelligent color temperature adjustment system can be realized, which has the ability to dynamically learn and adapt, ensuring that users always get the best experience.

[0108] It can be seen that the spectral data of the ambient light source in the environment where the display is located is collected, the spectral data is decomposed at multiple scales, and the spectral characteristic information of the ambient light source is extracted; based on the spectral characteristic information, the current ambient light source type is identified, and the color temperature information and intensity distribution of the ambient light source are obtained; the user's historical ambient light source information and color temperature adjustment information are obtained, and the current color temperature of the display is adjusted in combination with the current ambient light source type, the intensity distribution of the ambient light source and the color temperature information; the user's feedback information on the adjusted color temperature is received, and the color temperature adjustment strategy is dynamically adjusted based on the feedback information, so that the spectral characteristic information of the ambient light source can be integrated, the light source type can be accurately identified, and the color temperature of the display can be dynamically adjusted based on the user's historical information and real-time feedback to achieve the best user experience and visual comfort.

[0109] Another embodiment of the present invention provides a color temperature adjustment system for a display, see Figure 3 , the system may include:

[0110] Extraction module 301, for collecting spectral data of the ambient light source in the environment where the display is located, performing multi-scale decomposition on the spectral data, and extracting spectral characteristic information of the ambient light source;

[0111] Identification module 302, used to identify the type of current ambient light source based on spectral characteristic information, and obtain color temperature information and intensity distribution of the ambient light source;

[0112] An adjustment module 303 is configured to obtain the user's historical ambient light source information and color temperature adjustment information, and adjust the current color temperature of the display based on the current ambient light source type, intensity distribution of the ambient light source, and color temperature information;

[0113] The adjustment module 304 is configured to receive user feedback on the adjusted color temperature and dynamically adjust the color temperature adjustment strategy based on the feedback.

[0114] It can be seen that the spectral data of the ambient light source in the environment where the display is located is collected, the spectral data is decomposed at multiple scales, and the spectral characteristic information of the ambient light source is extracted; based on the spectral characteristic information, the current ambient light source type is identified, and the color temperature information and intensity distribution of the ambient light source are obtained; the user's historical ambient light source information and color temperature adjustment information are obtained, and the current color temperature of the display is adjusted in combination with the current ambient light source type, the intensity distribution of the ambient light source and the color temperature information; the user's feedback information on the adjusted color temperature is received, and the color temperature adjustment strategy is dynamically adjusted based on the feedback information, so that the spectral characteristic information of the ambient light source can be integrated, the light source type can be accurately identified, and the color temperature of the display can be dynamically adjusted based on the user's historical information and real-time feedback to achieve the best user experience and visual comfort.

[0115] An embodiment of the present invention further provides a storage medium storing a computer program, wherein the computer program is configured to execute the steps of any one of the above method embodiments when running.

[0116] Specifically, in this embodiment, the above-mentioned storage medium may be configured to store a computer program for performing the following steps:

[0117] S201, collecting spectral data of an ambient light source in an environment where a display is located, performing multi-scale decomposition on the spectral data, and extracting spectral characteristic information of the ambient light source;

[0118] S202, identifying the type of the current ambient light source based on the spectral characteristic information, and obtaining the color temperature information and intensity distribution of the ambient light source;

[0119] S203, obtaining the user's historical ambient light source information and color temperature adjustment information, and adjusting the current color temperature of the display in combination with the current ambient light source type, the intensity distribution of the ambient light source, and the color temperature information;

[0120] S204: Receive user feedback on the adjusted color temperature, and dynamically adjust the color temperature adjustment strategy based on the feedback.

[0121] It can be seen that the spectral data of the ambient light source in the environment where the display is located is collected, the spectral data is decomposed at multiple scales, and the spectral characteristic information of the ambient light source is extracted; based on the spectral characteristic information, the current ambient light source type is identified, and the color temperature information and intensity distribution of the ambient light source are obtained; the user's historical ambient light source information and color temperature adjustment information are obtained, and the current color temperature of the display is adjusted in combination with the current ambient light source type, the intensity distribution of the ambient light source and the color temperature information; the user's feedback information on the adjusted color temperature is received, and the color temperature adjustment strategy is dynamically adjusted based on the feedback information, so that the spectral characteristic information of the ambient light source can be integrated, the light source type can be accurately identified, and the color temperature of the display can be dynamically adjusted based on the user's historical information and real-time feedback to achieve the best user experience and visual comfort.

[0122] An embodiment of the present invention further provides an electronic device, comprising a memory and a processor, wherein the memory stores a computer program, and the processor is configured to run the computer program to perform the steps in any one of the above method embodiments.

[0123] Specifically, the electronic device may further include a transmission device and an input / output device, wherein the transmission device is connected to the processor, and the input / output device is connected to the processor.

[0124] Specifically, in this embodiment, the processor may be configured to execute the following steps through a computer program:

[0125] S201, collecting spectral data of an ambient light source in an environment where a display is located, performing multi-scale decomposition on the spectral data, and extracting spectral characteristic information of the ambient light source;

[0126] S202, identifying the type of the current ambient light source based on the spectral characteristic information, and obtaining the color temperature information and intensity distribution of the ambient light source;

[0127] S203, obtaining the user's historical ambient light source information and color temperature adjustment information, and adjusting the current color temperature of the display in combination with the current ambient light source type, the intensity distribution of the ambient light source, and the color temperature information;

[0128] S204: Receive user feedback on the adjusted color temperature, and dynamically adjust the color temperature adjustment strategy based on the feedback.

[0129] It can be seen that the spectral data of the ambient light source in the environment where the display is located is collected, the spectral data is decomposed at multiple scales, and the spectral characteristic information of the ambient light source is extracted; based on the spectral characteristic information, the current ambient light source type is identified, and the color temperature information and intensity distribution of the ambient light source are obtained; the user's historical ambient light source information and color temperature adjustment information are obtained, and the current color temperature of the display is adjusted in combination with the current ambient light source type, the intensity distribution of the ambient light source and the color temperature information; the user's feedback information on the adjusted color temperature is received, and the color temperature adjustment strategy is dynamically adjusted based on the feedback information, so that the spectral characteristic information of the ambient light source can be integrated, the light source type can be accurately identified, and the color temperature of the display can be dynamically adjusted based on the user's historical information and real-time feedback to achieve the best user experience and visual comfort.

[0130] The above describes in detail the structure, features and effects of the present invention based on the embodiments shown in the drawings. The above is only a preferred embodiment of the present invention, but the scope of implementation of the present invention is not limited to what is shown in the drawings. Any changes made in accordance with the concept of the present invention, or modifications to equivalent embodiments with equivalent changes, which do not exceed the spirit covered by the description and drawings, should be within the scope of protection of the present invention.

Claims

1. A method for adjusting the color temperature of a display, characterized in that: The method comprises: Collecting spectral data of the ambient light source in the environment where the display is located, performing multi-scale decomposition on the spectral data, and extracting spectral characteristic information of the ambient light source; Identify the type of the current ambient light source based on the spectral characteristic information, and obtain the color temperature information and intensity distribution of the ambient light source; identifying the type of the ambient light source based on the spectral characteristic information includes: Perform fuzzy reasoning based on the spectral feature vector to identify multiple possible light source types of the ambient light source; calculate the confidence between the spectral feature vector and the feature vector of each possible light source type; and calculate a weighted score for each possible light source type based on the confidence; wherein the weighted score is: Ri_{source}=Wi_{source}·Ci_{source} Wherein, Ri_{source} is the weighted score of the i-th light source, Wi_{source} is the weight of the i-th light source, and Ci_{source} is the confidence of the i-th light source; the light source type with the highest weighted score is determined as the final ambient light source type, and the ambient light source type includes light-emitting diodes, incandescent lamps, or fluorescent lamps; Obtain the user's historical ambient light source information and color temperature adjustment information, and adjust the current color temperature of the display in combination with the current ambient light source type, the intensity distribution of the ambient light source, and the color temperature information. The user's historical ambient light source information and color temperature adjustment information are obtained, and historical color temperature adjustment information corresponding to historical ambient light sources of the same type as the current ambient light source is searched. The user's desired color temperature is determined based on the searched historical color temperature adjustment information. Based on the intensity distribution and color temperature information of the current ambient light source, the influence value of the ambient light source on the current color temperature is calculated. The influence value is: Where T_{ambient} is the current ambient light color temperature, T_{baseline} is the preset baseline color temperature, L_{ambient} is the current ambient light intensity, and L_{max} is the maximum ambient light intensity value; According to the user's desired color temperature and the impact value, the current color temperature of the display is adjusted by a preset state equation; wherein the preset state equation is: T_{new}=T_{current}+K_p·E+K_d·Delta T_{ambient} Where T_{new} is the color temperature of the display after adjustment, T_{current} is the current color temperature of the display, E is the difference between the user's desired color temperature and the current color temperature, Delta T_{ambient} is the influence value, and K_p and K_d are the corresponding influence coefficients; Receive user feedback on the adjusted color temperature, and dynamically adjust the color temperature adjustment strategy based on the feedback information.

2. The method according to claim 1, characterized in that The multi-scale decomposition of the spectral data to extract spectral characteristic information of the ambient light source includes: The spectral data is subjected to multi-scale decomposition, spectral features at a specific scale are extracted, and a spectral feature vector is generated, wherein the spectral feature vector includes: spectral intensity, wavelength, and color temperature-related characteristic indicators of the feature point.

3. The method according to claim 2, characterized in that The receiving user feedback information on the adjusted color temperature and dynamically adjusting the color temperature adjustment strategy according to the feedback information includes: The Q-Learning algorithm of reinforcement learning is used to dynamically adjust the color temperature adjustment strategy based on the user's satisfaction rating information on the current color temperature feedback. The difference between the user's satisfaction rating and the average of the historical satisfaction ratings is used as the reward value, and the corresponding action is selected according to the current Q value to adjust the color temperature. The action selected is the action that maximizes the Q value.

4. A color temperature adjustment system for a display, characterized in that: The system comprises: An extraction module is used to collect spectral data of the ambient light source in the environment where the display is located, perform multi-scale decomposition on the spectral data, and extract spectral characteristic information of the ambient light source; An identification module is configured to identify the current ambient light source type based on spectral feature information and obtain the color temperature information and intensity distribution of the ambient light source. Identifying the ambient light source type based on the spectral feature information includes: performing fuzzy reasoning based on the spectral feature vector to identify multiple possible light source types of the ambient light source; calculating the confidence level between the spectral feature vector and the feature vectors of each possible light source type; and calculating a weighted score for each possible light source type based on the confidence level. The weighted score is: Ri_{source}=Wi_{source}·Ci_{source} Wherein, Ri_{source} is the weighted score of the i-th light source, Wi_{source} is the weight of the i-th light source, and Ci_{source} is the confidence of the i-th light source; the light source type with the highest weighted score is determined as the final ambient light source type, and the ambient light source type includes light-emitting diodes, incandescent lamps, or fluorescent lamps; The adjustment module is used to obtain the user's historical ambient light source information and color temperature adjustment information, and adjust the current color temperature of the display in combination with the current ambient light source type, the intensity distribution of the ambient light source, and the color temperature information. The module obtains the user's historical ambient light source information and color temperature adjustment information, searches for historical color temperature adjustment information corresponding to historical ambient light sources of the same type as the current ambient light source, determines the user's desired color temperature based on the searched historical color temperature adjustment information, and calculates the impact value of the ambient light source on the current color temperature based on the intensity distribution and color temperature information of the current ambient light source. The impact value is: Where T_{embient} is the current ambient light color temperature, T_{baseline} is the preset baseline color temperature, L_{ambient} is the current ambient light intensity, and L_{max} is the maximum ambient light intensity value; According to the user's desired color temperature and the impact value, the current color temperature of the display is adjusted by a preset state equation; wherein the preset state equation is: T_{new}=T_{current}+K_p·E+K_d·Delta T_{ambient} Where T_{new} is the color temperature of the display after adjustment, T_{current} is the current color temperature of the display, E is the difference between the user's desired color temperature and the current color temperature, Delta T_{ambient} is the influence value, and K_p and K_d are the corresponding influence coefficients; The adjustment module is used to receive user feedback on the adjusted color temperature and dynamically adjust the color temperature adjustment strategy based on the feedback information.

5. The system according to claim 4, characterized in that The extraction module is specifically used to: The spectral data is subjected to multi-scale decomposition, spectral features at a specific scale are extracted, and a spectral feature vector is generated, wherein the spectral feature vector includes: spectral intensity, wavelength, and color temperature-related characteristic indicators of the feature point.

6. A storage medium, characterized in that The storage medium stores a computer program, wherein the computer program is configured to execute the method according to any one of claims 1 to 3 when executed.

7. An electronic device comprising a memory and a processor, characterized in that: A computer program is stored in the memory, and the processor is configured to run the computer program to perform the method according to any one of claims 1 to 3.

Images