A kind of nimble light ring control method, system, storage medium and program product

Abstract

A kind of nimble light ring control method, system, storage medium and program product, in the method, construct multidimensional interactive feature space, state change information is mapped as trajectory point;State transition vector between adjacent trajectory points is calculated, and state transition threshold is determined;Several state stable intervals are divided;Interaction intensity curve is generated;The energy distribution function of state stable interval is calculated, and key interaction segment is determined;Feature parameter of key interaction segment is extracted and the energy gradient value of adjacent segment is obtained;According to feature parameter and energy gradient value, light effect rendering strategy is generated;According to light effect rendering strategy, the display state of nimble light ring is adjusted, to make the display state of nimble light ring and the fluctuation trend of energy distribution function keep synchronous change.This application improves the matching degree of nimble light ring collaborative operation when frequent state change and interactive event are carried out on panel, and then improves the adaptability of providing visual feedback for user.

Description

Technical Field

[0001] The present application relates to the field of lighting control, and in particular to a method, system, storage medium, and program product for controlling a dynamic halo light. Background Art

[0002] With the increasing popularity of mobile smart devices, tablets, due to their portability and large screens, are playing an increasingly important role in daily work and entertainment. To enhance user interaction and visual feedback, tablets often feature a ring-shaped indicator light around the front camera, known as a dynamic halo light. However, traditional dynamic halo lights only display basic device status information, such as power on and charging, and lack interaction with running tablet applications. This results in a limited functionality of the halo light, failing to fully realize its potential as a visual interaction element.

[0003] In related technologies, the type of application currently running can be identified and the corresponding display effect can be selected from a library of preset lighting effects. For example, a rhythmic effect can be displayed when playing a music player, or a competitive atmosphere lighting effect can be displayed when playing a game. This control method achieves a preliminary linkage between the halo light and the application scenario, enhancing the fun and interactivity of the device.

[0004] However, since applications often generate a large number of state changes and interaction events during operation, it is difficult to achieve deep collaboration between the halo light and the application by relying solely on the application type to select the preset lighting effect mode, and it is difficult to provide users with accurate and timely visual feedback. Summary of the Invention

[0005] The present application provides a method, system, storage medium, and program product for controlling a smart halo light, which are used to improve the matching degree of the coordinated operation of the smart halo light when a tablet undergoes frequent state changes and interactive events, thereby improving the adaptability of providing visual feedback to users.

[0006] In the first aspect, the present application provides a method for controlling a smart halo light, which obtains interaction data of a target application currently running on a tablet, the interaction data including status change information of the program interface, user touch operation information, and program resource usage information;

[0007] Construct a multidimensional interactive feature space based on the interactive data, and map the state change information into trajectory points in the multidimensional interactive feature space. Each trajectory point includes a state identifier, a timestamp, and spatial coordinate information.

[0008] Calculate the state transition vector between adjacent trajectory points and determine the state transition threshold based on the direction angle and vector modulus of the state transition vector;

[0009] Divide the trajectory points into several state stable intervals based on the state transition threshold;

[0010] For each stable state interval, an interaction intensity curve is generated by combining user touch operation information and program resource usage information;

[0011] The energy distribution function of the state stable interval is calculated based on the interaction intensity curve, and the area where the function value of the energy distribution function exceeds the preset energy threshold is determined as the key interaction segment;

[0012] Extract the characteristic parameters of key interaction segments and obtain the energy gradient values ​​of adjacent segments;

[0013] Generate a lighting effect rendering strategy based on the feature parameters and energy gradient values. The lighting effect rendering strategy includes energy pulse mode, gradient transition rules, and breathing cycle parameters.

[0014] The display state of the smart halo light is adjusted according to the lighting effect rendering strategy so that the display state of the smart halo light keeps pace with the fluctuation trend of the energy distribution function.

[0015] By employing the above technical solution, interaction data from the target application currently running on the tablet is collected to construct a multidimensional interaction feature space. State change information is mapped as trajectory points. State transition vectors are calculated to determine transition thresholds and then state stability intervals are divided. An interaction intensity curve is generated by combining touch operation and resource usage information. An energy distribution function is then derived, and characteristic parameters and energy gradient values ​​of key interaction segments are extracted. Finally, a lighting rendering strategy is generated to adjust the display state of the dynamic halo light, ensuring that the display state of the dynamic halo light accurately reflects the energy changes during the user's interaction with the application, with lighting effect changes synchronously mapped to interaction behavior. By employing multidimensional feature space mapping and the energy distribution function, the system accurately captures state changes and energy fluctuations during the interaction process. By dividing the state stability intervals and extracting key interaction segments, the lighting effect display maintains overall coherence while highlighting important interaction nodes, enhancing the naturalness and smoothness of the lighting effect experience. By controlling lighting effect rendering based on the energy distribution function, the lighting effect intensity changes are consistent with the user's interaction habits while accurately representing the energy fluctuations during the interaction, enhancing the intuitiveness and immersiveness of the lighting effect feedback.

[0016] In conjunction with some embodiments of the first aspect, in some embodiments, constructing a multidimensional interaction feature space based on interaction data specifically includes:

[0017] Build a circular buffer queue and store the state change information in the circular buffer queue;

[0018] The state change information in the circular buffer queue is input into the long short-term memory network to extract the temporal dependency features and obtain the feature vector sequence;

[0019] Input the feature vector sequence into the variational autoencoder for dimensionality reduction and compression to obtain low-dimensional feature representation;

[0020] Use low-dimensional feature representation to train the preset probability model and obtain the state transition probability matrix;

[0021] The feature space is adaptively gridded according to the state transition probability matrix to obtain a multi-dimensional interactive feature space.

[0022] By adopting the above technical solution, state change information is fed into a long short-term memory network through a circular buffer queue to extract temporal dependency features. This information is then compressed and reduced using a variational autoencoder to obtain a low-dimensional feature representation. This feature representation is then used to train a pre-set probability model to obtain a state transition probability matrix. Based on this representation, the feature space is adaptively meshed to obtain a multidimensional interaction feature space. This technical solution utilizes a deep learning model to perform multi-level feature extraction and dimensionality reduction on interaction data, reducing the complexity of the state space and enabling the system to efficiently process large amounts of real-time interaction data. By capturing the temporal dependencies of state changes through a long short-term memory network and combining it with the feature compression capabilities of a variational autoencoder, the constructed feature space retains key information from the interaction data while also exhibiting good generalization. Adaptive meshing based on the state transition probability matrix enables the structure of the feature space to dynamically adapt to interaction patterns in different application scenarios, improving the system's ability to express interactive behaviors and computational efficiency.

[0023] In conjunction with some embodiments of the first aspect, in some embodiments, for each state stability interval, an interaction intensity curve is generated by combining user touch operation information and program resource usage information, specifically including:

[0024] In the state stable interval, a sliding window of preset length is used to sample the user's touch operation information in segments to obtain a touch sequence sample;

[0025] Extracting touch pressure, velocity, and acceleration features from touch sequence samples to obtain a touch feature vector;

[0026] Perform wavelet transform on the program resource occupancy information within the state stable interval to obtain the resource occupancy feature vector;

[0027] Input the touch feature vector and resource occupancy feature vector into the multi-layer attention neural network to obtain the feature fusion result;

[0028] The feature fusion results are smoothed by Kalman filtering to generate an interaction intensity curve corresponding to the state stability interval.

[0029] By adopting the above technical solution, a sliding window is used to segmentally sample touch operation information within the stable state range and extract touch features. A wavelet transform is performed on program resource usage information to obtain resource usage features. The two types of feature vectors are input into a multi-layer attention neural network for feature fusion, and finally, a Kalman filter is used for smoothing to generate an interaction intensity curve. Through multi-dimensional feature extraction and fusion, a comprehensive analysis of user touch behavior and system resource status is achieved. The use of a sliding window for touch sequence sampling and feature extraction, combined with wavelet transform processing of resource usage data, enables the system to simultaneously capture local details and global trends during the interaction process. The feature fusion mechanism of the multi-layer attention neural network can adaptively adjust the weights of different features, improving the accuracy of interaction intensity calculation, while the Kalman filter smoothing ensures the continuity and stability of the interaction intensity curve, reducing the impact of noise interference on lighting effect control.

[0030] In conjunction with some embodiments of the first aspect, in some embodiments, after adjusting the display state of the dynamic halo light according to the lighting effect rendering strategy, the method further includes:

[0031] Obtain the gaze coordinate data and gaze duration data collected by the user's eye movement sensor;

[0032] Collect the user's current application scenario identification and operation behavior data on the tablet;

[0033] Generate gaze heat distribution map based on gaze coordinate data and divide lighting effect priority areas;

[0034] Configure the brightness gradient and display density of the dynamic halo light based on the lighting effect priority area;

[0035] Write the brightness gradient and display density parameters into the lighting effect rendering strategy.

[0036] By employing the aforementioned technical solution, gaze data and gaze duration data collected by the user's eye movement sensor are acquired. Combined with the user's application scenario identifiers and operational behavior data on the tablet, a gaze heat map is generated and lighting effect priority zones are divided. The brightness gradient and display density parameters of the Smart Halo Light are configured accordingly. This technical solution uses visual attention data to guide lighting effect configuration, enabling the Smart Halo Light's display to adapt to the user's visual attention pattern. The gaze heat map intuitively reflects the user's visual attention distribution, and the lighting effect priority zones divided based on this map accurately guide the allocation of lighting effect resources. The brightness gradient and display density configured according to the priority zones align the lighting effect intensity with the user's visual attention, enhancing the accuracy and effectiveness of lighting effect prompts. The dynamic matching of lighting effect display parameters with user visual behavior improves the targeted lighting effect feedback and reduces ineffective or disruptive lighting effect displays.

[0037] In conjunction with some embodiments of the first aspect, in some embodiments, configuring the brightness gradient and display density of the dynamic halo light based on the lighting effect priority area specifically includes:

[0038] Calculate the shortest projection distance from the lighting effect priority area to the tablet frame;

[0039] Establish a brightness attenuation function based on the shortest projection distance;

[0040] Generate brightness gradient values ​​and activation density coefficients for each segment based on the brightness attenuation function;

[0041] Convert the brightness gradient value into the adjustment instruction of LED driving current;

[0042] Configure the brightness gradient and display density of the dynamic halo light based on the activation density coefficient.

[0043] By adopting the above technical solution, the shortest projection distance from the lighting effect priority area to the tablet frame is calculated, and a brightness attenuation function that takes into account spatial position relationships is established, so that the lighting effect display can be reasonably attenuated according to the laws of visual perception. Based on the brightness gradient values ​​and activation density coefficients generated for each segment based on the brightness attenuation function, precise control of the lighting effect intensity is achieved. The brightness gradient value is converted into an adjustment instruction for the LED drive current, and the display parameters are configured according to the activation density coefficient, so that the display effect of the smart halo light can form a good correspondence with the user's actual visual attention area. This adaptive brightness configuration method based on spatial distance avoids interference with the user's vision caused by the lighting effect display and improves the comfort of the lighting effect prompt. By precisely controlling the LED drive current, the display effect is guaranteed while reducing energy consumption, and the visual impact of sudden brightness changes between different areas on the user is reduced.

[0044] In conjunction with some embodiments of the first aspect, in some embodiments, after configuring the brightness gradient and display density of the smart halo light according to the activation density coefficient, the method further includes:

[0045] Monitor the lighting effect display status after configuration;

[0046] Collect user interaction response data to the current lighting effect configuration;

[0047] Evaluate the suitability of the current lighting effect configuration based on the interaction response data.

[0048] By adopting the above technical solution, the actual usage effect of the lighting effect configuration can be directly obtained by monitoring the display status of the configured lighting effect in real time and collecting the user's interactive response data to the current lighting effect configuration. The adaptability of the current lighting effect configuration is evaluated based on the interactive response data, allowing the system to understand whether the lighting effect configuration conforms to the user's usage habits and visual experience. This evaluation mechanism based on actual user feedback overcomes the problem that the preset configuration parameters may not match the user's actual needs. By continuously collecting and analyzing user interactive response data, the system can promptly identify problems in the lighting effect configuration, provide an accurate evaluation basis for subsequent parameter optimization, improve the personalization and practicality of the lighting effect configuration, and enhance the user experience.

[0049] In conjunction with some embodiments of the first aspect, in some embodiments, evaluating the adaptability of the current lighting effect configuration based on the interactive response data specifically includes:

[0050] Statistics on the user's operation accuracy and response time under the current lighting effect configuration;

[0051] Identify the success rate of lighting effect configurations in guiding user attention;

[0052] Calculate the degree of matching between the lighting effect brightness gradient and the user's line of sight;

[0053] Generate the current lighting effect configuration adaptability based on the success rate and matching degree.

[0054] By adopting the above technical solutions, the system establishes a comprehensive adaptation evaluation system by counting the user's operation accuracy and response time under the current lighting effect configuration, identifying the success rate of the lighting effect configuration in guiding the user's attention, and calculating the degree of match between the lighting effect brightness gradient and the user's line of sight. This system takes into account the user's operational performance, attention guidance effect, and the coordination of the visual experience, making the adaptation evaluation results more objective and accurate. By quantifying the user's actual usage effect into specific evaluation indicators, the system can accurately identify the advantages and disadvantages of the current lighting effect configuration. The adaptation evaluation results generated based on the success rate and matching degree provide a reliable decision-making basis for the dynamic optimization of the lighting effect configuration, improving the system's ability to adapt to user needs.

[0055] In a second aspect, an embodiment of the present application provides a smart halo light control system, which includes: one or more processors and a memory; the memory is coupled to the one or more processors, the memory is used to store computer program code, the computer program code includes computer instructions, and the one or more processors call the computer instructions to enable the system to execute the method described in the first aspect and any possible implementation of the first aspect.

[0056] In a third aspect, an embodiment of the present application provides a computer-readable storage medium comprising instructions, which, when executed on a system, enables the system to execute the method described in the first aspect and any possible implementation of the first aspect.

[0057] In a fourth aspect, an embodiment of the present application provides a computer program product, characterized in that when the computer program product is run on a system, the system executes the method described in any possible implementation manner in the first aspect.

[0058] One or more technical solutions provided in the embodiments of this application have at least the following technical effects or advantages:

[0059] This application provides a method for controlling a dynamic halo light. This method acquires interaction data from the target application currently running on a tablet, constructs a multidimensional interaction feature space, and maps state change information into trajectory points. The method then calculates the state transition vector, determines the transition threshold, and then divides the state into stable intervals. The method then generates an interaction intensity curve based on touch operation and resource usage information. This curve then generates an energy distribution function, extracts the characteristic parameters and energy gradient values ​​of key interaction segments, and ultimately generates a lighting rendering strategy to adjust the dynamic halo light display state. This ensures that the dynamic halo light display accurately reflects the energy changes during the user's interaction with the application, and the lighting effect changes are synchronously mapped to the interaction behavior. By using multidimensional feature space mapping and the energy distribution function, the system accurately captures state changes and energy fluctuations during the interaction process. By dividing the stable intervals and extracting key interaction segments, the lighting effect display maintains overall coherence while highlighting important interaction nodes, enhancing the naturalness and smoothness of the lighting effect experience. By controlling the lighting effect rendering based on the energy distribution function, the lighting effect intensity changes conform to the user's interaction habits while accurately expressing the energy fluctuations during the interaction, enhancing the intuitiveness and immersiveness of the lighting effect feedback.

[0060] 2. The present application provides a method for controlling a smart halo light, which obtains the gaze data and gaze duration data collected by the user's eye movement sensor, combines the user's application scenario identification and operation behavior data on the tablet, generates a gaze heat distribution map and divides the lighting effect priority areas, and configures the brightness gradient and display density parameters of the smart halo light accordingly. This technical solution guides the lighting effect configuration by introducing visual attention data, so that the display effect of the smart halo light can adapt to the user's visual attention mode. The gaze heat distribution map intuitively reflects the user's visual attention distribution, and the lighting effect priority areas divided based on this can accurately guide the allocation of lighting effect resources. The brightness gradient and display density configured according to the priority area form a corresponding relationship between the lighting effect intensity and the user's visual attention, thereby enhancing the accuracy and effectiveness of the lighting effect prompts. The dynamic matching of lighting effect display parameters with user visual behavior improves the pertinence of lighting effect feedback and reduces invalid or disruptive lighting effect displays.

[0061] 3. The present application provides a method for controlling a smart halo light. By real-time monitoring of the display status of the configured lighting effect and collecting the user's interactive response data to the current lighting effect configuration, the actual usage effect of the lighting effect configuration can be directly obtained. The adaptability of the current lighting effect configuration is evaluated based on the interactive response data, so that the system can understand whether the lighting effect configuration conforms to the user's usage habits and visual perception. This evaluation mechanism based on actual user feedback overcomes the problem that the preset configuration parameters may not match the user's actual needs. By continuously collecting and analyzing the user's interactive response data, the system can promptly discover problems in the lighting effect configuration, provide an accurate evaluation basis for subsequent parameter optimization, improve the personalization and practicality of the lighting effect configuration, and enhance the user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0062] Figure 1 This is a flow chart of a method for controlling a dynamic halo light in an embodiment of the present application.

[0063] Figure 2 This is a flow chart of a lighting effect configuration method based on user visual attention in an embodiment of the present application.

[0064] Figure 3 This is a schematic diagram of the physical device structure of a smart halo light control system provided in an embodiment of the present application. DETAILED DESCRIPTION

[0065] The terms used in the following examples of the present application are only for the purpose of describing specific embodiments and are not intended to limit the present application. As used in the specification and appended claims of this application, the singular expressions "a," "an," "said," "above," "the," and "this" are intended to include plural expressions as well, unless the context clearly indicates otherwise. It should also be understood that the term "and / or" used in this application refers to any or all possible combinations comprising one or more of the listed items.

[0066] In the following, the terms "first" and "second" are used for descriptive purposes only and should not be understood to imply or suggest relative importance or implicitly indicate the number of the technical features indicated. Therefore, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. In the description of the embodiments of this application, unless otherwise specified, "plurality" means two or more.

[0067] The following uses an embodiment and combines Figure 1 , a method for controlling a dynamic halo light in an embodiment of the present application is described:

[0068] See also Figure 1, which is a flow chart of a method for controlling a smart halo light in an embodiment of the present application.

[0069] S101, obtaining interaction data of a target application currently running on the tablet, constructing a multi-dimensional interaction feature space based on the interaction data, and mapping state change information to trajectory points in the multi-dimensional interaction feature space;

[0070] The system obtains the interaction data of the target application currently running on the tablet. The interaction data includes information on state changes in the program interface, user touch operation information, and program resource usage information. A multi-dimensional interaction feature space is constructed based on the interaction data, and the state change information is mapped to a trajectory point in the multi-dimensional interaction feature space. Each trajectory point includes a state identifier, a timestamp, and spatial coordinate information. Specifically: a circular buffer queue is constructed, and the state change information is stored in the circular buffer queue; the state change information in the circular buffer queue is input into a long short-term memory network to extract temporal dependency features and obtain a feature vector sequence; the feature vector sequence is input into a variational autoencoder for dimensionality reduction and compression to obtain a low-dimensional feature representation; the low-dimensional feature representation is used to train a preset probability model to obtain a state transition probability matrix; the feature space is adaptively gridded according to the state transition probability matrix to obtain a multi-dimensional interaction feature space.

[0071] This step forms the basis of the smart halo light control method, with the goal of acquiring the application's interaction data and constructing a multidimensional feature space capable of characterizing application state changes. The system first obtains various interaction data from the target application currently running on the tablet, including state changes in the program interface, user touch operations, and resource usage during program runtime. Based on this raw interaction data, the system constructs a multidimensional interaction feature space through operations such as feature extraction and dimensionality reduction. In this feature space, each dimension represents a type of interaction feature. The state changes of the application during operation are mapped to a trajectory in this feature space, with each point on the trajectory corresponding to the state of the application at a certain moment.

[0072] To construct a multidimensional interactive feature space, the system can employ the following technical solutions: First, state change information is stored in a circular buffer queue, which retains the recent state change history. The state change information in the queue is then fed into a long short-term memory (LSTM) neural network. The LSTM extracts the temporal dependency characteristics of the state changes, generating a series of feature vectors. Next, a variational autoencoder (VAE) is used to reduce the dimensionality of the feature vector sequence, yielding a more streamlined low-dimensional feature representation. Based on the low-dimensional features, the system trains a preset probabilistic model to obtain a transition probability matrix between states. Finally, the feature space is adaptively gridded based on the state transition probabilities, yielding the final multidimensional interactive feature space. In this space, each grid represents an application state, and the size of the grid reflects the stability of that state.

[0073] S102, calculating the state transition vector between adjacent trajectory points, and determining the state transition threshold according to the direction angle and vector modulus of the state transition vector;

[0074] In this step, the system further analyzes the distribution of trajectory points in the multidimensional interaction feature space to identify transition patterns between different interaction states, specifically rapid transitions and sudden changes between states. State transitions often signal significant changes in the user-program interaction and are a key factor in driving lighting effects. By measuring the state transition vectors between adjacent trajectory points, the dynamic characteristics of state transitions, such as direction and rate, can be accurately characterized.

[0075] Specifically, the system first needs to construct a directed adjacency relationship of the trajectory points according to the timestamp order of the trajectory points, that is, the predecessor and successor of each trajectory point. Then, for each pair of adjacent trajectory points, the system calculates their coordinate difference vector in the interaction feature space to obtain a state transition vector. The direction of the transition vector represents the trend of state change, the components of the vector in different feature dimensions reflect the relative change intensity of each interaction factor, and the modulus of the vector reflects the severity of the state change. By calculating the angle between the transition vector and each feature axis, the system can determine the dominance of state changes in different interaction modes; and by calculating the Euclidean length of the transition vector, the jump amplitude of the state change can be measured.

[0076] Furthermore, the system can use methods such as statistical hypothesis testing to perform significance analysis on the migration vectors between different trajectory points. By setting hypothesis test thresholds for indicators such as vector modulus and direction angle, key transition points in the state space can be automatically identified. These transition points often correspond to significant changes in the user's interaction mode with the program, such as the rapid transfer of operation hotspots, major switching of application functions, etc., and the corresponding lighting effects usually also need to make obvious changes in response. Therefore, determining the key state transition threshold through hypothesis testing can help the system accurately grasp the mutation points of the interaction rhythm and adjust the lighting effects in time to match the interactive experience.

[0077] S103, dividing the trajectory points into several state stable intervals based on the state transition threshold;

[0078] After identifying key transition points in the state-space trajectory, this step involves further dividing the trajectory sequence into several phased state stability intervals. Each stability interval contains a series of trajectory points that maintain continuity and stability in interaction mode and operational state, representing a relatively complete and consistent stage of user-program interaction. This stable interval division enables a macro-level structured description of interaction behavior over time, facilitating targeted analysis and control strategy generation for different interaction stages.

[0079] Specifically, the system cuts and segments the trajectory point sequence based on the identified state transition points. A state stable interval is formed before and after each transition point, and the transition point itself becomes the critical point of the adjacent stable interval. In order to ensure that the interaction state characteristics of each stable interval are statistically consistent and stable, the system usually needs to filter out stable intervals that are too short. The system can set a minimum length threshold for the stable interval, merge trajectory segments whose duration is lower than the threshold and no obvious state transition has occurred, and incorporate them into their adjacent stable intervals, thereby reducing the degree of fragmentation of the stable interval.

[0080] S104: For each stable state interval, generate an interaction intensity curve by combining user touch operation information and program resource usage information;

[0081] For each state-stable interval, the system generates an interaction intensity curve by combining user touch operation information and program resource occupancy information. Specifically, the system uses a sliding window of preset length to perform segmented sampling of user touch operation information within the state-stable interval to obtain touch sequence samples; extracts touch pressure, velocity, and acceleration features from the touch sequence samples to obtain a touch feature vector; performs wavelet transform on the program resource occupancy information within the state-stable interval to obtain a resource occupancy feature vector; inputs the touch feature vector and the resource occupancy feature vector into a multi-layer attention neural network to obtain a feature fusion result; and performs Kalman filtering on the feature fusion result to generate an interaction intensity curve corresponding to the state-stable interval.

[0082] In this step, the system needs to provide a more detailed quantitative characterization of the interaction process within each stable state interval. By generating an interaction intensity curve, it reveals the instantaneous changes in the intensity of the user's interaction with the program during this period. Interaction intensity is an important indicator of user enthusiasm and engagement. It combines the influence of user subjective initiative and the objective program load, and is closely related to the user's immersion and interactive experience. By analyzing interaction intensity, we can obtain the core control signals that drive lighting effects, synchronizing the lighting effects with the rhythm of the interaction process.

[0083] Specifically, in order to obtain interaction intensity information, the system needs to perform feature extraction and fusion analysis on two types of original interaction data: touch operation and resource occupancy within each stable interval. For touch operation data, the system uses a sliding window method to perform segmented sampling to obtain a series of touch sample sequences that reflect local operation characteristics. Then, the system extracts physical features such as touch pressure, speed, and acceleration that reflect the user's operation intention and behavior state for each touch sample to obtain a compact touch feature vector representation. As for resource occupancy data, due to its non-stationary characteristics and noise interference, traditional statistical features are difficult to accurately characterize. Therefore, the system uses time-frequency analysis methods such as wavelet transform to adaptively extract interaction load features such as texture and energy from the two dimensions of time and frequency through multi-scale decomposition of resource occupancy signals.

[0084] After obtaining touch features and resource usage features, the system needs to further establish a correlation between the two to obtain a fused representation of interaction strength. Considering the different contributions of touch and resource usage to interaction strength in different interaction stages and application scenarios, the system adopts the concept of an attention mechanism and proposes a multi-level feature fusion model. At the bottom level of the model, the system uses a network of gated units to process the two feature views of touch and resource usage separately, learning their internal temporal dependencies. At the top level of the model, the system uses attention weights to adaptively aggregate feature representations from different views, automatically extracting key determinants from the complex human-computer interaction signals. The middle layer of the model alternates between multi-head attention mechanisms to fully exploit the correlations between different interaction modalities and achieve cross-modal feature enhancement. This layered attention fusion mechanism gives the system the ability to actively understand interaction semantics, enabling it to flexibly adapt to different interaction scenarios.

[0085] Finally, the system maps the fused interaction intensity feature sequence onto the time axis of the stable interval to construct a time series of interaction intensity. Considering the continuity and smoothness of the interaction process, the system can further remove noise from the sequence using smoothing algorithms such as Kalman filtering. It also extracts morphological features of the sequence through methods such as peak detection and curve fitting to generate an interaction intensity curve corresponding to the stable interval.

[0086] S105, calculating an energy distribution function of a state stable interval based on the interaction intensity curve, and determining a region where the function value of the energy distribution function exceeds a preset energy threshold as a key interaction segment;

[0087] In this step, the system further extracts semantic meaning and analyzes the importance of the interaction intensity curve to identify the most critical interaction segments that impact the interactive experience. These segments often correspond to peak interaction intensity intervals, reflecting the concentrated energy distribution of the interaction process within the stable state range and the decisive period driving lighting effect changes. By constructing an energy distribution function, we can quantitatively characterize the contribution of interaction intensity at each moment to the overall interaction process. By setting energy thresholds, we can adaptively extract key interaction segments of varying importance to meet the needs of different lighting rendering requirements.

[0088] Specifically, after obtaining the interaction intensity curve, the system needs to design a measurement function to map the intensity value to the importance weight of the interaction process. An intuitive measurement idea is the energy method, which is to compare the interaction intensity curve to an energy signal. The integral area of ​​the curve on the time axis reflects the total energy of the interaction process, corresponding to the overall effort level of completing a certain interactive task input in the state stable interval. The high-intensity section on the curve corresponds to the time segment with high energy density and greater contribution to the interaction process. Therefore, the system can square the interaction intensity curve to obtain an energy density function that is proportional to the instantaneous energy. Then, the energy density function is integrated on the time axis and normalized to obtain the energy distribution function of the interaction process in the state stable interval. The function value of this function reflects the contribution weight of the interaction intensity at each moment to the completion quality of the overall interaction process.

[0089] S106, extracting characteristic parameters of key interaction segments and obtaining energy gradient values ​​of adjacent segments;

[0090] In this step, the system needs to provide a more nuanced quantitative characterization of the key interaction segments extracted in the previous step, providing the necessary parameter input for the subsequent generation of lighting effect mapping strategies. By extracting the characteristic parameters of key segments, the microscopic evolution of the interaction process within the segment can be described from multiple dimensions such as time, frequency, and morphology. By analyzing the energy gradient changes between adjacent segments, the fluctuations of the entire interaction process can be further characterized at a macro level. The combination of segment features and gradient information can form a comprehensive deconstruction of the key interaction semantics, providing rich and precise mapping elements for lighting effect control.

[0091] Specifically, for each key interaction segment, the system can extract multi-level and multi-type feature parameters. In the time domain, the system can calculate statistics such as the duration, average intensity, and intensity variance of the segment to reflect the continuity, intensity, and fluctuation of the interaction process within the segment; in the frequency domain, it can perform spectral analysis on the interaction intensity sequence of the segment, calculate indicators such as the frequency domain distribution of energy, spectral center of gravity, and bandwidth, and characterize the frequency characteristics of the interaction rhythm within the segment; in terms of morphology, it can perform morphological analysis on the intensity curve of the segment, extract key morphological points such as extreme points and inflection points, and calculate morphological parameters such as peak-to-valley height difference, rising and falling slopes, etc., to describe the detailed characteristics of the intensity changes within the segment. During the feature extraction process, the system can also make full use of existing audio and video signal analysis tool libraries and machine learning platforms, and through technologies such as transfer learning and knowledge distillation, make targeted improvements to the algorithm to form a dedicated feature engineering process suitable for interaction sequence analysis.

[0092] In addition to the characteristic information of the key segments themselves, the connection between segments during the interaction process also has important guiding significance for lighting effect design. To obtain the transition characteristics between adjacent segments, the system needs to calculate the difference between the energy distribution functions of adjacent segments to obtain the energy gradient value of the adjacent interval. The positive or negative sign of the gradient value reflects the rising and falling trend of the energy level when the interaction process crosses the key segment, while the absolute value of the gradient reflects the intensity of the energy level change. Based on the direction and form of the energy level transition, the system can semantically classify the connection transition between adjacent segments, such as gradual increase, sudden decrease, and oscillation of the energy level, and further quantify and analyze transition characteristic indicators such as the energy level transition amplitude and mutation rate. The combination of gradient features and internal segment features can form a complete characterization of key interactions in both time and space dimensions, allowing the system to fully understand the micro-details of human-computer interaction in the macro-semantic flow.

[0093] S107, generating a lighting effect rendering strategy according to the feature parameters and the energy gradient value;

[0094] The system generates a lighting effect rendering strategy based on the characteristic parameters and energy gradient values. The lighting effect rendering strategy includes energy pulse mode, gradual transition rules and breathing cycle parameters.

[0095] In this step, the system needs to further transform the interaction semantic parameters extracted previously, such as key segment features and adjacent segment energy gradients, into direct strategies for controlling lighting rendering. Lighting strategies directly dictate the lighting's appearance and dynamic changes at different moments and are key to achieving immersion and comfort. Ideal lighting design should cleverly blend the macrostructure and micro-details of the interaction process, creating a lighting atmosphere that aligns with the rhythm of human-computer interaction. Therefore, the generation of lighting strategies requires trade-offs and optimization across multiple parameter dimensions, while also supporting adaptive adjustments during the interaction process.

[0096] Specifically, the system starts from multiple visual channels such as hue, brightness, and saturation, designs lighting effect mapping functions for different interaction semantic parameters, and establishes a mapping relationship from parameter space to lighting control space. For example, the system can use the color temperature mapping function to map the average intensity level of key segments to the color temperature change of the light. The higher the interaction intensity, the higher the mapped color temperature, and the color light tends to be warmer. The system can also use the brightness mapping function to map the volatility of intensity to the dynamic change of light intensity. The more violent the fluctuation, the stronger the peak-to-valley contrast of the brightness change. In addition, the system can also use saturation mapping to map the mutation rate of the energy gradient to the saturation change of color. The steeper the energy level transition, the more obvious the saturation change of color. The combination and synergy of different mapping functions can render lighting effects that echo the interaction semantics in multiple visual dimensions.

[0097] S108: Adjust the display state of the dynamic halo light according to the lighting effect rendering strategy.

[0098] The system adjusts the display status of the smart halo light according to the lighting effect rendering strategy so that the display status of the smart halo light keeps pace with the fluctuation trend of the energy distribution function.

[0099] In this step, the system needs to translate the lighting rendering strategy into actual control actions for the dynamic halo lights, adjust the display status of the lights, and faithfully translate the changes in interactive semantics into the flow of light and shadow. This requires the lighting effect driving mechanism to be efficient, accurate, stable, and flexible at both the strategy parsing and hardware control levels.

[0100] First, the system needs to parse and transcode the lighting rendering strategy, extracting parameter information such as color, brightness, and dynamic characteristics specified in the strategy and converting it into specific lighting control instructions. Common strategy description formats include keyframe sequences, parameter curves, and state machine transition diagrams. The system needs to design efficient parsing algorithm frameworks for different description paradigms, balancing versatility and performance. For example, for frame sequence parsing, multithreaded parallel processing can be used to improve frame rate; for parameter curve parsing, a lookup table interpolation algorithm can be used to reduce computational overhead; and for state machine parsing, hash indexing can be used to improve conversion efficiency. Furthermore, due to the varying technical specifications and interface protocols of different lighting hardware, the system also needs to adapt rendering parameters to the hardware-specific instruction format based on the lighting hardware abstraction model during strategy transcoding. This system also performs instruction set optimization to achieve the optimal visual experience within constraints such as power consumption and latency.

[0101] After parsing and transcoding the policy, the system needs to transmit control commands to the Smart Halo Light's hardware circuitry in real time via a communication protocol and monitor the execution of these commands by each lighting unit. Existing lighting control communication solutions primarily include DMX512, DALI, and ZigBee. The system must select an appropriate communication protocol based on the lighting network topology and application scenario, balancing control latency, synchronization accuracy, dynamic range, and interference immunity. Furthermore, the system must carefully design and schedule the timing and priority of control commands to ensure visual consistency and synchronization across large-scale lighting arrays. For example, the system can adopt a master-slave centralized control architecture, where a central controller issues dimming commands to each lighting unit, simplifying synchronous control. Alternatively, the system can adopt an autonomous distributed control architecture, empowering each lighting unit with computing and storage capabilities to asynchronously execute policy scripts and reduce communication overhead. At the same time, in response to abnormal conditions that may occur when the lamps execute instructions, such as overheating protection and voltage instability, the system also needs to establish a real-time monitoring and early warning mechanism to dynamically adjust parameters such as the upper limit of brightness according to the working status of the lamps, and send warning information to users when necessary.

[0102] In the above embodiment, interaction data from the target application currently running on the tablet is acquired to construct a multidimensional interaction feature space. State change information is mapped as trajectory points. State transition vectors are calculated to determine transition thresholds and then state stable intervals are divided. An interaction intensity curve is generated by combining touch operation and resource usage information. An energy distribution function is then derived, and characteristic parameters and energy gradient values ​​for key interaction segments are extracted. Ultimately, a lighting rendering strategy is generated to adjust the display state of the dynamic halo light. This ensures that the display state of the dynamic halo light accurately reflects energy changes during the user's interaction with the application, with lighting effect changes synchronously mapped to interaction behavior. By employing multidimensional feature space mapping and the energy distribution function, the system accurately captures state changes and energy fluctuations during interaction. By dividing the state stable intervals and extracting key interaction segments, the lighting effect display maintains overall coherence while highlighting important interaction nodes, enhancing the naturalness and smoothness of the lighting effect experience. By controlling lighting effect rendering based on the energy distribution function, lighting effect intensity changes align with user interaction habits while accurately representing energy fluctuations during interaction, enhancing the intuitiveness and immersiveness of lighting effect feedback.

[0103] In order to further optimize the control effect of the smart halo light, the embodiment of the present application also provides a lighting effect configuration method based on the user's visual attention. This method realizes the precise matching of lighting effect display and user visual behavior by introducing eye tracking technology, and can further improve the pertinence of lighting effect feedback on the basis of the above-mentioned lighting effect rendering based on interactive data. This method not only takes into account the interaction status between the user and the application, but also combines the user's visual attention distribution characteristics to form a complete lighting effect control closed-loop system. Through the real-time collection and processing of visual attention data, the system can dynamically adjust the display parameters of the lighting effect, so that the display effect of the smart halo light is more in line with the user's visual perception habits. The following is combined with Figure 2 , a lighting effect configuration method based on user visual attention in an embodiment of the present application is described:

[0104] See also Figure 2 , which is a flow chart of a lighting effect configuration method based on user visual attention in an embodiment of the present application.

[0105] S201, obtaining gaze coordinate data and gaze duration data collected by the user's eye movement sensor;

[0106] This step aims to track and characterize the dynamic changes in the capacitor's impedance parameters during the energizing process. The instantaneous impedance reflects the microscopic process of dielectric polarization and charge response under AC excitation and is a key physical quantity that characterizes energy storage efficiency and loss levels. By calculating the impedance's temporal trajectory, we can understand the energy conversion and dissipation characteristics of the energizing process, which is an important basis for subsequent performance evaluation and optimization control.

[0107] The system can use methods such as frequency-domain impedance spectroscopy analysis or time-domain transient response analysis to measure the voltage and current waveforms across the capacitor in real time and estimate the impedance amplitude and phase angle based on an equivalent circuit model or differential equation model. During the estimation process, the system can combine signal processing techniques such as Kalman filtering and adaptive filtering to suppress the influence of factors such as power supply ripple and environmental noise, thereby improving the signal-to-noise ratio of the impedance trajectory. The system can also optimize the dynamic range and sensitivity of the impedance measurement by properly configuring parameters such as the frequency, amplitude, and waveform of the excitation signal.

[0108] In complex real-world applications, the impedance of capacitive devices can be affected by factors such as mechanical vibration and electromagnetic interference. To address this issue, the system employs methods such as adaptive threshold determination and wavelet denoising to detect and correct anomalies and distortion in the impedance trajectory in real time. Data collected from multiple sensors is used to enhance the robustness of impedance sensing through multi-source information fusion. The system can also adaptively adjust the gain of the measurement channel and the weighting coefficient of the measurement data based on changes in environmental conditions. In short, through adaptively optimized impedance parameter identification, the system can obtain a comprehensive and accurate instantaneous impedance change trajectory.

[0109] S202: Collect the user's current application scenario identifier and operation behavior data on the tablet;

[0110] Based on the impedance trajectory, this step further extracts key features that reflect the multi-scale characteristics of impedance variation. The wavelet transform is a time-frequency domain analysis tool that can simultaneously extract local time and frequency characteristics from time-domain signals, making it suitable for processing non-stationary, time-varying signals such as impedance. Multi-scale decomposition of the impedance trajectory using wavelet basis functions yields a series of characteristic components, or wavelet coefficients, that represent the impedance at different time and frequency scales. This provides a richer dimension of information for subsequent feature analysis and pattern recognition.

[0111] Depending on the capacitor's structural parameters and energizing conditions, the system can select different types of wavelet basis functions and decomposition scales, balancing time-frequency resolution with computational efficiency. For example, using compactly supported orthogonal wavelet bases such as Haar and Daubechies can yield wavelet coefficients with good locality and sparsity. During the decomposition process, the system can employ methods such as singular value decomposition to reduce the dimensionality of the coefficient matrix and design adaptive threshold functions to perform soft and hard thresholding on the coefficient amplitudes, extracting the most informative feature components.

[0112] In practical applications, due to the complexity and variability of the enabling conditions, the multi-scale characteristics of the impedance trajectory may exhibit time-varying drift. To address this issue, the system can use an adaptive wavelet transform algorithm to track the changes in the probability distribution of the scale coefficients and adaptively adjust the center frequency and time window length of the wavelet basis to achieve dynamic matching with the signal characteristics. In addition, the system can also use analysis methods such as wavelet packet decomposition and multi-wavelet fusion to enrich the types of multi-scale features and explore the impedance variation patterns from new feature dimensions such as energy and singularity. In short, through the adaptive optimization of the wavelet feature extraction method, the system can comprehensively characterize the multi-scale characteristics of the impedance trajectory in the time and frequency domains.

[0113] S203: Generate a gaze heat distribution map based on the gaze coordinate data and divide the lighting effect priority areas;

[0114] This step utilizes the multi-scale wavelet coefficients of impedance to further construct a quantitative evaluation index reflecting the stability of the charging process. This index, in turn, determines the minimum data observation period required for performance evaluation and condition monitoring. The stability index directly measures the severity and fluctuation of impedance changes during the charging process and is a key indicator for evaluating the quality of charging performance. Choosing the appropriate minimum observation period maximizes the timeliness of evaluation decisions while maintaining the statistical characteristics of the sampled data, reducing the time cost of blind observation and waiting.

[0115] The system can integrate indicators such as stationarity tests, time-frequency energy entropy, and constitutive correlation to assess impedance stability at different scales from multiple perspectives. For example, a stability index function is designed based on statistical quantities such as the mean, variance, and skewness of the wavelet coefficients, and a mapping model is constructed to convert the index values ​​into stability level scores. Furthermore, the system can use dimensionality reduction methods such as principal component analysis and independent component analysis to select the optimal feature subset for stability assessment. Fusion strategies such as fuzzy comprehensive evaluation can then be used to map multiple indicators into a comprehensive stability metric.

[0116] S204, configuring the brightness gradient and display density of the dynamic halo light based on the lighting effect priority area;

[0117] The system configures the brightness gradient and display density of the smart halo light based on the lighting effect priority area. Specifically, it calculates the shortest projection distance from the lighting effect priority area to the tablet frame; establishes a brightness attenuation function based on the shortest projection distance; generates brightness gradient values ​​and activation density coefficients for each segment based on the brightness attenuation function; converts the brightness gradient values ​​into adjustment instructions for the LED drive current; and configures the brightness gradient and display density of the smart halo light based on the activation density coefficient.

[0118] This step serializes the capacitance and temperature values ​​during the energizing process, based on the minimum observation period. Capacitance and temperature are two key physical quantities that affect the energizing effect. The capacitance sampling sequence reflects the charge storage dynamics caused by dielectric polarization, while the temperature sampling sequence reflects the energy dissipation of the energizing process. The changing patterns and interactions between the two determine the charging characteristics and performance of the capacitor. By collecting a complete capacitance-temperature sequence, the current energizing state can be accurately assessed and the remaining time for charging to complete can be predicted.

[0119] Based on the capacitor's design parameters, the system selects high-precision, wide-range, and interference-resistant sensor elements and, through scientifically and rationally arranged points, acquires the global temperature field distribution. During the sampling process, the system employs technologies such as DVFS, analog-to-digital conversion, and programmable gain amplification to adaptively adjust the sampling rate and amplification factor based on the signal's spectral characteristics, minimizing power consumption and storage overhead while maintaining signal quality. Furthermore, the system further enhances the reliability of sampled data through fault-tolerance mechanisms such as double-precision redundancy, adaptive compression, and anomaly detection.

[0120] In actual application scenarios, the capacitance-temperature sampling sequence may be affected by fluctuations in equipment operating conditions and interference from environmental factors, resulting in random omissions or abnormal distortion. To address this problem, the system can use algorithms such as data interpolation, compressed sensing, and causal convolution to flexibly fill in missing data, correct distortion, and achieve stable and reliable reconstruction of the sequence. The system can also comprehensively utilize prior knowledge such as physical modeling of capacitor components and big data mining to assist in anomaly detection and fault diagnosis of capacitance-temperature sequences, enhancing the robustness and interpretability of state perception. In short, through optimized sensor sampling and intelligent data repair, the system can obtain high-quality capacitance-temperature sequences, laying a data foundation for subsequent performance evaluation.

[0121] S205, writing the brightness gradient and display density parameters into the lighting effect rendering strategy;

[0122] This step quantitatively characterizes the effect of temperature changes on the capacitor charging characteristics through cross-correlation analysis of the capacitance sequence and the temperature sequence, and obtains the temperature influence coefficient. In the actual charging process, fluctuations in ambient temperature often cause synchronous changes in the capacitance value, resulting in a thermal expansion effect. Accurately estimating the temperature influence coefficient and establishing a decoupling compensation model for the capacitance value to temperature are key to achieving performance evaluation of the capacitor under constant temperature conditions and ensuring consistent charging results.

[0123] The system can use signal processing methods such as time-domain cross-correlation and frequency-domain coherence analysis to measure the similarity between capacitance and temperature sequences at different time and frequency scales. For example, by calculating the cross-correlation function of the two sequences, the time difference between the capacitance value and the temperature change is obtained, reflecting the speed of the temperature-capacitance response. The cross-power spectrum is calculated to characterize the frequency-domain gain of the capacitance value under temperature fluctuation excitation, reflecting the strength of the temperature-capacitance coupling. In the cross-correlation calculation, the system can also use preprocessing methods such as autoregressive sliding average and wavelet denoising to effectively remove the trend term and random noise of the sequence and highlight the temperature-capacitance correlation.

[0124] In complex actual production environments, the thermal characteristics of capacitors may drift as devices age and materials degrade, reducing the stability of the temperature-capacitance correlation. To address this issue, the system can regularly conduct online calibration tests, using charge and discharge data under multiple operating conditions and a wide temperature range to refresh the temperature influence coefficient. The system can also use optimization methods such as adaptive filtering and differential evolution to adjust the order and weight parameters of the cross-correlation model online to achieve synchronous tracking of the algorithm and system status. In short, through the dynamic adaptive cross-correlation modeling method, the system can accurately characterize the temperature-capacitance coupling characteristics, laying the model foundation for capacitor constant temperature compensation and performance evaluation.

[0125] S206, monitoring the lighting effect display status after configuration;

[0126] This step utilizes the temperature influence coefficient to perform physical-based decoupling and temperature drift correction on the original capacitance sampling sequence, restoring the capacitance variation pattern under isothermal conditions and eliminating the masking effect of ambient temperature fluctuations. Through model-based compensation and separation technology, the intrinsic polarization mechanism can be extracted from the time-varying capacitance sampling data, accurately perceiving the charge and discharge characteristics of the dielectric material during the energization process. This is the basis for traceable and evaluable capacitor performance under ever-changing temperature conditions.

[0127] Specifically, the system first estimates the temperature drift at each sampling moment based on the cross-correlation model, and then performs equivalent reverse compensation on the capacitance sampling value based on the temperature influence coefficient, thereby restoring the capacitance sequence to the change curve at the reference temperature and eliminating the influence of temperature fluctuations. During the compensation process, the system can use parameter identification methods such as least squares and Kalman filtering to adaptively calibrate the temperature influence coefficient to overcome parameter drift caused by aging, device differences, etc. In addition, the system can also use signal separation techniques such as independent component analysis and empirical mode decomposition to further decompose the compensated capacitance curve into intrinsic components of different time scales, which can not only remove random errors, but also quantitatively characterize the charging characteristics under different mechanisms.

[0128] S207, collecting user interaction response data to the current lighting effect configuration;

[0129] This step performs envelope tracking and morphological analysis on the capacitance change curve after decoupling compensation to extract relevant characteristic parameters. The capacitance envelope curve intuitively reflects the evolution of the polarization mechanism of the dielectric material as the charging process progresses, embodies the cumulative saturation characteristics of the polarization charge, and is an important basis for characterizing and predicting the charging behavior of capacitors. By analyzing characteristic parameters such as the amplitude fluctuation and steepness of the envelope curve, the progress stage of the current enabling state can be quantitatively assessed, thereby optimizing the charging control strategy.

[0130] The system can use signal processing techniques such as Hilbert transform and peak detection to extract the upper and lower envelopes of the capacitance change curve. Then, the morphological characteristics of the envelope curve are quantitatively characterized by parameters. For example, the starting capacitance value and the ending capacitance value reflect the change in the total amount of charge; the rise time and peak time reflect the speed of the charging rate; the maximum slope and the average slope reflect the magnitude of the polarization intensity; the curvature radius and the inflection point position reflect the stage-by-stage changes in the polarization mechanism. During the parameter extraction process, the system can also use time-frequency analysis methods such as wavelet analysis and empirical mode decomposition to adaptively separate the skeleton shape and detailed features of the envelope curve, overcome the influence of interference factors such as local fluctuations and background noise, and improve the accuracy and reliability of characteristic parameter identification.

[0131] In actual complex application scenarios, the envelope shape of the capacitance change curve may be diverse due to device differences and process fluctuations, making it difficult to fully characterize a fixed feature template. To address this problem, the system can adopt a data-oriented feature self-learning method, and through machine learning models such as deep convolutional networks, automatically extract deep features with strong discriminability and good generalization ability directly from massive sample data. In addition, the system can also adopt a transfer learning strategy, using prior knowledge such as material structure parameters and simulation models to guide the extraction and optimization of envelope features, and achieve synergistic enhancement between empirical models and data-driven. In short, through adaptive intelligent feature extraction methods, the system can comprehensively and accurately characterize the evolution characteristics of the capacitor charging envelope, providing richer decision-making basis for performance evaluation.

[0132] S208: Evaluate the adaptability of the current lighting effect configuration according to the interactive response data.

[0133] The system evaluates the adaptability of the current lighting effect configuration based on the interactive response data, specifically including: counting the user's operation accuracy and response time under the current lighting effect configuration; identifying the success rate of the lighting effect configuration in guiding the user's attention; calculating the degree of match between the lighting effect brightness gradient and the user's line of sight migration; and generating the adaptability of the current lighting effect configuration based on the success rate and matching degree.

[0134] This step uses the extracted capacitance envelope characteristics to make a comprehensive decision based on rules and data to determine whether the current capacitor needs to be re-energized. The so-called secondary empowerment means that after the conventional charging is completed, after a short dormancy, the pulse voltage is applied again to redistribute the residual polarization charge inside the capacitor to reduce dielectric loss and improve charging efficiency. By triggering the secondary empowerment in time, problems such as uneven local charging of the capacitor and low energy conversion efficiency can be overcome, thereby stabilizing the charging effect and shortening the aging process.

[0135] The system first qualitatively defines decision rules based on expert knowledge. For example, when the slope of the charging curve falls below the national standard, energy replenishment is required; when curve oscillations are insufficiently damped, charge distribution must be evened out; and when the curve inflection point appears prematurely, deep stimulation is required. Next, the system employs intelligent algorithms such as fuzzy logic and decision trees to map these qualitative decision rules to quantitative thresholds of characteristic parameters, forming precise judgment criteria. Furthermore, through data-driven methods such as incremental learning and online optimization, the system adaptively adjusts rule thresholds based on massive charging and discharging logs, continuously enhancing the accuracy and adaptability of its decisions.

[0136] In the above embodiment, the gaze data and gaze duration data collected by the user's eye movement sensor are obtained, and combined with the user's application scenario identification and operation behavior data on the tablet, a gaze heat distribution map is generated and the lighting effect priority areas are divided, and the brightness gradient and display density parameters of the smart halo light are configured accordingly. This technical solution guides the lighting effect configuration by introducing visual attention data, so that the display effect of the smart halo light can adapt to the user's visual attention mode. The gaze heat distribution map intuitively reflects the user's visual attention distribution, and the lighting effect priority areas divided based on this can accurately guide the allocation of lighting effect resources. The brightness gradient and display density configured according to the priority area form a corresponding relationship between the lighting effect intensity and the user's visual attention, thereby enhancing the accuracy and effectiveness of the lighting effect prompts. The dynamic matching of lighting effect display parameters with user visual behavior improves the pertinence of lighting effect feedback and reduces invalid or disruptive lighting effect displays.

[0137] The following describes the system in the embodiment of the present invention from the perspective of hardware processing. Figure 3 , which is a schematic diagram of the physical device structure of a smart halo light control system provided in an embodiment of the present application.

[0138] It should be noted that Figure 3 The structure of the system shown is only an example and should not limit the functions and scope of use of the embodiments of the present invention.

[0139] like Figure 3As shown, the system includes a central processing unit (CPU) 301, which can perform various appropriate actions and processes, such as the methods described in the above embodiments, based on programs stored in a read-only memory (ROM) 302 or programs loaded from a storage unit 308 into a random access memory (RAM) 303. RAM 303 also stores various programs and data required for system operation. CPU 301, ROM 302, and RAM 303 are interconnected via a bus 304. An input / output (I / O) interface 305 is also connected to bus 304.

[0140] The following components are connected to the I / O interface 305: an input section 306 including a camera, infrared sensor, and the like; an output section 307 including a liquid crystal display (LCD) and speakers; a storage section 308 including a hard disk and the like; and a communication section 309 including a network interface card such as a LAN (Local Area Network) card or a modem. The communication section 309 performs communication processing via a network such as the Internet. A drive 310 is also connected to the I / O interface 305 as needed. Removable media 311, such as a magnetic disk, optical disk, magneto-optical disk, or semiconductor memory, is installed in the drive 310 as needed, so that computer programs read from the media can be installed in the storage section 308 as needed.

[0141] In particular, according to embodiments of the present invention, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of the present invention include a computer program product comprising a computer program carried on a computer-readable medium, the computer program including a computer program for executing the methods illustrated in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via the communication section 309 and / or installed from removable media 311. When executed by the central processing unit (CPU) 301, the computer program performs the various functions defined in the present invention.

[0142] It should be noted that the computer-readable medium described in the embodiments of the present invention may be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. A computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to, an electrical connection having one or more conductors, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM), flash memory, optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In the present invention, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In the present invention, a computer-readable signal medium may include a data signal transmitted in baseband or as part of a carrier wave, which carries a computer-readable computer program. Such a propagated data signal may take any of a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof.

[0143] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architectures, functions and operations of the systems, methods and computer program products according to various embodiments of the present invention. Each box in the flowchart or block diagram can represent a module, program segment, or part of the code, and the above-mentioned module, program segment, or part of the code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the boxes can also occur in an order different from that marked in the accompanying drawings. For example, two boxes shown in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flowchart, and the combination of boxes in the block diagram or flowchart, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or can be implemented using a combination of dedicated hardware and computer instructions.

[0144] As another aspect, the present invention further provides a computer-readable storage medium, which may be included in the system described in the above embodiments, or may exist independently and not incorporated into the system. The storage medium carries one or more computer programs, and when executed by a processor of a system, the system implements the methods provided in the above embodiments.

[0145] As described above, the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the above embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the above embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present application.

[0146] As used in the above embodiments, the term “when” may be interpreted to mean “if” or “after” or “in response to determining that” or “in response to detecting that”, depending on the context. Similarly, the phrases “upon determining that” or “if (stated condition or event) is detected” may be interpreted to mean “if determining that” or “in response to determining that” or “upon detecting (stated condition or event)” or “in response to detecting (stated condition or event)”, depending on the context.

[0147] In the above embodiments, all or part of the embodiments can be implemented using software, hardware, firmware, or any combination thereof. When implemented using software, all or part of the embodiments can be implemented in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the processes or functions described in the embodiments of the present application are generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., coaxial cable, optical fiber, digital subscriber line) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that integrates one or more available media. The available medium can be a magnetic medium (e.g., a floppy disk, hard disk, tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid-state drive).

[0148] Those skilled in the art will appreciate that all or part of the process steps in the above-described method embodiments can be implemented by a computer program instructing the relevant hardware. The program can be stored in a computer-readable storage medium, and when executed, the program can include the process steps in the above-described method embodiments. The aforementioned storage medium includes various media capable of storing program code, such as ROM or random access memory (RAM), magnetic disks, or optical disks.

Claims

1. A method for controlling a dynamic halo light, characterized in that: include: Obtaining interaction data of a target application currently running on the tablet, the interaction data including information on state changes in the program interface, user touch operation information, and program resource usage information; Constructing a multidimensional interactive feature space according to the interactive data, and mapping the state change information into trajectory points in the multidimensional interactive feature space, each of the trajectory points including a state identifier, a timestamp, and spatial coordinate information; Calculating the state transition vector between adjacent trajectory points, and determining the state transition threshold according to the direction angle and vector modulus of the state transition vector; Dividing the trajectory points into a plurality of state stable intervals based on the state transition threshold; For each of the state stable intervals, generating an interaction intensity curve by combining the user touch operation information and the program resource occupancy information; An energy distribution function of the state stable interval is calculated based on the interaction intensity curve, and an area where a function value of the energy distribution function exceeds a preset energy threshold is determined as a key interaction segment; Extracting characteristic parameters of the key interaction segments and obtaining energy gradient values ​​of adjacent segments; generating a lighting effect rendering strategy according to the characteristic parameters and the energy gradient value, wherein the lighting effect rendering strategy includes an energy pulse mode, a gradual transition rule, and a breathing cycle parameter; The display state of the smart halo light is adjusted according to the lighting effect rendering strategy, so that the display state of the smart halo light keeps changing synchronously with the fluctuation trend of the energy distribution function.

2. The method according to claim 1, characterized in that The constructing of a multi-dimensional interaction feature space according to the interaction data specifically includes: Constructing a circular buffer queue, and storing the state change information in the circular buffer queue; Inputting the state change information in the circular buffer queue into a long short-term memory network, extracting temporal dependency features, and obtaining a feature vector sequence; Inputting the feature vector sequence into a variational autoencoder for dimensionality reduction compression to obtain a low-dimensional feature representation; Using the low-dimensional feature representation to train a preset probability model to obtain a state transition probability matrix; The feature space is adaptively grid-divided according to the state transition probability matrix to obtain a multi-dimensional interactive feature space.

3. The method according to claim 1, characterized in that The step of generating an interaction intensity curve for each stable state interval by combining the user touch operation information and the program resource occupancy information specifically includes: Segmentally sampling the user touch operation information using a sliding window of a preset length within the state stable interval to obtain touch sequence samples; Extracting touch pressure, velocity, and acceleration features from the touch sequence samples to obtain a touch feature vector; Performing wavelet transform on the program resource occupancy information within the state stable interval to obtain a resource occupancy feature vector; Inputting the touch feature vector and the resource occupancy feature vector into a multi-layer attention neural network to obtain a feature fusion result; The feature fusion result is subjected to Kalman filtering smoothing processing to generate an interaction intensity curve corresponding to the state stability interval.

4. The method according to claim 1, wherein After adjusting the display state of the smart halo light according to the lighting effect rendering strategy, the method further includes: Obtain the gaze coordinate data and gaze duration data collected by the user's eye movement sensor; Collecting the user's current application scenario identifier and operation behavior data on the tablet; Generating a gaze heat distribution map according to the gaze coordinate data and dividing the lighting effect priority areas; Configuring the brightness gradient and display density of the dynamic halo light based on the lighting effect priority area; The brightness gradient and the display density parameter are written into the lighting effect rendering strategy.

5. The method according to claim 4, characterized in that The configuring the brightness gradient and display density of the smart halo light based on the lighting effect priority area specifically includes: Calculate the shortest projection distance from the lighting effect priority area to the tablet frame; Establishing a brightness attenuation function according to the shortest projection distance; generating a brightness gradient value and an activation density coefficient for each segment based on the brightness attenuation function; Converting the brightness gradient value into an adjustment instruction for the LED driving current; The brightness gradient and display density of the smart halo light are configured according to the activation density coefficient.

6. The method according to claim 5, characterized in that After configuring the brightness gradient and display density of the smart halo light according to the activation density coefficient, the method further includes: Monitor the lighting effect display status after configuration; Collecting the user's interactive response data to the current lighting effect configuration; The adaptability of the current lighting effect configuration is evaluated according to the interactive response data.

7. The method according to claim 6, characterized in that The evaluating the adaptability of the current lighting effect configuration according to the interactive response data specifically includes: Counting the operation accuracy and response time of the user under the current lighting effect configuration; Identifying the success rate of the lighting effect configuration in directing the user's attention; Calculating the degree of matching between the lighting effect brightness gradient and the user's sightline migration; The current lighting effect configuration adaptability is generated based on the success rate and the matching degree.

8. A smart halo light control system, characterized in that: The system comprises: One or more processors and a memory; the memory is coupled to the one or more processors, the memory is used to store computer program code, the computer program code includes computer instructions, and the one or more processors call the computer instructions to cause the system to execute the method according to any one of claims 1 to 7.

9. A computer-readable storage medium comprising instructions, characterized in that: When the instructions are executed on a system, the system is caused to perform the method according to any one of claims 1 to 7.

10. A computer program product, characterized in that When the computer program product is run on a system, the system is caused to perform the method according to any one of claims 1 to 7.

Images