Festival Lighting Scenario Mode Automatic Adjustment System Based on Smart Home System

Abstract

The present invention relates to the technical field of smart home, and discloses an automatic adjustment system for festival lighting scene modes based on a smart home system. The system includes a main controller, a lighting scene mode recognition module, a dynamic adjustment execution module, an environmental parameter acquisition module, a user behavior analysis module, etc. The lighting scene mode recognition module generates an initial scene mode according to the festival type and time. The environmental parameter acquisition module collects environmental data in real time. The user behavior analysis module analyzes user data to generate a preference feature vector. The main controller fuses multi-dimensional information to generate a target scene mode instruction, and the dynamic adjustment execution module adjusts the lighting device accordingly. In addition, the system also has functions such as anomaly detection, adaptive correction, scene mode optimization, device compatibility detection, and energy consumption balance. The present invention realizes the intelligent and personalized adjustment of festival lighting scene modes, improves device compatibility and energy consumption management efficiency, and brings a better festival lighting experience to users.

Description

Technical Field

[0001] The present invention relates to the technical field of smart home, and specifically to an automatic adjustment system for festival lighting scene modes based on a smart home system. Background Art

[0002] With the improvement of people's living standards, smart home products have gradually become popular, and people's demand for the intelligence and personalization of the home environment has also been increasing. During festivals, creating a unique and suitable lighting atmosphere has become the pursuit of many families, which has promoted the development of an automatic adjustment system for festival lighting scene modes. However, there are still many deficiencies in the current related technologies in the market.

[0003] On the one hand, the current lighting scene mode adjustment systems have a low level of intelligence in festival scenarios. Many systems only provide preset fixed lighting modes and cannot be dynamically adjusted according to the actual environment and user needs. For example, in different festival atmospheres, the color, brightness, and dynamic effects of the lights should be different to better fit the festival theme. However, traditional systems are difficult to automatically generate appropriate lighting scene modes based on factors such as festival type, time, and environmental light intensity. For example, at Christmas, the outdoor ambient light is relatively dim, and the indoor lights should be brighter and more colorful to create a cheerful atmosphere. However, existing systems may not be able to automatically sense the environmental changes and make corresponding adjustments, resulting in a mismatch between the lighting effect and the festival atmosphere and unable to meet the diverse needs of users for festival lighting.

[0004] On the other hand, the consideration of user personalization needs is not sufficient. Each user has different preferences and usage habits for lights. However, most existing systems lack in-depth analysis of user behavior and preferences. They cannot accurately capture historical operation data of users, such as information on scene mode switching frequency, brightness adjustment amplitude, and color preferences, and are also difficult to generate personalized lighting adjustment schemes by combining users' real-time activity trajectories. For example, some users like to create a warm lighting atmosphere in the living room, while prefer soft light in the bedroom. However, traditional systems cannot make precise lighting adjustments according to these personalized needs, greatly reducing the user experience.

[0005] In addition, the issues of device compatibility and energy consumption management are also relatively prominent. There are differences in functions and parameters among lighting devices of different brands and models. The existing systems have deficiencies in compatibility with various lighting devices, and problems such as parameter mismatches and inability to control properly are likely to occur. This not only limits users' choices of lighting devices but also affects the overall performance of the system. In terms of energy consumption management, many systems lack effective energy consumption balancing strategies and cannot reasonably regulate according to the actual power consumption and the energy consumption requirements of the target scenario mode, resulting in relatively serious energy waste. For example, in some situations where high brightness and complex dynamic effects are not required, the lighting devices still operate with high energy consumption, increasing users' usage costs and not conforming to the development trend of energy conservation and environmental protection. Summary of the Invention

[0006] The purpose of the present invention is to provide an automatic adjustment system for festival lighting scenario modes based on a smart home system to solve the problems raised in the above-mentioned background technology.

[0007] To achieve the above purpose, the present invention provides the following technical solution: An automatic adjustment system for festival lighting scenario modes based on a smart home system includes a main controller, a lighting scenario mode recognition module, a dynamic adjustment execution module, an environmental parameter acquisition module, and a user behavior analysis module;

[0008] The lighting scenario mode recognition module is used to generate an initial scenario mode according to the preset festival type and time information. The initial scenario mode includes lighting color parameters, brightness parameters, and dynamic effect parameters;

[0009] The environmental parameter acquisition module collects indoor light intensity, user location distribution data, and external environmental light data in real time and sends the data to the main controller;

[0010] The user behavior analysis module generates a user preference feature vector by analyzing the user's historical operation data and real-time activity trajectory;

[0011] The main controller receives the initial scenario mode, environmental parameters, and user preference feature vector, and generates a target scenario mode instruction through a multi-dimensional fusion algorithm;

[0012] The dynamic adjustment execution module adjusts the operating parameters of the lighting device according to the target scenario mode instruction and feeds back the adjustment status to the main controller in real time;

[0013] The system also includes an abnormal mode detection module. If the deviation between the adjustment status fed back by the dynamic adjustment execution module and the target scenario mode instruction exceeds the preset threshold, an adjustment abnormal signal is generated, and an adaptive correction algorithm is triggered through the main controller.

[0014] Preferably, the specific implementation method of the lighting scenario mode recognition module is as follows:

[0015] Match the preset festival types according to the calendar data and associate with the standard scenario mode library corresponding to the festivals;

[0016] Divide the scenario mode time periods based on the time information, including the preheating period, the core period, and the ending period;

[0017] In the preheating period, perform weighted fusion on the basic parameters in the standard scenario mode library and the real-time ambient light data to generate the initial brightness gradient value;

[0018] In the core period, dynamically adjust the spatial distribution weights of the light colors according to the user location distribution data;

[0019] In the ending period, reduce the light dynamic effect parameters through a time decay function until the closing threshold is reached.

[0020] Preferably, the specific analysis process of the user behavior analysis module includes:

[0021] Collect the scenario mode switching frequency, brightness adjustment amplitude, and color preference sequence in the user's historical operation data;

[0022] Divide the user behavior into high-activity, medium-activity, and low-activity categories through a clustering algorithm and generate category labels;

[0023] The real-time activity trajectory is obtained through an indoor positioning system, and the coordinate set and residence duration of the user's staying area are extracted;

[0024] Perform spatio-temporal correlation analysis on the category labels and the coordinate set to generate the user preference feature vector, and the vector includes the regional weight value, color correlation degree, and dynamic response coefficient.

[0025] Preferably, the specific steps of the multi-dimensional fusion algorithm are as follows:

[0026] Normalize the initial scenario mode parameters, ambient light intensity, and user preference feature vector into the first matrix, the second matrix, and the third matrix respectively;

[0027] Extract the hidden features of each matrix through a convolutional neural network and calculate the feature similarity weights;

[0028] Perform weighted summation on the hidden features according to the weights to generate a fusion feature matrix;

[0029] Map the fusion feature matrix to the light parameter space and output the target scenario mode instruction, including the color coding value, brightness gradient curve, and dynamic effect frequency.

[0030] Preferably, the implementation method of the adaptive correction algorithm is as follows:

[0031] When adjusting the abnormal signal generation, the main controller starts the correction priority queue and sorts the abnormal parameters according to the degree of deviation;

[0032] For the color coding deviation, the gain coefficients of the RGB channels are adjusted using a color gamut compensation model;

[0033] For the brightness gradient deviation, the brightness curve is reconstructed by piecewise linear interpolation;

[0034] For the dynamic effect frequency deviation, the fundamental frequency component is extracted using Fourier transform and the phase parameters are recalibrated.

[0035] Preferably, the system further includes a scenario mode optimization module, and its specific implementation method is as follows:

[0036] Collect the difference data between the target scenario mode instruction and the actual adjustment state, and generate a difference feature set;

[0037] Construct a difference reward function through a reinforcement learning model to optimize the weight allocation strategy of the multi-dimensional fusion algorithm;

[0038] If the mean value of the difference feature set is lower than the preset threshold after continuous N optimizations, the parameters in the standard scenario mode library are updated.

[0039] Preferably, the design of the difference reward function includes:

[0040] Quantify the color difference, brightness difference, and dynamic effect difference into the first reward sub-item, the second reward sub-item, and the third reward sub-item respectively;

[0041] Apply a dynamic weight to the third reward sub-item according to the dynamic response coefficient in the user preference feature vector;

[0042] Iteratively update the weight allocation strategy through the gradient ascent algorithm until the reward function converges.

[0043] Preferably, the system further includes a device compatibility detection module, and its operation process is as follows:

[0044] Scan the connected lighting devices to obtain the color range, maximum brightness, and response delay parameters supported by the devices;

[0045] Calculate the matching degree between the device parameters and the required parameters of the target scenario mode instruction;

[0046] If the matching degree is lower than the preset threshold, generate a device downgrade instruction and truncate the required parameters according to the device support range;

[0047] If the matching degree is higher than the preset threshold, generate a device optimization instruction to activate the overclocking mode of the device to improve the response speed.

[0048] Preferably, the specific method for calculating the matching degree is as follows:

[0049] Perform an intersection operation on the device color range and the target color coding value to calculate the color gamut coverage ratio;

[0050] Calculate the ratio of the maximum brightness of the device to the peak value of the target brightness gradient curve;

[0051] Calculate the absolute value of the difference between the device response delay parameter and the reciprocal of the dynamic effect frequency;

[0052] Combine the above calculation results into a matching degree score through a weighted summation formula.

[0053] Preferably, the system further includes an energy consumption balancing module, and its implementation method includes:

[0054] Real-time monitor the total power consumption of the lighting device and associate it with the expected energy consumption threshold of the target scenario mode instruction;

[0055] If the total power consumption exceeds a preset ratio of the expected energy consumption threshold, start an energy consumption hierarchical regulation strategy:

[0056] First, reduce the brightness of the lights in the low-priority area, secondly, reduce the frequency of the dynamic effects, and finally, adjust the color saturation;

[0057] If the total power consumption is lower than a preset ratio of the expected energy consumption threshold, activate the redundant energy consumption allocation model and allocate the remaining power to the area with the highest weight in the user preference feature vector.

[0058] Compared with the prior art, the beneficial effects of the present invention are:

[0059] Through the lighting scenario mode recognition module, the present invention generates an initial scenario mode based on the preset festival type and time information, and combines the data collected in real time by the environmental parameter acquisition module, such as indoor light intensity, user location distribution data, and external environmental light data, as well as the user preference feature vector generated by the user behavior analysis module, and uses the multi-dimensional fusion algorithm of the main controller to generate a target scenario mode instruction. This enables the system to automatically adjust the color, brightness, and dynamic effects of the lights according to different festivals, different time periods, and real-time environmental changes. For example, during the Spring Festival, in the evening (preheating period), as the external environmental light gradually darkens, the system automatically increases the brightness of the lights, and combines the user location distribution to enhance the color weight of the red lights in the living room area where the family gathers, creating a festive atmosphere; during the core evening period, according to the characteristics of frequent user activities in the living room, the system further optimizes the dynamic effects of the lights, such as increasing the flashing frequency, making the festival atmosphere more enthusiastic. This intelligent adjustment method greatly improves the fit between the lighting scenario mode and the festival atmosphere, providing users with a better festival lighting experience.

[0060] The user behavior analysis module generates a user preference feature vector containing regional weight values, color correlation degrees, and dynamic response coefficients by collecting and analyzing users' historical operation data and real-time activity trajectories. This enables the system to deeply understand the unique needs and usage habits of each user and achieve personalized lighting adjustment. For example, for users who like to read in the bedroom, the system can automatically adjust the brightness and color temperature of the bedroom lights according to their staying duration and operation habits in the bedroom to make it more suitable for reading; for highly active users who often switch lighting scene modes, the system can, based on their historical switching frequencies and preferences, preferentially recommend scene modes that match their preferences, improving the convenience and satisfaction of user operations. This personalized design fully respects the individual differences of users, allowing each user to enjoy a festival lighting environment that meets their own needs.

[0061] The setting of the device compatibility detection module effectively solves the problem of compatibility between different lighting devices. This module scans the connected lighting devices before the system runs, obtains the color range, maximum brightness, and response delay parameters supported by the devices, and calculates the matching degree with the required parameters of the target scene mode instruction. If the matching degree is lower than the preset threshold, a device downgrading instruction is generated to truncate the required parameters according to the range supported by the device; if the matching degree is higher than the preset threshold, a device optimization instruction is generated to activate the overclocking mode of the device to improve the response speed. This function ensures that the system can be well adapted to various brands and models of lighting devices. Users are more free to choose lighting devices without being restricted by compatibility issues. At the same time, it also improves the control accuracy and stability of the system for different devices, ensuring the consistency of the lighting adjustment effect.

[0062] The energy consumption balancing module realizes the effective management of the energy consumption of lighting devices. By real-time monitoring the total power consumption of lighting devices and associating with the expected energy consumption threshold of the target scene mode instruction, when the total power consumption exceeds the preset proportion of the expected energy consumption threshold, the energy consumption hierarchical regulation strategy is activated. First, the brightness of the lights in the low-priority area is reduced, followed by reducing the frequency of dynamic effects, and finally adjusting the color saturation, thereby effectively reducing energy consumption. When the total power consumption is lower than the preset proportion of the expected energy consumption threshold, the redundant energy consumption allocation model is activated to allocate the remaining power to the area with the highest weight in the user preference feature vector, achieving the rational use of energy. For example, after the festival activities end and there is no one in some areas, the system automatically reduces the brightness of the lights in these areas to reduce unnecessary energy consumption; while in the key areas where users often move, such as the sofa area in the living room, when there is remaining power, the system automatically increases the brightness of the lights in this area to improve the user experience. This energy consumption balancing strategy not only reduces the user's electricity cost but also conforms to the social development trend of energy conservation and environmental protection, with significant economic and environmental benefits.

[0063] The scenario mode optimization module generates a difference feature set by collecting the difference data between the target scenario mode instructions and the actual adjustment status, constructs a difference reward function using a reinforcement learning model, and optimizes the weight allocation strategy of the multi-dimensional fusion algorithm. If the mean value of the difference feature set is lower than the preset threshold after N consecutive optimizations, the parameters in the standard scenario mode library are updated. This enables the system to continuously learn and adapt to the actual usage situation, continuously optimize the lighting adjustment effect. Over time, the system's response to user needs and environmental changes will be more accurate, providing users with a more high-quality and stable automatic adjustment service for festival lighting scenario modes. BRIEF DESCRIPTION OF THE DRAWINGS

[0064] Figure 1 is the working principle diagram of the automatic adjustment system for festival lighting scenario modes of the present invention;

[0065] Figure 2 is the workflow architecture diagram of the lighting scenario mode recognition module;

[0066] Figure 3 is the working logic architecture diagram of the user behavior analysis module. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0067] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0068] Please refer to Figures 1 - 3 , the present invention provides a technical solution: an automatic adjustment system for festival lighting scenario modes based on a smart home system, the system includes:

[0069] A lighting scenario mode recognition module: This module generates an initial scenario mode based on preset festival types and time information. The initial scenario mode covers lighting color parameters, brightness parameters, and dynamic effect parameters. During actual operation, it accurately matches the preset festival type by obtaining calendar data and associates with the standard scenario mode library corresponding to the festival, providing a basis for subsequent operations.

[0070] Environmental parameter acquisition module: This module undertakes the important task of collecting indoor light intensity, user location distribution data, and external environmental light data in real time, and sends this data to the main controller in a timely manner. Among them, the indoor light intensity can be collected by light sensors distributed at different positions in the room. These sensors convert light signals into electrical signals, which are transmitted to the main controller after analog-to-digital conversion; the user location distribution data can be obtained through indoor positioning systems such as Bluetooth positioning, Wi-Fi positioning, or UWB positioning technology; the external environmental light data is collected by environmental light sensors installed at appropriate positions outdoors.

[0071] User behavior analysis module: By deeply analyzing the user's historical operation data and real-time activity trajectories, a user preference feature vector is generated. Specifically, first collect information such as the scenario mode switching frequency, brightness adjustment amplitude, and color preference sequence in the user's historical operation data, and then use clustering algorithms to classify user behaviors into high-activity, medium-activity, and low-activity categories, and generate corresponding category labels. The real-time activity trajectories are obtained through the indoor positioning system, and the coordinate set and stay duration of the user's stay area are extracted from them. Finally, a spatio-temporal correlation analysis is performed on the category labels and the coordinate set to generate a user preference feature vector including regional weight values, color correlation degrees, and dynamic response coefficients.

[0072] Main controller: As the core control unit of the system, the main controller receives the initial scenario mode from the lighting scenario mode recognition module, the environmental parameters from the environmental parameter acquisition module, and the user preference feature vector from the user behavior analysis module. The main controller uses a multi-dimensional fusion algorithm to comprehensively process this information and generate a target scenario mode instruction. This instruction contains key parameters such as the color coding value of the light, the brightness gradient curve, and the dynamic effect frequency, providing an operation basis for the dynamic adjustment execution module.

[0073] Dynamic adjustment execution module: According to the target scenario mode instruction issued by the main controller, this module is responsible for adjusting the operating parameters of the lighting equipment, such as controlling the color, brightness, and dynamic effects of the lights. At the same time, it will feedback the adjustment status to the main controller in real time so that the main controller can timely understand the working conditions of the lighting equipment and achieve closed-loop control.

[0074] Abnormal mode detection module: The system also sets up an abnormal mode detection module to monitor the deviation between the adjustment status feedback by the dynamic adjustment execution module and the target scenario mode instruction. If the deviation exceeds the preset threshold, this module will generate an adjustment abnormal signal and trigger an adaptive correction algorithm through the main controller to handle the abnormal situation and ensure that the operation of the lighting equipment meets the expectations.

[0075] The following further illustrates the present invention in conjunction with Embodiments 1 to 5:

[0076] Embodiment 1:

[0077] This embodiment aims to elaborate in detail the specific working process of the lighting scene mode recognition module, enabling it to generate initial scene modes more accurately to meet the lighting requirements of different festivals and time periods.

[0078] The system identifies the type of festival corresponding to the current date by reading calendar data. For example, if the detected date is December 25th, it is determined as Christmas; if it is the first day of the first lunar month, it is determined as the Spring Festival. Each festival has a corresponding standard scene mode library preset, which is stored in the storage device of the system and contains the parameters of the common lighting scene modes for that festival. Taking Christmas as an example, the standard scene mode library may contain parameters such as red and green as the main colors, with a flashing dynamic effect; the standard scene mode library for the Spring Festival may have red as the main color, higher brightness, and a festive and lively dynamic effect.

[0079] Based on the time information, the lighting scene modes during the festival are divided into a preheating period, a core period, and an ending period. For example, for Christmas, the preheating period can be set from 18:00 to 24:00 on December 24th, the core period from 00:00 to 12:00 on December 25th, and the ending period from 12:00 to 24:00 on December 25th. The lighting scene modes in different periods will vary to create different atmospheres.

[0080] Operation during the preheating period: During the preheating period, in order to make the lighting effect better adapt to the ambient light change, the basic parameters in the standard scene mode library are weighted and fused with the real-time ambient light data to generate an initial brightness gradient value. Let the basic brightness parameter in the standard scene mode library be and the real-time ambient light intensity be , and the weighting coefficients be and ( ), then the calculation formula for the initial brightness gradient value is: . For example, if the basic brightness in the Christmas standard scene mode library is 50 (assuming the brightness value range is 0 - 100), the current ambient light intensity is 30, the weighting coefficient , , then the initial brightness gradient value .

[0081] During the core period, the spatial distribution weight of the light color is dynamically adjusted according to the user location distribution data. Suppose the system obtains through the indoor positioning system that the users are mainly concentrated in the living room area. At this time, the color weights of red and green (taking Christmas as an example) in the living room area lights can be increased to make the lights in this area more festive. When specifically implemented, the color weight adjustment coefficient of each area can be calculated according to the density of the user location distribution. Let the user density of a certain area be , the initial color weight of this area is , the adjusted color weight is , and the adjustment coefficient is ( is related to , the larger, the larger), then .

[0082] During the end period, in order to gradually turn off the lights and avoid a sudden feeling, the dynamic effect parameters of the lights are reduced through a time decay function until the turn-off threshold is reached. Let the initial value of the light dynamic effect parameter be , the time decay function is , where is the difference between the current time and the start time of the end period. After time , the calculation formula for the dynamic effect parameter is: . For example, if the initial value of the dynamic effect parameter is 80 (assuming the value range is 0 - 100), and the time decay function is ( in hours), 1 hour after the start of the end period, the dynamic effect parameter . As time goes by, the dynamic effect parameter gradually decreases. When is less than the turn-off threshold (such as 10), the dynamic effect of the lights is turned off.

[0083] Example 2:

[0084] The system continuously records the operation behaviors of users on the light scene modes, including the scene mode switching frequency, the brightness adjustment amplitude, and the color preference sequence. For example, within the past week, the user switched the light scene mode from the "daily mode" to the "romantic mode" 5 times, which is the scene mode switching frequency information; each time the user adjusted the brightness, the adjustment amplitude was recorded, such as adjusting from brightness 50 to 60, and the adjustment amplitude was 10; at the same time, the different light colors selected by the user were recorded to form a color preference sequence. For example, if the user selected warm yellow lights many times, then the weight of warm yellow in the color preference sequence is relatively high.

[0085] Use clustering algorithms to analyze the collected historical user operation data, classify user behaviors into high-activity, medium-activity, and low-activity categories, and generate category labels. Common clustering algorithms such as the K-Means algorithm, assuming (i.e., divided into 3 categories), the algorithm will automatically divide users into different categories according to the characteristics of user behavior data. For example, if a user frequently switches the scenario mode, significantly adjusts the brightness, and has diverse color selections, their behavior may be classified into the high-activity category; while users with fewer operations and little change may be classified into the low-activity category.

[0086] Obtain the real-time activity trajectory of the user through the indoor positioning system, and extract the coordinate set and residence duration of the area where the user stays. For example, the coordinate range of the user in the living room is - , and the residence duration is 30 minutes. Conduct spatio-temporal correlation analysis on this information and the category labels obtained from user behavior clustering. Let the user category label be , the coordinate set of the staying area be , the residence duration be , and the calculation of the regional weight value can consider the relationship between the residence duration and category activity, such as , where is the activity coefficient corresponding to category (the value is larger for the high-activity category, and the value is smaller for the low-activity category), and are the residence durations and corresponding activity coefficients of other areas respectively. The color correlation degree can be determined according to the color preference selected by the user when staying in this area. For example, if the user repeatedly selects blue lights in a certain area, the color correlation degree of this area with blue is higher. The dynamic response coefficient can be calculated according to the operation frequency and amplitude of the user in different areas. The higher the operation frequency and the larger the amplitude, the larger the dynamic response coefficient. Through these calculations, generate a user preference feature vector including the regional weight value, color correlation degree, and dynamic response coefficient.

[0087] Example 3:

[0088] This example details how the multi-dimensional fusion algorithm fuses the initial scenario mode parameters, environmental light intensity, and user preference feature vector to generate a more reasonable target scenario mode instruction.

[0089] Normalize the initial scenario mode parameters, environmental light intensity, and user preference feature vector into the first matrix, the second matrix, and the third matrix respectively. Assume that the initial scenario mode parameters include the light color parameters (the RGB values may range from ), the brightness parameter (such as ), dynamic effect parameters (such as 's blinking frequency), combine them into a vector , through the normalization formula (where is the original value, and are the minimum and maximum values of this parameter), normalize it to the interval to obtain the first matrix. For the environmental light intensity (assuming the value range is ), also perform normalization processing to obtain the second matrix. The user preference feature vector includes the regional weight value , color correlation , dynamic response coefficient , and also perform normalization processing to obtain the third matrix.

[0090] Use a convolutional neural network (CNN) to extract implicit features from each matrix. The CNN contains multiple convolutional layers, pooling layers, and fully connected layers. By sliding the convolutional kernel on the matrix for convolution, features at different levels are extracted. For example, after passing through the convolutional layer, the first matrix extracts features related to the lighting scene mode, such as color matching features, brightness change trend features, etc.; the second matrix extracts environmental light intensity change features; the third matrix extracts user preference-related features. Then calculate the similarity weights between the features of each matrix. Let the features of the first matrix be , the features of the second matrix be , the features of the third matrix be , and the feature similarity weights , , can be calculated by methods such as calculating the cosine similarity between feature vectors, such as (here taking the calculation of the similarity weight between and as an example), and perform normalization processing to make .

[0091] According to the calculated weights, perform weighted summation on the implicit features to generate a fused feature matrix. Let the fused feature matrix be , then . This fused feature matrix combines the information of the initial scene mode, environmental light, and user preferences.

[0092] Map the fused feature matrix to the lighting parameter space and output the target scenario mode instruction. Through a fully connected layer or other means, convert the fused feature matrix into the color coding value, brightness gradient curve, and dynamic effect frequency of the lighting. For example, after passing through the linear transformation and activation function of the fully connected layer, the fused feature matrix obtains a color coding value of (red), a brightness gradient curve that gradually rises from 50 to 80 within the next 1 hour, and a dynamic effect frequency of flashing once every 5 seconds and other target scenario mode instructions.

[0093] Example 4:

[0094] This example details how the adaptive correction algorithm corrects the lighting parameters when the system detects an adjustment anomaly to ensure the normal operation of the lighting device.

[0095] When the deviation between the adjustment state feedback by the dynamic adjustment execution module and the target scenario mode instruction exceeds the preset threshold, the anomaly mode detection module generates an adjustment anomaly signal, and the main controller starts the correction priority queue. For example, if the preset color deviation threshold is 10 (assuming calculated based on RGB value deviation), the brightness deviation threshold is 5, and the dynamic effect frequency deviation threshold is 2. When the detected color coding deviation is 15, the brightness gradient deviation is 8, and the dynamic effect frequency deviation is 3, sort the abnormal parameters according to the degree of deviation, first process the brightness gradient deviation, then process the color coding deviation, and finally process the dynamic effect frequency deviation.

[0096] For the color coding deviation, use the color gamut compensation model to adjust the gain coefficients of the RGB channels. Let the original RGB channel values be , the deviation be , the adjusted RGB channel values be , and the gain coefficients be , , , then , , . The calculation of the gain coefficient can be adjusted according to the deviation magnitude and color gamut range, such as ( is the absolute value of the deviation) to ensure that the adjusted color is within a reasonable color gamut range.

[0097] For the brightness gradient deviation, reconstruct the brightness curve through piecewise linear interpolation. Assume the target brightness gradient curve is , and the actually measured brightness curve is . In the time period with a large deviation, select multiple interpolation nodes and . According to the piecewise linear interpolation formula (when ), reconstruct the brightness curve to make the actual brightness curve closer to the target brightness curve.

[0098] For the dynamic effect frequency deviation, the base frequency component is extracted by Fourier transform and the phase parameters are recalibrated. Assume that the actual dynamic effect frequency signal is , through Fourier transform Get its spectrum and extract the fundamental frequency component Calculate the actual phase Phase with target Deviation , by adjusting the phase parameters, such as , recalibrate the phase of the dynamic effect frequency to restore the dynamic effect to normal.

[0099] Embodiment 5:

[0100] This embodiment focuses on the specific implementation of the scenario mode optimization module, the device compatibility detection module and the energy consumption balancing module, and is committed to further improving system functions and enhancing system performance and user experience.

[0101] ①Scenario mode optimization module

[0102] Difference data collection and feature set generation: The system continuously monitors and collects the difference data between the target scene mode command and the actual adjustment state. Taking color as an example, assuming that the target color encoding value is RGB (255, 0, 0), and the color value obtained after the actual adjustment is RGB (245, 5, 5), by calculating the difference between the two in each RGB channel, such as the red channel difference is 255 - 245 = 10, the green channel difference is 0 - 5 = -5, and the blue channel difference is 0 - 5 = -5, these differences are integrated into color difference data. For brightness, if the target brightness gradient curve is set to 60 at a certain moment (assuming the brightness value range is 0 - 100), and the actual measured brightness value is 55, then the brightness difference is 60 - 55 = 5. For dynamic effects, if the target dynamic effect frequency is flashing once every 4 seconds, and the actual measurement is flashing once every 5 seconds, then the dynamic effect difference is reflected as the frequency deviation. The difference data of these colors, brightness and dynamic effects are summarized to generate a difference feature set as the basis for subsequent optimization.

[0103] Difference reward function construction and weight optimization: Use the reinforcement learning model to construct a difference reward function. Quantify the color difference, brightness difference and dynamic effect difference as the first reward sub-item , Second reward item And the third reward sub-item For color differences, the Euclidean distance formula in color space is used for quantification, namely:

[0104]

[0105] The larger the distance value calculated by this formula, the greater the color difference, and the reward value is smaller, to guide the system to reduce the color difference. The brightness difference is quantified as , directly taking the absolute value of the difference between the target brightness and the actual brightness. The larger the difference, the smaller the reward value, prompting the actual brightness to approach the target brightness. For the dynamic effect difference, let the target frequency be , and the actual frequency be , and the quantization formula is . According to the dynamic response coefficient in the user preference feature vector, a dynamic weight is applied to the third reward sub-item, that is, the final dynamic effect reward sub-item is . Through the gradient ascent algorithm, the weight allocation strategy of the multi-dimensional fusion algorithm is iteratively updated. In each iteration, the weights are adjusted according to the feedback of the reward function, continuously trying different weight combinations until the reward function converges. At this time, the obtained weight allocation strategy can enable the system to better meet the actual needs and reduce the differences when generating the target scenario mode instruction.

[0106] Standard scenario mode library update: The system sets a threshold for the continuous optimization times , and after each optimization, calculates the mean value of the difference feature set. If after consecutive optimizations, the mean value of the difference feature set is lower than the preset threshold, this indicates that the current optimization strategy is effective, and the difference between the actual adjustment effect of the system and the target scenario mode instruction is within an acceptable range. At this time, the optimized parameters are updated to the standard scenario mode library, enabling the standard scenario mode library to keep pace with the times, adapt to the usage habits of different users and environmental changes, and provide more accurate basic data for the subsequent festival lighting scenario mode adjustment.

[0107] ② Device compatibility detection module

[0108] Device parameter acquisition: When the system starts the device compatibility detection process, it first scans the connected lighting devices. Through the interaction with the communication protocol of the lighting devices, it obtains the color range supported by the devices. For example, the RGB color value range supported by some devices may be (0 - 200, 0 - 200, 0 - 200); obtains the maximum brightness of the devices. Suppose the maximum brightness of a certain device is 800 lumens; and obtains the response delay parameter of the devices. For example, the response delay of a certain device is 0.1 seconds. These parameters are the key basis for evaluating the compatibility between the devices and the target scenario mode instruction.

[0109] Match degree calculation: Calculate the match degree between the device parameters and the required parameters of the target scenario mode instruction. For the device color range and the target color coding value, use the intersection operation to calculate the gamut coverage ratio. Suppose the representation of the device color range in the RGB space is , and the target color coding value is , then the calculation method of the gamut coverage ratio is as follows: Calculate the ratio of the intersection length to the device channel range length on each channel, and then take the average value. For the maximum brightness of the device and the peak value of the target brightness gradient curve, calculate the ratio of the two. Suppose the maximum brightness of the device is , and the peak value of the target brightness gradient curve is , then the brightness ratio . For the device response delay parameter and the reciprocal of the dynamic effect frequency, calculate the absolute value of the difference. Suppose the device response delay is , and the dynamic effect frequency is , then the delay difference . Finally, combine the above calculation results into a match degree score through the weighted summation formula, that is , where , , are weight coefficients, and , adjust the weights according to actual needs to highlight the importance of different parameters.

[0110] Instruction generation: Generate corresponding instructions according to the comparison result between the match degree score and the preset threshold. If the match degree is lower than the preset threshold, it means that the device cannot fully meet the requirements of the target scenario mode instruction. At this time, generate a device downgrade instruction. This instruction truncates the required parameters according to the device support range. For example, if the target color coding value exceeds the device color range, adjust the color value to the maximum or minimum value supported by the device; if the target brightness exceeds the maximum brightness of the device, set the brightness to the maximum brightness of the device. If the match degree is higher than the preset threshold, it indicates that the device has the ability to better execute the target scenario mode instruction. At this time, generate a device optimization instruction to activate the overclocking mode of the device (if the device supports) to improve the response speed and further optimize the lighting effect.

[0111] ③ Energy consumption balancing module

[0112] Power consumption monitoring and threshold association: The energy consumption balancing module monitors the total power consumption of the lighting device in real time. By communicating with the power monitoring circuit of the lighting device or the relevant smart meter, obtain the real-time power consumption data of all current lighting devices and accumulate them to obtain the total power consumption . At the same time, associate the expected energy consumption threshold , this threshold is preset according to factors such as different festival scene modes, the number of lighting devices, and the expected usage duration. For example, for a festival lighting scene mode of a small gathering with an expected usage duration of 3 hours, according to the power specifications of the lighting devices, the expected energy consumption threshold is set to 1 degree of electricity (i.e., 1000 watt-hours).

[0113] Energy consumption hierarchical control strategy: When the total power consumption exceeds the preset ratio of the expected energy consumption threshold (such as 110%, that is ), the energy consumption hierarchical control strategy is activated. First, the lighting brightness of the low-priority areas is preferentially reduced. The system pre-divides the area priorities according to the area weight values in the user preference feature vector, and the areas with lower weight values are low-priority areas. Suppose the current brightness of a certain low-priority area is , and it is reduced by a certain ratio (such as 10%), and the new brightness value . If the total power consumption still does not meet the standard after reducing the brightness of the low-priority areas, then the frequency of the dynamic effects is reduced secondly. For example, the original dynamic effect frequency is to flash once every 3 seconds, and it is adjusted to flash once every 5 seconds. If the total power consumption still exceeds the threshold, then finally the color saturation is adjusted. By adjusting the color saturation algorithm, the color saturation is reduced to reduce the power consumption of the lighting devices.

[0114] Redundant energy consumption allocation model: When the total power consumption is lower than the preset ratio of the expected energy consumption threshold (such as 90%, that is ), the redundant energy consumption allocation model is activated. According to the area weight values in the user preference feature vector, the area with the highest weight is found, and the remaining power consumption is allocated to this area. Suppose the remaining power consumption is , and the current brightness of this area is , and the increased brightness value is calculated according to the relationship between power consumption and brightness (such as a linear relationship), ( is the proportional coefficient of power consumption and brightness change, which can be determined through device parameters and experiments), so as to increase the lighting brightness of this area and meet the lighting needs of users for key areas.

[0115] It should be noted that in this text, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprising", "including" or any other variant thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device comprising a series of elements not only includes those elements, but also includes other elements not expressly listed, or elements inherent to such process, method, article or device.

[0116] Although embodiments of the present invention have been shown and described, those of ordinary skill in the art can understand that various changes, modifications, substitutions and variations can be made to these embodiments without departing from the principles and spirit of the present invention. The scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A holiday lighting scene mode automatic adjustment system based on a smart home system, characterized in that: It includes a main controller, a lighting scenario pattern recognition module, a dynamic adjustment execution module, an environmental parameter acquisition module and a user behavior analysis module; The lighting scene mode recognition module is used to generate an initial scene mode according to the preset festival type and time information, and the initial scene mode includes lighting color parameters, brightness parameters and dynamic effect parameters; The environmental parameter acquisition module collects indoor light intensity, user location distribution data and external ambient light data in real time, and sends the data to the main controller; The user behavior analysis module generates a user preference feature vector by analyzing the user's historical operation data and real-time activity trajectory; The main controller receives the initial scene mode, environmental parameters and user preference feature vector, and generates a target scene mode instruction through a multi-dimensional fusion algorithm; The dynamic adjustment execution module adjusts the operating parameters of the lighting equipment according to the target scene mode instruction, and feeds back the adjustment status to the main controller in real time; The system further comprises an abnormal mode detection module, which generates an abnormal adjustment signal and triggers an adaptive correction algorithm through a main controller if the deviation between the adjustment state fed back by the dynamic adjustment execution module and the target scenario mode instruction exceeds a preset threshold; The specific implementation of the lighting scene mode recognition module is as follows: Matching preset holiday types according to calendar data and associating with the standard scene mode library corresponding to the holiday; Divide the scenario mode time periods based on time information, including warm-up period, core period and end period; During the warm-up period, the basic parameters in the standard scene mode library are weighted and fused with the real-time ambient light data to generate the initial brightness gradient value; During the core period, the spatial distribution weight of the lighting color is dynamically adjusted according to the user location distribution data; At the end of the period, the light dynamics parameters are reduced through a time decay function until the shutdown threshold is reached.

2. The holiday lighting scene mode automatic adjustment system based on the smart home system according to claim 1 is characterized in that: The specific analysis process of the user behavior analysis module includes: Collect scene mode switching frequency, brightness adjustment range and color preference sequence from the user's historical operation data; Use clustering algorithms to classify user behaviors into high-activity, medium-activity, and low-activity categories, and generate category labels; The real-time activity trajectory is obtained through the indoor positioning system, and the coordinate set of the user's stay area and the length of stay are extracted; The category labels and the coordinate sets are subjected to a spatiotemporal correlation analysis to generate a user preference feature vector, which includes a region weight value, a color correlation degree, and a dynamic response coefficient.

3. The holiday lighting scene mode automatic adjustment system based on the smart home system according to claim 1 is characterized in that: The specific steps of the multi-dimensional fusion algorithm are: Normalizing the initial scene mode parameters, the ambient light intensity and the user preference feature vector into a first matrix, a second matrix and a third matrix respectively; The implicit features of each matrix are extracted through convolutional neural network, and the feature similarity weights are calculated; Perform weighted summation of implicit features according to weights to generate a fusion feature matrix; The fused feature matrix is ​​mapped to the lighting parameter space, and the target scene mode instructions are output, including color coding values, brightness gradient curves, and dynamic effect frequencies.

4. The holiday lighting scene mode automatic adjustment system based on the smart home system according to claim 3 is characterized in that: The implementation of the adaptive correction algorithm is as follows: When an abnormal regulation signal is generated, the main controller starts the correction priority queue and sorts the abnormal parameters according to the degree of deviation; For color coding deviation, the color gamut compensation model is used to adjust the gain coefficient of RGB channels; For brightness gradient deviation, the brightness curve is reconstructed by piecewise linear interpolation; For the dynamic effect frequency deviation, the fundamental frequency component is extracted by Fourier transform and the phase parameters are recalibrated.

5. The holiday lighting scene mode automatic adjustment system based on the smart home system according to claim 1 is characterized in that: The system also includes a scenario mode optimization module, which is specifically implemented as follows: Collect the difference data between the target scenario mode instruction and the actual adjustment state to generate a difference feature set; Construct a differential reward function through a reinforcement learning model and optimize the weight allocation strategy of the multi-dimensional fusion algorithm; If the mean of the difference feature set after N consecutive optimizations is lower than the preset threshold, the parameters in the standard scenario model library are updated; The design of the difference reward function includes: Quantify the color difference, brightness difference and dynamic effect difference into the first reward sub-item, the second reward sub-item and the third reward sub-item respectively; Applying dynamic weights to the third reward sub-item according to the dynamic response coefficient in the user preference feature vector; The weight distribution strategy is iteratively updated through the gradient ascent algorithm until the reward function converges.

6. The holiday lighting scene mode automatic adjustment system based on the smart home system according to claim 1, characterized in that: The system also includes a device compatibility detection module, and its operation process is as follows: Scan the connected lighting devices to obtain the color range, maximum brightness and response delay parameters supported by the devices; Calculate the matching degree between the device parameters and the required parameters of the target scenario mode instructions; If the matching degree is lower than the preset threshold, a device downgrade instruction is generated to truncate the required parameters according to the device support range; If the matching degree is higher than the preset threshold, a device optimization instruction is generated to activate the device's overclocking mode to improve the response speed; The specific method for calculating the matching degree is: Perform intersection operation on the device color range and the target color encoding value to calculate the color gamut coverage ratio; Calculate the ratio of the maximum brightness of the device to the peak value of the target brightness gradient curve; Calculate the absolute value of the difference between the device response delay parameter and the inverse of the dynamic effect frequency; The above calculation results are combined into a matching score through a weighted summation formula.

7. The holiday lighting scene mode automatic adjustment system based on the smart home system according to claim 1 is characterized in that: The system also includes an energy consumption balancing module, which is implemented in the following ways: Monitor the total power consumption of lighting equipment in real time and associate it with the expected energy consumption threshold of the target scenario mode command; If the total power consumption exceeds the preset ratio of the expected energy consumption threshold, the energy consumption hierarchical control strategy is activated: First, reduce the light brightness in low-priority areas, then reduce the frequency of dynamic effects, and finally adjust color saturation; If the total power consumption is lower than the preset ratio of the expected energy consumption threshold, the redundant energy consumption allocation model is activated to allocate the remaining power consumption to the area with the highest weight in the user preference feature vector.

Images