Light emitting diode intelligent dimming system based on multispectral control

Abstract

The invention relates to the technical field of intelligent lighting, and discloses a light emitting diode intelligent dimming system based on multispectral control, which comprises a multi-sensor data acquisition module, a data fusion processing unit, a user behavior prediction module, a dynamic spectrum adjustment module and the like. Environmental data are collected in real time through multiple sensors, user behaviors are predicted in combination with a machine learning algorithm, and personalized adjustment and dynamic response of illumination are achieved. The system can accurately adjust the color temperature, brightness and spectral distribution of the light source according to the changes of ambient light, temperature and humidity, human body activities and the like, and provides a more efficient and energy-saving illumination scheme. Meanwhile, through cooperative work of the Internet of Things technology and intelligent equipment, the comfort level of the whole environment is optimized. Particularly, the intelligent feedback and learning module of the system continuously optimizes the control strategy according to the use feedback of the user, the user experience and the adaptability of the system are further improved, and a comfortable and intelligent lighting environment is provided for the user.

Description

Technical Field

[0001] The invention relates to a light emitting diode intelligent dimming system based on multi-spectrum control and the system, belonging to the technical field of intelligent lighting. Background Art

[0002] Existing intelligent lighting systems are widely used in places such as homes, offices and commercial spaces. They aim to improve comfort, energy saving and ease of use by automatically adjusting parameters such as light intensity and color temperature. Traditional intelligent lighting systems usually rely on ambient light sensors or timers to adjust light. These systems adjust the light source according to preset conditions or simple light sensor feedback. However, these methods fail to fully consider the complex changes in the indoor environment and the personalized needs of users. For example, most lighting adjustment systems rely on a single ambient light sensor to sense the ambient light intensity, while ignoring multiple environmental factors such as temperature and humidity changes, human activity status and air quality. Although some systems further adjust the lighting effect by adding temperature and humidity sensors, the adjustment of these systems is still fixed or relatively simple, and it is difficult to dynamically adjust according to specific user behavior and real-time environmental changes, resulting in the lighting effect in some special environments (such as high temperature, high humidity or low light environment) cannot meet the user's comfort needs.

[0003] In order to solve this problem, the industry has tried to introduce data collection and analysis methods based on multiple sensors, such as combining human body sensors with temperature and humidity sensors for linkage adjustment. Although this method can improve the shortcomings of traditional systems to a certain extent, due to the relatively simple data fusion and control algorithms between different sensors, it is often difficult to effectively achieve the comprehensive adjustment of multiple factors such as light, temperature, humidity, and air quality, making it difficult to provide more accurate and personalized lighting solutions. In addition, existing technologies often ignore the prediction and feedback mechanism of user behavior. Users' lighting needs are dynamically changing, and systems that rely on traditional sensors find it difficult to intelligently predict users' specific needs based on historical usage data or real-time environmental changes, resulting in insufficient system response speed and accuracy, which further affects the comfort and personalization of the lighting experience.

[0004] Therefore, the existing technology still has the following shortcomings, such as a single sensor and a fixed adjustment mechanism are difficult to cope with the complex and dynamically changing indoor environment, lack of prediction of user behavior and adjustment of personalized lighting needs, resulting in unstable system adjustment effect, and the data fusion and control algorithm between multiple sensors is simple and cannot achieve precise dynamic adjustment. Summary of the invention

[0005] The present invention provides a light emitting diode intelligent dimming system based on multi-spectrum control, the main purpose of which is to solve the above-mentioned problems.

[0006] To achieve the above-mentioned purpose, the present invention provides a light emitting diode intelligent dimming system based on multi-spectral control, comprising: a multi-sensor data acquisition module, which is used to obtain data including ambient light intensity, temperature and humidity, human activity and air quality through multiple sensors; A data fusion processing unit is used to receive data from the multiple sensors, and to perform comprehensive processing on the data through a fusion algorithm to generate an environmental state evaluation signal, wherein the environmental state evaluation signal is used to reflect the comprehensive influence of light intensity, temperature, and humidity factors in the environment, and to determine corresponding light adjustment parameters according to the environmental state evaluation signal; A user behavior prediction module is used to predict the user's lighting needs under specific environmental conditions through a machine learning algorithm based on historical user behavior data and real-time sensor data, and generate a predicted lighting adjustment plan, wherein the predicted lighting adjustment plan includes the color temperature, brightness and adjustment method of the light source; A dynamic spectrum adjustment module, used to dynamically adjust the spectrum output of the light-emitting diode according to the environmental state evaluation signal and the predicted illumination adjustment scheme, including adjusting the color temperature, brightness, and spectrum distribution of the diode, and adjusting the output of cold light and warm light according to environmental conditions; The temperature, humidity and light source linkage adjustment module is used to dynamically adjust the output of the light source according to the temperature and humidity changes in the environment. The light source is automatically adjusted to cold light or warm light that adapts to the current environment according to the parameter data of temperature and humidity to ensure that the user obtains a comfortable lighting effect under specific temperature and humidity conditions; A multi-device collaborative control unit communicates and collaborates with smart devices in the building through the Internet of Things technology, adjusts the working state of the smart devices based on data fed back by sensors, and coordinates with the lighting adjustment function to provide comprehensive comfort optimization in the overall environment; Intelligent feedback and learning module, which is used to automatically adjust the control strategy according to the feedback data of users during actual use, and continuously optimize the lighting and environmental control strategy through machine learning algorithms to adapt to different users and environmental conditions; The control interface is used to receive the target lighting conditions set by the user and adjust the lighting through a graphical interface or voice commands. The control interface interacts with each module and adjusts the light source output according to the user input, and feeds back the adjustment results to the user end.

[0007] Preferably, adjusting the output of cold light and warm light according to environmental conditions specifically means that when the ambient temperature is low, the output of warm light including yellow or orange light is preferentially adjusted to provide a warm feeling; when the ambient temperature is high, the output of cold light including white or blue light is preferentially adjusted to provide a cool feeling.

[0008] Preferably, the smart device includes an air conditioner, a humidifier and an air purifier, and the multi-device collaborative control unit adjusts the working state of the smart device to coordinate with the light adjustment function according to the data collected by the multi-sensor data acquisition module.

[0009] Preferably, the user's feedback data during actual use includes user comfort evaluation data and user demand change data.

[0010] Preferably, the multi-sensor data acquisition module performs data acquisition through an ambient light intensity sensor, a temperature and humidity sensor, a human body sensor and an air quality sensor, wherein the temperature and humidity sensor is used to monitor changes in temperature and humidity in the environment, the human body sensor is used to detect the activity status of human beings indoors, and the air quality sensor is used to detect the air quality in the environment.

[0011] Preferably, the data fusion processing unit fuses the data from each sensor through a weighted average algorithm to generate the environmental status assessment signal, and the weight coefficient of the weighted average algorithm is dynamically adjusted according to historical data and real-time sensor data.

[0012] Preferably, the user behavior prediction module uses historical user lighting demand data and real-time sensor data to predict the user's lighting demand under different environmental conditions based on a regression model and generates a corresponding lighting adjustment plan, wherein the regression model includes a linear regression or a support vector regression model.

[0013] Preferably, the dynamic spectrum adjustment module includes a color temperature adjustment unit, a brightness adjustment unit and a spectrum distribution adjustment unit. The color temperature adjustment unit changes the color temperature by adjusting the driving current of the light-emitting diode, and the brightness adjustment unit adjusts the brightness of the light source by adjusting the driving current or pulse width modulation PWM control signal.

[0014] Preferably, the intelligent feedback and learning module automatically adjusts the lighting and environmental control strategies by using a machine learning algorithm by continuously receiving comfort evaluation data and demand change data from users, wherein the machine learning algorithm includes a decision tree algorithm or a deep learning algorithm.

[0015] Preferably, the control interface receives the target lighting condition set by the user through a graphical user interface GUI, and supports the user to adjust the light source output through voice control through a voice command module, wherein the voice command module includes a voice recognition unit and a natural language processing unit.

[0016] Compared with the problems described in the background technology, the beneficial effects of the present invention are: by integrating multiple sensors (ambient light, temperature and humidity, human activity, air quality) and applying data fusion algorithms, the environmental state is evaluated in real time and accurate lighting adjustment parameters are generated. This intelligent environmental perception mechanism enables the system to flexibly adjust the lighting scheme under changing environmental conditions, and can more accurately adapt to the needs of different times and conditions compared with the traditional static adjustment method. Especially in complex indoor environments, it can provide more accurate and efficient lighting adjustment than single sensor control through dynamic response to environmental changes; through the user behavior prediction module, combined with historical lighting data and real-time sensor input, it can accurately predict the user's lighting needs under different environmental conditions. This behavior prediction based on machine learning algorithms not only improves the personalization and intelligence level of lighting, but also effectively avoids the decrease in comfort caused by the inflexible fixed settings of traditional systems. Every time a user enters the space, the system can dynamically optimize the color temperature, brightness and other parameters of the light source according to the historical behavior pattern and current environmental conditions to achieve a personalized lighting experience; and through the Internet of Things technology, the lighting system is linked with air conditioners, humidifiers, air purifiers and other equipment to coordinate and adjust in real time according to sensor feedback. The collaborative work between different smart devices not only improves environmental comfort, but also saves energy through multi-dimensional control and maintains the optimal balance between indoor temperature, humidity and light. This collaborative control goes beyond a single lighting system and can achieve more comprehensive environmental optimization; in specific use, as user feedback accumulates, the system can continuously learn and adjust to optimize lighting and environmental control strategies to ensure the best effect under changing user needs and environmental conditions. This intelligent feedback mechanism not only improves the adaptability of the system, but also continuously optimizes itself during user use to meet individual needs and changes in complex environments. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 This is a system architecture diagram of the present invention.

[0018] Figure 2 Schematic diagram of collaborative control between the system of the present invention and intelligent devices.

[0019] The purpose, features and advantages of the present invention will be further described with reference to the accompanying drawings in conjunction with the embodiments. DETAILED DESCRIPTION

[0020] It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention.

[0021] See also Figure 1 — Figure 2, the embodiment of the present application provides an intelligent dimming system for light-emitting diodes based on multi-spectral control. It includes: a multi-sensor data acquisition module, which is used to obtain data including ambient light intensity, temperature and humidity, human activity and air quality through multiple sensors; a data fusion processing unit, which is used to receive data from the multiple sensors and perform comprehensive processing on the data through a fusion algorithm to generate an environmental state evaluation signal, the environmental state evaluation signal is used to reflect the comprehensive influence of light intensity, temperature and humidity factors in the environment, and determine the corresponding light adjustment parameters according to the environmental state evaluation signal; a user behavior prediction module, which is used to predict the user's light requirements under specific environmental conditions through a machine learning algorithm based on historical user behavior data and real-time sensor data, and generate a predicted light adjustment scheme, the predicted light adjustment scheme includes the color temperature, brightness and adjustment method of the light source; a dynamic spectrum adjustment module, which is used to dynamically adjust the spectral output of the light-emitting diode according to the environmental state evaluation signal and the predicted light adjustment scheme, including adjusting the color temperature, brightness, and spectral distribution of the diode, and adjusting the cold light and The output of warm light; a temperature, humidity and light source linkage adjustment module, which is used to dynamically adjust the output of the light source according to the changes in temperature and humidity in the environment. The light source is automatically adjusted to cold light or warm light that adapts to the current environment according to the parameter data of temperature and humidity to ensure that users obtain comfortable lighting effects under specific temperature and humidity conditions; a multi-device collaborative control unit, which communicates and collaborates with smart devices in the building through the Internet of Things technology, adjusts the working status of smart devices according to the data fed back by the sensors, and coordinates with the lighting adjustment function to provide comprehensive comfort optimization in the overall environment; an intelligent feedback and learning module, which is used to automatically adjust the control strategy according to the feedback data of the user during actual use, and continuously optimize the lighting and environmental control strategy through machine learning algorithms to adapt to different users and environmental conditions; a control interface, which is used to receive the target lighting conditions set by the user, and adjust the lighting through a graphical interface or voice commands. The control interface interacts with each module for data, adjusts the light source output according to the user input, and feeds back the adjustment results to the user end.

[0022] Preferably, the output of cold light and warm light adjusted according to environmental conditions specifically refers to that when the ambient temperature is low, the output of warm light including yellow or orange light is preferentially adjusted to provide a warm feeling; when the ambient temperature is high, the output of cold light including white or blue light is preferentially adjusted to provide a cool feeling. Preferably, the smart device includes an air conditioner, a humidifier and an air purifier, and the multi-device collaborative control unit adjusts the working state of the smart device to coordinate with the light adjustment function according to the data collected by the multi-sensor data acquisition module. Preferably, the feedback data from the user during actual use refers to user comfort evaluation data and user demand change data.

[0023] Preferably, the multi-sensor data acquisition module performs data acquisition through an ambient light intensity sensor, a temperature and humidity sensor, a human body sensor and an air quality sensor, wherein the temperature and humidity sensor is used to monitor changes in temperature and humidity in the environment, the human body sensor is used to detect the activity status of human beings indoors, and the air quality sensor is used to detect the air quality in the environment.

[0024] Preferably, the data fusion processing unit fuses the data from each sensor through a weighted average algorithm to generate the environmental status assessment signal, and the weight coefficient of the weighted average algorithm is dynamically adjusted according to the historical data and the real-time sensor data. Preferably, the user behavior prediction module uses the historical user lighting demand data and the real-time sensor data to predict the user's lighting demand under different environmental conditions based on the regression model, and generates a corresponding lighting adjustment scheme, and the regression model includes a linear regression or a support vector regression model. Preferably, the dynamic spectrum adjustment module includes a color temperature adjustment unit, a brightness adjustment unit and a spectrum distribution adjustment unit, the color temperature adjustment unit changes the color temperature by adjusting the driving current of the light emitting diode, and the brightness adjustment unit adjusts the brightness of the light source by adjusting the driving current or the pulse width modulation PWM control signal.

[0025] Preferably, the intelligent feedback and learning module automatically adjusts the lighting and environmental control strategies by continuously receiving the comfort evaluation data and demand change data from the user using a machine learning algorithm, wherein the machine learning algorithm includes a decision tree algorithm or a deep learning algorithm. Preferably, the control interface receives the target lighting conditions set by the user through a graphical user interface GUI, and supports the user to adjust the light source output through voice control through a voice command module, wherein the voice command module includes a voice recognition unit and a natural language processing unit.

[0026] Embodiment 1: This embodiment describes in detail the implementation method of the LED intelligent dimming system based on multi-spectral control in a specific application. Specifically, this system uses four main sensors for data collection: ambient light intensity sensor, temperature and humidity sensor, human activity sensor and air quality sensor. The function of each sensor is as follows: ambient light intensity sensor: used to monitor the light intensity of the indoor environment in real time, in lux. The output signal will be used as the basic input for adjusting the light intensity. Temperature and humidity sensor: monitor the temperature and humidity changes in the room, in degrees Celsius (°C) and relative humidity (%) respectively. These data are used to adjust the color temperature and brightness of the light source. Human activity sensor: detects whether there is human activity in the room through infrared sensing technology. If someone enters, adjust the light intensity; if no one enters, automatically adjust to energy-saving mode. Air quality sensor: used to detect CO2 concentration and other harmful gases in the air. When the air quality decreases, the light source system can automatically cooperate with other intelligent devices such as air purifiers, humidifiers, etc. to make appropriate adjustments. The data of all sensors are transmitted to the data fusion processing unit through wireless protocols to provide input for subsequent system adjustments.

[0027] The data fusion processing unit is responsible for receiving data from multiple sensors and fusing them through a weighted average algorithm to generate an environmental status evaluation signal (hereinafter referred to as the "evaluation signal"). The evaluation signal reflects the combined impact of light, temperature and humidity, human activity and air quality in the environment. Weighted average algorithm: Set the data weight coefficient of each sensor (for example, the weight of the temperature and humidity sensor is 0.3, the weight of the light sensor is 0.4, the weight of the human activity sensor is 0.2, and the weight of the air quality sensor is 0.1), and calculate the evaluation signal through weighted averaging. The formula is as follows: ;in: To evaluate the signal; is the temperature data; is the light intensity data; The human activity status (0 or 1, 0 means no one, 1 means someone); The evaluation signal is then passed to the user behavior prediction module and the dynamic spectrum adjustment module for subsequent adjustment calculations.

[0028] The user behavior prediction module uses a regression model to make predictions based on historical user behavior data and real-time sensor data. Specific steps include: historical behavior data collection: the system builds a user behavior database by recording changes in user lighting needs (such as lighting preferences and light source brightness in different time periods); regression model selection: the support vector regression (SVR) model is used to train with historical lighting demand data and real-time sensor input to generate a user behavior prediction model. This model can predict the user's lighting needs based on real-time environmental data; prediction and adjustment: when the system receives new environmental data, the prediction model will generate the user's current lighting needs, including parameters such as color temperature and brightness, and feed it back to the dynamic spectrum adjustment module.

[0029] The dynamic spectrum adjustment module dynamically adjusts the spectral output of the light-emitting diode according to the evaluation signal and the user behavior prediction results. The adjustment method is as follows: color temperature adjustment: the color temperature of the light source is changed by adjusting the driving current of the light-emitting diode. Specifically, if the temperature value in the evaluation signal is low (lower than 20°C), the light source is automatically adjusted to a warm tone (such as yellow or orange); if the temperature is high (higher than 30°C), it is adjusted to a cool tone (such as white or blue); brightness adjustment: the brightness of the light source is adjusted according to changes in ambient light intensity. For example, when the light intensity is weak, the brightness is automatically increased; when the light is sufficient, the brightness is reduced; spectral distribution adjustment: the brightness output of the light source is controlled through a pulse width modulation (PWM) signal, and the ratio of cold light to warm light is dynamically adjusted to optimize user comfort.

[0030] The intelligent feedback and learning module receives the user's comfort evaluation data in real time and uses machine learning algorithms (such as decision trees or deep learning) to automatically adjust the control strategy. Specific steps include: user feedback data collection: the system regularly collects user comfort feedback (such as user satisfaction evaluation under different lighting conditions) and demand change data; model optimization: based on the collected feedback data, the lighting and environmental control strategies are continuously adjusted. This process uses machine learning algorithms to optimize the existing adjustment strategies so that the system can gradually adapt to the personalized needs of different users. In addition, the present invention uses the Internet of Things technology, and the system can work in conjunction with other smart devices (such as air conditioners, humidifiers, air purifiers, etc.). The specific method is to provide multi-sensor data to a multi-device collaborative control unit, which adjusts the working state according to the collaborative needs between the devices. For example, when the temperature and humidity are high, the system can adjust the humidifier and air conditioner to adjust the light to provide a more comfortable indoor environment.

[0031] Embodiment 2: This embodiment uses four main sensors for data collection: ambient light intensity sensor, temperature and humidity sensor, human activity sensor and air quality sensor. In order to achieve more accurate data fusion, we optimize the weighted average algorithm to ensure that the weight coefficient of each sensor is dynamically adjusted according to the actual environmental changes and historical data, so as to more flexibly reflect the changes in environmental conditions.

[0032] Specifically, first, each sensor collects data such as light intensity, temperature and humidity, human activity status, and air quality in the environment in real time. Then, the following steps are used for data fusion processing: Data normalization: The data collected by each sensor will be normalized to ensure that the data of different sensors are compared and fused under the same dimension; Dynamic weight adjustment: The weight coefficient is adjusted according to the feedback of real-time data and historical data. For example, if the temperature and humidity in the environment change greatly, the weight of the temperature and humidity sensor will increase, and the weight of the light intensity sensor may decrease accordingly; Weighted average calculation: The data of all sensors are weighted averaged according to the adjusted weights to generate a comprehensive evaluation signal, which is used to reflect the comprehensive influence of factors such as light intensity, temperature, and humidity in the environment; Through this optimized data fusion algorithm, the system can more accurately evaluate the changes in the current environment and provide a more reliable basis for subsequent light adjustment; Improvement of user behavior prediction and dynamic spectrum adjustment.

[0033] This embodiment further improves the user behavior prediction module, combines real-time sensor data with historical behavior data, and uses a regression analysis model to predict the user's lighting needs under different environmental conditions. Specific steps include: historical data collection: the system collects and stores users' lighting preferences, activity status, and corresponding environmental data in different time periods. Use these data to build a user behavior database; regression analysis model training: use regression analysis models such as support vector regression (SVR) to train the user behavior database and generate a prediction model that can accurately predict the user's lighting needs; real-time prediction: when the system receives new environmental data, the prediction model will generate the user's current lighting needs in real time based on the current environmental status and the user's historical behavior data, including color temperature, brightness and other parameters.

[0034] And based on the predicted lighting needs, the system will adjust the output of the LED, including: Color temperature adjustment: by adjusting the driving current of the LED, the color temperature of the light source is changed. For example, when the ambient temperature is low, the system will automatically adjust the light source to a warm color to provide a sense of warmth; when the ambient temperature is high, the system will adjust it to a cool color to provide a sense of coolness. Brightness adjustment: Automatically adjust the brightness of the light source according to changes in ambient light intensity. For example, when the light is weak, the system will automatically increase the brightness; and when the light is strong, the brightness will decrease accordingly. Spectral distribution adjustment: Through the pulse width modulation (PWM) control signal, the output ratio of cold light to warm light is adjusted to optimize the user's comfort.

[0035] At the same time, in order to improve the adaptive ability of the system, this embodiment optimizes the intelligent feedback and learning module, and adopts a continuous optimization mechanism based on a decision tree algorithm or a deep learning algorithm. Specific processes include: user feedback data collection: the system will regularly collect user comfort feedback data, including user satisfaction evaluations on light intensity, color temperature, and the overall environment; feedback data analysis: use machine learning algorithms to analyze the collected user feedback, find out the relationship between the user's lighting needs and comfort, and update the user behavior prediction model; dynamic optimization adjustment strategy: based on user feedback, the system will automatically adjust the lighting and environmental control strategies to meet the user's personalized needs. This process ensures that the system can continuously optimize the lighting adjustment effect under changing environmental conditions.

[0036] This embodiment also strengthens the collaborative control with other smart devices (such as air conditioners, humidifiers, air purifiers, etc.). Through the Internet of Things technology, the system can communicate and collaborate with smart devices in the building in real time. Specific control logic, such as environmental perception and device linkage: when the sensor detects abnormal temperature and humidity, the system will automatically adjust the working state of the air conditioner or humidifier, and adjust the light source according to the real-time lighting adjustment requirements; comprehensive optimization: the collaborative work of multiple devices will optimize the comfort of the overall environment, and also help save energy. For example, when the temperature and humidity are high, the system can adjust the air conditioner and humidifier to adjust the lighting to maintain a comfortable balance in the indoor environment.

[0037] Embodiment 3: This embodiment is based on multiple sensors (ambient light intensity sensor, temperature and humidity sensor, human body sensor, air quality sensor) for data collection, combined with weighted average algorithm and regression prediction model for data processing and light source adjustment. The main workflow of the system is: sensor data collection, data fusion and processing, user behavior prediction, dynamic spectrum adjustment and feedback adjustment. The following are the specific implementation steps of the system, data collection and sensor configuration: The ambient light intensity sensor collects light intensity data (unit: Lux), which reflects the lighting conditions of the current environment. The temperature and humidity sensor is used to collect temperature (unit: Celsius, °C) and humidity (unit: percentage, %) data in the environment for adjusting the color temperature and brightness of the light source. The human body sensor monitors the human body activities in the room in real time through infrared sensing technology to determine whether there are people entering or leaving the room. Its output value is 0 (no one) or 1 (someone). The air quality sensor monitors the concentration of carbon dioxide and other harmful substances in the air, and is used to coordinate and control the indoor air quality and light adjustment.

[0038] Data fusion and environmental status assessment: The input signal of each sensor (light intensity, temperature and humidity, human activity status and air quality data) is weighted by the data fusion processing unit to generate an environmental status assessment signal. This signal is a comprehensive result of multiple factors such as ambient light, temperature and humidity, human activity and air quality. The weighted algorithm adopts, for example, first normalizing the data of all sensors to ensure that the values ​​of different data sources can be effectively fused under the same dimension. Then, the weight coefficient of each sensor is dynamically adjusted according to historical data and real-time feedback. Specifically, if the temperature and humidity change greatly, the weight of the temperature and humidity sensor is increased and the weight of the ambient light sensor is reduced, and vice versa. The adjustment method of the weight coefficient is trained through a linear regression model to ensure that the fusion algorithm can change flexibly according to the actual environmental conditions. User behavior prediction and light demand generation: Based on the user's historical behavior data and real-time environmental data, the system uses a support vector regression (SVR) model to predict light demand. Historical data includes users' preferences for light intensity and color temperature, activity patterns, etc. in different time periods. By training the regression model, user light demand prediction results for different environmental conditions can be generated. After data fusion, the system generates the user's lighting requirements under current environmental conditions through a prediction model, including parameters such as color temperature (such as warm light, cold light) and brightness (bright, dark). The input of the user behavior prediction model is historical lighting demand data and real-time sensor input data, and the output is the optimal lighting adjustment plan.

[0039] Dynamic spectrum adjustment and environmental adaptability adjustment: The dynamic spectrum adjustment module adjusts the spectrum output of the light-emitting diode according to the environmental status assessment signal and the user demand prediction results. Color temperature adjustment is achieved by adjusting the LED drive current to ensure that the color temperature of the light source adapts to the changes in ambient temperature. When the ambient temperature is below 20°C, the system automatically adjusts to warm tones; when the temperature is above 30°C, it adjusts to cool tones. Brightness adjustment is adjusted according to the ambient light intensity, increasing the brightness when the light is weak and automatically reducing the brightness when the light is strong. The adjustment of spectral distribution is achieved through pulse width modulation (PWM) technology, adjusting the output ratio of cold light and warm light to optimize user comfort.

[0040] Intelligent feedback and learning mechanism: The system continuously collects user comfort feedback data (such as user satisfaction under different lighting conditions) through the intelligent feedback module, and inputs this data into the machine learning algorithm (such as decision tree or deep learning algorithm). Based on the collected feedback data, the machine learning algorithm optimizes the user behavior prediction model and adjusts the control strategy to ensure that the lighting effect can be continuously optimized as user needs and environmental changes. Through this intelligent feedback mechanism, the system can dynamically adapt to the needs of different users and continuously optimize the adjustment strategy during actual use to ensure that the personalized needs of users are met in the long term. And this system also supports the Internet of Things technology to work in collaboration with smart devices in the building (such as air conditioners, humidifiers, air purifiers, etc.). Sensor data not only affects the adjustment of light sources, but also adjusts the working status of other devices. Through the Internet of Things protocol, the system can communicate with smart devices in real time to jointly optimize the indoor environment. For example, when the temperature and humidity sensor detects excessive humidity, the system can automatically adjust the working status of the humidifier and air conditioner to achieve the best balance of light, temperature and humidity, and improve environmental comfort.

[0041] Embodiment 4: In this embodiment, the intelligent dimming system uses multiple sensors to collect real-time data in the environment, including ambient light intensity sensors, temperature and humidity sensors, human activity sensors, and air quality sensors. In order to ensure that the system can provide optimal light adjustment under changing environmental conditions, the data of each sensor is synchronously collected through a unified data acquisition module. The real-time and accuracy of data acquisition are the basis for the efficient operation of the system. The collected raw data is preprocessed by the data fusion processing unit. First, the system normalizes the output data of each sensor so that the data of each sensor are compared and fused under the same dimension. This process ensures that the numerical differences between sensors will not have unnecessary effects on subsequent calculations, thereby avoiding errors caused by differences in units or magnitudes.

[0042] The main task of the data fusion processing unit is to generate a comprehensive environmental status assessment signal based on the real-time collected data. This signal reflects the comprehensive impact of various variables in the environment (such as temperature and humidity, light intensity, human activity, air quality, etc.). In this embodiment, we use a weighted average algorithm for data fusion. In this algorithm, the system dynamically adjusts the weight coefficient of each sensor according to the real-time data of the sensor. Specifically, when the ambient temperature changes greatly, the weight coefficient of the temperature and humidity sensor will increase, and the impact of the change in light intensity on the system will also increase accordingly. The weight coefficient is dynamically adjusted through a regression analysis model to ensure that the impact of each sensor in a specific situation is maximized. The output of the fusion algorithm is a comprehensive evaluation signal, which represents a comprehensive evaluation of the environmental state. The system will generate corresponding light adjustment parameters based on this evaluation signal to ensure a balance between light and other environmental factors.

[0043] In order to improve the personalization and intelligence of the system, we introduced a user behavior prediction module. This module predicts lighting demand through a machine learning algorithm based on historical user lighting demand data and current environmental conditions. Historical data includes information such as user lighting preferences and activity patterns in different time periods. Using these historical data, the system predicts user behavior through a support vector regression (SVR) model. The prediction results include the color temperature, brightness and adjustment method of the light source. This prediction model can be updated in real time to adapt to changes in user needs. Whenever the system obtains new environmental data, the user behavior prediction module generates the latest lighting demand plan and passes it to the dynamic spectrum adjustment module.

[0044] The dynamic spectrum adjustment module is one of the core modules of the system. It dynamically adjusts the spectral output of the light-emitting diode according to the fused environmental state evaluation signal and the user behavior prediction results. This module is divided into three sub-units: Color temperature adjustment unit: adjusts the color temperature of the light source by adjusting the driving current of the light-emitting diode. For example, when the temperature is low, the system automatically adjusts to warm tones (such as yellow or orange), and when the temperature is high, the system adjusts to cool tones (such as white or blue). Brightness adjustment unit: According to the changes in the ambient light intensity, the system automatically adjusts the brightness of the light source. In the case of weak light, the brightness is automatically increased; when the light is sufficient, the brightness is automatically reduced. Spectral distribution adjustment unit: Optimize the user's comfort by controlling the ratio of cold light and warm light. This process is controlled using pulse width modulation (PWM) technology, which enables the system to adaptively adjust the ratio of cold light and warm light under different environmental conditions to achieve the best lighting effect.

[0045] The intelligent feedback and learning module provides the system with continuous optimization capabilities. By collecting feedback data from users during actual use, including user satisfaction with lighting conditions and changes in environmental requirements, the system can continuously optimize its control strategy. Machine learning algorithms (such as decision trees or deep learning algorithms) are used to analyze these feedback data and adjust the lighting and environmental control strategies based on the analysis results. Through this feedback mechanism, the system can adaptively adjust the lighting adjustment parameters to achieve a personalized and customized lighting experience. As the use process progresses, the system will gradually optimize its adjustment strategy based on the accumulated user data and environmental changes.

[0046] This embodiment also realizes the coordinated control of smart devices. Through the Internet of Things technology, the smart lighting system interacts with other smart devices (such as air conditioners, humidifiers, air purifiers, etc.) in real time. Based on the data input of multiple sensors, the system can adjust the working status of other devices related to lighting. For example, when the temperature and humidity are high, the system automatically adjusts the working status of the air conditioner or humidifier to ensure the best balance between indoor temperature, humidity and lighting, and improve overall comfort.

[0047] It is obvious to those skilled in the art that the present invention is not limited to the details of the above exemplary embodiments, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.

[0048] Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solution of the present invention can be modified or replaced by equivalents without departing from the spirit and scope of the technical solution of the present invention.

Claims

1. An intelligent dimming system for light emitting diodes based on multi-spectrum control, characterized in that: include: Multi-sensor data acquisition module, used to obtain data including ambient light intensity, temperature and humidity, human activity and air quality through multiple sensors; A data fusion processing unit is used to receive data from the multiple sensors, and to perform comprehensive processing on the data through a fusion algorithm to generate an environmental state evaluation signal, wherein the environmental state evaluation signal is used to reflect the comprehensive influence of light intensity, temperature, and humidity factors in the environment, and to determine corresponding light adjustment parameters according to the environmental state evaluation signal; A user behavior prediction module is used to predict the user's lighting needs under specific environmental conditions through a machine learning algorithm based on historical user behavior data and real-time sensor data, and generate a predicted lighting adjustment plan, wherein the predicted lighting adjustment plan includes the color temperature, brightness and adjustment method of the light source; A dynamic spectrum adjustment module, used to dynamically adjust the spectrum output of the light-emitting diode according to the environmental state evaluation signal and the predicted illumination adjustment scheme, including adjusting the color temperature, brightness, and spectrum distribution of the diode, and adjusting the output of cold light and warm light according to environmental conditions; The temperature, humidity and light source linkage adjustment module is used to dynamically adjust the output of the light source according to the temperature and humidity changes in the environment. The light source is automatically adjusted to cold light or warm light to adapt to the current environment according to the parameter data of temperature and humidity; The multi-device collaborative control unit communicates and collaborates with the smart devices in the building through the Internet of Things technology, and adjusts the working status of the smart devices based on the data fed back by the sensors; Intelligent feedback and learning module, which is used to automatically adjust the control strategy based on the user's feedback data during actual use, and continuously optimize the lighting and environmental control strategy through machine learning algorithms; The control interface is used to receive the target lighting conditions set by the user and adjust the lighting through a graphical interface or voice commands. The control interface interacts with each module and adjusts the light source output according to the user input, and feeds back the adjustment results to the user end.

2. The LED intelligent dimming system based on multi-spectrum control according to claim 1, characterized in that: The adjusting the output of cold light and warm light according to environmental conditions specifically means that when the ambient temperature is low, the output of warm light is adjusted to include yellow or orange light to provide a warm feeling; when the ambient temperature is high, the output of cold light is adjusted to include white or blue light to provide a cool feeling.

3. The LED intelligent dimming system based on multi-spectrum control according to claim 2, characterized in that: The smart devices include air conditioners, humidifiers and air purifiers. The multi-device collaborative control unit adjusts the working states of the smart devices to coordinate with the light adjustment function based on the data collected by the multi-sensor data acquisition module.

4. The LED intelligent dimming system based on multi-spectrum control according to claim 1, characterized in that: The user's feedback data during actual use includes user comfort evaluation data and user demand change data.

5. The LED intelligent dimming system based on multi-spectrum control according to claim 1, characterized in that: The multi-sensor data acquisition module collects data through an ambient light intensity sensor, a temperature and humidity sensor, a human body sensor, and an air quality sensor. The temperature and humidity sensor is used to monitor changes in temperature and humidity in the environment, the human body sensor is used to detect the activity status of human beings indoors, and the air quality sensor is used to detect the air quality in the environment.

6. The LED intelligent dimming system based on multi-spectrum control according to claim 1, characterized in that: The data fusion processing unit fuses the data from each sensor through a weighted average algorithm to generate the environmental status assessment signal, and the weight coefficient of the weighted average algorithm is dynamically adjusted according to historical data and real-time sensor data.

7. The LED intelligent dimming system based on multi-spectrum control according to claim 1, characterized in that: The user behavior prediction module uses historical user lighting demand data and real-time sensor data to predict the user's lighting demand under different environmental conditions based on a regression model and generates a corresponding lighting adjustment plan. The regression model includes a linear regression or a support vector regression model.

8. The LED intelligent dimming system based on multi-spectrum control as claimed in claim 1, characterized in that: The dynamic spectrum adjustment module includes a color temperature adjustment unit, a brightness adjustment unit and a spectrum distribution adjustment unit. The color temperature adjustment unit changes the color temperature by adjusting the driving current of the light emitting diode, and the brightness adjustment unit adjusts the brightness of the light source by adjusting the driving current or the pulse width modulation PWM control signal.

9. The LED intelligent dimming system based on multi-spectrum control according to claim 1, characterized in that: The intelligent feedback and learning module continuously receives comfort evaluation data and demand change data from users, and uses machine learning algorithms to automatically adjust lighting and environmental control strategies. The machine learning algorithms include decision tree algorithms or deep learning algorithms.

10. The LED intelligent dimming system based on multi-spectrum control according to claim 1, characterized in that: The control interface receives the target lighting condition set by the user through the graphical user interface GUI, and supports the user to adjust the light source output through voice control through the voice command module, and the voice command module includes a voice recognition unit and a natural language processing unit.

Images