Intelligent decorative lighting control system based on Internet of Things and AI prediction

Abstract

The invention discloses an intelligent lighting control system based on the Internet of Things and AI prediction, and relates to the technical field of intelligent lighting, and the system comprises a data collection module which is connected with an ambient light sensor, a motion sensor and an electric quantity sensor through an intelligent lamp, collects the state data of intelligent lighting in real time, and sends the state data to a server; by integrating the ambient light sensor, the motion sensor and the electric quantity sensor, the system can sense environment changes and user behaviors in real time, self-adaptive adjustment of lamplight is achieved, user operation is simplified, a user does not need to frequently and manually adjust lamplight, the indoor illumination brightness can be automatically adjusted according to the ambient light intensity, and the user experience is improved. Meanwhile, through application of the AI prediction module, through deep analysis of user behavior modes and environment data, the illumination requirements of the user in different scenes can be accurately predicted, the lamplight state is adjusted in advance, and the user experience is further improved.

Description

Technical Field

[0001] The present invention relates to the field of intelligent lighting technology, and specifically to an intelligent lighting control system based on the Internet of Things and AI prediction. Background Art

[0002] With the rapid development of the Internet of Things (IoT) technology, the smart home sector has ushered in unprecedented changes. By connecting various devices to the internet, IoT technology enables interoperability and data sharing between devices, providing users with a more convenient and intelligent living experience. Against this backdrop, smart lighting systems, as a key component of smart homes, have gradually attracted widespread market attention. Smart lighting systems not only automatically adjust brightness based on ambient light but also enable remote control via mobile apps and voice control, greatly enhancing living comfort and convenience. Furthermore, with the continuous advancement of artificial intelligence technology, the use of AI algorithms to conduct in-depth analysis of user behavior patterns and environmental data to achieve more precise and personalized lighting control has become a new trend in the development of smart lighting systems.

[0003] However, traditional smart lighting systems still have many shortcomings in terms of technical implementation and application. First, traditional systems often rely on a single ambient light sensor or timer for lighting adjustment, and lack an in-depth understanding and prediction ability of user behavior patterns, resulting in inaccurate lighting adjustment and an inability to meet users' personalized needs in different scenarios. Secondly, the control method of traditional systems is relatively simple, and users need to operate through mobile phone apps or physical switches, which is not convenient enough and lacks diversified control methods such as voice control and remote control. In addition, traditional systems also have shortcomings in energy consumption management. They are unable to monitor and analyze the power consumption data of lamps in real time, making it difficult to provide effective energy-saving suggestions, which is not conducive to the rational use and conservation of energy. Finally, traditional systems lack a user feedback mechanism and are unable to collect and process users' evaluations and suggestions on lighting effects and system functions in a timely manner, making it difficult to carry out continuous optimization and upgrading.

[0004] Therefore, the development of an intelligent lighting control system based on the Internet of Things and AI prediction not only improves user experience and energy efficiency, but also promotes technological innovation and development in the field of smart homes. Summary of the Invention

[0005] The purpose of this invention is to make up for the shortcomings of the existing technology and provide an intelligent lighting control system based on the Internet of Things and AI prediction. By integrating ambient light, motion and power sensors, it realizes real-time data collection and encrypted transmission. Users can remotely log in to the system through mobile phones and tablet devices to view and adjust the status of lamps, including switch, brightness, color temperature and LED flicker characteristic data. The intelligent control module coordinates each unit according to the received instructions to realize automatic dimming, timing control, and scene mode switching functions. The AI prediction module uses user usage data and environmental data to predict user needs and optimize control strategies. The energy consumption management module conducts in-depth analysis of lamp power consumption data and provides energy-saving suggestions. The feedback processing module collects user evaluations and suggestions to promote continuous optimization of the system.

[0006] To solve the above technical problems, the present invention provides the following technical solutions: an intelligent lighting control system based on the Internet of Things and AI prediction, the system comprising:

[0007] Data acquisition module: connects the ambient light sensor, motion sensor and power sensor through the smart lamp to collect the smart lighting status data in real time, encrypts the data in JSON format through the communication network, and transmits it to the smart control module;

[0008] User interaction module: Users use the mobile phone, tablet APP or web page to enter the username and password to log in to the system; after logging in, they can view the status of the lamp switch, brightness, and color temperature on the interactive interface, and personalize the brightness threshold and adjustment speed of the automatic dimming, the on / off time of the timer control, and the cycle mode function;

[0009] Intelligent control module: It consists of an automatic dimming control unit, a timing control unit, a scene mode control unit, a color temperature adjustment control unit, a motion detection control unit, a voice control unit, and a remote control unit. It coordinates each unit to precisely control the intelligent lighting according to the received instructions.

[0010] AI prediction module: collects user usage data and environmental data, analyzes and mines user behavior patterns, predicts user needs in similar scenarios, and predicts the changing trend of ambient light intensity, and transmits it to the intelligent control module;

[0011] Energy consumption management module: Receives energy consumption data uploaded by smart lamps, including power consumption and usage duration, conducts in-depth analysis, explores users' energy consumption patterns and trends, generates energy consumption reports, and provides energy-saving suggestions to users;

[0012] Feedback processing module: Receives user feedback and suggestions on lighting effects and system functions through the user interaction module, classifies and analyzes them, and informs technical personnel to repair and optimize functional problems; user suggestions are combined with system optimization directions and incorporated into the system upgrade plan.

[0013] Furthermore, each sensor in the data acquisition module collects data: the ambient light sensor collects ambient light intensity, color and LED stroboscopic characteristic data in real time; the motion sensor captures data on human motion status, position and duration; and the power sensor monitors the power of the lamp.

[0014] Furthermore, the specific contents of the automatic dimming control unit, timing control unit, scene mode control unit, color temperature adjustment control unit, motion detection control unit, voice control unit and remote control unit in the intelligent control module are as follows:

[0015] The automatic dimming control unit receives the ambient light prediction results and brightness adjustment suggestions from the AI prediction and analysis module, as well as the user-preset brightness threshold, adjustment speed, light intensity, comfort level parameters and LED strobe data. It calculates the light intensity adjustment value through the ambient light adaptive dimming algorithm, generates a command and sends it to the smart lighting device. At the same time, it receives the light intensity information and LED strobe feedback data fed back by the device in real time, and makes fine adjustments to the deviation compared with the expected value.

[0016] The timing control unit receives the user-set timing control parameters of light on / off time, cycle mode, device ID and user ID, optimizes the timing tasks based on the user behavior information predicted by AI, and sorts the timing tasks according to the task priority judgment formula. The system schedules them in sequence and sends the on / off command to the smart lighting device at the set time, and supports users to modify the parameters at any time.

[0017] The scene mode control unit reads and encrypts the corresponding brightness, color temperature, and audio synchronization parameters from the system database according to the preset or custom scene mode selected by the user on the operation interface, generates and sends scene mode switching instructions to the smart lighting device through the Internet of Things, and supports user-defined scenes;

[0018] The color temperature adjustment control unit receives the current color temperature, desired color temperature, and color temperature range parameters set by the user, calculates the adjustment value from the current color temperature to the desired color temperature through the color temperature adjustment optimization algorithm, generates an instruction containing the target color temperature value and adjustment method based on the adjustment value, and sends it to the smart lighting device through the Internet of Things. After the device executes it, it receives feedback on the current color temperature information and performs secondary adjustments if there is any deviation.

[0019] The motion detection control unit receives data on the motion status, position, direction, and speed of a person collected by the motion detection sensor, filters out noise interference, and performs logical judgment based on preset automatic light switching conditions. If the light-on or light-off conditions are met, the corresponding instruction is generated;

[0020] The voice control unit collects user lighting control voice commands through a microphone, removes noise interference, converts them into text information and performs semantic analysis to understand the user's intentions, and converts them into control commands that the system can recognize and send to the smart lighting device;

[0021] The remote control unit: the user enters the user ID and device ID in the mobile phone application to log in to the system, and the remote control unit communicates to verify the identity. After logging in, it receives the user's instructions to view the lighting status, adjust the brightness and color temperature, select the scene mode, and set the scheduled task operation on the remote control interface, and sends them to the intelligent control module after parsing and processing to control the intelligent lighting equipment.

[0022] Furthermore, the automatic dimming control unit in the intelligent control module calculates the adjustment value of the light intensity through the ambient light adaptive dimming algorithm. Assume that the ambient light intensity collected by the ambient light sensor in real time is E, and the current light intensity fed back by the intelligent lamp is L current , the user sets the brightness threshold as T, the adjustment speed factor as S, and the comfort level corresponding to the comfort adjustment coefficient as C in the system operation interface. The calculation formula is: L new =L current +k1×(TE)×S×C×M, where L new is the adjusted light intensity, k1 is the adjustment coefficient set according to the light effect curve and response speed of the lamp, and the value range is 0.1 to 1.0, M is the LED flicker influence coefficient, which is determined comprehensively according to the characteristics of LED flicker frequency, flicker depth, etc., and the value range is 0.1-1.0. The greater the flicker interference to the human eye, the closer the M value is to 1.0, and vice versa, the closer it is to 0.1. new With L current Compare and if there is a difference, generate a light intensity adjustment instruction.

[0023] Furthermore, the timing control unit in the intelligent control module sorts the timing tasks by the task priority judgment formula, assuming that the task start time is t start , duration is t duration , the task frequency factor is F, the urgency factor is U, and the task priority calculation formula is: Among them, t now is the current time, w1, w2, and w3 are weight coefficients set according to task importance and resource allocation, and the priority P of each scheduled task is calculated. The scheduled tasks are sorted according to the priority P.

[0024] Furthermore, the color temperature adjustment control unit in the intelligent control module calculates the adjustment value from the current color temperature to the desired color temperature through the color temperature adjustment optimization algorithm. Suppose the user sets the desired color temperature value to C in the system operation interface. desired , color temperature range is T range, get the current color temperature of the lamp C current , the adjustment amount calculation formula is: Where ΔC is the color temperature adjustment amount, and k2 is the color temperature adjustment coefficient set according to the characteristics of the lamp.

[0025] Furthermore, the motion detection control unit in the intelligent control module determines whether to turn on or off the light. Assume that the motion detection state collected by the motion sensor in real time is M, the ambient light intensity collected by the ambient light sensor is E, and the time interval after the last light is turned off is T. off , set the decision threshold T in the system background according to the scenario and user habits threshold , with a value range of 0.5 to 5.0, and the formula is: If the decision result D=1, the system generates a light-on command; if D=0, it generates a light-off command.

[0026] Furthermore, the AI prediction module predicts user behavior through a multi-layer perceptron neural network model, which consists of an input layer, a hidden layer, and an output layer; the input layer receives user historical operation data, environmental data, and time data; the hidden layer outputs h j ,j=1,…,n h , n h is the number of neurons in the hidden layer, h j is the output value of the jth neuron in the hidden layer, and the calculation formula is: Where: w ij It is the weight between the i-th neuron in the input layer and the j-th neuron in the hidden layer, which determines the influence of the input layer neurons on the hidden layer neurons. in represents the number of neurons in the input layer, x i is the input value of the i-th neuron in the input layer mentioned above, b j is the bias of the jth neuron in the hidden layer, σ is the activation function; the output layer outputs y k , k=1,…,n out , n out is the number of neurons in the output layer, y k The output value of the kth neuron in the output layer is calculated as follows: Where: v jk is the weight between the jth neuron in the hidden layer and the kth neuron in the output layer, h j is the output value of the jth neuron in the hidden layer, c k is the bias of the kth neuron in the output layer.

[0027] Furthermore, the AI prediction module predicts the changing trend of the ambient light intensity through the autoregressive moving average model. Assume that the time series of the ambient light intensity is {Et}, the calculation formula is: Among them E t-i is the time series value of the ambient light intensity at time ti, p is the autoregressive order, ∈ t-j is the white noise sequence value at time tj, q is the moving average order, φ i is the autoregressive coefficient, θ j is the moving average coefficient, ∈ t is a white noise column, which represents the prediction error. The model is used to predict the ambient light intensity E at the future moment. t+1 ,The model is based on user historical operation data and environmental data,,and is trained using the back-propagation algorithm with the,activation function being ReLU.

[0028] Compared with existing technologies, this intelligent lighting control system based on the Internet of Things and AI prediction has the following beneficial effects:

[0029] 1. By integrating ambient light sensors, motion sensors and power sensors, the present invention enables the system to perceive environmental changes and user behavior in real time and achieve adaptive adjustment of lighting. This not only simplifies user operations, eliminating the need for users to frequently manually adjust lighting, but also automatically adjusts indoor lighting brightness according to ambient light intensity, creating a more comfortable and pleasant living environment. At the same time, the application of the AI prediction module, through in-depth analysis of user behavior patterns and environmental data, can accurately predict users' lighting needs in different scenarios, adjust lighting status in advance, and further enhance user experience. In addition, the energy consumption management module monitors and analyzes the power consumption data of smart lamps in real time, and provides users with energy-saving suggestions.

[0030] 2. The present invention realizes all-round and precise control of smart lighting by integrating multiple functional units such as automatic dimming, timing control, scene mode, color temperature adjustment, motion detection, voice control and remote control. In particular, the combination of the automatic dimming control unit and the timing control unit not only improves the flexibility and accuracy of light adjustment, but also optimizes the execution order of timed tasks through the task priority judgment formula, ensuring efficient use of system resources. The scene mode control unit allows users to preset or customize lighting scenes according to different needs. In addition, the addition of the voice control unit and the remote control unit further enhances the convenience and accessibility of the system. No matter where the user is, he can easily control the lighting system in his home through voice commands or mobile phone applications and enjoy the convenience and comfort brought by intelligence.

[0031] Other advantages, objects and features of the present invention will be described in part in the following description and, in part, will be apparent to those skilled in the art based on an examination of the following or may be learned from the practice of the invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] To more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present invention. Those skilled in the art can also derive other drawings based on these drawings without inventive effort.

[0033] Figure 1 It is the architecture of smart lighting control system based on IoT and AI prediction;

[0034] Figure 2 This is a workflow diagram of the intelligent lighting control system based on the Internet of Things and AI prediction. DETAILED DESCRIPTION

[0035] In order to further illustrate the technical means and effects adopted by the present invention to achieve the predetermined purpose of the invention, the specific implementation methods, structures, features and effects of the present invention are described in detail below in conjunction with the accompanying drawings and preferred embodiments.

[0036] Example 1:

[0037] In a smart home environment, the smart lighting control system plays a full role. The data acquisition module collects data in real time through the ambient light sensor, motion sensor and power sensor connected to the smart lamp. The ambient light sensor collects ambient light intensity E, color, LED stroboscopic characteristic data, the motion sensor captures human movement status, position, and duration data, and the power sensor monitors the power of the lamp. The collected data is encrypted in JSON format through the communication network and transmitted to the smart control module. Figure 1 shown.

[0038] Users log in to the system through the mobile phone APP, view the lamp switch, brightness, and color temperature status on the interactive interface, and set the brightness threshold and adjustment speed function of automatic dimming. The intelligent control module coordinates the work of each unit according to the received instructions.

[0039] The automatic dimming control unit receives the ambient light prediction results and brightness adjustment suggestions of the AI prediction and analysis module, as well as the user-preset brightness threshold T, adjustment speed factor S, and comfort adjustment coefficient C corresponding to the comfort level, and combines the current light intensity L fed back by the smart lamp. current , use the ambient light adaptive dimming algorithm to calculate the light intensity adjustment value L new , LED stroboscopic influence coefficient M, the calculation formula is: L new =L current +k1×(TE)×S×C×M, if L new With L currentIf there are differences, light intensity adjustment instructions are generated and sent to smart lighting devices via the Internet of Things. The dimming strategy is continuously optimized based on real-time changes in ambient light.

[0040] The timing control unit receives the parameters of the light on / off time and cycle mode set by the user, optimizes the timing tasks based on the user behavior information predicted by AI, and sorts the timing tasks according to the task priority judgment formula. The calculation formula is: The system schedules in sequence and sends switch commands to smart lighting devices at set times.

[0041] The scene mode control unit reads and encrypts the corresponding brightness, color temperature, and audio synchronization parameters from the system database based on the preset or custom scene mode selected by the user, and generates and sends scene mode switching instructions to the smart lighting device through the Internet of Things.

[0042] The color temperature adjustment control unit receives the current color temperature and the desired color temperature C set by the user desired , color temperature range T range Parameters, combined with the current color temperature value C of the lamp current And the color temperature adjustment coefficient k2 set according to the characteristics of the lamp, use the adjustment amount calculation formula to calculate the color temperature adjustment amount ΔC, the calculation formula is: Generate a command containing the target color temperature value and adjustment method and send it to the smart lighting device through the Internet of Things. After the device executes it, it receives feedback on the current color temperature information. If there is any deviation, it will make a secondary adjustment. The motion detection control unit receives the data of the person's motion status M, position, direction and speed collected by the motion detection sensor, combined with the ambient light intensity E collected by the ambient light sensor and the time interval T since the last light was turned off. off , make logical judgments based on the decision formula, the formula is: If D=1, the system generates a light-on command; if D=0, it generates a light-off command.

[0043] The voice control unit collects the user's lighting control voice commands through a microphone, pre-processes them to remove noise interference, converts them into text information and performs semantic analysis to understand the user's intentions, converts the text information into control commands that the system can recognize, and sends them to the smart lighting device.

[0044] After the user enters the user ID and device ID through the mobile phone application to log in to the system and verify the identity, the remote control unit receives the user's operation instructions on the remote control interface, parses and processes them, and sends them to the intelligent control module through the network to control the intelligent lighting equipment.

[0045] The AI prediction module collects user usage data and environmental data, and predicts user behavior through a multi-layer perceptron neural network model. The model input layer receives user historical operation data, environmental data, and time data, and the hidden layer outputs Output layer neuron output At the same time, the changing trend of ambient light intensity is predicted by the autoregressive moving average model, and the calculation formula is: Provides prediction information for intelligent control modules.

[0046] The energy consumption management module receives the energy consumption data of power consumption and usage time uploaded by smart lamps, analyzes and mines the energy consumption patterns and trends of users, generates energy consumption reports, and provides energy-saving suggestions for users. The feedback processing module receives the evaluation and suggestions of users on lighting effects and system functions given by the user interaction module through the user interaction module. After classification and analysis, the feedback of functional problems is notified to the technical staff for repair and optimization. The user suggestions are integrated into the system upgrade plan in combination with the system optimization direction, such as Figure 2 shown.

[0047] To sum up, in the smart home scenario, the smart lighting control system based on the Internet of Things and AI prediction has achieved a highly intelligent and personalized lighting experience. The data acquisition module accurately collects environmental and equipment data to provide a basis for system decision-making. The various units of the intelligent control module work together, and the automatic dimming, timing control, and scene mode switching functions meet diverse needs. The use of formulas ensures precise control. The AI prediction module uses models to predict user behavior and environmental changes, making the system smarter. Energy consumption management helps save energy, and feedback processing continuously optimizes the system. The system improves the comfort and convenience of home life, effectively integrates technologies, and provides innovative solutions for smart home lighting.

[0048] Example 2:

[0049] In a modern office building, a company's office area has deployed an intelligent lighting control system based on the Internet of Things and AI prediction to achieve an efficient, energy-saving and comfortable lighting environment.

[0050] In terms of the data acquisition module, each smart lamp is connected to an ambient light sensor, a motion sensor and a power sensor. The ambient light sensor continuously collects data on the ambient light intensity E, color LED stroboscopic characteristics, and information in the office area; the motion sensor constantly captures data on human movement status, position, and duration; and the power sensor accurately monitors the power of the lamp. These collected data will be encrypted in JSON format via the communication network and stably transmitted to the smart control module server, providing a real-time and accurate data basis for subsequent smart control.

[0051] Employees can log in to the system through the company's tablet APP or on the computer web page. When logging in, they need to enter their username and password to be verified by the server. After a successful login, they can intuitively view the switch status, current brightness and color temperature of the lamps on the interactive interface. At the same time, employees can also personalize the brightness threshold, adjustment speed, timed control switch time and cycle mode function of automatic dimming according to their own needs.

[0052] The intelligent control module is the core of the entire system, and its internal units have clear division of labor and close coordination.

[0053] Automatic dimming control unit: It receives the ambient light prediction results and brightness adjustment suggestions provided by the AI prediction and analysis module, and combines the brightness threshold T, adjustment speed factor S, comfort level corresponding to the comfort adjustment coefficient C, and the current light intensity L fed back by the smart lamps. current , LED flicker influence coefficient M, calculate the light intensity adjustment value L through the ambient light adaptive dimming algorithm new , the calculation formula is: L new =L current +k1×(TE)×S×C×M, when L new With L current When there is a difference, the automatic dimming control unit will generate a light intensity adjustment instruction and send it to the smart lighting device through the Internet of Things. In addition, it will receive the light intensity information feedback from the device in real time and compare it with the expected value. If there is any deviation, it will make fine adjustments. At the same time, it will continuously optimize the dimming strategy according to the real-time changes in ambient light. For example, on cloudy days, the ambient light intensity E becomes weaker, and the automatic dimming control unit will increase the light intensity according to the algorithm to ensure that the office area is well lit.

[0054] Timing control unit: Receives the lighting on / off time, cycle mode, device ID, and user ID timing control parameters set by employees. At the same time, it optimizes the timing tasks based on the user behavior information predicted by AI and sorts the timing tasks according to the task priority judgment formula. The formula is: The system will schedule according to the priority P order and send switch commands to the smart lighting devices at the set time. For example, on weekday mornings, the system will turn on the lights a while before employees go to work, so that employees can have a bright environment when they enter the office area; after get off work, the system will automatically turn off the lights to avoid energy waste. Moreover, employees can modify these timing control parameters at any time to adapt to different work arrangements.

[0055] Scene mode control unit: Employees can select preset scene modes, such as "meeting mode" and "daily office mode" on the operation interface, and can also customize scene modes. After selecting the corresponding mode, the scene mode control unit will read the corresponding brightness, color temperature, and audio synchronization parameters from the system database and encrypt them. It will generate and send scene mode switching instructions to the smart lighting device through the Internet of Things. In "meeting mode", the light brightness will automatically adjust to a suitable low brightness state, and the color temperature will also change accordingly, creating a focused meeting atmosphere.

[0056] Color temperature adjustment control unit: receives the current color temperature and expected color temperature C set by the employee desired , color temperature range T range Parameters, combined with the current color temperature value C of the lamp current And the color temperature adjustment coefficient k2 set according to the characteristics of the lamp, use the adjustment amount calculation formula to calculate the adjustment value ΔC from the current color temperature to the desired color temperature. The calculation formula is: Based on the adjustment value, an instruction containing the target color temperature value and adjustment method is generated and sent to the smart lighting device via the Internet of Things. After the device executes it, the color temperature adjustment control unit will receive feedback on the current color temperature information. If there is a deviation from the target color temperature, a secondary adjustment will be made. For example, if employees feel visual fatigue after working for a long time, the system can adjust the light color temperature to a softer warm tone to relieve visual stress.

[0057] Motion detection control unit: receives the data of the person's motion status M, position, direction and speed collected by the motion detection sensor, processes the data and filters out noise interference, and makes logical judgments based on the preset automatic light switching conditions. Suppose the ambient light intensity collected by the ambient light sensor is E, and the time interval since the last light was turned off is T. off , set the decision threshold T in the system background according to the scenario and user habits threshold , make decisions through the formula, the formula is: If D=1, the system generates a light-on command; if D=0, it generates a light-off command. For example, during lunch break, if there is no activity in the office area and the ambient light intensity meets certain conditions, the motion detection control unit will automatically turn off the lights to save energy.

[0058] Voice control unit: The system collects user voice commands for lighting control through microphones distributed throughout the office area. The collected voice commands are pre-processed to remove noise interference, then converted into text information and semantically analyzed to understand user intentions. The text information is converted into control commands that the system can recognize and send to smart lighting equipment. When employees are busy with their hands, they can easily control the lights by simply saying voice commands such as "turn up the lights" or "switch to conference mode lights."

[0059] Remote control unit: When the company's managers are on business trips or not in the office area, they can enter the user ID and device ID in the mobile application to log in to the system. After the remote control unit communicates and verifies the identity, the manager can view the lighting status of the office area, adjust the brightness and color temperature, select the scene mode, and set scheduled tasks on the remote control interface. The operation instructions are parsed and processed and sent to the intelligent control module through the network, which then controls the intelligent lighting equipment and realizes remote management of the office area lighting.

[0060] The AI prediction module plays a key role in assisting decision-making in the entire system. It collects user usage data and environmental data and uses a multi-layer perceptron neural network model to predict user behavior. The input layer of the model receives user historical operation data, environmental data, and time data; the output of the hidden layer n h is the number of neurons in the hidden layer; the output of neurons in the output layer n out is the number of neurons in the output layer. At the same time, the AI prediction module predicts the changing trend of ambient light intensity through the autoregressive moving average model. The formula is: Predict the ambient light intensity E at the future moment t+1 , providing accurate prediction information for the intelligent control module, making the system control more intelligent and precise.

[0061] The energy consumption management module receives the energy consumption data of the smart lamps, including their own power consumption and usage duration, conducts in-depth analysis of this energy consumption data, explores the user's energy consumption patterns and trends, and generates energy consumption reports based on the analysis. For example, if the analysis finds that the energy consumption of lamps in a certain area is too high during a specific time period, the module can adjust the lighting settings or check whether there are any abnormalities in the equipment, provide energy-saving suggestions to the company, and help the company reduce energy costs.

[0062] The feedback processing module is responsible for receiving employees' evaluations and suggestions on lighting effects and system functions submitted through the user interaction module during use, classifying and analyzing this feedback information, and promptly notifying technical personnel to repair and optimize any functional problem feedback; for user suggestions, the module combines them with the system optimization direction and incorporates them into the system upgrade plan to continuously improve system performance and user experience.

[0063] In summary, the intelligent lighting control system in the smart office scenario has greatly optimized office lighting management. The data acquisition module monitors the environment and lamp status in real time, laying the foundation for intelligent control. The intelligent control module uses various units and related formulas to achieve automatic dimming, reasonable timing regulation, and flexible scene switching functions to meet different office needs. The AI prediction module accurately predicts user behavior and ambient light changes to improve control accuracy. The energy consumption management module generates reports to help energy saving. The feedback processing module promotes continuous improvement of the system. This system improves office efficiency, reduces energy consumption, enhances the comfort of the office environment, and provides strong support for the intelligent upgrade of lighting in modern office spaces.

[0064] The above description is merely a preferred embodiment of the present invention and does not constitute any form of limitation to the present invention. Although the present invention has been disclosed as above in terms of a preferred embodiment, it is not intended to limit the present invention. Any person skilled in the art can, without departing from the scope of the technical solution of the present invention, make some changes or modifications to equivalent embodiments using the technical contents disclosed above. However, any brief modifications, equivalent changes and modifications made to the above embodiments based on the technical essence of the present invention without departing from the content of the technical solution of the present invention are still within the scope of the technical solution of the present invention.

Claims

1. The intelligent lighting control system based on the Internet of Things and AI prediction is characterized by: The system includes: Data acquisition module: connects the ambient light sensor, motion sensor and power sensor through the smart lamp to collect the smart lighting status data in real time, encrypts the data in JSON format through the communication network, and transmits it to the smart control module; User interaction module: Users use the mobile phone, tablet APP or web page to enter the username and password to log in to the system; after logging in, they can view the status of the lamp switch, brightness, and color temperature on the interactive interface, and personalize the brightness threshold and adjustment speed of the automatic dimming, the on / off time of the timer control, and the cycle mode function; Intelligent control module: It consists of an automatic dimming control unit, a timing control unit, a scene mode control unit, a color temperature adjustment control unit, a motion detection control unit, a voice control unit, and a remote control unit. It coordinates each unit to precisely control the intelligent lighting according to the received instructions. AI prediction module: collects user usage data and environmental data, analyzes and mines user behavior patterns, predicts user needs in similar scenarios, and predicts the changing trend of ambient light intensity, and transmits it to the intelligent control module; Energy consumption management module: Receives energy consumption data uploaded by smart lamps, including power consumption and usage duration, conducts in-depth analysis, explores users' energy consumption patterns and trends, generates energy consumption reports, and provides energy-saving suggestions to users; Feedback processing module: Receives user feedback and suggestions on lighting effects and system functions through the user interaction module, classifies and analyzes them, and informs technical personnel to repair and optimize functional problems; user suggestions are combined with system optimization directions and incorporated into the system upgrade plan.

2. The intelligent lighting control system based on the Internet of Things and AI prediction according to claim 1 is characterized in that: Each sensor in the data acquisition module collects data: the ambient light sensor collects ambient light intensity, color and LED stroboscopic characteristic data in real time; the motion sensor captures data on human motion status, position and duration; and the power sensor monitors the power of the lamp.

3. The intelligent lighting control system based on the Internet of Things and AI prediction according to claim 1 is characterized in that: The specific contents of the automatic dimming control unit, timing control unit, scene mode control unit, color temperature adjustment control unit, motion detection control unit, voice control unit and remote control unit in the intelligent control module are as follows: The automatic dimming control unit receives the ambient light prediction results and brightness adjustment suggestions from the AI prediction and analysis module, as well as the user-preset brightness threshold, adjustment speed, light intensity, comfort level parameters and LED strobe data. It calculates the light intensity adjustment value through the ambient light adaptive dimming algorithm, generates a command and sends it to the smart lighting device. At the same time, it receives the light intensity information and LED strobe feedback data fed back by the device in real time, and makes fine adjustments to the deviation compared with the expected value. The timing control unit receives the user-set timing control parameters of light on / off time, cycle mode, device ID and user ID, optimizes the timing tasks based on the user behavior information predicted by AI, and sorts the timing tasks according to the task priority judgment formula. The system schedules them in sequence and sends the on / off command to the smart lighting device at the set time, and supports users to modify the parameters at any time. The scene mode control unit reads and encrypts the corresponding brightness, color temperature, and audio synchronization parameters from the system database according to the preset or custom scene mode selected by the user on the operation interface, generates and sends scene mode switching instructions to the smart lighting device through the Internet of Things, and supports user-defined scenes; The color temperature adjustment control unit receives the current color temperature, desired color temperature, and color temperature range parameters set by the user, calculates the adjustment value from the current color temperature to the desired color temperature through the color temperature adjustment optimization algorithm, generates an instruction containing the target color temperature value and adjustment method based on the adjustment value, and sends it to the smart lighting device through the Internet of Things. After the device executes it, it receives feedback on the current color temperature information and performs secondary adjustments if there is any deviation. The motion detection control unit receives data on the motion status, position, direction, and speed of a person collected by the motion detection sensor, filters out noise interference, and performs logical judgment based on preset automatic light switching conditions. If the light-on or light-off conditions are met, the corresponding instruction is generated; The voice control unit collects user lighting control voice commands through a microphone, removes noise interference, converts them into text information and performs semantic analysis to understand the user's intentions, and converts them into control commands that the system can recognize and send to the smart lighting device; The remote control unit: the user enters the user ID and device ID in the mobile phone application to log in to the system, and the remote control unit communicates to verify the identity. After logging in, it receives the user's instructions to view the lighting status, adjust the brightness and color temperature, select the scene mode, and set the scheduled task operation on the remote control interface, and sends them to the intelligent control module after parsing and processing to control the intelligent lighting equipment.

4. The intelligent lighting control system based on the Internet of Things and AI prediction according to claim 3 is characterized in that: The automatic dimming control unit in the intelligent control module calculates the adjustment value of the light intensity through the ambient light adaptive dimming algorithm. Assume that the ambient light intensity collected by the ambient light sensor in real time is E, and the current light intensity fed back by the intelligent lamp is L current , the user sets the brightness threshold as T, the adjustment speed factor as S, and the comfort level corresponding to the comfort adjustment coefficient as C in the system operation interface. The calculation formula is: L new =L current +k1×(TE)×S×C×M, where L new is the adjusted light intensity, k1 is the adjustment coefficient set according to the light effect curve and response speed of the lamp, and the value range is 0.1 to 1.0, M is the LED flicker influence coefficient, which is determined comprehensively according to the characteristics of LED flicker frequency, flicker depth, etc., and the value range is 0.1-1.

0. The greater the flicker interference to the human eye, the closer the M value is to 1.0, and vice versa, the closer it is to 0.

1. new With L current Compare and if there is a difference, generate a light intensity adjustment instruction.

5. The intelligent lighting control system based on the Internet of Things and AI prediction according to claim 3 is characterized in that: The timing control unit in the intelligent control module sorts the timing tasks according to the task priority judgment formula, assuming that the task start time is t start , duration is t duration , the task frequency factor is F, the urgency factor is U, and the task priority calculation formula is: Among them, t now is the current time, w1, w2, and w3 are weight coefficients set according to task importance and resource allocation, and the priority P of each scheduled task is calculated. The scheduled tasks are sorted according to the priority P.

6. The intelligent lighting control system based on the Internet of Things and AI prediction according to claim 3 is characterized in that: The color temperature adjustment control unit in the intelligent control module calculates the adjustment value from the current color temperature to the desired color temperature through the color temperature adjustment optimization algorithm. If the user sets the desired color temperature value to C in the system operation interface, desired , color temperature range is T range , get the current color temperature of the lamp C current , the adjustment amount calculation formula is: Where ΔC is the color temperature adjustment amount, and k2 is the color temperature adjustment coefficient set according to the characteristics of the lamp.

7. The intelligent lighting control system based on the Internet of Things and AI prediction according to claim 3 is characterized in that: The motion detection control unit in the intelligent control module determines whether to turn on or off the light. The motion detection state collected by the motion sensor in real time is M, the ambient light intensity collected by the ambient light sensor is E, and the time interval after the last light is turned off is T. off , set the decision threshold T in the system background according to the scenario and user habits threshold , with a value range of 0.5 to 5.0, and the formula is: If the decision result D=1, the system generates a light-on command; if D=0, it generates a light-off command.

8. The intelligent lighting control system based on the Internet of Things and AI prediction according to claim 1 is characterized in that: The AI prediction module predicts user behavior through a multi-layer perceptron neural network model, which consists of an input layer, a hidden layer, and an output layer; the input layer receives user historical operation data, environmental data, and time data; the hidden layer outputs h j ,j=1,…,n h , n h is the number of neurons in the hidden layer, h j is the output value of the jth neuron in the hidden layer, and the calculation formula is: Where: w ij It is the weight between the i-th neuron in the input layer and the j-th neuron in the hidden layer, which determines the influence of the input layer neurons on the hidden layer neurons. in represents the number of neurons in the input layer, x i is the input value of the i-th neuron in the input layer mentioned above, b j is the bias of the jth neuron in the hidden layer, σ is the activation function; the output layer outputs y k , k=1,…,n out , n out is the number of neurons in the output layer, y k The output value of the kth neuron in the output layer is calculated as follows: Where: v jk is the weight between the jth neuron in the hidden layer and the kth neuron in the output layer, h j is the output value of the jth neuron in the hidden layer, c k is the bias of the kth neuron in the output layer.

9. The intelligent lighting control system based on the Internet of Things and AI prediction according to claim 1 is characterized in that: The AI prediction module predicts the changing trend of ambient light intensity through the autoregressive moving average model. Assume that the time series of ambient light intensity is {E t }, the calculation formula is: Among them E t-i is the time series value of the ambient light intensity at time ti, p is the autoregressive order, ∈ t-j is the white noise sequence value at time tj, q is the moving average order, φ i is the autoregressive coefficient, θ j is the moving average coefficient, ∈ t is a white noise column, which represents the prediction error. The model is used to predict the ambient light intensity E at the future moment. t+1 ,The model is based on user historical operation data and environmental data,,and is trained using the back-propagation algorithm with the,activation function being ReLU.

Images