An induction control system for an induction LED lighting lamp

Abstract

The present invention relates to the field of inductive control of lighting lamps, and in particular to an inductive control system of an inductive LED lighting lamp. The method comprises the following steps: the lighting scene module is used to: identify all LED lighting lamps in an area; calculate the position of each LED lighting lamp node in the area, and identify the scene usage in the area to construct multiple LED lighting scene sub-areas; the ambient light feature module is used to: obtain the ambient light parameters of the scene sub-areas; track the spatial distribution of the ambient light parameters of the scene sub-areas, and mine the ambient light state characteristics to generate the comprehensive state characteristics of the ambient light; the multi-area lighting coordination module is used to: adjust the dynamic light source output parameters of multiple LED lighting scene sub-areas and perform multi-area lighting coordination smoothing based on the comprehensive state characteristics of the ambient light to generate multi-area lighting coordination control parameters. The present invention realizes fast and accurate inductive control of LED lighting lamps.

Description

Technical Field

[0001] The present invention relates to the field of induction control of lighting lamps, and in particular to an induction control system of an induction-type LED lighting lamp. Background Art

[0002] As an important part of the intelligent lighting system, induction LED lighting is widely used in homes, businesses, public places and other fields. With its high efficiency, energy saving and environmental protection, it has become the first choice for modern lighting solutions. With the continuous development of intelligent technology, the traditional manual switch control method has gradually failed to meet the user's needs for convenience, energy saving and environmental adaptability. Induction LED lighting integrates various sensing technologies, such as infrared sensing and ultrasonic sensing, to achieve automatic response to changes in the surrounding environment. It can automatically control the opening and closing of lights according to factors such as human movement, light intensity, temperature changes, etc., thereby greatly improving the convenience of use and energy saving effect.

[0003] However, in the long-term operation, the inductive control performance of inductive LED lighting may be affected by many factors. Environmental factors such as changes in temperature and humidity, sensor aging, external interference signals, and the installation location of the lamp may lead to inaccurate inductive control, or even false triggering or failure. Traditional inductive control methods usually rely on fixed threshold settings and simple sensor signal processing, which are easily affected by external noise or dynamically changing environments, resulting in low control accuracy and inaccurate timing of turning the light on or off, affecting the user experience.

[0004] Therefore, in order to meet the needs of modern intelligent lighting systems for efficient and precise control, a new sensing control method is needed. Summary of the invention

[0005] In order to solve the above technical problems, the present invention proposes an induction control system for an induction-type LED lighting lamp to solve at least one of the above technical problems.

[0006] To achieve the above object, the present invention provides an inductive control system for an inductive LED lighting lamp, wherein the inductive control system for the inductive LED lighting lamp comprises a lighting scene module, an ambient light feature module, a multi-region lighting coordination module, a lighting delay optimization module, a movement trajectory prediction module and an inductive lighting control module:

[0007] The lighting scene module is used to: identify all LED lighting lamps in the area; calculate the node positions of all LED lighting lamps in the area one by one, and identify the usage scenes in the area to construct multiple LED lighting scene sub-areas;

[0008] The ambient light feature module is used to: obtain ambient light parameters of the scene sub-area; track the light space distribution of the ambient light parameters of the scene sub-area, and mine the ambient light state features to generate ambient light comprehensive state features;

[0009] The multi-region lighting coordination module is used to: perform dynamic light source output parameter adjustment and multi-region lighting coordination smoothing on multiple LED lighting scene sub-regions based on the comprehensive state characteristics of the ambient light, so as to generate multi-region lighting coordination control parameters;

[0010] The lighting delay optimization module is used to: collect pedestrian infrared sensing signals in real time; perform lighting threshold detection on pedestrian infrared sensing signals, and perform lighting delay optimization based on multi-region lighting collaborative control parameters to generate multi-region lighting delay optimization parameters;

[0011] The movement trajectory prediction module is used to: perform dynamic behavior analysis on pedestrian infrared sensing signals and perform multi-time point movement trajectory prediction, thereby generating a pedestrian dynamic prediction trajectory;

[0012] The inductive lighting control module is used to make advance inductive lighting control decisions on multi-zone lighting delay optimization parameters according to pedestrian dynamic prediction trajectories, and to perform enhanced transfer learning to build an intelligent lighting inductive control model.

[0013] By identifying all the LED lights in the area, the system of the present invention can accurately obtain the location information of the LED lighting equipment, and provide basic data support for subsequent control and adjustment. Accurate identification of LED lights helps the system to establish a spatial distribution model of LED lighting equipment, laying the foundation for subsequent intelligent control. Calculating the position of each LED light node and identifying the scene one by one helps the system understand the role and influence range of each lighting point, and provides support for fine control. Constructing LED lighting scene sub-areas helps to personalize the lighting needs of different areas, improve lighting effects and energy-saving effects. By acquiring ambient light parameters and tracking the spatial distribution of light, the system can realize dynamic perception and adjustment of ambient light, improve lighting effects and comfort. Mining the characteristics of ambient light status helps the system to better understand the changing laws of ambient light, and provide a more accurate reference basis for intelligent adjustment. Through the generation of lighting collaborative control parameters, the system can realize multiple Coordination and unified adjustment of regional lighting improves lighting uniformity and comfort, and realizes collaborative lighting control, which helps optimize the overall lighting effect, improves energy efficiency and user experience. Real-time collection of pedestrian infrared sensing signals helps the system perceive real-time crowd flow and provide real-time data support for intelligent lighting control. Through lighting threshold detection and delay optimization, the system can dynamically adjust lighting brightness and delay according to crowd flow, improve energy saving and safety. Dynamic behavior analysis and mobile trajectory prediction help the system accurately grasp the laws of crowd behavior and provide a more accurate basis for lighting control decisions. Generating dynamic predicted pedestrian trajectories helps the system predict the direction of crowd flow in advance and provide a more efficient response strategy for intelligent lighting control. Lighting control decisions based on dynamic predicted trajectories help the system realize intelligent and personalized lighting adjustment and improve user experience and comfort. Strengthening transfer learning can continuously optimize the intelligent lighting sensing control model and improve the intelligence level and adaptability of the system.

[0014] Preferably, the lighting scene module is used to: identify all LED lighting lamps in the area; calculate the node positions of all LED lighting lamps in the area one by one, and identify the usage scenes in the area to construct multiple LED lighting scene sub-areas, specifically for:

[0015] Identify all LED lights in the area;

[0016] Calculating the position of each LED lighting node of all LED lighting lamps in the area one by one to generate the spatial position coordinates of each LED node;

[0017] Perform spatial layout analysis on the spatial position coordinates of each LED node to generate LED node spatial layout data;

[0018] Identify the usage scenarios in the region based on the spatial layout data of the LED nodes, thereby obtaining multiple regional usage scenarios;

[0019] Based on multiple regional usage scenarios, regional scene segmentation is performed on all LED lighting lamps in the area to construct multiple LED lighting scene sub-areas.

[0020] The present invention uses corresponding sensors or technical means to identify and mark all LED lighting fixtures in the area and establish a location database for LED lighting fixtures. The position of each LED lighting fixture node in the area is calculated to determine its specific coordinates in space, including height, angle and other information. The spatial position coordinates of the LED nodes are analyzed, and their relative positions and distribution patterns are considered to better understand the overall layout characteristics of the LED lighting fixtures. Based on the location information and lighting characteristics of the LED nodes, different usage scenarios in the area are identified, such as work areas, rest areas, meeting areas, etc. According to different usage scenarios, the LED lighting fixtures are divided into corresponding regional scenes to form multiple LED lighting scene sub-areas to achieve targeted lighting control.

[0021] Preferably, the ambient light feature module is used to: obtain ambient light parameters of the scene sub-area; track the light space distribution of the ambient light parameters of the scene sub-area, and mine the ambient light state features to generate ambient light comprehensive state features, specifically for:

[0022] Detecting ambient light parameters of multiple LED-illuminated scene sub-areas based on a light sensor to obtain ambient light parameters of the scene sub-areas;

[0023] The ambient light parameters of the scene sub-areas are averaged to calculate the ambient light intensity, and the average ambient light intensity of each sub-area is generated;

[0024] Performing light space distribution tracing on the ambient light parameters of the scene sub-area to obtain light space distribution tracing data;

[0025] Perform light distribution change evolution on the light space distribution tracking data to generate light space distribution change characteristics;

[0026] The ambient light state characteristics are mined based on the average ambient light intensity and light spatial distribution change characteristics of each sub-area to generate the comprehensive ambient light state characteristics.

[0027] The present invention detects ambient light parameters through light sensors, and the system can obtain the lighting conditions of sub-areas of LED lighting scenes in real time, providing a data basis for subsequent adjustment and optimization. Real-time monitoring of ambient light parameters helps the system dynamically adjust the brightness and color temperature of LED lighting lamps according to actual lighting conditions, thereby improving lighting effects and energy-saving efficiency. By calculating the average ambient light intensity, the system can understand the overall lighting level of each sub-area, providing a reference basis for lighting adjustment. The average calculation of ambient light intensity helps the system optimize lighting uniformity and comfort, and improves user experience. By tracking the spatial distribution of light, the system can understand the distribution of light in space, providing data support for fine adjustment. ,Realizing the tracking of light spatial distribution helps the system adjust the lighting angle and range of LED lighting according to the changes in spatial lighting, improve the lighting effect and light uniformity, through the evolution of light distribution changes, the system can track the dynamic changes of light distribution, and provide a deeper understanding for lighting adjustment, realizing the evolution of light distribution changes helps the system predict the trend of light changes and provide more accurate reference data for intelligent lighting control, and the mining of ambient light state features helps the system integrate various lighting parameters and provide a more comprehensive ambient light state analysis for intelligent lighting control, and the generation of ambient light comprehensive state features can help the system better understand the overall characteristics of ambient light and provide a basis for the optimization of intelligent lighting control algorithms.

[0028] Preferably, the multi-region lighting coordination module is used to: perform dynamic light source output parameter adjustment and multi-region lighting coordination smoothing on multiple LED lighting scene sub-regions based on the comprehensive state characteristics of the ambient light, so as to generate multi-region lighting coordination control parameters, specifically for:

[0029] Perform regional lighting demand analysis on multiple LED lighting scene sub-areas to obtain the lighting demand characteristics of each scene sub-area;

[0030] Calculate the regional lighting brightness based on the lighting demand characteristics of each scene sub-region to generate a regional lighting demand brightness value;

[0031] Dynamically adjusting the light source output parameters of multiple LED lighting scene sub-areas based on the comprehensive state characteristics of the ambient light, thereby obtaining the light source output characteristic parameters of each sub-area;

[0032] Multi-region lighting collaborative smoothing is performed according to the lighting demand characteristics of each scene sub-region and the light source output characteristic parameters of each sub-region to generate multi-region lighting collaborative control parameters.

[0033] Through regional lighting demand analysis, the present invention can enable the system to understand the lighting demand characteristics of each sub-area, including brightness, color temperature, etc., to provide a basis for subsequent lighting adjustment. Detailed lighting demand analysis helps the system to formulate personalized lighting plans according to the functions and usage scenarios of different areas, improve lighting effects and comfort. By calculating the regional lighting demand brightness value, the system can determine the required lighting brightness level for each sub-area, providing a basis for adjusting the light source output parameters. Realizing regional lighting brightness calculation helps the system to accurately adjust the brightness of LED lamps according to lighting needs, improve lighting effects and energy-saving efficiency. Through dynamic light source output parameter adjustment, the system can adjust the brightness, color temperature and other parameters of LED lamps in real time according to the comprehensive state characteristics of ambient light to adapt to different environments. Realizing light source output characteristic parameter adjustment helps the system to dynamically adjust lighting according to ambient light changes, improve the quality and stability of lighting effects. Multi-area lighting collaborative smoothness enables the system to achieve lighting coordination between different areas, ensure that the overall lighting effect is unified and comfortable, and realize multi-area lighting collaborative control parameters helps the system improve the consistency and stability of the overall lighting effect and enhance user experience.

[0034] Preferably, the specific steps of dynamically adjusting the light source output parameters of multiple LED lighting scene sub-areas based on the comprehensive state characteristics of the ambient light to obtain the light source output characteristic parameters of each sub-area include:

[0035] Based on the comprehensive state characteristics of ambient light, the optimal light source color temperature analysis is performed on multiple LED lighting scene sub-areas to generate the optimal light source color temperature parameters for each scene sub-area;

[0036] Calculate the color temperature difference between regions for the optimal light source color temperature parameters of each scene sub-region, so as to obtain the color temperature difference data between sub-regions;

[0037] Calculate the spatial color temperature uniformity based on the color temperature difference data between the sub-areas, thereby generating uniform light source color temperature output parameters;

[0038] Performing a light source illumination frequency analysis on the illumination demand characteristics of each scene sub-area to obtain a light source illumination frequency parameter for each scene sub-area;

[0039] Dynamic light source output parameter adjustment is performed on the uniform light source color temperature output parameter and the light source illumination frequency parameter of each scene sub-area, thereby obtaining the light source output characteristic parameter of each sub-area.

[0040] Through the optimal light source color temperature analysis, the present invention can determine the optimal light source color temperature parameters for each sub-area to provide the lighting effect that best suits the scene. The determination of the optimal light source color temperature parameters helps to improve the realism and comfort of the lighting effect, making the lighting more in line with people's visual needs. Through the color temperature difference calculation, the system can understand the color temperature difference between different sub-areas, thereby adjusting the light source color temperature to achieve a more uniform lighting effect. The color temperature difference calculation helps to improve the consistency and coordination of the overall lighting, making the color temperature transition between different areas smoother and more natural. Through the spatial color temperature uniformity calculation, the system can evaluate the color temperature distribution uniformity of the overall lighting system, and adjust the light source color temperature output parameters to improve the uniformity, so as to achieve spatial Color temperature uniformity helps to eliminate the visual discomfort caused by color temperature non-uniformity and improve the quality and comfort of the overall lighting effect. Through light source lighting frequency analysis, the system can understand the light source lighting frequency parameters of different sub-areas to meet the needs of light source brightness in different scenes. Light source lighting frequency analysis helps the system adjust the brightness of LED lights according to the needs of different scenes and improve the adaptability and comfort of lighting effects. Through dynamic light source output parameter adjustment, the system can adjust the parameters of LED lights in real time according to the uniform light source color temperature and lighting frequency parameters to meet actual lighting needs. Realizing the adjustment of light source output characteristic parameters helps the system dynamically adjust the lighting effect according to the requirements of different scenes and improve the intelligence and personalization of lighting.

[0041] Preferably, the lighting delay optimization module is used to: collect pedestrian infrared sensing signals in real time; perform lighting threshold detection on pedestrian infrared sensing signals, and perform lighting delay optimization to generate multi-region lighting delay optimization parameters, specifically for:

[0042] Collect pedestrian infrared sensing signals in real time; perform environmental filtering and noise reduction on pedestrian infrared sensing signals to obtain environmental noise-reduced infrared sensing signals;

[0043] Calculate the time series signal strength of the environmental noise reduction infrared sensing signal to generate a time series signal strength curve;

[0044] Perform lighting threshold detection on the timing signal strength curve based on the preset infrared sensing parameter threshold, and when the preset infrared sensing parameter threshold is not less than the timing signal strength, it is marked as the sensing lighting time point;

[0045] The lighting delay is optimized through multi-zone lighting collaborative control parameters based on the sensing lighting time point to generate multi-zone lighting delay optimization parameters.

[0046] The present invention can ensure that the system can timely sense the presence of pedestrians by real-time collection of pedestrian infrared sensing signals, and provide an accurate data basis for subsequent lighting control. By real-time signal collection, the system can respond to the arrival of pedestrians in real time, and improve the sensitivity and intelligence of the lighting system to environmental changes. Environmental filtering and noise reduction help to remove interference signals and improve the accuracy and reliability of pedestrian sensing signals. Noise reduction processing can effectively reduce false triggering and improve the stability and accuracy of the system. Time series signal strength calculation can help the system understand the intensity change trend of pedestrian sensing signals and provide a reference basis for subsequent lighting control. Through time series signal strength calculation, the system can more accurately judge the position and behavior of pedestrians and improve the intelligence level of the lighting system. Lighting threshold detection helps to determine when the lighting system needs to be activated to respond to the arrival of pedestrians and improve the energy efficiency and energy saving of the lighting system. Marking the sensing lighting time point can ensure that the lighting system responds in time when needed, and improve user experience and safety. Through the optimization of multi-region lighting collaborative control parameters, the system can realize multi-region lighting collaborative control according to the sensing lighting time point, improve the consistency and overall sense of lighting effects, and generate lighting delay optimization parameters to accurately adjust the lighting delay time and improve the lighting system's intelligent response capability to pedestrian behavior.

[0047] Preferably, the specific steps of optimizing the lighting delay by using the multi-zone lighting collaborative control parameters based on the sensing lighting time point to generate the multi-zone lighting delay optimization parameters are:

[0048] Based on the sensing lighting time point, the LED lighting lamps are dynamically triggered through multi-zone lighting collaborative control parameters, and the dynamic lighting response parameters are obtained in real time;

[0049] calculating a timestamp of the lighting response based on the dynamic lighting response parameter;

[0050] Calculating the response delay of the timestamp of the lighting response according to the sensing lighting time point, thereby obtaining a lighting response delay value;

[0051] The lighting delay optimization is performed on the multi-zone lighting collaborative control parameters according to the lighting response delay value to generate the multi-zone lighting delay optimization parameters.

[0052] The present invention can dynamically adjust the brightness and color temperature of the LED lighting lamp according to the sensing lighting time point and the multi-zone lighting control parameters through dynamic lighting sensing triggering, thereby realizing more intelligent lighting adjustment. Through sensing triggering, the system can adjust the lighting effect according to the real-time situation, thereby improving energy efficiency and user experience. Real-time acquisition of lighting response parameters can help the system to quickly respond to changes in lighting demand, thereby improving the real-time and flexibility of the lighting system. Through real-time parameter acquisition, the system can dynamically adjust the parameters of the LED lighting lamp according to the actual situation, thereby providing a lighting effect that better meets the demand. Calculating the timestamp of the lighting response helps to record the time point of the lighting system response, thereby providing a time reference for subsequent delay calculation and optimization. The recording of the timestamp can help the system analyze the time performance of the lighting response, thereby optimizing the response speed and accuracy of the system. The response delay calculation can evaluate the response speed of the system to the sensing signal, thereby helping to identify and solve the delay problem, thereby improving the real-time and accuracy of the system. The acquisition of the lighting response delay value can provide an important reference for system optimization, thereby ensuring that the lighting system can quickly and accurately respond to user needs. The lighting delay optimization can adjust the lighting control parameters according to the actual response delay situation, thereby improving the response speed and accuracy of the system. Through delay optimization, the system can realize more sophisticated lighting control, thereby improving user experience and energy efficiency.

[0053] Preferably, the movement trajectory prediction module is used to: perform dynamic behavior analysis on pedestrian infrared sensing signals and perform multi-time point movement trajectory prediction, thereby generating a pedestrian dynamic prediction trajectory, specifically for:

[0054] Perform signal strength change analysis on the environmental noise reduction infrared sensing signal to generate sensing signal strength change data;

[0055] Evolving the pedestrian movement route based on the sensing signal strength change data, thereby generating the pedestrian movement route;

[0056] Calculate the length of time a pedestrian stays in a certain area based on their movement route to obtain the length of time they stay in the behavior area;

[0057] Perform time-series movement position recognition on the pedestrian's moving route to obtain the pedestrian's time-series movement position;

[0058] Perform dynamic behavior analysis on the duration of stay in the behavior area and the temporal movement position of pedestrians to generate dynamic behavior feature data;

[0059] The dynamic behavior feature data is used to predict the multi-time point movement trajectory to generate the pedestrian dynamic prediction trajectory.

[0060] The present invention can help the system understand the activities of pedestrians in the environment and improve the perception of pedestrians through signal strength change analysis. The generated sensing signal strength change data can provide basic data for subsequent pedestrian behavior analysis and enhance the intelligent perception ability of the system. The evolution of pedestrian movement routes can help the system simulate the movement trajectory of pedestrians in the environment and provide a basis for subsequent behavior analysis and prediction. The generation of pedestrian movement routes can help the system better understand the activity patterns and paths of pedestrians and improve the accuracy of pedestrian behavior analysis. The calculation of regional residence time can help the system identify the residence time of pedestrians in different areas and provide important data reference for dynamic behavior analysis. The acquisition of the residence time in the behavior area can help the system to have an in-depth understanding of pedestrian behavior patterns and improve the intelligent analysis ability of pedestrian behavior. The recognition of the temporal movement position can help the system track the position changes of pedestrians at different time points, and provide time series data support for dynamic behavior analysis. The acquisition of the temporal movement position of pedestrians can help the system accurately capture the activity trajectory of pedestrians and improve the accuracy of pedestrian behavior analysis. Dynamic behavior analysis can help the system deeply understand the activity patterns and behavior characteristics of pedestrians, so as to realize the intelligent recognition and analysis of pedestrian behavior. The generation of dynamic behavior characteristic data can help the system establish a pedestrian behavior model, which provides an important basis for subsequent prediction and response. The multi-time point movement trajectory prediction can help the system predict the future movement trajectory of pedestrians and realize the intelligent prediction and response of pedestrian behavior. The generation of pedestrian dynamic prediction trajectory helps the system prepare lighting response measures in advance and optimize the intelligence and response speed of the lighting system.

[0061] Preferably, the inductive lighting control module is used to make pre-inductive lighting control decisions on multi-zone lighting delay optimization parameters according to pedestrian dynamic prediction trajectories, and to perform enhanced transfer learning to build an intelligent lighting inductive control model, specifically for:

[0062] Calculate the moving trajectory speed of the pedestrian's dynamic predicted trajectory to generate the pedestrian's dynamic trajectory predicted speed;

[0063] Predicting the arrival time of multiple LED lighting scene sub-areas based on the predicted speed of pedestrian dynamic trajectories, thereby generating the sub-area arrival time of the predicted trajectory;

[0064] Pre-sensing lighting control decisions are made on multi-region lighting delay optimization parameters based on the sub-region arrival times of the predicted trajectories to generate pre-sensing lighting control strategies;

[0065] Strengthen transfer learning of pre-sensing lighting control strategies and build intelligent lighting sensing control models.

[0066] The present invention can help the system understand the speed characteristics of pedestrian movement through pedestrian dynamic trajectory speed calculation, and provide important data support for subsequent prediction and control. Generating pedestrian dynamic trajectory prediction speed helps the system predict the future movement trajectory and behavior pattern of pedestrians more accurately. Regional arrival time prediction can help the system predict the time when pedestrians arrive at sub-areas of different lighting scenes and optimize the lighting control response speed. Generating sub-area arrival time of predicted trajectory helps the system adjust lighting brightness and regional coverage in real time according to pedestrian behavior, and improves the intelligent perception and response performance of the lighting system. Optimizing lighting delay parameters based on the predicted sub-area arrival time can help the system adjust lighting brightness and coverage in advance and realize intelligent lighting control. Generating pre-sensing lighting control strategy helps the system respond in advance according to predicted pedestrian behavior, and improves the intelligent perception and energy-saving effect of the lighting system. Strengthening transfer learning can help the system continuously optimize lighting control strategy and improve the system's intelligent perception and response ability to pedestrian behavior. Building an intelligent lighting sensing control model helps the system realize intelligent prediction and response to various pedestrian behavior scenarios and improve the sensing control performance of LED lighting. BRIEF DESCRIPTION OF THE DRAWINGS

[0067] Figure 1 The present invention is a schematic structural diagram of an induction control system of an induction-type LED lighting lamp. DETAILED DESCRIPTION

[0068] 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.

[0069] The present application example provides an induction control system for an induction-type LED lighting lamp. The execution subject of the induction control system for the induction-type LED lighting lamp includes but is not limited to: mechanical equipment, data processing platform, cloud server node, network upload device, etc. equipped with the system can be regarded as the general computing node of the present application, and the data processing platform includes but is not limited to: at least one of an audio and image management system, an information management system, and a cloud data management system.

[0070] See also Figure 1 The present invention provides an inductive control system for an inductive LED lighting lamp, wherein the inductive control system comprises a lighting scene module, an ambient light feature module, a multi-region lighting coordination module, a lighting delay optimization module, a movement trajectory prediction module and an inductive lighting control module:

[0071] The lighting scene module is used to: identify all LED lighting lamps in the area; calculate the node positions of all LED lighting lamps in the area one by one, and identify the usage scenes in the area to construct multiple LED lighting scene sub-areas;

[0072] The ambient light feature module is used to: obtain ambient light parameters of the scene sub-area; track the light space distribution of the ambient light parameters of the scene sub-area, and mine the ambient light state features to generate ambient light comprehensive state features;

[0073] The multi-region lighting coordination module is used to: perform dynamic light source output parameter adjustment and multi-region lighting coordination smoothing on multiple LED lighting scene sub-regions based on the comprehensive state characteristics of the ambient light, so as to generate multi-region lighting coordination control parameters;

[0074] The lighting delay optimization module is used to: collect pedestrian infrared sensing signals in real time; perform lighting threshold detection on pedestrian infrared sensing signals, and perform lighting delay optimization based on multi-region lighting collaborative control parameters to generate multi-region lighting delay optimization parameters;

[0075] The movement trajectory prediction module is used to: perform dynamic behavior analysis on pedestrian infrared sensing signals and perform multi-time point movement trajectory prediction, thereby generating a pedestrian dynamic prediction trajectory;

[0076] The inductive lighting control module is used to make advance inductive lighting control decisions on multi-zone lighting delay optimization parameters according to pedestrian dynamic prediction trajectories, and to perform enhanced transfer learning to build an intelligent lighting inductive control model.

[0077] By identifying all the LED lights in the area, the system of the present invention can accurately obtain the location information of the LED lighting equipment, and provide basic data support for subsequent control and adjustment. Accurate identification of LED lights helps the system to establish a spatial distribution model of LED lighting equipment, laying the foundation for subsequent intelligent control. Calculating the position of each LED light node and identifying the scene one by one helps the system understand the role and influence range of each lighting point, and provides support for fine control. Constructing LED lighting scene sub-areas helps to personalize the lighting needs of different areas, improve lighting effects and energy-saving effects. By acquiring ambient light parameters and tracking the spatial distribution of light, the system can realize dynamic perception and adjustment of ambient light, improve lighting effects and comfort. Mining the characteristics of ambient light status helps the system to better understand the changing laws of ambient light, and provide a more accurate reference basis for intelligent adjustment. Through the generation of lighting collaborative control parameters, the system can realize multiple Coordination and unified adjustment of regional lighting improves lighting uniformity and comfort, and realizes collaborative lighting control, which helps optimize the overall lighting effect, improves energy efficiency and user experience. Real-time collection of pedestrian infrared sensing signals helps the system perceive real-time crowd flow and provide real-time data support for intelligent lighting control. Through lighting threshold detection and delay optimization, the system can dynamically adjust lighting brightness and delay according to crowd flow, improve energy saving and safety. Dynamic behavior analysis and mobile trajectory prediction help the system accurately grasp the laws of crowd behavior and provide a more accurate basis for lighting control decisions. Generating dynamic predicted pedestrian trajectories helps the system predict the direction of crowd flow in advance and provide a more efficient response strategy for intelligent lighting control. Lighting control decisions based on dynamic predicted trajectories help the system realize intelligent and personalized lighting adjustment and improve user experience and comfort. Strengthening transfer learning can continuously optimize the intelligent lighting sensing control model and improve the intelligence level and adaptability of the system.

[0078] In the embodiment of the present invention, refer to Figure 1 , is a schematic diagram of the structure of an induction control system of an induction-type LED lighting lamp of the present invention. In this example, the induction control system of the induction-type LED lighting lamp includes:

[0079] The lighting scene module is used to: identify all LED lighting lamps in the area; calculate the node positions of all LED lighting lamps in the area one by one, and identify the usage scenes in the area to construct multiple LED lighting scene sub-areas;

[0080] In this embodiment, necessary equipment is prepared, including laser scanners, cameras, sensors (such as infrared, ultrasonic), etc., to ensure that the LED lights in the area can be accurately identified and recorded, and the target area is divided into multiple sub-areas to facilitate the gradual scanning and identification of LED lamps. A laser scanner or camera is used to scan the environment, and the position information of all LED lights in the area is recorded. The position information of the lamps is extracted from the image through image processing technology (such as edge detection and color recognition). Combined with sensor data, the existence of the lamps is confirmed, and the information of the identified LED lights (such as position, type, status, etc.) is stored in a database to form a preliminary list of lamps. The collected lamp position information is converted into a unified coordinate system (such as a Cartesian coordinate system or a polar coordinate system) for subsequent analysis. The node position of the lamp is calibrated for accuracy: multiple measurement data are averaged to eliminate errors, and a filtering algorithm (such as a Kalman filter) is applied to smooth the position data. The node position of each LED lamp is organized into a usable data format (such as JSON, CSV). For subsequent use, the processed LED lighting node location information is stored in the database to form a complete location information library of lamps. Different usage scenario characteristics are defined according to the functions and usage requirements of the area, such as work scenarios, leisure scenarios, channel scenarios, etc., and analyzed in combination with environmental data (such as light intensity, temperature, humidity, etc.) and user behavior data (such as traffic flow, activity type, etc.): Use data mining technology (such as cluster analysis, classification algorithm) to identify the usage scenarios in the area, and apply machine learning algorithms (such as decision trees, support vector machines) to classify the usage scenarios of different areas. Based on the analysis results, the LED lighting in the area is classified according to different usage scenarios: Specify the main usage scenarios for each sub-area, and record the relevant lamp information. According to the identified usage scenarios and corresponding lamps, the entire area is divided into multiple LED lighting scene sub-areas: Determine the boundaries, main functions and lighting requirements of each sub-area, and store the information of the constructed multiple LED lighting scene sub-areas (such as location, function, lamp distribution, etc.) in the database for subsequent lighting control and management.

[0081] The ambient light feature module is used to: obtain ambient light parameters of the scene sub-area; track the light space distribution of the ambient light parameters of the scene sub-area, and mine the ambient light state features to generate ambient light comprehensive state features;

[0082] In this embodiment, a suitable ambient light sensor (such as a photometer or a colorimeter) is selected to measure the ambient light parameters of the scene sub-area, including light intensity, color temperature, spectral distribution, etc. The ambient light sensor is installed in the scene sub-area to ensure that it can cover the entire area and avoid obstruction and interference. Ensure that the height and orientation of the sensor meet the measurement requirements, usually at the height and horizontal plane of the normal human eye. Configure the sampling frequency and measurement time period of the sensor to ensure that the ambient light parameters can be obtained in different time periods. Perform multiple measurements to ensure the accuracy and representativeness of the data. The measured ambient light parameters (light intensity, color temperature, etc.) are stored in a database to form an ambient light parameter data set for the scene sub-area. Select a suitable ray tracing algorithm, such as Monte Carlo ray tracing, radiometry, etc., to simulate the propagation and distribution of light in space. Establish a three-dimensional model of the scene sub-area, including information such as the position, shape, and material of the lamp, so as to perform ray tracing calculations. Use computer graphics software (such as Blender, 3dsMax, etc.) or dedicated optical simulation software (such as Radiance) to create the model. Use the selected ray tracing algorithm to simulate the illumination of the scene sub-area: starting from the light source, track the propagation of light in space, and record the interaction between light and the surface of the object (such as reflection, refraction, absorption, etc.). Calculate the light intensity and color temperature of each point to generate a light spatial distribution map. Store the results of ray tracing (light distribution map, intensity distribution data, etc.) in the database for subsequent analysis and feature mining. Define indicators of ambient light state characteristics, including average light intensity, light uniformity, color temperature variation range, spectral distribution characteristics, etc. Perform statistical analysis on the acquired ambient light parameters and light spatial distribution data: calculate various characteristic indicators and identify the overall state of ambient light. Use data mining techniques (such as cluster analysis and principal component analysis) to mine potential ambient light characteristics. Summarize the analysis results and generate ambient light comprehensive state characteristics: integrate various characteristic indicators into a comprehensive indicator to facilitate subsequent lighting control decisions. Store the generated ambient light comprehensive state characteristics in the database for subsequent application and reference.

[0083] The multi-region lighting coordination module is used to: perform dynamic light source output parameter adjustment and multi-region lighting coordination smoothing on multiple LED lighting scene sub-regions based on the comprehensive state characteristics of the ambient light, so as to generate multi-region lighting coordination control parameters;

[0084] In this embodiment, the comprehensive state characteristic data of ambient light is extracted from the database, including the light intensity, color temperature, and light uniformity of each sub-area, the ambient light characteristics of each sub-area are evaluated, and the lighting requirements of each area are identified: the difference between the actual light intensity and the target light intensity (set according to the application scenario) is compared to determine the area with insufficient light, excessive light, or inappropriate color temperature. According to the evaluation results, a priority is set for each sub-area so that the area with the highest lighting demand is given priority during adjustment. According to the comprehensive state characteristics of the ambient light, the target light source output parameters of each sub-area are set, including the desired light intensity and color temperature, and a suitable control algorithm is selected for dynamic adjustment: PID control algorithm: used to adjust the light source output in real time, and adjust according to the error between the current light and the target light. Fuzzy control: when the ambient light changes are uncertain, fuzzy logic is used to adjust the output, calculate the output parameters of the LED lamps in each sub-area that need to be adjusted, and generate adjustment instructions according to the calculation results to update the brightness and color temperature settings of each LED lamp. Design a smoothing algorithm for multi-zone lighting collaborative control to avoid sudden changes: Use linear interpolation or Bezier curves to smooth the adjustment process to ensure that the lighting changes between adjacent areas are natural and smooth, and apply the smoothing algorithm in the generated adjustment instructions: Ensure that the light intensity changes between adjacent areas remain consistent to avoid sudden brightness changes, integrate the adjusted output parameters into multi-zone lighting collaborative control parameters to form a unified control strategy, and upload the generated multi-zone lighting collaborative control parameters to the lighting control system: Use DMX, DALI or other lighting control protocols to transmit new parameters to each LED lamp, monitor the effect after implementation, and collect feedback on the lighting status of each area: Use ambient light sensors to monitor light intensity and color temperature in real time to ensure that the adjustment achieves the expected effect, and make necessary adjustments based on real-time feedback results to ensure that the lighting effect meets user needs and preset standards: If the lighting in some areas still does not meet the requirements, recalculate the output parameters and adjust them, and record the final lighting status and adjustment parameters in the database for subsequent analysis and optimization.

[0085] The lighting delay optimization module is used to: collect pedestrian infrared sensing signals in real time; perform lighting threshold detection on pedestrian infrared sensing signals, and perform lighting delay optimization based on multi-region lighting collaborative control parameters to generate multi-region lighting delay optimization parameters;

[0086] In this embodiment, an infrared sensor or a motion sensor is installed in the target area to monitor the dynamics of pedestrians in real time, ensure that the installation position of the sensor can cover the entire area and avoid blind spots, configure the sampling frequency and sensitivity of the infrared sensor to ensure that the signal of pedestrian movement can be accurately captured, set the data format and storage method to ensure that the collected signal can be convenient for subsequent analysis, start the sensor, monitor and record the infrared sensing signal when pedestrians pass by in real time, transmit the collected signal data (such as signal strength, timestamp, etc.) to the data processing system in real time, determine the lighting threshold, and set a suitable signal strength threshold according to different scenarios and needs: for example, set the signal strength threshold when pedestrians approach to trigger the lighting system, process the infrared sensing signal collected in real time, and extract valid data: use a filtering algorithm (such as a low-pass filter) to remove noise to ensure the accuracy of the signal, compare the processed signal with the set threshold to determine whether the trigger condition is met: if the signal strength exceeds the set threshold, record the time and related data of the triggering event, and store the record of the triggering event (such as timestamp, signal strength, etc.) in the data The delay calculation standard of the lighting response is determined in the database for subsequent delay optimization analysis, which is usually the difference between the time of the trigger signal and the actual response time of the lamp. The collected trigger event data is analyzed to calculate the delay of each event. According to the delay analysis results, the lighting control strategy is adjusted: If the response delay in some areas is too long, consider optimizing the transmission path of the control signal or adjusting the response mechanism of the lamp, generate new multi-area lighting delay optimization parameters, ensure that the system can respond to the arrival of pedestrians faster, store the optimized delay parameters in the database, and facilitate subsequent lighting control decisions and monitoring. The generated multi-area lighting delay optimization parameters are uploaded to the lighting control system, and a new control strategy is implemented. The infrared sensing signals and lighting responses when pedestrians pass by are continuously monitored to ensure the effectiveness of the optimization measures. The feedback mechanism is used to ensure that the system adjusts the lighting strategy in real time according to the new data. According to the feedback results in actual operation, necessary adjustments are made to ensure that the response time of the lighting system is always kept within a reasonable range. The final lighting delay optimization parameters and operating status are recorded in the database for subsequent system evaluation and optimization.

[0087] The movement trajectory prediction module is used to: perform dynamic behavior analysis on pedestrian infrared sensing signals and perform multi-time point movement trajectory prediction, thereby generating a pedestrian dynamic prediction trajectory;

[0088] In this embodiment, pedestrian infrared sensing signal data is extracted from the database, including timestamp, signal strength, location and other information. Data is sorted to ensure that the data format is unified and complete. Features are extracted from pedestrian signal data to identify key indicators of pedestrian dynamic behavior: Movement speed: Calculate the movement speed of pedestrians in different time periods. Stay time: Identify the length of time pedestrians stay in a specific area. Activity mode: Based on the trajectory data of pedestrian movement, identify common activity patterns (such as walking, staying, etc.). Use machine learning methods (such as cluster analysis, classification algorithms) to build dynamic behavior models:

[0089] Input the extracted features into the model to identify typical behavior patterns and changing trends. For example, use K-means clustering to analyze different movement patterns, or use the random forest algorithm to classify behaviors. According to the constructed model, analyze the dynamic behavior status of pedestrians in real time, and record the current behavior type and possible movement trend. Organize historical trajectory data, including pedestrian location information, timestamps, and corresponding dynamic behavior status. Ensure the continuity and accuracy of data for effective prediction. Select a suitable prediction model for multi-time point movement trajectory prediction: Time series model: such as ARIMA or LSTM (Long Short-Term Memory Network), which is suitable for processing time series data prediction. Regression analysis: Use regression models (such as linear regression) to predict future positions. Use historical data to train the selected prediction model: Take the historical trajectory and corresponding behavior features as input, and learn the movement rules of pedestrians through the model. Cross-validate the model and adjust the parameters to improve the prediction accuracy. In the real-time system, use the trained model to predict the future trajectory of pedestrians: Input the current dynamic behavior features and the most recent movement trajectory to generate future movement trajectory points. Generate predicted trajectories for multiple time points, usually including short-term (such as within 1 minute) and medium-term (such as within 10 minutes) trajectory estimates. Record the prediction results, including the location information and timestamp at each time point. Store the generated pedestrian dynamic prediction trajectory data in the database for subsequent analysis and application. Includes the predicted position, time and corresponding behavior state at each time point. Use the predicted trajectory for applications such as intelligent lighting control, security monitoring, and navigation systems: for example, adjust the lighting intensity based on the predicted trajectory to improve the perceived comfort of pedestrians. In security monitoring, the predicted trajectory can help the system identify potential risks in advance. Establish a feedback mechanism to monitor the difference between the actual movement trajectory of pedestrians and the predicted results in real time: if there is a large deviation between the prediction and the actual trajectory, retrain and adjust the model to improve the accuracy of future predictions.

[0090] The inductive lighting control module is used to make advance inductive lighting control decisions on multi-zone lighting delay optimization parameters according to pedestrian dynamic prediction trajectories, and to perform enhanced transfer learning to build an intelligent lighting inductive control model.

[0091] In this embodiment, the generated pedestrian dynamic prediction trajectory data is extracted from the database, including the location information and timestamp of each time point, and the extracted prediction trajectory is analyzed to identify the movement pattern and expected arrival time of the pedestrian: determine the arrival time of the pedestrian in each area to make a decision for lighting control, obtain multi-area lighting delay optimization parameters, which define the lighting response time and expected brightness of each area, associate the predicted trajectory with the delay optimization parameters for subsequent use, and select a suitable lighting control algorithm (such as rule-based control, fuzzy logic control or PID control) to achieve pre-sensing lighting decision: ensure that the selected algorithm can dynamically adjust the lighting according to the pedestrian arrival time. Dynamically adjust lighting parameters Generate lighting control decisions based on pedestrian dynamic prediction trajectory and delay optimization parameters: Determine the lighting start time and intensity for each area. For example, if the predicted arrival time is T minutes, turn on the lighting at T-1 minutes to ensure sufficient lighting when pedestrians arrive. Adjust lighting intensity and color temperature according to regional characteristics (such as corridors, rest areas, etc.), collect historical lighting control data, including pedestrian behavior, lighting response, environmental conditions, etc., for model training, organize data to ensure consistent format for subsequent use, and select appropriate reinforcement learning algorithms (such as DeepQ-Learning, ProximalPolicyOptimization, etc.). ion, etc.), build intelligent lighting sensor control models: ensure that the selected algorithm can handle the complexity and dynamic changes of multiple areas, use the collected historical data to train the reinforcement learning model: train the model in a simulated environment, optimize the lighting control strategy through a continuous trial and error process, define the reward mechanism to ensure that the model can learn effective strategies, for example, give positive rewards when pedestrians successfully reach the predetermined area and the lighting is appropriate, apply the trained model to new environments or different scenarios to accelerate adaptation and optimization: use existing knowledge to speed up the learning process in new scenarios, adjust model parameters to adapt to new ambient light conditions and pedestrian behavior, and test intelligent lighting sensors in actual environments The effect of the model should be controlled: monitor the matching of pedestrian arrival time and lighting on time, evaluate the effectiveness of lighting control, further optimize the model according to the test results, ensure its applicability and effectiveness in different environments, upload the generated lighting control decision and reinforcement learning model to the lighting control system, implement new control strategies, continuously monitor pedestrian dynamics and lighting response, obtain real-time feedback on system operation effects, adjust the control strategy according to the feedback data to improve the adaptability of the system, record the final lighting control results and operating status in the database for subsequent analysis and optimization, evaluate the effectiveness of the lighting control strategy, and ensure continuous improvement in practical applications.

[0092] In this embodiment, the lighting scene module is used to: identify all LED lighting lamps in the area; calculate the node positions of all LED lighting lamps in the area one by one, and identify the usage scenes in the area to construct multiple LED lighting scene sub-areas, specifically for:

[0093] Identify all LED lights in the area;

[0094] Calculating the position of each LED lighting node of all LED lighting lamps in the area one by one to generate the spatial position coordinates of each LED node;

[0095] Perform spatial layout analysis on the spatial position coordinates of each LED node to generate LED node spatial layout data;

[0096] Identify the usage scenarios in the region based on the spatial layout data of the LED nodes, thereby obtaining multiple regional usage scenarios;

[0097] Based on multiple regional usage scenarios, regional scene segmentation is performed on all LED lighting lamps in the area to construct multiple LED lighting scene sub-areas.

[0098] In this embodiment, the area to be identified can be determined by using a map or CAD drawing to clearly define the area boundary, using appropriate identification tools such as LiDAR, photogrammetry, computer vision (such as a deep learning model), etc., selecting appropriate sensors (such as cameras, sensor arrays) for data collection, performing data collection within the delimited area, recording images or point cloud data of all LED lights in the area, using image processing algorithms (such as YOLO, TensorFlowObjectDetection, etc.) to process the collected data, identifying all LED lights, and storing the identified lamp information (such as location, model) in a database. Determine the coordinate system of the area (such as Cartesian coordinate system or polar coordinate system) for position calculation, and perform spatial position calculation for each identified LED lighting fixture, which usually includes the following steps: Use the conversion relationship between the coordinates in the image and the actual coordinates, use sensor data (such as depth information) to calculate the three-dimensional coordinates of each lamp, store the spatial position coordinates (such as X, Y, Z) of each LED lamp in the database, form a coordinate list of the LED node, collect the spatial position coordinates of all LED lamps, prepare for layout analysis, and use spatial analysis tools (such as GIS software, MATLAB, Python's SciPy library, etc.) to perform spatial layout analysis on LED nodes: Calculate The distance between LED lights, identify the distribution density of lamps, generate a spatial layout map, display the distribution of LED lights, store the generated LED node spatial layout data (such as distribution map, density map) in a structured data format (such as JSON, CSV or database), determine the criteria for identifying usage scenarios, such as regional functions (office, leisure, transportation, etc.), time periods, user behavior patterns, etc. Based on the LED node spatial layout data, combined with environmental information in the area (such as traffic flow, activity type), use scenario identification: Use clustering algorithms (such as K-means, DBSCAN) to classify areas, identify different usage scenarios, analyze data, and identify multiple areas The usage scenarios of the LED lighting are identified, and the identified multiple regional usage scenarios are stored in a structured data format, including scene names, regional descriptions, related lamps and other information. The standards for regional scene segmentation are defined. For example, based on the functions of the usage scenarios, the layout and quantity of LED lamps, etc., the LED lighting lamps are segmented into regional scenes according to the identified multiple regional usage scenarios: LED lamps of the same usage scenario are divided into the same sub-region to form multiple LED lighting scene sub-regions. The segmentation algorithm (such as image segmentation and regional growing algorithm) is used to ensure the rationality of each scene sub-region. The information of the constructed multiple LED lighting scene sub-regions is stored in a database, including the lamp configuration of each sub-region, scene description and other information.

[0099] In this embodiment, the ambient light feature module is used to: obtain the ambient light parameters of the scene sub-area; track the light space distribution of the ambient light parameters of the scene sub-area, and mine the ambient light state features to generate the ambient light comprehensive state features, which are specifically used for:

[0100] Detecting ambient light parameters of multiple LED-illuminated scene sub-areas based on a light sensor to obtain ambient light parameters of the scene sub-areas;

[0101] The ambient light parameters of the scene sub-areas are averaged to calculate the ambient light intensity, and the average ambient light intensity of each sub-area is generated;

[0102] Performing light space distribution tracing on the ambient light parameters of the scene sub-area to obtain light space distribution tracing data;

[0103] Perform light distribution change evolution on the light space distribution tracking data to generate light space distribution change characteristics;

[0104] The ambient light state characteristics are mined based on the average ambient light intensity and light spatial distribution change characteristics of each sub-area to generate the comprehensive ambient light state characteristics.

[0105] In this embodiment, a suitable light sensor (such as a photoresistor, a photoelectric sensor, a illuminance meter, etc.) is selected to ensure that it can accurately measure the ambient light parameters under different lighting conditions. A light sensor is installed in each LED lighting scene sub-area to ensure that the sensor position can represent the lighting conditions of the area. The sensor should avoid being blocked to ensure that it can capture the changes in ambient light in real time. The sensor is started to monitor the ambient light parameters in real time, and the recorded data includes light intensity (in lux), color temperature, spectral distribution, etc. The data collection cycle can be set to every minute or every hour to capture the changes in ambient light, and the collected ambient light parameter data is recorded. The data is stored in a database or file system to ensure the integrity and traceability of the data. The ambient light parameter data of each sub-area is extracted from the database and prepared for average calculation. The ambient light parameters of each sub-area are averaged: using a simple averaging method, the light intensity data in each sub-area is added and divided by the number of data points. The calculated average ambient light intensity of each sub-area is recorded in the database for subsequent analysis. An appropriate ray tracing model (such as ray tracing algorithm, Monte Carlo method, etc.) is selected to simulate the distribution of light in space. The lighting parameters and spatial layout information of each sub-area are input into the ray tracing model. In the model, ensure that the model can take into account the position of the light source, reflection characteristics and the influence of obstacles, run the ray tracing model, simulate the propagation and distribution of light in the sub-area, capture the distribution data of light in space, including light intensity distribution, illuminance map, etc., store the traced light space distribution data in a structured format (such as JSON, CSV or database) for subsequent analysis, select appropriate analysis tools (such as MATLAB, Python's NumPy and Matplotlib library) for data analysis, and perform change evolution analysis on the light space distribution tracking data: identify the change pattern of light distribution through time series analysis, calculate the light intensity change at different time points, identify trends and anomalies, record the light space distribution change characteristics in the database, form a light distribution change characteristic report, define the standards for mining ambient light state characteristics, including average ambient light intensity, light distribution change characteristics, etc., analyze the average ambient light intensity and light space distribution change characteristics of each sub-area: use machine learning algorithms (such as cluster analysis, principal component analysis, etc.) to mine the comprehensive state characteristics of ambient light, generate feature data sets, extract key feature indicators, and store the generated ambient light comprehensive state characteristics in a structured data format to ensure subsequent visualization and analysis.

[0106] In this embodiment, the multi-region lighting coordination module is used to: perform dynamic light source output parameter adjustment and multi-region lighting coordination smoothing on multiple LED lighting scene sub-regions based on the comprehensive state characteristics of the ambient light, so as to generate multi-region lighting coordination control parameters, specifically for:

[0107] Perform regional lighting demand analysis on multiple LED lighting scene sub-areas to obtain the lighting demand characteristics of each scene sub-area;

[0108] Calculate the regional lighting brightness based on the lighting demand characteristics of each scene sub-region to generate a regional lighting demand brightness value;

[0109] Dynamically adjusting the light source output parameters of multiple LED lighting scene sub-areas based on the comprehensive state characteristics of the ambient light, thereby obtaining the light source output characteristic parameters of each sub-area;

[0110] Multi-region lighting collaborative smoothing is performed according to the lighting demand characteristics of each scene sub-region and the light source output characteristic parameters of each sub-region to generate multi-region lighting collaborative control parameters.

[0111] In this embodiment, the standards for lighting demand analysis are determined, including lighting type (such as reading, leisure, work, etc.), sight requirements, spatial functions, etc., and user activity data, usage frequency, spatial characteristics (such as area, ceiling height), etc. of each scene sub-area are collected. Questionnaires or sensor data are used to collect user preferences and needs for lighting, and the collected data are analyzed to identify the lighting demand characteristics of each scene sub-area: quantitative analysis methods (such as statistical analysis, regression analysis) are used to evaluate the lighting needs of different scenes, and demand characteristic indicators are generated, such as necessary lighting intensity (lux), color temperature requirements, etc. The lighting demand characteristics of each scene sub-area are stored in a database for subsequent calculation and analysis, and the standards for brightness calculation are determined. Considering factors such as ambient light, target brightness, and lighting mode, a suitable calculation model (such as IESNA standard, CIE standard) is selected to calculate the regional lighting demand brightness value, and the regional lighting brightness calculation is performed for each scene sub-area: the required lighting brightness value is calculated according to the lighting demand characteristics and spatial layout, and the required luminous flux and illuminance are calculated using formulas to ensure that the scene characteristic requirements are met, based on the previously generated environment The comprehensive state characteristics of light are analyzed to analyze the impact of ambient light on different scene sub-areas, design a light source output parameter adjustment model, consider ambient light changes, user needs and lighting characteristics, determine adjustment parameters, such as light source brightness, color temperature and dimming method, and adjust the light source output characteristic parameters for each sub-area: according to the ambient light state characteristics and regional lighting needs, adjust the output brightness and color temperature of the LED lamp in real time, use control systems (such as DMX, DALI, etc.) to implement adjustments to ensure that the output parameters meet the requirements, and record the light source output characteristic parameters of each sub-area in the database for subsequent optimization and control. Determine the standards for multi-area lighting collaborative control, including brightness balance, user experience and energy-saving goals between areas, design a multi-area lighting collaborative control model, consider the lighting demand characteristics and light source output characteristic parameters of each area, and perform multi-area lighting collaborative smoothing according to the lighting demand characteristics and light source output characteristic parameters of each scene sub-area: use algorithms (such as fuzzy control, PID control) to calculate the coordination parameters between areas to ensure a smooth transition of the overall lighting effect, adjust the light source output of different areas, and ensure the balance of the overall lighting effect under changing environmental conditions.

[0112] In this embodiment, the specific steps of dynamically adjusting the light source output parameters of multiple LED lighting scene sub-areas based on the comprehensive state characteristics of the ambient light to obtain the light source output characteristic parameters of each sub-area include:

[0113] Based on the comprehensive state characteristics of ambient light, the optimal light source color temperature analysis is performed on multiple LED lighting scene sub-areas to generate the optimal light source color temperature parameters for each scene sub-area;

[0114] Calculate the color temperature difference between regions for the optimal light source color temperature parameters of each scene sub-region, so as to obtain the color temperature difference data between sub-regions;

[0115] Calculate the spatial color temperature uniformity based on the color temperature difference data between the sub-areas, thereby generating uniform light source color temperature output parameters;

[0116] Performing a light source illumination frequency analysis on the illumination demand characteristics of each scene sub-area to obtain a light source illumination frequency parameter for each scene sub-area;

[0117] Dynamic light source output parameter adjustment is performed on the uniform light source color temperature output parameter and the light source illumination frequency parameter of each scene sub-area, thereby obtaining the light source output characteristic parameter of each sub-area.

[0118] In this embodiment, the comprehensive state characteristics of the ambient light of each scene sub-area are collected, including information such as the current light intensity, color temperature, and usage scenarios. The optimal light source color temperature standard is formulated according to different usage scenarios (such as reading, work, leisure, etc.), and Kelvin (K) is usually used as the unit. The optimal light source color temperature parameter is calculated for each scene sub-area: the current ambient light color temperature is compared with the predefined optimal color temperature standard, and the closest value is selected as the optimal color temperature parameter of each sub-area. The current color temperature data of each scene sub-area is collected, including the optimal color temperature parameter. The color temperature difference between the optimal light source color temperature parameters of each scene sub-area is calculated: color temperature difference = |current color temperature−optimal color temperature|. The calculated color temperature difference data between the sub-areas is stored in a database to form a color temperature difference report. The calculation standard of color temperature uniformity is determined, which usually includes a uniformity threshold (such as ±100K) and an evaluation method. The spatial color temperature uniformity is calculated based on the color temperature difference data between the sub-areas. The standard deviation of the color temperature difference between different regions is used to generate uniform light source color temperature output parameters. The lighting demand characteristic data of each scene sub-region is collected, including frequency of use, time period, activity type, etc. The light source lighting frequency analysis is performed on the lighting demand characteristics of each scene sub-region: the number of times the light source is turned on and off in different time periods is counted, and the average lighting frequency is calculated. Data analysis tools (such as Python's Pandas library) are used for frequency statistics. The light source lighting frequency parameters of each scene sub-region are stored in the database for subsequent adjustment. A light source output parameter adjustment model is designed. The adjustment parameters, such as the brightness, color temperature and dimming mode of the light source, are determined by combining the uniform light source color temperature output parameters and the light source lighting frequency parameters. Dynamic light source output parameter adjustment is performed for each sub-region: the output parameters of the LED lamp are adjusted in real time according to the uniform light source color temperature output parameters and the light source lighting frequency parameters. The control system (such as DMX, DALI, etc.) is used to implement the adjustment to ensure that the output parameters meet the requirements.

[0119] In this embodiment, the lighting delay optimization module is used to: collect pedestrian infrared sensing signals in real time; perform lighting threshold detection on pedestrian infrared sensing signals, and perform lighting delay optimization to generate multi-region lighting delay optimization parameters, which are specifically used to:

[0120] Collect pedestrian infrared sensing signals in real time; perform environmental filtering and noise reduction on pedestrian infrared sensing signals to obtain environmental noise-reduced infrared sensing signals;

[0121] Calculate the time series signal strength of the environmental noise reduction infrared sensing signal to generate a time series signal strength curve;

[0122] Perform lighting threshold detection on the timing signal strength curve based on the preset infrared sensing parameter threshold, and when the preset infrared sensing parameter threshold is not less than the timing signal strength, it is marked as the sensing lighting time point;

[0123] The lighting delay is optimized through multi-zone lighting collaborative control parameters based on the sensing lighting time point to generate multi-zone lighting delay optimization parameters.

[0124] In this embodiment, a suitable infrared sensor (such as a passive infrared sensor PIR or a thermal imaging sensor) is selected to ensure that it can detect pedestrians in real time in the target area. The infrared sensor is installed in an appropriate position to ensure that it covers the area to be monitored and avoids obstruction and interference. The data acquisition frequency of the sensor is configured to ensure that the infrared signal of pedestrians passing by can be obtained in real time. A microcontroller (such as Arduino, RaspberryPi, etc.) or a data acquisition device is used to connect the sensor to read the signal. The collected infrared signal is promptly saved in a data storage system (such as a database or a file system) for subsequent processing. A suitable filtering algorithm, such as a low-pass filter, a Kalman filter, or a median filter, is selected to remove environmental noise from the infrared signal. The infrared sensing signal collected in real time is subjected to environmental filtering processing: the filtering algorithm is applied to the collected signal to remove noise and retain valid signals, and an environmental noise reduction infrared sensing signal is generated. The signal comparison before and after the processing is recorded, and the processed environmental noise reduction infrared sensing signal is stored in a database for subsequent analysis. A time series signal is generated according to the environmental noise reduction infrared sensing signal to ensure that each time point has a corresponding signal strength value. The intensity of the environmental noise reduction infrared sensing signal is calculated: a suitable algorithm (such as a maximum value) is used. , average value, etc.), calculate the signal strength at each time point, generate a time series signal strength curve, draw a graph of signal strength changing over time, store the time series signal strength curve data in a database for subsequent analysis and visualization, preset infrared sensing parameter thresholds, usually based on historical data or environmental requirements (for example, set a signal strength threshold), perform lighting threshold detection on the time series signal strength curve: traverse the signal strength curve to determine whether the signal strength at each time point meets the preset threshold, when the signal strength is greater than or equal to the threshold, mark it as a sensing lighting time point, store the identified sensing lighting time point in the database, form a time point list for subsequent processing, determine the parameters for lighting delay optimization, including delay time, sensing lighting duration, and inter-regional collaborative control strategy, design a delay optimization model based on sensing lighting time points and multi-region lighting collaborative control parameters: analyze the lighting needs of different areas to ensure the coordination of light source output between sensing lighting points, perform lighting delay optimization through multi-region lighting collaborative control parameters according to sensing lighting time points: adjust the lighting on time and duration of each area to ensure sufficient light when pedestrians pass by, and store the generated multi-region lighting delay optimization parameters in the database for subsequent implementation and optimization.

[0125] In this embodiment, the specific steps of optimizing the lighting delay by using the multi-zone lighting collaborative control parameters based on the sensing lighting time point to generate the multi-zone lighting delay optimization parameters are:

[0126] Based on the sensing lighting time point, the LED lighting lamps are dynamically triggered through multi-zone lighting collaborative control parameters, and the dynamic lighting response parameters are obtained in real time;

[0127] calculating a timestamp of the lighting response based on the dynamic lighting response parameter;

[0128] Calculating the response delay of the timestamp of the lighting response according to the sensing lighting time point, thereby obtaining a lighting response delay value;

[0129] The lighting delay optimization is performed on the multi-zone lighting collaborative control parameters according to the lighting response delay value to generate the multi-zone lighting delay optimization parameters.

[0130] In this embodiment, previously stored sensing lighting time points are read from the database. These time points are detected based on the infrared signal strength. The coordinated control parameters of dynamic lighting are determined, including the brightness target, color temperature requirement and response time of each area. When the sensing lighting time point is detected, the LED lighting in the corresponding area is dynamically triggered through the control system (such as DMX, DALI or intelligent lighting system): the brightness, color temperature and opening state of the lamp are adjusted in real time to ensure that the lighting meets the current needs. When the lighting is triggered, the response parameters of the LED lamp, such as the opening time, brightness change, color temperature change, etc., are monitored and recorded in real time. When the LED lighting is triggered, the timestamp of the triggering event is recorded. This timestamp represents the exact moment when the lamp is activated. The recorded timestamp data is formatted into a unified time format (such as ISO8601) for subsequent analysis. The timestamp data is stored in the database and associated with the sensing lighting time point to form a complete trigger record. The calculation standard of the response delay is defined. It is usually the difference between the response timestamp and the sensing lighting time point. The following calculation is performed for each sensing lighting time point and the corresponding response timestamp: response delay = response timestamp − sensing lighting time point. The calculated result is the delay time of each response, usually in milliseconds. The response delay value is analyzed to determine whether the response time of the lighting system needs to be optimized. A threshold is set to determine whether the delay is acceptable. The multi-zone lighting collaborative control parameters are adjusted according to the response delay value to ensure that the lamps in each area can respond to the sensing time point faster. Possible optimization measures include adjusting the signal transmission delay, optimizing the control algorithm, or updating the hardware configuration. Update parameters in the control system to reduce response delay. Reconfigure the control strategy of the LED lamp to ensure that the preset brightness and color temperature can be quickly reached near the sensing time point. After the optimization is implemented, re-perform the dynamic lighting sensing trigger test to verify whether the response delay meets the expected optimization goal. The optimized parameters and verification results are recorded in the database for subsequent reference and further optimization.

[0131] In this embodiment, the movement trajectory prediction module is used to: perform dynamic behavior analysis on pedestrian infrared sensing signals and perform multi-time point movement trajectory prediction, thereby generating a pedestrian dynamic prediction trajectory, specifically for:

[0132] Perform signal strength change analysis on the environmental noise reduction infrared sensing signal to generate sensing signal strength change data;

[0133] Evolving the pedestrian movement route based on the sensing signal strength change data, thereby generating the pedestrian movement route;

[0134] Calculate the length of time a pedestrian stays in a certain area based on their movement route to obtain the length of time they stay in the behavior area;

[0135] Perform time-series movement position recognition on the pedestrian's moving route to obtain the pedestrian's time-series movement position;

[0136] Perform dynamic behavior analysis on the duration of stay in the behavior area and the temporal movement position of pedestrians to generate dynamic behavior feature data;

[0137] The dynamic behavior feature data is used to predict the multi-time point movement trajectory to generate the pedestrian dynamic prediction trajectory.

[0138] In this embodiment, the signal strength at each time point is analyzed for changes: the increase or decrease of the signal strength is calculated, and the difference method is used (such as calculating the strength difference between adjacent time points): change = current strength - previous strength, the change value is recorded, and the sensing signal strength change data is generated. The sensing signal strength change data is used in combination with the trigger time of the infrared sensing signal to determine the time point when the pedestrian passes by, and the movement mode of the pedestrian is identified by analyzing the signal strength change data: when the signal strength change reaches a preset threshold, the specific location where the pedestrian passes is recorded, and the pedestrian movement route is generated using an interpolation method or a trajectory smoothing algorithm (such as a B-spline curve), and the generated pedestrian movement route data is stored in a database to form a pedestrian trajectory record, and the specific area where the pedestrian stays (such as an area with a small signal strength change) is identified based on the pedestrian movement route, and the pedestrian's stay time in each stay area is counted: the entry and exit time of the stay area is calculated by the timestamp, and the stay time = exit time - entry time, and the pedestrian movement route data is used to sort out the pedestrian position corresponding to each time point, and the pedestrian Perform time series analysis on the moving route and extract the specific location at each time point: use the timestamp to match the location data to form a time series moving location list, store the pedestrian time series moving location data in the database for subsequent analysis, define the indicators of dynamic behavior characteristics, including dwell time, moving speed, frequent areas, etc., and analyze according to the dwell time of the behavior area and the pedestrian time series moving location: use statistical analysis methods (such as cluster analysis, trend analysis) to identify different behavior patterns, generate dynamic behavior feature data, such as frequent activity areas, average dwell time, etc., store the dynamic behavior feature data in the database for subsequent prediction and analysis, select a suitable prediction model (such as linear regression, ARIMA, LSTM, etc.) for trajectory prediction, use the dynamic behavior feature data and pedestrian time series moving location data as input, prepare for trajectory prediction, and use the selected prediction model to predict the future moving trajectory: input the current dynamic behavior feature data, calculate the future moving location, generate the pedestrian dynamic prediction trajectory, and identify the possible moving path and stay area.

[0139] In this embodiment, the sensing lighting control module is used to make pre-sensing lighting control decisions on multi-zone lighting delay optimization parameters according to pedestrian dynamic prediction trajectories, and perform enhanced transfer learning to build an intelligent lighting sensing control model, which is specifically used to:

[0140] Calculate the moving trajectory speed of the pedestrian's dynamic predicted trajectory to generate the pedestrian's dynamic trajectory predicted speed;

[0141] Predicting the arrival time of multiple LED lighting scene sub-areas based on the predicted speed of pedestrian dynamic trajectories, thereby generating the sub-area arrival time of the predicted trajectory;

[0142] Pre-sensing lighting control decisions are made on multi-region lighting delay optimization parameters based on the sub-region arrival times of the predicted trajectories to generate pre-sensing lighting control strategies;

[0143] Strengthen transfer learning of pre-sensing lighting control strategies and build intelligent lighting sensing control models.

[0144] In this embodiment, pedestrian dynamic predicted trajectory data is extracted from the database, including the position and timestamp of each time point. For each trajectory, the pedestrian's moving speed is calculated: speed = position change / time change, where the position change is the distance between two adjacent positions (Euclidean distance can be used), and the time change is the corresponding time difference. According to the pedestrian dynamic trajectory predicted speed and the current time, the time for the pedestrian to arrive at each LED lighting scene sub-area is calculated: for each target area, the formula: arrival time = current time + (target area distance / predicted speed) is used to determine the strategy standards for pre-sensing lighting control, including response time, lighting intensity and color temperature, etc. Based on the arrival time of the sub-area of ​​the predicted trajectory, a pre-sensing lighting control strategy is formulated: the lighting start time is set in advance according to the arrival time to ensure that the pedestrian has sufficient lighting when arriving. For example, if the pedestrian is expected to arrive at a certain area after T minutes, the lighting intensity is increased before T minutes. Historical data is collected, including Including pedestrian behavior, lighting control response, ambient light conditions, etc., as the data set for model training, select appropriate reinforcement learning algorithms (such as DeepQ-Learning, ProximalPolicyOptimization, etc.) to build an intelligent lighting sensing control model, and use reinforcement learning frameworks (such as TensorFlow, PyTorch) to train the model: use the pre-sensing lighting control strategy as the initial strategy, conduct multiple attempts and optimizations, and gradually adjust the model parameters to improve accuracy and response speed by simulating behaviors under different scenarios and conditions. Apply the trained model to new environments and scenarios to optimize the intelligent lighting control strategy: use transfer learning to use existing knowledge to accelerate learning and adaptation to new scenarios, test the intelligent lighting sensing control model in a real environment, verify its effect, and further optimize and adjust the model based on the test results to ensure its applicability and effectiveness in different environments.

[0145] Therefore, the embodiments should be regarded as illustrative and non-restrictive from all points, and the scope of the present invention is limited by the appended claims rather than the above description, and it is therefore intended that all changes falling within the meaning and range of equivalent elements of the application documents are included in the present invention.

[0146] The above is only a specific embodiment of the present invention, so that those skilled in the art can understand or implement the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features invented herein.

Claims

1. An induction control system for an induction LED lighting lamp, characterized in that: The induction control system of the induction LED lighting lamp includes a lighting scene module, an ambient light feature module, a multi-region lighting coordination module, a lighting delay optimization module, a movement trajectory prediction module and an induction lighting control module: The lighting scene module is used to: identify all LED lighting lamps in the area; calculate the node positions of all LED lighting lamps in the area one by one, and identify the usage scenes in the area to construct multiple LED lighting scene sub-areas; The ambient light feature module is used to: obtain ambient light parameters of the scene sub-area; track the light space distribution of the ambient light parameters of the scene sub-area, and mine the ambient light state features to generate the ambient light comprehensive state features; The multi-region lighting coordination module is used to: perform dynamic light source output parameter adjustment and multi-region lighting coordination smoothing on multiple LED lighting scene sub-regions based on the comprehensive state characteristics of the ambient light, so as to generate multi-region lighting coordination control parameters; The lighting delay optimization module is used to: collect pedestrian infrared sensing signals in real time; Perform lighting threshold detection on pedestrian infrared sensing signals, and optimize lighting delay based on multi-zone lighting collaborative control parameters to generate multi-zone lighting delay optimization parameters; The movement trajectory prediction module is used to: perform dynamic behavior analysis on pedestrian infrared sensing signals and perform multi-time point movement trajectory prediction, thereby generating a pedestrian dynamic prediction trajectory; The inductive lighting control module is used to make advance inductive lighting control decisions on multi-zone lighting delay optimization parameters according to pedestrian dynamic prediction trajectories, and to perform enhanced transfer learning to build an intelligent lighting inductive control model.

2. The induction control system of the induction LED lighting lamp according to claim 1, characterized in that: The lighting scene module is used to: identify all LED lighting lamps in the area; calculate the node positions of all LED lighting lamps in the area one by one, and identify the usage scenes in the area to construct multiple LED lighting scene sub-areas, specifically for: Identify all LED lights in the area; Calculating the position of each LED lighting node of all LED lighting lamps in the area one by one to generate the spatial position coordinates of each LED node; Perform spatial layout analysis on the spatial position coordinates of each LED node to generate LED node spatial layout data; Identify the usage scenarios in the region based on the spatial layout data of the LED nodes, thereby obtaining multiple regional usage scenarios; Based on multiple regional usage scenarios, regional scene segmentation is performed on all LED lighting lamps in the area to construct multiple LED lighting scene sub-areas.

3. The induction control system of the induction LED lighting lamp according to claim 1, characterized in that: The ambient light feature module is used to: obtain ambient light parameters of the scene sub-area; track the light space distribution of the ambient light parameters of the scene sub-area, and mine the ambient light state features to generate ambient light comprehensive state features, specifically for: Detecting ambient light parameters of multiple LED-illuminated scene sub-areas based on a light sensor to obtain ambient light parameters of the scene sub-areas; The ambient light parameters of the scene sub-areas are averaged to calculate the ambient light intensity, and the average ambient light intensity of each sub-area is generated; Performing light space distribution tracing on the ambient light parameters of the scene sub-area to obtain light space distribution tracing data; Perform light distribution change evolution on the light space distribution tracking data to generate light space distribution change characteristics; The ambient light state characteristics are mined based on the average ambient light intensity and light spatial distribution change characteristics of each sub-area to generate the comprehensive ambient light state characteristics.

4. The induction control system of the induction LED lighting lamp according to claim 1, characterized in that: The multi-region lighting coordination module is used to: perform dynamic light source output parameter adjustment and multi-region lighting coordination smoothing on multiple LED lighting scene sub-regions based on the comprehensive state characteristics of the ambient light, so as to generate multi-region lighting coordination control parameters, specifically for: Perform regional lighting demand analysis on multiple LED lighting scene sub-areas to obtain the lighting demand characteristics of each scene sub-area; Calculate the regional lighting brightness based on the lighting demand characteristics of each scene sub-region to generate a regional lighting demand brightness value; Dynamically adjusting the light source output parameters of multiple LED lighting scene sub-areas based on the comprehensive state characteristics of the ambient light, thereby obtaining the light source output characteristic parameters of each sub-area; Multi-region lighting collaborative smoothing is performed according to the regional lighting demand brightness value and the light source output characteristic parameters of each sub-region to generate multi-region lighting collaborative control parameters.

5. The induction control system of the induction LED lighting lamp according to claim 4, characterized in that: The specific steps of dynamically adjusting the light source output parameters of multiple LED lighting scene sub-areas based on the comprehensive state characteristics of the ambient light to obtain the light source output characteristic parameters of each sub-area include: Based on the comprehensive state characteristics of ambient light, the optimal light source color temperature analysis is performed on multiple LED lighting scene sub-areas to generate the optimal light source color temperature parameters for each scene sub-area; Calculate the color temperature difference between regions for the optimal light source color temperature parameters of each scene sub-region, so as to obtain the color temperature difference data between sub-regions; Calculate the spatial color temperature uniformity based on the color temperature difference data between the sub-areas, thereby generating uniform light source color temperature output parameters; Performing a light source illumination frequency analysis on the illumination demand characteristics of each scene sub-area to obtain a light source illumination frequency parameter for each scene sub-area; Dynamic light source output parameter adjustment is performed on the uniform light source color temperature output parameter and the light source illumination frequency parameter of each scene sub-area, thereby obtaining the light source output characteristic parameter of each sub-area.

6. The induction control system of the induction LED lighting lamp according to claim 1, characterized in that: The lighting delay optimization module is used to: collect pedestrian infrared sensing signals in real time; perform lighting threshold detection on pedestrian infrared sensing signals, and perform lighting delay optimization to generate multi-region lighting delay optimization parameters, specifically for: Collect pedestrian infrared sensing signals in real time; perform environmental filtering and noise reduction on pedestrian infrared sensing signals to obtain environmental noise-reduced infrared sensing signals; Calculate the time series signal strength of the environmental noise reduction infrared sensing signal to generate a time series signal strength curve; Perform lighting threshold detection on the timing signal strength curve based on the preset infrared sensing parameter threshold, and when the preset infrared sensing parameter threshold is not less than the timing signal strength, it is marked as the sensing lighting time point; The lighting delay is optimized through multi-zone lighting collaborative control parameters based on the sensing lighting time point to generate multi-zone lighting delay optimization parameters.

7. The induction control system of the induction LED lighting lamp according to claim 6, characterized in that: The specific steps of optimizing the lighting delay by using the multi-zone lighting collaborative control parameters based on the sensing lighting time point to generate the multi-zone lighting delay optimization parameters are: Based on the sensing lighting time point, the LED lighting lamp is dynamically triggered through the multi-zone lighting collaborative control parameters, and the dynamic lighting response parameters are obtained in real time; calculating a timestamp of the lighting response based on the dynamic lighting response parameter; Calculating the response delay of the timestamp of the lighting response according to the sensing lighting time point, thereby obtaining a lighting response delay value; The lighting delay optimization is performed on the multi-zone lighting collaborative control parameters according to the lighting response delay value to generate the multi-zone lighting delay optimization parameters.

8. The induction control system of the induction LED lighting lamp according to claim 1, characterized in that: The movement trajectory prediction module is used to: perform dynamic behavior analysis on pedestrian infrared sensing signals and perform multi-time point movement trajectory prediction, thereby generating a pedestrian dynamic prediction trajectory, specifically for: Perform signal strength change analysis on the environmental noise reduction infrared sensing signal to generate sensing signal strength change data; Evolving the pedestrian movement route based on the sensing signal strength change data, thereby generating the pedestrian movement route; Calculate the length of time a pedestrian stays in a certain area based on their movement route to obtain the length of time they stay in the behavior area; Perform time-series movement position recognition on the pedestrian's moving route to obtain the pedestrian's time-series movement position; Perform dynamic behavior analysis on the duration of stay in the behavior area and the temporal movement position of pedestrians to generate dynamic behavior feature data; The dynamic behavior feature data is used to predict the multi-time point movement trajectory to generate the pedestrian dynamic prediction trajectory.

9. The induction control system of the induction LED lighting lamp according to claim 1, characterized in that: The inductive lighting control module is used to make pre-inductive lighting control decisions on multi-area lighting delay optimization parameters according to pedestrian dynamic prediction trajectories, and to perform enhanced transfer learning to build an intelligent lighting inductive control model, specifically for: Calculate the moving trajectory speed of the pedestrian's dynamic predicted trajectory to generate the pedestrian's dynamic trajectory predicted speed; Predicting the arrival time of multiple LED lighting scene sub-areas based on the predicted speed of pedestrian dynamic trajectories, thereby generating the sub-area arrival time of the predicted trajectory; Pre-sensing lighting control decisions are made on multi-region lighting delay optimization parameters based on the sub-region arrival times of the predicted trajectories to generate pre-sensing lighting control strategies; Strengthen transfer learning of pre-sensing lighting control strategies and build intelligent lighting sensing control models.

Images