LED intelligent induction driving system and method adaptive to ambient light

Abstract

The invention provides a self-adaptive ambient light LED intelligent induction driving system and method, and the method comprises the steps: collecting ambient light sensing data and human body sensing data through a multi-sensing unit, and extracting and preprocessing ambient light features and human body sensing features; constructing an ambient light-LED brightness color temperature adaptive mapping model based on a human visual comfort threshold, and determining an LED-driven dynamic adjustment strategy in combination with human body induction characteristics; according to an adjusting strategy, a PWM modulation mode is adopted to adaptively adjust core parameters such as current and duty ratio of LED driving, and real-time calibration compensation is carried out on sensing data and a mapping model through a dynamic calibration module; in the operation process of the LED lighting equipment, the driving system continuously optimizes driving parameter output according to the environment light change and the dynamic change of the human body induction state. According to the invention, adaptive intelligent driving of the LED lighting equipment according to ambient light and human body induction can be realized, lighting visual comfort and energy saving performance are improved, and adjustment errors caused by sensor drift and LED light decay are compensated at the same time.

Description

Technical Field

[0001] This invention relates to the field of LED driving technology, and specifically to an adaptive ambient light LED intelligent sensing driving system and method. Background Technology

[0002] LED lighting, with its advantages of energy saving, long lifespan, and fast response speed, has been widely used in various lighting scenarios such as homes, offices, public transportation, and commercial venues. With the development of intelligent technology, LED intelligent driving systems with ambient light sensing and human body sensing have become an industry trend. Traditional LED sensing driving systems typically only realize simple ambient light brightness sensing switches or fixed brightness levels, as well as human body sensing switch functions based on infrared sensors. Their level of intelligence and adjustment accuracy cannot meet the needs of modern lighting.

[0003] However, existing technologies for traditional LED intelligent sensing drive systems have several drawbacks: First, they only collect the single parameter of ambient light illuminance without combining it with color temperature parameters for joint adjustment, resulting in poor visual comfort of LED lighting and an inability to match human visual needs under different ambient light color temperatures; Second, human body sensing relies solely on infrared sensors, which are susceptible to interference from ambient temperature and obstructions, leading to false triggering and missed triggering issues, and the adjustment process is abrupt, only performing a fixed brightness switch after sensing; Third, the lack of a dynamic calibration mechanism means that sensor drift after long-term use and LED light decay will gradually increase the error in drive adjustment, affecting long-term performance; Fourth, the drive adjustment uses a fixed algorithm strategy, which cannot adaptively iteratively optimize based on dynamic changes in ambient light and human body sensing status, resulting in poor energy efficiency and adaptability.

[0004] By fusing multi-sensor data to collect multi-dimensional data on ambient light and human presence, and combining this with an adaptive mapping model based on human visual comfort, coupled with closed-loop control involving dynamic calibration and iterative optimization, the accuracy of LED driver adjustment and visual comfort can be improved. Furthermore, the driving strategy can be flexibly adjusted according to human condition and changes in ambient light, significantly enhancing energy efficiency. Simultaneously, it compensates for sensor and LED usage errors, extending system lifespan. Therefore, achieving high-precision, self-adaptive, and fully closed-loop intelligent driving of LED lighting equipment based on ambient light and human presence sensing has become a significant challenge for the industry. Summary of the Invention

[0005] This invention provides an adaptive ambient light LED intelligent sensing driving system and method, which can realize the adaptive intelligent driving adjustment of LED lighting equipment according to multi-dimensional parameters of ambient light and human body sensing status, improve lighting visual comfort and energy saving, and solve the adjustment error problems caused by sensor drift and LED light decay.

[0006] To achieve the above objectives, the present invention is implemented through the following technical solution: In a first aspect, this application provides an adaptive ambient light LED intelligent sensing and driving method for intelligently driving and adjusting LED lighting devices, comprising the following steps: Ambient light sensing data and human body sensing data are collected from the multi-sensor acquisition unit, and then ambient light features and human body sensing features are extracted and preprocessed. An adaptive mapping model of ambient light-LED brightness and color temperature is established based on the human visual comfort threshold, and the dynamic adjustment strategy of LED driving is determined by combining the pre-processed human sensory characteristics. According to the dynamic adjustment strategy, the core driving parameters of the LED lighting device are adaptively adjusted using a modulation method to achieve precise matching and adjustment of LED brightness and color temperature; Collect real-time operating status data of LED lighting equipment and ambient light reference data, and perform dynamic calibration and parameter compensation on the ambient light-LED brightness and color temperature adaptive mapping model. During the operation of LED lighting equipment, the output values ​​of the core driving parameters are continuously iterated and optimized based on the dynamic changes in ambient light sensing data and human body sensing data.

[0007] Preferably, the process of acquiring ambient light sensing data and human body sensing data from the multi-sensor acquisition unit, and then extracting ambient light features and human body sensing features and performing feature preprocessing specifically includes: The ambient light illuminance and color temperature values ​​are collected by the photosensitive sensor and color temperature sensor in the multi-sensor acquisition unit as ambient light sensing data. The infrared sensing signal, human movement trajectory signal and sensing distance value are collected by the infrared sensing sensor and millimeter-wave radar sensor as human body sensing data. Illumination change rate and color temperature fluctuation value are extracted from ambient light sensing data as ambient light characteristics, and effective sensing signal intensity, human movement speed and sensing duration are extracted from human body sensing data as human body sensing characteristics. The median filtering algorithm is used to denoise the ambient light features and human body sensing features. The min-max normalization algorithm is then used to normalize the denoised features to obtain standardized feature data.

[0008] Preferably, the ambient light-LED brightness and color temperature adaptive mapping model established based on the human visual comfort threshold specifically includes: Collect experimental data on human visual comfort under different ambient light intensities and color temperatures, set human visual comfort thresholds in multiple ranges, and divide the ranges into ambient light intensities and color temperatures. Using the illuminance and color temperature of ambient light as input variables and the optimal matching brightness and color temperature of LEDs as output variables, an adaptive mapping model of ambient light-LED brightness and color temperature based on a BP neural network is constructed. Using the human visual comfort threshold as a constraint, the mapping model is trained and optimized so that the LED brightness and color temperature values ​​output by the model meet the requirements of human visual comfort.

[0009] Preferably, the dynamic adjustment strategy for LED driving, determined by combining pre-processed human body sensing characteristics, specifically includes: The human body sensing status is determined based on the pre-processed human body sensing characteristics. The human body sensing status includes three states: effective sensing of a person, sensing of no one, and human body moving. If there is a person effectively detected, a high-precision continuous adjustment strategy is adopted to make the LED brightness and color temperature change smoothly in real time with the ambient light; if a person is moving, a gradual adjustment strategy is adopted to control the adjustment step size of LED brightness and color temperature to match the speed of human movement; if there is no one detected, a low-power standby adjustment strategy is adopted to adjust the LED brightness to the energy-saving threshold.

[0010] Preferably, the adaptive adjustment of the core driving parameters of the LED lighting device using a modulation method according to the dynamic adjustment strategy specifically includes: The core modulation method is PWM pulse width modulation. The LED brightness value and color temperature value matched in the dynamic adjustment strategy are converted into the corresponding PWM duty cycle and drive current value, which serve as the core driving parameters of the LED lighting device. The drive control unit converts the PWM duty cycle and drive current value into drive electrical signals, which are then input to the drive circuit of the LED lighting equipment to achieve precise matching and adjustment of LED brightness and color temperature without flicker fluctuations during the adjustment process.

[0011] Preferably, the dynamic calibration and parameter compensation of the ambient light-LED brightness and color temperature adaptive mapping model specifically includes: Ambient light reference illuminance and reference color temperature values ​​are collected using a standard light sensor calibrator as ambient light reference data, and the actual operating current, voltage, and brightness values ​​of LED lighting equipment are collected using a current and voltage acquisition module as real-time operating status data. The deviation rate between the LED brightness and color temperature values ​​predicted by the calculation model and the measured values ​​in the actual working state data is adjusted when the deviation rate exceeds the preset threshold. To address the errors caused by sensor drift and LED light decay, an error compensation function is established based on ambient light reference data and LED operating time to compensate for ambient light sensing data and model output values ​​in real time.

[0012] Preferably, the multi-sensor acquisition unit is an integrated sensor module, and the core driving parameters include PWM duty cycle, driving current value, and color temperature adjustment voltage value.

[0013] Secondly, this application provides an adaptive ambient light LED intelligent sensing and driving system, which includes an LED lighting device and a driving control unit, wherein the driving control unit includes: The acquisition module is used to acquire ambient light sensing data and human body sensing data from the multi-sensor acquisition unit, and then extract ambient light features and human body sensing features and perform feature preprocessing. The model building module is used to establish an adaptive mapping model of ambient light-LED brightness and color temperature based on the human visual comfort threshold, and to determine the dynamic adjustment strategy of LED driving by combining the preprocessed human sensory characteristics. The drive adjustment module is used to adaptively adjust the core drive parameters of the LED lighting device according to the dynamic adjustment strategy using a modulation method, so as to achieve precise matching and adjustment of LED brightness and color temperature. The calibration and compensation module is used to collect real-time operating status data and ambient light reference data of LED lighting equipment, and to perform dynamic calibration and parameter compensation on the ambient light-LED brightness and color temperature adaptive mapping model. The iterative optimization module is used to continuously iterate and optimize the output values ​​of the core driving parameters based on the dynamic changes of ambient light sensing data and human body sensing data during the operation of LED lighting equipment.

[0014] Thirdly, this application provides a computer device, the computer device including a memory and a processor, the memory storing code, and the processor being configured to acquire the code and execute the above-described adaptive ambient light LED intelligent sensing driving method.

[0015] Fourthly, this application provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described adaptive ambient light LED intelligent sensing driving method.

[0016] The technical solutions provided by the embodiments disclosed in this application have the following beneficial effects: In this embodiment, multi-dimensional sensing data of ambient light and human body sensing are collected from a multi-sensor acquisition unit, and feature data is extracted and preprocessed. An ambient light-LED brightness and color temperature adaptive mapping model is constructed based on the human visual comfort threshold, and a dynamic adjustment strategy is determined in combination with the human body sensing state. The core parameters of the LED driver are adjusted by PWM modulation to achieve accurate matching of brightness and color temperature. The mapping model is dynamically calibrated and error compensated by ambient light reference data and LED working status data. Finally, the driving parameters are continuously iteratively optimized according to the dynamic changes of the sensing data.

[0017] Therefore, this application achieves accurate acquisition of multi-dimensional data from ambient light and human body sensing through multi-sensor fusion technology, solving the problems of limited information and poor anti-interference capability of traditional single-sensor acquisition, and effectively improving the reliability of sensing and light sensing acquisition. Secondly, an adaptive mapping model based on human visual comfort threshold is constructed to jointly match and adjust the brightness and color temperature of ambient light and LEDs, significantly improving the visual comfort of lighting and meeting the visual needs of humans in different scenarios. Furthermore, differentiated dynamic adjustment strategies are formulated according to different states of human body sensing, realizing high-precision continuous adjustment when people are present, gradual adjustment when people are moving, and low-power standby when no one is present, maximizing energy saving while ensuring the lighting experience. At the same time, the dynamic calibration and error compensation mechanism effectively solves the long-term adjustment error problem caused by sensor drift and LED light decay, extending the effective service life of the system. Finally, through closed-loop iterative optimization, the drive system can adapt to the dynamic changes of ambient light and human body sensing in real time, realizing self-adaptive intelligent drive in all scenarios. In summary, the solution proposed in this application can achieve high-precision, self-adaptive, and fully closed-loop intelligent drive adjustment of LED lighting equipment based on ambient light and human body sensing, while also providing visual comfort, energy efficiency, and long-term stability. Attached Figure Description

[0018] Other features, objects, and advantages of the present invention will become more apparent from the following detailed description of non-limiting embodiments with reference to the accompanying drawings: Figure 1 This is an exemplary flowchart of an LED intelligent sensing driving method for adaptive ambient light, as shown in some embodiments of this application. Figure 2 This is a schematic diagram of the drive control unit structure of an adaptive ambient light LED intelligent sensing drive system according to some embodiments of this application; Figure 3 This is a schematic diagram of the structure of a computer device for implementing the method of this application, according to some embodiments of this application. Detailed Implementation

[0019] The technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative effort are within the scope of protection of the present invention.

[0020] The present invention will be further described in detail below with reference to the accompanying drawings.

[0021] Reference Figure 1 In a first aspect, this application provides an adaptive ambient light LED intelligent sensing driving method for intelligently driving and adjusting LED lighting devices, comprising the following steps: Ambient light sensing data and human body sensing data are collected from the multi-sensor acquisition unit, and then ambient light features and human body sensing features are extracted and preprocessed. An adaptive mapping model of ambient light-LED brightness and color temperature is established based on the human visual comfort threshold, and the dynamic adjustment strategy of LED driving is determined by combining the pre-processed human sensory characteristics. According to the dynamic adjustment strategy, the core driving parameters of the LED lighting device are adaptively adjusted using a modulation method to achieve precise matching and adjustment of LED brightness and color temperature; Collect real-time operating status data of LED lighting equipment and ambient light reference data, and perform dynamic calibration and parameter compensation on the ambient light-LED brightness and color temperature adaptive mapping model. During the operation of LED lighting equipment, the output values ​​of the core driving parameters are continuously iterated and optimized based on the dynamic changes in ambient light sensing data and human body sensing data.

[0022] This invention utilizes multi-sensor acquisition as its data foundation, human visual comfort as its core constraint, and dynamic calibration and iterative optimization as a closed-loop guarantee to achieve full-process adaptive adjustment of LED intelligent sensing drive. First, it collects ambient light and human body sensing data through multi-sensor acquisition units, extracts and preprocesses ambient light and human body sensing characteristics, then constructs an ambient light-LED brightness and color temperature adaptive mapping model based on human visual comfort thresholds. Combining the preprocessed human body sensing characteristics, it determines an appropriate dynamic adjustment strategy for the LED drive. Subsequently, it uses modulation to transform the adjustment strategy into adjustment actions for the core drive parameters, achieving precise matching of LED brightness and color temperature. Simultaneously, it collects ambient light reference data and real-time LED operating status data to dynamically calibrate and compensate parameters for the mapping model. Finally, during the operation of the LED lighting equipment, it continuously iterates and optimizes the output values ​​of the core drive parameters based on the dynamic changes in the sensor data, forming a fully closed-loop drive adjustment process of sensor acquisition, model construction, drive adjustment, calibration compensation, and iterative optimization. This system enables adaptive intelligent driving adjustment of LED lighting equipment based on multi-dimensional ambient light parameters and human body sensing status. It breaks through the limitations of traditional fixed adjustment strategies for LED drivers, improves visual comfort while optimizing energy efficiency, and effectively compensates for adjustment errors caused by sensor drift and LED light decay. This ensures long-term accuracy of driving adjustment, achieves dynamic adaptation across all scenarios, and makes LED lighting driving adjustment more in line with actual usage needs.

[0023] In some embodiments, acquiring ambient light sensing data and human body sensing data from a multi-sensor acquisition unit, and then extracting ambient light features and human body sensing features and performing feature preprocessing specifically includes: The ambient light illuminance and color temperature values ​​are collected by the photosensitive sensor and color temperature sensor in the multi-sensor acquisition unit as ambient light sensing data. The infrared sensing signal, human movement trajectory signal and sensing distance value are collected by the infrared sensing sensor and millimeter-wave radar sensor as human body sensing data. Illumination change rate and color temperature fluctuation value are extracted from ambient light sensing data as ambient light characteristics, and effective sensing signal intensity, human movement speed and sensing duration are extracted from human body sensing data as human body sensing characteristics. The median filtering algorithm is used to denoise the ambient light features and human body sensing features. The min-max normalization algorithm is then used to normalize the denoised features to obtain standardized feature data.

[0024] It should be noted that an integrated multi-sensor acquisition unit is used. A photosensitive sensor and a color temperature sensor collect ambient light illuminance and color temperature values, respectively. An infrared sensor and a millimeter-wave radar sensor collect infrared sensing signals, human movement trajectory signals, and sensing distance values ​​for human body sensing. Illuminance change rate and color temperature fluctuation values ​​are extracted from the collected ambient light sensing data as ambient light features. Effective sensing signal strength, human movement speed, and sensing duration are extracted from the human body sensing data as human body sensing features. First, a median filtering algorithm is used to denoise the extracted ambient light and human body sensing features, eliminating abnormal data caused by environmental interference. Then, a min-max normalization algorithm is used to normalize the denoised feature data, completing the standardized preprocessing of the feature data.

[0025] This invention achieves multi-dimensional data acquisition of ambient light and human body sensing through multi-sensor fusion acquisition, which effectively improves the comprehensiveness and anti-interference ability of the data compared with single-sensor acquisition. The targeted extracted features can accurately reflect the core features of ambient light changes and human body sensing status. Combined with median filtering and min-max normalization preprocessing, data noise is effectively removed and the influence of different feature dimensions is eliminated, providing high-quality standardized feature data for subsequent mapping model construction and adjustment strategy formulation, ensuring the accuracy of subsequent algorithm processing.

[0026] In some embodiments, establishing an adaptive mapping model for ambient light-LED brightness and color temperature based on a human visual comfort threshold specifically includes: Collect experimental data on human visual comfort under different ambient light intensities and color temperatures, set human visual comfort thresholds in multiple ranges, and divide the ranges into ambient light intensities and color temperatures. Using the illuminance and color temperature of ambient light as input variables and the optimal matching brightness and color temperature of LEDs as output variables, an adaptive mapping model of ambient light-LED brightness and color temperature based on a BP neural network is constructed. Using the human visual comfort threshold as a constraint, the mapping model is trained and optimized so that the LED brightness and color temperature values ​​output by the model meet the requirements of human visual comfort.

[0027] In practice, the human visual comfort data under different ambient light and color temperature conditions is first collected through human visual comfort experiments. Based on the experimental data, multiple ranges of human visual comfort thresholds are set, and the ambient light and color temperature are divided into ranges. The ambient light illuminance and color temperature values ​​are used as model input variables, and the optimal matching brightness and color temperature values ​​of the LED are used as model output variables to construct an ambient light-LED brightness and color temperature adaptive mapping model based on a BP neural network. The set human visual comfort thresholds are used as constraints for model training to train and optimize the parameters of the BP neural network model, so that the LED brightness and color temperature values ​​output by the model always meet the requirements of human visual comfort.

[0028] Based on experiments on human visual comfort, a mapping model is constructed to ensure that the matching and adjustment of LED brightness and color temperature are always centered on human visual perception. This allows the adjusted LED lighting to accurately match changes in ambient light while meeting the physiological needs of human vision, effectively improving the visual comfort of lighting and avoiding visual fatigue caused by lighting parameters that do not meet human visual needs. At the same time, the BP neural network modeling method improves the model's ability to fit changes in ambient light, making the matching of brightness and color temperature more accurate.

[0029] In some embodiments, determining the dynamic adjustment strategy for LED driving by combining preprocessed human body sensing characteristics specifically includes: The human body sensing status is determined based on the pre-processed human body sensing characteristics. The human body sensing status includes three states: effective sensing of a person, sensing of no one, and human body moving. If there is a person effectively detected, a high-precision continuous adjustment strategy is adopted to make the LED brightness and color temperature change smoothly in real time with the ambient light; if a person is moving, a gradual adjustment strategy is adopted to control the adjustment step size of LED brightness and color temperature to match the speed of human movement; if there is no one detected, a low-power standby adjustment strategy is adopted to adjust the LED brightness to the energy-saving threshold.

[0030] It should be noted that, based on the pre-processed human body sensing characteristics, a state judgment threshold is set. By comparing the feature data with the threshold, the human body sensing state is divided into three types: effective sensing with a person present, human body moving, and no human body present. Differentiated dynamic adjustment strategies for LED driving are formulated for different human body sensing states. In the effective sensing state with a person present, a high-precision continuous adjustment strategy is adopted to make the LED brightness and color temperature change smoothly in real time with the ambient light. In the human body moving state, a gradual adjustment strategy is adopted to match the adjustment step size of LED brightness and color temperature with the speed of human body movement. In the no human body present state, a low-power standby adjustment strategy is adopted to adjust the LED brightness to the preset energy-saving threshold.

[0031] This invention achieves differentiated intelligent adjustment based on human body sensing status, avoiding the rigidity of traditional fixed adjustment strategies. It ensures the accuracy and comfort of lighting when someone is effectively sensed, makes the lighting adjustment more in line with the actual scene of human movement when a person is moving, and maximizes lighting energy saving when no one is sensed. It takes into account both the user's lighting experience and the system's energy efficiency, making LED driver adjustment more scenario-based and intelligent.

[0032] In some embodiments, adaptively adjusting the core driving parameters of the LED lighting device according to the modulation method based on the dynamic adjustment strategy specifically includes: The core modulation method is PWM pulse width modulation. The LED brightness value and color temperature value matched in the dynamic adjustment strategy are converted into the corresponding PWM duty cycle and drive current value, which serve as the core driving parameters of the LED lighting device. The drive control unit converts the PWM duty cycle and drive current value into drive electrical signals, which are then input to the drive circuit of the LED lighting equipment to achieve precise matching and adjustment of LED brightness and color temperature without flicker fluctuations during the adjustment process.

[0033] It should be noted that PWM pulse width modulation is used as the core modulation method to establish the correspondence between LED brightness and color temperature values ​​and PWM duty cycle and drive current values. The LED brightness and color temperature values ​​matched in the dynamic adjustment strategy are converted into corresponding PWM duty cycle and drive current values, which serve as the core driving parameters of the LED lighting device. The drive control unit converts the converted PWM duty cycle and drive current values ​​into corresponding drive electrical signals, which are then input to the drive circuit of the LED lighting device. The drive circuit controls the light emission state of the LED beads, achieving precise matching and adjustment of LED brightness and color temperature. Moreover, the modulation frequency avoids the persistence of vision range of the human eye, ensuring flicker-free fluctuations during the adjustment process.

[0034] This invention achieves precise conversion and adjustment of core driving parameters through PWM modulation, ensuring that the adjustment of LED brightness and color temperature is precisely matched with the dynamic adjustment strategy, thus guaranteeing the accuracy of the adjustment. The flicker-free adjustment method further improves the visual comfort of lighting, avoiding visual fatigue and eye damage caused by flicker. At the same time, the compatibility between the driving electrical signal and the LED driving circuit makes the adjustment action more stable and efficient.

[0035] In some embodiments, dynamic calibration and parameter compensation of the ambient light-LED brightness and color temperature adaptive mapping model specifically includes: Ambient light reference illuminance and reference color temperature values ​​are collected using a standard light sensor calibrator as ambient light reference data, and the actual operating current, voltage, and brightness values ​​of LED lighting equipment are collected using a current and voltage acquisition module as real-time operating status data. The deviation rate between the LED brightness and color temperature values ​​predicted by the calculation model and the measured values ​​in the actual working state data is adjusted when the deviation rate exceeds the preset threshold. To address the errors caused by sensor drift and LED light decay, an error compensation function is established based on ambient light reference data and LED operating time to compensate for ambient light sensing data and model output values ​​in real time.

[0036] It should be noted that the ambient light reference illuminance and reference color temperature values ​​are collected using a standard light sensor calibrator as ambient light reference data, while the actual operating current, voltage, and brightness values ​​of the LED lighting equipment are collected using a current and voltage acquisition module as real-time operating status data. The deviation rate between the LED brightness and color temperature values ​​predicted by the ambient light-LED brightness and color temperature adaptive mapping model and the measured values ​​in the real-time operating status data is calculated. When the deviation rate exceeds a preset threshold, the weight parameters of the mapping model are incrementally corrected. Based on the ambient light reference data and LED operating time, a linear error compensation function is established to compensate for errors caused by sensor drift and LED light decay in real time for the ambient light sensing data and model output values.

[0037] This invention achieves real-time correction of the mapping model through a dynamic calibration mechanism, ensuring that the model's output always matches the actual scene and guaranteeing the accuracy of drive adjustment. The error compensation function can effectively offset the long-term usage errors caused by sensor drift and LED light decay, solving the problem of decreased adjustment accuracy of traditional LED drive systems after long-term use, improving the long-term stability of the system, and extending the overall service life of the LED intelligent sensing drive system.

[0038] In some embodiments, the multi-sensor acquisition unit is an integrated sensor module, and the core driving parameters include PWM duty cycle, driving current value, and color temperature adjustment voltage value.

[0039] It should be noted that the multi-sensor acquisition unit is set as an integrated sensing module, integrating the photosensitive sensor, color temperature sensor, infrared sensor, and millimeter-wave radar sensor into the same module structure, and adopting a low-power design to adapt to various LED lighting devices; the core driving parameters of the LED lighting device are clearly defined, including the PWM duty cycle, driving current value, and color temperature adjustment voltage value, which correspond to the core control dimensions of LED brightness adjustment, current drive, and color temperature adjustment, respectively.

[0040] The integrated sensing module design enables modular integration of multiple sensors, facilitating integration and installation with various LED lighting devices, reducing system assembly difficulty, and the low-power design also meets the energy-saving requirements of LED lighting. The clear definition of the core driving parameters makes the adjustment of LED brightness and color temperature more targeted, avoiding adjustment deviations caused by parameter ambiguity, and further improving the accuracy and controllability of driving adjustment.

[0041] Reference Figure 2 Secondly, this application provides an adaptive ambient light LED intelligent sensing drive system, which includes an LED lighting device and a drive control unit, wherein the drive control unit includes: The acquisition module is used to acquire ambient light sensing data and human body sensing data from the multi-sensor acquisition unit, and then extract ambient light features and human body sensing features and perform feature preprocessing. The model building module is used to establish an adaptive mapping model of ambient light-LED brightness and color temperature based on the human visual comfort threshold, and to determine the dynamic adjustment strategy of LED driving by combining the preprocessed human sensory characteristics. The drive adjustment module is used to adaptively adjust the core drive parameters of the LED lighting device according to the dynamic adjustment strategy using a modulation method, so as to achieve precise matching and adjustment of LED brightness and color temperature. The calibration and compensation module is used to collect real-time operating status data and ambient light reference data of LED lighting equipment, and to perform dynamic calibration and parameter compensation on the ambient light-LED brightness and color temperature adaptive mapping model. The iterative optimization module is used to continuously iterate and optimize the output values ​​of the core driving parameters based on the dynamic changes of ambient light sensing data and human body sensing data during the operation of LED lighting equipment.

[0042] It should be noted that the drive control unit adopts a modular functional architecture design, with clear functional boundaries and strong synergy among the modules. This not only ensures the efficient implementation of the adaptive drive method but also improves the system's scalability and maintainability, facilitating subsequent upgrades and adjustments to module functions based on actual needs. The system organically combines hardware devices with algorithm models, enabling the various functions of LED intelligent sensing drive to form a complete implementation chain, ensuring the stability and reliability of system operation.

[0043] Reference Figure 3Thirdly, this application provides a computer device, which includes a memory and a processor. The memory stores code, and the processor is configured to acquire the code and execute the aforementioned adaptive ambient light LED intelligent sensing driving method. The computer device provides a dedicated hardware platform for the adaptive ambient light LED intelligent sensing driving method. The processor's hardware computing power ensures the efficient and stable execution of various algorithms, model construction, and data processing within the method, avoiding the inefficiency problems associated with general-purpose equipment. Furthermore, the hardware architecture of this computer device is adaptable to various computing scenarios, allowing for flexible selection of desktop computers, embedded microcontrollers, industrial control boards, and other device forms according to actual application needs, thus improving the feasibility and practicality of the driving method.

[0044] In some embodiments, the LED intelligent sensing driving method for adaptive ambient light in the above embodiments can be implemented by a computer device, which includes at least one processor, a communication bus, a memory, and at least one communication interface.

[0045] A processor can be a general-purpose central processing unit (CPU) or an application-specific integrated circuit (ASIC).

[0046] A communication bus can be used to transmit information between the aforementioned components.

[0047] The memory can be read-only memory (ROM) or other types of static storage devices capable of storing static information and instructions, random access memory (RAM) or other types of dynamic storage devices capable of storing information and instructions, or electrically erasable programmable read-only memory (EEPROM), compact disc read-only memory (CD-ROM) or other optical disc storage, optical disc storage (including compressed optical discs, laser discs, optical discs, universal optical discs, Blu-ray discs, etc.), magnetic disks or other magnetic storage devices, or any other medium capable of carrying or storing desired program code in the form of instructions or data structures and accessible by a computer, but not limited to these. The memory can exist independently and be connected to the processor via a communication bus. The memory can also be integrated with the processor.

[0048] The memory stores program code for executing the solution of this application, and its execution is controlled by a processor. The processor executes the program code stored in the memory. The program code may include one or more software modules. In the above embodiments, the adaptive ambient light LED intelligent sensing driving method can be implemented by a processor and one or more software modules in the program code in the memory.

[0049] A communication interface is a device that uses any transceiver or similar device to communicate with other devices or communication networks, such as Ethernet, radio access network (RAN), wireless local area networks (WLAN), etc.

[0050] In a specific implementation, as one example, a computer device may include multiple processors, each of which may be a single-core (single-CPU) processor or a multi-core (multi-CPU) processor. Here, a processor may refer to one or more devices, circuits, and / or processing cores used to process data (e.g., computer program instructions).

[0051] The aforementioned computer device can be a general-purpose computer device or a special-purpose computer device. In specific implementations, the computer device can be a desktop computer, a portable computer, a network server, a handheld digital assistant (PDA), a mobile phone, a tablet computer, a wireless terminal device, a communication device, or an embedded device. This application does not limit the type of computer device.

[0052] Fourthly, this application provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the aforementioned LED intelligent sensing and driving method for adaptive ambient light. The computer-readable storage medium enables the software-based implementation of the LED intelligent sensing and driving method for adaptive ambient light, facilitating the storage, transmission, and cross-device deployment of the method. It allows for portability and use on different computer devices, significantly reducing the application and promotion costs of the driving method. Simultaneously, the storage characteristics of the computer-readable storage medium ensure the stability of the program, preventing the loss or tampering of the method's logic and making the execution of the driving method more consistent.

[0053] To better understand the technical solution of this application, the technical solution of this application will be described in detail below with reference to the accompanying drawings and specific embodiments.

[0054] refer to Figure 1The figure is an exemplary flowchart of an adaptive ambient light LED intelligent sensing driving method according to some embodiments of this application. The adaptive ambient light LED intelligent sensing driving method mainly includes the following steps: In step 101, ambient light sensing data and human body sensing data are collected from the multi-sensor acquisition unit, and then ambient light features and human body sensing features are extracted and preprocessed.

[0055] It should be noted that the reference Figure 2 As shown in the figure, this figure is a schematic diagram of the overall structure of an LED intelligent sensing drive system in some embodiments of this application. The system mainly includes a multi-sensor acquisition unit, a drive control unit, an LED lighting device, a calibration and detection unit, and a power supply unit. The multi-sensor acquisition unit is connected to the acquisition module of the drive control unit, the calibration and detection unit is connected to the calibration and compensation module of the drive control unit, the output terminal of the drive control unit is connected to the drive circuit of the LED lighting device, and the power supply unit provides a stable operating voltage for the entire system, realizing a closed-loop control of sensor acquisition, drive adjustment, and calibration compensation.

[0056] It should also be noted that the multi-sensor acquisition unit in this application is an integrated sensing module, which integrates a photosensitive sensor, a color temperature sensor, an infrared sensor, and a millimeter-wave radar sensor. It can simultaneously acquire ambient light intensity and color temperature, as well as human infrared sensing, movement trajectory, and sensing distance. This module adopts a low-power design and is suitable for the integrated installation of various LED lighting devices. The sensing data in this application refers to the raw electrical signals and numerical parameters acquired by the sensors, which are transmitted to the drive control unit for processing after analog-to-digital conversion.

[0057] In practice, the acquisition of ambient light sensing data and human body sensing data from the multi-sensor acquisition unit can be achieved in the following way: First, the raw data of ambient light and human body sensing are acquired in real time by each sensor in the multi-sensor acquisition unit, and the analog sensing signals are converted into numerical digital signals by the analog-to-digital converter (ADC); then, the digitized sensing data is transmitted to the acquisition module of the drive control unit using the serial communication protocol (UART); finally, the acquisition module performs preliminary format conversion on the received sensing data to obtain standardized ambient light sensing data and human body sensing data.

[0058] In some embodiments, extracting ambient light features and human body sensing features and performing feature preprocessing can be achieved using the following steps: The ambient light illuminance and color temperature values ​​are collected by the photosensitive sensor and color temperature sensor in the multi-sensor acquisition unit as ambient light sensing data. The infrared sensing signal, human movement trajectory signal and sensing distance value are collected by the infrared sensing sensor and millimeter-wave radar sensor as human body sensing data. Illumination change rate and color temperature fluctuation value are extracted from ambient light sensing data as ambient light characteristics, and effective sensing signal intensity, human movement speed and sensing duration are extracted from human body sensing data as human body sensing characteristics. The median filtering algorithm is used to denoise the ambient light features and human body sensing features. The min-max normalization algorithm is then used to normalize the denoised features to obtain standardized feature data.

[0059] In specific implementation, the extraction of ambient light features and human body sensing features can be achieved in the following way: Based on the time series data of ambient light illuminance and color temperature values, the illuminance change rate and color temperature fluctuation value per unit time are calculated using the difference method, which serves as the core feature of ambient light; the infrared sensing signals of human body sensing are threshold-filtered to extract the intensity value of the effective sensing signal; the human movement speed is calculated based on the human movement trajectory signal collected by millimeter-wave radar; and the duration of the effective sensing signal is statistically analyzed as the sensing duration, which serves as the core feature of human body sensing. During feature preprocessing, the median filtering algorithm is first used to denoise the feature data, removing outliers caused by environmental interference. Then, the min-max normalization algorithm is used to map all feature data to the [0,1] interval to obtain standardized feature data, eliminating the influence of different feature dimensions and providing unified input data for subsequent model construction.

[0060] In step 102, an ambient light-LED brightness and color temperature adaptive mapping model is established based on the human visual comfort threshold, and the dynamic adjustment strategy of LED driving is determined by combining the preprocessed human sensory characteristics.

[0061] In some embodiments, establishing an adaptive mapping model for ambient light-LED brightness and color temperature based on human visual comfort thresholds can be achieved through the following steps: Collect experimental data on human visual comfort under different ambient light intensities and color temperatures, set human visual comfort thresholds in multiple ranges, and divide the ranges into ambient light intensities and color temperatures. Using the illuminance and color temperature of ambient light as input variables and the optimal matching brightness and color temperature of LEDs as output variables, an adaptive mapping model of ambient light-LED brightness and color temperature based on a BP neural network is constructed. Using the human visual comfort threshold as a constraint, the mapping model is trained and optimized so that the LED brightness and color temperature values ​​output by the model meet the requirements of human visual comfort.

[0062] In practice, visual comfort scores were first collected from different groups of people in an ambient light illuminance range of 50-10000 lx and a color temperature range of 2700-6500 K through a visual comfort experiment. Based on the scores, three levels of human visual comfort thresholds (excellent, good, and moderate) were set. Ambient light was further divided into three illuminance ranges: low (<300 lx), medium (300-1000 lx), and high (>1000 lx), and three color temperature ranges: low (2700-3500 K), medium (3500-5000 K), and high (5...). The model is designed to handle three color temperature ranges (000-6500K). A three-layer backpropagation (BP) neural network is constructed, with two neurons in the input layer (ambient light illuminance and color temperature), 10 neurons in the hidden layer, and two neurons in the output layer (LED brightness and color temperature). The network weights and biases are initialized. Finally, the human visual comfort threshold is used as a constraint, and the network is trained using gradient descent. The weights and biases are iteratively optimized to ensure that the visual comfort scores corresponding to the LED brightness and color temperature values ​​output by the model reach a level of "good" or above, thus completing the construction of the mapping model.

[0063] In some embodiments, determining the dynamic adjustment strategy for LED driving by combining preprocessed human body sensing characteristics can be achieved through the following steps: The human body sensing status is determined based on the pre-processed human body sensing characteristics. The human body sensing status includes three states: effective sensing of a person, sensing of no one, and human body moving. If there is a person effectively detected, a high-precision continuous adjustment strategy is adopted to make the LED brightness and color temperature change smoothly in real time with the ambient light; if a person is moving, a gradual adjustment strategy is adopted to control the adjustment step size of LED brightness and color temperature to match the speed of human movement; if there is no one detected, a low-power standby adjustment strategy is adopted to adjust the LED brightness to the energy-saving threshold.

[0064] In specific implementation, a state judgment threshold is set based on the pre-processed human body sensing characteristics: when the effective sensing signal strength is greater than the preset threshold, the sensing duration exceeds 3 seconds, and the human body movement speed is 0, it is determined to be a state where someone is effectively sensed; when the effective sensing signal strength is greater than the preset threshold and the human body movement speed is greater than 0, it is determined to be a state where a human body is moving; when the effective sensing signal strength is less than the preset threshold, it is determined to be a state where no one is sensed. Adjustment strategies are formulated for different states: in the state where someone is effectively sensed, the adjustment step size of the drive system is set to 1% / 100ms to achieve real-time, continuous, and smooth adjustment of LED brightness and color temperature; in the state where a human body is moving, the adjustment step size is positively correlated with the human body movement speed, with a larger adjustment step size for faster movement, avoiding flickering lighting caused by rapid human movement; in the state where no one is sensed, the LED brightness is adjusted to an energy-saving threshold below 5%, and the color temperature is adjusted to 3000K to achieve minimum power consumption standby.

[0065] In step 103, the core driving parameters of the LED lighting device are adaptively adjusted using a modulation method according to the dynamic adjustment strategy to achieve precise matching and adjustment of LED brightness and color temperature.

[0066] In some embodiments, adaptively adjusting the core driving parameters of the LED lighting device according to the modulation method based on the dynamic adjustment strategy specifically includes: The core modulation method is PWM pulse width modulation. The LED brightness value and color temperature value matched in the dynamic adjustment strategy are converted into the corresponding PWM duty cycle and drive current value, which serve as the core driving parameters of the LED lighting device. The drive control unit converts the PWM duty cycle and drive current value into drive electrical signals, which are then input to the drive circuit of the LED lighting equipment to achieve precise matching and adjustment of LED brightness and color temperature without flicker fluctuations during the adjustment process.

[0067] It should be noted that the core driving parameters in this application include PWM duty cycle, driving current value, and color temperature adjustment voltage value. The PWM duty cycle and driving current value are used to adjust the LED brightness, and the color temperature adjustment voltage value is used to adjust the light emission ratio of the warm and cool LED beads to achieve color temperature adjustment. The PWM modulation frequency used in this application is 100kHz, which is much higher than the visual persistence frequency of the human eye, ensuring that there is no flicker fluctuation during the adjustment process.

[0068] In practice, firstly, a correspondence table is established between LED brightness and PWM duty cycle and drive current value, and a correspondence table is established between LED color temperature and color temperature adjustment voltage value. Based on the LED brightness and color temperature values ​​matched in the dynamic adjustment strategy, the corresponding PWM duty cycle, drive current value, and color temperature adjustment voltage value are retrieved from the correspondence table. Then, the PWM modulation module in the drive control unit generates the corresponding PWM wave, the current adjustment module outputs the matched drive current, and the voltage adjustment module outputs the matched color temperature adjustment voltage. Finally, the above drive signals are input to the constant current and constant voltage drive circuit of the LED lighting equipment. The drive circuit controls the brightness and ratio of the warm and cool LED beads according to the input signal, realizing precise matching and adjustment of LED brightness and color temperature.

[0069] In step 104, real-time operating status data of LED lighting equipment and ambient light reference data are collected, and the ambient light-LED brightness and color temperature adaptive mapping model is dynamically calibrated and parameter compensated.

[0070] In some embodiments, dynamic calibration and parameter compensation of the ambient light-LED brightness and color temperature adaptive mapping model specifically includes: Ambient light reference illuminance and reference color temperature values ​​are collected using a standard light sensor calibrator as ambient light reference data, and the actual operating current, voltage, and brightness values ​​of LED lighting equipment are collected using a current and voltage acquisition module as real-time operating status data. The deviation rate between the LED brightness and color temperature values ​​predicted by the calculation model and the measured values ​​in the actual working state data is adjusted when the deviation rate exceeds the preset threshold (5%). To address the errors caused by sensor drift and LED light decay, an error compensation function is established based on ambient light reference data and LED operating time to compensate for ambient light sensing data and model output values ​​in real time.

[0071] In practice, the standard light sensor in the calibration and testing unit collects ambient light reference data every 24 hours, while the current and voltage acquisition module collects real-time operating status data of the LED lighting equipment and transmits the data to the calibration compensation module. The calibration compensation module calculates the deviation rate between the model's predicted value and the measured value using the formula: Deviation rate = |Predicted value - Measured value| / Measured value × 100%. When the deviation rate exceeds 5%, incremental learning is used to fine-tune the weight parameters of the mapping model, bringing the deviation rate back to within the threshold. Simultaneously, a linear error compensation function is established based on the sensor's usage time and the LED's operating time: Compensation value = Original value (1 - kt), where k is the error coefficient and t is the usage time. This function is used to compensate for the ambient light sensing data and model output value in real time, effectively offsetting the errors caused by sensor drift and LED light decay.

[0072] In step 105, during the operation of the LED lighting equipment, the output values ​​of the core driving parameters are continuously iteratively optimized based on the dynamic changes in ambient light sensing data and human body sensing data.

[0073] In practice, the iterative optimization module of the drive control unit uses a 100ms iteration cycle. In each cycle, it collects the latest ambient light sensing data and human body sensing data, inputs them into the calibrated ambient light-LED brightness and color temperature adaptive mapping model, and obtains the latest LED brightness matching value and color temperature matching value. Combined with the real-time human body sensing status, it determines the latest dynamic adjustment strategy and updates the output values ​​of the drive core parameters. The iterative optimization module also records the sensing data, drive parameters, and visual comfort feedback data of each cycle, continuously enriching the model's training dataset and achieving continuous self-optimization of the model. This enables the drive system to adapt to the dynamic changes of ambient light and human body sensing in real time, ensuring a good lighting experience and energy-saving effect in all scenarios.

[0074] On the other hand, in some embodiments, this application provides an adaptive ambient light LED intelligent sensing drive system, which includes an LED lighting device and a drive control unit, referenced... Figure 2 The figure is a schematic diagram of the structure of a drive control unit according to some embodiments of this application. The drive control unit includes: an acquisition module, a model building module, a drive adjustment module, a calibration compensation module, and an iterative optimization module, which are described below: The acquisition module in this application is mainly used to acquire ambient light sensing data and human body sensing data from the multi-sensor acquisition unit, and then extract ambient light features and human body sensing features and perform feature preprocessing. The model building module in this application is used to establish an ambient light-LED brightness and color temperature adaptive mapping model based on the human visual comfort threshold, and to determine the dynamic adjustment strategy of LED driving by combining the preprocessed human sensory characteristics. The driving adjustment module in this application is used to adaptively adjust the core driving parameters of the LED lighting device according to the dynamic adjustment strategy using a modulation method, so as to achieve precise matching and adjustment of LED brightness and color temperature. The calibration and compensation module in this application is used to collect real-time operating status data of LED lighting equipment and ambient light reference data, and to perform dynamic calibration and parameter compensation on the ambient light-LED brightness and color temperature adaptive mapping model. The iterative optimization module in this application is used to continuously iteratively optimize the output value of the core driving parameters based on the dynamic changes of ambient light sensing data and human body sensing data during the operation of the LED lighting equipment.

[0075] The technical solutions provided by the embodiments disclosed in this application have the following beneficial effects: In this embodiment, multi-dimensional sensing data of ambient light and human body sensing are collected from a multi-sensor acquisition unit, and feature data is extracted and preprocessed. An ambient light-LED brightness and color temperature adaptive mapping model is constructed based on the human visual comfort threshold, and a dynamic adjustment strategy is determined in combination with the human body sensing state. The core parameters of the LED driver are adjusted by PWM modulation to achieve accurate matching of brightness and color temperature. The mapping model is dynamically calibrated and error compensated by ambient light reference data and LED working status data. Finally, the driving parameters are continuously iteratively optimized according to the dynamic changes of the sensing data.

[0076] Therefore, this application achieves accurate acquisition of multi-dimensional data from ambient light and human body sensing through multi-sensor fusion technology, solving the problems of limited information and poor anti-interference capability of traditional single-sensor acquisition, and effectively improving the reliability of sensing and light sensing acquisition. Secondly, an adaptive mapping model based on human visual comfort threshold is constructed to jointly match and adjust the brightness and color temperature of ambient light and LEDs, significantly improving the visual comfort of lighting and meeting the visual needs of humans in different scenarios. Furthermore, differentiated dynamic adjustment strategies are formulated according to different states of human body sensing, realizing high-precision continuous adjustment when people are present, gradual adjustment when people are moving, and low-power standby when no one is present, maximizing energy saving while ensuring the lighting experience. At the same time, the dynamic calibration and error compensation mechanism effectively solves the long-term adjustment error problem caused by sensor drift and LED light decay, extending the effective service life of the system. Finally, through closed-loop iterative optimization, the drive system can adapt to the dynamic changes of ambient light and human body sensing in real time, realizing self-adaptive intelligent drive in all scenarios. In summary, the solution proposed in this application can achieve high-precision, self-adaptive, and fully closed-loop intelligent drive adjustment of LED lighting equipment based on ambient light and human body sensing, while also providing visual comfort, energy efficiency, and long-term stability.

[0077] The technical solutions provided by the embodiments of the present invention have been described in detail above. Specific examples have been used to illustrate the principles and implementation methods of the embodiments of the present invention. The descriptions of the embodiments above are only for helping to understand the principles of the embodiments of the present invention. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the embodiments of the present invention. Therefore, the content of this specification should not be construed as a limitation of the present invention.

Claims

1. An adaptive ambient light LED intelligent sensing driving method for intelligently driving and adjusting LED lighting equipment, characterized in that, Includes the following steps: Ambient light sensing data and human body sensing data are collected from the multi-sensor acquisition unit, and then ambient light features and human body sensing features are extracted and preprocessed. An adaptive mapping model of ambient light-LED brightness and color temperature is established based on the human visual comfort threshold, and the dynamic adjustment strategy of LED driving is determined by combining the pre-processed human sensory characteristics. According to the dynamic adjustment strategy, the core driving parameters of the LED lighting device are adaptively adjusted using a modulation method to achieve precise matching and adjustment of LED brightness and color temperature; Collect real-time operating status data of LED lighting equipment and ambient light reference data, and perform dynamic calibration and parameter compensation on the ambient light-LED brightness and color temperature adaptive mapping model. During the operation of LED lighting equipment, the output values ​​of the core driving parameters are continuously iterated and optimized based on the dynamic changes in ambient light sensing data and human body sensing data.

2. The LED intelligent sensing and driving method for adaptive ambient light as described in claim 1, characterized in that, The process involves acquiring ambient light sensing data and human body sensing data from a multi-sensor acquisition unit, then extracting ambient light features and human body sensing features, and performing feature preprocessing. Specifically, this includes: The ambient light illuminance and color temperature values ​​are collected by the photosensitive sensor and color temperature sensor in the multi-sensor acquisition unit as ambient light sensing data. The infrared sensing signal, human movement trajectory signal and sensing distance value are collected by the infrared sensing sensor and millimeter-wave radar sensor as human body sensing data. Illumination change rate and color temperature fluctuation value are extracted from ambient light sensing data as ambient light characteristics, and effective sensing signal intensity, human movement speed and sensing duration are extracted from human body sensing data as human body sensing characteristics. The median filtering algorithm is used to denoise the ambient light features and human body sensing features. The min-max normalization algorithm is then used to normalize the denoised features to obtain standardized feature data.

3. The LED intelligent sensing and driving method for adaptive ambient light as described in claim 1, characterized in that, The specific steps of establishing an adaptive mapping model between ambient light and LED brightness and color temperature based on human visual comfort threshold include: Collect experimental data on human visual comfort under different ambient light intensities and color temperatures, set human visual comfort thresholds in multiple ranges, and divide the ranges into ambient light intensities and color temperatures. Using the illuminance and color temperature of ambient light as input variables and the optimal matching brightness and color temperature of LEDs as output variables, an adaptive mapping model of ambient light-LED brightness and color temperature based on a BP neural network is constructed. Using the human visual comfort threshold as a constraint, the mapping model is trained and optimized so that the LED brightness and color temperature values ​​output by the model meet the requirements of human visual comfort.

4. The LED intelligent sensing and driving method for adaptive ambient light as described in claim 1, characterized in that, The dynamic adjustment strategy for LED driving, determined by combining pre-processed human body sensing characteristics, specifically includes: The human body sensing status is determined based on the pre-processed human body sensing characteristics. The human body sensing status includes three states: effective sensing of a person, sensing of no one, and human body moving. If there is a person effectively detected, a high-precision continuous adjustment strategy is adopted to make the LED brightness and color temperature change smoothly in real time with the ambient light; if a person is moving, a gradual adjustment strategy is adopted to control the adjustment step size of LED brightness and color temperature to match the speed of human movement; if there is no one detected, a low-power standby adjustment strategy is adopted to adjust the LED brightness to the energy-saving threshold.

5. The LED intelligent sensing and driving method for adaptive ambient light as described in claim 1, characterized in that, The dynamic adjustment strategy employs a modulation method to adaptively adjust the core driving parameters of the LED lighting device, specifically including: The core modulation method is PWM pulse width modulation. The LED brightness value and color temperature value matched in the dynamic adjustment strategy are converted into the corresponding PWM duty cycle and drive current value, which serve as the core driving parameters of the LED lighting device. The drive control unit converts the PWM duty cycle and drive current value into drive electrical signals, which are then input to the drive circuit of the LED lighting equipment to achieve precise matching and adjustment of LED brightness and color temperature without flicker fluctuations during the adjustment process.

6. The LED intelligent sensing and driving method for adaptive ambient light as described in claim 1, characterized in that, The dynamic calibration and parameter compensation of the ambient light-LED brightness and color temperature adaptive mapping model specifically includes: Ambient light reference illuminance and reference color temperature values ​​are collected using a standard light sensor calibrator as ambient light reference data, and the actual operating current, voltage, and brightness values ​​of LED lighting equipment are collected using a current and voltage acquisition module as real-time operating status data. The deviation rate between the LED brightness and color temperature values ​​predicted by the calculation model and the measured values ​​in the actual working state data is adjusted when the deviation rate exceeds the preset threshold. To address the errors caused by sensor drift and LED light decay, an error compensation function is established based on ambient light reference data and LED operating time to compensate for ambient light sensing data and model output values ​​in real time.

7. The LED intelligent sensing and driving method for adaptive ambient light as described in claim 1, characterized in that, The multi-sensor acquisition unit is an integrated sensor module, and the core driving parameters include PWM duty cycle, driving current value, and color temperature adjustment voltage value.

8. An adaptive ambient light LED intelligent sensing and driving system, the system comprising an LED lighting device and a drive control unit, characterized in that, The drive control unit includes: The acquisition module is used to acquire ambient light sensing data and human body sensing data from the multi-sensor acquisition unit, and then extract ambient light features and human body sensing features and perform feature preprocessing. The model building module is used to establish an adaptive mapping model of ambient light-LED brightness and color temperature based on the human visual comfort threshold, and to determine the dynamic adjustment strategy of LED driving by combining the preprocessed human sensory characteristics. The drive adjustment module is used to adaptively adjust the core drive parameters of the LED lighting device according to the dynamic adjustment strategy using a modulation method, so as to achieve precise matching and adjustment of LED brightness and color temperature. The calibration and compensation module is used to collect real-time operating status data and ambient light reference data of LED lighting equipment, and to perform dynamic calibration and parameter compensation on the ambient light-LED brightness and color temperature adaptive mapping model. The iterative optimization module is used to continuously iterate and optimize the output values ​​of the core driving parameters based on the dynamic changes of ambient light sensing data and human body sensing data during the operation of LED lighting equipment.

9. A computer device comprising a memory and a processor, the memory storing code, characterized in that, The processor is configured to acquire the code and execute the LED intelligent sensing driving method for adaptive ambient light as described in any one of claims 1 to 7.

10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it implements the LED intelligent sensing driving method for adaptive ambient light as described in any one of claims 1 to 7.

Images