Progressive light adjusting method and system based on dynamic perception

Abstract

The invention belongs to the technical field of light adjustment, and particularly relates to a progressive light adjustment method and system based on dynamic perception, and the method comprises the steps: collecting environment light information and user behavior data in real time through a non-intrusive sensing device, and guaranteeing that the system always knows a current environment state and user activities; in combination with a preset lighting preference guide, a suitable brightness and color temperature range is defined for each activity, so that personalized lighting experience is provided; the existing illumination is gradually adjusted to the target setting, and the change of the environment and the user behavior is continuously monitored during the adjustment period to ensure that the adjustment path accords with the real-time condition; once a new change is detected, the system re-evaluates the environment state to form a cyclic optimization process, so that light adjustment is ensured to always adapt to user requirements; according to the method, the flexibility and the intelligent level of the intelligent lighting system are remarkably improved, and a more humanized and energy-saving lighting solution is realized.

Description

Technical Field

[0001] The present invention belongs to the technical field of lighting adjustment, and in particular relates to a progressive lighting adjustment method and system based on dynamic perception. Background Art

[0002] Most current smart lighting systems rely on fixed lighting parameters or preset schedules to adjust light brightness and color temperature. These systems typically include: Ambient light sensors: used to detect the light intensity in the environment to automatically adjust the brightness of indoor lights. Timer controllers: automatically adjust lights according to a set schedule, such as gradually increasing brightness in the morning to simulate a sunrise effect. Manual control: allows users to directly control lights through a remote control, mobile phone application or wall switch.

[0003] Although existing technologies can provide automation and convenience to a certain extent, they often lack the ability to deeply understand and dynamically respond to user activity patterns. In particular, when environmental conditions or user behavior change, these systems may not be able to make appropriate adjustments in time, resulting in poor user experience or energy waste.

[0004] The main problem faced by existing intelligent lighting systems is the mismatch between static settings and dynamic needs. Specifically, these systems cannot identify the user's activity type in real time and provide personalized lighting settings based on these activities. This may result in the brightness and color temperature of the light not being suitable for the current needs when the user is performing different activities (such as reading, working, and resting), which in turn affects the user's comfort and work efficiency. Summary of the invention

[0005] The purpose of the present invention is to provide a progressive lighting adjustment method and system based on dynamic perception, which can identify user activities in real time and dynamically adjust lighting settings. This method not only improves user comfort, but also optimizes energy efficiency to solve the problems raised in the above background technology.

[0006] To achieve the above object, the present invention proposes a progressive lighting adjustment method based on dynamic perception, comprising the following steps: Collecting ambient light information and user behavior data, wherein the ambient light information includes brightness level and color temperature parameters, and the user behavior data is obtained through a non-invasive sensing device; Based on the acquired ambient light information and user behavior data, the current environment status is evaluated and whether there are significant changes. If so, the subsequent processing flow is triggered; Analyze user behavior patterns when there are significant changes to identify the user's activity type, and define appropriate brightness and color temperature ranges for each activity based on the identified activity type and referring to pre-set lighting preference guidelines; Select an initial value as the target lighting setting from the appropriate range of brightness and color temperature, and prepare to make adjustments, gradually adjust the existing lighting to the selected target setting, and continuously monitor the changes in ambient light information and user behavior data during the adjustment period to ensure that the adjustment path is in line with the real-time situation; When new changes are detected, the environmental status is re-evaluated, thus forming a cyclic optimization process for lighting adjustment.

[0007] Preferably, the collecting of ambient light information and user behavior data includes: Obtain initial measurements of ambient light brightness and color temperature through non-intrusive sensing devices, and calculate average light level and average color temperature; According to the calculation results, the comprehensive illumination characteristic parameters of the current environment are determined, and the obtained parameters are used to adjust the sensitivity of the non-invasive sensing device to optimize the accuracy of subsequent data collection.

[0008] Preferably, the step of evaluating the current environmental state based on the acquired ambient light information and user behavior data and determining whether there is a significant change includes: Based on the acquired illumination characteristic parameters, the stability index of the current environmental state is calculated; Based on the stability index, determine whether there is a significant change. If it exceeds the preset threshold, it is considered that the environment has changed significantly; otherwise, it is considered that the environment remains stable. When it is determined that there is a significant change, the change rate is calculated, and the obtained change rate is used to decide whether to trigger a subsequent processing flow. If the change rate exceeds a preset threshold, the subsequent processing flow is triggered.

[0009] Preferably, analyzing the user's behavior pattern when there is a significant change to identify the user's activity type includes: Based on the identified significant changes and rates of change, collect a user behavior dataset that covers the frequency and duration of users’ actions under different lighting conditions; According to the data set, the action density of each behavior pattern is calculated, and the obtained action density and lighting characteristic parameters are combined to construct the user activity feature vector; The feature vector is used to match the closest activity type, providing a basis for the next step of lighting settings.

[0010] Preferably, the combination of the identified activity type and referring to a preset lighting preference guide to define a suitable brightness and color temperature range for each activity includes: Based on the identified activity type, query a pre-set lighting preference guide containing recommended brightness and color temperature ranges for different activity types; Based on the recommended brightness and color temperature ranges corresponding to the activity type, calculate the target brightness and target color temperature, and select the middle value in the recommended range as the initial target; Combine the obtained target brightness and target color temperature to evaluate whether the current ambient light characteristics are close to the target settings, and measure the gap by calculating the deviation; Using the deviation, the adjustment strategy is determined. If the deviation exceeds the preset threshold, lighting adjustment is required.

[0011] Preferably, selecting an initial value as a target lighting setting from a range of suitable brightness and color temperature and preparing to perform an adjustment operation includes: Based on the calculated target brightness and target color temperature, determine the initial brightness value and initial color temperature value within the appropriate range, and select the lower limit of the recommended range as the initial value; Based on the initial brightness value and the initial color temperature value, the gap between the current lighting setting and the target is evaluated, measured by calculating the deviation; Based on the obtained deviation, the adjustment path is planned. If the deviation exceeds the preset decimal value, the adjustment increment is set to ensure that the progressive adjustment process is smooth and natural; Use adjustment increments to prepare for the first adjustment operation, gradually adjust the current lighting settings to the initial value, and record the status after this adjustment to provide a benchmark for subsequent adjustments.

[0012] Preferably, the stepwise adjusting the existing lighting to the selected target setting comprises: Based on the determined initial brightness value and initial color temperature value, and the adjustment increment, setting the time interval of each adjustment; According to the time interval, the first adjustment operation is started to gradually adjust the current lighting settings to the initial value, and the state after this adjustment, including the new brightness and color temperature, is recorded. Combined with the obtained state, the target brightness and color temperature for the next adjustment are calculated; Using the target brightness and color temperature, the next adjustment is performed after the next time interval, and this process is repeated until the actual brightness and color temperature reach or approach the target, respectively. The status is updated after each adjustment, and it is checked whether the termination condition is met, that is, whether it is close enough to the target.

[0013] Preferably, during the adjustment period, continuously monitoring the changes in ambient light information and user behavior data to ensure that the adjustment path conforms to the real-time situation includes: The ambient light brightness, color temperature and user behavior data are collected in real time through non-invasive sensing devices. These data are updated at fixed intervals, and the stability index of the current environmental status is recalculated based on the latest data obtained. Based on the stability index, evaluate whether there is a significant change. If it exceeds the preset threshold, it is considered that the environment or user behavior has changed significantly. At this time, recalculate the action density; Using the obtained motion density and new lighting characteristic parameters, an updated user activity feature vector is constructed. The closest activity type is re-matched according to the new feature vector, and the target brightness and target color temperature are adjusted accordingly to ensure that the adjustment path is consistent with the real-time situation.

[0014] Preferably, when a new change is detected, the environmental state is re-evaluated, thereby forming a cyclic optimization process for lighting adjustment, including: When significant changes are detected, new lighting characteristic parameters and user activity feature vectors are recorded; Based on the illumination characteristic parameters, a re-evaluated stability index is calculated; Combined with the obtained stability index, determine whether the environmental status needs to be re-evaluated. If it exceeds the preset threshold, a re-evaluation is triggered; By using the set flag, when the flag indicates that re-evaluation is needed, the environmental state is re-evaluated, the new lighting characteristic parameters and user activity feature vector are used as new input data, the environmental state is re-evaluated, and the target brightness and target color temperature are updated according to the new evaluation results.

[0015] On the other hand, the present invention provides a progressive lighting adjustment system based on dynamic perception, comprising: A data collection module, used to collect ambient light information and user behavior data, wherein the ambient light information includes brightness level and color temperature parameters, and the user behavior data is obtained through a non-invasive sensing device; The environment assessment module is used to evaluate the current environment status based on the acquired ambient light information and user behavior data, and determine whether there is a significant change. If so, it triggers the subsequent processing flow; Activity recognition and preference matching module, which is used to analyze the user's behavior pattern when there is a significant change to identify the user's activity type, and define the appropriate brightness and color temperature range for each activity based on the identified activity type and the pre-set lighting preference guide; The lighting adjustment module is used to select an initial value as the target lighting setting from the range of appropriate brightness and color temperature, and prepare to perform adjustment operations, gradually adjust the existing lighting to the selected target setting, and continuously monitor the changes in ambient light information and user behavior data during the adjustment period to ensure that the adjustment path is in line with the real-time situation; The loop optimization module is used to re-evaluate the environmental status when new changes are detected, thereby forming a loop optimization process for lighting adjustment.

[0016] Technical effects and advantages of the present invention: Compared with the prior art, the present invention provides a progressive lighting adjustment method and system based on dynamic perception, which has the following advantages: The present invention utilizes non-invasive sensing devices to collect ambient light information and user behavior data in real time, ensuring that the system is always aware of the current environmental status and user activities; combined with pre-set lighting preference guidelines, the appropriate brightness and color temperature range is defined for each activity, thereby providing a personalized lighting experience; the existing lighting is gradually adjusted to the target setting, and changes in the environment and user behavior are continuously monitored during the adjustment period to ensure that the adjustment path is in line with the real-time situation; once new changes are detected, the system will re-evaluate the environmental status, forming a cyclic optimization process to ensure that the light adjustment always adapts to user needs; this method significantly improves the flexibility and intelligence level of the intelligent lighting system, and realizes a more humane and energy-saving lighting solution. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 It is a flow chart of the progressive lighting adjustment method based on dynamic perception of the present invention; Figure 2 The block diagram of the progressive lighting adjustment system based on dynamic perception of the present invention. DETAILED DESCRIPTION

[0018] The following will be combined with the accompanying drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments. The specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention. Based on the embodiments in the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0019] The present invention provides a progressive lighting adjustment method based on dynamic perception, which can recognize user activities in real time and dynamically adjust lighting settings. This method not only improves user comfort, but also optimizes energy efficiency. The details are as follows: like Figure 1 As shown, the progressive lighting adjustment method based on dynamic perception proposed in this embodiment includes the following steps: Step 1: Collecting ambient light information and user behavior data, wherein the ambient light information includes brightness level and color temperature parameters, and the user behavior data is obtained through a non-invasive sensing device; further comprising the following sub-processes: The initial measurement values ​​of ambient light brightness L and color temperature T are obtained through non-invasive sensing devices, ensuring that the system can perceive the specific conditions of the current ambient light in real time and accurately, providing a reliable data basis for subsequent processing. The application of non-invasive sensing devices ensures a non-intrusive user experience.

[0020] Based on the L and T values, the average light level A is calculated using the formula A=(L_max+L_min) / 2; the average color temperature B is calculated at the same time using the formula B=(T_max+T_min) / 2; by calculating the average light level A and the average color temperature B, possible instantaneous fluctuations in ambient light can be eliminated, providing more stable and reliable parameters for subsequent analysis and adjustment.

[0021] Based on the obtained A and B, the light characteristic parameter P of the current environment is determined. The formula is P=sqrt(A^2+B^2). This parameter is used to characterize the comprehensive lighting conditions. The light characteristic parameter P comprehensively reflects the brightness and color temperature of the current environment, providing a unified standard for subsequent evaluation. The square root formula is used to combine brightness and color temperature, so that the parameter can better characterize the comprehensive lighting conditions, improving the adaptability and accuracy of the system.

[0022] The calculated P value is used to adjust the sensitivity S of the non-invasive sensing device. The formula is S=P*k, where k is the preset proportional coefficient. The sensitivity of the sensing device is dynamically adjusted according to the light characteristic parameters of the current environment to ensure that subsequent data collection is more accurate, reduce the possibility of misjudgment, and improve the response speed and efficiency of the system.

[0023] Specific, specific composition and principle of non-invasive sensing device: Light sensor: used to measure the brightness level (lux) and color temperature (Kelvin) in the environment. Such sensors can be photodiodes, photoresistors, or more complex RGB / IR color sensors.

[0024] Motion detectors: such as infrared sensors or microwave radar sensors, which are used to capture the presence of people and the frequency and duration of their movements. This helps identify the type of user activity.

[0025] Sound sensor (optional): In some cases, a microphone can also be added to monitor the ambient noise level to help determine whether the user is in a meeting, taking a break, or other specific activities.

[0026] Temperature and humidity sensors (optional): While the main focus is on light conditions, additional environmental parameters such as temperature and humidity can also help to provide a more complete picture of indoor conditions.

[0027] Working principle: Data collection: Each sensor automatically records the ambient light brightness and color temperature, as well as the user's behavior data (such as movement frequency, duration, and position changes) at regular intervals (for example, once a minute). All of this data is transmitted to the central processing unit for analysis.

[0028] Sensitivity adjustment: Based on the calculated comprehensive illumination characteristic parameter P, the system dynamically adjusts the sensitivity S of the non-intrusive sensing device. This means that as the ambient light changes, the sensor can adaptively optimize its working range to ensure the accuracy of subsequent data collection.

[0029] Privacy protection: Non-intrusive sensing devices are designed with privacy issues in mind, avoiding the use of cameras or other technologies that may infringe on personal privacy. They only focus on measuring necessary physical quantities, such as light intensity, color temperature, and the presence or absence of human motion, without involving image or video recording.

[0030] Through the above-mentioned structure and principle, the non-invasive sensing device can provide accurate and timely data input for the intelligent lighting system without affecting the user experience, thereby realizing a more humane and energy-saving lighting solution.

[0031] Assume that in a smart office environment, the dynamic perception-based progressive lighting adjustment system of the present invention is installed. The following are the specific implementation steps: Data collection: Multiple non-intrusive sensing devices are installed on the office ceiling, which automatically record the ambient light brightness L and color temperature T once a minute.

[0032] Initial measurements show that ambient light levels range from 200 to 500 lux (lx) and color temperatures range from 3000 to 5000 Kelvin (K).

[0033] Calculate average light level and color temperature: The system calculates the average light level A=(200+500) / 2=350lx and the average color temperature B=(3000+5000) / 2=4000K.

[0034] Determine the optical characteristic parameters: Based on the above calculation results, the system further determines the light characteristic parameter P=sqrt(350^2+4000^2)≈4007.86, which represents the comprehensive lighting conditions of the current environment.

[0035] Adjust the sensitivity of the sensor: The system calculates the new sensitivity of the sensing device S=Pk=4007.860.01≈40.08 based on the preset proportional coefficient k (for example, k=0.01). This means that the sensing device will continue to monitor environmental changes with higher sensitivity to capture more subtle changes.

[0036] Through accurate data collection and sensitivity adjustment, the system can quickly respond to changes in ambient light and provide a comfortable lighting experience. Avoid unnecessary high or low brightness settings to reduce energy waste. Appropriate lighting conditions help improve employee efficiency and comfort, especially when working for long hours. According to different time periods and activity types, it automatically adjusts to the most suitable brightness and color temperature to meet personalized needs.

[0037] Step 2: Based on the acquired data, evaluate the current environmental status and determine whether there are significant changes. If so, trigger the subsequent processing flow; further including the following sub-flows: Based on the acquired light characteristic parameter P, the stability index Q of the current environment state is calculated, and the formula is Q=|P_current-P_previous| / P_previous; by calculating the stability index Q, the degree of change of the current environment light characteristic relative to the previous state can be quantified. This helps the system accurately determine whether the environment has changed significantly, thereby providing a scientific basis for subsequent processing.

[0038] According to the Q value, it is judged whether there is a significant change. If Q is greater than the preset threshold R, it is considered that the environment has changed significantly; otherwise, it is considered that the environment remains stable. The introduction of threshold R as a judgment standard avoids misjudgment caused by small fluctuations. Only when the change exceeds a certain limit will the system start further processing, which improves the reliability and response efficiency of the system.

[0039] When significant changes are determined, the rate of change F is calculated using the formula F=(P_current-P_previous) / Δt; the rate of change F is used to measure the speed of environmental changes. Rapid changes may mean sudden changes in user activity or external light sources, while slow changes may be gradual changes in natural light. This step helps the system better understand the nature of the changes and provides data support for subsequent adjustment strategies.

[0040] The obtained change rate F is used to decide whether to trigger the subsequent processing flow. If F exceeds another preset threshold G, the subsequent processing flow is triggered. By setting the change rate threshold G, it is ensured that the subsequent processing flow is triggered only when the change speed is fast and the impact is large. This further reduces unnecessary adjustment operations and improves the intelligence level of the system and user experience.

[0041] Assume that in a smart office environment, the dynamic perception-based progressive lighting adjustment system of the present invention is installed. The following are the specific implementation steps: Data collection and initial calculations: The system automatically records the ambient light brightness and color temperature once a minute and calculates the light characteristic parameter P. Assume that the light characteristic parameter obtained by the last measurement is P_previous=4007.86 (see step 1 embodiment).

[0042] Calculate the stability index Q: At the current moment, the new light characteristic parameter P_current=4500 is measured again. Calculate the stability index Q: Q=∣4500-4007.864007.86∣≈0.123Q=4007.864500-4007.86≈0.123; Determine whether there is a significant change: The preset threshold R is set to 0.1 (i.e. 10%). Since Q≈0.123>R, the system determines that the environment has changed significantly.

[0043] Calculate the rate of change F: Assuming that the time interval Δt between two measurements is 1 minute (60 seconds), calculate the rate of change F: F = 4500-4007.8660≈8.19 units / second F = 604500-4007.86≈8.19 units / second; Determine whether to trigger subsequent processing: The preset change rate threshold G is set to 5 units / second. Since F≈8.19>G, the system triggers the subsequent processing flow and prepares to adjust the lighting to adapt to the new environmental conditions.

[0044] By calculating the stability index Q and the rate of change F, the system can accurately determine the magnitude and speed of environmental changes to avoid misjudgment and overreaction. Adjustments are made only when necessary, reducing energy waste caused by frequent adjustments. Quickly respond to significant changes to ensure that lighting settings always meet the actual needs of users and provide a comfortable lighting environment. Appropriate lighting conditions can help improve employee work efficiency, especially when light changes frequently, such as sunrise in the morning or sunset in the evening.

[0045] Step 3: Based on the results of step 2, analyze the user's behavior pattern to identify the user's activity type. This process utilizes the deep analysis of user behavior data; it further includes the following sub-processes: Based on the determined significant changes and change rates F, a user behavior dataset H is collected, which covers the frequency and duration of users' actions under different lighting conditions; by collecting user behavior data in real time, the system can capture users' immediate activity patterns and provide detailed data support for subsequent analysis. This step ensures that the system has a more comprehensive and accurate understanding of user behavior.

[0046] Based on the data set H, the action density I of each behavior pattern is calculated using the formula I=H_actions / H_time; the action density I quantifies the intensity of the user's activities in a specific time period. This indicator helps to distinguish different types of activities (such as work, rest, or movement), thus providing a basis for personalized lighting settings. By calculating the action density, the system can more accurately identify the user's behavior pattern.

[0047] Combining the obtained motion density I and light characteristic parameter P, construct the user activity feature vector J, the formula is J=(I,P); combining the motion density I and light characteristic parameter P, form the user activity feature vector J. This vector comprehensively reflects the relationship between the user's activity pattern and the current lighting conditions, allowing the system to understand the user's needs more comprehensively. In this way, the system can better match the user's actual activity type.

[0048] Using the feature vector J, the closest activity type L is matched through the preset behavior classification rule K. Through the preset behavior classification rule K, the system can quickly and accurately identify the user's current activity type L. This step ensures that the system can adjust the lighting settings according to the user's actual needs, improving the personalization of the user experience. At the same time, using the feature vector J for matching enhances the accuracy of classification.

[0049] Assume that in a smart office environment, the dynamic perception-based progressive lighting adjustment system of the present invention is installed. The following are the specific implementation steps: Significant change detection and user behavior data collection: The system detects a significant change and calculates the rate of change F≈8.19 units / second (see step 2). At this point, the system begins to collect the user behavior data set H, recording the frequency and duration of the user's actions in the next few minutes. For example, the user may be typing at a desk, standing and walking, or having a meeting.

[0050] Calculate the action density I: Assuming that within 5 minutes, the system records 30 obvious actions of the user (such as keyboard tapping, mouse clicking, or standing up), the action density I is calculated and the user activity feature vector J is constructed; Combine the action density I calculated in the previous step and the current light characteristic parameter P (assuming P = 4500, see step 2 embodiment) to construct the user activity feature vector J: J = (6 actions / minute, 4500); The closest matching activity type L: The system compares the feature vector J with the known activity type model through the preset behavior classification rule K. Assume that rule K defines several common activity types and their corresponding feature vector ranges: Working mode: (5-10 actions / minute, 3000-5000) Meeting mode: (10-20 actions / minute, 4000-6000) Rest mode: (0-3 actions / minute, 2000-3500) According to the feature vector J=(6actions / minute,4500), the system determines that the current user is in "working mode".

[0051] By deeply analyzing user behavior data and combining it with light characteristic parameters, the system can accurately identify the user's activity type and avoid misjudgment. It automatically adjusts the lighting brightness and color temperature according to different activity types to provide the lighting conditions that best suit the user's current needs. Appropriate lighting conditions help improve employee work efficiency, especially in the case of long hours of office work, and reduce visual fatigue. The system can quickly respond to changes in user behavior, provide a comfortable lighting experience, and improve the quality of the overall office environment.

[0052] Step 4: Based on the activity types identified in step 3, refer to the pre-set lighting preference guide to define the appropriate brightness and color temperature range for each activity; further including the following sub-processes: According to the identified activity type L, the system queries the pre-set lighting preference guide M, which contains the recommended brightness X and color temperature Y ranges for different activity types. By querying the lighting preference guide, the system can quickly obtain the optimal lighting parameters for a specific activity type, ensuring that subsequent adjustments have a basis. This step ensures that the system's understanding of user needs is more personalized and accurate.

[0053] Based on the recommended brightness X and color temperature Y ranges corresponding to activity type L, the target brightness Z1 and target color temperature Z2 are calculated, and the formulas are Z1=(X_max+X_min) / 2 and Z2=(Y_max+Y_min) / 2 respectively; by calculating the middle value within the recommended range as the initial target setting, the system can provide a reasonable starting point while maintaining comfort. This approach avoids the discomfort caused by extreme settings and provides a basis for subsequent gradual adjustments.

[0054] Based on the combined target brightness Z1 and target color temperature Z2, evaluate whether the current ambient light characteristic parameter P is close to the target setting. The gap is measured by calculating the deviations D1 and D2, with the formulas D1 = |Z1 - C_brightness| and D2 = |Z2 - C_color_temperature| respectively. By calculating the deviations D1 and D2, the system can quantify the gap between the current ambient light and the target setting. This evaluation helps determine whether an adjustment is needed and the extent of the adjustment. This step ensures that the system's response is more accurate and timely.

[0055] Using the deviations D1 and D2, determine the adjustment strategy. If D1 or D2 exceeds the preset thresholds T1 or T2, then lighting adjustment is required. The introduction of the thresholds T1 and T2 as the judgment criteria avoids frequent adjustments caused by minor deviations, improving the system's stability and user experience. Only when the deviation exceeds a certain limit will the system initiate the adjustment operation to ensure the necessity and effectiveness of the adjustment.

[0056] Suppose in an intelligent office environment, the progressive lighting adjustment system based on dynamic perception described in the present invention is installed. The following are the specific implementation steps: Query the lighting preference guide M: The system identifies that the user is in the "working mode" (see the embodiment in step three). Query the lighting preference guide M to obtain that the recommended brightness X range for the "working mode" is 300 to 500 lux (lx), and the color temperature Y range is 4000 to 5000 Kelvin (K).

[0057] Calculate the target brightness Z1 and target color temperature Z2: Z1 = (300 + 500) / 2 = 400 lx; Z2 = (4000 + 5000) / 2 = 4500 K; Evaluate whether the current ambient light characteristic parameter P is close to the target setting: Suppose the current ambient light characteristic parameters are C_brightness = 350 lx and C_color_temperature = 4200 K. Calculate the deviations D1 and D2: D1 = |400 - 350| = 50 lx D2 = |4500 - 4200| = 300 K; Determine the adjustment strategy: The preset threshold T1 is set to 60 lx, and T2 is set to 400 K. Since D1 = 50 < T1 and D2 = 300 < T2, the system determines that the current ambient light characteristics are already close enough to the target setting and no immediate adjustment is required.

[0058] By querying the lighting preference guide and calculating the target settings, the system can provide lighting conditions that meet the needs of the user's current activities, improving the user's comfort and work efficiency. Avoiding unnecessary frequent adjustments reduces energy waste while ensuring that the lighting settings are always within a reasonable range. The introduction of deviation thresholds avoids misjudgments and overreactions caused by small fluctuations, improving the stability and reliability of the system.

[0059] Step 5: From the appropriate range obtained in step 4, select an initial value as the target lighting setting and prepare for adjustment; further including the following sub-processes: Based on the calculated target brightness Z1 and target color temperature Z2, the initial brightness value V1 and initial color temperature value V2 within the appropriate range are determined, with the formula V1=X_min and V2=Y_min; by selecting the minimum value of the recommended range as the initial value, the system ensures that the adjustment starts from a more conservative starting point. This helps reduce the visual impact on the user and provides a smooth transition basis for subsequent gradual adjustments.

[0060] Based on the initial brightness value V1 and the initial color temperature value V2, the gap between the current lighting setting and the target is evaluated and measured by calculating the deviations E1 and E2, with the formulas E1=|V1-C_brightness| and E2=|V2-C_color_temperature| respectively; by calculating the deviations E1 and E2, the system can quantify the gap between the current lighting setting and the target initial value. This evaluation helps determine whether adjustments are needed and the extent of the adjustments, ensuring that the system responds more accurately and promptly.

[0061] Combined with the obtained deviations E1 and E2, the adjustment path is planned. If E1 or E2 exceeds the preset decimal value P1 or P2, the adjustment increments ΔV1 and ΔV2 are set, and the formulas are ΔV1=(Z1-V1) / N and ΔV2=(Z2-V2) / N; if the deviations E1 or E2 exceed the preset decimal values ​​P1 or P2, the adjustment increments ΔV1 and ΔV2 are set. This method ensures that the adjustment process is gradual, avoids abrupt changes, and improves the user experience. At the same time, step-by-step adjustment also makes each adjustment easier to control and optimize.

[0062] Prepare for the first adjustment operation with adjustment increments ΔV1 and ΔV2. Adjust the current lighting settings step by step to the initial values ​​V1 and V2, and record the state U1 after this adjustment. By making adjustments step by step, the system can achieve a smooth transition without disturbing the user. Recording the adjusted state U1 provides a benchmark for subsequent adjustments, ensuring that the entire adjustment process is planned and controlled.

[0063] Suppose in an intelligent office environment, the progressive lighting adjustment system based on dynamic perception described in the present invention is installed. The following are the specific implementation steps: Determine the initial brightness value V1 and the initial color temperature value V2: According to the target brightness Z1 = 400 lx and the target color temperature Z2 = 4500 K calculated in Step 4 (see the embodiment of Step 4), query the recommended brightness X range for the "working mode" is 300 to 500 lx, and the color temperature Y range is 4000 to 5000 K.

[0064] Determine the initial brightness value V1 and the initial color temperature value V2: V1 = 300 lx V2 = 4000 K Evaluate the gap between the current lighting settings and the target: Suppose the current ambient light characteristic parameters are C_brightness = 350 lx and C_color_temperature = 4200 K. Calculate the deviations E1 and E2: E1 = |300 - 350| = 50 lx E2 = |4000 - 4200| = 200 K Plan the adjustment path: The preset small values P1 are set to 60 lx and P2 to 400 K. Since E1 = 50 < P1 and E2 = 200 < P2, the system decides to make an adjustment. Set the adjustment increments ΔV1 and ΔV2. Suppose N = 10 (i.e., the adjustment is completed in 10 steps): ΔV1 = (400 - 300) / 10 = 10 lx / step ΔV2 = (4500 - 4000) / 10 = 50 K / step Prepare for the first adjustment operation: The system gradually adjusts the current lighting settings to the initial values V1 = 300 lx and V2 = 4000 K, and records the state U1 after this adjustment. For example, the system can gradually increase the brightness by 10 lx and the color temperature by 50 K per minute until the initial values are reached.

[0065] By starting the adjustment from a lower initial value, the system reduces the visual impact on the user and provides a more comfortable transition experience. Through step-by-step adjustment, the system can more finely control the adjustment process, ensuring that each adjustment is smooth and progressive, and improving the overall adjustment quality.

[0066] Step 6: Gradually adjust the existing lighting to the target settings selected in Step 5 to ensure a natural transition process without disturbing the user; further including the following sub-processes: Based on the determined initial brightness value V1 and initial color temperature value V2, as well as the adjustment increments ΔV1 and ΔV2, the time interval T_interval for each adjustment is set, and the formula is T_interval=ΔT_base+α*|ΔV|; by calculating the time interval T_interval, the system can ensure that each adjustment is gradual, and dynamically adjust the time interval according to the size of the adjustment increment. This method ensures the naturalness of the transition process, reduces the visual impact on the user, and improves the response speed of the system.

[0067] According to the time interval T_interval, the first adjustment operation is started to gradually adjust the current lighting settings from the existing values ​​to V1 and V2. The state U1 after this adjustment is recorded, where U1 contains the new brightness L1 and color temperature T1; by gradually adjusting and recording the state after each adjustment, the system can ensure that each adjustment is smooth and provide benchmark data for subsequent adjustments. This step ensures that the entire adjustment process is planned and controllable, avoiding abrupt changes.

[0068] Combined with the obtained state U1, the target brightness L_next and color temperature T_next for the next adjustment are calculated, and the formulas are L_next=L1+ΔV1 and T_next=T1+ΔV2 respectively; by calculating the target value for the next adjustment, the system can continue to move towards the target setting, ensuring that each adjustment is moving towards the final goal. This method makes the entire adjustment process more organized and efficient.

[0069] Using L_next and T_next, the next adjustment is performed after the next time interval T_interval. This process is repeated until the actual brightness and color temperature reach or approach the target values ​​Z1 and Z2, respectively. After each adjustment, the state U is updated and the termination conditions are checked, that is, E3=|L_next-Z1|<ε and E4=|T_next-Z2|<ε. By continuously updating the state and checking the termination conditions, the system is able to ensure that the adjustment stops when the target setting is reached and avoid over-adjustment. This approach not only improves the accuracy of the system, but also ensures the smoothness and naturalness of the adjustment process.

[0070] Assume that in a smart office environment, the dynamic perception-based progressive lighting adjustment system of the present invention is installed. The following are the specific implementation steps: Set the time interval T_interval for each adjustment: Assume that the preset basic time interval ΔT_base = 60 seconds (i.e. 1 minute) and the proportional coefficient α = 0.5. According to the adjustment increments ΔV1 = 10lx / step and ΔV2 = 50K / step obtained in step 5, calculate the time interval T_interval: T_interval = 60 + 0.5 * (10 + 50) = 85 seconds To start the first adjustment operation: The system starts to gradually adjust from the current lighting settings (assuming C_brightness = 350lx, C_color_temperature = 4200K) to the initial values ​​V1 = 300lx and V2 = 4000K. After the adjustment, the new state U1 is recorded, assuming that the adjusted brightness L1 = 310lx and color temperature T1 = 4050K.

[0071] Calculate the target brightness L_next and color temperature T_next for the next adjustment: According to the new state U1, calculate the target value for the next adjustment: L_next=310+10=320lx T_next=4050+50=4100K Perform the next adjustment and check the termination condition: After the next time interval T_interval = 85 seconds, the system adjusts the brightness to 320lx and the color temperature to 4100K, and records the new state U2. Repeat this process until the actual brightness and color temperature reach or approach the target values ​​Z1 = 400lx and Z2 = 4500K respectively. After each adjustment, update the state U and check the termination condition: E3=|L_next-400|<ε E4=|T_next-4500|<ε Assume that ε is set to 10lx and 50K, when E3 and E4 are both less than ε, the system considers that the target setting has been reached and stops adjusting.

[0072] By setting appropriate time intervals and gradual adjustments, the system ensures the naturalness and continuity of the transition process, reducing the visual impact on users. Step-by-step adjustments make each adjustment gradual, ensuring the smoothness of the adjustment process and the comfort of the user experience.

[0073] Step 7: Continuously monitor changes in ambient light information and user behavior data to ensure that the adjustment path is consistent with the real-time situation; further including the following sub-processes: The ambient light brightness L and color temperature T as well as user behavior data H_new are collected in real time through non-invasive sensing devices. These data are updated at fixed intervals of Δt. By collecting the latest ambient light information and user behavior data in real time, the system can dynamically perceive environmental changes and ensure that the adjustment path always meets the real-time situation. This step ensures the response speed and accuracy of the system.

[0074] Based on the latest data L, T and H_new, recalculate the stability index Q_new of the current environmental state, the formula is Q_new=|P_current-P_previous| / P_previous; By calculating the new stability index Q_new, the system can quantify the degree of change of the current environmental state relative to the previous state. This evaluation helps the system to detect significant changes in a timely manner and provide a scientific basis for subsequent processing.

[0075] Combined with the Q_new value, evaluate whether there is a significant change. If Q_new exceeds the preset threshold R, it is considered that the environment or user behavior has changed significantly. At this time, recalculate the action density I_new, the formula is I_new=H_new_actions / Δt; introduce the threshold R as the judgment criterion to avoid misjudgment caused by small fluctuations. Only when the change exceeds a certain limit will the system start further processing, which improves the reliability and response efficiency of the system. Recalculating the action density I_new helps to understand the user's behavior pattern more accurately.

[0076] Using the obtained action density I_new and the new ambient light characteristic parameter P_current, construct the updated user activity feature vector J_new, the formula is J_new=(I_new,P_current). Re-match the closest activity type L_new according to J_new, and adjust the target brightness Z1_new and target color temperature Z2_new accordingly. Combine the action density I_new with the new ambient light characteristic parameter P_current to form the updated user activity feature vector J_new. This vector comprehensively reflects the relationship between the user's activity pattern and the current lighting conditions, allowing the system to understand the user's needs more comprehensively.

[0077] Assume that in a smart office environment, the dynamic perception-based progressive lighting adjustment system of the present invention is installed. The following are the specific implementation steps: Real-time collection of ambient light information and user behavior data: The system collects ambient light brightness L, color temperature, and user behavior data H_new in real time every minute (Δt=60 seconds) through non-invasive sensing devices. Assume that the data collected at the current moment is L=380 lx, T=4300 K, and the user behavior data H_new shows that the user has slight movements (such as keyboard tapping).

[0078] Recalculate the stability index Q_new of the current environment state: Assume that the light characteristic parameter measured last time is P_previous=4007.86 (see step 2 embodiment). Calculate the new stability index Q_new: Q_new = |4000 - 4007.86| / 4007.86 ≈ 0.00196 To assess whether there are significant changes: The preset threshold R is set to 0.01 (i.e. 1%). Since Q_new ≈ 0.00196 < R, the system determines that the environment remains stable. However, to ensure accuracy, the system continues to monitor and record user behavior data H_new. Assuming that in the next minute, the user performs 10 obvious actions (such as mouse clicks, keyboard taps, etc.), the action density I_new is calculated: I_new = 10 actions / 60 seconds ≈ 0.167 actions / second Construct the updated user activity feature vector J_new: Combining the newly calculated action density I_new and the current light characteristic parameter P_current=4000, the user activity feature vector J_new is constructed: J_new = (0.167 actions / second, 4000) Re-match the closest activity type L_new, and adjust the target brightness Z1_new and target color temperature Z2_new: The system compares the feature vector J_new with the known activity type model through the preset behavior classification rule K. Assume that rule K defines several common activity types and their corresponding feature vector ranges: Working mode: (0.1-0.3 actions / second, 3000-5000) Conference mode: (0.3-0.5 actions / second, 4000-6000) Rest mode: (0-0.1 actions / second, 2000-3500) According to the feature vector J_new=(0.167 actions / second, 4000), the system determines that the current user is still in "working mode". However, considering that the ambient light characteristic parameter P_current has slightly changed, the system decides to fine-tune the target brightness and color temperature: Z1_new = (300 + 500) / 2 = 400 lx Z2_new = (4000 + 5000) / 2 = 4500K.

[0079] By collecting and analyzing the latest ambient light information and user behavior data in real time, the system can quickly capture any significant changes and ensure that the adjustment path always meets the real-time situation. Adjustments are only made when necessary, reducing energy waste caused by frequent adjustments and achieving more efficient energy management.

[0080] Step 8: When new changes are detected in step 7, return to step 2 to re-evaluate the environmental status, thereby forming a cyclic optimization process to ensure that the lighting always adapts to user needs; further including the following sub-processes: When significant changes are detected, new ambient light characteristic parameters P_new and user activity feature vectors J_new are recorded; by recording these new data, the system provides the latest and most accurate information for subsequent re-evaluation. This step ensures that the system's decisions are based on the latest environmental status, improving the pertinence and accuracy of adjustments.

[0081] Based on P_new and J_new, the re-evaluated stability index Q_recalc is calculated, and the formula is Q_recalc=|P_new-P_previous| / P_previous; by calculating the re-evaluated stability index Q_recalc, the system can quantify the degree of change of the current environment relative to the previous state. This evaluation helps the system determine whether further processing is needed to avoid unnecessary frequent adjustments.

[0082] Combined with the obtained Q_recalc value, determine whether it is necessary to re-evaluate the environmental status. If Q_recalc exceeds the preset threshold R, a re-evaluation is triggered; otherwise, the current adjustment path is continued. At this time, a temporary flag bit M is set. When M=1, it means that a re-evaluation is required; the threshold R is introduced as a judgment standard to avoid misjudgment caused by small fluctuations. Only when the change exceeds a certain limit will the system start a re-evaluation, which improves the reliability and response efficiency of the system. The use of the flag bit M simplifies the control logic and ensures the flexibility and maintainability of the system.

[0083] By using the set flag M, when M=1, the environmental status is re-evaluated. P_new and J_new are used as new input data to re-evaluate the environmental status, and update the target brightness Z1_new and target color temperature Z2_new based on the new evaluation results to ensure that the lighting settings always meet the real-time needs of the user. By re-evaluating the environmental status and updating the target settings, the system can quickly respond to changes in the environment and user behavior, ensuring that the lighting settings always meet the real-time needs of the user. This step forms a closed-loop control system and achieves a continuous optimization effect.

[0084] Assume that in a smart office environment, the dynamic perception-based progressive lighting adjustment system of the present invention is installed. The following are the specific implementation steps: Record the new ambient light characteristic parameter P_new and user activity feature vector J_new: In step seven, the system detects a significant change (see step seven embodiment), and records a new ambient light characteristic parameter P_new=4050 and a user activity feature vector J_new=(0.167 actions / second, 4050).

[0085] Calculate the re-evaluated stability index Q_recalc: Assume that the light characteristic parameter measured last time is P_previous=4007.86 (see step 2 embodiment). Calculate the new stability index Q_recalc: Q_recalc = |4050 - 4007.86| / 4007.86 ≈ 0.0105 Determine whether a reassessment of the environmental status is necessary: The preset threshold R is set to 0.01 (i.e. 1%). Since Q_recalc ≈ 0.0105 > R, the system determines that a re-evaluation is required and sets the flag M=1.

[0086] Conduct a reassessment of the state of the environment: The system takes P_new=4050 and J_new=(0.167 actions / second, 4050) as new input data and re-evaluates the state of the environment. Assume that the result of the re-evaluation shows that the user is still in "work mode", but the ambient light characteristics have changed slightly. Therefore, the system decides to fine-tune the target brightness and color temperature: Z1_new = (300 + 500) / 2 = 400 lx Z2_new = (4000 + 5000) / 2 = 4500K.

[0087] By real-time monitoring and rapid response to significant changes, the system can capture changes in the environment or user behavior at the first opportunity, ensuring timely and effective adjustments. Re-evaluation and adjustment are only performed when necessary, reducing unnecessary operations and achieving more efficient energy management. The system can quickly respond to changes in the environment and user behavior, provide a comfortable lighting environment, and improve the quality of the overall office environment.

[0088] On the other hand, the present invention proposes a progressive lighting adjustment system based on dynamic perception, such as Figure 2 As shown, including: A data collection module, used to collect ambient light information and user behavior data, wherein the ambient light information includes brightness level and color temperature parameters, and the user behavior data is obtained through a non-invasive sensing device; The environment assessment module is used to evaluate the current environment status based on the acquired ambient light information and user behavior data, and determine whether there is a significant change. If so, it triggers the subsequent processing flow; Activity recognition and preference matching module, which is used to analyze the user's behavior pattern when there is a significant change to identify the user's activity type, and define the appropriate brightness and color temperature range for each activity based on the identified activity type and the pre-set lighting preference guide; The lighting adjustment module is used to select an initial value as the target lighting setting from the range of appropriate brightness and color temperature, and prepare to perform adjustment operations, gradually adjust the existing lighting to the selected target setting, and continuously monitor the changes in ambient light information and user behavior data during the adjustment period to ensure that the adjustment path is in line with the real-time situation; The loop optimization module is used to re-evaluate the environmental status when new changes are detected, thereby forming a loop optimization process for lighting adjustment.

[0089] In addition, the above-mentioned data acquisition module, environmental assessment module, activity recognition and preference matching module, lighting adjustment module and loop optimization module are also used to execute other steps of the above-mentioned progressive lighting adjustment method based on dynamic perception when executed, which are not described one by one here.

[0090] In summary, the present invention utilizes non-invasive sensing devices to collect ambient light information and user behavior data in real time, ensuring that the system is always aware of the current environmental status and user activities; combined with pre-set lighting preference guidelines, an appropriate brightness and color temperature range is defined for each activity, thereby providing a personalized lighting experience; the existing lighting is gradually adjusted to the target setting, and changes in the environment and user behavior are continuously monitored during the adjustment period to ensure that the adjustment path is in line with the real-time situation; once new changes are detected, the system will re-evaluate the environmental status, forming a cyclic optimization process to ensure that the light adjustment always adapts to user needs; this method significantly improves the flexibility and intelligence level of the intelligent lighting system, and realizes a more humane and energy-saving lighting solution.

[0091] Finally, it should be noted that the above is only a preferred embodiment of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, it is still possible for those skilled in the art to modify the technical solutions described in the aforementioned embodiments or to make equivalent substitutions for some of the technical features therein. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A progressive lighting adjustment method based on dynamic perception, characterized in that: The following steps are involved: Collecting ambient light information and user behavior data, wherein the ambient light information includes brightness level and color temperature parameters, and the user behavior data is obtained through a non-invasive sensing device; Based on the acquired ambient light information and user behavior data, the current environment status is evaluated and whether there are significant changes. If so, the subsequent processing flow is triggered; Analyze user behavior patterns when there are significant changes to identify the user's activity type, and define appropriate brightness and color temperature ranges for each activity based on the identified activity type and referring to pre-set lighting preference guidelines; Select an initial value as the target lighting setting from the appropriate range of brightness and color temperature, and prepare to make adjustments, gradually adjust the existing lighting to the selected target setting, and continuously monitor the changes in ambient light information and user behavior data during the adjustment period to ensure that the adjustment path is in line with the real-time situation; When new changes are detected, the environmental status is re-evaluated, thus forming a cyclic optimization process for lighting adjustment.

2. The method for progressive lighting adjustment based on dynamic perception according to claim 1, characterized in that: The collecting of ambient light information and user behavior data includes: Obtain initial measurements of ambient light brightness and color temperature through non-intrusive sensing devices, and calculate average light level and average color temperature; According to the calculation results, the comprehensive illumination characteristic parameters of the current environment are determined, and the obtained parameters are used to adjust the sensitivity of the non-invasive sensing device to optimize the accuracy of subsequent data collection.

3. The method of progressive lighting adjustment based on dynamic perception according to claim 2, characterized in that: The method of evaluating the current environment state based on the acquired ambient light information and user behavior data and determining whether there is a significant change includes: Based on the acquired illumination characteristic parameters, the stability index of the current environmental state is calculated; Based on the stability index, determine whether there is a significant change. If it exceeds the preset threshold, it is considered that the environment has changed significantly; otherwise, it is considered that the environment remains stable. When it is determined that there is a significant change, the change rate is calculated, and the obtained change rate is used to decide whether to trigger a subsequent processing flow. If the change rate exceeds a preset threshold, the subsequent processing flow is triggered.

4. The method of progressive lighting adjustment based on dynamic perception according to claim 3, characterized in that: Analyzing the user's behavior pattern when there is a significant change to identify the user's activity type includes: Based on the identified significant changes and rates of change, collect a user behavior dataset that covers the frequency and duration of users’ actions under different lighting conditions; According to the data set, the action density of each behavior pattern is calculated, and the obtained action density and lighting characteristic parameters are combined to construct the user activity feature vector; The feature vector is used to match the closest activity type, providing a basis for the next step of lighting settings.

5. The method for progressive lighting adjustment based on dynamic perception according to claim 4, characterized in that: The combination of the identified activity type and the preset lighting preference guide is used to define the appropriate brightness and color temperature range for each activity, including: Based on the identified activity type, query a pre-set lighting preference guide containing recommended brightness and color temperature ranges for different activity types; Based on the recommended brightness and color temperature ranges corresponding to the activity type, calculate the target brightness and target color temperature, and select the middle value in the recommended range as the initial target; Combine the obtained target brightness and target color temperature to evaluate whether the current ambient light characteristics are close to the target settings, and measure the gap by calculating the deviation; Using the deviation, the adjustment strategy is determined. If the deviation exceeds the preset threshold, the lighting needs to be adjusted.

6. The method for progressive lighting adjustment based on dynamic perception according to claim 5, characterized in that: The process of selecting an initial value as a target lighting setting from a range of suitable brightness and color temperature and preparing for adjustment includes: Based on the calculated target brightness and target color temperature, determine the initial brightness value and initial color temperature value within the appropriate range, and select the lower limit of the recommended range as the initial value; Based on the initial brightness value and the initial color temperature value, the gap between the current lighting setting and the target is evaluated, measured by calculating the deviation; Based on the obtained deviation, the adjustment path is planned. If the deviation exceeds the preset decimal value, the adjustment increment is set to ensure that the progressive adjustment process is smooth and natural; Use adjustment increments to prepare for the first adjustment operation, gradually adjust the current lighting settings to the initial value, and record the status after this adjustment to provide a benchmark for subsequent adjustments.

7. The method of progressive lighting adjustment based on dynamic perception according to claim 6, characterized in that: The step-by-step process of adjusting the existing lighting to the selected target setting includes: Based on the determined initial brightness value and initial color temperature value, and the adjustment increment, setting the time interval of each adjustment; According to the time interval, the first adjustment operation is started to gradually adjust the current lighting settings to the initial value, and the state after this adjustment, including the new brightness and color temperature, is recorded. Combined with the obtained state, the target brightness and color temperature for the next adjustment are calculated; Using the target brightness and color temperature, the next adjustment is performed after the next time interval, and this process is repeated until the actual brightness and color temperature reach or approach the target, respectively. The status is updated after each adjustment, and it is checked whether the termination condition is met, that is, whether it is close enough to the target.

8. The method for progressive lighting adjustment based on dynamic perception according to claim 7, characterized in that: During the adjustment period, the changes in ambient light information and user behavior data are continuously monitored to ensure that the adjustment path conforms to the real-time situation, including: The ambient light brightness, color temperature and user behavior data are collected in real time through non-invasive sensing devices. These data are updated at fixed intervals, and the stability index of the current environmental status is recalculated based on the latest data obtained. Based on the stability index, evaluate whether there is a significant change. If it exceeds the preset threshold, it is considered that the environment or user behavior has changed significantly. At this time, recalculate the action density; Using the obtained motion density and new lighting characteristic parameters, an updated user activity feature vector is constructed. The closest activity type is re-matched according to the new feature vector, and the target brightness and target color temperature are adjusted accordingly to ensure that the adjustment path is consistent with the real-time situation.

9. The method for progressive lighting adjustment based on dynamic perception according to claim 8, characterized in that: When a new change is detected, the environment status is re-evaluated, thereby forming a cyclic optimization process for lighting adjustment, including: When significant changes are detected, new lighting characteristic parameters and user activity feature vectors are recorded; Based on the illumination characteristic parameters, a re-evaluated stability index is calculated; Combined with the obtained stability index, determine whether the environmental status needs to be re-evaluated. If it exceeds the preset threshold, a re-evaluation is triggered; By using the set flag, when the flag indicates that re-evaluation is needed, the environmental state is re-evaluated, the new lighting characteristic parameters and user activity feature vector are used as new input data, the environmental state is re-evaluated, and the target brightness and target color temperature are updated according to the new evaluation results.

10. A progressive lighting adjustment system based on dynamic perception for implementing the method according to any one of claims 1 to 9, characterized in that: include: A data collection module, used to collect ambient light information and user behavior data, wherein the ambient light information includes brightness level and color temperature parameters, and the user behavior data is obtained through a non-invasive sensing device; The environment assessment module is used to evaluate the current environment status based on the acquired ambient light information and user behavior data, and determine whether there is a significant change. If so, it triggers the subsequent processing flow; Activity recognition and preference matching module, which is used to analyze the user's behavior pattern when there is a significant change to identify the user's activity type, and define the appropriate brightness and color temperature range for each activity based on the identified activity type and the pre-set lighting preference guide; The lighting adjustment module is used to select an initial value as the target lighting setting from the range of appropriate brightness and color temperature, and prepare to perform adjustment operations, gradually adjust the existing lighting to the selected target setting, and continuously monitor the changes in ambient light information and user behavior data during the adjustment period to ensure that the adjustment path is in line with the real-time situation; The loop optimization module is used to re-evaluate the environmental status when new changes are detected, thereby forming a loop optimization process for lighting adjustment.

Images