Intelligent self-adaptive lighting system based on environment perception and behavior recognition

Abstract

The invention provides an intelligent self-adaptive lighting system based on environmental perception and behavior recognition, relates to the technical field of self-adaptive lighting control, and aims to determine an illumination perception rule during adaptive adjustment of the brightness of a lighting source in a target area according to a lighting adjacent path and dynamic atmosphere information, perform layered compensation on the illumination perception rule, and improve the brightness of the lighting source in the target area. Obtaining an adaptive compensation strategy when the illumination angle of the illumination light source is adjusted; according to the posture activity index and the behavior response index, determining a state partition constraint when the illumination light source in the target area carries out illumination partition decision making along with the user motion trail, and determining a light color rheological characteristic when the illumination light source carries out color temperature switching according to the state partition constraint; and carrying out self-correction matching on the illumination demand mode in the illumination environment of the target area according to the adaptive compensation strategy and the light color rheological characteristics. According to the invention, linkage self-correction control can be carried out on the illumination mechanism of the illumination light source, so that the real-time response capability of the intelligent illumination system under the driving of complex space behaviors is improved.

Description

Technical Field

[0001] The present application relates to the field of adaptive lighting control technology, and more specifically, to an intelligent adaptive lighting system based on environmental perception and behavior recognition. Background Art

[0002] Adaptive lighting control is a method that dynamically adjusts the lighting system's output parameters based on real-time perception of various environmental factors, including natural light intensity, spatial layout, number of users, and activity type, combined with user behavioral characteristics such as activity frequency, movement trajectory, and location distribution, to intelligently match and optimize lighting effects. This control mechanism automatically switches lighting modes based on the user's needs in different scenarios, such as reading, resting, walking, and meetings, thereby improving lighting comfort and energy efficiency.

[0003] However, existing intelligent adaptive lighting control based on environmental perception and behavior recognition suffers from issues such as a lag in the illumination adjustment mechanism's response to changes in user local behavior, a lack of dynamic compensation strategies for lighting angle adjustment, and a disconnect between color temperature switching and user motion. This makes it difficult for the lighting system to accurately adapt lighting effects under multi-scene switching and dynamic behavior. Consequently, the lighting environment's spatial distribution and color perception cannot meet users' immediate lighting comfort needs, limiting the stability of intelligent lighting systems in highly dynamic environments. Therefore, the industry faces the challenge of implementing linked self-correction control over the lighting mechanism of lighting sources to improve the real-time responsiveness of intelligent lighting systems driven by complex spatial behavior. Summary of the Invention

[0004] The present application provides an intelligent adaptive lighting system based on environmental perception and behavior recognition, which can perform linked self-correction control on the lighting mechanism of the lighting source to improve the real-time response capability of the intelligent lighting system under the drive of complex spatial behavior.

[0005] In a first aspect, the present application provides an intelligent adaptive lighting system based on environmental perception and behavior recognition, the adaptive lighting system comprising: The data acquisition module is used to collect dynamic atmosphere information of the lighting environment in the target area and behavioral response indicators during user activities in real time; A hierarchical compensation module is configured to determine an adjacent lighting path of a lighting scene in a target area, determine an illuminance perception rule for adaptively adjusting the brightness of the lighting source in the target area based on the adjacent lighting path and the dynamic atmosphere information, perform hierarchical compensation on the illuminance perception rule, and obtain an adaptive compensation strategy for adjusting the lighting angle of the lighting source; a zoning constraint module, configured to obtain a posture activity index when the user is active in a target area, determine a state zoning constraint for the lighting light source in the target area when making lighting zoning decisions along the user's motion trajectory based on the posture activity index and the behavioral response index, and further determine the light color rheological characteristics of the lighting light source when switching color temperature based on the state zoning constraint; The self-correction module is used to perform self-correction matching on the lighting demand pattern in the lighting environment of the target area according to the adaptation compensation strategy and the light color rheology characteristics.

[0006] In this embodiment, the dynamic atmosphere information refers to a multi-dimensional perception data set of the current light environment state of the target area.

[0007] In this embodiment, the behavioral response index refers to the behavioral data of the user's body posture, movement reaction, and spatial displacement under different lighting conditions.

[0008] In this embodiment, determining the adjacent lighting paths of the lighting scene in the target area specifically includes: determining an initial lighting deviation of the target area according to initial environmental parameters under a static lighting state; Determining a steady-state illumination gradient of a lighting scene change by using the initial illumination deviation; An illumination proximity path of an illumination scene in a target area is determined according to the steady-state illumination gradient.

[0009] In this embodiment, the illuminance perception rule is subjected to layered compensation to obtain an adaptive compensation strategy when the lighting light source adjusts the lighting angle, specifically including: Determine the spatial position characteristics and luminous flux elasticity margin of the lighting source through the illumination perception rule; generating conflict resolution information when adjusting the lighting angle according to the spatial position feature and the luminous flux elastic margin; The conflict resolution information is used to determine an adaptation compensation strategy for adjusting the lighting angle of the lighting source.

[0010] In this embodiment, obtaining the posture activity index of the user when moving in the target area specifically includes: Collect dynamic fluctuation indicators of user joint movements in the target area; Determining the amount of gesture sequence response in the user activity history data; A gesture activity index when the user is active in the target area is determined according to the dynamic fluctuation index and the gesture sequence response amount.

[0011] In this embodiment, the user motion trajectory refers to the position movement path of the user in a designated area that changes over time.

[0012] In this embodiment, the lighting zoning decision refers to the process of dividing the lighting area according to user distribution and regional requirements and controlling the lighting intensity and switch status of each zone as needed.

[0013] In this embodiment, the light color rheological characteristics of the lighting source when the color temperature is switched are determined by the state partition constraint and specifically include: generating a rheological configuration rule for color temperature switching based on the state partition constraint; Determine the light color correction information of the lighting source during the color temperature switching process; The light color rheological characteristics of the lighting light source when the color temperature is switched are determined according to the rheological configuration rule and the light color correction information.

[0014] In this embodiment, performing self-correction matching on the lighting demand pattern in the lighting environment of the target area according to the adaptation compensation strategy and the light color rheological characteristics specifically includes: Determining the balance feedback intensity when adjusting the lighting demand mode in the lighting environment of the target area according to the adaptive compensation strategy; Determining the allocation guidance attributes when allocating the lighting demand mode in the lighting environment of the target area through the light color rheological characteristics; A self-correction matching strategy for the target area lighting demand pattern is determined by the balance feedback strength and the adjustment guidance attribute, and self-correction matching is performed on the lighting demand pattern in the target area lighting environment according to the self-correction matching strategy.

[0015] The technical solutions provided by the embodiments disclosed in this application have the following beneficial effects: By collecting the dynamic atmosphere information of the lighting environment in the target area and the behavioral response indicators of the user during activities in real time; determining the lighting adjacent path of the lighting scene in the target area, determining the illuminance perception rules when adaptively adjusting the brightness of the lighting source in the target area based on the lighting adjacent path and the dynamic atmosphere information, performing layered compensation on the illuminance perception rules, and obtaining an adaptive compensation strategy when the lighting source adjusts the lighting angle; obtaining the posture activity index of the user when he is active in the target area, determining the state partitioning constraints when the lighting source in the target area makes lighting partitioning decisions along the user's motion trajectory based on the posture activity index and the behavioral response indicators, and then determining the light color rheological characteristics of the lighting source when switching color temperature based on the state partitioning constraints; and performing self-correction matching on the lighting demand pattern in the lighting environment of the target area based on the adaptive compensation strategy and the light color rheological characteristics.

[0016] It can be seen from this that in the present application, the lighting environment and user behavior status can be multi-dimensionally linked and adjusted in the intelligent lighting control scenario; among them, by real-time collection of dynamic atmosphere information of the lighting environment in the target area and behavioral response indicators during user activities, it is possible to realize instant perception of ambient light disturbances and changes in user behavior, comprehensively build a dynamic input foundation for lighting scenes, and thus improve the environmental adaptability and behavioral response accuracy of the lighting control system in complex spaces; by determining the illuminance perception rules when adaptively adjusting the brightness of the lighting source according to the lighting adjacent paths and dynamic atmosphere information, and performing layered compensation to obtain the adaptive compensation strategy when adjusting the lighting angle, it is possible to incorporate the illuminance transition rules and individual perception differences into the process of adjusting the light source brightness and spatial lighting angle, realize gradual coordination of illuminance control and elastic compensation of spatial lighting coverage, and effectively improve the balance of light distribution and user Visual comfort; by obtaining the posture activity index of the user when he is active in the target area, and combining it with the behavioral response index to determine the state partitioning constraints of the lighting light source when making lighting partitioning decisions according to the user's movement trajectory, and further determining the light color rheological characteristics when the color temperature is switched, the lighting system can achieve continuous linkage of partition response and color temperature adjustment under changes in user behavior frequency and movement trajectory, dynamically optimize the degree of matching of the lighting system to the user's intention, and enhance the consistency and immersion of the light environment and individual behavior; by self-correcting and matching the lighting demand pattern in the lighting environment of the target area based on the adaptive compensation strategy and light color rheological characteristics, the lighting system can achieve self-optimization and parameter fine-tuning of the lighting control strategy in long-term operation, and build a feedback closed-loop structure with adaptive regulation capabilities, thereby improving the response speed, strategy accuracy and light environment stability of the lighting system in changing scenarios.

[0017] In summary, the technical solution adopted in this application can perform linked self-correction control on the lighting mechanism of the lighting source to improve the real-time response capability of the intelligent lighting system driven by complex spatial behaviors. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following is a brief introduction to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only the embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0019] Figure 1 This is a module structure diagram of an intelligent adaptive lighting system based on environmental perception and behavior recognition provided by this application; Figure 2 This is a flow chart of determining illumination perception rules according to the present application; Figure 3This is a flow chart of determining state partition constraints provided by this application. DETAILED DESCRIPTION

[0020] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0021] An embodiment of the present application provides an intelligent adaptive lighting system based on environmental perception and behavior recognition, the core of which is to collect dynamic atmosphere information of the lighting environment in the target area and behavioral response indicators during user activities in real time; determine the lighting proximity path of the lighting scene in the target area, determine the illuminance perception rules when adaptively adjusting the brightness of the lighting source in the target area based on the lighting proximity path and the dynamic atmosphere information, perform layered compensation on the illuminance perception rules, and obtain an adaptive compensation strategy when the lighting source adjusts the lighting angle; obtain the posture activity index of the user when he is active in the target area, determine the state partition constraint of the lighting source in the target area when making lighting partition decisions along the user's motion trajectory based on the posture activity index and the behavioral response indicator, and then determine the light color rheological characteristics of the lighting source when switching color temperature based on the state partition constraint; and self-correct and match the lighting demand pattern in the lighting environment of the target area based on the adaptive compensation strategy and the light color rheological characteristics.

[0022] In order to better understand the above technical solution, the following will be described in detail with reference to the accompanying drawings and specific implementation methods. Figure 1 As shown in FIG, this figure is a module structure diagram of an intelligent adaptive lighting system based on environment perception and behavior recognition according to this embodiment of the present application. The adaptive lighting system includes: a data acquisition module 100, a layered compensation module 200, a partition constraint module 300 and a self-correction module 400, which are described as follows: The data collection module 100 is used to collect dynamic atmosphere information of the lighting environment in the target area and behavioral response indicators of users during activities in real time.

[0023] In a specific implementation, multiple high-sensitivity light sensors (such as digital illuminometers) and full-spectrum sensors are deployed in the target area to collect real-time data on light intensity, color temperature variations, and lighting uniformity at different locations. Cameras are used to perform image processing on the light-dark contrast, shadow direction, and color distribution in the environment. The real-time collected data and the processed image results are used as dynamic atmosphere information. To obtain user activity response data, three-dimensional visual recognition cameras or millimeter-wave radar equipment can be deployed in the space, combined with deep learning gesture recognition algorithms, to capture the user's head direction, body rotation, walking path, hand movements, etc. Based on the response time delay, movement frequency, and space occupancy, behavioral response indicators are generated during the user's activity. In other embodiments, other methods can also be used to obtain dynamic atmosphere information of the lighting environment in the target area and behavioral response indicators during user activity, which are not limited here.

[0024] It should be noted that in this application, dynamic atmosphere information refers to a multi-dimensional perception data set of the current light environment state of the target area; behavioral response indicators refer to the behavioral data of the user's body posture, movement reaction and spatial displacement under different lighting conditions.

[0025] The layered compensation module 200 is used to determine the lighting adjacent path of the lighting scene in the target area, determine the illuminance perception rules when the brightness of the lighting light source in the target area is adaptively adjusted based on the lighting adjacent path and the dynamic atmosphere information, perform layered compensation on the illuminance perception rules, and obtain an adaptive compensation strategy when the lighting angle of the lighting light source is adjusted.

[0026] In this embodiment, the following method may be used to determine the adjacent lighting paths of the lighting scene in the target area: determining an initial lighting deviation of the target area according to initial environmental parameters under a static lighting state; Determining a steady-state illumination gradient of a lighting scene change by using the initial illumination deviation; An illumination proximity path of an illumination scene in a target area is determined according to the steady-state illumination gradient.

[0027] In specific implementation, with the lighting system in a static state, multiple digital illuminance sensors and color temperature sensors deployed throughout the target area collect current illumination and color temperature data. Each sensor is associated with a spatial cell in the regional grid. A preset standard illuminance and color temperature reference template (e.g., based on the national architectural lighting standard GB 50034) is then used to compare the numerical deviation between the measured value and the reference value for each spatial cell. This deviation is used as the initial illumination deviation for the target area. Based on this initial illumination deviation, the initial illumination deviation data is mapped into a two-dimensional or three-dimensional spatial coordinate system. By establishing the relative illuminance change rate between each grid cell, the gradient between adjacent cells (i.e., the magnitude of illuminance change per unit distance) is calculated. The central difference method is used to calculate the spatial first-order gradient of the illuminance deviation. Subsequently, an illuminance gradient vector field is constructed, with the direction of the arrow representing the direction of illumination change and the length of the arrow representing the gradient strength. This forms a steady-state illumination gradient for the changing lighting scene. Finally, regions in space with consistent steady-state lighting gradients or continuous steady-state lighting gradients are clustered. Region growing can be used to expand from the local core of the steady-state lighting gradient to the surrounding area, identifying multiple connected blocks of the steady-state lighting gradient. The lighting fixtures within each connected block are considered a group of neighboring lighting nodes. The actual impact of each node on the illumination of surrounding nodes is then analyzed, and a "node-influence intensity" matrix is ​​constructed. Graph theory methods (such as the Dijkstra algorithm) are used to create a path graph, defining weighted edges from each lighting node to its neighboring nodes. This results in the illumination neighboring paths of the lighting scene in the target area.

[0028] It should be noted that, in this application, the initial environmental parameters refer to the characteristic values ​​of the measured illuminance and color temperature of each spatial position in the environment under static lighting conditions; the initial lighting deviation refers to the degree of deviation between the actual illuminance of each spatial unit in the target area and the preset standard lighting value before the lighting system is dynamically adjusted; the steady-state lighting gradient refers to the stable distribution trend formed by the change of color temperature between different spatial positions under the current lighting conditions; the lighting adjacent path refers to the linkable path network formed by multiple lighting sources that physically and logically influence each other in the lighting scene.

[0029] Preferably, in this embodiment, the illumination perception rule for adaptively adjusting the brightness of the lighting source in the target area is determined according to the lighting adjacent path and the dynamic atmosphere information, referring to Figure 2 As shown in FIG, this figure is a schematic diagram of a process for determining illumination perception rules in some embodiments of the present application. In this embodiment, determining illumination perception rules can be implemented by using the following steps: In step S21, the illumination transition sequence when the brightness of the illumination light source in the target area is adaptively adjusted is analyzed through the illumination proximity path; In step S22, the ambient light interference factor and the user preference sequence in the dynamic atmosphere information are extracted; In step S23, a dynamic perception gap is generated when the brightness of the lighting source is adaptively adjusted according to the illumination transition sequence and the ambient light interference factor; In step S24, the illumination perception rule for adaptively adjusting the brightness of the lighting source in the target area is determined based on the dynamic perception gap and the user preference sequence.

[0030] In specific implementation, the path connection sequence between each lighting source and its adjacent light sources is first obtained, and the physical distance, illuminance superposition relationship, and influence direction between each pair of nodes are extracted. Using a brightness adjustment simulation model, the starting light source is set to perform brightness enhancement or attenuation operations. This brightness change is then propagated along the adjacent paths, and the intensity of the illuminance impact on each light source is calculated. By superimposing the actual illuminance changes at each node and sequentially recording the illuminance value changes at each node, a recursive illuminance transition sequence is generated along the path starting from the starting node. This is the illuminance transition sequence when the brightness of the lighting source in the target area is adaptively adjusted. Next, an illumination sensor array collects incident illuminance values ​​at different time periods and spatial locations and compares them with the lighting system output illuminance to identify excess brightness sources (such as window sunlight and display screen light). Wavelength spectrum analysis technology is used to determine the light source type and annotate interference attributes, thereby obtaining an ambient light interference factor. This ambient light interference factor includes information such as light source type, interference intensity, and location distribution. Regarding user preferences, historical dimming records are correlated with user behavioral response indicators (such as frequent head turning, eye covering, and light avoidance). A sequence mining algorithm based on a hidden Markov model is used to extract the brightness change trajectories and adjustment ranges selected or preferred by users in different scenarios, forming a user preference sequence. The theoretical illuminance values ​​of each lighting node in the illuminance transition sequence are then compared with the measured illuminance values ​​corrected for ambient light interference factors. The illuminance difference at each node is calculated and used as the brightness perception gap. Finally, the dynamic perception gap and the user preference sequence are fused into a model and fed as an input vector into a brightness adaptation decision model based on fuzzy logic control. Each rule in this brightness adaptation decision model consists of three prerequisites: the illuminance transition level, the perception gap threshold range, and the user preference label; and an output result: the adjustment level and the ramp coefficient. The corresponding rule is then matched to the current state, outputting a brightness adjustment target value and transition curve. This brightness adjustment target value and transition curve serve as the illuminance perception rule for brightness adaptation of the lighting source in the target area.

[0031] It should be noted that, in the present application, the illumination transition sequence refers to the illumination level difference sequence caused by the change in light intensity between each lighting unit when the lighting light source adjusts the brightness in the order of adjacent paths; the ambient light interference factor refers to the key factor that causes interference to the overall lighting environment caused by the non-lighting system light source in the target area; the user preference sequence refers to the historical preference behavior data set of users for brightness intensity, transition rhythm, and light direction in different situations; the dynamic perception gap refers to the perception delay area formed between the actual brightness perception effect and the target brightness expectation due to environmental interference during the adjustment process of the lighting system; the illumination perception rule refers to the judgment criteria generated by the lighting system based on the current illumination state, user perception needs, and the degree of interference influence for controlling the brightness adjustment amplitude, rhythm, and direction of the light source.

[0032] In this embodiment, the illumination perception rule is subjected to layered compensation to obtain an adaptive compensation strategy for adjusting the illumination angle of the illumination light source, which can be specifically implemented by the following steps, namely: Determine the spatial position characteristics and luminous flux elasticity margin of the lighting source through the illumination perception rule; generating conflict resolution information when adjusting the lighting angle according to the spatial position feature and the luminous flux elastic margin; The conflict resolution information is used to determine an adaptation compensation strategy for adjusting the lighting angle of the lighting source.

[0033] In its implementation, multiple light sensors deployed within the target lighting area collect real-time illuminance values ​​at each spatial location. The collected illuminance data is then matched against pre-set illuminance perception rules. The actual illuminance distribution of each light source is spatially fitted to extract its illumination coverage boundary, primary illumination direction, and restricted area angle. The spatial positional characteristics of the light source are determined using a three-dimensional spatial coordinate system. The luminous flux elasticity margin of the light source is calculated based on the ratio of its rated luminous flux, current output power, and remaining dimming capacity. A luminance coverage relationship diagram is then established between the light sources to identify areas where illumination overlap or illumination gaps may occur under different angle adjustment conditions. A conflict resolution model is constructed based on this illuminance coverage diagram. An angle adjustment simulation function is used to predict the coverage changes of each light source at different angles. The light intensity in the overlapping area is dynamically adjusted based on the luminous flux elasticity margin. This generates angle configuration combinations that, under specific adjustment scenarios, do not cause local overexposure or dark areas. These angle configuration combinations serve as conflict resolution information for lighting angle adjustment. Finally, the light source with the least constraint is adjusted first, and its angle adjustment range is selected from the conflict resolution information to select the maximum amplitude direction without cross-interference; secondly, for the target light source that has overlapping interactions with multiple light sources, its current luminous flux elastic margin is calculated, and its output power is adjusted in conjunction with the angle adjustment to ensure that the total illuminance of the affected area remains within the acceptable range specified by the illuminance perception rules; thirdly, for the dynamically illuminated area, the local illuminance reconstruction algorithm is used to adjust the angle and power of the edge light source to compensate for the boundary deviation caused by non-uniform illumination. This process is used as an adaptive compensation strategy for the lighting angle adjustment of the lighting source.

[0034] It should be noted that, in this application, lighting angle adjustment refers to the process of dynamically changing the spatial direction of the light emitted by the lighting light source according to the changes in the lighting requirements of the target area; the spatial position feature refers to the positional relationship between the lighting light source and the illuminated area in the three-dimensional coordinate system; the luminous flux elastic margin refers to the dynamic adjustment capability space between the current output power of the light source and its rated output power; the conflict resolution information refers to the constraint data structure of the mutual influence between light sources during the lighting angle adjustment process; the adaptive compensation strategy refers to a control scheme that performs dual adjustment of angle and power based on the current environment and light source status to maintain stable illumination in the target area.

[0035] The partition constraint module 300 is used to obtain the posture activity index of the user when the user is active in the target area, and determine the state partition constraint of the lighting light source in the target area when making lighting partition decisions along the user's motion trajectory based on the posture activity index and the behavioral response index. The state partition constraint is then used to determine the light color rheological characteristics of the lighting light source when switching color temperature.

[0036] In this embodiment, obtaining the posture activity index of the user when moving in the target area can be specifically achieved by using the following steps, namely: Collect dynamic fluctuation indicators of user joint movements in the target area; Determining the amount of gesture sequence response in the user activity history data; A gesture activity index when the user is active in the target area is determined according to the dynamic fluctuation index and the gesture sequence response amount.

[0037] In specific implementation, multimodal sensing devices (such as depth cameras, millimeter-wave radars, and inertial measurement units) are first used to track the three-dimensional spatial motion trajectory of the user's major joints (including shoulders, elbows, knees, and hips) in real time within the target area. By establishing a time series of joint positions on a continuous time axis, the displacement amplitude change curve of each joint per unit time is calculated, and joint velocity, acceleration, and their changing trends are extracted from this. This continuous change process is then divided into discrete sliding windows, and the standard deviation of the motion amplitude, the maximum instantaneous rate of change, and rhythmicity indicators within each time period are extracted. Ultimately, dynamic fluctuation indicators of the user's joint motion within the target area are generated. Then, the user's historical posture sequences collected at different time periods are normalized and encoded. A posture recognition model (such as a posture sequence analysis model based on the fusion of a convolutional neural network and a long short-term memory network) is used to extract skeletal structure features in each frame. The posture sequence response degree of posture changes is constructed based on the rhythmicity, amplitude, and time interval of the skeletal structure changes. By setting behavioral classification criteria, the posture sequence response degree is classified into different activity categories (such as walking, standing, waving, and turning). The classification results are used as the posture sequence response quantity in the user's activity history data. Finally, the dynamic fluctuation index extracted in the current period is normalized and mapped to the posture sequence response quantity. The index is normalized using a weighted fusion model, and a comprehensive score is calculated using linear weighting or attention-based feature fusion methods. This fusion model establishes a mapping relationship between user behavior data and activity level based on a machine learning regression framework (such as support vector regression or random forest regression). During model training, the labeled activity level in the historical data is used as a supervisory signal for fitting. The final fitted value is used as the posture activity index when the user is active in the target area.

[0038] It should be noted that, in this application, the dynamic fluctuation index refers to a numerical expression for measuring the fluctuation of the displacement, velocity and acceleration of the user's body joints over time during the activity process; the user activity history data refers to a time-series data set that records the user's movement posture, behavior trajectory and movement amplitude at each time node in a specific area; the posture sequence response quantity refers to the quantitative result of the amplitude, speed and duration of each posture change of the user over a period of time; the posture activity index refers to the numerical level of the user's current activity intensity, movement switching frequency and behavior complexity in the target area.

[0039] Preferably, in this embodiment, the state partition constraint when the lighting light source in the target area follows the user's motion trajectory is determined according to the posture activity index and the behavior response index, referring to Figure 3 As shown in FIG, this figure is a schematic diagram of a process for determining state partition constraints in some embodiments of the present application. In this embodiment, determining state partition constraints can be implemented using the following steps: In step S31, dynamic configuration information corresponding to the user's motion trajectory is determined according to the posture activity index; In step S32, a trajectory confidence weight for lighting partition decision-making is determined based on the dynamic configuration information; In step S33, determining the linkage conflict index of the lighting light sources in the target area when making lighting zoning decisions; In step S34, the state partition constraint of the lighting light source in the target area when making a lighting partition decision along the user's motion trajectory is determined according to the trajectory confidence weight, the linkage conflict index and the behavior response index.

[0040] In specific implementation, a high-precision motion tracking system (such as a visual-inertial positioning module or an ultra-wideband positioning system) is first deployed within the target area to record the user's position sequence and movement speed in three-dimensional space in real time. This motion trajectory is then correlated with the user's current posture activity index. For example, a high activity index indicates frequent user activity, rapid trajectory changes, and frequent turns. A trajectory classification module (such as a trajectory pattern recognition algorithm based on a hidden Markov model) is then invoked to determine the trajectory type (e.g., stop, cruise, or detour). Dynamic configuration information corresponding to the user's motion trajectory is then generated based on the posture activity level. This dynamic configuration information is then input into a trajectory confidence assessment model. This model, which can be based on fuzzy logic, Bayesian reasoning, or decision tree classification, performs a weighted score based on three factors: the degree of match between the current trajectory and historical trajectories, the frequency of trajectory switching, and the magnitude of posture activity. The weighted score is used as the trajectory confidence weight for lighting zoning decisions. During real-time zoning control, the system detects whether the lighting zones of multiple user trajectories overlap, or whether the same zone is assigned different lighting states simultaneously due to multiple behavioral response indicators. A conflict identification module (e.g., a conflict matrix mapping mechanism) is used to quantify the degree of conflict between inter-zone lighting configurations. This module then combines the conflict impact range, user priority, and light source load capacity to generate a linkage conflict index for the target area's lighting zoning decisions. Finally, the trajectory confidence weights, linkage conflict index, and behavioral response index are input into a multi-objective optimization model (e.g., a constraint-solving framework based on weighted multi-objective linear programming). This model then determines the control state for each lighting zone. State zoning constraints include lighting activation area boundary constraints, lighting delay duration limits, brightness increment limits, and color temperature switching frequency. The multi-objective optimization model automatically mitigates conflicts. For example, if two user trajectories overlap but one has a low weight and slow behavioral response, the system automatically suppresses its lighting request, delaying the response or reducing the lighting range. Ultimately, a set of state zoning constraints is generated that ensures complete lighting coverage, timely response, and optimized energy consumption. These constraints are the state zoning constraints for the lighting sources in the target area that follow user trajectory during lighting zoning decisions.

[0041] It should be noted that, in this application, dynamic configuration information refers to a set of parameters that reflect the path characteristics and behavioral trends of the user's current motion status and behavioral activity; trajectory confidence weight refers to the credibility score that measures the degree of influence of the user's motion trajectory on the lighting adjustment decision in the current scenario; linkage conflict index refers to the degree of lighting state conflict caused by multiple user trajectories during the multi-light source linkage control process; state partition constraint refers to a set of rules set for the dynamic division and control state changes of the lighting area under the influence of multiple users and multiple behaviors; user motion trajectory refers to the position movement path generated by the user in the specified area over time, which is used to characterize his activity range and action patterns; lighting zoning decision refers to the process of dividing the lighting area according to user distribution and regional needs and controlling the light intensity and switch status of each partition as needed.

[0042] In this embodiment, the light color rheological characteristics of the lighting source when the color temperature is switched by the state partition constraint can be specifically implemented in the following manner, namely: generating a rheological configuration rule for color temperature switching based on the state partition constraint; Determine the light color correction information of the lighting source during the color temperature switching process; The light color rheological characteristics of the lighting light source when the color temperature is switched are determined according to the rheological configuration rule and the light color correction information.

[0043] In specific implementation, the lighting area is first divided into multiple state zones. Each state zone represents a spatial unit with specific lighting requirements or functional scenarios, such as a reading area, rest area, or pedestrian area. Within each state zone, desired light environment parameters are generated based on the area's purpose, human activity type, time period, and user habits. These parameters include the target color temperature, color temperature change rate, and the allowable brightness gradient range. A mapping relationship is then established based on these parameters to form a rheological configuration rule for color temperature switching. This rheological configuration rule clearly specifies how the lighting source should smoothly transition from the current color temperature value to the target color temperature value within each state zone. Specifically, it includes the color temperature transition curve, brightness adjustment, and spectral energy distribution adjustment path. This modeling can be implemented using constrained fuzzy logic reasoning or a multi-factor cluster matching model based on historical user feedback, which will not be detailed here. Then, during the color temperature switching process, the current luminous state parameters of the lighting source are monitored in real time, including the current color temperature, brightness, spectral energy distribution, and color deviation. This optical information is acquired using a high-resolution light and color sensor array, and the data is de-noised and normalized using a multi-channel signal filtering module. The difference between the current state and the target state is calculated, and the resulting difference serves as the light color correction information for the lighting source during the color temperature switching process. Finally, the rheological configuration rules are integrated with the light color correction information. A frame-by-frame drive or gradient curve control strategy can be used to segmentally modulate the driving current of the lighting source, controlling the drive ratio of each color channel in the LED group and achieving a smooth color temperature transition. The specific process includes adjusting the driving current ratio in stages according to the time step specified by the rheological configuration rules; and dynamically adjusting the compensation amplitude of each stage based on the light color correction information. This process can be achieved by calling the color temperature gradient function library through a digital signal control unit and generating a control instruction sequence through real-time interpolation. Ultimately, this achieves a continuous light color rheological output during the color temperature switching process, thereby obtaining the light color rheological characteristics of the lighting source during color temperature switching.

[0044] It should be noted that, in this application, color temperature switching refers to adjusting the color temperature of light emitted by the lighting source according to changes in lighting needs to achieve a dynamic transition between cold and warm light; rheological configuration rules refer to the gradual logic and optical adjustment path that control the color temperature change of the lighting source under a specific state partition; light color correction information refers to the set of compensation parameters calculated by the difference between the current light color state and the target light color state during the color temperature switching process; light color rheological characteristics refer to the continuous change pattern of the output light color of the lighting source over time during the color temperature switching process.

[0045] The self-correction module 400 is configured to perform self-correction matching on the lighting demand pattern in the lighting environment of the target area according to the adaptation compensation strategy and the light color rheology characteristics.

[0046] In this embodiment, the self-correction matching of the lighting demand pattern in the lighting environment of the target area according to the adaptation compensation strategy and the light color rheological characteristics can be specifically performed in the following manner, namely: Determining the balance feedback intensity when adjusting the lighting demand mode in the lighting environment of the target area according to the adaptive compensation strategy; Determining the allocation guidance attributes when allocating the lighting demand mode in the lighting environment of the target area through the light color rheological characteristics; A self-correction matching strategy for the target area lighting demand pattern is determined by the balance feedback strength and the adjustment guidance attribute, and self-correction matching is performed on the lighting demand pattern in the target area lighting environment according to the self-correction matching strategy.

[0047] In its implementation, a real-time feedback mechanism based on a visual adaptation response model is first implemented, setting a minimum deviation threshold between ambient illuminance and human visual comfort. When the actual lighting intensity exceeds or falls below the target deviation threshold, ambient light sensors and human presence sensors collect real-time ambient illuminance and human activity density values ​​in the target area. This collected data is then fed into a visual response model to calculate the difference between the current lighting state and the desired visual state. This difference serves as the equilibrium feedback intensity for adjusting the lighting demand pattern in the target area's lighting environment. Next, a light color evolution model based on time series analysis is constructed. Dynamic clustering and rheological trend analysis is performed on historically collected illuminance values, color temperature values, and visual preference feedback values. A sliding window mechanism and a rate-of-change boundary model are used to identify different stages of light color change, such as the transition period (rapid light change), the stable period (constant light color), and the perturbation period (interruptions in the light environment). The identified results serve as guiding attributes for adjusting the lighting demand pattern in the target area's lighting environment. Finally, the equilibrium feedback intensity and guiding attributes are fed as input variables into a fuzzy controller or reinforcement learning lighting strategy engine to construct a state-action mapping model. This state-action mapping model continuously perceives deviations between ambient illumination, user visual behavior (e.g., gaze frequency and activity path), and dimming result feedback. Through policy training, it generates a matching strategy with adaptive weight adjustment capabilities. This matching strategy serves as a self-correcting matching strategy for the target area's lighting demand pattern. During the policy execution phase, the optimal adjustment action is selected based on the current state, such as increasing brightness, adjusting color temperature, or pausing adjustment. This adjustment is executed in real time through intelligent lighting terminals such as dimmable LEDs and dynamic color temperature lamps. The adjusted feedback information is then recollected for the next round of self-correcting matching.

[0048] It should be noted that, in this application, the lighting demand pattern refers to a combined control scheme of lighting brightness, color temperature and time changes generated according to different environments and crowd activity needs; the balance feedback intensity refers to the adjustment amplitude control parameter when responding to the difference between the current lighting state and the target visual comfort during the lighting adjustment process; the adjustment guidance attribute refers to the attribute set used to guide the brightness and color temperature adjustment direction, amplitude and rhythm during the lighting demand pattern adjustment process; the self-correction matching strategy refers to the strategy set for autonomous correction and dynamic matching of the current lighting demand pattern during the lighting environment adjustment process; self-correction matching refers to the dynamic adjustment process of the lighting system automatically adjusting parameters based on feedback information to continuously match the set target lighting state.

[0049] It can be seen from this that in the present application, the lighting environment and user behavior status can be multi-dimensionally linked and adjusted in the intelligent lighting control scenario; among them, by real-time collection of dynamic atmosphere information of the lighting environment in the target area and behavioral response indicators during user activities, it is possible to realize instant perception of ambient light disturbances and changes in user behavior, comprehensively build a dynamic input foundation for lighting scenes, and thus improve the environmental adaptability and behavioral response accuracy of the lighting control system in complex spaces; by determining the illuminance perception rules when adaptively adjusting the brightness of the lighting source according to the lighting adjacent paths and dynamic atmosphere information, and performing layered compensation to obtain the adaptive compensation strategy when adjusting the lighting angle, it is possible to incorporate the illuminance transition rules and individual perception differences into the process of adjusting the light source brightness and spatial lighting angle, realize gradual coordination of illuminance control and elastic compensation of spatial lighting coverage, and effectively improve the balance of light distribution and user Visual comfort; by obtaining the posture activity index of the user when he is active in the target area, and combining it with the behavioral response index to determine the state partitioning constraints of the lighting light source when making lighting partitioning decisions according to the user's movement trajectory, and further determining the light color rheological characteristics when the color temperature is switched, the lighting system can achieve continuous linkage of partition response and color temperature adjustment under changes in user behavior frequency and movement trajectory, dynamically optimize the degree of matching of the lighting system to the user's intention, and enhance the consistency and immersion of the light environment and individual behavior; by self-correcting and matching the lighting demand pattern in the lighting environment of the target area based on the adaptive compensation strategy and light color rheological characteristics, the lighting system can achieve self-optimization and parameter fine-tuning of the lighting control strategy in long-term operation, and build a feedback closed-loop structure with adaptive regulation capabilities, thereby improving the response speed, strategy accuracy and light environment stability of the lighting system in changing scenarios.

[0050] In summary, the technical solution adopted in this application can perform linked self-correction control on the lighting mechanism of the lighting source to improve the real-time response capability of the intelligent lighting system driven by complex spatial behaviors.

[0051] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems) and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0052] Those skilled in the art will appreciate that all or part of the steps in the various methods of the above embodiments can be completed by instructing related hardware through a program. The program can be stored in a computer-readable storage medium, including a read-only memory (ROM), a random access memory (RAM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), a one-time programmable read-only memory (OTPROM), an electronically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM), or other optical disc storage, magnetic disk storage, or magnetic tape storage, or any other computer-readable medium capable of carrying or storing data.

[0053] It should also be noted that the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, commodity, or apparatus that includes a series of elements includes not only those elements but also other elements not explicitly listed, or includes elements inherent to such process, method, commodity, or apparatus. In the absence of further limitations, an element defined by the phrase "comprises a..." does not exclude the presence of other identical elements in the process, method, commodity, or apparatus that includes the element.

Claims

1. An intelligent adaptive lighting system based on environmental perception and behavior recognition, characterized in that: The adaptive lighting system comprises: The data acquisition module is used to collect dynamic atmosphere information of the lighting environment in the target area and behavioral response indicators during user activities in real time; A hierarchical compensation module is configured to determine an adjacent lighting path of a lighting scene in a target area, determine an illuminance perception rule for adaptively adjusting the brightness of the lighting source in the target area based on the adjacent lighting path and the dynamic atmosphere information, perform hierarchical compensation on the illuminance perception rule, and obtain an adaptive compensation strategy for adjusting the lighting angle of the lighting source; a zoning constraint module, configured to obtain a posture activity index when the user is active in a target area, determine a state zoning constraint for the lighting light source in the target area when making lighting zoning decisions along the user's motion trajectory based on the posture activity index and the behavioral response index, and further determine the light color rheological characteristics of the lighting light source when switching color temperature based on the state zoning constraint; The self-correction module is used to perform self-correction matching on the lighting demand pattern in the lighting environment of the target area according to the adaptation compensation strategy and the light color rheology characteristics.

2. The intelligent adaptive lighting system based on environment perception and behavior recognition according to claim 1, characterized in that: The dynamic atmosphere information refers to a multi-dimensional perception data set of the current light environment state of the target area.

3. The intelligent adaptive lighting system based on environment perception and behavior recognition according to claim 1, characterized in that: The behavioral response index refers to the behavioral data of the user's body posture, movement reaction and spatial displacement generated under different lighting conditions.

4. The intelligent adaptive lighting system based on environment perception and behavior recognition according to claim 1, characterized in that: Determining the lighting proximity path of the lighting scene in the target area specifically includes: determining an initial lighting deviation of the target area according to initial environmental parameters under a static lighting state; Determining a steady-state illumination gradient of a lighting scene change by using the initial illumination deviation; An illumination proximity path of an illumination scene in a target area is determined according to the steady-state illumination gradient.

5. The intelligent adaptive lighting system based on environment perception and behavior recognition according to claim 1, characterized in that: The illumination perception rule is subjected to layered compensation to obtain an adaptive compensation strategy for adjusting the lighting angle of the lighting source, specifically including: Determine the spatial position characteristics and luminous flux elasticity margin of the lighting source through the illumination perception rule; generating conflict resolution information when adjusting the lighting angle according to the spatial position feature and the luminous flux elastic margin; The conflict resolution information is used to determine an adaptation compensation strategy for adjusting the lighting angle of the lighting source.

6. The intelligent adaptive lighting system based on environment perception and behavior recognition according to claim 1, characterized in that: Obtaining the user's posture activity index when moving in the target area specifically includes: Collect dynamic fluctuation indicators of user joint movements in the target area; Determining the amount of gesture sequence response in the user activity history data; A gesture activity index when the user is active in the target area is determined according to the dynamic fluctuation index and the gesture sequence response amount.

7. The intelligent adaptive lighting system based on environment perception and behavior recognition according to claim 1, characterized in that: The user motion trajectory refers to the position movement path of the user in a specified area that changes over time.

8. The intelligent adaptive lighting system based on environment perception and behavior recognition according to claim 1, characterized in that: The lighting zoning decision-making refers to the process of dividing the lighting area according to user distribution and regional requirements and controlling the light intensity and switch status of each zone as needed.

9. The intelligent adaptive lighting system based on environment perception and behavior recognition according to claim 1, characterized in that: The light color rheological characteristics when the lighting source switches color temperature determined by the state partition constraint specifically include: generating a rheological configuration rule for color temperature switching based on the state partition constraint; Determine the light color correction information of the lighting source during the color temperature switching process; The light color rheological characteristics of the lighting light source when the color temperature is switched are determined according to the rheological configuration rule and the light color correction information.

10. The intelligent adaptive lighting system based on environment perception and behavior recognition according to claim 1, characterized in that: The self-correction matching of the lighting demand pattern in the lighting environment of the target area according to the adaptation compensation strategy and the light color rheological characteristics specifically includes: Determining the balance feedback intensity when adjusting the lighting demand mode in the lighting environment of the target area according to the adaptive compensation strategy; Determining the allocation guidance attributes when allocating the lighting demand mode in the lighting environment of the target area through the light color rheological characteristics; A self-correction matching strategy for the target area lighting demand pattern is determined by the balance feedback strength and the adjustment guidance attribute, and self-correction matching is performed on the lighting demand pattern in the target area lighting environment according to the self-correction matching strategy.

Images