Adaptive duty cycle dimming control method, device, equipment and storage medium

Abstract

The application provides a self-adaptive duty cycle dimming control method, device, equipment and storage medium. The preset point in the home space is subjected to spatial light field reconstruction processing, and the real effective illumination of the preset point is corrected; the visual perception weight corresponding to a target user in the home space is quantized; the scene coefficient corresponding to the target user is obtained; the target illumination is determined based on the real effective illumination, the visual perception weight, the scene coefficient, a preset reference illumination and an AI correction coefficient; and the current dimming duty cycle of the preset point is recursively derived based on the target illumination and the dimming duty cycle of the preset point in the last period, so as to realize self-adaptive dimming of the preset point. The application solves the problems of population misfit and scene misfit in traditional dimming, and the problem of dimming misjudgment caused by reflection interference, realizes full light source dynamic coupling, overcomes the one-sidedness of single quantization, perfectly balances visual comfort and energy saving demand, and fully adapts to home dynamic demand.

Description

Technical Field

[0001] This application belongs to the field of intelligent lighting adaptive control technology, and relates to an adaptive duty cycle dimming control method, device, equipment and storage medium. Background Technology

[0002] Home lighting environments are characterized by high spatial constraints, strong reflective heterogeneity, random human movement, and time-varying scenes. Existing smart lighting technologies have failed to fully deconstruct these physical and behavioral characteristics, exhibiting significant technical deficiencies and mechanistic bottlenecks. For example, existing technologies have not effectively adapted to the specific characteristics of home scenarios, lack systematic and collaborative solutions for suppressing interference from reflective surfaces and reconstructing the true light field, and are unable to meet the high-precision, personalized lighting needs of practical home environments. Summary of the Invention

[0003] This application provides an adaptive duty cycle dimming control method, apparatus, device, and storage medium, which provides an adaptive intelligent lighting control scheme that takes into account visual comfort, energy saving, and operability.

[0004] In a first aspect, this application provides an adaptive duty cycle dimming control method, the method comprising: performing spatial light field reconstruction processing on a preset point in a home space to correct the true effective illuminance of the preset point; calculating the visual perception weight corresponding to the target user based on the crowd coefficient, posture coefficient, and distance between the light fixture and the preset point in the home space; obtaining the scene coefficient corresponding to the target user; determining the target illuminance based on the true effective illuminance, the visual perception weight, the scene coefficient, the preset reference illuminance, and the AI ​​correction coefficient, wherein the AI ​​model adaptively adjusts the AI ​​correction coefficient by collecting home space data in real time; and recursively calculating the current dimming duty cycle of the preset point based on the target illuminance and the dimming duty cycle of the preset point in the previous cycle to achieve adaptive dimming of the preset point.

[0005] This application's embodiments construct a perfect closed loop of "perception-computation-decision-execution": first, spatial light field reconstruction ensures accurate measurement of the true and effective illuminance at preset points; second, visual weights and scene coefficients ensure accurate calculation; third, AI models ensure stable decision-making; and finally, recursive duty cycles ensure smooth adjustment. This addresses four core pain points in home settings: light distortion, discomfort for individuals, environmental interference, and abrupt adjustments.

[0006] In one implementation of the first aspect, the step of performing spatial light field reconstruction processing on a preset point within the home space to correct the true effective illuminance of the preset point includes: collecting the natural direct illuminance of the preset point; calculating the artificial direct illuminance of the preset point based on the number of lamps in the home space; quantifying the reflected interference illuminance of the preset point based on the reflective materials in the home space; and correcting the true effective illuminance based on the natural direct illuminance, the artificial direct illuminance, and the reflected interference illuminance.

[0007] In one implementation of the first aspect, the expression for calculating the artificial direct illuminance at the preset point based on the sum of the number of light fixtures in the home space is:

[0008]

[0009] in, Indicates the number of light fixtures. Indicates the first The light intensity of the lamp, This indicates the angle between the light output axis of the lamp and the normal to the preset point. Indicates the first The distance from each lamp to the preset point Indicates the first Type coefficient of lamps, This represents the direct illuminance of artificial light at the preset point P.

[0010] In one implementation of the first aspect, quantifying the reflected interference illuminance of the preset point based on the reflective material within the home space includes: identifying the reflective material of the preset point within the home space; querying a reflection correction coefficient based on the reflective material; obtaining the surface reflectivity based on the reflective material; measuring a first distance from the reflective surface of the reflective material to the sensor; matching a spatial correction coefficient based on the spatial dimensions of the home space; and quantifying the reflected interference illuminance of the preset point based on the sensor's original reading, the reflection correction coefficient, the surface reflectivity, the first distance, and the spatial correction coefficient.

[0011] In one implementation of the first aspect, quantifying the visual perception weights corresponding to the target users within the home space includes: mapping the crowd coefficients of the target users within the home space; and matching the posture coefficients of the target users within the home space.

[0012] Measure the second distance between the light fixtures and the preset point in the home space; perform a fusion calculation on the basic weight, the crowd coefficient, the posture coefficient, and the second distance to obtain the visual perception weight corresponding to the target user.

[0013] In one implementation of the first aspect, the expression for determining the target illuminance based on the true effective illuminance, the visual perception weight, the scene coefficient, the preset reference illuminance, and the AI ​​correction coefficient is as follows:

[0014]

[0015] in, Indicates the true effective illuminance. Represents visual perception weights. Indicates the preset reference illuminance. Indicates the AI ​​correction factor. denoted by , where P represents the preset point.

[0016] In one implementation of the first aspect, the method further includes: when the environment within the home space changes, the AI ​​model collects the home space data in real time and automatically corrects the AI ​​correction coefficient based on the home space data to ensure that the target illuminance is adapted to the current home space, wherein the home space data includes, but is not limited to: reflective material, attitude coefficient, and scene coefficient.

[0017] Secondly, this application provides an adaptive duty cycle dimming control device, the device comprising: a true effective illuminance determination module, used to perform spatial light field reconstruction processing on a preset point in a home space and correct the true effective illuminance of the preset point; a visual perception weight determination module, used to calculate the visual perception weight corresponding to the target user based on the crowd coefficient, posture coefficient, and distance between the lamps and the preset point in the home space; a scene coefficient determination module, used to obtain the scene coefficient corresponding to the target user; a target illuminance determination module, used to determine the target illuminance based on the true effective illuminance, the visual perception weight, the scene coefficient, a preset reference illuminance, and an AI correction coefficient, wherein the AI ​​model adaptively adjusts the AI ​​correction coefficient by collecting home space data in real time; and an adaptive dimming module, used to recursively deduce the current dimming duty cycle of the preset point based on the target illuminance and the dimming duty cycle of the preset point in the previous cycle, so as to achieve adaptive dimming of the preset point.

[0018] Thirdly, embodiments of this application provide a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the adaptive duty cycle dimming control method described in any one of the first aspects of embodiments of this application.

[0019] Fourthly, embodiments of this application provide an electronic device, the electronic device comprising: a memory storing a computer program; and a processor communicatively connected to the memory, which executes the adaptive duty cycle dimming control method described in any one of the first aspects of embodiments of this application when the computer program is invoked.

[0020] As described above, the adaptive duty cycle dimming control method, apparatus, device, and storage medium of this application have the following beneficial effects:

[0021] 1) Traditional illuminance calculation often relies on direct measurement from a single sensor or only considers the state of the lights being on, ignoring the dramatic dynamic changes of natural light over time and weather. This application independently collects and superimposes "direct natural light" and "direct artificial light" at a preset point, and performs spatial light field reconstruction processing to achieve dynamic coupling of all light sources, overcoming the one-sidedness of single quantification; accurately corrects the true effective illuminance of the preset point, effectively eliminates interference components introduced by multi-path reflections in the environment, suppresses light field distortion, and accurately analyzes and restores the true effective illuminance of the preset point in the home space. This step removes false light data and provides a high-fidelity data base for subsequent dimming closed loops, fundamentally eliminating the deviation between system perception and human visual perception, and avoiding the risk of misjudgment of insufficient illuminance caused by inflated sensor data.

[0022] 2) By quantifying the visual perception weight of the target user and obtaining the current scene coefficient, the problem of "one-size-fits-all" dimming, which is not suitable for the target audience and the scene is mismatched, is solved. The system is endowed with "empathy". The system can dynamically adjust the visual perception weight according to the identity information, behavior and actions of the target user in the home space, perfectly balancing visual comfort and energy saving needs, fully adapting to the dynamic needs of the home, and protecting eye health to the extreme.

[0023] 3) By integrating multiple parameters such as real effective illuminance, visual perception weight, scene coefficient, and preset benchmark illuminance, an AI decision-making model is constructed. Based on real-time collected home space data, the AI ​​correction coefficient is adjusted online adaptively and iteratively. A physical constraint mechanism is introduced to construct the AI ​​model, giving the system online self-learning and dynamic evolution capabilities. Based on the advance prediction and dynamic compensation of time-varying environmental characteristics, the AI ​​correction coefficient can calibrate the target illuminance in real time, significantly improving the robustness and convergence of the dimming control system. This ensures that under transient and sudden environmental disturbances, the system can still respond quickly and accurately output the optimal illuminance solution that meets the physical boundary conditions. Attached Figure Description

[0024] Figure 1A The diagram shows an application scenario corresponding to the adaptive duty cycle dimming control method provided in the embodiments of this application.

[0025] Figure 1BThe flowchart shown is an example of an adaptive duty cycle dimming control method provided in this application.

[0026] Figure 2 The flowchart shown is a process provided in this application embodiment to reconstruct the spatial light field of a preset point in a home space and correct the true effective illuminance of the preset point.

[0027] Figure 3 The flowchart shown is a process for quantifying the reflected interference illuminance of the preset point provided in an embodiment of this application.

[0028] Figure 4 The flowchart shown is a quantification flowchart of the visual perception weights corresponding to target users in a home space, provided in an embodiment of this application.

[0029] Figure 5 The diagram shown is a structural diagram of the adaptive duty cycle dimming control device provided in an embodiment of this application.

[0030] Figure 6 The diagram shown is a structural diagram of an electronic device provided in an embodiment of this application.

[0031] Component designation explanation

[0032] S11~S15 step 54 Target Illuminance Determination Module S21~S24 step 55 Adaptive dimming module S31~S36 step 60 electronic devices S41~S44 step 61 processor 50 Adaptive duty cycle dimming control device 62 Non-volatile storage media 51 True effective illuminance determination module 63 System bus 52 Visual perception weight determination module 64 Internal memory 53 Scene coefficient determination module 65 Network interface Detailed Implementation

[0033] The following specific examples illustrate the implementation of this application. Those skilled in the art can easily understand other advantages and effects of this application from the content disclosed in this specification. This application can also be implemented or applied through other different specific embodiments, and various details in this specification can also be modified or changed based on different viewpoints and applications without departing from the spirit of this application. It should be noted that, unless otherwise specified, the following embodiments and features in the embodiments can be combined with each other.

[0034] It should be noted that the illustrations provided in the following embodiments are only schematic representations of the basic concept of this application. Therefore, the drawings only show the components related to this application and are not drawn according to the actual number, shape and size of the components in the actual implementation. In the actual implementation, the form, quantity and proportion of each component can be arbitrarily changed, and the layout of the components may also be more complex.

[0035] like Figure 1AAs shown in the diagram, this embodiment provides an application scenario illustration of an adaptive duty cycle dimming control method. Specifically, it includes: multiple lighting fixtures installed on the ceiling of a standard home interior space to provide basic lighting while enabling independent dimming control. The spatial light field formed by the fixtures is reconstructed using preset points within the space, correcting the true effective illuminance at each point to provide accurate basic data for dimming control. This quantifies the visual perception weight corresponding to the target user, matching the user's visual characteristics. Simultaneously, scene coefficients are obtained based on the user's activity type to adapt to the lighting needs of different scenarios. Based on the corrected true effective illuminance, visual perception weights, scene coefficients, and preset baseline illuminance, the target illuminance is calculated using an AI correction coefficient. The AI ​​model adaptively adjusts the correction coefficient by collecting real-time home space data. Based on the target illuminance and the dimming duty cycle of the preset points in the previous cycle, the current dimming duty cycle is recursively calculated, driving the fixtures to achieve precise and dynamic adaptive dimming to meet the user's personalized lighting needs.

[0036] The technical solutions in the embodiments of this application will be described in detail below with reference to the accompanying drawings.

[0037] like Figure 1B As shown in the flowchart, this application provides an adaptive duty cycle dimming control method. Figure 1B As shown, the adaptive duty cycle dimming control method provided in this application includes the following steps S11 to S15.

[0038] S11, Perform spatial light field reconstruction processing on preset points in the home space to correct the true effective illuminance of the preset points.

[0039] The preset points within the home space can be set arbitrarily and reasonably based on actual application needs, and this application does not impose any restrictions on this.

[0040] S12, quantify the visual perception weights corresponding to the target users in the home space.

[0041] For example, target users include the elderly, infants, and young people.

[0042] For example, the elderly have poor eyesight and need brighter light, but they also have a low tolerance for glare; babies' eyes are still developing and they are very sensitive to strong light; while young people are relatively more resilient.

[0043] For example, the target user's posture directly determines whether the light will shine directly into their eyes. If the target user is lying on their back, the ceiling light is likely to shine directly into their eyes, resulting in a high posture coefficient; if the target user is lying down to read a book, or standing with their head down looking at their phone, the light is usually outside their line of sight, resulting in a low posture coefficient.

[0044] For example, the light intensity is closely related to the distance to a preset point (like a fire, the closer you are, the hotter it gets). The system measures the distance from the light fixture to a certain "preset point," which is usually the location of the target user (such as the target user's head or the book the target user is reading).

[0045] Specifically, the visual perception weights corresponding to the target user are quantified based on the base weights, target user, posture coefficient, and distance.

[0046] S13, obtain the scene coefficient corresponding to the target user.

[0047] For example, the scenarios corresponding to the target users are reading scenarios, movie-watching scenarios, and rest scenarios.

[0048] For example, the scene coefficient for reading is 1.1, the scene coefficient for watching a movie is 0.8, and the scene coefficient for resting is 0.9.

[0049] It should be noted that the scene coefficients for reading, watching movies, and resting scenarios listed in the above examples are merely illustrative and this application does not impose any restrictions on them.

[0050] For example, if the target user turns on the main light in the room, or presses the "reading mode" button, or if the target user sits at the desk and the desk lamp is turned on, the system will infer that the target user's scenario is a reading scenario, and then directly call the scenario coefficient of 1.1 for the reading scenario.

[0051] For example, by observing the target user's behavior trajectory and environmental changes through sensors: if the target user is detected sitting at a desk with light above the desk, the reading scenario corresponding to the target user can be accurately determined by combining the above posture and position information.

[0052] S14, determine the target illuminance based on the actual effective illuminance, the visual perception weight, the scene coefficient, the preset benchmark illuminance, and the AI ​​correction coefficient.

[0053] The AI ​​model adaptively adjusts the AI ​​correction coefficient by collecting real-time data on the home space.

[0054] In some embodiments, the method further includes: when the environment within the home space changes, the AI ​​model collects the home space data in real time and automatically corrects the AI ​​correction coefficient based on the home space data to ensure that the target illuminance is adapted to the current home space. The home space data includes, but is not limited to: reflective material, attitude coefficient, and scene coefficient.

[0055] For example, the AI ​​model in this application is an adaptive dimming inference model embedded in the closed loop of smart home lighting control and integrated with a physical model. Deployed on the ESP32-C3 edge computing unit, it achieves local real-time inference (latency <50ms) without cloud dependency. Its core function is to adapt to dynamic home scenarios and achieve precise dimming decisions. Its core functions include two points:

[0056] I. Dynamically Adjusting the AI ​​Correction Coefficient By collecting real-time data on home space such as reflective surface type, human posture, illuminance changes, and scene switching, it automatically adjusts... (0.8~1.2) values, corrected target illuminance Calculation results.

[0057] Second, by combining physical parameters such as spatial light field reconstruction and visual perception weight, and through autonomous learning and real-time reasoning, the dimming decision is dynamically optimized. The entire process of "data acquisition → light field reconstruction → visual perception weight calculation → dimming output" is connected to achieve true "AI adaptive" dimming, which is different from existing dimming algorithms with fixed parameters.

[0058] In some embodiments, the expression for determining the target illuminance based on the true effective illuminance, the visual perception weight, the scene coefficient, the preset reference illuminance, and the AI ​​correction coefficient is as follows:

[0059]

[0060] in, Indicates the true effective illuminance. Represents visual perception weights. Indicates the preset reference illuminance. Indicates the AI ​​correction factor. denoted by , where P represents the preset point.

[0061] S15, based on the target illuminance and the dimming duty cycle of the preset point in the previous cycle, the current dimming duty cycle of the preset point is recursively calculated to achieve adaptive dimming of the preset point.

[0062] For example, the expression for recursively deriving the current dimming duty cycle of the preset point based on the target illuminance and the dimming duty cycle of the preset point in the previous cycle is as follows:

[0063] ,

[0064] in, , This indicates the duty cycle of the previous period. Indicates the AI ​​correction factor. This indicates the maximum illuminance of the luminaire (lx). Indicates target illuminance, Indicates the current dimming duty cycle. This represents the smoothing coefficient (0.05~0.2, default 0.1).

[0065] This application provides an adaptive duty cycle dimming control method. By reconstructing the spatial light field of a preset point, the true effective illuminance of the preset point is corrected, effectively eliminating interference components introduced by multipath reflections in the environment, suppressing light field distortion, and accurately analyzing and restoring the true effective illuminance of the preset point in the home space. This step eliminates false lighting data, providing a high-fidelity data foundation for subsequent dimming closed-loop, fundamentally eliminating the deviation between system perception and human visual perception, and avoiding the risk of misjudgment of insufficient illuminance due to inflated sensor data. By quantifying the visual perception weight of the target user and obtaining the current scene coefficient, the method solves the problem of "one-size-fits-all" dimming, which is unsuitable for all user groups and mismatched with all scenes. It gives the system "empathy," allowing it to respond according to "who you are (old, young, or old)" and "where you are (sitting)." The system dynamically adjusts visual perception weights based on whether the user is lying down or standing, or what they are doing (reading, watching a movie, or resting), perfectly balancing visual comfort and energy-saving needs. It comprehensively adapts to dynamic home requirements and provides ultimate protection for eye health. It integrates multiple parameters, including real effective illuminance, visual perception weights, scene coefficients, and preset benchmark illuminance, to construct an AI decision-making model. Based on real-time collected home space data, it performs online adaptive iterative adjustment of the AI ​​correction coefficients, introducing a physical constraint mechanism to build the AI ​​model. This endows the system with online self-learning and dynamic evolution capabilities. Based on the advance prediction and dynamic compensation of time-varying environmental characteristics, the AI ​​correction coefficients can calibrate the target illuminance in real time, significantly improving the robustness and convergence of the dimming control system. This ensures that even under transient environmental disturbances, the system can still quickly respond and accurately output the optimal illuminance solution that meets the physical boundary conditions.

[0066] This application's embodiments construct a perfect closed loop of "perception-computation-decision-execution": first, spatial light field reconstruction ensures accurate measurement of the true and effective illuminance at preset points; second, visual weights and scene coefficients ensure accurate calculation; third, AI models ensure stable decision-making; and finally, recursive duty cycles ensure smooth adjustment. This addresses four core pain points in home settings: light distortion, discomfort for individuals, environmental interference, and abrupt adjustments.

[0067] like Figure 2 As shown, this application embodiment provides a flowchart for reconstructing the spatial light field of a preset point in a home space and correcting the true effective illuminance of the preset point, as follows: Figure 2 As shown, the method for reconstructing the spatial light field of a preset point in a home space and correcting the true effective illuminance of the preset point provided in this application embodiment includes the following steps S21 to S24.

[0068] S21, collect the natural direct illuminance at the preset point.

[0069] For example, the natural direct illuminance at a preset point is collected in real time based on a spectral sensor.

[0070] S22, calculate the artificial light direct illuminance at the preset point based on the number of light fixtures in the home space.

[0071] In some embodiments, the expression for calculating the artificial direct illuminance at the preset point based on the sum of the number of light fixtures in the home space is:

[0072]

[0073] in, Indicates the number of light fixtures. Indicates the first The light intensity of the lamp, This indicates the angle between the light output axis of the lamp and the normal to the preset point. Indicates the first The distance from each lamp to the preset point Indicates the first Type coefficient of lamps, This represents the direct illuminance of artificial light at the preset point P.

[0074] S23, quantify the reflected interference illuminance of the preset point based on the reflective material in the home space.

[0075] S24, correct the true effective illuminance based on the natural light direct illuminance, the artificial light direct illuminance, and the reflected interference illuminance.

[0076] For example, the expression for correcting the true effective illuminance based on the natural direct illuminance, the artificial direct illuminance, and the reflected interference illuminance is as follows:

[0077]

[0078] in, This represents the natural direct illuminance (lx) at the preset point P. This represents the direct illuminance (lx) of artificial light at the preset point P. This represents the reflected interference illuminance (lx) at the preset point P. This represents the actual effective illuminance at the preset point P.

[0079] This application provides a method for reconstructing the spatial light field of preset points in a home space and correcting the true effective illuminance of the preset points. Traditional illuminance calculations often rely solely on direct measurement from a single sensor or only consider the state of the lights being on, ignoring the dramatic dynamic changes in natural light over time and weather. This application independently collects and superimposes "direct natural light" and "direct artificial light," accurately restoring the true illuminance baseline when natural and artificial light are mixed during the day. This avoids overestimating artificial lighting needs when natural light is sufficient or underestimating ambient illuminance on cloudy or rainy days, achieving dynamic coupling of all light sources and overcoming the one-sidedness of single-quantification. In home spaces, the reflectivity of walls, floors, and furniture (such as glass mirrors, high-gloss paint, and dark fabrics) varies greatly. Traditional "direct illuminance" models ignore these reflection interferences, resulting in calculation results that are seriously inconsistent with the "brightness (visual illuminance)" actually perceived by users. This application effectively eliminates localized glare (artificially high) caused by highly reflective materials or localized darkness (artificially low) caused by dark light-absorbing materials by introducing "quantified reflective interference illuminance based on reflective materials," making the calculated illuminance closer to the real visual perception of the human eye, filling the gap in the quantification of reflected light, and eliminating the calculation blind spots caused by environmental materials. The true effective illuminance obtained by this application through multi-dimensional correction provides a high-fidelity data anchor for subsequent health risk mapping and lighting intervention decisions, and provides a reliable data foundation for precise lighting intervention.

[0080] like Figure 3 As shown in the figure, this application embodiment provides a flowchart for quantifying the reflected interference illuminance of the preset point, as follows: Figure 3 As shown, the method for quantifying the reflected interference illuminance of the preset point provided in this application embodiment includes the following steps S31 to S36.

[0081] S31, Identify the reflective material of a preset point within the home space.

[0082] For example, reflective materials at preset points in a home space include glass, wood, etc.

[0083] For example, different materials have different absorption and reflectivity for electromagnetic waves of different wavelengths. Wood has obvious texture and a specific reflection spectrum in the near-infrared band; while glass has a specific absorption peak in the infrared band, and its reflectivity is strongly correlated with the angle of incidence. The system can use the reflectivity differences of the built-in near-infrared sensor to help classify the reflective materials at preset points in the home space.

[0084] For example, non-metallic highly reflective materials such as glass produce a significant polarization effect (partially polarized light) when reflecting natural light or artificial light, while the light reflected from a wooden surface is almost unpolarized. By using a binocular camera equipped with a polarizer to capture the difference in the polarization state of light, it is possible to identify the specular reflection area (glass) and diffuse reflection area (wood) at a preset point in a home space with extremely high accuracy.

[0085] It should be noted that the reflective materials of the preset points in the home space listed in the above examples are only used as examples, and this application will not elaborate further.

[0086] S32, query the reflection correction coefficient based on the reflective material.

[0087] For example, the reflection correction factor for glass is 0.8, the reflection correction factor for wood is 0.4, and the default reflection correction factor for other reflective materials is 0.6, which can be obtained directly by looking up the table of reflection correction factors for the corresponding reflective materials.

[0088] S33, Obtain the surface reflectivity based on the reflective material.

[0089] For example, since the reflectivity of the same material is relatively fixed in terms of macroscopic physical properties, the system usually does not need to "measure" it every time, but can query and obtain it based on a preset "material-reflectivity optical database".

[0090] For example, the surface reflectivity of glass is 0.7~0.8, the surface reflectivity of mirror is 0.85~0.95, and the surface reflectivity of latex paint is 0.2~0.3.

[0091] It should be noted that the specific values ​​of surface reflectance of glass, mirrors and latex paint listed in the above examples are merely illustrative and this application does not impose any limitations on them.

[0092] S34, Measure the first distance from the reflective surface of the reflective material to the sensor.

[0093] For example, a miniature distance sensor can be integrated into the illuminance sensor node or smart lighting fixture to directly measure the physical distance from the reflective surface of the reflective material to the sensor.

[0094] S35, Match a space correction coefficient based on the spatial dimensions of the home space.

[0095] For example, when the living space is a small apartment (<8㎡), the corresponding space correction coefficient is 0.8; when the living space is a medium-sized apartment (8-15㎡), the corresponding space correction coefficient is 0.9; and when the living space is a large apartment (>15㎡), the corresponding space correction coefficient is 1.0.

[0096] It should be noted that the space correction coefficients for matching the spatial dimensions of the home spaces listed in the above examples are merely illustrative examples, and this application will not elaborate on them further.

[0097] S36, quantify the reflected interference illuminance of the preset point based on the original sensor readings, the reflection correction coefficient, the surface reflectivity, the first distance, and the spatial correction coefficient.

[0098] For example, the expression for quantifying the reflected interference illuminance at the preset point based on the original sensor readings, the reflection correction coefficient, the surface reflectivity, the first distance, and the spatial correction coefficient is as follows:

[0099]

[0100] in, Indicates the reflection correction coefficient. Indicates surface reflectivity. This represents the sensor's raw reading. Indicates the distance from the reflective surface to the sensor. Indicates the spatial correction factor. This represents the reflected interference illuminance at the preset point P.

[0101] This application embodiment constructs multi-dimensional quantitative data including reflection correction coefficient, surface reflectivity, first distance, and spatial correction coefficient, deeply integrating environmental physical properties with optical propagation laws. It not only accurately depicts the optical attenuation and morphological variation of a single reflection, but also compensates for the cumulative error of multiple reflections under different volume spaces through the spatial correction coefficient. This achieves high fidelity in the illuminance of reflection interference, effectively eliminating the illusion of 'artificially high' illuminance caused by highly reflective materials or narrow spaces. It provides a solid and reliable data foundation for subsequently restoring the effective illuminance actually received by users and accurately implementing lighting interventions for health risks.

[0102] like Figure 4 As shown in the figure, this application embodiment provides a flowchart for quantifying the visual perception weight of a target user in a home space. The method for quantifying the visual perception weight of a target user in a home space provided by this application embodiment includes the following steps S41 to S44.

[0103] S41, mapping the population coefficient of the target users within the home space.

[0104] For example, the mapping is not arbitrary, but is rigorously deduced based on human visual physiology and lighting engineering standards (such as CIE standards), and its internal logic is as follows:

[0105] Adults (1.0) – Baseline: Adults have good lens transparency, and their retinal photoreceptor cells are at a stable peak, resulting in moderate sensitivity to light. Therefore, the visual comfort threshold for adults is used as the baseline of 1.0 for system calculations.

[0106] Elderly (1.2) – Gain Compensation: As people age, the lens of the human eye yellows and becomes cloudy (early cataracts), resulting in a significant decrease in light transmittance; simultaneously, photoreceptor cells in the macular region of the retina degenerate. Elderly individuals require 2-3 times more light flux than younger people to achieve the same visual clarity when viewing the same object. Therefore, the system maps a coefficient of 1.2 (>1.0), which will proportionally increase the ambient brightness when calculating target illuminance to compensate for the degraded optical transmittance in the elderly.

[0107] Children (0.8) – Suppression and Protection: Infants and children's eyes are still developing, their lenses are extremely clear and transparent, and their pupils are more sensitive to light, making them extremely sensitive to strong light. At the same time, excessive blue light can easily penetrate a child's lens and reach the retina, causing irreversible light damage. Therefore, the system maps a coefficient of 0.8 (<1.0), which will proportionally reduce the target illuminance in subsequent calculations, thus playing a role in preventing glare and protecting the retina.

[0108] S42, Match the posture coefficients of the target user within the home space.

[0109] An exemplary in-depth analysis based on ergonomics and spatial lighting optics (especially anti-glare UGR control):

[0110] When the target user is seated, the corresponding posture coefficient is 1.0 – the baseline maximum brightness requirement.

[0111] Visual task concentration: Sitting posture is usually accompanied by highly focused visual tasks (reading, working, crafting). At this time, the line of sight is downward, and the desktop or work surface is the main area receiving light, requiring sufficient illumination (such as 300-500 lux).

[0112] Large light-receiving cross section: When sitting, the torso and face have the largest light-receiving cross section relative to the overhead light, resulting in high light utilization. Therefore, the coefficient is set to a baseline of 1.0, requiring the system to output sufficient luminous flux.

[0113] The target user is a seated or standing user, with a corresponding posture coefficient of 0.7 – this corresponds to an elevated line of sight and reduced anti-glare.

[0114] Horizontal line of sight: When standing, a person's natural line of sight shifts from downward to horizontal. At this time, the light from the overhead light is more likely to shine directly into the eyes (creating direct glare).

[0115] Cutoff Angle Limitation: To avoid glare when standing, the luminaire must reduce its output brightness and narrow its solid angle of emission. The system is matched to 0.7, which is 70% of the brightness at a seated position. This satisfies the lighting requirements for walking / talking while standing, while strictly controlling glare interference at the horizontal line of sight.

[0116] The target user is lying down, with a corresponding posture coefficient of 0.5 – extremely low light exposure and ambient light dimming.

[0117] Pupil dilation and looking upwards: When lying down (such as on a bed or recliner), the eyes look upwards, directly facing the ceiling and light fixtures; at the same time, the pupils will naturally dilate when resting, and become extremely sensitive to light, so even dim light will feel dazzling.

[0118] S43, Measure the second distance between the light fixtures in the home space and the preset point.

[0119] For example, when the distance between the light fixture and the preset point The corresponding second distance is 1.0, which is the distance between the lamp and the preset point. exist When the distance is within the range, the corresponding second distance is Distance between the light fixture and the preset point When the distance is 0.4, the corresponding second distance is 0.4.

[0120] S44, perform a fusion calculation on the basic weights, the crowd coefficients, the posture coefficients, and the second distance to obtain the visual perception weights corresponding to the target user.

[0121] For example, the expression for the visual perception weight corresponding to the target user is obtained by fusing the basic weight, the crowd coefficient, the posture coefficient, and the second distance:

[0122]

[0123] in, Indicates the basic weight. This represents the target user's posture coefficient. Represents the distance coefficient. This represents the population coefficient.

[0124] For example, the base weights include the fixation area, non-fixation area, transition area, and non-transition area. For instance, the fixation area is set to 1.0, the non-fixation area is set to 0.5, and the transition area is set to 0.7~0.9.

[0125] Considering crowds, posture, or distance alone is insufficient to recreate a realistic visual experience. This application deeply integrates basic physical weights with crowds (physiological variables), posture (behavioral variables), and distance (spatial variables) for calculation. The final output "visual perception weight" becomes a multi-dimensional composite scaling factor. This weight can dynamically scale the sensor's cold "physical readings" to a "perceptual intensity" that fits the current user's real state.

[0126] This application also provides an implementation scenario for the adaptive duty cycle dimming control method.

[0127] I. Implementation Scenarios

[0128] The 12㎡ medium-sized family living room (δ=0.9) has ample natural light at 2 PM, allowing adults to sit and read on the sofa. The core solution addresses the issue of misjudging the dimming caused by reflections from the glass coffee table.

[0129] II. Hardware Configuration

[0130] Lighting fixtures: 1 ceiling light ( , , ), 4 downlights ( , , ); 2. Reflective surface: Glass coffee table ( ), latex paint wall ( ); 3. The sensing and computing units are integrated into the ceiling light, directly replacing the original light fixture.

[0131] III. Implementation Steps

[0132] Data collection: Adults detected ( Sitting posture ), 0.6m from point P ( Glass coffee table ; , .

[0133] Spatial light field reconstruction: Reflection interference illuminance: ;

[0134] Direct illuminance from artificial lights: 2 downlights on ( ),in (i.e., the angle between the light output axis of the downlight and the normal at point P). , , , Substitute into the formula ;

[0135] True effective illuminance: Substitute ,Will , , Substitute and calculate .

[0136] Visual weight calculation: .

[0137] Target illumination optimization: Substituting into the formula Because the calculation is performed on a single point P, ( Already merged ), , , Calculated Because of the ceiling light Actual (Limited by the maximum illuminance of the lamps).

[0138] PWM dimming output: , The lighting fixtures are controlled to operate with a duty cycle of 0.37 and a color temperature of 4000K (neutral white light suitable for reading, selected based on experience: 4000K neutral white light is between warm and cool light, and is an industry-recognized color temperature suitable for reading, balancing text clarity and eye strain); at this time, the reading area (point P) is blended... Both natural and artificial light are maintained at a stable illuminance of 400 lx (this 400 lx is an empirically selected value; the preset illuminance range for reading scenarios is 300-500 lx, and the middle value is chosen to suit typical home reading needs. Precise matching via PWM dimming ensures stable illuminance after the integration of natural and artificial light). Non-focused areas are adjusted according to basic weighting. Reduced to 160 lx (calculated based on: known reference illuminance of 400 lx in the reading area and base weight of the non-fixed area). The theoretical calculation value is 400lx × 0.5 = 200lx. Combining the basic lighting needs of the non-focus area with the energy-saving target, it is finely adjusted to 160lx, which not only meets the basic activity needs, but also achieves energy consumption optimization. Overall, it takes into account both visual comfort and energy saving.

[0139] The embodiments of this application can effectively solve the problem of dimming misjudgment caused by reflection interference, with a true illuminance error of ≤5% (better than the prior art of ≥15%); the illuminance in the reading area meets the standard, and the energy consumption in the non-viewing area is reduced by 20%; there is no dimming jump, which is suitable for practical home use.

[0140] The scope of protection of the adaptive duty cycle dimming control method described in this application is not limited to the execution order of the steps listed in this embodiment. Any solution implemented by adding, subtracting, or replacing steps in the prior art based on the principles of this application is included within the scope of protection of this application.

[0141] This application also provides an adaptive duty cycle dimming control device, which can implement the adaptive duty cycle dimming control method described in this application. However, the implementation device of the adaptive duty cycle dimming control method described in this application includes, but is not limited to, the structure of the adaptive duty cycle dimming control device listed in this embodiment. All structural modifications and substitutions of the prior art made based on the principles of this application are included within the protection scope of this application.

[0142] like Figure 5As shown, in one embodiment, the adaptive duty cycle dimming control device 50 of this application includes a true effective illuminance determination module 51, a visual perception weight determination module 52, a scene coefficient determination module 53, a target illuminance determination module 54, and an adaptive dimming module 55.

[0143] The true effective illuminance determination module 51 is used to perform spatial light field reconstruction processing on preset points in the home space and correct the true effective illuminance of the preset points.

[0144] The visual perception weight determination module 52 is used to calculate the visual perception weight corresponding to the target user based on the crowd coefficient, posture coefficient, and distance between the lamps and preset points in the home space.

[0145] The scenario coefficient determination module 53 is used to obtain the scenario coefficient corresponding to the target user.

[0146] The target illuminance determination module 54 is used to determine the target illuminance based on the actual effective illuminance, the visual perception weight, the scene coefficient, the preset benchmark illuminance, and the AI ​​correction coefficient. The AI ​​model adaptively adjusts the AI ​​correction coefficient by collecting home space data in real time.

[0147] The adaptive dimming module 55 is used to recursively deduce the current dimming duty cycle of the preset point based on the target illuminance and the dimming duty cycle of the preset point in the previous cycle, so as to realize adaptive dimming of the preset point.

[0148] The structure and principle of the real effective illuminance determination module 51, the visual perception weight determination module 52, the scene coefficient determination module 53, the target illuminance determination module 54, and the adaptive dimming module 55 correspond one-to-one with the steps in the adaptive duty cycle dimming control method described above, so they will not be repeated here.

[0149] In the embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, or methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative. For instance, the division of modules / units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple modules or units may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection of apparatuses or modules or units may be electrical, mechanical, or other forms.

[0150] The modules / units described as separate components may or may not be physically separate. The components shown as modules / units may or may not be physical modules; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules / units can be selected to achieve the objectives of the embodiments of this application, depending on actual needs. For example, the functional modules / units in the various embodiments of this application may be integrated into one processing module, or each module / unit may exist physically separately, or two or more modules / units may be integrated into one module / unit.

[0151] Those skilled in the art will further recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of the various examples have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0152] This application also provides an electronic device. Figure 6 The diagram shown is a structural schematic of an electronic device 60 in one embodiment of this application. The adaptive duty cycle dimming control method provided in this embodiment can be applied to… Figure 6 The electronic device shown is 60, but it is not limited to this. For example... Figure 6 As shown, the electronic device 60 includes a processor 61, a memory, a system bus 63, and a network interface 65. The memory may include a non-volatile storage medium 62 and internal memory 64.

[0153] The non-volatile storage medium 62 can store an operating system and a computer program. The computer program includes program instructions that, when executed, cause the processor to perform any of the adaptive duty cycle dimming control methods provided in the embodiments of this application.

[0154] The processor provides computing and control capabilities, supporting the operation of the entire computer device.

[0155] The internal memory 64 provides an environment for the execution of a computer program in a non-volatile storage medium. When the computer program is executed by the processor, it enables the processor to execute any of the adaptive duty cycle dimming control methods provided in the embodiments of this application.

[0156] This network interface 65 is used for network communication, such as sending assigned tasks. Those skilled in the art will understand that... Figure 6The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0157] It should be understood that processor 61 can be a Central Processing Unit (CPU), but it can also be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. Among these, the general-purpose processor can be a microprocessor or any conventional processor.

[0158] The electronic device 60 in this application embodiment may include terminal devices such as tablet computers, laptop computers, mobile phones, supercomputers, and smart wearable devices. It can also be applied to databases, servers, and service response systems based on terminal artificial intelligence. This application embodiment does not impose any restrictions on the specific type of electronic device.

[0159] For example, electronic devices can be stations (STAION, ST) in WLANs, cellular phones, cordless phones, Session Initiation Protocol (SIP) phones, Wireless Local Loop (WLL) stations, handheld devices with wireless communication capabilities, computing devices or other processing devices connected to a wireless modem, computers, laptops, handheld communication devices, handheld computing devices, and / or other devices for communicating over wireless systems, as well as next-generation communication systems, such as mobile terminals in 6G networks, mobile terminals in future evolved Public Land Mobile Networks (PLMNs), or mobile terminals in future evolved Non-terrestrial Networks (NTNs).

[0160] This application also provides a computer-readable storage medium. Those skilled in the art will understand that all or part of the steps in the methods of the above embodiments can be implemented by a program instructing a processor. The program can be stored in a computer-readable storage medium, which is a non-transitory medium, such as random access memory, read-only memory, flash memory, hard disk, solid-state drive, magnetic tape, floppy disk, optical disk, and any combination thereof. The storage medium can be any available medium accessible to a computer or a data storage device such as a server or data center that integrates one or more available media. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., digital video disc (DVD)), or a semiconductor medium (e.g., solid-state disk (SSD)).

[0161] This application embodiment may also provide a computer program product comprising one or more computer instructions. When the computer instructions are loaded and executed on a computing device, all or part of the processes or functions described in this application embodiment are generated. The computer instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions may be transmitted from one website, computer, or data center to another via wired (e.g., coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means.

[0162] When the computer program product is executed by a computer, the computer performs the method described in the foregoing method embodiments. The computer program product can be a software installation package; when the foregoing method is required, the computer program product can be downloaded and executed on the computer.

[0163] The descriptions of the processes or structures corresponding to the above figures each have their own emphasis. For parts of a process or structure that are not described in detail, please refer to the relevant descriptions of other processes or structures.

[0164] The above embodiments are merely illustrative of the principles and effects of this application and are not intended to limit this application. Any person skilled in the art can modify or alter the above embodiments without departing from the spirit and scope of this application. Therefore, all equivalent modifications or alterations made by those skilled in the art without departing from the spirit and technical concept disclosed in this application should still be covered by the claims of this application.

Claims

1. An adaptive duty cycle dimming control method, characterized in that, The method includes: The spatial light field of preset points in the home space is reconstructed to correct the true effective illuminance of the preset points. Quantifying the visual perception weights corresponding to target users within the home space includes: mapping the population coefficient of target users within the home space based on the age of the target users; matching the posture coefficient of target users within the home space based on the sitting, standing, and lying postures of the target users; measuring the second distance between the lamps and preset points within the home space; and performing a fusion calculation on the basic weights, the population coefficients, the posture coefficients, and the second distances to obtain the visual perception weights corresponding to the target users. Obtain the scene coefficient corresponding to the target user; determine the target illuminance based on the real effective illuminance, the visual perception weight, the scene coefficient, the preset benchmark illuminance, and the AI ​​correction coefficient, wherein the AI ​​model adaptively adjusts the AI ​​correction coefficient by collecting home space data in real time; The current dimming duty cycle of the preset point is recursively calculated based on the target illuminance and the dimming duty cycle of the preset point in the previous cycle, so as to achieve adaptive dimming of the preset point.

2. The method according to claim 1, characterized in that, The process of reconstructing the spatial light field at preset points within the home space to correct the true effective illuminance of the preset points includes: Collect the natural direct illuminance at the preset points; The artificial direct illuminance at the preset point is calculated based on the number of lamps in the home space. The reflected interference illuminance at the preset point is quantified based on the reflective material within the home space. The actual effective illuminance is corrected based on the natural light direct illuminance, the artificial light direct illuminance, and the reflected interference illuminance.

3. The method according to claim 2, characterized in that, The expression for calculating the direct illuminance of artificial lights at the preset point based on the sum of the number of lights in the home space is as follows: in, Indicates the number of light fixtures. Indicates the first The light intensity of the lamp, This indicates the angle between the light output axis of the lamp and the normal to the preset point. Indicates the first The distance from each lamp to the preset point Indicates the first Type coefficient of lamps, This represents the direct illuminance of artificial light at the preset point P.

4. The method according to claim 2, characterized in that, The quantification of the reflected interference illuminance at the preset point based on the reflective material within the home space includes: Identify the reflective material at preset points within the home space; Based on the reflective material, query the reflection correction coefficient; The surface reflectivity is obtained based on the reflective material; Measure the first distance from the reflective surface of the reflective material to the sensor; Based on the spatial dimensions of the aforementioned home space, a space correction coefficient is matched; The reflected interference illuminance at the preset point is quantified based on the sensor's original readings, the reflection correction coefficient, the surface reflectivity, the first distance, and the spatial correction coefficient.

5. The method according to claim 1, characterized in that, The expression for determining the target illuminance based on the true effective illuminance, the visual perception weight, the scene coefficient, the preset reference illuminance, and the AI ​​correction coefficient is as follows: in, Indicates the true effective illuminance. Represents visual perception weights. Indicates the preset reference illuminance. Indicates the AI ​​correction factor. denoted by , where P represents the preset point.

6. The method according to claim 1, characterized in that, The method further includes: When the environment within the home space changes, the AI ​​model collects data about the home space in real time. The AI ​​correction coefficient is automatically adjusted based on the home space data to ensure that the target illuminance is adapted to the current home space. The home space data includes, but is not limited to, reflective materials, attitude coefficients, and scene coefficients.

7. An adaptive duty cycle dimming control device, characterized in that, The device includes: The true effective illuminance determination module is used to perform spatial light field reconstruction processing on preset points in the home space and correct the true effective illuminance of the preset points. A visual perception weight determination module is used to quantify the visual perception weight corresponding to the target user in the home space; including: mapping the population coefficient of the target user in the home space based on the age of the target user; matching the posture coefficient of the target user in the home space based on the sitting, standing, and lying posture of the target user; measuring the second distance between the lamps in the home space and the preset point; and performing a fusion calculation on the basic weight, the population coefficient, the posture coefficient, and the second distance to obtain the visual perception weight corresponding to the target user; The scenario coefficient determination module is used to obtain the scenario coefficient corresponding to the target user; The target illuminance determination module is used to determine the target illuminance based on the actual effective illuminance, the visual perception weight, the scene coefficient, the preset benchmark illuminance, and the AI ​​correction coefficient. The AI ​​model adaptively adjusts the AI ​​correction coefficient by collecting home space data in real time. An adaptive dimming module is used to recursively deduce the current dimming duty cycle of the preset point based on the target illuminance and the dimming duty cycle of the preset point in the previous cycle, so as to achieve adaptive dimming of the preset point.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the method of any one of claims 1 to 6.

9. An electronic device, characterized in that, The electronic device includes: A memory that stores a computer program; The processor, which is communicatively connected to the memory, executes the method of any one of claims 1 to 6 when the computer program is invoked.

Images