Lighting control method and system based on illumination self-adaption

Abstract

This invention relates to the field of intelligent lighting technology and proposes a method and system for controlling sensor-activated lights based on adaptive illumination. The method includes: decomposing the light source contribution of multi-dimensional light field data to obtain natural light component spectra and artificial light component spectra; performing temporal evolution analysis on the variation law of illumination contribution to obtain natural light evolution characteristics; performing feature matching and strategy mapping on the natural light evolution characteristics to obtain a switch judgment threshold and anti-jitter holding time; comparing the natural light component illumination with the switch judgment threshold to obtain an initial illumination satisfaction level, and compensating and correcting the initial illumination satisfaction level to obtain illumination satisfaction; jointly determining the presence of human body sensing signals and illumination satisfaction to obtain a sensing trigger state; and performing anti-jitter delay verification on candidate switch actions based on the sensing trigger state and anti-jitter holding time to obtain the light switch output state. This invention can improve the efficiency of sensor-activated light control based on adaptive illumination.

Description

Technical Field

[0001] This invention relates to the field of intelligent lighting technology, and in particular to a light-adaptive sensor-controlled light switching method and system. Background Technology

[0002] Most existing sensor-controlled lighting solutions rely on a single illumination threshold for light control, failing to distinguish the contributions of natural and artificial light in the environment. They struggle to capture the changing characteristics of illumination in different sub-areas over time, and their illumination judgment parameters are often fixed, unable to dynamically adapt to changing illumination trends. This leads to illumination recognition errors and false triggering of lights. Furthermore, traditional solutions simply combine human body sensor signals and illumination values ​​for logical judgment, lacking compensation and correction for illumination components and failing to implement differentiated anti-shake verification logic for illumination variation characteristics. Instantaneous fluctuations in ambient illumination and sensor signal noise can cause frequent light start-stop cycles.

[0003] Traditional control methods struggle to achieve precise illumination analysis and adaptive parameter adjustment for specific spatial sub-regions. Illumination assessment results are easily distorted by artificial light interference, the reliability of joint judgment based on human body sensing and illumination conditions is insufficient, and anti-shake processing cannot match the actual rate of illumination change. Consequently, the overall recognition accuracy and operational stability of lighting control are limited. Therefore, improving the illumination analysis accuracy and operational stability of sensor-controlled lights has become an urgent problem to be solved. Summary of the Invention

[0004] This invention provides a light-adaptive sensor-controlled light switch method and system to solve the problems mentioned in the background art.

[0005] To achieve the above objectives, the present invention provides a light-adaptive sensor-controlled light switch method, comprising:

[0006] D1. Collect multidimensional light field data of sub-regions in the target area, and decompose the light source contribution of the multidimensional light field data to obtain the natural light component spectrum and artificial light component spectrum of the sub-region.

[0007] D2. Based on the natural light component spectrum, perform a time-series evolution analysis on the variation law of illumination contribution in the target region to obtain the natural light evolution characteristics of the sub-region;

[0008] D3. Based on the preset historical light-sensing response record, perform feature matching on the natural light evolution characteristics, and perform strategy mapping on the matching results to obtain the on / off judgment threshold and anti-shake holding time of the sub-region.

[0009] D4. Compare the natural light component illumination of the sub-region with the switch determination threshold item by item to obtain the initial illumination satisfaction level of the sub-region, and compensate and correct the initial illumination satisfaction level based on the artificial light component spectrum to obtain the illumination satisfaction of the sub-region.

[0010] D5. Obtain the human presence sensing signal of a sub-region in the target area, and jointly determine the human presence sensing signal with the illumination satisfaction to obtain the sensing trigger state of the sub-region.

[0011] D6. Based on the induction trigger state, determine the candidate switch action of the sub-region, and perform anti-shake delay verification on the candidate switch action based on the induction trigger state and the anti-shake holding time, to obtain the light switch output state of the sub-region in the target region.

[0012] In a preferred embodiment, the step of acquiring multidimensional light field data of a sub-region within the target region and performing light source contribution decomposition on the multidimensional light field data to obtain the natural light component spectrum and artificial light component spectrum of the sub-region includes:

[0013] Divide the target area into spatially independent sub-regions;

[0014] Spectral features are extracted from the multidimensional light field data of the sub-region to obtain the spectral response of the sub-region, which is the light response intensity of the sub-region in different wavelength ranges.

[0015] Based on the response intensity of the spectral response, the light source type of the sub-region is identified to obtain the light source type of the sub-region. The light source type is used to distinguish between the natural light contribution region and the artificial light contribution region.

[0016] The spectral response intensities of the natural light contribution region and the artificial light contribution region are collected and statistically analyzed to obtain the natural light contribution data and artificial light contribution data of the sub-region.

[0017] The natural light contribution data and the artificial light contribution data are reconstructed to obtain the natural light component spectrum and the artificial light component spectrum of the sub-region.

[0018] In a preferred embodiment, the step of performing a time-series evolution analysis on the illumination contribution variation pattern of the target region based on the natural light component spectrum to obtain the natural light evolution characteristics of the sub-region includes:

[0019] The natural light component map is sliced ​​temporally to obtain a natural light component image sequence, which represents the distribution of natural light contribution of the sub-region at different times.

[0020] Based on the natural light component image sequence, cross-frame difference analysis is performed on the illumination contribution value of the target region to obtain the illumination change increment sequence of the sub-region.

[0021] By identifying continuous segments in the incremental sequence of illumination changes, the type of increase or decrease trend and the rate of change of natural illumination in the sub-region are obtained;

[0022] Based on the increase / decrease trend type and the change rate, the illumination change pattern of the sub-region is summarized to obtain the natural light evolution characteristics of the sub-region.

[0023] In a preferred embodiment, the step of performing feature matching on the natural light evolution characteristics based on preset historical light response records, and performing strategy mapping on the matching results to obtain the on / off determination threshold and anti-shake holding duration of the sub-region includes:

[0024] The preset historical light-sensing response records are categorized by scene to obtain the historical light-sensing feature library of the preset historical light-sensing response records;

[0025] Based on the historical light sensing feature database, the natural light evolution features are compared and matched to obtain the matching confidence level of the natural light evolution features;

[0026] Based on the matching confidence level, the target historical scene is located from the historical light-sensing feature library, and the control strategy associated with the target historical scene is obtained. The control strategy includes historical threshold parameters and historical image stabilization parameters.

[0027] The control strategy is adaptively adjusted to obtain the switching threshold and anti-shake duration of the sub-region.

[0028] In a preferred embodiment, the adaptive adjustment of the control strategy to obtain the switching determination threshold and anti-shake holding time of the sub-region includes:

[0029] Based on the rate of change in the natural light evolution characteristics, the historical threshold parameters are compared to obtain the threshold offset of the sub-region;

[0030] Based on the threshold offset, the historical threshold parameter is corrected to obtain the switch determination threshold of the sub-region;

[0031] Based on the rate of change in the natural light evolution characteristics, the historical stabilization duration of the sub-region is allocated to obtain the stabilization retention duration of the sub-region, wherein the higher the rate of change, the longer the stabilization retention duration.

[0032] In a preferred embodiment, the step of comparing the natural light component illumination of the sub-region with the switch determination threshold item by item to obtain the initial illumination satisfaction level of the sub-region, and compensating and correcting the initial illumination satisfaction level based on the artificial light component spectrum to obtain the illumination satisfaction of the sub-region, includes:

[0033] The natural light component illumination of the sub-region is compared with the switch determination threshold item by item to obtain the natural light satisfaction ratio of the sub-region.

[0034] Based on the preset illumination level, the natural light satisfaction ratio is graded to obtain the initial illumination satisfaction level of the sub-region.

[0035] Based on the illumination value of the artificial light component in the sub-region of the artificial light component spectrum, the artificial light contribution of the initial illumination satisfaction level is quantified to obtain the artificial light compensation coefficient of the sub-region.

[0036] Based on the preset historical light-sensing response records, the proportion of natural light-driven decision frequency and artificial light-driven decision frequency in the sub-region is statistically analyzed to obtain the natural light weight coefficient and artificial light weight coefficient of the sub-region.

[0037] Based on the natural light satisfaction ratio, the artificial light compensation coefficient, the natural light weighting coefficient, and the artificial light weighting coefficient, the initial illumination satisfaction level of the sub-region is cross-coordinated and corrected to obtain the illumination satisfaction of the sub-region.

[0038] In a preferred embodiment, the formula for calculating the illumination satisfaction is as follows:

[0039] ;

[0040] in, For the first The illumination satisfaction of each sub-region For the first The natural light in each sub-region satisfies the required proportions. For the first The natural light weighting coefficients for each sub-region For the first The artificial light compensation coefficient for each sub-region For the first The artificial light weighting coefficients for each sub-region.

[0041] In a preferred embodiment, the step of acquiring a human presence sensing signal in a sub-region of the target area and jointly determining the human presence sensing signal with the illumination satisfaction level to obtain the sensing trigger state of the sub-region includes:

[0042] The human presence sensing signal of a sub-region in the target region is sampled in time to obtain the sensing signal time sequence of the sub-region;

[0043] Based on the time sequence of the sensing signal, the presence of human beings in the sub-region is evaluated to obtain the confidence level of human beings in the sub-region, and the confidence level of human beings is divided into low confidence level and high confidence level.

[0044] Based on the credibility of the human body presence and the light satisfaction, the sub-region is gated and triggered to obtain the sensing trigger state of the sub-region. In the sub-region with low credibility, the light on / off state of the sub-region is maintained. In the sub-region with high credibility, when the light satisfaction is lower than the preset trigger boundary, the light on state of the sub-region is triggered.

[0045] In a preferred embodiment, determining candidate switch actions for the sub-region based on the induction trigger state, and performing anti-shake delay verification on the candidate switch actions based on the induction trigger state and the anti-shake holding duration to obtain the light switch output state of the sub-region in the target region, includes:

[0046] Based on the sensing trigger state, the sub-region is mapped with action commands to obtain candidate switch actions for the sub-region;

[0047] The candidate switch actions are categorized by action direction to obtain the candidate action directions for the sub-region;

[0048] Based on the candidate action direction and the anti-shake duration, the sub-region is configured with a differentiated verification window to obtain the anti-shake verification window for the sub-region.

[0049] Within the anti-shake verification window, the state of the sensor triggering state of the sub-region is compared to obtain the state consistency verification result of the sub-region.

[0050] Based on the state consistency verification result, the candidate switch action is output confirmation to obtain the light switch output state of the sub-region in the target area.

[0051] To address the aforementioned problems, the present invention also provides a light-adaptive sensor-controlled lamp switch system, the system comprising:

[0052] The multidimensional light field decomposition module is used to collect multidimensional light field data of sub-regions in the target area, and to decompose the light source contribution of the multidimensional light field data to obtain the natural light component spectrum and artificial light component spectrum of the sub-region.

[0053] The natural light temporal analysis module is used to perform temporal evolution analysis on the light contribution variation law of the target region based on the natural light component spectrum, and obtain the natural light evolution characteristics of the sub-region;

[0054] The strategy mapping module is used to perform feature matching on the natural light evolution characteristics based on preset historical light-sensing response records, and to perform strategy mapping on the matching results to obtain the on / off judgment threshold and anti-shake holding time of the sub-region.

[0055] The illumination satisfaction compensation calculation module is used to compare the natural light component illumination of the sub-region with the switch judgment threshold item by item to obtain the initial illumination satisfaction level of the sub-region, and to compensate and correct the initial illumination satisfaction level based on the artificial light component spectrum to obtain the illumination satisfaction of the sub-region.

[0056] The human presence sensing and illumination joint decision module is used to acquire the human presence sensing signal of a sub-region in the target area, and to jointly determine the human presence sensing signal and the illumination satisfaction to obtain the sensing trigger state of the sub-region.

[0057] The anti-shake lighting control output module is used to determine the candidate switch action of the sub-region based on the sensing trigger state, and to perform anti-shake delay verification on the candidate switch action based on the sensing trigger state and the anti-shake holding duration, so as to obtain the lighting switch output state of the sub-region in the target region.

[0058] Compared with the prior art, the present invention has the following beneficial effects:

[0059] 1. This invention decomposes the light source contribution of multidimensional light field data to separate the natural light component spectrum and the artificial light component spectrum. It then extracts the natural light evolution characteristics through temporal evolution analysis and completes feature matching and strategy mapping based on historical light response records. This adaptively outputs the switch judgment threshold and anti-shake holding time. This method can dynamically adjust control parameters according to the actual changes in illumination in sub-regions, achieving adaptive adaptation of illumination judgment conditions, improving the accuracy of illumination condition recognition, and reducing misjudgment problems caused by fixed thresholds.

[0060] 2. This invention obtains illumination satisfaction by co-calculating natural and artificial light, jointly determines illumination satisfaction with human presence sensing signals, and performs anti-shake delay verification on candidate switching actions based on anti-shake hold duration. Through multi-dimensional illumination compensation correction and the human presence-illumination joint decision mechanism, reliable output of sub-region lighting control actions is achieved, effectively suppressing frequent switching actions caused by instantaneous illumination fluctuations and human presence sensing signal disturbances, and improving the overall control stability and operating efficiency of sensor-controlled lights. Attached Figure Description

[0061] Figure 1 This is a flowchart illustrating a light-adaptive sensor-controlled light switch method according to an embodiment of the present invention.

[0062] Figure 2 A functional block diagram of a light-adaptive sensor-controlled lamp switch system provided in an embodiment of the present invention;

[0063] The realization of the objective, functional features and advantages of the present invention will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0064] It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.

[0065] This application provides a light-adaptive sensor-activated light switch control method. The executing entity of the light-adaptive sensor-activated light switch control method includes, but is not limited to, at least one of the following electronic devices that can be configured to execute the method provided in this application: a server, a terminal, etc. In other words, the light-adaptive sensor-activated light switch control method can be executed by software or hardware installed on a terminal device or a server device. The server includes, but is not limited to, a single server, a server cluster, a cloud server, or a cloud server cluster. The server can be an independent server or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, content delivery networks (CDNs), and big data and artificial intelligence platforms.

[0066] Reference Figure 1 The diagram shown is a schematic flowchart of a light-adaptive sensor-controlled light switch method according to an embodiment of the present invention. In this embodiment, the light-adaptive sensor-controlled light switch method includes:

[0067] D1. Collect multidimensional light field data of sub-regions in the target area, and decompose the light source contribution of the multidimensional light field data to obtain the natural light component spectrum and artificial light component spectrum of the sub-region.

[0068] In this embodiment of the invention, the step of acquiring multidimensional light field data of a sub-region within the target area and performing light source contribution decomposition on the multidimensional light field data to obtain the natural light component spectrum and artificial light component spectrum of the sub-region includes:

[0069] Divide the target area into spatially independent sub-regions;

[0070] Spectral features are extracted from the multidimensional light field data of the sub-region to obtain the spectral response of the sub-region, which is the light response intensity of the sub-region in different wavelength ranges.

[0071] Based on the response intensity of the spectral response, the light source type of the sub-region is identified to obtain the light source type of the sub-region. The light source type is used to distinguish between the natural light contribution region and the artificial light contribution region.

[0072] The spectral response intensities of the natural light contribution region and the artificial light contribution region are collected and statistically analyzed to obtain the natural light contribution data and artificial light contribution data of the sub-region.

[0073] The natural light contribution data and the artificial light contribution data are reconstructed to obtain the natural light component spectrum and the artificial light component spectrum of the sub-region.

[0074] The target area is divided according to the spatial distribution boundary. The boundary is the coverage of the independent lighting control circuit within the target area. Each sub-area corresponds to an independent lighting control unit. There is no spatial overlap between sub-areas and the sub-areas completely cover the entire target area. After the division, each sub-area has spatial independence. Different sub-areas correspond to non-overlapping spatial ranges within the target area. Each sub-area can serve as an independent lighting processing unit to receive all subsequent light field-related processing flows.

[0075] For each sub-region that has been divided, spectral feature extraction is performed on the multi-dimensional light field data. All wavelength ranges contained in the multi-dimensional light field data are completely traversed, and the light response intensity corresponding to each wavelength range is read one by one. All wavelength ranges and their corresponding light response intensities are completely sorted and summarized. After sorting and summarizing, the spectral response of the sub-region is obtained. The spectral response completely preserves the correspondence between the light response intensities of the sub-region in different wavelength ranges.

[0076] The system reads the light response intensity corresponding to each wavelength range in the generated spectral response, compares the distribution characteristics of the light response intensity in different wavelength ranges to identify the light source type, determines the light source type corresponding to the current sub-region based on the distribution characteristics of the light response intensity, and directly distinguishes between the natural light contribution area and the artificial light contribution area based on the determined light source type, clarifying which spatial ranges within the sub-region belong to the natural light contribution area and which spatial ranges belong to the artificial light contribution area.

[0077] All spatial locations within the sub-region marked as natural light contribution areas are located. All spectral response intensities corresponding to these spatial locations are collected and organized. The collected spectral response intensities are then statistically processed, and the natural light contribution data for the sub-region is output after the statistical processing. Simultaneously, all spatial locations within the sub-region marked as artificial light contribution areas are located. All spectral response intensities corresponding to these spatial locations are collected. The corresponding spectral response intensities are then statistically processed, and the artificial light contribution data for the sub-region is output after the statistical processing.

[0078] Read the generated natural light contribution data and perform map reconstruction according to the illumination distribution information of each spatial location within the sub-region. Map the illumination information carried by the natural light contribution data onto the corresponding spatial locations to fully reproduce the spatial distribution of natural light within the sub-region. After map reconstruction, the natural light component map of the sub-region is obtained. Then, read the generated artificial light contribution data and perform map reconstruction with reference to the distribution information of each spatial location within the sub-region. Map the illumination information recorded in the artificial light contribution data onto the corresponding spatial locations to fully reproduce the spatial distribution of artificial light within the sub-region. After map reconstruction, the artificial light component map of the sub-region is obtained.

[0079] The beneficial effects include dividing the target area into multiple spatially independent sub-regions for targeted light field analysis, identifying the light source type based on spectral response, directly separating the natural light contribution area and the artificial light contribution area, and then generating natural light component maps and artificial light component maps through aggregation statistics and map reconstruction. This can completely separate the two different sources of light in the environment, accurately restore the actual spatial light distribution of natural light and artificial light in different sub-regions, eliminate the problem of light information confusion caused by the mixing of the two types of light, and provide accurate and reliable original light field basic data for subsequent lighting control processes such as lighting time sequence evolution analysis and lighting satisfaction calculation, ensuring the authenticity and effectiveness of the environmental lighting identification in the subsequent sensor-controlled lighting process.

[0080] D2. Based on the natural light component spectrum, perform a time-series evolution analysis on the variation law of illumination contribution in the target region to obtain the natural light evolution characteristics of the sub-region;

[0081] In this embodiment of the invention, the step of performing a time-series evolution analysis on the illumination contribution variation law of the target region based on the natural light component spectrum to obtain the natural light evolution characteristics of the sub-region includes:

[0082] The natural light component map is sliced ​​temporally to obtain a natural light component image sequence, which represents the distribution of natural light contribution of the sub-region at different times.

[0083] Based on the natural light component image sequence, cross-frame difference analysis is performed on the illumination contribution value of the target region to obtain the illumination change increment sequence of the sub-region.

[0084] By identifying continuous segments in the incremental sequence of illumination changes, the type of increase or decrease trend and the rate of change of natural illumination in the sub-region are obtained;

[0085] Based on the increase / decrease trend type and the change rate, the illumination change pattern of the sub-region is summarized to obtain the natural light evolution characteristics of the sub-region.

[0086] The natural light component map is processed by temporal slicing in chronological order. Each slice operation captures the complete spatial distribution information of natural light in a sub-region at a specific time. The map content corresponding to different time nodes is captured in sequence. The map fragments captured at each time node are arranged and combined in chronological order. After the arrangement and combination are completed, a natural light component image sequence is generated. The natural light component image sequence completely preserves the distribution of all natural light contribution of the sub-region at different times.

[0087] Content comparison processing is performed on adjacent image frames in the natural light component image sequence one by one. The illumination contribution value corresponding to each spatial position in each frame is read. The arithmetic mean of the differences of all spatial positions is taken as the illumination change increment for that time interval. The illumination contribution value of each position in the next frame is subtracted from the illumination contribution value of the corresponding position in the previous frame to obtain the numerical change of illumination contribution at each spatial position between adjacent frames. The change results obtained from the comparison of all frames are arranged in order according to the time sequence of the image sequence. After the arrangement is completed, the illumination change increment sequence of the sub-region is generated.

[0088] The entire sequence of light change increments is traversed sequentially over time. Data segments that are time-continuous and maintain a consistent direction of change are divided into independent continuous segments. For each continuous segment identified, the overall trend of light change corresponding to that segment is determined, thereby identifying the type of increase or decrease in natural light in the sub-region. At the same time, the overall change magnitude of all data within the continuous segment is calculated, combined with the actual time span corresponding to the continuous segment, to determine the rate of light change corresponding to the continuous segment. After completing the traversal and identification of all continuous segments, the complete type of increase or decrease in natural light and the rate of change of change in the sub-region are obtained.

[0089] By combining the obtained increase and decrease trend types, the overall trend of natural light change in the sub-region is clarified. By combining the obtained change rate, the speed of change of natural light is determined. The increase and decrease trend types and change rates corresponding to different time periods in the same sub-region are integrated and sorted out. In the sorting process, the illumination processes with the same change trend and similar change rate are grouped into the same change pattern. After completing the classification and sorting of all illumination processes in the sub-region, the pattern of illumination change law in the sub-region is summarized. After the pattern is summarized, the natural light evolution characteristics of the sub-region are obtained.

[0090] The beneficial effects are that by obtaining image sequences of natural light components at different times through time-series slicing, obtaining the incremental sequence of illumination changes based on cross-frame difference analysis, and then carrying out continuous segment identification to extract the type and rate of increase and decrease in illumination, the evolution characteristics of natural light are obtained by summarizing the pattern of illumination change. This can fully explore the dynamic change pattern of natural light in sub-regions over time, remove the information interference brought by artificial light, and objectively reflect the real dynamic evolution process of natural light. This provides a real and effective feature basis for feature matching of subsequent historical light response records and adaptive calculation of threshold and anti-shake duration, and improves the matching degree between subsequent lighting control parameter configuration and actual lighting environment.

[0091] D3. Based on the preset historical light-sensing response record, perform feature matching on the natural light evolution characteristics, and perform strategy mapping on the matching results to obtain the on / off judgment threshold and anti-shake holding time of the sub-region.

[0092] In this embodiment of the invention, the step of performing feature matching on the natural light evolution characteristics based on preset historical light response records, and performing strategy mapping on the matching results to obtain the on / off determination threshold and anti-shake holding duration of the sub-region includes:

[0093] The preset historical light-sensing response records are categorized by scene to obtain the historical light-sensing feature library of the preset historical light-sensing response records;

[0094] Based on the historical light sensing feature database, the natural light evolution features are compared and matched to obtain the matching confidence level of the natural light evolution features;

[0095] Based on the matching confidence level, the target historical scene is located from the historical light-sensing feature library, and the control strategy associated with the target historical scene is obtained. The control strategy includes historical threshold parameters and historical image stabilization parameters.

[0096] The control strategy is adaptively adjusted to obtain the switching threshold and anti-shake duration of the sub-region.

[0097] The adaptive adjustment of the control strategy to obtain the switching threshold and anti-shake duration of the sub-region includes:

[0098] Based on the rate of change in the natural light evolution characteristics, the historical threshold parameters are compared to obtain the threshold offset of the sub-region;

[0099] Based on the threshold offset, the historical threshold parameter is corrected to obtain the switch determination threshold of the sub-region;

[0100] Based on the rate of change in the natural light evolution characteristics, the historical stabilization duration of the sub-region is allocated to obtain the stabilization retention duration of the sub-region, wherein the higher the rate of change, the longer the stabilization retention duration.

[0101] The system reads each preset historical light sensor response record one by one, reading all the ambient lighting information and corresponding lighting control execution status stored within the records. Each record includes natural light evolution characteristics, on / off judgment threshold, anti-shake holding time, and actual operating effect data. Based on the natural light change trend and the speed of light change recorded in the records, each historical light sensor response record is classified into the corresponding scene category. After all historical light sensor response records are classified and stored, a historical light sensor feature library corresponding to the preset historical light sensor response records is constructed. The historical light sensor feature library completely includes various historical lighting features and related lighting control records bound to them according to scene category.

[0102] The system retrieves historical feature content corresponding to various scenes stored in the historical light sensing feature database. It then compares the natural light evolution features obtained from the current sub-region with the historical features of each scene category in the database item by item. The cosine similarity algorithm is used to calculate feature similarity, and the similarity value is the matching confidence score, ranging from 0 to 1, with a passing threshold of 0.7. The system checks the consistency of the light change trends and the rate of light change contained in each feature, and calculates the consistency percentage across all feature dimensions. This generates the matching confidence score for the natural light evolution features, which reflects the degree of consistency between the current natural light evolution features and the features of various scenes in the historical light sensing feature database.

[0103] Based on the calculated matching confidence levels, select scenes from the historical light-sensing feature library that meet the set requirements as target historical scenes. Read the complete content of the control strategy bound to the target historical scene, and extract the corresponding historical threshold parameters and historical anti-shake parameters from the control strategy. The historical threshold parameters record the illumination reference standard used for light switch judgment in the historical scene, and the historical anti-shake parameters record the time reference standard used to suppress light malfunctions in the historical scene.

[0104] Adaptive adjustment is performed on the control strategy that includes historical threshold parameters and historical stabilization parameters. After a complete parameter correction and duration allocation process, the switch judgment threshold and stabilization duration that are adapted to the actual illumination state of the current sub-region are output.

[0105] Extract the change rate information recorded in the natural light evolution characteristics, compare the deviation between the light change state corresponding to the change rate and the historical light change state adapted to the historical threshold parameters, find the difference between the current light change state and the historical scene light change state, and obtain the threshold offset of the sub-region after complete sorting and quantification. The threshold offset represents the amount of modification that needs to be made to the historical threshold parameters.

[0106] The threshold offset is used to perform threshold correction on the historical threshold parameters. The reference standard of the historical threshold parameters is changed according to the change reflected by the threshold offset to eliminate the state gap between the current lighting environment and the historical scene lighting environment. After the correction is completed, the switch judgment threshold that adapts to the current lighting status of the sub-region is obtained.

[0107] The rate of change carried by the evolution characteristics of natural light is read, and the historical image stabilization duration is allocated based on the actual situation of the rate of change. The rate of change corresponds to how fast the illumination state changes. The faster the illumination state changes, the longer the image stabilization time is allocated, and the slower the illumination state changes, the shorter the image stabilization time is allocated. After the time allocation is completed, the image stabilization duration of the sub-region is obtained.

[0108] The beneficial effects are as follows: by classifying scenes and constructing a historical light sensing feature library based on preset historical light sensing response records, the real-time acquired natural light evolution features are compared with historical features in the library to obtain matching confidence. Based on the matching confidence, the target historical scene is located and the corresponding control strategy is retrieved. Then, based on the change rate within the natural light evolution features, the threshold offset is calculated, the historical threshold parameters are corrected, and the historical anti-shake duration is allocated. It can combine past actual lighting control operation experience to complete the adaptive adaptation of parameters without the need for fixed parameter configuration. The switch judgment threshold and anti-shake holding duration are dynamically changed according to the current natural light change rate, so that the lighting control judgment standard and anti-shake time can fit the real-time light evolution of the sub-area, reducing the probability of false lighting triggers caused by fixed parameters, and outputting adapted basic control parameters for subsequent light level judgment and anti-shake verification.

[0109] D4. Compare the natural light component illumination of the sub-region with the switch determination threshold item by item to obtain the initial illumination satisfaction level of the sub-region, and compensate and correct the initial illumination satisfaction level based on the artificial light component spectrum to obtain the illumination satisfaction of the sub-region.

[0110] In this embodiment of the invention, the step of comparing the natural light component illumination of the sub-region with the switch determination threshold item by item to obtain the initial illumination satisfaction level of the sub-region, and compensating and correcting the initial illumination satisfaction level based on the artificial light component spectrum to obtain the illumination satisfaction of the sub-region, includes:

[0111] The natural light component illumination of the sub-region is compared with the switch determination threshold item by item to obtain the natural light satisfaction ratio of the sub-region.

[0112] Based on the preset illumination level, the natural light satisfaction ratio is graded to obtain the initial illumination satisfaction level of the sub-region.

[0113] Based on the illumination value of the artificial light component in the sub-region of the artificial light component spectrum, the artificial light contribution of the initial illumination satisfaction level is quantified to obtain the artificial light compensation coefficient of the sub-region.

[0114] Based on the preset historical light-sensing response records, the proportion of natural light-driven decision frequency and artificial light-driven decision frequency in the sub-region is statistically analyzed to obtain the natural light weight coefficient and artificial light weight coefficient of the sub-region.

[0115] Based on the natural light satisfaction ratio, the artificial light compensation coefficient, the natural light weighting coefficient, and the artificial light weighting coefficient, the initial illumination satisfaction level of the sub-region is cross-coordinated and corrected to obtain the illumination satisfaction of the sub-region.

[0116] The formula for calculating the illumination satisfaction is as follows:

[0117] ;

[0118] in, For the first The illumination satisfaction of each sub-region For the first The natural light in each sub-region satisfies the required proportions. For the first The natural light weighting coefficients for each sub-region For the first The artificial light compensation coefficient for each sub-region For the first The artificial light weighting coefficients for each sub-region.

[0119] The natural light component illumination collected and stored at each spatial point in the sub-region is extracted. The natural light component illumination value corresponding to each spatial point in the sub-region is compared with the switch judgment threshold that has been adaptively adjusted. The arithmetic mean of the ratios of all sampling points is taken as the natural light satisfaction ratio of the sub-region, with a value range of 0 to 2. The ratio of the natural light component illumination relative to the switch judgment threshold at each point is calculated. The ratio results calculated for all spatial points in the sub-region are uniformly collected and integrated. After the integration calculation, the natural light satisfaction ratio of the sub-region is obtained. The natural light satisfaction ratio can fully reflect the overall proportion of natural light component illumination relative to the switch judgment threshold in the entire sub-region, and intuitively show the degree to which the judgment standard can be met by relying solely on natural light conditions.

[0120] The preset illumination levels are derived from extensive testing data of lighting control equipment under varying illumination conditions. Multiple independent level ranges are defined based on differences in illumination sufficiency, resulting in four levels: sufficient (greater than 1.2), acceptable (0.8, 1.2), insufficient (0.5, 0.8), and severely insufficient (less than 0.5). The corresponding initial satisfaction levels are 4 to 1, with each level range corresponding to a fixed proportional value. The preset illumination levels are retrieved, and the acquired natural light satisfaction ratios are compared to the proportional ranges within each level range to determine the specific level range into which the current natural light satisfaction ratio falls. This completes the grading process for natural light satisfaction ratios. The initial illumination satisfaction level for each sub-region is then obtained. This initial illumination satisfaction level is based solely on the natural light component within the sub-region and only reflects the sufficiency of illumination from natural light alone.

[0121] The artificial light component illumination values ​​corresponding to all spatial points in the sub-region are read from the complete record of the artificial light component map. The artificial light component illumination values ​​corresponding to each spatial location in the sub-region are included in the calculation scope of this quantization process. Based on the actual magnitude of the artificial light component illumination values, the illumination gain effect of artificial light on the environment is converted into a standardized quantized value that can participate in the level correction calculation. This completes the quantization process of artificial light contribution for the initial illumination satisfaction level. After the quantization process is completed, the artificial light compensation coefficient of the sub-region is obtained. The artificial light compensation coefficient can quantitatively characterize the actual gain contribution that artificial light can make to the overall environmental illumination within the current sub-region.

[0122] The preset historical light sensor response record is continuously collected and stored by the device during its long-term operation. It accumulates the light source, triggering conditions, and decision results corresponding to each lighting control decision. The system reads all past lighting control decision records for this sub-region from the preset historical light sensor response record, distinguishing whether each decision was triggered primarily by changes in natural light conditions or artificial light conditions. The total number of natural light-driven decisions and the total number of artificial light-driven decisions are counted separately. The percentage of natural light-driven decision frequency is calculated by dividing the total number of natural light-driven decisions by the cumulative total number of all lighting control decisions in this sub-region, generating the natural light weight coefficient for this sub-region. Similarly, the percentage of artificial light-driven decision frequency is calculated by dividing the total number of artificial light-driven decisions by the cumulative total number of all lighting control decisions in this sub-region, generating the artificial light weight coefficient for this sub-region. These two weight coefficients respectively reflect the respective influence of natural and artificial light sources in all past historical lighting control decisions for this sub-region.

[0123] The calculated natural light satisfaction ratio, artificial light compensation coefficient, natural light weight coefficient, and artificial light weight coefficient are all imported into this correction process. Taking into account the actual degree to which natural light can meet the judgment criteria, the light gain effect of artificial light on the overall environment, and the actual impact of the two types of light sources in the historical lighting control decision-making process of this sub-region, cross-coordinated correction processing is carried out on the initial light satisfaction level calculated solely based on natural light component illumination. This process compensates for the one-sidedness of the evaluation caused by using only natural light for illumination assessment. The light contribution of both natural and artificial light is included in the evaluation consideration. After completing the multi-dimensional conditional co-correction, the light satisfaction of the sub-region is obtained. The light satisfaction can objectively reflect the actual state of sufficient illumination in the overall environment of the sub-region by comprehensively considering the contributions of the two types of light sources.

[0124] The natural light satisfaction ratio of a sub-region is obtained by comparing the natural light component illumination at each point in the sub-region with the switch judgment threshold, and then collecting and integrating the comparison results of all points. The natural light weight coefficient and artificial light weight coefficient of the sub-region are obtained by reading the preset historical light sensing response records and calculating the proportion of the natural light driving decision frequency and the artificial light driving decision frequency in the sub-region to the total frequency of all lighting control decisions. The artificial light compensation coefficient of the sub-region is obtained by reading the artificial light component illumination value at each position in the sub-region within the artificial light component spectrum and completing the artificial light contribution quantification process. All the above parameters are dimensionless proportional values, and the dimensions of each other are kept consistent.

[0125] This calculation process comprehensively incorporates the natural light satisfaction ratio, natural light weighting coefficient, artificial light compensation coefficient, and artificial light weighting coefficient. It merges the contribution results corresponding to natural light and artificial light, and then combines the interaction between the four types of parameters to complete the constraint calculation of the overall result. Finally, it outputs the illumination satisfaction level of the sub-region, thereby incorporating both natural and artificial light conditions into the illumination evaluation process. This enables cross-coordinated correction of the initial illumination satisfaction level and fully reflects the overall illumination sufficiency level under the combined effect of natural and artificial light within the sub-region.

[0126] Assuming all other conditions remain unchanged, an increase in the natural light satisfaction ratio or an increase in the artificial light compensation coefficient will cause the final output illumination satisfaction to increase synchronously. Increasing the natural light weighting coefficient can amplify the improvement effect of the natural light satisfaction ratio on the output result, and increasing the artificial light weighting coefficient can amplify the improvement effect of the artificial light compensation coefficient on the output result. The interaction constraint between the four types of parameters can limit the range of change in illumination satisfaction and prevent the illumination satisfaction from increasing without limit.

[0127] The beneficial effects are as follows: The natural light satisfaction ratio is obtained by comparing the ratios of the natural light component illumination and the switch judgment threshold; an initial illumination satisfaction level is generated based on the preset illumination levels defined by actual measurements; and the artificial light component illumination value is analyzed and quantified to obtain the artificial light compensation coefficient. Relying on historical light-sensing response records accumulated over long-term equipment operation, the frequency proportion of different light source-driven decisions is statistically analyzed to obtain weighting coefficients, and the initial illumination satisfaction level is cross-coordinatedly corrected to obtain the illumination satisfaction. This method considers the illumination contribution of both natural and artificial light, abandoning the one-sided mode of relying solely on natural light to evaluate illumination, avoiding evaluation bias caused by ignoring artificial light, and outputting an illumination satisfaction level that fits the actual working conditions. This provides a reliable basis for the joint judgment of human and artificial illumination, ensuring the accuracy of sensor-controlled lighting decisions.

[0128] D5. Obtain the human presence sensing signal of a sub-region in the target area, and jointly determine the human presence sensing signal with the illumination satisfaction to obtain the sensing trigger state of the sub-region.

[0129] In this embodiment of the invention, the step of acquiring a human presence sensing signal in a sub-region of the target area and jointly determining the human presence sensing signal with the illumination satisfaction level to obtain the sensing trigger state of the sub-region includes:

[0130] The human presence sensing signal of a sub-region in the target region is sampled in time to obtain the sensing signal time sequence of the sub-region;

[0131] Based on the time sequence of the sensing signal, the presence of human beings in the sub-region is evaluated to obtain the confidence level of human beings in the sub-region, and the confidence level of human beings is divided into low confidence level and high confidence level.

[0132] Based on the credibility of the human body presence and the light satisfaction, the sub-region is gated and triggered to obtain the sensing trigger state of the sub-region. In the sub-region with low credibility, the light on / off state of the sub-region is maintained. In the sub-region with high credibility, when the light satisfaction is lower than the preset trigger boundary, the light on state of the sub-region is triggered.

[0133] The system continuously collects human presence sensing signals from sub-regions within the target area at fixed time intervals. After each collection, the sensing signal content corresponding to the current moment is saved along with the corresponding timestamp. The sensing signals collected at different time points are arranged and summarized in chronological order to obtain the sensing signal time sequence of the sub-region. The sensing signal time sequence completely records all the information about the changes in all human presence sensing signals in the sub-region over time within a continuous time range.

[0134] The system reads the sensor signal content corresponding to all time nodes in the time sequence of the sensor signal, compares the frequency of occurrence, duration, and continuity of the sensor signal within a continuous time period to conduct a human presence assessment in the sub-region, and judges the possibility that there are actually people in the sub-region based on the signal performance over multiple time periods. After the assessment is completed, the credibility of human presence in the sub-region is obtained. According to the credibility threshold, the calculated credibility of human presence is directly divided into two categories: low credibility and high credibility, so as to distinguish whether the sensor signal effectively detects human beings or is an abnormal signal caused by environmental interference.

[0135] By combining the already defined categories of human presence confidence with the calculated illumination satisfaction, gated trigger matching processing is performed for sub-regions. The final output is the sensor trigger state of the sub-region. When a sub-region is determined to have low confidence, it means that the sensor signal is insufficient to confirm that someone is present. The current on / off state of the sub-region is maintained without modification. When a sub-region is determined to have high confidence, it means that the sensor signal confirms that someone is present. The illumination satisfaction is then compared with the preset trigger boundary. The preset trigger boundary was obtained through extensive field testing and calibration based on the on-site lighting control requirements. It is set to an illumination satisfaction of 0.8. If the value is lower than this, it is determined that the illumination is insufficient and the condition for turning on the lights is met. When the illumination satisfaction is lower than the preset trigger boundary, the sensor trigger state corresponding to turning on the lights in the sub-region is generated.

[0136] The beneficial effects are as follows: by obtaining a temporal sequence of sensing signals through time-series sampling, the credibility of human presence is evaluated based on the temporal signals and divided into two levels. Gating trigger matching is then completed by combining the credibility level with the lighting satisfaction level. This can filter out invalid sensing signals caused by environmental disturbances, preventing the lighting action from being executed directly based on a single sensing signal. The lighting trigger state is only generated when there is high credibility confirmation of a person's presence and insufficient lighting conditions. In low credibility scenarios, the original lighting state is maintained, reducing the phenomenon of accidental lighting activation caused by interference signals. This improves the reliability of the joint judgment of human presence sensing and lighting conditions, providing an accurate trigger judgment basis for subsequent lighting control action output.

[0137] D6. Based on the induction trigger state, determine the candidate switch action of the sub-region, and perform anti-shake delay verification on the candidate switch action based on the induction trigger state and the anti-shake holding time, to obtain the light switch output state of the sub-region in the target region.

[0138] In this embodiment of the invention, the step of determining candidate switch actions for the sub-region based on the induction trigger state, and performing anti-shake delay verification on the candidate switch actions based on the induction trigger state and the anti-shake holding duration to obtain the light switch output state of the sub-region in the target region includes:

[0139] Based on the sensing trigger state, the sub-region is mapped with action commands to obtain candidate switch actions for the sub-region;

[0140] The candidate switch actions are categorized by action direction to obtain the candidate action directions for the sub-region;

[0141] Based on the candidate action direction and the anti-shake duration, the sub-region is configured with a differentiated verification window to obtain the anti-shake verification window for the sub-region.

[0142] Within the anti-shake verification window, the state of the sensor triggering state of the sub-region is compared to obtain the state consistency verification result of the sub-region.

[0143] Based on the state consistency verification result, the candidate switch action is output confirmation to obtain the light switch output state of the sub-region in the target area.

[0144] The system reads the generated sensor trigger states in the sub-region and performs action command mapping according to the pre-established correspondence between the states and control commands. Different types of sensor trigger states are converted into operation commands that can be recognized and executed by the lighting control unit. After the mapping conversion is completed, candidate switch actions for the sub-region are obtained. The candidate switch actions represent the lighting operation that the sensor trigger state wants to perform. This action has not yet been debounced and cannot be directly output for execution.

[0145] The intention of the light operation represented by the candidate switch action is analyzed. The action direction is classified according to the result to be achieved by the light operation. The candidate switch action is distinguished as either the light-on direction or the light-off direction. After classification, the candidate action direction of the sub-region is obtained. The candidate action direction is used to reflect the trend of the light state change that the candidate switch action expects to achieve.

[0146] By combining the determined candidate motion directions and the previously calculated image stabilization duration, a differentiated configuration of the verification window is carried out. The corresponding time interval is set according to the length of the image stabilization duration corresponding to different motion directions, thereby generating the image stabilization verification window of the sub-region. The image stabilization verification window is a continuous time interval, and the length of this time interval is determined with the image stabilization duration. It is used to limit the time range that needs to be continuously monitored during the image stabilization verification process.

[0147] Within the complete time interval corresponding to the anti-shake verification window, the real-time output of the sensor trigger state of the sub-region is continuously collected and acquired. The real-time sensor trigger state collected at each time node of the window is compared with the original sensor trigger state when the candidate switch action is generated. The actual situation of state changes within the window is statistically analyzed. After the comparison of all time intervals is completed, the state consistency verification result of the sub-region is obtained. The state consistency verification result can reflect whether the trigger state remains stable and does not jump within the verification period.

[0148] The system reads the consistency verification result of the state output from the anti-shake verification window. Based on the verification result, it determines whether the candidate switch action meets the conditions for external output. When the verification result shows that the induction trigger state is consistent within the verification window, the candidate switch action is confirmed to be valid and the action is allowed to be output. When the verification result shows that the induction trigger state inside the window has changed, the output of the candidate switch action is not confirmed. After the output confirmation process, the output state of the light switch in the sub-region of the target area is finally obtained. The output state of the light switch is the final control state that can be directly driven by the lighting hardware after anti-shake filtering.

[0149] The beneficial effect is that the sensor trigger state is mapped to obtain candidate switch actions. After classifying the action direction, a differential anti-shake verification window is configured based on the anti-shake hold time. Within the verification window, the consistency of the sensor trigger state is compared, and the output confirmation of the candidate switch action is completed based on the verification result. This method can configure an appropriate verification duration for different operation directions, which can filter out invalid switch actions caused by brief jumps in the trigger signal, avoid frequent start-stop of lights caused by instantaneous fluctuations in illumination or instantaneous disturbances from human body induction, ensure the stable and reliable output state of the light switch, and further improve the actual operational stability of the overall sensor lighting control system.

[0150] like Figure 2The diagram shown is a functional block diagram of a light-adaptive sensor-controlled lamp switch system provided in an embodiment of the present invention.

[0151] The light-adaptive sensor-controlled light switch system 100 described in this invention can be installed in an electronic device. Depending on the functions implemented, the light-adaptive sensor-controlled light switch system 100 may include a multi-dimensional light field decomposition module 101, a natural light temporal analysis module 102, a strategy mapping module 103, a light satisfaction compensation calculation module 104, a human-sensory light joint decision module 105, and an anti-shake light control output module 106. The module described in this invention can also be called a unit, referring to a series of computer program segments that can be executed by the processor of an electronic device and perform a fixed function, stored in the memory of the electronic device.

[0152] In this embodiment, the functions of each module / unit are as follows:

[0153] The multidimensional light field decomposition module 101 is used to collect multidimensional light field data of sub-regions in the target area, and to decompose the light source contribution of the multidimensional light field data to obtain the natural light component spectrum and artificial light component spectrum of the sub-region.

[0154] The natural light temporal analysis module 102 is used to perform temporal evolution analysis on the change law of illumination contribution in the target area based on the natural light component spectrum, and obtain the natural light evolution characteristics of the sub-region.

[0155] The strategy mapping module 103 is used to perform feature matching on the natural light evolution features based on preset historical light-sensing response records, and to perform strategy mapping on the matching results to obtain the on / off judgment threshold and anti-shake holding time of the sub-region.

[0156] The illumination satisfaction compensation calculation module 104 is used to compare the natural light component illumination of the sub-region with the switch determination threshold item by item to obtain the initial illumination satisfaction level of the sub-region, and to compensate and correct the initial illumination satisfaction level based on the artificial light component spectrum to obtain the illumination satisfaction of the sub-region.

[0157] The human presence sensing and illumination joint decision module 105 is used to acquire the human presence sensing signal of a sub-region in the target area, and to jointly determine the human presence sensing signal and the illumination satisfaction to obtain the sensing trigger state of the sub-region.

[0158] The anti-shake light control output module 106 is used to determine the candidate switch action of the sub-region according to the sensing trigger state, and to perform anti-shake delay verification on the candidate switch action according to the sensing trigger state and the anti-shake holding time, so as to obtain the light switch output state of the sub-region in the target region.

[0159] In the several embodiments provided by this invention, it should be understood that the disclosed methods and systems can be implemented in other ways. For example, the system embodiments described above are merely illustrative; for instance, the division of modules is only a logical functional division, and other division methods may be used in actual implementation.

[0160] The modules described as separate components may or may not be physically separate. The components shown as modules may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0161] Furthermore, the functional modules in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or in the form of hardware plus software functional modules.

[0162] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.

[0163] This application embodiment can acquire and process relevant data based on artificial intelligence technology. Artificial intelligence is the theory, method, technology, and application system that uses digital computers or machines controlled by digital computers to simulate, extend, and expand human intelligence, perceive the environment, acquire knowledge, and use that knowledge to obtain optimal results.

[0164] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention.

Claims

1. A light-adaptive sensor-controlled light switch method, characterized in that, The method includes: D1. Collect multidimensional light field data of sub-regions in the target area, and decompose the light source contribution of the multidimensional light field data to obtain the natural light component spectrum and artificial light component spectrum of the sub-region. D2. Based on the natural light component spectrum, perform a time-series evolution analysis on the variation law of illumination contribution in the target region to obtain the natural light evolution characteristics of the sub-region; D3. Based on the preset historical light-sensing response record, perform feature matching on the natural light evolution characteristics, and perform strategy mapping on the matching results to obtain the on / off judgment threshold and anti-shake holding time of the sub-region. D4. Compare the natural light component illumination of the sub-region with the switch determination threshold item by item to obtain the initial illumination satisfaction level of the sub-region, and compensate and correct the initial illumination satisfaction level based on the artificial light component spectrum to obtain the illumination satisfaction of the sub-region. D5. Obtain the human presence sensing signal of a sub-region in the target area, and jointly determine the human presence sensing signal with the illumination satisfaction to obtain the sensing trigger state of the sub-region. D6. Based on the induction trigger state, determine the candidate switch action of the sub-region, and perform anti-shake delay verification on the candidate switch action based on the induction trigger state and the anti-shake holding time, to obtain the light switch output state of the sub-region in the target region.

2. The light-adaptive sensor-controlled light switch method as described in claim 1, characterized in that, The process involves collecting multidimensional light field data from sub-regions within the target area, and then performing light source contribution decomposition on the multidimensional light field data to obtain the natural light component spectrum and artificial light component spectrum of the sub-region, including: Divide the target area into spatially independent sub-regions; Spectral features are extracted from the multidimensional light field data of the sub-region to obtain the spectral response of the sub-region, which is the light response intensity of the sub-region in different wavelength ranges. Based on the response intensity of the spectral response, the light source type of the sub-region is identified to obtain the light source type of the sub-region. The light source type is used to distinguish between the natural light contribution region and the artificial light contribution region. The spectral response intensities of the natural light contribution region and the artificial light contribution region are collected and statistically analyzed to obtain the natural light contribution data and artificial light contribution data of the sub-region. The natural light contribution data and the artificial light contribution data are reconstructed to obtain the natural light component spectrum and the artificial light component spectrum of the sub-region.

3. The light-adaptive sensor-controlled light switch method as described in claim 1, characterized in that, The step involves performing a time-series evolution analysis on the variation pattern of illumination contribution in the target region based on the natural light component spectrum, to obtain the natural light evolution characteristics of the sub-region, including: The natural light component map is sliced ​​temporally to obtain a natural light component image sequence, which represents the distribution of natural light contribution of the sub-region at different times. Based on the natural light component image sequence, cross-frame difference analysis is performed on the illumination contribution value of the target region to obtain the illumination change increment sequence of the sub-region. By identifying continuous segments in the incremental sequence of illumination changes, the type of increase or decrease trend and the rate of change of natural illumination in the sub-region are obtained; Based on the increase / decrease trend type and the change rate, the illumination change pattern of the sub-region is summarized to obtain the natural light evolution characteristics of the sub-region.

4. The light-adaptive sensor-controlled light switch method as described in claim 1, characterized in that, The process of performing feature matching on the natural light evolution characteristics based on preset historical light response records, and mapping the matching results to obtain the on / off threshold and stabilization duration for the sub-region, includes: The preset historical light-sensing response records are categorized by scene to obtain the historical light-sensing feature library of the preset historical light-sensing response records; Based on the historical light sensing feature database, the natural light evolution features are compared and matched to obtain the matching confidence level of the natural light evolution features; Based on the matching confidence level, the target historical scene is located from the historical light-sensing feature library, and the control strategy associated with the target historical scene is obtained. The control strategy includes historical threshold parameters and historical image stabilization parameters. The control strategy is adaptively adjusted to obtain the switching threshold and anti-shake duration of the sub-region.

5. The illumination-adaptive sensor-controlled light switch method as described in claim 4, characterized in that, The adaptive adjustment of the control strategy to obtain the switching threshold and anti-shake duration of the sub-region includes: Based on the rate of change in the natural light evolution characteristics, the historical threshold parameters are compared to obtain the threshold offset of the sub-region; Based on the threshold offset, the historical threshold parameter is corrected to obtain the switch determination threshold of the sub-region; Based on the rate of change in the natural light evolution characteristics, the historical stabilization duration of the sub-region is allocated to obtain the stabilization retention duration of the sub-region, wherein the higher the rate of change, the longer the stabilization retention duration.

6. The light-adaptive sensor-controlled light switch method as described in claim 1, characterized in that, The step of comparing the natural light component illumination of the sub-region with the switch determination threshold item by item to obtain the initial illumination satisfaction level of the sub-region, and compensating and correcting the initial illumination satisfaction level based on the artificial light component spectrum to obtain the illumination satisfaction of the sub-region, includes: The natural light component illumination of the sub-region is compared with the switch determination threshold item by item to obtain the natural light satisfaction ratio of the sub-region. Based on the preset illumination level, the natural light satisfaction ratio is graded to obtain the initial illumination satisfaction level of the sub-region. Based on the illumination value of the artificial light component in the sub-region of the artificial light component spectrum, the artificial light contribution of the initial illumination satisfaction level is quantified to obtain the artificial light compensation coefficient of the sub-region. Based on the preset historical light-sensing response records, the proportion of natural light-driven decision frequency and artificial light-driven decision frequency in the sub-region is statistically analyzed to obtain the natural light weight coefficient and artificial light weight coefficient of the sub-region. Based on the natural light satisfaction ratio, the artificial light compensation coefficient, the natural light weighting coefficient, and the artificial light weighting coefficient, the initial illumination satisfaction level of the sub-region is cross-coordinated and corrected to obtain the illumination satisfaction of the sub-region.

7. The light-adaptive sensor-controlled light switch method as described in claim 6, characterized in that, The formula for calculating the illumination satisfaction is as follows: ； in, For the first The illumination satisfaction of each sub-region For the first The natural light in each sub-region satisfies the required proportions. For the first The natural light weighting coefficients for each sub-region For the first The artificial light compensation coefficient for each sub-region For the first The artificial light weighting coefficients for each sub-region.

8. The light-adaptive sensor-controlled light switch method as described in claim 1, characterized in that, The process of acquiring a human presence sensing signal in a sub-region of the target area and jointly determining the human presence sensing signal with the illumination satisfaction level to obtain the sensing trigger state of the sub-region includes: The human presence sensing signal of a sub-region in the target region is sampled in time to obtain the sensing signal time sequence of the sub-region; Based on the time sequence of the sensing signal, the presence of human beings in the sub-region is evaluated to obtain the confidence level of human beings in the sub-region, and the confidence level of human beings is divided into low confidence level and high confidence level. Based on the credibility of the human body presence and the light satisfaction, the sub-region is gated and triggered to obtain the sensing trigger state of the sub-region. In the sub-region with low credibility, the light on / off state of the sub-region is maintained. In the sub-region with high credibility, when the light satisfaction is lower than the preset trigger boundary, the light on state of the sub-region is triggered.

9. The light-adaptive sensor-controlled light switch method as described in claim 1, characterized in that, The process of determining candidate switch actions for the sub-region based on the induction trigger state, and performing anti-shake delay verification on the candidate switch actions based on the induction trigger state and the anti-shake holding duration, to obtain the light switch output state of the sub-region in the target region, includes: Based on the sensing trigger state, the sub-region is mapped with action commands to obtain candidate switch actions for the sub-region; The candidate switch actions are categorized by action direction to obtain the candidate action directions for the sub-region; Based on the candidate action direction and the anti-shake duration, the sub-region is configured with a differentiated verification window to obtain the anti-shake verification window for the sub-region. Within the anti-shake verification window, the state of the sensor triggering state of the sub-region is compared to obtain the state consistency verification result of the sub-region. Based on the state consistency verification result, the candidate switch action is output confirmation to obtain the light switch output state of the sub-region in the target area.

10. A light-adaptive sensor-controlled lighting system, characterized in that, For implementing the light-adaptive sensor-controlled light switch method of claim 1, the system comprises: The multidimensional light field decomposition module is used to collect multidimensional light field data of sub-regions in the target area, and to decompose the light source contribution of the multidimensional light field data to obtain the natural light component spectrum and artificial light component spectrum of the sub-region. The natural light temporal analysis module is used to perform temporal evolution analysis on the light contribution variation law of the target region based on the natural light component spectrum, and obtain the natural light evolution characteristics of the sub-region; The strategy mapping module is used to perform feature matching on the natural light evolution characteristics based on preset historical light-sensing response records, and to perform strategy mapping on the matching results to obtain the on / off judgment threshold and anti-shake holding time of the sub-region. The illumination satisfaction compensation calculation module is used to compare the natural light component illumination of the sub-region with the switch judgment threshold item by item to obtain the initial illumination satisfaction level of the sub-region, and to compensate and correct the initial illumination satisfaction level based on the artificial light component spectrum to obtain the illumination satisfaction of the sub-region. The human presence sensing and illumination joint decision module is used to acquire the human presence sensing signal of a sub-region in the target area, and to jointly determine the human presence sensing signal and the illumination satisfaction to obtain the sensing trigger state of the sub-region. The anti-shake lighting control output module is used to determine the candidate switch action of the sub-region based on the sensing trigger state, and to perform anti-shake delay verification on the candidate switch action based on the sensing trigger state and the anti-shake holding duration, so as to obtain the lighting switch output state of the sub-region in the target region.

Images