Multi-spectral light source intelligent dimming method, device and storage medium

Abstract

The present invention relates to a multi-spectral light source intelligent dimming method, device and storage medium. The method includes obtaining spectral parameters and ambient light data of the multi-spectral light source, analyzing and processing the spectral parameters based on the ambient light data to obtain corresponding target spectral information; obtaining real-time output data of the multi-spectral light source, and performing correlation processing with the target spectral information to obtain a corresponding real-time spectrum group; obtaining illumination feedback data of the multi-spectral light source, and performing spectral prediction on the target spectral information to obtain corresponding spectral adjustment information; performing dimming planning analysis on the real-time spectrum group and the spectral adjustment information to obtain a corresponding initial light source control scheme; performing spectral recognition on the illumination feedback data to obtain corresponding characteristic spectral information; and performing dimming optimization on the initial light source control scheme according to the characteristic spectral response parameters to obtain a corresponding global dimming strategy. The present invention can achieve global optimization of the system by optimizing and adjusting the characteristic spectral response parameters.

Description

Technical Field

[0001] The present invention relates to the technical field of multi-spectrum light sources, and in particular to a multi-spectrum light source intelligent dimming method, device and storage medium. Background Art

[0002] As an advanced lighting solution, multi-spectral light source technology has been widely used in industrial production, scientific research, medical diagnosis and other fields. With the increasing demand for intelligence and precise control, how to achieve intelligent dimming of multi-spectral light sources and precise spectral matching has become one of the key research topics in this field. Existing spectral dimming technologies usually only focus on the adjustment of spectral parameters in a single dimension, such as simple control of light intensity or color temperature, while ignoring the combined effects of ambient light changes, multi-spectral combination effects, and real-time spectral response characteristics. This one-sided dimming method often leads to unstable spectral output and low spectral matching accuracy, which makes it difficult to meet the actual needs of high-precision spectral application scenarios. Summary of the invention

[0003] The main purpose of the present invention is to provide a multi-spectral light source intelligent dimming method, device and storage medium, which can achieve global optimization of the system by optimizing and adjusting the characteristic spectral response parameters.

[0004] To achieve the above object, the present invention provides a multi-spectrum light source intelligent dimming method, comprising:

[0005] Acquire spectral parameters and ambient light data of a multi-spectral light source, analyze and process the spectral parameters based on the ambient light data, and obtain corresponding target spectral information;

[0006] Acquire the real-time output data of the multi-spectral light source, and associate it with the target spectrum information to obtain a corresponding real-time spectrum group;

[0007] Acquiring illumination feedback data of the multi-spectral light source, and performing spectrum prediction on the target spectrum information to obtain corresponding spectrum adjustment information;

[0008] Performing dimming planning analysis on the real-time spectrum group and the spectrum adjustment information to obtain a corresponding initial light source control solution;

[0009] Performing spectral recognition on the illumination feedback data to obtain corresponding characteristic spectral information, and performing spectral prediction on the characteristic spectral information based on the spectral adjustment information to obtain corresponding characteristic spectral response parameters;

[0010] The initial light source control scheme is dimmed and optimized according to the characteristic spectral response parameters to obtain a corresponding global dimming strategy.

[0011] Furthermore, the acquiring of spectral parameters and ambient light data of the multi-spectral light source, and analyzing and processing the spectral parameters based on the ambient light data to obtain corresponding target spectral information includes:

[0012] Performing wavelength scanning detection on the multi-spectral light source to obtain corresponding wavelength distribution data;

[0013] Quantitatively analyzing the spectral intensity of the multi-spectral light source according to the wavelength distribution data to obtain a corresponding spectral intensity characteristic matrix;

[0014] Performing spectral decomposition on the ambient light data to obtain corresponding ambient spectral component parameters;

[0015] Performing spectral interference analysis on the spectral intensity characteristic matrix according to the environmental spectral component parameters to obtain a corresponding spectral interference pattern;

[0016] Performing phase modulation processing on the spectral interference pattern to obtain corresponding spectral phase modulation parameters;

[0017] Spectrally resampling the ambient spectral component parameters according to the spectral phase modulation parameters to obtain a corresponding spectral resampling sequence;

[0018] Performing a spectral deconvolution operation on the spectral resampling sequence to obtain corresponding spectral deconvolution features;

[0019] Performing a spectral mapping transformation on the spectral phase modulation parameter according to the spectral deconvolution feature to obtain a corresponding spectral mapping relationship;

[0020] Performing spectral dynamic compensation on the spectral mapping relationship to obtain a corresponding spectral compensation factor;

[0021] Performing spectral reconstruction on the spectral mapping relationship according to the spectral compensation factor to obtain corresponding spectral reconstruction data;

[0022] The spectral reconstruction data and the spectral deconvolution features are spectrally fused to obtain the target spectral information.

[0023] Furthermore, the real-time output data of the multi-spectral light source is acquired and associated with the target spectrum information to obtain a corresponding real-time spectrum group, including:

[0024] Dynamically scanning the output spectrum of the multi-spectral light source to obtain a corresponding spectrum scanning sequence;

[0025] Calculate the spectrum distribution density according to the spectrum scanning sequence to obtain corresponding spectrum density data;

[0026] Performing spectral energy distribution analysis on the spectral density data to obtain corresponding energy distribution characteristic values;

[0027] Performing characteristic correlation calculation on the target spectral information according to the energy distribution characteristic value to obtain a corresponding spectral correlation coefficient;

[0028] Performing spectral feature weight calculation on the spectral correlation coefficient to obtain a corresponding spectral weight parameter;

[0029] Performing hierarchical analysis on the spectral density data according to the spectral weight parameter to obtain corresponding spectral hierarchy data;

[0030] Performing spectral component extraction processing on the spectral hierarchy data to obtain corresponding spectral characteristic components;

[0031] The spectral hierarchy data is optimized in real time by spectral combination according to the spectral characteristic components to obtain the real time spectral group.

[0032] Furthermore, the obtaining of the illumination feedback data of the multi-spectral light source and the spectrum prediction of the target spectrum information to obtain the corresponding spectrum adjustment information includes:

[0033] Performing time-series sampling processing on the illumination feedback data to obtain a corresponding spectrum sampling sequence;

[0034] Extracting spectral components of the target spectral information according to the spectral sampling sequence to obtain corresponding target spectral component data;

[0035] Calculating the spectral energy distribution of the target spectral component data to obtain corresponding spectral energy distribution parameters;

[0036] Performing spectral correlation analysis on the spectral sampling sequence according to the spectral energy distribution parameter to obtain a corresponding spectral correlation coefficient;

[0037] Performing spectral trend analysis on the spectral correlation coefficient to obtain corresponding spectral change parameters;

[0038] Performing spectral mapping processing on the target spectral information according to the spectral variation parameter to obtain corresponding spectral mapping data;

[0039] Performing spectrum compensation calculation on the spectrum mapping data to obtain corresponding spectrum compensation parameters;

[0040] Performing spectral calibration and fusion on the spectral mapping data according to the spectral compensation parameters to obtain corresponding fused spectral parameters;

[0041] The spectrum change parameter is predicted and calculated according to the fused spectrum parameter to obtain the spectrum adjustment information.

[0042] Furthermore, the dimming planning analysis is performed on the real-time spectrum group and the spectrum adjustment information to obtain a corresponding initial light source control scheme, including:

[0043] Performing adjustment parameter quantization processing on the spectrum adjustment information according to the real-time spectrum group to obtain corresponding spectrum adjustment parameters;

[0044] Performing interval segmentation processing on the spectrum adjustment parameter to obtain corresponding spectrum adjustment intervals;

[0045] Performing feature mapping processing on the spectrum adjustment parameters according to the spectrum adjustment interval to obtain a corresponding spectrum mapping matrix;

[0046] Performing sparse decomposition processing on the spectral mapping matrix to obtain a corresponding spectral basis vector group;

[0047] Performing orthogonal decomposition processing on the spectral basis vector group to obtain corresponding spectral orthogonal information;

[0048] A scheme is constructed according to the spectral orthogonal information and the spectral mapping matrix to obtain the initial light source control scheme.

[0049] Further, the performing spectral recognition on the illumination feedback data to obtain corresponding characteristic spectral information, and performing spectral prediction on the characteristic spectral information based on the spectral adjustment information to obtain corresponding characteristic spectral response parameters, includes:

[0050] Performing spectral segmentation processing on the illumination feedback data to obtain corresponding multiple groups of spectral subsequences;

[0051] Performing frequency domain conversion processing on the multiple groups of spectral subsequences to obtain corresponding frequency domain feature vectors;

[0052] Extracting spectrum features from the multiple groups of spectrum subsequences according to the frequency domain feature vectors to obtain corresponding spectrum feature matrices;

[0053] Performing autocorrelation analysis on the spectral feature matrix to obtain corresponding spectral correlation coefficients;

[0054] Performing cluster analysis on the spectral feature matrix according to the spectral correlation coefficient to obtain a corresponding spectral clustering vector;

[0055] Performing feature matching calculation on the spectral clustering vector to obtain corresponding feature spectral information;

[0056] Performing time-series interpolation processing on the characteristic spectrum information according to the spectrum adjustment information to obtain a corresponding spectrum change sequence;

[0057] Performing trend extrapolation analysis on the spectral change sequence to obtain a corresponding spectral prediction sequence;

[0058] Spectral parameter calculation is performed according to the spectral prediction sequence to obtain the characteristic spectral response parameter.

[0059] Furthermore, the dimming optimization of the initial light source control scheme according to the characteristic spectral response parameters to obtain a corresponding global dimming strategy includes:

[0060] Performing distribution analysis on the characteristic spectral response parameters to obtain a corresponding spectral distribution sequence;

[0061] Performing spectrum mapping analysis on the initial light source control scheme according to the spectrum distribution sequence to obtain corresponding spectrum mapping information;

[0062] Performing calibration feature analysis on the spectral mapping information to obtain a corresponding calibration parameter group;

[0063] Performing spectral optimization calculation on the calibration parameter group to obtain corresponding spectral optimization coefficients;

[0064] Performing global sequence optimization on the initial light source control scheme according to the spectrum optimization coefficient to obtain a corresponding optimized control sequence;

[0065] Performing dynamic adjustment instruction analysis on the optimized control sequence to obtain corresponding dimming control instructions;

[0066] The initial light source control scheme is globally optimized according to the dimming control instruction to obtain the global dimming strategy.

[0067] The present invention further provides a multi-spectrum light source intelligent dimming device, which is applied to any of the multi-spectrum light source intelligent dimming methods described above, comprising:

[0068] An acquisition module, the acquisition module is used to acquire spectral parameters and ambient light data of the multi-spectral light source, and analyze and process the spectral parameters based on the ambient light data to obtain corresponding target spectral information;

[0069] An analysis module, the analysis module is used to obtain the real-time output data of the multi-spectral light source, and associate it with the target spectrum information to obtain a corresponding real-time spectrum group;

[0070] An association module, the association module is used to obtain the illumination feedback data of the multi-spectral light source, and perform spectrum prediction on the target spectrum information to obtain corresponding spectrum adjustment information;

[0071] A processing module, the processing module is used to perform dimming planning analysis on the real-time spectrum group and the spectrum adjustment information to obtain a corresponding initial light source control solution;

[0072] A control module, the control module is used to perform spectral recognition on the illumination feedback data to obtain corresponding characteristic spectral information, perform spectral prediction on the characteristic spectral information based on the spectral adjustment information to obtain corresponding characteristic spectral response parameters;

[0073] An execution module is used to perform dimming optimization on the initial light source control scheme according to the characteristic spectral response parameters to obtain a corresponding global dimming strategy.

[0074] The present invention also provides a storage medium storing computer instructions, wherein the computer instructions are used to enable a computer to execute any of the above methods.

[0075] The present invention provides a multi-spectral light source intelligent dimming method, device and storage medium, which have the following beneficial effects:

[0076] By acquiring the spectral parameters of the multi-spectral light source and the ambient light data for analysis and processing, the actual spectral requirements can be evaluated more accurately, thereby improving the accuracy of spectral adjustment and providing reliable basic data support for light source control. By correlating and analyzing the real-time output data with the target spectral information, the refined management of different spectral combinations is achieved, which helps to achieve on-demand dimming and avoid spectral mismatch. Predictive analysis of the target spectral information based on the light feedback data can ensure that the system can output stably under different environmental conditions, reduce spectral deviation, and improve the overall control accuracy of the system. By comprehensively planning the real-time spectral group and spectral adjustment information, a more reasonable dimming plan is formulated, and the global optimization of the system is achieved by optimizing and adjusting the characteristic spectral response parameters, thereby effectively improving the spectral matching effect. At the same time, by considering spectral recognition and prediction, the spectral output strategy can be flexibly adjusted according to the characteristics and demand changes of different application scenarios, making the system more adaptable to diverse spectral application needs. BRIEF DESCRIPTION OF THE DRAWINGS

[0077] Figure 1 It is a flow chart of a multi-spectrum light source intelligent dimming method provided by the present invention;

[0078] Figure 2 It is a structural diagram of a multi-spectrum light source intelligent dimming device provided by the present invention.

[0079] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0080] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0081] The present invention is further described below in conjunction with the accompanying drawings and specific implementation methods.

[0082] Reference Figure 1 As shown, the present invention provides a multi-spectrum light source intelligent dimming method, comprising:

[0083] Step S1: Acquire spectral parameters of a multi-spectral light source and ambient light data, analyze and process the spectral parameters based on the ambient light data, and obtain corresponding target spectral information;

[0084] Step S2: acquiring real-time output data of the multi-spectral light source, and performing correlation processing with target spectrum information to obtain a corresponding real-time spectrum group;

[0085] Step S3: obtaining illumination feedback data of the multi-spectral light source, and performing spectrum prediction on the target spectrum information to obtain corresponding spectrum adjustment information;

[0086] Step S4: performing dimming planning analysis on the real-time spectrum group and spectrum adjustment information to obtain a corresponding initial light source control solution;

[0087] Step S5: performing spectral recognition on the illumination feedback data to obtain corresponding characteristic spectral information, and performing spectral prediction on the characteristic spectral information based on the spectral adjustment information to obtain corresponding characteristic spectral response parameters;

[0088] Step S6: Optimize the dimming of the initial light source control scheme according to the characteristic spectral response parameters to obtain a corresponding global dimming strategy.

[0089] Based on the above steps, the detailed process is as follows:

[0090] Step S1: Acquiring the spectrum parameters of the multi-spectral light source mainly includes the spectrum power distribution, spectrum bandwidth, peak wavelength and other basic parameters of each wavelength channel. Ambient light data is collected in real time through a light sensor, including ambient illumination, color temperature, color rendering index and other information.

[0091] The collected ambient light data is preprocessed, including data smoothing and outlier removal. The processed ambient light data is correlated with the spectral parameters to establish a spectrum-environment mapping relationship model. Based on this model, the optimal target spectral distribution is calculated according to the current environmental conditions. Specifically, it includes: analyzing the spectral composition of the ambient light to determine the spectral components that need to be supplemented or weakened; optimizing the spectral energy distribution in combination with the human eye visual characteristic curve; considering the special requirements of different application scenarios for spectral quality. Output the target spectral information containing the weight coefficients of each wavelength channel to provide a benchmark for subsequent dimming control.

[0092] Step S2: Collect the real-time output data of the multi-spectral light source, including the actual spectral energy distribution of each wavelength channel, through a spectrum analyzer or other equipment. Compare and analyze these real-time data with the target spectrum information, and calculate the deviation between the actual output and the target.

[0093] Based on this deviation information, the output of each wavelength channel is dynamically combined and optimized to form multiple optional real-time spectrum combination schemes. Each scheme contains specific dimming parameters for different wavelength channels and takes into account the mutual influence between channels. This process needs to consider the physical characteristics of the light source to ensure that the generated spectrum combination scheme is feasible. The output real-time spectrum group provides an optional solution for subsequent dimming planning.

[0094] Step S3: Obtain real-time illumination feedback data of the multi-spectral light source illumination area through a distributed illumination sensor network, including information such as illumination distribution and spectral energy distribution at each point in space. A spectral prediction model is established based on the target spectral information, which comprehensively considers multiple influencing factors such as the optical properties of the light source, spatial attenuation laws, and environmental factors.

[0095] The propagation characteristics of the target spectrum at different spatial locations are predicted through this model to obtain the theoretical spectrum distribution. The prediction results are compared and analyzed with the actual feedback data to generate adjustment information containing spectrum compensation parameters. These adjustment information reflects the difference between the actual lighting effect and the expected target, providing a basis for subsequent dimming optimization. The output of this step directly affects the subsequent dimming planning and optimization process.

[0096] Step S4: Based on the real-time spectrum group and spectrum adjustment information obtained previously, enter the dimming planning and analysis stage. Take various possible schemes in the real-time spectrum group as the basis for decision-making, and take the spectrum adjustment information as the specific requirement. Through multi-objective optimization analysis, calculate multiple indicators such as spectrum quality, energy efficiency, and adjustment stability. The optimization process quantitatively evaluates and weighs indicators such as high color rendering and energy consumption. At the same time, combined with hardware constraints, including dimming resolution, response time, power limit, etc. Iterative optimization calculations are performed based on the value range and constraint relationship of each parameter. After multiple rounds of iterative calculations, a better initial light source control scheme is obtained. This scheme includes specific control parameters for each wavelength channel, such as PWM duty cycle, drive current, etc. All parameters are within the range that can be achieved by hardware. This initial scheme provides a basic framework and reference basis for subsequent fine-tuning.

[0097] Step S5: Spectral analysis is performed on the acquired light feedback data to extract key features, such as the main wavelength components, energy distribution characteristic points, etc. These features constitute characteristic spectral information, which characterizes the essential characteristics of the current lighting environment. Then, based on the existing spectral adjustment information, the changing trend of the spectrum is predicted. The prediction analysis includes factors such as spatial position, time change, and environmental interference to achieve dynamic prediction of characteristic spectral information. The prediction process calculates parameters based on the spectral response law. Through predictive calculation, the spectral changes under different dimming strategies are analyzed to obtain characteristic spectral response parameters including response time, stability, fluctuation range, and other parameters. These parameters reflect the response characteristics of the light source to the dimming command, providing an important basis for the final dimming optimization.

[0098] Step S6: Use the characteristic spectral response parameters as feedback corrections to optimize and adjust the initial light source control scheme. Adopt an adaptive control method to dynamically adjust the control strategy according to the real-time response characteristics. The optimization objectives include spectral quality, energy efficiency, user comfort and other indicators. Determine the optimal balance point through quantitative analysis of these indicators. The optimization process includes reliability analysis to verify the stable operation capability of the dimming strategy under various environmental conditions. Perform sensitivity analysis and stability evaluation on various parameters. The final output global dimming strategy contains a complete dimming execution plan, including dimming curves, response timing, compensation parameters, etc. for each wavelength channel, to achieve comprehensive optimization of spectral quality, operation stability and economy.

[0099] The present invention provides a multi-spectral light source intelligent dimming method, which can more accurately evaluate the actual spectral demand by acquiring the spectral parameters and ambient light data of the multi-spectral light source for analysis and processing, thereby improving the accuracy of spectral regulation and providing reliable basic data support for light source control. By correlating and analyzing the real-time output data with the target spectral information, the refined management of different spectral combinations is achieved, which helps to achieve dimming on demand and avoid spectral mismatch. Predictive analysis of the target spectral information based on the light feedback data can ensure that the system can output stably under different environmental conditions, reduce spectral deviation, and improve the overall control accuracy of the system. By comprehensively planning the real-time spectral group and spectral regulation information, a more reasonable dimming scheme is formulated, and the global optimization of the system is achieved by optimizing and adjusting the characteristic spectral response parameters, thereby effectively improving the spectral matching effect. At the same time, by considering spectral recognition and prediction, the spectral output strategy can be flexibly adjusted according to the characteristics and demand changes of different application scenarios, so that the system is more adaptable to diverse spectral application needs.

[0100] In one embodiment, spectral parameters of a multi-spectral light source and ambient light data are obtained, and the spectral parameters are analyzed and processed based on the ambient light data to obtain corresponding target spectral information, including:

[0101] When performing wavelength scanning detection on a multi-spectral light source, a high-precision spectrometer is used to perform full spectrum scanning on the wavelength range of the multi-spectral light source. The scanning accuracy is set to 0.1nm, and the scanning range is 380nm-780nm. The light intensity data at different wavelengths is recorded by the photoelectric detector of the spectrometer to form wavelength distribution data. The scanning speed of the spectrometer is set to 10nm / s, and the sampling time for each wavelength point is 0.1s to ensure the accuracy of data collection.

[0102] Based on the acquired wavelength distribution data, the spectral intensity of the multi-spectral light source is analyzed using the spectral intensity quantization analysis algorithm, and the light intensity value of each wavelength point is mapped to a digital quantization interval of 0-255 to construct an m×n dimensional spectral intensity feature matrix, where m represents the number of wavelength sampling points and n represents the light intensity quantization level. The linear mapping method is used in the quantization process to ensure that the dynamic range of the light intensity data is reasonably allocated.

[0103] The spectral decomposition of ambient light data uses the Fourier transform method to decompose the ambient light data in the frequency domain and extract the spectral components corresponding to different frequency components. Each spectral component contains amplitude and phase information. The frequency resolution is set to 0.5Hz during the decomposition process to ensure the integrity of the ambient spectral components.

[0104] In the process of spectral interference analysis, the ambient spectral components are convolved with the spectral intensity characteristic matrix to obtain the spectral interference pattern. The convolution kernel size of the convolution operation is set to 3×3, with a step size of 1. The spatial distribution characteristics of spectral interference are identified by calculating the local correlation between the spectral components and the characteristic matrix.

[0105] Phase modulation processing uses digital phase modulation technology to modulate the phase information in the spectral interference pattern. The modulation depth range is 0-2π, the modulation step is π / 8, and the spectral phase modulation parameters are generated. The influence of phase noise is considered during the modulation process, and the phase noise suppression threshold is set to 0.1π.

[0106] The spectral resampling process performs non-uniform sampling of the ambient spectral components according to the spectral phase modulation parameters. The sampling interval is dynamically adjusted according to the changes in the phase modulation parameters to generate a spectral resampling sequence. The number of sampling points is set to twice the original data to ensure the integrity of the spectral information after resampling.

[0107] The spectral deconvolution operation uses the Wiener filter algorithm to deconvolve the spectral resampling sequence and restore the original spectral characteristics. The regularization parameter of the filter is set to 0.01, the number of iterations is 50, and the deconvolution result is optimized by the minimum mean square error criterion.

[0108] The spectral mapping transformation uses a nonlinear mapping method to establish the correspondence between the spectral phase modulation parameters and the target spectral space. The mapping function uses cubic spline interpolation, and the number of control points is set to 1 / 10 of the spectral bandwidth to ensure the smoothness of the mapping process.

[0109] Spectral dynamic compensation is based on an adaptive compensation algorithm, which calculates the error distribution in the spectral mapping relationship and generates a compensation factor. The compensation threshold is set to 5% of the mapping error, and the compensation range covers the entire spectral range.

[0110] During the spectrum reconstruction process, the spectrum compensation factor is applied to the spectrum mapping relationship, and the spectrum is corrected using an iterative reconstruction algorithm. The iterative termination condition is that the reconstruction error is less than 1% or the number of iterations reaches 100.

[0111] The spectral feature fusion adopts a weighted fusion strategy to fuse the spectral reconstruction data with the spectral deconvolution features at the feature level. The fusion weight is dynamically allocated according to the feature reliability, and the feature reliability threshold is set to 0.8. The target spectral information finally output contains complete features such as spectral energy distribution and chromaticity parameters.

[0112] This embodiment uses a high-precision spectrometer to perform a full spectrum scan of the light source, achieving a precise scanning accuracy of 0.1nm and ensuring the accuracy of the wavelength distribution data. The light intensity value is mapped to a digital quantization interval of 0-255 through a spectral intensity quantization analysis algorithm, achieving accurate quantification of the spectral intensity. The Fourier transform method is used to perform spectral decomposition of the ambient light data, combined with a frequency resolution setting of 0.5Hz, to ensure the complete extraction of the ambient spectral components. In the phase modulation process, a modulation step of π / 8 and a phase noise suppression threshold of 0.1π are set to effectively reduce the interference of phase noise. High-quality reconstruction of spectral information is achieved through the combined application of non-uniform sampling and Wiener filtering algorithms.

[0113] In one embodiment, real-time output data of a multi-spectral light source is obtained, and associated with target spectrum information to obtain a corresponding real-time spectrum group, including:

[0114] The real-time output data of the multi-spectral light source is collected and acquired by the spectrum analyzer. The sampling frequency of the spectrum analyzer is set to 1000Hz and the sampling accuracy is 0.1nm. The spectrum analyzer performs real-time dynamic scanning of the output spectrum of the multi-spectral light source, collects spectral data in the visible light range of 380-780nm, and forms a spectrum scanning sequence containing spectral wavelengths and corresponding light intensities. During the scanning process, the scanning step length of the spectrum analyzer is 1nm, and each scan collects data at 401 wavelength points.

[0115] Based on the acquired spectral scanning sequence, the spectral distribution density is calculated using the spectral density analysis algorithm. The algorithm divides the entire visible spectrum into 40 sub-intervals, each with a span of 10nm, and counts the spectral energy distribution in each interval. By calculating the ratio of the spectral energy in each interval to the total energy, the spectral density data is obtained, which reflects the concentration of spectral energy in different wavelength ranges.

[0116] Spectral energy distribution analysis uses energy feature extraction method to convert spectral density data into energy distribution characteristic values. Four characteristic parameters are set: peak wavelength position, half-peak width, energy center of gravity position and energy distribution uniformity. By numerically calculating the spectral density data, the specific values ​​of these four parameters are obtained to form the energy distribution characteristic value.

[0117] During the characteristic correlation calculation process, the energy distribution characteristic values ​​obtained are compared and analyzed with the pre-stored target spectrum information. The Pearson correlation coefficient calculation method is used to calculate the correlation between the real-time spectrum and the target spectrum in four characteristic parameters, and generate the corresponding spectrum correlation coefficient matrix. The correlation coefficient ranges from -1 to 1, and the larger the absolute value, the stronger the correlation.

[0118] The spectral feature weight calculation adopts an adaptive weight allocation algorithm, which assigns different weight values ​​to different feature parameters according to the numerical value of the spectral correlation coefficient. The calculation of the weight value takes into account the absolute value of the correlation coefficient and its changing trend. The weight value ranges from 0 to 1, and the sum of all weight values ​​is 1. The calculated weight parameters are used for subsequent spectral layer analysis.

[0119] The spectrum layered analysis process adopts a multi-level decomposition method to divide the spectrum density data into multiple levels according to the size of the weight parameter. Each level corresponds to a characteristic parameter, and the number of levels is the same as the number of characteristic parameters. The data of each level is processed independently to generate spectrum layer data, which contains the spectral energy distribution information of each level.

[0120] Spectral component extraction uses a characteristic component separation algorithm, which extracts features from spectral data at each level. The extraction process is based on a preset feature template, which includes three types of features: main wavelength component, sub-wavelength component, and background component. The specific values ​​of these three types of features at each level are calculated to form a spectral characteristic component data set.

[0121] The real-time spectrum combination optimization adopts a dynamic optimization algorithm, which recombines the spectrum data at each level according to the extracted spectral characteristic components. The optimization process considers three indicators: spectral continuity, energy balance and color reproduction. The optimal combination scheme is found through iterative calculation to generate the final real-time spectrum group. The optimization result meets the requirements of spectral continuity error less than 1%, energy balance deviation less than 3%, and color rendering index greater than 90.

[0122] This embodiment achieves high-precision collection and analysis of spectral data by adopting a multi-spectral light source intelligent dimming method. By dividing the visible spectrum into 40 sub-intervals for density analysis, the calculation accuracy of the spectral energy distribution is improved. The four-parameter feature extraction method is adopted to achieve accurate characterization of spectral features. The feature correlation calculation based on the Pearson correlation coefficient and the adaptive weight allocation algorithm ensure the accuracy and adaptability of spectral regulation. The application of multi-level decomposition method and characteristic component separation algorithm makes the spectral combination optimization process more accurate and controllable. The optimization effect finally achieved is significant, the spectral continuity error is controlled within 1%, the energy balance deviation is less than 3%, and the color rendering index exceeds 90. While ensuring the accuracy of spectral regulation, the stability and reliability of spectral output are significantly improved.

[0123] In one embodiment, the illumination feedback data of the multi-spectral light source is obtained, and the spectrum is predicted for the target spectrum information to obtain the corresponding spectrum adjustment information, including:

[0124] In the process of obtaining light feedback data, a high-precision spectral sensor is used to monitor the multi-spectral light source in real time, and the light feedback data is sampled in time according to a preset sampling period (e.g. 1ms) to generate a spectral sampling sequence containing information such as spectral intensity and wavelength distribution. The sampling sequence must satisfy the sampling theorem, and the sampling frequency must be no less than twice the highest frequency of the signal.

[0125] When extracting spectral components of the target spectral information, multi-scale frequency decomposition is performed based on the spectral sampling sequence to decompose the target spectral information into spectral components of different frequency bands to obtain the target spectral component data. During the decomposition process, appropriate basis functions are selected and the number of decomposition layers is set to 3 to ensure the integrity and accuracy of the spectral components.

[0126] In the spectral energy distribution calculation stage, the spectral energy density of the target spectral component data is estimated, the energy distribution of each band is calculated, and the parameters describing the spectral energy distribution characteristics are obtained, including indicators such as energy density function and energy concentration. In the calculation, the window width is adaptively adjusted according to the data characteristics.

[0127] In the process of spectral correlation analysis, the spectral energy distribution parameters and the spectral sampling sequence are cross-correlated, the correlation coefficients between different bands are calculated, and the correlation between spectral components is evaluated. The threshold of the correlation coefficient is set to 0.8 to determine significant correlation.

[0128] In the spectral trend analysis stage, the spectral correlation coefficient is analyzed in time series to identify the spectral change trend and extract the spectral change characteristic parameters. The smoothing coefficient α is set to 0.3 to predict the short-term spectral change trend.

[0129] In the spectral mapping process, the mapping relationship between the target spectrum and the actual spectrum is established based on the spectral change parameters, and the mapping relationship is constructed through nonlinear calculation to obtain the spectral mapping data. The construction of the mapping relationship needs to take into account the nonlinear characteristics of the spectrum to ensure the mapping accuracy.

[0130] The spectrum compensation calculation process analyzes the deviation between the spectrum mapping data and the target spectrum, calculates the required compensation amount, and obtains the spectrum compensation parameters. In the compensation calculation, the proportional coefficient Kp=0.6, the integration time Ti=0.1s, and the differential time Td=0.01s.

[0131] In the spectral calibration and fusion stage, the spectral compensation parameters are applied to the spectral mapping data to perform spectral calibration and data fusion to obtain fused spectral parameters. During the fusion process, the weight coefficients are dynamically adjusted based on the signal-to-noise ratio of each spectral component.

[0132] In the prediction calculation stage, the fused spectrum parameters are used to predict the spectrum change parameters, and the spectrum adjustment information is output by recursively estimating the spectrum change trend. During the prediction process, the setting of process parameters and measurement parameters needs to balance the prediction accuracy and system stability.

[0133] This embodiment obtains light feedback data in real time through a high-precision spectral sensor, and uses a preset sampling period for time-series sampling processing to ensure the accuracy and real-time performance of data acquisition. The target spectral information is extracted by multi-scale frequency decomposition technology, and the spectral energy distribution is calculated by combining the adaptive energy density estimation method, thereby achieving accurate identification and characterization of spectral features. Based on cross-correlation analysis and time series analysis technology, the spectral change trend is dynamically tracked, a nonlinear mapping relationship is established, and the accuracy of spectral regulation is improved. The dynamic weight fusion strategy is used for spectral calibration, and the spectral regulation information is output in conjunction with the recursive prediction algorithm, which significantly improves the dimming accuracy and response speed of the system. This method effectively solves the problems of spectral distortion and response lag in the dimming process of traditional multi-spectral light sources, and provides reliable technical support for the intelligent regulation of multi-spectral light sources.

[0134] In one embodiment, dimming planning analysis is performed on the real-time spectrum group and the spectrum adjustment information to obtain a corresponding initial light source control solution, including:

[0135] The spectrum data in the real-time spectrum group is quantified, and the spectrum adjustment information is converted into standardized spectrum adjustment parameters by setting parameters such as spectrum adjustment range, adjustment step and adjustment target value. The spectrum adjustment parameters include multi-dimensional spectrum feature quantities such as spectrum intensity parameters, color temperature parameters and color rendering parameters, which are mapped to the standard range of 0-1 through normalization.

[0136] The spectral adjustment interval is divided by piecewise linear interpolation method. Multiple control nodes are set within the value range of the spectral adjustment parameters, and each two adjacent control nodes form an adjustment interval. The spectral parameter changes in each adjustment interval are calculated by linear interpolation to ensure smooth transition of spectral adjustment. The number of control nodes is determined according to the spectral adjustment accuracy requirements, and is generally set to 3-7 nodes.

[0137] The feature mapping process maps the spectral adjustment interval to a high-dimensional feature space and constructs a spectral mapping matrix. The row vectors of the matrix represent the spectral components of different wavelengths, and the column vectors represent the spectral features of different adjustment intervals. The matrix element values ​​represent the weight coefficients of the spectral components in each adjustment interval, and the value range is 0-1. The mapping process is based on spectral similarity calculation, using cosine similarity as the metric.

[0138] The sparse decomposition of the spectral mapping matrix uses a non-negative matrix decomposition algorithm to decompose the high-dimensional matrix into a linear combination of several low-dimensional basis vectors. Each vector in the basis vector group corresponds to a type of basic spectral feature, and the vector dimension is equal to the number of spectral wavelength sampling points. Sparse decomposition retains the main feature information in the matrix and reduces the computational complexity of subsequent processing.

[0139] Orthogonal decomposition uses the Gram-Schmidt orthogonalization method to convert the spectral basis vector group into a mutually orthogonal standard orthogonal basis. The orthogonalization process eliminates the correlation between the basis vectors, so that each basis vector independently expresses different spectral features. The number of orthogonal basis vectors is determined by the number of principal components of the spectral features. Generally, 3-5 basis vectors can express the main spectral features.

[0140] The construction of the initial light source control scheme is based on the spectral orthogonal information. The target spectrum is projected and decomposed on the orthogonal basis to obtain the combination coefficients of each basis vector. The combination coefficients are multiplied by the spectrum mapping matrix to obtain the output intensity control amount of each light source. This scheme realizes the coordinated control of multiple light sources to ensure that the spectral output meets the regulation requirements. The accuracy of the control scheme is determined by the number of orthogonal basis vectors and the dimension of the spectrum mapping matrix.

[0141] This embodiment achieves intelligent and precise control of multi-spectral light sources by systematically analyzing the dimming planning of spectral groups and adjustment information. By setting standardized spectral adjustment parameters and dividing the adjustment interval by piecewise linear interpolation method, a smooth transition of spectral adjustment is ensured, avoiding visual discomfort caused by spectral jumps in traditional dimming methods. The spectral mapping matrix is ​​constructed by feature mapping and sparse decomposition, which effectively reduces the computational complexity of the system and improves the generation efficiency of dimming schemes. The spectral basis vectors are decomposed based on the Gram-Schmidt orthogonalization method, eliminating the correlation interference between basis vectors and ensuring the independent expression and precise control of each spectral feature. This scheme realizes the coordinated control of multiple light sources through orthogonal basis projection decomposition, which effectively solves the problem of mutual interference among multiple light sources in traditional dimming systems, while improving the accuracy and controllability of spectral output.

[0142] In one embodiment, spectral recognition is performed on the illumination feedback data to obtain corresponding characteristic spectral information, and spectral prediction is performed on the characteristic spectral information based on the spectral adjustment information to obtain corresponding characteristic spectral response parameters, including:

[0143] When performing spectral recognition on the illumination feedback data, spectral segmentation processing is performed on the received illumination feedback data, and the illumination feedback data is divided into multiple groups of spectral subsequences based on a preset spectral wavelength range. The preset spectral wavelength range includes the visible light band 380-780nm, the near-infrared band 780-2500nm and the ultraviolet band 100-380nm.

[0144] After obtaining multiple groups of spectral subsequences, each spectral subsequence is transformed into the frequency domain by fast Fourier transform to obtain the corresponding frequency domain feature vector. The frequency domain feature vector contains the amplitude and phase information of the spectral signal at different frequencies, reflecting the frequency distribution characteristics of the spectral signal.

[0145] Based on the obtained frequency domain feature vectors, the spectral features of multiple groups of spectral subsequences are extracted. During the extraction process, the wavelet transform method is used to decompose each spectral subsequence at different scales, extract characteristic parameters such as peak value, valley value, slope, etc., and construct a spectral feature matrix. The constructed spectral feature matrix contains the numerical representation of each spectral subsequence in different feature dimensions.

[0146] Autocorrelation analysis is performed on the obtained spectral feature matrix to calculate the correlation coefficient between each eigenvector in the matrix to form a correlation coefficient matrix. The correlation coefficient reflects the degree of association between different spectral features and provides a basis for subsequent clustering analysis.

[0147] Using the obtained spectral correlation coefficient, a clustering algorithm is used to perform cluster analysis on the characteristic vectors in the spectral feature matrix, and spectral data with similar characteristics are clustered into one category to obtain a spectral clustering vector. The clustering vector reflects the distribution law of different spectral features.

[0148] Through feature matching calculation, the spectral clustering vector is matched with the preset spectral feature template to extract the corresponding feature spectral information. The feature matching process adopts the minimum Euclidean distance criterion to ensure the accuracy of the matching results.

[0149] According to the spectral adjustment information, the characteristic spectral information is processed by cubic spline interpolation to supplement the missing values ​​in the spectral data and generate a continuous spectral change sequence. The interpolation process ensures the continuity and smoothness of the spectral data.

[0150] The trend extrapolation analysis of the spectrum change sequence is carried out, and the autoregressive moving average model is used to predict the spectrum change trend at future moments to generate a spectrum prediction sequence. The prediction process takes into account the change law and periodic characteristics of historical data.

[0151] According to the obtained spectrum prediction sequence, the spectrum parameters such as spectral energy distribution, color temperature, color rendering index, etc. are calculated, and finally the characteristic spectrum response parameters are obtained. These parameters are used to guide the subsequent light source dimming control and realize intelligent spectrum adjustment.

[0152] During the entire spectrum recognition and prediction process, the changes in spectrum parameters are monitored in real time. When the spectrum response parameters exceed the preset threshold range, the automatic correction mechanism of the spectrum parameters is triggered to ensure the accuracy and stability of spectrum adjustment. The preset threshold range is set according to the needs of different application scenarios to meet actual usage requirements.

[0153] This embodiment performs multi-dimensional spectral analysis and processing on the light feedback data, and the method realizes the accurate identification and prediction of spectral features. By combining spectral segmentation processing and frequency domain conversion, the spectral features in different wavelength ranges are effectively extracted, and the accuracy of spectral identification is enhanced. The spectral segment feature extraction method based on wavelet transform comprehensively captures the multi-scale characteristics of spectral signals, providing a reliable data basis for subsequent analysis. Through the combined application of autocorrelation analysis and cluster analysis, the intrinsic correlation between spectral features is deeply explored, and the reliability of feature identification is improved. By using cubic spline interpolation and trend extrapolation analysis, accurate prediction of spectral changes is achieved, providing an accurate reference basis for intelligent dimming. The system's integrated real-time monitoring and automatic correction mechanism ensures the stability and adaptability of spectral regulation, and can flexibly adjust spectral parameters according to the needs of different scenarios, thereby improving the practicality and reliability of the system.

[0154] In one embodiment, the initial light source control scheme is dimmed and optimized according to the characteristic spectral response parameters to obtain a corresponding global dimming strategy, including:

[0155] The distribution analysis and processing of characteristic spectral response parameters is based on the spectral response curve. The spectral response intensity values ​​in different wavelength ranges are sampled according to the preset wavelength interval to generate a spectral distribution sequence. The sequence contains wavelength points and corresponding response intensity value pairs to form discrete spectral distribution characteristics. The sampling interval is set to 1-10nm, and the number of sampling points is determined according to the spectral range, generally 300-800 sampling points.

[0156] Spectral mapping analysis maps the spectral distribution sequence to the initial light source control scheme. Through spectral response calculation, the influence weight of each control parameter on the spectral output is calculated to form a spectral mapping matrix. This matrix describes the quantitative relationship between the control parameters and the spectral output, and contains the mapping coefficients of each wavelength point.

[0157] The calibration feature analysis calibrates the spectral mapping information and calculates the calibration parameter group. The preset calibration curve is used to perform nonlinear correction on the mapping coefficient to eliminate the influence of errors and environmental factors. The calibration parameter group includes correction parameters such as gain coefficient and bias coefficient to improve the accuracy of spectral mapping.

[0158] The spectrum optimization calculation is based on the calibration parameter group, and the spectrum optimization coefficient is calculated by iterative optimization operation. The optimization goal is to minimize the deviation between the target spectrum and the actual output spectrum. The constraints include the light source output range limit, power limit, etc. The optimization coefficient reflects the adjustment direction and amplitude of each control parameter.

[0159] Global sequence optimization applies the spectral optimization coefficients to the initial control scheme to generate an optimized control sequence. The optimization process takes into account the global spectral characteristics to ensure that the spectral output of each wavelength range is coordinated and consistent. The control sequence contains timing information, which describes the change of control parameters over time.

[0160] Dynamic adjustment instruction analysis converts the optimized control sequence into specific hardware control instructions. According to the preset instruction format, the control parameters are mapped into digital control signals, and synchronization information and verification information are added. The control instructions adopt the standard communication protocol format to ensure accurate transmission and execution.

[0161] The intelligent dimming of multi-spectral light sources performs global control optimization on the initial scheme based on the dimming control instructions. The global dimming strategy comprehensively considers factors such as spectral characteristics, hardware limitations, and control accuracy to ensure stable operation while meeting application requirements. The strategy has adaptive characteristics and adjusts control parameters according to changes in the external environment.

[0162] This embodiment establishes a complete spectral control mechanism by systematically analyzing and optimizing the characteristic spectral response parameters. The spectral distribution sequence is obtained by sampling at preset wavelength intervals, which realizes the accurate quantification of spectral characteristics. Based on spectral mapping analysis, a quantitative relationship between control parameters and spectral output is established, and the system error is eliminated by combining calibration feature analysis, thereby improving the accuracy of spectral control. Iterative optimization is used to calculate the spectral optimization coefficient to achieve the optimal spectral output under constraints, thereby ensuring the stability of the dimming effect. Global sequence optimization ensures the coordination of spectral output in each wavelength range, and dynamic adjustment instruction analysis provides a standardized hardware control interface. This method establishes an adaptive global dimming strategy, which takes into account hardware limitations and control accuracy while ensuring spectral characteristics, and significantly improves the level of intelligent control of multi-spectral light sources.

[0163] Reference Figure 2 As shown, the present invention also provides a multi-spectrum light source intelligent dimming device, which is applied to any of the multi-spectrum light source intelligent dimming methods mentioned above, comprising:

[0164] An acquisition module is used to obtain spectral parameters of a multi-spectral light source and ambient light data, analyze and process the spectral parameters based on the ambient light data, and obtain corresponding target spectral information;

[0165] An analysis module is used to obtain real-time output data of the multi-spectral light source, associate it with the target spectrum information, and obtain a corresponding real-time spectrum group;

[0166] The association module is used to obtain the illumination feedback data of the multi-spectral light source, and perform spectrum prediction on the target spectrum information to obtain the corresponding spectrum adjustment information;

[0167] A processing module, which is used to perform dimming planning analysis on the real-time spectrum group and spectrum adjustment information to obtain a corresponding initial light source control solution;

[0168] A control module, the control module is used to perform spectral recognition on the illumination feedback data to obtain corresponding characteristic spectral information, perform spectral prediction on the characteristic spectral information based on the spectral adjustment information to obtain corresponding characteristic spectral response parameters;

[0169] The execution module is used to optimize the dimming of the initial light source control scheme according to the characteristic spectral response parameters to obtain the corresponding global dimming strategy.

[0170] The present invention provides a multi-spectral light source intelligent dimming device, which can more accurately evaluate the actual spectral demand by acquiring the spectral parameters and ambient light data of the multi-spectral light source for analysis and processing, thereby improving the accuracy of spectral adjustment and providing reliable basic data support for light source control. By correlating and analyzing the real-time output data with the target spectral information, refined management of different spectral combinations is achieved, which helps to achieve on-demand dimming and avoid spectral mismatch. Predictive analysis of the target spectral information based on the light feedback data can ensure that the system can output stably under different environmental conditions, reduce spectral deviation, and improve the overall control accuracy of the system. By comprehensively planning the real-time spectral group and spectral adjustment information, a more reasonable dimming scheme is formulated, and the global optimization of the system is achieved by optimizing and adjusting the characteristic spectral response parameters, thereby effectively improving the spectral matching effect. At the same time, by considering spectral recognition and prediction, the spectral output strategy can be flexibly adjusted according to the characteristics and demand changes of different application scenarios, so that the system is more adaptable to diverse spectral application needs.

[0171] The present invention also provides a storage medium storing computer instructions, wherein the computer instructions are used to enable a computer to execute any of the above methods.

[0172] It should be noted that technicians in the relevant technical field can clearly understand that for the convenience and conciseness of description, the specific working process of the system and each module described above can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

[0173] The above description is only a preferred embodiment of the present invention, and does not limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made by using the contents of the present invention specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. A multi-spectrum light source intelligent dimming method, characterized in that: include: Acquire spectral parameters and ambient light data of a multi-spectral light source, analyze and process the spectral parameters based on the ambient light data, and obtain corresponding target spectral information; Acquire the real-time output data of the multi-spectral light source, and associate it with the target spectrum information to obtain a corresponding real-time spectrum group; Acquiring illumination feedback data of the multi-spectral light source, and performing spectrum prediction on the target spectrum information to obtain corresponding spectrum adjustment information; Performing dimming planning analysis on the real-time spectrum group and the spectrum adjustment information to obtain a corresponding initial light source control solution; Performing spectral recognition on the illumination feedback data to obtain corresponding characteristic spectral information, and performing spectral prediction on the characteristic spectral information based on the spectral adjustment information to obtain corresponding characteristic spectral response parameters; Perform dimming optimization on the initial light source control scheme according to the characteristic spectral response parameters to obtain a corresponding global dimming strategy; The acquiring of spectral parameters and ambient light data of the multi-spectral light source, and analyzing and processing the spectral parameters based on the ambient light data to obtain corresponding target spectral information includes: Performing wavelength scanning detection on the multi-spectral light source to obtain corresponding wavelength distribution data; Quantitatively analyzing the spectral intensity of the multi-spectral light source according to the wavelength distribution data to obtain a corresponding spectral intensity characteristic matrix; Performing spectral decomposition on the ambient light data to obtain corresponding ambient spectral component parameters; Performing spectral interference analysis on the spectral intensity characteristic matrix according to the environmental spectral component parameters to obtain a corresponding spectral interference pattern; Performing phase modulation processing on the spectral interference pattern to obtain corresponding spectral phase modulation parameters; Spectrally resampling the ambient spectral component parameters according to the spectral phase modulation parameters to obtain a corresponding spectral resampling sequence; Performing a spectral deconvolution operation on the spectral resampling sequence to obtain corresponding spectral deconvolution features; Performing a spectral mapping transformation on the spectral phase modulation parameter according to the spectral deconvolution feature to obtain a corresponding spectral mapping relationship; Performing spectral dynamic compensation on the spectral mapping relationship to obtain a corresponding spectral compensation factor; Performing spectral reconstruction on the spectral mapping relationship according to the spectral compensation factor to obtain corresponding spectral reconstruction data; The spectral reconstruction data and the spectral deconvolution features are spectrally fused to obtain the target spectral information.

2. The multi-spectrum light source intelligent dimming method according to claim 1, characterized in that: The acquiring of the real-time output data of the multi-spectral light source and the associating processing with the target spectrum information to obtain a corresponding real-time spectrum group includes: Dynamically scanning the output spectrum of the multi-spectral light source to obtain a corresponding spectrum scanning sequence; Calculate the spectrum distribution density according to the spectrum scanning sequence to obtain corresponding spectrum density data; Performing spectral energy distribution analysis on the spectral density data to obtain corresponding energy distribution characteristic values; Performing characteristic correlation calculation on the target spectral information according to the energy distribution characteristic value to obtain a corresponding spectral correlation coefficient; Performing spectral feature weight calculation on the spectral correlation coefficient to obtain a corresponding spectral weight parameter; Performing hierarchical analysis on the spectral density data according to the spectral weight parameter to obtain corresponding spectral hierarchy data; Performing spectral component extraction processing on the spectral hierarchy data to obtain corresponding spectral characteristic components; The spectral hierarchy data is optimized in real time by spectral combination according to the spectral characteristic components to obtain the real time spectral group.

3. The multi-spectrum light source intelligent dimming method according to claim 1, characterized in that: The obtaining of the illumination feedback data of the multi-spectral light source and performing spectrum prediction on the target spectrum information to obtain corresponding spectrum adjustment information includes: Performing time-series sampling processing on the illumination feedback data to obtain a corresponding spectrum sampling sequence; Extracting spectral components of the target spectral information according to the spectral sampling sequence to obtain corresponding target spectral component data; Calculating the spectral energy distribution of the target spectral component data to obtain corresponding spectral energy distribution parameters; Performing spectral correlation analysis on the spectral sampling sequence according to the spectral energy distribution parameter to obtain a corresponding spectral correlation coefficient; Performing spectral trend analysis on the spectral correlation coefficient to obtain corresponding spectral change parameters; Performing spectral mapping processing on the target spectral information according to the spectral variation parameter to obtain corresponding spectral mapping data; Performing spectrum compensation calculation on the spectrum mapping data to obtain corresponding spectrum compensation parameters; Performing spectral calibration and fusion on the spectral mapping data according to the spectral compensation parameters to obtain corresponding fused spectral parameters; The spectrum change parameter is predicted and calculated according to the fused spectrum parameter to obtain the spectrum adjustment information.

4. The multi-spectrum light source intelligent dimming method according to claim 1, characterized in that: The performing dimming planning analysis on the real-time spectrum group and the spectrum adjustment information to obtain a corresponding initial light source control scheme includes: Performing adjustment parameter quantization processing on the spectrum adjustment information according to the real-time spectrum group to obtain corresponding spectrum adjustment parameters; Performing interval segmentation processing on the spectrum adjustment parameter to obtain corresponding spectrum adjustment intervals; Performing feature mapping processing on the spectrum adjustment parameters according to the spectrum adjustment interval to obtain a corresponding spectrum mapping matrix; Performing sparse decomposition processing on the spectral mapping matrix to obtain a corresponding spectral basis vector group; Performing orthogonal decomposition processing on the spectral basis vector group to obtain corresponding spectral orthogonal information; A scheme is constructed according to the spectral orthogonal information and the spectral mapping matrix to obtain the initial light source control scheme.

5. The multi-spectrum light source intelligent dimming method according to claim 1, characterized in that: The performing spectral identification on the illumination feedback data to obtain corresponding characteristic spectral information, and performing spectral prediction on the characteristic spectral information based on the spectral adjustment information to obtain corresponding characteristic spectral response parameters, includes: Performing spectral segmentation processing on the illumination feedback data to obtain corresponding multiple groups of spectral subsequences; Performing frequency domain conversion processing on the multiple groups of spectral subsequences to obtain corresponding frequency domain feature vectors; Extracting spectrum features from the multiple groups of spectrum subsequences according to the frequency domain feature vectors to obtain corresponding spectrum feature matrices; Performing autocorrelation analysis on the spectral feature matrix to obtain corresponding spectral correlation coefficients; Performing cluster analysis on the spectral feature matrix according to the spectral correlation coefficient to obtain a corresponding spectral clustering vector; Performing feature matching calculation on the spectral clustering vector to obtain corresponding feature spectral information; Performing time-series interpolation processing on the characteristic spectrum information according to the spectrum adjustment information to obtain a corresponding spectrum change sequence; Performing trend extrapolation analysis on the spectral change sequence to obtain a corresponding spectral prediction sequence; Spectral parameter calculation is performed according to the spectral prediction sequence to obtain the characteristic spectral response parameter.

6. The multi-spectrum light source intelligent dimming method according to claim 1, characterized in that: The dimming optimization of the initial light source control scheme according to the characteristic spectral response parameters to obtain a corresponding global dimming strategy includes: Performing distribution analysis on the characteristic spectral response parameters to obtain a corresponding spectral distribution sequence; Performing spectrum mapping analysis on the initial light source control scheme according to the spectrum distribution sequence to obtain corresponding spectrum mapping information; Performing calibration feature analysis on the spectral mapping information to obtain a corresponding calibration parameter group; Performing spectral optimization calculation on the calibration parameter group to obtain corresponding spectral optimization coefficients; Performing global sequence optimization on the initial light source control scheme according to the spectrum optimization coefficient to obtain a corresponding optimized control sequence; Performing dynamic adjustment instruction analysis on the optimized control sequence to obtain corresponding dimming control instructions; The initial light source control scheme is globally optimized according to the dimming control instruction to obtain the global dimming strategy.

7. A multi-spectrum light source intelligent dimming device, characterized in that: The multi-spectral light source intelligent dimming method according to any one of claims 1 to 6 comprises: An acquisition module, the acquisition module is used to acquire spectral parameters and ambient light data of the multi-spectral light source, and analyze and process the spectral parameters based on the ambient light data to obtain corresponding target spectral information; An analysis module, the analysis module is used to obtain the real-time output data of the multi-spectral light source, and associate it with the target spectrum information to obtain a corresponding real-time spectrum group; An association module, the association module is used to obtain the illumination feedback data of the multi-spectral light source, and perform spectrum prediction on the target spectrum information to obtain corresponding spectrum adjustment information; A processing module, the processing module is used to perform dimming planning analysis on the real-time spectrum group and the spectrum adjustment information to obtain a corresponding initial light source control solution; A control module, the control module is used to perform spectral recognition on the illumination feedback data to obtain corresponding characteristic spectral information, perform spectral prediction on the characteristic spectral information based on the spectral adjustment information to obtain corresponding characteristic spectral response parameters; An execution module, the execution module is used to perform dimming optimization on the initial light source control scheme according to the characteristic spectral response parameters to obtain a corresponding global dimming strategy; The acquiring of spectral parameters and ambient light data of the multi-spectral light source, and analyzing and processing the spectral parameters based on the ambient light data to obtain corresponding target spectral information includes: Performing wavelength scanning detection on the multi-spectral light source to obtain corresponding wavelength distribution data; Quantitatively analyzing the spectral intensity of the multi-spectral light source according to the wavelength distribution data to obtain a corresponding spectral intensity characteristic matrix; Performing spectral decomposition on the ambient light data to obtain corresponding ambient spectral component parameters; Performing spectral interference analysis on the spectral intensity characteristic matrix according to the environmental spectral component parameters to obtain a corresponding spectral interference pattern; Performing phase modulation processing on the spectral interference pattern to obtain corresponding spectral phase modulation parameters; Spectrally resampling the ambient spectral component parameters according to the spectral phase modulation parameters to obtain a corresponding spectral resampling sequence; Performing a spectral deconvolution operation on the spectral resampling sequence to obtain corresponding spectral deconvolution features; Performing a spectral mapping transformation on the spectral phase modulation parameter according to the spectral deconvolution feature to obtain a corresponding spectral mapping relationship; Performing spectral dynamic compensation on the spectral mapping relationship to obtain a corresponding spectral compensation factor; Performing spectral reconstruction on the spectral mapping relationship according to the spectral compensation factor to obtain corresponding spectral reconstruction data; The spectral reconstruction data and the spectral deconvolution features are spectrally fused to obtain the target spectral information.

8. A storage medium, characterized in that: Computer instructions are stored, and the computer instructions are used to make a computer execute the method according to any one of claims 1 to 6.

Images