Training method based on illumination optimization model

Abstract

The invention relates to the technical field of optical engineering, in particular to a training method based on an illumination optimization model. The method comprises the following steps: acquiring exhibition hall illumination data, and performing exhibition hall illumination feature extraction and exhibit area illumination feature extraction according to the exhibition hall illumination data so as to obtain exhibition hall illumination data and exhibit area illumination data; performing light source position optimization analysis according to the exhibition hall illumination data to obtain exhibition hall light source position optimization data; obtaining standard illumination data of the exhibit area; performing color temperature anomaly analysis on the exhibit area illumination data according to the exhibit area standard illumination data so as to obtain exhibit area color temperature anomaly data; performing exhibit color distortion analysis according to the exhibit area color temperature abnormal data to obtain exhibit color distortion data; and performing color temperature dynamic compensation according to the exhibit color distortion data so as to obtain exhibit area color temperature dynamic compensation data. The lighting quality and energy efficiency are improved based on the optical engineering technology.

Description

Technical Field

[0001] The present invention relates to the field of optical engineering technology, and in particular to a method for training a lighting optimization model. Background Art

[0002] Traditional methods for training lighting optimization models usually rely on a large amount of computing resources, especially when performing lighting simulation, color temperature adjustment, and light source position optimization. The amount of computing required is large. Especially in large-scale exhibition environments, the optimization process of the lighting system needs to process a large amount of input data, including light source characteristics, ambient lighting conditions, and the spatial layout of the display area. The processing and analysis of these data often require powerful computing power, which increases the computing cost and equipment investment, and the training time is long. Traditional methods rely on historical data or static data to train lighting models. However, these data usually cannot reflect changes in the real-time environment, such as changes in external lighting and the impact of audience activities on lighting. Since the lighting optimization process cannot be adjusted immediately according to environmental changes, the adaptability and practicality of the training model are insufficient. In addition, if there are dynamic changes in the lighting system and display area of ​​the exhibition hall, the real-time performance of the traditional method is poor, resulting in a lag in the optimization effect and affecting the efficiency of practical applications. Summary of the invention

[0003] Based on this, it is necessary for the present invention to provide a lighting optimization model training method to solve at least one of the above technical problems.

[0004] To achieve the above purpose, a lighting optimization model training method includes the following steps: Step S1: Acquire the exhibition hall lighting data, and extract the exhibition hall lighting features and the exhibit area lighting features according to the exhibition hall lighting data, so as to obtain the exhibition hall lighting data and the exhibit area lighting data; perform light source position optimization analysis according to the exhibition hall lighting data, so as to obtain the exhibition hall light source position optimization data; Step S2: acquiring standard lighting data of the exhibition area; performing color temperature anomaly analysis on the lighting data of the exhibition area according to the standard lighting data of the exhibition area, thereby obtaining color temperature anomaly data of the exhibition area; Step S3: performing an exhibit color distortion analysis based on the exhibit area color temperature abnormality data, thereby obtaining exhibit color distortion data; performing color temperature dynamic compensation based on the exhibit color distortion data, thereby obtaining exhibit area color temperature dynamic compensation data; Step S4: obtaining a lighting optimization model; training the lighting optimization model according to the exhibition hall light source position optimization data and the exhibition area color temperature dynamic compensation data, thereby obtaining a lighting optimization training model; Step S5: Perform lighting energy consumption evaluation according to the lighting optimization training model to obtain lighting energy consumption data; perform energy efficiency optimization according to the lighting energy consumption to obtain lighting energy efficiency optimization data, and upload it to the lighting optimization training model to perform the lighting energy efficiency optimization task.

[0005] The present invention can accurately extract the lighting characteristics of the exhibition hall and the exhibit area by collecting and analyzing the lighting data of the exhibition hall, and then optimize the position of the light source, so as to ensure that the light source arrangement of the exhibition hall is more reasonable and meets the display requirements, optimize the distribution and layout of the light source, and improve the lighting quality. Through this step, unnecessary energy consumption can be reduced, and the audience's exhibition experience can be improved at the same time. By obtaining the standard lighting data of the exhibit area and performing color temperature abnormality analysis, the color temperature abnormality problem of the exhibit area can be quickly identified and corrected, ensuring that the color performance of the exhibits is more accurate and natural, and reducing the problem of inconsistent display effects caused by color temperature fluctuations. The color temperature adjustment of the exhibit area provides more accurate color restoration for the display, effectively improves the quality of the exhibit display, and avoids visual distortion caused by unstable color temperature. Further, by performing color temperature dynamic compensation, the color temperature change of the exhibit area can be adjusted in real time during the exhibition process, so that the color presentation always remains in the best state, optimizes the color restoration of the exhibits, and improves the display effect of the exhibits. This dynamic compensation mechanism can respond according to real-time data, avoiding the disadvantage of being unable to cope with real-time changes in traditional methods. By inputting the exhibition hall light source position optimization data and the exhibit area color temperature dynamic compensation data into the lighting optimization model for training, a more accurate and efficient lighting optimization training model can be obtained. The model can be intelligently adjusted according to actual needs to optimize the lighting plan. The lighting energy consumption assessment and energy efficiency optimization functions not only help evaluate the energy consumption status of the lighting system, but also further reduce energy consumption costs through lighting energy efficiency optimization, while improving the energy efficiency of the lighting system to ensure more efficient operation of the system. This process can be continuously optimized and adjusted by uploading data to the training model to form an adaptive and intelligent lighting optimization system, which significantly improves the energy-saving effect and operating efficiency of the lighting system, and at the same time improves the system's adaptability to dynamically changing environments. These technical advantages ensure that the present invention can respond to environmental changes in real time in practical applications, provide efficient optimization solutions, and ultimately achieve the goals of energy saving, improving display effects, and improving resource utilization efficiency.

[0006] Optionally, step S1 specifically includes: Step S11: Acquire exhibition hall lighting data, and extract exhibition hall lighting features and exhibit area lighting features based on the exhibition hall lighting data, so as to obtain exhibition hall lighting data and exhibit area lighting data; Step S12: performing glare optimization analysis according to the exhibition hall lighting data, thereby obtaining exhibition hall lighting glare optimization data; Step S13: performing illumination uniformity optimization analysis according to the exhibition hall lighting data, thereby obtaining the exhibition hall illumination uniformity optimization data; Step S14: integrating the exhibition hall lighting position optimization features according to the exhibition hall lighting glare optimization data and the exhibition hall lighting uniformity optimization data, thereby obtaining the exhibition hall light source position optimization data.

[0007] By acquiring and analyzing the lighting data of the exhibition hall, the present invention can deeply understand the lighting characteristics of the exhibition hall and the exhibit area, laying the foundation for subsequent optimization work. The acquisition of the exhibition hall lighting data makes the lighting characteristics more accurate, so that the lighting optimization can be performed more effectively. By analyzing the lighting data of the exhibition hall, glare optimization can be performed, effectively reducing the glare problem caused by excessive light or improper angle, thereby providing visitors with a more comfortable exhibition experience and avoiding light interference affecting the display effect. Further, the uniform optimization analysis of the exhibition hall lighting can effectively adjust the lighting distribution inside the exhibition hall, ensure that the light in the entire exhibition area is uniform, avoid the problem of excessive brightness or darkness in local areas, and improve the display effect of the exhibits and the visual experience of the audience. The optimization of the uniformity of the exhibition hall lighting also improves the energy utilization efficiency and avoids unnecessary energy waste. Through the analysis of glare optimization and uniform optimization of lighting, the lighting environment of the exhibition hall has been comprehensively improved, the display effect of the exhibits is more vivid, and the audience experience is more comfortable. By integrating these two optimization data to optimize the position of the light source in the exhibition hall, it is ensured that the position of the light source is more reasonable and scientific. It can improve the accuracy of light source layout, avoid excessive concentration or dispersion of light sources, optimize the direction and intensity of exhibit lighting, improve the overall efficiency of the lighting system, and cope with the complexity of the exhibition hall space layout. Compared with traditional lighting optimization methods, the present invention can process more dynamic data in real time and adapt to changes in different exhibition environments, thereby greatly improving the adaptability and optimization effect of the lighting system, avoiding the shortcomings of traditional methods due to over-reliance on static data or historical data.

[0008] Optionally, step S12 is specifically: Step S121: performing light source emission simulation according to the exhibition hall lighting data, thereby obtaining light source emission simulation data; Step S122: extracting emission angle features from the light source emission simulation data, thereby obtaining light source emission angle data; Step S123: obtaining audience position data; Step S124: performing glare evaluation on the audience position data according to the light source emission angle data, thereby obtaining the exhibition hall lighting glare data; Step S125: adjusting the light source angle of the exhibition hall lighting glare data, thereby obtaining light source angle adjustment data; Step S126: adjusting the installation height of the exhibition hall lighting glare data, thereby obtaining installation height adjustment data; Step S127: performing exhibition hall lighting glare optimization integration according to the light source angle adjustment data and the installation height adjustment data, thereby obtaining exhibition hall lighting glare optimization data.

[0009] The present invention can more accurately analyze the angular characteristics of light source emission by extracting the characteristics of the light source emission angle, thereby providing data support for optimizing the lighting effect. This process can provide designers with a more scientific reference for light source layout to achieve the most optimized light source distribution. Furthermore, by obtaining audience position data and combining light source emission angle data for glare evaluation, the glare area that affects the audience's visual experience during the exhibition can be effectively identified. By obtaining the exhibition hall lighting glare data, targeted adjustments can be made to ensure that the lighting in the exhibition environment does not cause discomfort to the audience. In response to the glare problem, the emission angle and installation height of the light source are further adjusted to effectively reduce glare and improve the lighting effect. This process can ensure accurate irradiation of light by adjusting the light source angle and installation height in real time, while avoiding the problem of excessive light concentration, thereby improving the display effect of exhibits and optimizing the audience's viewing experience. By adjusting and integrating the light source angle and installation height, the glare optimization of the exhibition hall lighting is finally achieved. Compared with traditional methods, the optimization method provided by the present invention has stronger adaptability and can be adjusted in real time according to the audience's position and the actual lighting environment of the exhibition hall, ensuring the real-time and accuracy of the lighting effect, avoiding the limitations caused by excessive reliance on historical data or static data in traditional methods.

[0010] Optionally, step S124 is specifically: Calculate the relative angle of the audience position data according to the light source emission angle data, so as to obtain the light source emission-audience position angle data; Obtain glare standard threshold data; Extract light source intensity features based on exhibition hall lighting data to obtain light source intensity data; Calculate the glare intensity according to the light source intensity data and the light source emission-audience position angle data, thereby obtaining the glare intensity data; The glare intensity data is used to evaluate the exhibition hall lighting glare according to the glare standard threshold data, so as to obtain the exhibition hall lighting glare data.

[0011] The present invention obtains the light source emission-audience position angle data by accurately calculating the relative angle between the light source emission angle and the audience position, and provides reliable data support for further optimizing the glare problem in the exhibition hall lighting. By introducing the glare standard threshold data, a scientific benchmark can be effectively set for the glare evaluation to ensure that the design of the lighting system meets the optimal exhibition viewing effect. The extraction of the light source intensity feature enables the luminous intensity of the light source to be quantified and analyzed, thereby providing more detailed light source parameters for subsequent lighting optimization. On this basis, by combining the light source intensity data with the light source emission-audience position angle data to calculate the glare intensity, the glare intensity generated by the light source to the audience can be comprehensively evaluated, further guiding the optimization of the lighting layout and reducing the uncomfortable visual effect. By combining the standard threshold data to evaluate the glare intensity of the exhibition hall lighting, it is possible to accurately determine which areas have excessive glare, thereby achieving precise adjustment and ensuring that the lighting of each exhibition area meets the needs of comfortable viewing. The implementation of this series of steps makes the lighting optimization process not only more refined and intelligent, but also able to adapt to the environmental changes of the exhibition hall in real time, avoiding the problem of being unable to quickly respond to real-time data in traditional methods.

[0012] Optionally, step S13 is specifically: Step S131: Drawing a lighting distribution area map according to the exhibition hall lighting data, thereby obtaining the exhibition hall lighting distribution area map; Step S132: performing minimum lighting area identification and maximum lighting area identification on the exhibition hall lighting distribution area map, thereby obtaining the exhibition hall minimum lighting area data and maximum lighting area data; Step S133: Calculate the illumination intensity according to the minimum illumination area data of the exhibition hall, so as to obtain the illumination intensity data of the minimum illumination area of ​​the exhibition hall; Step S134: Calculate the illumination intensity according to the data of the maximum illumination area of ​​the exhibition hall, so as to obtain the illumination intensity data of the maximum illumination area of ​​the exhibition hall; Step S135: Calculate the average illumination according to the exhibition hall lighting distribution area map, so as to obtain the average illumination of the exhibition hall; Step S136: Identify the illumination intensity data of the minimum illumination area and the illumination intensity data of the maximum illumination area according to the average illumination of the exhibition hall, so as to obtain the data of the too dark illumination area and the data of the too bright illumination area; Step S137: increasing the light source density of the dark area data, thereby obtaining light source density increase data; Step S138: Optimizing the reflectivity of the exhibition space material in the over-bright area data, thereby obtaining the exhibition space material data; Step S139: Perform uniform optimization and integration of the exhibition hall lighting according to the light source density increase data and the exhibition space material data, so as to obtain the exhibition hall lighting uniform optimization data.

[0013] The present invention can accurately locate the area with weak or excessive lighting intensity by identifying the minimum lighting area and the maximum lighting area, thereby providing a target area for lighting optimization. By combining the minimum and maximum lighting area data to calculate the lighting intensity, the actual lighting intensity of each area can be quantified, further providing a scientific basis for lighting balance adjustment. The calculation of the average illumination of the exhibition hall provides a global indicator for the overall lighting effect, which helps to evaluate whether the lighting system is balanced. By identifying the areas with too dark and too bright lighting, the areas that need to be optimized can be carefully found, providing a direction for subsequent adjustments. By increasing the light source density to optimize the areas with too dark lighting, the light intensity of these areas can be effectively improved, and the overall lighting quality can be improved; and by optimizing the material reflectivity of the exhibition space to solve the problem of over-bright areas, the lighting can be better balanced to avoid energy waste. Finally, by combining the increase in light source density and the optimization of the exhibition space material, the uniform optimization of the exhibition hall lighting can be achieved, the lighting effect of the exhibition space can be improved, and the lighting intensity of each area can be ensured to meet the design requirements, thereby improving the exhibition experience and energy efficiency. The implementation of this series of steps not only solves the problem that the lighting effect cannot be adjusted in real time in the traditional method, but also effectively improves the adaptability and optimization efficiency of the lighting system.

[0014] Optionally, step S2 specifically includes: Step S21: Acquire standard lighting data of the exhibition area; Step S22: Calculating the color temperature according to the lighting data of the exhibit area, thereby obtaining the color temperature data of the exhibit area; Step S23: performing spatial abnormal color temperature analysis on the color temperature data of the exhibition area according to the standard lighting data of the exhibition area, thereby obtaining spatial abnormal color temperature data; Step S24: performing temporal abnormal color temperature analysis on the color temperature data of the exhibit area according to the standard lighting data of the exhibit area, thereby obtaining temporal abnormal color temperature data; Step S25: integrating the color temperature anomaly of the exhibit area according to the spatial anomaly color temperature data and the temporal anomaly color temperature data, thereby obtaining the color temperature anomaly data of the exhibit area.

[0015] The present invention provides accurate benchmark data for subsequent color temperature analysis by acquiring standard lighting data of the exhibition area, which helps to ensure that the lighting effect of the exhibition area meets the predetermined standard. By performing color temperature calculation on the lighting data of the exhibition area, the actual color temperature data of the exhibition area can be obtained, providing a quantitative basis for further optimization. By combining the standard lighting data of the exhibition area with the color temperature data of the exhibition area for spatial and temporal abnormal color temperature analysis, the color temperature abnormalities occurring in different spatial positions and time periods can be fully identified. The non-uniformity of the lighting effect can be accurately revealed, and important information can be provided for locating the area that needs to be adjusted. By integrating the spatial abnormal color temperature data and the temporal abnormal color temperature data, the color temperature abnormality data of the exhibition area is finally obtained, which effectively summarizes various color temperature problems and provides more targeted guidance for subsequent adjustments. Not only the accuracy and efficiency of color temperature adjustment are improved, but also the lighting system can better adapt to the dynamic changes of the exhibition environment, ensuring that each exhibition area has the best lighting effect under different time and space conditions, thereby improving the quality of exhibit display and improving the exhibition experience.

[0016] Optionally, step S23 is specifically: Step S231: Generate a reference color temperature according to the standard lighting data of the exhibit area, thereby obtaining reference color temperature data of the exhibit area; Step S232: constructing a spatial distribution diagram of the color temperature data of the exhibit area, thereby obtaining a spatial distribution diagram of the color temperature of the exhibit area; Step S233: Calculating the color temperature deviation of the color temperature space distribution diagram of the exhibit area according to the benchmark color temperature data of the exhibit area, thereby obtaining the color temperature deviation data of the exhibit area; Step S234: performing color temperature deviation area statistics according to the color temperature deviation data of the exhibit area, thereby obtaining high color temperature area data and low color temperature area data; Step S235: performing an exhibit material spectrum analysis on the high color temperature area data, thereby obtaining the exhibit material spectrum data of the high color temperature area; Step S236: evaluating the color restoration degree of exhibits in the low color temperature area data, thereby obtaining the color restoration degree data of exhibits in the low color temperature area; Step S237: Merging the spatial abnormal color temperatures according to the material spectrum data of the exhibits in the high color temperature area and the color restoration degree data of the exhibits in the low color temperature area, thereby obtaining spatial abnormal color temperature data.

[0017] The present invention can provide a clear reference standard for the lighting adjustment of the exhibition area by generating reference color temperature data according to the standard lighting data of the exhibition area, thereby ensuring that the color temperature meets expectations. Constructing a spatial distribution map of the color temperature data of the exhibition area helps to visualize the lighting effect in the display area, so that the spatial distribution of the color temperature is clear at a glance, which is convenient for discovering lighting uniformity problems. Deviation calculation of the color temperature spatial distribution map based on the reference color temperature data of the exhibition area can quantify the difference between the actual color temperature and the ideal color temperature, and provide accurate data for subsequent adjustments. By performing regional statistics on the color temperature deviation data, the lighting problem is further refined, and high color temperature and low color temperature areas are identified to provide specific directions for the adjustment work. Performing spectral analysis of exhibit material in high color temperature areas helps to evaluate the reflective characteristics of exhibit material in these areas, ensuring the optimization of the display effect of exhibits under high color temperature conditions. The evaluation of the color restoration of exhibits in low color temperature areas can ensure the color performance and display effect of exhibits in low color temperature environments, and avoid the negative impact of color temperature deviation on the visual effect of the exhibits themselves. By combining and analyzing the spectral data of exhibit materials in high color temperature areas and the color restoration data of exhibits in low color temperature areas, we can effectively identify and integrate abnormal color temperature problems in the space, optimize the lighting effects of the exhibition area, and improve the exhibition quality and viewing experience.

[0018] Optionally, step S235 is specifically: Identify the light source type for the high color temperature area data, thereby obtaining the light source type data; Extracting spectral features according to the light source type data, thereby obtaining light source type spectral data; Obtain exhibit material data; Collect reflectivity according to the exhibit material data to obtain the exhibit material reflectivity; Perform exhibition area light source identification on the high color temperature area data to obtain exhibition area light source data, and perform light source illumination simulation based on the exhibition area light source data and light source type spectrum data to obtain exhibition area light source illumination data; Analyze the light reflected by the exhibit materials according to the light source irradiation data of the exhibition area and the reflectivity of the exhibit materials, so as to obtain the reflection data of the exhibit materials; Perform reflection band statistics on the reflection data of the exhibit materials, so as to obtain the reflection band data of the exhibit materials; Interactive analysis of light source color temperature is performed based on reflection band data to obtain spectral data of exhibit material in high color temperature areas.

[0019] The present invention can accurately identify the type of light source used in the exhibition area by identifying the light source type of the high color temperature area data, and provide data support for subsequent lighting analysis and optimization. Spectral feature extraction based on light source type data can deeply understand the impact of different light sources on the lighting environment, and provide a theoretical basis for accurately adjusting the color temperature. Acquiring exhibit material data helps to analyze the visual effects of the exhibits in detail, ensuring that the performance of the material under different lighting conditions is correctly understood. By collecting the reflectivity of the exhibit material data, the reflection characteristics of various materials under different lighting conditions can be determined, providing a basis for the coordination of light source irradiation and exhibit display. The exhibition area light source identification for the high color temperature area can identify the specific light source configuration in the exhibition area, and by combining with the light source type spectral data to simulate the light source irradiation, reliable data support is provided for the optimization of light distribution and color temperature in the exhibition environment. Combining the exhibition area light source irradiation data with the exhibit material reflectivity to analyze the reflected light of the exhibit material, the light reflection effect can be effectively predicted, thereby ensuring the true presentation of the exhibit under lighting conditions. By performing reflection band statistics on the exhibit material reflection data, the specific band of the material reflection can be obtained, providing more dimensional data support for optimizing the exhibit display effect. Through interactive analysis of light source color temperature, the spectral data of exhibit materials in high color temperature areas can be obtained, thereby ensuring that the display effect and visual quality of exhibit materials in high color temperature areas are maximized, ensuring that the overall effect of the exhibition is optimal.

[0020] Optionally, step S3 specifically includes: Step S31: converting the exhibit color model according to the abnormal color temperature data of the exhibit area, thereby obtaining the exhibit color model; Step S32: obtaining reference color data; Step S33: Calculate the color difference of the exhibit color model according to the reference color data, so as to obtain color difference data; Step S34: evaluating the color distortion of the exhibit according to the color difference data, thereby obtaining the color distortion data of the exhibit; Step S35: Perform color temperature dynamic compensation according to the exhibit color distortion data, thereby obtaining exhibit area color temperature dynamic compensation data.

[0021] The present invention can map the color performance of the exhibit from one environmental condition to another environmental condition by converting the exhibit color model according to the color temperature abnormality data of the exhibit area, thereby ensuring the consistency of the exhibit color under different lighting conditions. Acquiring benchmark color data helps to establish a standard reference, so that the subsequent color difference calculation has a clear comparison benchmark, thereby more accurately evaluating the color changes of the exhibits in different lighting environments. By performing color difference calculation on the exhibit color model, the deviation of the exhibit color under different lighting conditions can be quantified to ensure that any color difference that does not meet the standard can be identified and adjusted in time. Performing an exhibit color distortion assessment based on color difference data helps to accurately identify color distortion caused by uneven lighting or other factors, and then provide an adjustment plan to enhance the visual effect of the exhibit. By performing color temperature dynamic compensation on the exhibit color distortion data, the color temperature of the exhibit area can be adjusted in real time to compensate for the visual deviation caused by color distortion, ensuring that the exhibition always maintains the best color presentation effect under different conditions, and improving the overall visual consistency and viewing experience of the exhibition.

[0022] Optionally, step S35 is specifically: Step S351: performing color cast identification according to the color distortion data of the exhibit, thereby obtaining color cast data; Step S352: performing statistics on the color cast data to obtain warm color data and cold color data; Step S353: increasing red light proportion compensation according to the warm color data, thereby obtaining red light proportion compensation data; Step S354: increasing the blue light ratio compensation according to the cold color data, thereby obtaining blue light ratio compensation data; Step S355: Performing dynamic compensation integration of the color temperature of the exhibit according to the red light ratio compensation data and the blue light ratio compensation data, thereby obtaining dynamic compensation data of the color temperature of the exhibit area.

[0023] The present invention can accurately detect the color deviation caused by abnormal color temperature by performing color cast identification on the color distortion data of the exhibit, thereby accurately identifying the color deviation of the exhibit during the display process and improving the color stability of the exhibition. Statistics on the color cast data are helpful to identify the warm or cold color areas in the exhibits, which provides a necessary basis for subsequent compensation. By adding red light ratio compensation to the warm color data, the red light component of the light source can be adjusted to eliminate the influence of the warm color, so that the color of the exhibit tends to standard white light and avoids yellowish or reddish color temperature distortion. By adding blue light ratio compensation to the cold color data, the blue light component can be enhanced, the cold color exhibit area can be adjusted, and the color of the exhibit can be more in line with the desired visual effect. By integrating the red light and blue light ratio compensation data, the color temperature of the exhibit can be effectively compensated dynamically, ensuring the stability of the color temperature and the accuracy of the color of the exhibit during the display process, thereby improving the visual experience of the audience and ensuring the real-time and accuracy of the color temperature adjustment. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] Other features, objects and advantages of the present invention will become more apparent from the detailed description of non-limiting embodiments thereof made with reference to the following drawings: Figure 1 A schematic diagram of the steps of the lighting optimization model training method of the present invention; Figure 2 Detailed step flow diagram of step S1 in the present invention; Figure 3 Detailed step flow diagram of step S2 in the present invention; 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

[0027] The following is a clear and complete description of the technical method of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by technicians in this field without creative work are within the scope of protection of the present invention.

[0028] In addition, the accompanying drawings are only schematic illustrations of the present invention and are not necessarily drawn to scale. The same reference numerals in the figures represent the same or similar parts, and their repeated description will be omitted. Some of the block diagrams shown in the accompanying drawings are functional entities and do not necessarily correspond to physically or logically independent entities. The functional entities can be implemented in software form, or implemented in one or more hardware modules or integrated circuits, or implemented in different networks and / or processor methods and / or microcontroller methods.

[0029] It should be understood that, although the terms "first", "second", etc. may be used herein to describe various units, these units should not be limited by these terms. These terms are used only to distinguish one unit from another unit. For example, without departing from the scope of the exemplary embodiments, the first unit may be referred to as the second unit, and similarly the second unit may be referred to as the first unit. The term "and / or" used herein includes any and all combinations of one or more of the listed associated items.

[0030] To achieve this, please refer to Figures 1 to 3 The present invention provides a method for training a lighting optimization model, the method comprising the following steps: Step S1: Acquire the exhibition hall lighting data, and extract the exhibition hall lighting features and the exhibit area lighting features according to the exhibition hall lighting data, so as to obtain the exhibition hall lighting data and the exhibit area lighting data; perform light source position optimization analysis according to the exhibition hall lighting data, so as to obtain the exhibition hall light source position optimization data; In this embodiment, the lighting data of the exhibition hall is obtained, including but not limited to parameters such as light source type, light intensity, lighting angle, lighting brightness and illumination. The light intensity of the light source type such as LED, halogen lamp or incandescent lamp is usually measured by a light meter in lux, and the lighting angle is obtained by the illumination angle information of the light source device. Then, these data are used to extract the lighting features of the exhibition hall, including the position and distribution of the light source and the spatial variation of the light intensity. The lighting feature extraction of the exhibit area includes measuring the light intensity distribution in the exhibit area, the distance relationship between the light source and the exhibit, and the uniformity of the light. By analyzing these parameters, the lighting data of the exhibition hall and the lighting data of the exhibit area can be obtained. When performing the optimization analysis of the light source position according to the exhibition hall lighting data, computer-aided design (CAD) software is used to simulate the lighting effects under different light source positions, and the light intensity distribution model (such as Inverse Square Law) is used to evaluate whether the light sources at different positions can evenly illuminate the exhibition hall, and the arrangement position of the light source is optimized according to the data. The optimization data of the light source position of the exhibition hall is obtained through the above steps.

[0031] Step S2: acquiring standard lighting data of the exhibition area; performing color temperature anomaly analysis on the lighting data of the exhibition area according to the standard lighting data of the exhibition area, thereby obtaining color temperature anomaly data of the exhibition area; In this embodiment, standard lighting data of the exhibition area is obtained, including standard parameters such as ideal light intensity, color temperature and lighting uniformity. The standard lighting data is generally determined based on the design requirements of the exhibition area, and the target light intensity is set to 500lux and the color temperature requirement is 3500K (white light). Next, the actual lighting data of the exhibition area is measured using a light meter and a color temperature meter to obtain the actual lighting data of the exhibition area and compare it with the standard lighting data. If there is a difference between the two, a color temperature anomaly analysis is performed. The color temperature anomaly analysis is performed by calculating the difference between the actual measured color temperature and the standard lighting color temperature. The color temperature deviation (unit: K) is usually used as an indicator. If the deviation exceeds 10K, it is considered to be a color temperature anomaly, thereby obtaining the color temperature anomaly data of the exhibit area.

[0032] Step S3: performing an exhibit color distortion analysis based on the exhibit area color temperature abnormality data, thereby obtaining exhibit color distortion data; performing color temperature dynamic compensation based on the exhibit color distortion data, thereby obtaining exhibit area color temperature dynamic compensation data; In this embodiment, the reflectivity data of the exhibit material is obtained. The reflectivity data can be measured by a spectrophotometer in percentage. For color temperature anomalies, the color changes of the exhibits under different color temperature conditions are compared, and the color difference formula (such as CIE76 or CIEDE2000) is used to calculate the degree of change in the color of the exhibits. If the color difference value exceeds the set threshold (such as 2.0), it is determined that the exhibit has color distortion. Dynamic color temperature compensation is performed based on the color distortion data of the exhibit. First, the color temperature deviation to be compensated is determined, and then the color temperature of the light source is adjusted according to the compensation algorithm to restore the original color of the exhibit. The amount of color temperature change to be compensated can be calculated based on the experimental results and the color temperature deviation, and the adjustment range is usually ±300K.

[0033] Step S4: obtaining a lighting optimization model; training the lighting optimization model according to the exhibition hall light source position optimization data and the exhibition area color temperature dynamic compensation data, thereby obtaining a lighting optimization training model; In this embodiment, a lighting optimization model is obtained. The model is constructed based on historical data, physical lighting principles, and machine learning algorithms. Historical data include light source type, light intensity, lighting uniformity of the exhibit area, and previous energy efficiency data. Physical lighting principles are used to describe the illumination range, reflectivity, refractive index, color temperature and other characteristics of the light source, and these principles are used as the basic theoretical framework of the model. Next, a suitable machine learning algorithm, such as a support vector machine (SVM) or a decision tree (DT), is selected and trained according to the input data. The input data includes exhibition hall light source position optimization data (such as the illuminance distribution and uniformity of the light source at different positions) and exhibit area color temperature dynamic compensation data (such as the adjustment amount and deviation of the light source color temperature). Each input feature, such as the type, position, illuminance, color temperature, etc. of the light source, needs to be obtained through data collection and on-site measurement. The light source type is usually obtained through equipment calibration, the illuminance is measured in real time using a light meter, and the color temperature is obtained through a color temperature meter. The model is trained using a cross-validation method to ensure its robustness and accuracy under different lighting conditions. Cross-validation reduces model overfitting by dividing the training set into multiple subsets and using different subsets as validation sets in turn. During the training process, the model parameters (such as the penalty parameter C of the support vector machine, the kernel function type, the tree depth of the decision tree, etc.) are adjusted for tuning, and optimization methods such as grid search or random search are used to finally obtain an optimized lighting optimization training model. The optimization steps of the model include minimizing the loss function, adjusting the error, etc., to ensure that it can handle dynamically changing lighting environments and complex lighting conditions.

[0034] Step S5: Perform lighting energy consumption evaluation according to the lighting optimization training model to obtain lighting energy consumption data; perform energy efficiency optimization according to the lighting energy consumption to obtain lighting energy efficiency optimization data, and upload it to the lighting optimization training model to perform the lighting energy efficiency optimization task.

[0035] In this embodiment, the training model is input based on actual light source data, which includes the power of each light source (in watts W), the operating time (in hours h), and the size of the lighting area (in square meters m). 2 ). The power of each light source is obtained through the specifications of the equipment or on-site measurements, which is usually clearly marked in the technical manual of the lamp, or measured using an electric meter. The operating time of the light source can be obtained through a real-time monitoring system, which usually records the switching time of each lamp. The size of the lighting area is obtained based on the floor plan of the exhibition area and actual measurement data. After entering this data, the training model will calculate the energy consumption estimate of each type of light source under the specified conditions, in kilowatt-hours (kWh). The energy consumption calculation formula is: Where P is the light source power (W) and t is the operating time (h). After obtaining the energy consumption data, energy efficiency optimization is performed. The energy efficiency optimization step uses optimization algorithms such as linear programming, particle swarm optimization or genetic algorithm, etc. The goal is to reduce energy consumption by adjusting the working state of the light source. By controlling the on and off state of the light source (for example, turning off unnecessary light sources) and adjusting the brightness (for example, automatically adjusting the brightness of the light source to adapt to the actual needs of the exhibition area), energy consumption can be minimized while maintaining the lighting effect. During the adjustment process, specific energy efficiency goals can be set, such as ensuring that the lighting intensity is within the standard range while reducing energy consumption to a specific level (for example, reducing it by 10%). After the optimization is completed, energy efficiency optimization data is obtained, including the adjusted light source configuration, energy consumption data, etc., and these data are uploaded to the lighting optimization training model for the next round of optimization tasks. The uploaded data is used for real-time updating of the model, so that it can adapt to different lighting environment changes after each optimization, and ultimately ensure the optimal energy efficiency of each lighting cycle.

[0036] Optionally, step S1 specifically includes: Step S11: Acquire exhibition hall lighting data, and extract exhibition hall lighting features and exhibit area lighting features based on the exhibition hall lighting data, so as to obtain exhibition hall lighting data and exhibit area lighting data; In this embodiment, data of all light sources in the exhibition hall are collected, including parameters such as power, color temperature, and illumination of each light source. The power of the light source is obtained by on-site measurement or by checking the equipment specification, and the unit is watt (W). The illumination data is obtained by measuring at multiple points in the exhibition hall using a illuminance meter, and the unit is lux (lx). The exhibition hall lighting data includes two parts: exhibition hall lighting and exhibit area lighting. The exhibition hall lighting data includes the distribution, power, and illumination distribution of light sources in the entire exhibition hall. The exhibit area lighting data includes the light source configuration and illumination level of each exhibit area, ensuring that sufficient and uniform lighting can be provided for each exhibit area. For the illumination data of each area, it is necessary to ensure that a fixed measurement time period is followed during collection to eliminate the influence of human factors and ensure the accuracy of the data.

[0037] Step S12: performing glare optimization analysis according to the exhibition hall lighting data, thereby obtaining exhibition hall lighting glare optimization data; In this embodiment, the illumination, position and type of light source (such as LED, fluorescent lamp, etc.) of each light source in the exhibition hall are obtained. The illumination distribution of each light source is analyzed through the glare evaluation formula to ensure that there is no area of ​​excessive direct illumination, which causes visual discomfort. In the standard glare evaluation method, a unified glare rating index (UGR) is used for analysis. When calculating the UGR value, the UGR value of each area is calculated based on parameters such as the power of the light source, the illumination distribution, and the reflectivity of the illuminated area. Usually, the UGR value should be controlled below 19. For areas exceeding 19, the design is optimized by adjusting the power and position of the light source or using appropriate shading devices to reduce the impact of glare. The range and degree of adjustment need to be clearly specified to ensure that the final light source distribution does not produce unnecessary glare.

[0038] Step S13: performing illumination uniformity optimization analysis according to the exhibition hall lighting data, thereby obtaining the exhibition hall illumination uniformity optimization data; In this embodiment, the illumination data of each point in the exhibition hall is used to analyze the illumination uniformity of each area of ​​the exhibition hall. Illumination uniformity is evaluated by calculating the unevenness of illumination distribution (usually the ratio of the maximum to the minimum light intensity). According to the illumination data, a standard uniformity threshold is set (such as the ratio of the maximum illumination to the minimum illumination does not exceed 1.5). If this standard is exceeded, the light source layout is adjusted. At this time, the positions of different light sources need to be optimized according to the illumination distribution diagram to avoid overly concentrated lighting areas. The adjustment of the light source position is based on the illumination data, and the angles and distances of each light source are gradually adjusted to ensure that the illumination distribution in the entire exhibition hall is more uniform and there is no obvious difference in illumination in each area.

[0039] Step S14: integrating the exhibition hall lighting position optimization features according to the exhibition hall lighting glare optimization data and the exhibition hall lighting uniformity optimization data, thereby obtaining the exhibition hall light source position optimization data.

[0040] In this embodiment, the two data need to be integrated through the weight coefficient, and the standard is set, for example, glare optimization accounts for 40% and lighting uniformity optimization accounts for 60%. After integration, the optimization algorithm (such as genetic algorithm or particle swarm optimization algorithm) is used to optimize the light source position of the exhibition hall. The optimization algorithm will calculate the optimal light source position based on the illumination data of each light source, the glare optimization results and the lighting uniformity analysis, and output the final exhibition hall light source position optimization data on this basis. The data includes the new position parameters of each light source and the corresponding optimization measures to ensure that the optimized light source layout not only meets the illumination uniformity requirements, but also avoids the generation of strong glare.

[0041] Optionally, step S12 is specifically: Step S121: performing light source emission simulation according to the exhibition hall lighting data, thereby obtaining light source emission simulation data; In this embodiment, the physical parameters of all light sources in the exhibition hall are obtained, including the power, type (such as LED or fluorescent lamp), color temperature, illumination, etc. of the light source. Using the specifications and measurement data of the light source, the luminous simulation is performed through optical simulation software (such as Radiance or LightTools). When simulating the light emission of the light source, the lighting data is input into the simulation software to simulate the luminous characteristics of the light source and calculate the light distribution of each light source in the exhibition hall. During the simulation process, modeling is performed according to the structural layout and reflectivity data of the exhibition hall to ensure that the simulation results are close to the actual lighting effect. In this process, the actual lighting coverage of each light source is obtained by setting parameters such as the reflectivity of ambient light and the radiation intensity of the light source. The simulation data includes the luminous intensity distribution and illumination change of each light source.

[0042] Step S122: extracting emission angle features from the light source emission simulation data, thereby obtaining light source emission angle data; In this embodiment, the light source emission angle information from the light source luminous simulation data is extracted. The ray tracing technology is used to analyze the angular distribution of the light emitted by each light source in space. The emission angle data is usually based on the half-viewing angle and full-viewing angle of the light source to determine the directional range of the light emitted by the light source. This process uses simulation software to subdivide the emitted light of each light source and calculate the emission angle range of the light source. It is usually segmented according to the beam angle of the light source, and the common angle range is 30°, 60°, 90°, etc. During the extraction process, a threshold is set to determine the effective emission range of the light source, such as only considering the effective light source radiation within the range of ±45°. The emission angle data finally obtained includes the emission angle range and light intensity distribution of each light source.

[0043] Step S123: obtaining audience position data; In this embodiment, the location of the audience in the exhibition hall is recorded. A laser rangefinder or handheld device is used to accurately measure the size of the exhibition hall and obtain the spatial coordinates of each area in the exhibition hall. A thermal imaging sensor or an infrared sensor is used to monitor the real-time location of the visiting audience in the main aisles and exhibits of the exhibition hall. The audience location data will include the spatial coordinates of each audience (such as X, Y, and Z coordinates) and mark the area where the audience is located. This data is updated in real time through a wireless positioning system (such as RFID) to ensure that the location of each audience is always recorded. The acquired data will be used for subsequent analysis to evaluate the lighting experience of audiences in different locations in the exhibition.

[0044] Step S124: performing glare evaluation on the audience position data according to the light source emission angle data, thereby obtaining the exhibition hall lighting glare data; In this embodiment, the angle between the sight line direction of each audience member in the exhibition hall and each light source is calculated by combining the emission angle data of the light source and the position data of the audience. Based on the angle, it is evaluated whether each audience member's sight line is directly aimed at the light source. If so, glare is caused. By calculating the relative angle between the emission angle of each light source and the audience's position (usually the angle between the irradiation direction of the light source and the audience's sight line direction), and judging according to the glare evaluation formula (such as UGR value or maximum brightness value). When evaluating glare, a standard is set. For example, when the UGR value is greater than 19, it is considered that there is a serious glare problem at this position. Based on the relationship between the position of each audience member and the light source, a specific glare data table is generated to record whether each audience member is affected by glare and the degree of impact.

[0045] Step S125: adjusting the light source angle of the exhibition hall lighting glare data, thereby obtaining light source angle adjustment data; In this embodiment, the areas or audiences affected by glare are identified based on the glare data. For these areas, the emission angle of the light source is adjusted to prevent the direct light source from irradiating the audience's eyes. For example, if the emission angle of a light source is too large, resulting in a too wide illumination area, the illumination range can be reduced by adjusting the inclination angle or rotation angle of the light source to reduce the glare effect. During adjustment, a mechanical adjustment device or an automatic dimming device is used to change the angle of the light source. The angle is usually adjusted in the range of 0° to 45°, and is adjusted according to the type and brightness of the light source to achieve the effect of lighting optimization. The adjusted light source angle data will be used in subsequent optimization processes.

[0046] Step S126: adjusting the installation height of the exhibition hall lighting glare data, thereby obtaining installation height adjustment data; In this embodiment, the relationship between the installation height of the light source in the exhibition hall and the impact of glare on the audience is analyzed based on the glare data. If the position of some light sources is too low or too high, the light will directly hit the audience's eyes, causing discomfort. In order to reduce glare, the installation height of the light source needs to be adjusted according to the relationship between the installation height of the light source and its irradiation angle. When adjusting, the position of the light source is raised or lowered to ensure that the irradiation angle of the light source does not produce excessive direct irradiation to the audience. For example, the installation height of the light source is increased to between 2.5 meters and 3.5 meters to reduce the direct irradiation of the light source to low areas. The adjusted light source installation height data will be used in the optimization process to ensure that the light source configuration adapts to the actual environment of the exhibition hall.

[0047] Step S127: performing exhibition hall lighting glare optimization integration according to the light source angle adjustment data and the installation height adjustment data, thereby obtaining exhibition hall lighting glare optimization data.

[0048] In this embodiment, the angle and installation height of the light source are comprehensively considered through the optimization algorithm to perform global optimization. During the integration process, a multi-objective optimization method (such as a genetic algorithm or a simulated annealing algorithm) is used to calculate the best combination of the light source angle and installation height to ensure that the lighting uniformity and aesthetic requirements are met while reducing glare. The angle and installation height adjustment data of each light source will be used to generate the final light source configuration plan. The final output of the exhibition hall lighting glare optimization data will include the adjustment angle, installation height and optimized lighting distribution of each light source to ensure the maximum lighting effect in the exhibition hall.

[0049] Optionally, step S124 is specifically: Calculate the relative angle of the audience position data according to the light source emission angle data, so as to obtain the light source emission-audience position angle data; In this embodiment, the emission angle data of the light source is obtained by simulating the light emission of the light source, which is usually the angle of the light beam radiated by the light source, defined as the angle between the light and the center line of the light source. The audience position data is usually obtained through a wireless sensor (such as RFID) or a laser positioning system, which records the spatial coordinates of each audience in the exhibition hall (such as X, Y, Z coordinates). According to the coordinates of each audience member and the coordinates of the light source, the relative position vector between the audience and the light source is calculated. Further, by calculating the angle between the light source emission angle and the audience position, the light source emission-audience position angle data is obtained. This process uses the vector calculation formula: Where A and B are the vectors of the light source emission direction and the viewer position, respectively. The obtained light source emission-viewer position angle data is used for subsequent glare intensity calculation.

[0050] Obtain glare standard threshold data; In this embodiment, the glare standard threshold data is obtained by referring to international standards (such as CIE 117 or UGR standards). The standard threshold is usually set according to different environments, light source types, audience viewing angles and other factors. The common setting standard is that when the UGR value is greater than 19, it is considered that significant glare will be generated in the line of sight. To ensure the accuracy of implementation, select standards that are suitable for the exhibition hall environment. Determine the appropriate threshold range through environmental assessment and exhibition hall layout design. The specific threshold is adjusted according to parameters such as the light source type, installation method, and reflectivity of the exhibition hall. The threshold data can be calculated based on historical data or industry experience. In this step, the UGR value (Unified Glare Rating) is used as the standard, and the UGR value threshold is set to 19 as the dividing line between acceptable and unacceptable glare intensities.

[0051] Extract light source intensity features based on exhibition hall lighting data to obtain light source intensity data; In this embodiment, the light source intensity feature extraction obtains preliminary light intensity information through the specifications and input power of the light source. Then, the photometer or illuminance meter is used to measure at multiple locations in the exhibition hall to obtain the actual illumination data of each location. According to the spatial distribution of light, optical simulation software (such as Radiance or Photopia) can be used to predict the illumination intensity of the light source. The light source intensity data is calculated based on the measured illumination data and the actual power characteristics of the light source, and the commonly used unit is lux (lx). Important parameters in this process include the power, color temperature, luminous flux, etc. of the light source, and it is necessary to ensure that the instruments used for measurement are accurately calibrated. The light source intensity data provides the basis for subsequent glare intensity calculations.

[0052] Calculate the glare intensity according to the light source intensity data and the light source emission-audience position angle data, thereby obtaining the glare intensity data; In this embodiment, the distance between each viewer and the light source is calculated, and the illuminance value at that position is obtained by combining the light intensity data of the light source. Then, according to the relative angle data of the viewer, the illuminance intensity value is adjusted using the emission angle of the light source and the angle between the viewer's position to simulate the formation of glare. The glare intensity calculation uses a glare evaluation formula, such as: Among them, I is the light intensity of the light source, θ is the angle between the light source emission angle and the audience position, and d is the distance between the audience and the light source. The result calculated by this formula is corrected according to the actual exhibition hall environment, and finally the glare intensity data of each position is obtained. The value is generally expressed in units of lumen (lm) or lux (lx). These data serve as the basis for subsequent glare evaluation.

[0053] The glare intensity data is used to evaluate the exhibition hall lighting glare according to the glare standard threshold data, so as to obtain the exhibition hall lighting glare data.

[0054] In this embodiment, each audience position within the evaluation range is defined. If the glare intensity at the position exceeds the set glare standard threshold (such as a UGR value of 19), it is considered that there is inappropriate glare at the position. For all audience positions, screening is performed by comparing the glare intensity data with the standard threshold one by one. Based on the evaluation results, a glare data report for the exhibition hall lighting is generated, in which the glare status (qualified or unqualified) and intensity value of each position will be recorded. The data of all positions will be summarized and the glare evaluation results of the overall exhibition hall lighting will be given. During the evaluation process, preset glare standards, such as UGR and glare intensity critical values, are used to ensure that all affected areas can be detected and adjusted in real time.

[0055] Optionally, step S13 is specifically: Step S131: Drawing a lighting distribution area map according to the exhibition hall lighting data, thereby obtaining the exhibition hall lighting distribution area map; In this embodiment, the lighting data model of the exhibition hall is established by obtaining information such as the light intensity, installation location and emission angle of each light source. The illumination range of each light source is determined by simulation or measured data, and a lighting distribution area map is drawn in combination with the specific layout information of the exhibition hall (such as room area, wall reflectivity, obstacle location, etc.). This figure reflects the illuminance distribution at each position in the exhibition hall. The lighting distribution is calculated using a illuminance meter or based on optical simulation tools (such as Radiance, DIALux). The illuminance value of each point in the figure is obtained by measurement or simulation, and the unit is lux (lx). The lighting distribution area map shows the light intensity of each area in the exhibition hall through color gradients or numerical values. This figure serves as the basis for subsequent analysis.

[0056] Step S132: performing minimum lighting area identification and maximum lighting area identification on the exhibition hall lighting distribution area map, thereby obtaining the exhibition hall minimum lighting area data and maximum lighting area data; In this embodiment, by setting a predetermined illumination threshold (such as 300lx), the illumination data is divided into regions. First, based on the lighting distribution area map, the area with illumination lower than the set threshold is identified and calibrated as the minimum illumination area. By analyzing the area with illumination lower than the threshold, the spatial range and corresponding coordinate data of the minimum illumination area are obtained. Secondly, the area with illumination higher than another predetermined threshold (such as 1500lx) is identified and calibrated as the maximum illumination area. By analyzing the area with illumination higher than the threshold, the spatial range and coordinate data of the maximum illumination area are obtained. Finally, the minimum illumination area data and the maximum illumination area data of the exhibition hall are output, and their positions, areas, and corresponding illumination values ​​are recorded respectively.

[0057] Step S133: Calculate the illumination intensity according to the minimum illumination area data of the exhibition hall, so as to obtain the illumination intensity data of the minimum illumination area of ​​the exhibition hall; In this embodiment, the overall illumination data of the area is obtained by weighted averaging the illumination value of each point in the area. When weighted averaging, the calculation is performed based on the actual illumination value (lux unit) of each point, and combined with factors such as the actual position and area of ​​the point. Then, combined with the light source position and light source intensity of the area, the photometric formula (for example, the inverse square law) is used to calculate the illumination intensity of each position in the minimum illumination area, and the formula is as follows: Among them, I is the light intensity of the light source, and d is the distance from the light source to the measurement point. Through this calculation, the light intensity data of the minimum lighting area of ​​the exhibition hall is obtained, and the unit is lux (lx).

[0058] Step S134: Calculate the illumination intensity according to the data of the maximum illumination area of ​​the exhibition hall, so as to obtain the illumination intensity data of the maximum illumination area of ​​the exhibition hall; In this embodiment, the illumination intensity of each point in the area is calculated using the illumination value of each point in the area and the light intensity of the light source. According to the illumination data of each point, combined with the actual position and intensity of the light source, the intensity is calculated using the same inverse square law formula. Considering that the maximum illumination area is usually a large area and there are multiple light sources illuminating together, the illumination of each point needs to be accumulated and calculated. Finally, the overall illumination intensity data of the maximum illumination area is calculated.

[0059] Step S135: Calculate the average illumination according to the exhibition hall lighting distribution area map, so as to obtain the average illumination of the exhibition hall; In this embodiment, the illumination data of each area point is obtained from the exhibition hall lighting distribution area map. The illumination data is obtained by measuring or simulating at different locations in the exhibition hall, and the illumination value of each location is usually in lux (lx). Next, the illumination values ​​of all area points are added up to obtain the total illumination. The total area of ​​the exhibition hall is calculated, which usually includes the total area of ​​all areas in the exhibition hall. After obtaining the total area, the total illumination is divided by the total area to obtain the average illumination of the exhibition hall. This value represents the overall lighting level in the exhibition hall and is the key data used as a benchmark in subsequent analysis to help identify areas with too dark or too bright lighting.

[0060] Step S136: Identify the illumination intensity data of the minimum illumination area and the illumination intensity data of the maximum illumination area according to the average illumination of the exhibition hall, so as to obtain the data of the too dark illumination area and the data of the too bright illumination area; In this embodiment, the average illumination is used as a reference, and the illumination intensity data of the minimum illumination area is compared with the reference. If the illumination intensity of some areas is lower than a certain threshold value of the reference illumination (such as lower than 70%), it is determined to be an area with too dark illumination. For the illumination intensity data of the maximum illumination area, if the illumination intensity of some areas is higher than a certain threshold value of the reference illumination (such as more than 130%), it is determined to be an area with too bright illumination. In this way, the too dark area and the too bright area are identified, and finally the data of the too dark area and the data of the too bright area are obtained, and their location, range, illumination value and other information are recorded.

[0061] Step S137: increasing the light source density of the dark area data, thereby obtaining light source density increase data; In this embodiment, the area of ​​the dark lighting area and its illumination data are analyzed to determine the degree of insufficient illumination in the area. Then, based on the area of ​​the area and the number of existing light sources, the number of light sources that need to be increased is calculated. The light source density increment calculation formula is as follows: Among them, the illuminance difference is the difference between the required illuminance and the actual illuminance of the area, and the area is the area of ​​the area where the lighting is too dark. According to the calculated light source density increment, the light source position is reasonably distributed, and the number and layout of light sources are optimized to obtain the light source density increase data.

[0062] Step S138: Optimizing the reflectivity of the exhibition space material in the over-bright area data, thereby obtaining the exhibition space material data; In this embodiment, the reflectivity of the materials such as the wall, floor, and ceiling in each area of ​​the exhibition space is evaluated, and the reflectivity data is obtained through field measurement or reference standards. The materials with higher reflectivity are optimized, such as paint and floor materials, to reduce the reflectivity of light, thereby reducing the light intensity in the over-bright areas. The optimization process includes selecting coatings or materials with low reflectivity, adjusting the display position of exhibits, changing the angle of illumination of the light source, etc. Ultimately, the optimized reflectivity data of the exhibition space materials provides a basis for improving the uniformity of lighting.

[0063] Step S139: Perform uniform optimization and integration of the exhibition hall lighting according to the light source density increase data and the exhibition space material data, so as to obtain the exhibition hall lighting uniform optimization data.

[0064] In this embodiment, combined with the light source density increase data, the number and position of light sources are adjusted to ensure that the light intensity of all areas in the exhibition hall is evenly distributed. Then, based on the exhibition space material data, the material of the area with high reflectivity in the exhibition hall space is optimized to reduce the reflection effect of the light source. Finally, taking into account the optimization of the light source layout, density and exhibition space material, the light uniformity optimization integration is performed by adjusting the light source intensity, angle, and the material of the exhibition space, and finally the exhibition hall lighting uniformity optimization data is obtained to ensure that the lighting uniformity in the exhibition hall reaches the expected goal.

[0065] Optionally, step S2 specifically includes: Step S21: Acquire standard lighting data of the exhibition area; In this embodiment, standard lighting data is obtained for each lighting point. These data are usually determined by the set lighting scheme, including brightness, color temperature and light source type. Standard lighting data should be measured or simulated based on the actual needs of the exhibition area. In order to ensure the accuracy of the data, an illuminance meter and a color temperature meter are used to obtain the light intensity and color temperature of the lighting point respectively. Standard lighting data also includes information such as technical parameters of lighting equipment, rated output power and spectral distribution of light sources. All data should be calibrated into standard units, such as lux (lx) and Kelvin (K), and comprehensively recorded in combination with the specific layout of the exhibition area.

[0066] Step S22: Calculating the color temperature according to the lighting data of the exhibit area, thereby obtaining the color temperature data of the exhibit area; In this embodiment, the color temperature data of each lighting point is obtained. A color thermometer is used to measure each lighting point to obtain the corresponding color temperature value. The color temperature is calculated based on the spectral characteristics emitted by the light source. The color temperature value of each lighting point is obtained by analyzing the relationship between the main wavelength of the spectrum and the color temperature. The standard lighting data includes the illumination data and the corresponding color temperature data of each point. These data will be used as a basis to further correct and optimize the color temperature through the color temperature calculation formula. During the calculation process, the overall color temperature distribution of the exhibit area is calculated based on the specific standard lighting data and the color temperature range of different light sources.

[0067] Step S23: performing spatial abnormal color temperature analysis on the color temperature data of the exhibition area according to the standard lighting data of the exhibition area, thereby obtaining spatial abnormal color temperature data; In this embodiment, the area is divided into multiple measurement points according to the layout of the exhibit area, and the color temperature data of each point is collected and compared with the standard lighting data. If the color temperature data of a certain area deviates from the standard range, it is considered that there is a spatial color temperature anomaly in the area. In specific implementation, a color temperature standard range is set, such as between 3000K and 5000K. If the color temperature of a certain point exceeds this range, it is considered to be abnormal. By comparing the color temperature data of all measurement points, recording and marking the areas with abnormal color temperature, it is ensured that all spatial anomalies in the exhibit area are identified.

[0068] Step S24: performing temporal abnormal color temperature analysis on the color temperature data of the exhibit area according to the standard lighting data of the exhibit area, thereby obtaining temporal abnormal color temperature data; In this embodiment, the color temperature data of each lighting point in the exhibit area at different time nodes are collected for time series analysis. The color temperature data of each lighting point is collected and recorded according to the preset time interval. It is compared with the standard lighting data to check the color temperature changes in a certain time period. If the color temperature of a certain period exceeds the normal range (for example, exceeds the maximum or minimum value in the standard lighting data), it is determined that there is a color temperature abnormality in this period. When analyzing, it is necessary to set a time threshold and compare it, identify the period that exceeds the threshold, and then identify the color temperature abnormality in time.

[0069] Step S25: integrating the color temperature anomaly of the exhibit area according to the spatial anomaly color temperature data and the temporal anomaly color temperature data, thereby obtaining the color temperature anomaly data of the exhibit area.

[0070] In this embodiment, the spatial abnormal color temperature data obtained in the spatial abnormal color temperature analysis and the temporal abnormal color temperature analysis are compared and integrated with the temporal abnormal color temperature data. The spatial abnormal color temperature data are used to determine all areas in the exhibit area where the color temperature deviates from the standard range. These spatial abnormal areas are obtained by comparing with the set color temperature standard range. For example, assuming that the standard color temperature range is 3000K to 5000K, if the color temperature values ​​of some areas exceed the range (such as exceeding 5000K or being lower than 3000K), these areas are considered to have spatial abnormalities. Temporal analysis is performed on these spatial abnormal areas to check the color temperature changes of these areas in different time periods. For example, if the color temperature of a certain spatial area is high or low in a specific time period, it can be considered that the color temperature abnormality of the area has a temporal variation feature. In this process, the temporal abnormal color temperature data is combined with the spatial abnormality data to identify those areas where both spatial abnormalities and temporal abnormalities exist in a specific time period. The color temperature threshold is set to further classify these areas. Assuming that the set time anomaly threshold is 5% (i.e., the color temperature fluctuation is allowed to be no more than 5%), if the color temperature of a certain spatial abnormal area fluctuates by more than this threshold within a certain period of time, it is considered that the color temperature anomaly in this area has not only spatial deviations, but also temporal fluctuations. Based on these data, classification and integration are performed to ultimately determine which areas of color temperature anomaly significantly deviate from the standard range in both space and time. For example, for color temperature data, if the color temperature value of a certain area exceeds 5000K and there are deviations exceeding the threshold at different time points, it is considered that there is a serious color temperature anomaly in this area, which is used as part of the overall color temperature anomaly data of the exhibit area to provide a basis for subsequent optimization.

[0071] Optionally, step S23 is specifically: Step S231: Generate a reference color temperature according to the standard lighting data of the exhibit area, thereby obtaining reference color temperature data of the exhibit area; In this embodiment, it is necessary to obtain standard lighting data for the exhibition area. Standard lighting data generally include color temperature values ​​of each lighting point in the exhibition area, and these color temperature values ​​can be obtained through light source parameters, lighting design solutions or specification parameters of lighting equipment. The color temperature of standard lighting data is generally set to a fixed value range, such as 3000K to 5000K. Next, the standard color temperature values ​​of each lighting point in the exhibition area are evenly distributed to generate reference color temperature data. With these data, a reference color temperature value can be generated for each lighting point, and a color temperature reference model can be formed in the entire exhibition area. This generation process needs to accurately calculate the reference color temperature value of each area based on the area of ​​the exhibition area and the layout of the light source to ensure that the lighting of the entire exhibition area meets the predetermined standards.

[0072] Step S232: constructing a spatial distribution diagram of the color temperature data of the exhibit area, thereby obtaining a spatial distribution diagram of the color temperature of the exhibit area; In this embodiment, it is necessary to collect color temperature data at various locations in the exhibit area. These data can be collected in real time by sensors or estimated by lighting design models. Based on these data, the color temperature value of each location is marked on the floor plan of the exhibit area, and different colors or gray values ​​are used to represent different color temperature levels. The color temperature value of each area is visualized through a spatial distribution map. The color temperature distribution map in the exhibit area shows the spatial variation of color temperature and shows which areas have higher or lower color temperature values. During the construction process, it is necessary to ensure that the color temperature data of each area is accurately collected and reasonably mapped to the spatial distribution map, so that the color temperature information of each location can accurately reflect the lighting environment in the exhibit area.

[0073] Step S233: Calculating the color temperature deviation of the color temperature space distribution diagram of the exhibit area according to the benchmark color temperature data of the exhibit area, thereby obtaining the color temperature deviation data of the exhibit area; In this embodiment, the color temperature value of each position in the exhibit area is compared with the reference color temperature value. For each position, the difference between its actual color temperature value and the reference color temperature value is calculated to obtain color temperature deviation data. The deviation calculation method can be performed by a simple subtraction operation, that is, the actual color temperature value minus the reference color temperature value to obtain the color temperature deviation. Through this calculation, the color temperature deviation of each position in the entire exhibit area can be obtained, and the distribution of the color temperature deviation can be analyzed. This deviation data can provide a basis for the subsequent identification of color temperature abnormal areas and lay a foundation for discovering high color temperature or low color temperature areas in the exhibit area.

[0074] Step S234: performing color temperature deviation area statistics according to the color temperature deviation data of the exhibit area, thereby obtaining high color temperature area data and low color temperature area data; In this embodiment, it is necessary to classify the color temperature deviation of the entire exhibit area according to the color temperature deviation data. The specific method is to divide the color temperature deviation values ​​of all areas according to the set threshold. For example, the threshold is set to ±10K. If the color temperature deviation of a certain area exceeds ±10K, it is marked as a high color temperature or low color temperature area. Through this process, all areas with large deviations in the exhibit area can be counted and classified as high color temperature areas and low color temperature areas respectively. In order to accurately count, weighted processing can also be performed according to the actual area of ​​the area to ensure that large areas of deviation areas can be fully considered and further guide the lighting optimization of the exhibit area.

[0075] Step S235: performing an exhibit material spectrum analysis on the high color temperature area data, thereby obtaining the exhibit material spectrum data of the high color temperature area; In this embodiment, it is necessary to determine the spectral characteristics of the exhibit material. The material of the exhibit usually affects its ability to reflect and absorb illumination light, and thus affects its color temperature perception. In order to perform spectral analysis, it is necessary to obtain the spectral data of the exhibit, which can be obtained through a spectrometer or other optical measurement tools. By analyzing the spectral characteristics of the exhibit material, it is possible to determine the color changes of the exhibit under different lighting conditions, especially the changes in the high color temperature area. When performing spectral analysis, it is necessary to pay attention to the reflectivity and absorptivity of the material, which can be obtained through actual measurement or reference to standard data. The analysis process can generate spectral data of exhibit materials in high color temperature areas with the help of spectral analysis instruments and software.

[0076] Step S236: evaluating the color restoration degree of exhibits in the low color temperature area data, thereby obtaining the color restoration degree data of exhibits in the low color temperature area; In this embodiment, it is necessary to evaluate the color reproduction of the exhibits under low color temperature lighting. The color reproduction of an exhibit refers to the difference between its color and the true color under different lighting conditions. In order to evaluate the color reproduction, a colorimeter or a color measurement tool is needed to measure the color of the exhibits in the low color temperature area. Usually, the evaluation process uses a standard color card or a true color as a benchmark to calculate the color difference value of the exhibits under low color temperature lighting. The color difference value can be calculated using the ΔE value (color difference value standard) to obtain quantitative data on the color reproduction by comparing the difference between the color of the exhibits at low color temperature and the reference color card. During the evaluation process, it is necessary to record the color difference of each exhibit in a low color temperature environment and form the color reproduction data of the exhibits in the low color temperature area.

[0077] Step S237: Merging the spatial abnormal color temperatures according to the material spectrum data of the exhibits in the high color temperature area and the color restoration degree data of the exhibits in the low color temperature area, thereby obtaining spatial abnormal color temperature data.

[0078] In this embodiment, it is necessary to combine the spectral data of the exhibit material in the high color temperature area and the color restoration data of the exhibit in the low color temperature area. The merging process analyzes the intersection of the high color temperature area and the low color temperature area to identify which areas show significant abnormalities in color temperature. The abnormalities in these areas are not only changes in color temperature, but are also closely related to the spectral characteristics and color restoration of the exhibit materials. In the merging process, set thresholds are used, such as the spectral difference in the high color temperature area exceeding 20%, and the color restoration difference in the low color temperature area exceeding 15% as the basis for merging. According to these standards, areas with significant color temperature anomalies are merged to form spatial abnormal color temperature data.

[0079] Optionally, step S235 is specifically: Identify the light source type for the high color temperature area data, thereby obtaining the light source type data; In this embodiment, it is necessary to collect spectral data of the light source in the high color temperature area through a spectrometer or other equipment to obtain the wavelength distribution of the light source. The data can be obtained by directly measuring the radiation spectrum of the light source in the high color temperature area, or by inferring it according to the specification manual of the light source. The measured spectral data will be compared with the common light source types (such as LED, fluorescent lamp, incandescent lamp, etc.) in the light source type database. The comparison process uses the minimum mean square error method (MSE) or a similarity algorithm (such as cosine similarity) to determine the degree of match between the spectral data and the light source type. Based on the matching results, the light source type in the high color temperature area is identified, and the light source type data is generated, which includes the type and spectral characteristics of the light source.

[0080] Extracting spectral features according to the light source type data, thereby obtaining light source type spectral data; In this embodiment, based on the light source type data, standard spectral data related to each light source type are selected, and these data can be obtained from the product manual or spectral database provided by the light source manufacturer. For example, for LED light sources, their spectral characteristics are usually concentrated in the blue and green bands, while fluorescent lamps have a strong ultraviolet spectrum distribution. Depending on the type of light source, a spectral analysis instrument such as a spectrophotometer is used to measure the radiation intensity of this type of light source at different wavelengths. Through these measurement data, the characteristic wavelength and corresponding radiation intensity of each light source type are extracted. These extracted spectral feature data will be used for subsequent light source irradiation simulation and material reflection analysis.

[0081] Obtain exhibit material data; In this embodiment, a material analyzer (such as an FTIR spectrometer or an X-ray fluorescence analyzer) is used to analyze the surface of the exhibit to obtain its chemical composition and physical structure data. Based on these data, the material type of the exhibit is determined, such as metal, plastic, wood, etc. Then, a spectrometer and other tools are used to measure the reflectivity and transmittance of the exhibit material in different bands. Usually, bands in the ultraviolet, visible light, and near-infrared regions are selected to analyze the reflection and absorption capacity of the exhibit material for light in different bands. The reflectivity data can be measured directly or calculated based on standard spectral data. The exhibit material data obtained in this process will provide a basis for subsequent reflectivity analysis.

[0082] Collect reflectivity according to the exhibit material data to obtain the exhibit material reflectivity; In this embodiment, a spectroscopic reflectometer is used to illuminate the surface of the exhibit and record the reflected spectrum data. The specific operation is to select a standard light source (such as the D65 standard light source) and capture the light reflected from the surface of the exhibit material through a detector. This process is usually carried out in the ultraviolet to near-infrared band, and the reflectivity is measured at multiple wavelengths. The collection of reflectivity data requires multi-angle measurement of different surfaces of the exhibits to ensure the representativeness and accuracy of the data. The collected data will form a reflectivity curve of the exhibit material, which shows the reflectivity of light of different wavelengths. These data can reflect the optical properties of the exhibit material in detail and provide a basis for subsequent light source illumination simulation.

[0083] Perform exhibition area light source identification on the high color temperature area data to obtain exhibition area light source data, and perform light source illumination simulation based on the exhibition area light source data and light source type spectrum data to obtain exhibition area light source illumination data; In this embodiment, it is necessary to arrange multiple light sensors in the high color temperature area to record the light source data at different positions. These sensors measure the radiation intensity and spectral information of the light source in real time and transmit them to the central processing system. The system compares the spectral analysis with the light source type database to identify the specific light source type in the exhibit area. These data provide the type information of the light sources in different areas of the exhibit area. The light source type data can include different types of light sources such as LEDs and fluorescent lamps. Using these light source data, the light source irradiation simulation is further performed. The geometric model of the exhibition area needs to be input into the irradiation simulation software (such as optical simulation software, etc.). In the software, the light source type data of the high color temperature area is input, and combined with its spectral characteristic information, the irradiation of the light source to the exhibit area is simulated. The simulation needs to use the radiation intensity data, wavelength distribution data of the light source, and the material reflectivity data of the exhibit area as input. During the simulation process, the distribution of the light source radiation at different positions is calculated, and a light source irradiation map is generated. In this way, the light source irradiation data of the entire exhibit area can be obtained, and the light intensity and spectral distribution of each area can be recorded in detail.

[0084] Analyze the light reflected by the exhibit materials according to the light source irradiation data of the exhibition area and the reflectivity of the exhibit materials, so as to obtain the reflection data of the exhibit materials; In this embodiment, the intensity of light reflected from the surface of the exhibit in different bands is calculated based on the light source illumination diagram and the reflectivity data of the exhibit. This analysis is achieved through ray tracing technology, that is, tracing the interaction process between the light emitted by the light source and the surface of the exhibit, and calculating the intensity and direction of the reflected light. For each band, the distribution and intensity of the reflected light are calculated to generate the light reflected data of the exhibit material.

[0085] Perform reflection band statistics on the reflection data of the exhibit materials, so as to obtain the reflection band data of the exhibit materials; In this embodiment, according to the analysis results of reflected light, multiple key bands (such as ultraviolet light, visible light and near infrared regions) are selected to count the intensity of reflected light in each band. By counting the reflected light in these bands, the reflection band data of the exhibit material is obtained. The data can be expressed as the distribution of the intensity of reflected light in different bands, and the reflection performance of different exhibit materials in each band is compared. Through these data, the reflection characteristics of the exhibits to different light sources can be understood in more detail.

[0086] Interactive analysis of light source color temperature is performed based on reflection band data to obtain spectral data of exhibit material in high color temperature areas.

[0087] In this embodiment, the reflection band data is matched with the spectral characteristics of different light sources to calculate the reflection characteristics of the exhibit material under different light sources. This analysis requires the color temperature, radiation intensity, wavelength distribution and reflection band data of each light source to be interactively analyzed. Through calculation, the color temperature reflection of the exhibit material under different light sources is obtained, and finally the spectral data of the exhibit material in the high color temperature area is obtained.

[0088] Optionally, step S3 specifically includes: Step S31: converting the exhibit color model according to the abnormal color temperature data of the exhibit area, thereby obtaining the exhibit color model; In this embodiment, the spectral data of the exhibit area is measured by an accurate spectral instrument (such as a spectrophotometer). During the measurement process, it is ensured that the wavelength range of the instrument covers the ultraviolet, visible light and near-infrared bands to obtain comprehensive color temperature data. By measuring the color temperature of the light source in the exhibit area, the specific color temperature value of the light source (such as 5000K, 6000K, etc.) is obtained, and the deviation between it and the standard color temperature value is recorded. Using these color temperature abnormality data, the color temperature of the light source is then mapped to the actual color of the exhibit using a color conversion formula (such as XYZ color space to RGB color space conversion). At this point, combined with the standard color temperature model, the abnormal color temperature data of the high color temperature light source is converted into the exhibit color model. In this conversion process, it is necessary to ensure that the standard color temperature compensation coefficient and color space conversion formula are used to perform accurate color adjustments to generate a standardized color model for the exhibit. Finally, the color model data of the exhibit is obtained for subsequent color difference calculation and distortion evaluation.

[0089] Step S32: obtaining reference color data; In this embodiment, a standard color light source (such as D65, A-type light source) is selected as the reference light source, and the spectrum is collected through the reflectance data under standard lighting conditions. Spectral instruments (such as colorimeters, spectrophotometers) are used to measure the color data presented by standard reference objects (such as white standard plates or color cards) under the illumination of standard light sources. The measured data will cover the reflectance spectrum of the exhibits and their color coordinates. The obtained benchmark color data includes color parameters such as color temperature value, RGB value, Lab value, etc., which have fixed reference standards. In order to ensure the accuracy of the benchmark color data, the equipment must be calibrated regularly and ensure that the test environment is free of any pollution or interference. The collection of benchmark color data needs to be completed under ideal color temperature conditions, and the color data under each standard light source must be recorded. This data will then be used to compare the color difference of the actual exhibit color model to ensure that the subsequent color difference calculation and distortion evaluation have a clear benchmark reference.

[0090] Step S33: Calculate the color difference of the exhibit color model according to the reference color data, so as to obtain color difference data; In this embodiment, the color coordinate values ​​(such as RGB or Lab values) of the reference color data and the exhibit color model data need to be compared. These color coordinate data are obtained by a colorimeter or a colorimeter. Next, by calculating the color difference value between the reference color and the exhibit color, the CIEDE2000 formula is used to calculate the difference between the various parameters in the formula (such as hue, brightness, saturation, etc.). In the process of color difference calculation, the measured RGB value or Lab value must be processed and the color difference value must be standardized to ensure that the color difference calculation can objectively reflect the actual degree of color deviation. When performing color difference calculation, the standard threshold value is set to ΔE≤1 for no perceived color difference, 1<ΔE≤2 for slight color difference, and ΔE>2 for obvious color difference. These values ​​are helpful in judging the degree of color distortion of the exhibits and provide a basis for subsequent compensation.

[0091] Step S34: evaluating the color distortion of the exhibit according to the color difference data, thereby obtaining the color distortion data of the exhibit; In this embodiment, distortion analysis is performed based on the color difference data using a color difference evaluation standard (such as a ΔE value). In this process, the color difference value needs to be compared with a predetermined distortion standard. The specific operation includes setting a color difference threshold. Usually, when the ΔE value exceeds 3, the color distortion is considered significant. For each exhibit, the degree of color deviation is determined based on the color difference calculation results and classified. At this time, a standard distortion evaluation model is used to analyze the color stability and consistency of the exhibits under different light source color temperatures. If the color difference value exceeds the set threshold, it is considered that there is color distortion, and it is corrected by further color adjustment or compensation methods. The distortion evaluation can also be presented through a visual chart, in which the color difference data of each exhibit is displayed in different color levels to help identify the most serious color distortion areas. The goal of this step is to quantify the color distortion of the exhibits and provide basic data for subsequent color temperature dynamic compensation.

[0092] Step S35: Perform color temperature dynamic compensation according to the exhibit color distortion data, thereby obtaining exhibit area color temperature dynamic compensation data.

[0093] In this embodiment, the color temperature compensation algorithm is used to take the color difference data evaluated in the previous step as input. These color difference data represent the deviation between the color of the exhibit and the reference color. Next, based on the color temperature compensation model, the color temperature of the light source is dynamically adjusted to reduce the color difference. If the color difference of the exhibit exceeds the standard due to the excessively high color temperature of the light source, the color distortion of the exhibit can be reduced by lowering the color temperature of the light source. During the compensation process, the reflectivity of the exhibit, the color temperature compensation coefficient, and the compensation strategy (such as the linear or nonlinear relationship between color temperature and color difference) need to be input to ensure that the compensation result achieves the expected color correction effect. After the compensation is completed, the color temperature data of the exhibit needs to be measured again to ensure that the color temperature has been adjusted to the ideal range and the color difference value is reduced to an acceptable range (such as a ΔE value less than 2). Finally, by adjusting the threshold and standard in the color temperature compensation algorithm, the color temperature dynamic compensation strategy is optimized to meet the color correction requirements under different exhibits and environmental conditions.

[0094] Optionally, step S35 is specifically: Step S351: performing color cast identification according to the color distortion data of the exhibit, thereby obtaining color cast data; In this embodiment, the color difference value is obtained by calculating the difference between the color of the exhibit and the reference color, and is usually calculated using CIEDE2000 or other standard color difference formulas. On this basis, after the color difference value is calculated, it is disassembled according to the different components of the color difference to identify the type of color cast (such as red cast, blue cast, yellow cast, etc.). The position of the exhibit in the color spectrum is determined by analyzing the RGB components of the color difference data or the L, a, and b three-dimensional components of the Lab color model. If the color distortion of the exhibit is mainly reflected in the red channel (such as R>G>B), it is identified as reddish; if the distortion is reflected in the blue channel (such as B>G>R), it is identified as bluish. In this process, a color cast threshold is set (such as a ΔE value greater than 2 is a significant color cast) as a standard for color cast identification. If the color difference is within the threshold, it is determined that no significant color cast has occurred. Finally, through calculation and judgment, the color cast data of the exhibit is obtained, and these data will be used for subsequent color light ratio compensation processing.

[0095] Step S352: performing statistics on the color cast data to obtain warm color data and cold color data; In this embodiment, it is necessary to classify different types of color cast (such as warm or cold) according to the color cast data obtained in step S351. To this end, based on the relevant components in the RGB or Lab color model, the number and degree of exhibits with warm colors (such as higher R values, lower G and B values) and cold colors (such as higher B values, lower R and G values) are respectively counted. During the statistical process, a standard color cast threshold is set, and the ΔE value of the color cast greater than 2 is usually regarded as a significant color cast, and the warm color and cold color are further subdivided. The statistical results can be presented in a table or graphic form, recording the number of occurrences of each color cast, the range of color cast values, etc. During the statistical process, for each type of color cast, the following standards are used for processing: warm color is usually defined as the color difference mainly reflected in the red light channel, and cold color is defined as the color difference mainly reflected in the blue light channel. The data of each color cast will be weighted and summarized according to the number of exhibits, severity and other parameters, and finally the warm color data and the cold color data are obtained. These statistical data will be used for subsequent light ratio adjustment processing.

[0096] Step S353: increasing red light proportion compensation according to the warm color data, thereby obtaining red light proportion compensation data; In this embodiment, it is necessary to extract the data of exhibits with warm colors based on the aforementioned color cast identification and statistical results. The color difference data of these exhibits show that their red light components are higher (that is, the value of the red channel is higher than that of the green and blue channels). In the compensation process, the compensation target is first set, that is, the red light component is increased to balance the warm color phenomenon. The specific operation is to adjust the gain coefficient of the red channel to increase the red light ratio. This gain coefficient can be calculated by analyzing the color difference data, usually a compensation coefficient based on the color difference correction model (such as when the coefficient is 1.2, it means that the red light gain is increased by 20%). During the adjustment process, a standard color correction device (such as a colorimeter) is used to measure the adjusted red light ratio in real time to ensure that the red light gain does not exceed the set threshold (such as the red light ratio is not greater than 50%). Finally, the red light ratio compensation data is obtained, which will be used in the subsequent color temperature dynamic compensation process.

[0097] Step S354: increasing the blue light ratio compensation according to the cold color data, thereby obtaining blue light ratio compensation data; In this embodiment, it is necessary to extract the data of the exhibits with cold colors based on color cast identification and statistical data. According to these data, the color difference data of the exhibits with cold colors indicates that the blue component is higher (that is, the value of the blue channel is higher than that of the red and green channels). At the beginning of the compensation process, the compensation target is first set, that is, the blue light component is increased to balance the cold color phenomenon. At this time, the gain coefficient of the blue channel is adjusted. The blue gain coefficient is usually obtained by calculating the color difference. The calculation formula of the gain coefficient is the compensation factor. For example, when it is set to 1.1, it means that the blue light gain is increased by 10%. During operation, a standard colorimeter is used to detect the adjusted blue light ratio to ensure that the blue light gain coefficient does not exceed the set upper limit (such as the blue light ratio is not greater than 60%). The gain coefficient in the compensation process can be dynamically adjusted according to the color difference value, and it is ensured that while increasing the blue light component, the balance of other color light components will not be affected. Through these operations, the blue light ratio compensation data is finally obtained, and the necessary compensation information is provided for the subsequent integration steps.

[0098] Step S355: Performing dynamic compensation integration of the color temperature of the exhibit according to the red light ratio compensation data and the blue light ratio compensation data, thereby obtaining dynamic compensation data of the color temperature of the exhibit area.

[0099] In this embodiment, the compensation priority of red light and blue light is set. Usually, the ratio compensation of red light and blue light needs to be weighed according to the specific color cast of the exhibit. The red light ratio compensation coefficient and the blue light ratio compensation coefficient are weighted and synthesized according to certain rules to form a new dynamic compensation coefficient. In specific operations, the compensation coefficient can be obtained by weighted average method. The weighted ratio of red light and blue light compensation coefficient is as follows: if the red light compensation coefficient is 1.2 and the blue light compensation coefficient is 1.1, then according to the actual color cast, the weighted ratio can be set to 60% (red light compensation) and 40% (blue light compensation). The integrated compensation coefficient is applied to the color temperature correction process of the exhibit, and the color balance is restored by adjusting the red and blue light ratio of the light source. During the implementation process, the color temperature meter and colorimeter are used in real time to monitor the compensation effect to ensure that the color of the exhibit after the color temperature adjustment is close to the standard color temperature (such as 5000K). By adjusting and optimizing the compensation coefficient, the color temperature dynamic compensation data of the exhibit area is obtained to ensure the restoration of the color of the exhibit.

[0100] Therefore, the embodiments should be regarded as illustrative and non-restrictive from all points, and the scope of the present invention is limited by the appended claims rather than the above description, and it is therefore intended that all changes falling within the meaning and range of equivalent elements of the application documents are included in the present invention.

[0101] The above description is only a specific embodiment of the present invention, so that those skilled in the art can understand or implement the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but should conform to the widest scope consistent with the principles and novel features invented herein.

Claims

1. A method for training a lighting optimization model, characterized in that: The following steps are involved: Step S1: Acquire the exhibition hall lighting data, and extract the exhibition hall lighting features and the exhibit area lighting features according to the exhibition hall lighting data, so as to obtain the exhibition hall lighting data and the exhibit area lighting data; perform light source position optimization analysis according to the exhibition hall lighting data, so as to obtain the exhibition hall light source position optimization data; Step S2: acquiring standard lighting data of the exhibition area; performing color temperature anomaly analysis on the lighting data of the exhibition area according to the standard lighting data of the exhibition area, thereby obtaining color temperature anomaly data of the exhibition area; Step S3: performing an exhibit color distortion analysis based on the exhibit area color temperature abnormality data, thereby obtaining exhibit color distortion data; performing color temperature dynamic compensation based on the exhibit color distortion data, thereby obtaining exhibit area color temperature dynamic compensation data; Step S4: obtaining a lighting optimization model; training the lighting optimization model according to the exhibition hall light source position optimization data and the exhibition area color temperature dynamic compensation data, thereby obtaining a lighting optimization training model; Step S5: performing lighting energy consumption evaluation according to the lighting optimization training model, thereby obtaining lighting energy consumption data; Energy efficiency optimization is performed based on lighting energy consumption to obtain lighting energy efficiency optimization data, which is then uploaded to the lighting optimization training model to perform lighting energy efficiency optimization tasks.

2. The lighting optimization model training method according to claim 1, characterized in that: Step S1 is specifically as follows: Step S11: Acquire exhibition hall lighting data, and extract exhibition hall lighting features and exhibit area lighting features based on the exhibition hall lighting data, so as to obtain exhibition hall lighting data and exhibit area lighting data; Step S12: performing glare optimization analysis according to the exhibition hall lighting data, thereby obtaining exhibition hall lighting glare optimization data; Step S13: performing illumination uniformity optimization analysis according to the exhibition hall lighting data, thereby obtaining the exhibition hall illumination uniformity optimization data; Step S14: integrating the exhibition hall lighting position optimization features according to the exhibition hall lighting glare optimization data and the exhibition hall lighting uniformity optimization data, thereby obtaining the exhibition hall light source position optimization data.

3. The lighting optimization model training method according to claim 2 is characterized in that: Step S12 is specifically as follows: Step S121: performing light source emission simulation according to the exhibition hall lighting data, thereby obtaining light source emission simulation data; Step S122: extracting emission angle features from the light source emission simulation data, thereby obtaining light source emission angle data; Step S123: obtaining audience position data; Step S124: performing glare evaluation on the audience position data according to the light source emission angle data, thereby obtaining the exhibition hall lighting glare data; Step S125: adjusting the light source angle of the exhibition hall lighting glare data, thereby obtaining light source angle adjustment data; Step S126: adjusting the installation height of the exhibition hall lighting glare data, thereby obtaining installation height adjustment data; Step S127: performing exhibition hall lighting glare optimization integration according to the light source angle adjustment data and the installation height adjustment data, thereby obtaining exhibition hall lighting glare optimization data.

4. The lighting optimization model training method according to claim 3 is characterized in that: Step S124 is specifically as follows: Calculate the relative angle of the audience position data according to the light source emission angle data, so as to obtain the light source emission-audience position angle data; Obtain glare standard threshold data; Extract light source intensity features based on exhibition hall lighting data to obtain light source intensity data; Calculate the glare intensity according to the light source intensity data and the light source emission-audience position angle data, thereby obtaining the glare intensity data; The glare intensity data is used to evaluate the exhibition hall lighting glare according to the glare standard threshold data, so as to obtain the exhibition hall lighting glare data.

5. The lighting optimization model training method according to claim 2, characterized in that: Step S13 is specifically as follows: Step S131: Drawing a lighting distribution area map according to the exhibition hall lighting data, thereby obtaining the exhibition hall lighting distribution area map; Step S132: performing minimum lighting area identification and maximum lighting area identification on the exhibition hall lighting distribution area map, thereby obtaining the exhibition hall minimum lighting area data and maximum lighting area data; Step S133: Calculate the illumination intensity according to the minimum illumination area data of the exhibition hall, so as to obtain the illumination intensity data of the minimum illumination area of ​​the exhibition hall; Step S134: Calculate the illumination intensity according to the data of the maximum illumination area of ​​the exhibition hall, so as to obtain the illumination intensity data of the maximum illumination area of ​​the exhibition hall; Step S135: Calculate the average illumination according to the exhibition hall lighting distribution area map, so as to obtain the average illumination of the exhibition hall; Step S136: Identify the illumination intensity data of the minimum illumination area and the illumination intensity data of the maximum illumination area according to the average illumination of the exhibition hall, so as to obtain the data of the too dark illumination area and the data of the too bright illumination area; Step S137: increasing the light source density of the dark area data, thereby obtaining light source density increase data; Step S138: Optimizing the reflectivity of the exhibition space material in the over-bright area data, thereby obtaining the exhibition space material data; Step S139: Perform uniform optimization and integration of the exhibition hall lighting according to the light source density increase data and the exhibition space material data, so as to obtain the exhibition hall lighting uniform optimization data.

6. The lighting optimization model training method according to claim 1, characterized in that: Step S2 is specifically as follows: Step S21: Acquire standard lighting data of the exhibition area; Step S22: Calculating the color temperature according to the lighting data of the exhibit area, thereby obtaining the color temperature data of the exhibit area; Step S23: performing spatial abnormal color temperature analysis on the color temperature data of the exhibition area according to the standard lighting data of the exhibition area, thereby obtaining spatial abnormal color temperature data; Step S24: performing temporal abnormal color temperature analysis on the color temperature data of the exhibit area according to the standard lighting data of the exhibit area, thereby obtaining temporal abnormal color temperature data; Step S25: integrating the color temperature anomaly of the exhibit area according to the spatial anomaly color temperature data and the temporal anomaly color temperature data, thereby obtaining the color temperature anomaly data of the exhibit area.

7. The lighting optimization model training method according to claim 6, characterized in that: Step S23 is specifically as follows: Step S231: Generate a reference color temperature according to the standard lighting data of the exhibit area, thereby obtaining reference color temperature data of the exhibit area; Step S232: constructing a spatial distribution diagram of the color temperature data of the exhibit area, thereby obtaining a spatial distribution diagram of the color temperature of the exhibit area; Step S233: Calculating the color temperature deviation of the color temperature space distribution diagram of the exhibit area according to the benchmark color temperature data of the exhibit area, thereby obtaining the color temperature deviation data of the exhibit area; Step S234: performing color temperature deviation area statistics according to the color temperature deviation data of the exhibit area, thereby obtaining high color temperature area data and low color temperature area data; Step S235: performing an exhibit material spectrum analysis on the high color temperature area data, thereby obtaining the exhibit material spectrum data of the high color temperature area; Step S236: evaluating the color restoration degree of exhibits in the low color temperature area data, thereby obtaining the color restoration degree data of exhibits in the low color temperature area; Step S237: Merging the spatial abnormal color temperatures according to the material spectrum data of the exhibits in the high color temperature area and the color restoration degree data of the exhibits in the low color temperature area, thereby obtaining spatial abnormal color temperature data.

8. The lighting optimization model training method according to claim 7, characterized in that: Step S235 is specifically as follows: Identify the light source type for the high color temperature area data, thereby obtaining the light source type data; Extracting spectral features according to the light source type data, thereby obtaining light source type spectral data; Obtain exhibit material data; Collect reflectivity according to the exhibit material data to obtain the exhibit material reflectivity; Perform exhibition area light source identification on the high color temperature area data to obtain exhibition area light source data, and perform light source irradiation simulation based on the exhibition area light source data and light source type spectrum data to obtain exhibition area light source irradiation data; Analyze the light reflected by the exhibit materials according to the light source irradiation data of the exhibition area and the reflectivity of the exhibit materials, so as to obtain the reflection data of the exhibit materials; Perform reflection band statistics on the reflection data of the exhibit material, so as to obtain the reflection band data of the exhibit material; Interactive analysis of light source color temperature is performed based on reflection band data to obtain spectral data of exhibit material in high color temperature areas.

9. The lighting optimization model training method according to claim 1, characterized in that: Step S3 is specifically as follows: Step S31: converting the exhibit color model according to the abnormal color temperature data of the exhibit area, thereby obtaining the exhibit color model; Step S32: obtaining reference color data; Step S33: Calculate the color difference of the exhibit color model according to the reference color data, so as to obtain color difference data; Step S34: evaluating the color distortion of the exhibit according to the color difference data, thereby obtaining the color distortion data of the exhibit; Step S35: Perform color temperature dynamic compensation according to the exhibit color distortion data, thereby obtaining exhibit area color temperature dynamic compensation data.

10. The lighting optimization model training method according to claim 9, characterized in that: Step S35 is specifically as follows: Step S351: performing color cast identification according to the color distortion data of the exhibit, thereby obtaining color cast data; Step S352: performing statistics on the color cast data to obtain warm color data and cold color data; Step S353: increasing red light proportion compensation according to the warm color data, thereby obtaining red light proportion compensation data; Step S354: increasing the blue light ratio compensation according to the cold color data, thereby obtaining blue light ratio compensation data; Step S355: Performing dynamic compensation integration of the color temperature of the exhibit according to the red light ratio compensation data and the blue light ratio compensation data, thereby obtaining dynamic compensation data of the color temperature of the exhibit area.

Images