Mirror assembly effect evaluation system and method based on internet of things

Abstract

The application discloses a mirror assembly effect evaluation system and method based on the Internet of Things, and particularly relates to the technical field of intelligent assembly evaluation. The system collects the use information of the assembled mirror through the Internet of Things sensor, generates a use information set and analyzes the mirror reflection to determine whether there is an early sign of inadaptation of the assembly effect and the environment. When the inadaptation sign is detected, the light adaptability features and visual aesthetic features are extracted from the information set to generate a light adaptability index and a visual aesthetic index respectively. Then, the indexes are input into a pre-trained machine learning model to calculate the assembly adaptability and divide the lenses into two categories of high adaptability and low adaptability. For the lenses of low adaptability, the system automatically performs reassembly and feature extraction until all the lenses reach high adaptability. The application can ensure that the reflection effect and visual performance of each lens under various illumination modes are in the best state, and improve the overall user experience.

Description

Technical Field

[0001] This invention relates to the field of intelligent assembly evaluation technology, and more specifically, to a mirror assembly effect evaluation system and method based on the Internet of Things. Background Technology

[0002] In many applications, mirrors not only serve as imaging tools but also enhance the aesthetics and functionality of spaces. However, traditional mirror assembly often exhibits insufficient adaptability in practical use, especially under varying lighting conditions. These problems are particularly pronounced in mirrors constructed from multiple lenses, where uneven lighting, reduced clarity, and brightness differences at the seams frequently affect the overall effect, leading to a poor visual experience for the user. Achieving high-quality assembly typically requires experienced technicians for adjustment and optimization, but this method struggles to precisely quantify the assembly effect, resulting in inconsistent quality and a lack of standardization.

[0003] With the rapid development of IoT technology, real-time monitoring and data analysis through smart sensors have become possible. IoT technology enables remote collection and analysis of usage data after mirror assembly, achieving intelligent detection and evaluation of the assembly effect. For example, through IoT sensors, parameters such as reflected light intensity, brightness uniformity, and clarity of the mirror can be collected under different ambient lighting conditions, generating datasets for systematic analysis. Based on IoT data support, the adaptability of the mirror during assembly can be quantified, forming a feedback mechanism to optimize the assembly process. This method not only improves the accuracy and consistency of the assembly effect but also identifies potential adaptability issues early, allowing for timely adjustments and improving overall assembly quality and user experience. Therefore, this paper proposes an IoT-based mirror assembly effect evaluation system and method. Summary of the Invention

[0004] To achieve the above objectives, the present invention provides the following technical solution:

[0005] The IoT-based method for evaluating the assembly effect of mirrors includes the following steps:

[0006] The usage information of the assembled mirror is collected by IoT sensors to obtain a usage information set;

[0007] Specular reflection analysis is performed based on the information set used, and then the results of the specular reflection analysis are used to determine whether there are early signs of mismatch between the mirror assembly effect and the usage environment.

[0008] When there are early signs that the mirror assembly effect is not compatible with the usage environment, light adaptability features and visual aesthetic features are extracted from the usage information set, and light adaptability index and visual aesthetic index are generated respectively.

[0009] The light adaptability index and visual aesthetics index are input into the pre-trained machine learning model, and the assembly fit degree is output. Based on the assembly fit degree, the lenses used for assembly are divided into two assembly types: high-fit assembly and low-fit assembly.

[0010] Lenses with low-fit assemblies are reassembled and features are re-extracted until all lenses used for assembly are classified as high-fit assemblies.

[0011] The mirror is assembled from multiple lenses, each of which is numbered and has a unique number.

[0012] In a preferred embodiment, specular reflection analysis refers to:

[0013] When the assembled mirror is used in the application environment, the application environment has multiple preset lighting modes. In each brightness mode, the sampling data obtained by sampling the intensity of the mirror reflection at the connection point is retrieved from the usage information set in order to obtain comprehensive connection data for each brightness mode. Multiple sets of sampling data are obtained, and each set of sampling data corresponds to a unique lighting mode. Then, the mean and standard deviation of each set of sampling data are calculated to obtain a stable combination [PJi, BZi] to reflect the reflection intensity; i represents the type number of the lighting mode, PJi represents the mean of the sampling data of the i-th lighting mode, and BZi represents the standard deviation of the sampling data of the i-th lighting mode.

[0014] In a preferred embodiment, determining whether there are early signs of incompatibility between the mirror assembly effect and the usage environment based on the results of specular reflection analysis refers to:

[0015] Obtain the specular reflection analysis result, i.e., the stability combination [PJi, BZi]. The i-th lighting mode has a preset specular reflection standard range one and a specular reflection standard range two. If the stability combination PJi and the specular reflection standard range one intersect, and the stability combination BZi and the specular reflection standard range two intersect, a normal signal is generated. If the stability combination PJi and the specular reflection standard range one intersect, and the stability combination BZi and the specular reflection standard range two do not intersect, an abnormal signal is generated. If an abnormal signal is generated in any lighting mode, it indicates an early sign that the mirror assembly effect is not compatible with the usage environment.

[0016] In a preferred embodiment, the logic for obtaining the light adaptability index is as follows:

[0017] For each individual lens, light reflection intensity data is extracted using a light sensor and sampled multiple times under different lighting modes. The extracted light adaptability feature data includes the average reflected light intensity and the standard deviation of reflected light brightness fluctuation under each lighting mode.

[0018] For each lens j, a light adaptability coefficient LS I jm is generated based on the light adaptability characteristics. This coefficient represents the degree to which lens j adapts to light under the current lighting conditions. The calculation formula is as follows:

[0019] L represents the illuminance under the current lighting conditions, i.e., the illuminance of the current type m lighting mode; Ravg represents the average reflected light intensity under the current lighting conditions; σR represents the standard deviation of the reflected light illuminance fluctuation under the current lighting conditions; k represents the preset fluctuation adjustment coefficient; and LSIjm represents the degree of light adaptation of lens j under the current type m lighting mode.

[0020] The following processing was performed on all lighting modes to obtain the light adaptability index of each lens across the full brightness range: U represents the total number of lighting modes, and Q is the preset sensitivity coefficient, where Q is greater than 1. total This indicates the light adaptability index of lens j across the entire brightness range.

[0021] In a preferred embodiment, the logic for obtaining the visual aesthetics index is as follows:

[0022] Extract the visual aesthetic features of each individual lens, including image sharpness, light distribution uniformity, and visual contrast. Then, calculate the visual aesthetic coefficient of lens j under the current lighting conditions, i.e., the current type m lighting mode. The calculation formula is as follows:

[0023] QXm represents the corresponding value of the image sharpness index of lens j under the current lighting type m, GXm represents the corresponding value of the light distribution uniformity index of lens j under the current lighting type m, SDm represents the corresponding value of the visual contrast index of lens j under the current lighting type m, VSIjm represents the visual aesthetics coefficient of lens j under the current lighting type m, and w1, w2, and w3 are all preset non-zero scaling coefficients.

[0024] The formula for calculating the visual aesthetics index is:

[0025] VSIj total This represents the visual aesthetics index of lens j across the entire brightness range.

[0026] In a preferred embodiment, the logic for obtaining the image sharpness index is as follows: the specular reflection image is analyzed by an image processing algorithm, the sharpness is quantified by edge detection, and the corresponding value of the image sharpness index is represented as the average value of the edge intensity.

[0027] The logic for obtaining the uniformity index of light distribution is as follows: the light intensity at multiple locations on the mirror surface is collected by a light sensor and its root mean square error is calculated. The result obtained is the corresponding value of the uniformity index of light distribution.

[0028] The logic for obtaining the visual contrast ratio is as follows: in different brightness areas, the contrast is calculated through the brightness difference, specifically using the average brightness difference between bright and dark areas.

[0029] Lm max Lm represents the average brightness of the bright area. min This represents the average brightness of the dark area.

[0030] In a preferred embodiment, the pre-trained machine learning model is a multinomial regression model.

[0031] In a preferred embodiment, classifying the lenses used for assembly into two assembly types—high-fit assembly and low-fit assembly—based on the degree of fit means:

[0032] The assembly fit of lens j is compared with the preset assembly fit threshold. If the assembly fit of lens j is greater than or equal to the preset assembly fit threshold, then lens j is classified as a highly fitted assembly type. If the assembly fit of lens j is less than the preset assembly fit threshold, then lens j is classified as a poorly fitted assembly type.

[0033] In a preferred embodiment, the IoT-based mirror assembly effect evaluation system includes:

[0034] The information acquisition module collects usage information of the assembled mirror through IoT sensors to obtain a usage information set.

[0035] The mirror reflection analysis module performs mirror reflection analysis based on the usage information set, and then determines whether there are early signs of incompatibility between the mirror assembly effect and the usage environment based on the mirror reflection analysis results.

[0036] The feature extraction module extracts light adaptability features and visual aesthetic features from the usage information set when there are early signs that the mirror assembly effect is not compatible with the usage environment, and generates light adaptability index and visual aesthetic index respectively.

[0037] The single lens type classification module inputs the light adaptability index and visual aesthetics index into the pre-trained machine learning model and outputs the assembly fit degree. Based on the assembly fit degree, the lenses used for assembly are classified into two assembly types: high-fit assembly and low-fit assembly.

[0038] The assembly optimization module reassembles lenses with low-fit assemblies and re-extracts features until all lenses used for assembly are classified as high-fit assemblies.

[0039] The technical effects and advantages of this invention are as follows:

[0040] By collecting data on the light adaptability and visual aesthetics of mirrors through IoT sensors, this invention can accurately quantify the assembly effect of each lens. Utilizing a pre-trained machine learning model to analyze assembly fit allows for a systematic and standardized evaluation of assembly quality, avoiding reliance on human experience and improving assembly accuracy and consistency. This invention ensures that each lens maintains optimal reflectivity and visual performance under various lighting conditions through the calculation of light adaptability and visual aesthetics indices. For lenses with low fit, the system automatically prompts for readjustment, ensuring that the assembled mirror presents a consistent visual effect under various lighting conditions in the application environment, thus enhancing the overall user experience.

[0041] This invention can quickly detect signs of misfit in the early stages of assembly through mirror reflection analysis, thereby promptly identifying and resolving potential assembly problems and reducing later maintenance costs. This real-time monitoring and adjustment mechanism avoids quality issues caused by assembly defects, improving product stability and reliability. The invention incorporates IoT technology, enabling real-time uploading and analysis of assembled mirror data, eliminating the need for frequent manual inspections. For poorly fitted lenses, machine learning models automatically classify and provide feedback, allowing the system to efficiently perform optimization operations, reducing the time cost of manual adjustments and significantly improving assembly efficiency and automation. Attached Figure Description

[0042] To facilitate understanding by those skilled in the art, the present invention will be further described below with reference to the accompanying drawings;

[0043] Figure 1 This is a schematic diagram of the IoT-based mirror assembly effect evaluation method in this invention.

[0044] Figure 2 This is a schematic diagram of the IoT-based mirror assembly effect evaluation system of the present invention. Detailed Implementation

[0045] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0046] Reference Figure 1 - Figure 2 The following examples were obtained:

[0047] Example 1: A method for evaluating the assembly effect of a mirror based on the Internet of Things, comprising the following steps:

[0048] The system collects usage information about the assembled mirror using IoT sensors, creating a usage information set. This step aims to gather data on the mirror's performance in its actual usage environment. Through IoT sensors, the system can collect real-time data on mirror reflection intensity, ambient brightness, and clarity, forming a complete usage information set. This information provides data support for subsequent analysis and judgment, enabling assessments to be based on the actual usage environment.

[0049] Specular reflection analysis is performed based on the usage information set, and the results are then used to determine early signs of mismatch between the mirror's assembly and the usage environment. This step aims to determine whether the mirror's assembly meets expectations in the current usage environment through specular reflection data analysis. By analyzing characteristics such as the uniformity of reflection intensity and brightness fluctuations at the joints, potential signs of mismatch can be detected early. If signs of mismatch are found, adjustments can be made in time before the problem escalates.

[0050] When early signs of mismatch between the mirror assembly and the usage environment are detected, light adaptability and visual aesthetics features are extracted from the usage information set, and light adaptability and visual aesthetics indices are generated respectively. When further signs of mismatch are detected, light adaptability and visual aesthetics features are extracted from the usage information set. The light adaptability index reflects the reflectivity of the lens under different brightness conditions, while the visual aesthetics index reflects the lens's sharpness and visual consistency. These two indices provide quantitative indicators for the accuracy and aesthetics of the assembly, providing a basis for subsequent assembly optimization.

[0051] The light adaptability index and visual aesthetics index are input into a pre-trained machine learning model, which outputs a fit score. Based on the fit score, the lenses used for assembly are classified into two types: high-fit and low-fit. The goal of this step is to use the machine learning model to comprehensively evaluate the assembly effect of the lenses. The pre-trained multinomial regression model calculates the fit score based on the light adaptability and visual aesthetics indices, and classifies the assembled lenses into high-fit and low-fit categories. This classification result helps the system identify which lenses meet the requirements and which lenses need further adjustment.

[0052] Lenses with poor fit are reassembled, and feature extraction is performed again until all lenses used for assembly are classified as high-fit assemblies. When some lenses are determined to be poorly fitted, the system triggers a reassembly process, adjusting the position and angle of these lenses and collecting feature data again. This step iterates repeatedly until all lenses eventually meet the high-fit assembly requirements, ensuring that the overall mirror assembly effect in the usage environment meets design standards and provides optimal visual experience and light adaptation.

[0053] The mirror is assembled from multiple lenses, each individually numbered with a unique identifier. This numbering system facilitates personalized tracking and analysis of each lens during the assembly process. This system ensures accurate identification and understanding of each lens's specific characteristics and assembly effect when collecting data on light adaptability and visual aesthetics, allowing for individual adjustments and optimizations, and improving the overall management precision of the assembly process.

[0054] Specular reflection analysis refers to:

[0055] When the assembled mirror is used in the application environment, the application environment has multiple preset lighting modes. In each brightness mode, the sampling data obtained by sampling the intensity of the mirror reflection at the connection point is retrieved from the usage information set in order to obtain comprehensive connection data for each brightness mode. Multiple sets of sampling data are obtained, and each set of sampling data corresponds to a unique lighting mode. Then, the mean and standard deviation of each set of sampling data are calculated to obtain a stable combination [PJi, BZi] to reflect the reflection intensity; i represents the type number of the lighting mode, PJi represents the mean of the sampling data of the i-th lighting mode, and BZi represents the standard deviation of the sampling data of the i-th lighting mode.

[0056] Multiple lighting modes are preset in the application environment. By sampling the intensity of mirror reflections under different brightness modes, the adaptability of the mirror assembly effect under various lighting conditions can be more comprehensively evaluated. This method ensures that the mirror has a stable visual effect under different ambient brightness levels. Sampling the reflected light intensity at the mirror joints ensures that the splicing effect between the mirrors is good, without obvious brightness differences or uneven reflections. Since the joints are the areas where light adaptation and visual consistency are most likely to have problems, specifically testing the data at the joints can effectively determine the assembly quality.

[0057] Judging from the results of mirror reflection analysis whether there are early signs of incompatibility between the mirror assembly effect and the usage environment refers to:

[0058] Obtain the specular reflection analysis result, i.e., the stability combination [PJi, BZi]. The i-th lighting mode has a preset specular reflection standard range one and a specular reflection standard range two. If the stability combination PJi and the specular reflection standard range one intersect, and the stability combination BZi and the specular reflection standard range two intersect, a normal signal is generated. If the stability combination PJi and the specular reflection standard range one intersect, and the stability combination BZi and the specular reflection standard range two do not intersect, an abnormal signal is generated. If an abnormal signal is generated in any lighting mode, it indicates an early sign that the mirror assembly effect is not compatible with the usage environment.

[0059] The "stability combination" of reflected light intensity under each lighting mode reflects the mirror's light stability under different lighting conditions. If the stability combination meets the standard range in all preset lighting modes, it indicates that the mirror's assembly is stable and reliable; otherwise, there may be early signs of incompatibility. If the stability combination does not meet the standard range in any lighting mode, an "abnormal signal" can be generated, indicating that there may be early signs of incompatibility in the assembly. This early warning mechanism allows for detection and adjustment before problems escalate, improving the overall assembly's adaptability and quality. Mirror reflection analysis, through multi-mode sampling and stability combination calculation, can systematically evaluate the adaptability of the assembled mirror in various lighting environments, ensuring no obvious defects at the joints and achieving a high-quality assembly effect.

[0060] The Light Adaptability Index (LAI) quantifies the light adaptation performance of a single lens under various ambient lighting conditions. This index reflects the stability and adaptability of a lens's light reflection under different lighting modes, helping to determine whether the lens's fit in the intended environment meets expectations. A higher LAI indicates better light adaptability, better reflection and adaptation to current ambient lighting conditions. This typically means that the lens exhibits better reflection and light stability under various lighting modes, demonstrating stronger environmental adaptability. Conversely, a lower LAI may indicate poor light adaptability under certain lighting modes, potentially resulting in uneven or unstable reflection and a risk of incompatibility. The logic for obtaining the LAI is as follows:

[0061] For each individual lens, light reflection intensity data is extracted using a light sensor and sampled multiple times under different lighting modes. The extracted light adaptability feature data includes the average reflected light intensity and the standard deviation of reflected light brightness fluctuation under each lighting mode.

[0062] For each lens j, a light adaptability coefficient LS I jm is generated based on the light adaptability characteristics. This coefficient represents the degree to which lens j adapts to light under the current lighting conditions. The calculation formula is as follows:

[0063] L represents the illuminance under the current lighting conditions, i.e., the current type m lighting mode, which can also be understood as the intensity of ambient light. This value is used to standardize the reflected light intensity data so that the results under different brightness modes can be reasonably compared. Ravg represents the average reflected light intensity under the current lighting conditions, which represents the reflection effect of lens j under the current brightness conditions. The higher this value, the stronger the reflection of light by the lens. σR represents the standard deviation of the reflected light illuminance fluctuation under the current lighting conditions, which is used to evaluate the reflection stability of the lens. A lower standard deviation indicates that the reflection effect is more stable. k represents the preset fluctuation adjustment coefficient. LSIjm represents the degree of light adaptation of lens j under the current type m lighting mode.

[0064] The following processing was performed on all lighting modes to obtain the light adaptability index of each lens across the full brightness range: U represents the total number of lighting modes, indicating how many different brightness conditions need to be considered. Q is a preset sensitivity coefficient; a value greater than 1 is used to highlight the impact of adaptability differences between different modes, making the final result more sensitive to the adaptability of different brightness modes. LSIj total This represents the light adaptability index of lens j across the entire brightness range, and represents the overall light adaptability effect of lens j under various brightness conditions.

[0065] The Visual Aesthetics Index quantifies the visual aesthetics of a single lens under different brightness modes. This index reflects the lens's overall performance in terms of image sharpness, light distribution uniformity, and visual contrast, helping to determine whether the lens provides a good visual experience in its assembly environment. A higher Visual Aesthetics Index indicates better aesthetics and visual performance in the current assembly environment. A higher index signifies excellent performance in image sharpness, light distribution uniformity, and visual contrast, providing a more comfortable visual experience across various brightness modes. A lower Visual Aesthetics Index may indicate poorer aesthetics under certain lighting modes, with potential deficiencies in sharpness, uniformity, or contrast, affecting the overall visual effect. The logic for obtaining the Visual Aesthetics Index is as follows:

[0066] Extract the visual aesthetic features of each individual lens, including image sharpness, light distribution uniformity, and visual contrast. Then, calculate the visual aesthetic coefficient of lens j under the current lighting conditions, i.e., the current type m lighting mode. The calculation formula is as follows:

[0067] QXm represents the image sharpness index of lens j under the current lighting mode m. It indicates the sharpness of lens j under the current lighting mode m, and the corresponding value is obtained through image processing algorithm analysis. A higher value indicates higher image sharpness and better visual performance of the lens. GXm represents the light distribution uniformity index of lens j under the current lighting mode m. It indicates the uniformity of light distribution of lens j under the current lighting mode m, and the corresponding value is calculated through the light intensity distribution on the lens surface. A lower value indicates more uniform light distribution. SDm represents the visual contrast index of lens j under the current lighting mode m, reflecting the contrast effect of lens j under the current lighting mode m. It is usually calculated through the brightness difference between bright and dark areas. A higher value means stronger contrast and more vivid visual performance. VSIjm represents the visual aesthetics coefficient of lens j under the current lighting mode m. w1, w2, and w3 are preset non-zero proportional coefficients used to adjust the influence of sharpness, uniformity, and contrast on visual aesthetics.

[0068] The formula for calculating the visual aesthetics index is:

[0069] VSIj total The visual aesthetic index of lens j under the full brightness range is obtained by nonlinear combination of the visual aesthetic coefficients under all lighting modes, and represents the overall visual aesthetic performance of lens j under the full brightness range.

[0070] The logic for obtaining the image sharpness index is as follows: Image processing algorithms are used to analyze the specular reflection image, and edge detection is used to quantify sharpness. The corresponding value of the image sharpness index is represented as the average edge intensity. The image sharpness index reflects the visual clarity of the lens under current lighting conditions. The higher the edge intensity, the sharper the image, and the better the visual performance of the lens. The sharpness index is used to quantify the visual quality of the lens, ensuring good visual effects under different lighting conditions.

[0071] The logic for obtaining the light distribution uniformity index is as follows: Light intensity is collected at multiple locations on the lens surface using a light sensor, and the root mean square error (RMSE) is calculated. The result is the corresponding value of the light distribution uniformity index. The light distribution uniformity index reflects whether the light distribution of the lens is uniform under current lighting conditions. The smaller the MRM, the more uniform the light distribution, indicating that there are no significant brightness differences on the lens surface. Uniform light distribution helps improve the overall visual experience and reduces visual discomfort and discontinuity.

[0072] The logic for obtaining the visual contrast ratio is as follows: in different brightness areas, the contrast is calculated through the brightness difference, specifically using the average brightness difference between bright and dark areas.

[0073] Lm max Lm represents the average brightness of the bright area. min The visual contrast ratio, representing the average brightness of dark areas, measures a lens's contrast performance under current lighting conditions. A higher contrast ratio indicates that the lens provides a clearer distinction between bright and dark areas, resulting in a more vivid and lifelike visual effect. Contrast is crucial for overall visual aesthetics, enhancing image detail.

[0074] The pre-trained machine learning model is a multinomial regression model, with the corresponding function expression: SPj = F(LSIj) total VSIj total SPj represents the fit and fit of lens j.

[0075] Based on the degree of fit, lenses used for assembly are divided into two assembly types: high-fit assembly and low-fit assembly.

[0076] The assembly fit of lens j is compared with the preset assembly fit threshold. If the assembly fit of lens j is greater than or equal to the preset assembly fit threshold, then lens j is classified as a highly fitted assembly type. If the assembly fit of lens j is less than the preset assembly fit threshold, then lens j is classified as a poorly fitted assembly type.

[0077] By evaluating and classifying the fit of lenses, it can be ensured that the assembled effect of each lens meets the preset fit requirements. A highly fitted lens indicates that it has achieved an ideal fit in terms of light adaptability and visual aesthetics, meeting the needs of the usage environment. If a lens is classified as poorly fitted, it indicates that its fit is not ideal and may affect the overall visual experience and light adaptability, requiring further adjustment or reassembly. Lenses classified as poorly fitted can be marked, and the system can further optimize these lenses without additional processing for highly fitted lenses. This method saves time and resources, making the assembly process more efficient. Through iterative optimization, all lenses eventually reach the high-fit standard, ensuring the consistency and stability of the entire assembly system. A highly fitted fit guarantees the visual quality and light adaptability of the lenses in the actual usage environment, thereby improving the user experience. Users can obtain a seamless visual effect, with lenses maintaining consistent light adaptability and visual aesthetics under various lighting conditions. By classifying lenses by fit, misfit issues during assembly can be identified and resolved early, reducing potential quality problems caused by poorly fitted lenses. This classification method helps ensure that each lens meets quality standards before the product is put into use, thereby reducing subsequent maintenance and replacement costs.

[0078] Example 2: An IoT-based mirror assembly effect evaluation system, comprising:

[0079] The information acquisition module collects usage information of the assembled mirror through IoT sensors to obtain a usage information set.

[0080] The mirror reflection analysis module performs mirror reflection analysis based on the usage information set, and then determines whether there are early signs of incompatibility between the mirror assembly effect and the usage environment based on the mirror reflection analysis results.

[0081] The feature extraction module extracts light adaptability features and visual aesthetic features from the usage information set when there are early signs that the mirror assembly effect is not compatible with the usage environment, and generates light adaptability index and visual aesthetic index respectively.

[0082] The single lens type classification module inputs the light adaptability index and visual aesthetics index into the pre-trained machine learning model and outputs the assembly fit degree. Based on the assembly fit degree, the lenses used for assembly are classified into two assembly types: high-fit assembly and low-fit assembly.

[0083] The assembly optimization module reassembles lenses with low-fit assemblies and re-extracts features until all lenses used for assembly are classified as high-fit assemblies.

[0084] The above formulas are all dimensionless calculations. The formulas are derived from software simulations based on a large amount of collected data to obtain the most recent real-world results. The preset parameters in the formulas are set by those skilled in the art according to the actual situation.

[0085] It should be understood that in the various embodiments of this application, the order of the above-mentioned processes does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0086] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0087] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0088] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A method for evaluating the assembly effect of mirrors based on the Internet of Things, characterized in that, Includes the following steps: The usage information of the assembled mirror is collected by IoT sensors to obtain a usage information set; Specular reflection analysis is performed based on the information set used, and then the results of the specular reflection analysis are used to determine whether there are early signs of mismatch between the mirror assembly effect and the usage environment. When there are early signs that the mirror assembly effect is not compatible with the usage environment, light adaptability features and visual aesthetic features are extracted from the usage information set, and light adaptability index and visual aesthetic index are generated respectively. The light adaptability index and visual aesthetics index are input into the pre-trained machine learning model, and the assembly fit degree is output. Based on the assembly fit degree, the lenses used for assembly are divided into two assembly types: high-fit assembly and low-fit assembly. Lenses with low-fit assembly are reassembled and features are re-extracted until all lenses used for assembly are classified as high-fit assembly types. Judging from the results of mirror reflection analysis whether there are early signs of incompatibility between the mirror assembly effect and the usage environment refers to: Obtain the specular reflection analysis results, i.e., the stability combination [PJi, BZi]. The i-th lighting mode has a preset specular reflection standard range one and a specular reflection standard range two. If the stability combination PJi and the specular reflection standard range one intersect and the stability combination BZi and the specular reflection standard range two intersect, a normal signal is generated. If the stability combination PJi and the specular reflection standard range one intersect and the stability combination BZi and the specular reflection standard range two do not intersect, an abnormal signal is generated. If an abnormal signal is generated in any lighting mode, it indicates an early sign that the mirror assembly effect is not compatible with the usage environment. Specular reflection analysis refers to: When the assembled mirror is used in the application environment, the application environment has multiple preset lighting modes. In each lighting mode, the sampling data obtained by sampling the intensity of the mirror reflection at the connection point is retrieved from the usage information set to obtain comprehensive connection data for each lighting mode. Multiple sets of sampling data are obtained, and each set of sampling data corresponds to a unique lighting mode. Then, the mean and standard deviation of each set of sampling data are calculated to obtain a stable combination [PJi, BZi] to reflect the reflection intensity; i represents the type number of the lighting mode, PJi represents the mean of the sampling data of the i-th lighting mode, and BZi represents the standard deviation of the sampling data of the i-th lighting mode.

2. The method for evaluating the assembly effect of a mirror based on the Internet of Things according to claim 1, characterized in that, The mirror is assembled from multiple lenses, each of which is numbered and has a unique number.

3. The method for evaluating the assembly effect of a mirror based on the Internet of Things according to claim 1, characterized in that, The logic for obtaining the light adaptability index is as follows: For each individual lens, light reflection intensity data is extracted using a light sensor and sampled multiple times under different lighting modes. The extracted light adaptability feature data includes the average reflected light intensity and the standard deviation of reflected light brightness fluctuation under each lighting mode. For each lens j, a light adaptability coefficient LSIjm is generated based on the light adaptability characteristics. This coefficient represents the degree to which lens j adapts to light under the current lighting conditions. The calculation formula is as follows: L represents the illuminance under the current lighting conditions, i.e., the illuminance under the current light type m, and Ravg represents the average reflected light intensity under the current lighting conditions. The standard deviation of the reflected light brightness fluctuation under the current lighting conditions is represented by , k represents the preset fluctuation adjustment coefficient, and LSIjm represents the degree of light adaptation of lens j under the current lighting mode of the current type m. The following processing was performed on all lighting modes to obtain the light adaptability index of each lens across the full brightness range: U represents the total number of lighting modes, Q is the preset sensitivity coefficient, and Q is greater than 1. total This indicates the light adaptability index of lens j across the entire brightness range.

4. The method for evaluating the assembly effect of a mirror based on the Internet of Things according to claim 3, characterized in that, The logic for obtaining the visual aesthetics index is as follows: Extract the visual aesthetic features of each individual lens, including image sharpness, light distribution uniformity, and visual contrast. Then, calculate the visual aesthetic coefficient of lens j under the current lighting conditions, i.e., the current type m lighting mode. The calculation formula is as follows: QXm represents the corresponding value of the image sharpness index of lens j under the current lighting type m, GXm represents the corresponding value of the light distribution uniformity index of lens j under the current lighting type m, SDm represents the corresponding value of the visual contrast index of lens j under the current lighting type m, VSIjm represents the visual aesthetics coefficient of lens j under the current lighting type m, and w1, w2, and w3 are all preset non-zero scaling coefficients. The formula for calculating the visual aesthetics index is: ;VSIj total This represents the visual aesthetics index of lens j across the entire brightness range.

5. The method for evaluating the assembly effect of a mirror based on the Internet of Things according to claim 4, characterized in that, The logic for obtaining the image sharpness index is as follows: analyze the specular reflection image through image processing algorithms, quantify the sharpness using edge detection, and the corresponding value of the image sharpness index is represented as the average value of the edge intensity; The logic for obtaining the uniformity index of light distribution is as follows: the light intensity at multiple locations on the mirror surface is collected by a light sensor and its root mean square error is calculated. The result obtained is the corresponding value of the uniformity index of light distribution. The logic for obtaining the visual contrast ratio is as follows: in different brightness areas, the contrast is calculated through the brightness difference, specifically using the average brightness difference between bright and dark areas. ;Lm max Lm represents the average brightness of the bright area. min This represents the average brightness of the dark area.

6. The method for evaluating the assembly effect of a mirror based on the Internet of Things according to claim 5, characterized in that, The pre-trained machine learning model is a multinomial regression model.

7. The method for evaluating the assembly effect of a mirror based on the Internet of Things according to claim 6, characterized in that, Based on the degree of fit, lenses used for assembly are divided into two assembly types: high-fit assembly and low-fit assembly. The assembly fit of lens j is compared with the preset assembly fit threshold. If the assembly fit of lens j is greater than or equal to the preset assembly fit threshold, then lens j is classified as a highly fitted assembly type. If the assembly fit of lens j is less than the preset assembly fit threshold, then lens j is classified as a poorly fitted assembly type.

8. A mirror assembly effect evaluation system based on the Internet of Things (IoT), implemented based on the mirror assembly effect evaluation method based on the IoT as described in any one of claims 1-7, characterized in that, include: The information acquisition module collects usage information of the assembled mirror through IoT sensors to obtain a usage information set. The mirror reflection analysis module performs mirror reflection analysis based on the usage information set, and then determines whether there are early signs of incompatibility between the mirror assembly effect and the usage environment based on the mirror reflection analysis results. The feature extraction module extracts light adaptability features and visual aesthetic features from the usage information set when there are early signs that the mirror assembly effect is not compatible with the usage environment, and generates light adaptability index and visual aesthetic index respectively. The single lens type classification module inputs the light adaptability index and visual aesthetics index into the pre-trained machine learning model and outputs the assembly fit degree. Based on the assembly fit degree, the lenses used for assembly are classified into two assembly types: high-fit assembly and low-fit assembly. The assembly optimization module reassembles lenses with low-fit assemblies and re-extracts features until all lenses used for assembly are classified as high-fit assemblies.

Images