Visual test analysis method and system applied to mobile phone display screen

Abstract

The invention discloses a visual test analysis method and system applied to a mobile phone display screen. The method comprises the following steps: constructing a test scheme database, acquiring specification information of a display screen to be tested, formulating a test scheme according to the specification information of the display screen to be tested, and testing according to the formulated test scheme to acquire test monitoring information; based on the test monitoring information, analyzing a visual test index when the target display screen to be tested is subjected to a visual test to obtain visual test index analysis information, and performing visual quality evaluation according to the visual test index analysis information to judge whether a display standard is met or not; and if the target to-be-tested display screen meets the display standard, performing visual comfort evaluation on the target to-be-tested display screen, judging whether the preset display control parameters need to be optimized or not according to a visual comfort evaluation result, and generating a control parameter optimization scheme. And the comprehensiveness of visual testing and the display comfort of the mobile phone display screen are improved, so that the mobile phone display screen can be adjusted more comprehensively.

Description

Technical Field

[0001] The present invention relates to the technical field of display screen testing and analysis, and in particular to a visual testing and analysis method and system applied to a mobile phone display screen. Background Art

[0002] With the rapid development of smartphone screen technology, users' visual experience requirements for display screens are gradually increasing. While providing high resolution and high brightness, if the mobile phone display screen has problems such as excessive flicker, inaccurate color temperature, too high or too low brightness, it is easy to cause visual fatigue and even cause discomfort to users. Traditional mobile phone display screen testing methods mainly focus on testing basic parameters such as color correction, brightness uniformity, contrast and resolution. Although these tests can evaluate the basic performance of the display screen to a certain extent, they do not take into account the comfort needs of the human eye when observing for a long time, and cannot fully reflect the visual effect of the display screen in actual usage scenarios.

[0003] Therefore, how to better conduct comprehensive visual testing and analysis on mobile phone displays while ensuring that basic test parameters meet standards while taking into account the visual comfort of the display is an important issue. Summary of the invention

[0004] The present invention overcomes the defects of the prior art and provides a visual test analysis method and system applied to a mobile phone display screen, the important purpose of which is to improve the comprehensiveness of visual testing and the display comfort of the mobile phone display screen.

[0005] To achieve the above-mentioned purpose, the first aspect of the present invention provides a visual test analysis method applied to a mobile phone display screen, comprising: Constructing a test solution database, obtaining the specification information of the display screen to be tested, formulating a test solution using the test solution database according to the specification information of the display screen to be tested, and performing a test according to the formulated test solution to obtain test monitoring information; Analyze visual test indicators of the target display screen to be tested during visual testing based on the test monitoring information to obtain visual test indicator analysis information, and perform visual quality assessment based on the visual test indicator analysis information to determine whether the display standard is met; If the target display screen to be tested meets the display standard, a visual comfort evaluation is performed on the target display screen to be tested, and based on the visual comfort evaluation result, it is determined whether the preset display control parameters need to be optimized, and a control parameter optimization plan is generated.

[0006] In this solution, the construction of a test solution database, obtaining the specification information of the display screen to be tested, formulating a test solution using the test solution database according to the specification information of the display screen to be tested, and performing a test according to the formulated test solution to obtain the test monitoring information specifically includes: Obtain display specification information, preset test schemes, and display test standard information corresponding to each item in the test scheme corresponding to different models of mobile phone display screens, associate the display specification preset test schemes with the display test standards, and generate a test scheme database; Acquire specification information of the display screen to be tested, perform feature extraction on the specification information of the display screen to be tested, and perform similarity calculation based on the extracted specification features of the display screen to be tested and the display specification information stored in the test solution database; Sorting is performed according to the calculated similarities to obtain a sorting table, the display screen model with the greatest similarity is extracted from the sorting table, a search tag is generated, and a test scheme search is performed in the test scheme database to obtain a number of searched test schemes; Acquire the test requirements of the display screen to be tested, extract the corresponding display test standard from the test solution database based on the retrieved test solution, perform matching analysis with the test requirements of the display screen to be tested to select a final test solution, and obtain final test solution information; A test environment is constructed according to the final test solution information, a target display screen to be tested is placed in the constructed test environment for testing, a test process is set according to the final test solution information to perform visual testing, and test monitoring is performed to obtain test monitoring information.

[0007] In this solution, the visual test index of the target display screen to be tested is analyzed based on the test monitoring information to obtain the visual test index analysis information, specifically including: Acquire test monitoring information, and extract test items based on the test scheme of the target display screen to be tested, wherein the test items are display test modes when the target display screen to be tested is subjected to visual testing; Performing data integration according to the extracted test items in combination with the test monitoring information, associating the test monitoring data of the target display screen to be tested with the corresponding test items, obtaining first analysis information, and performing visual test indicator analysis based on the first analysis information; Extracting test monitoring data of the color test item according to the first analysis information, converting the RGB color space data into the CIE Lab color space, and calculating the Delta E value based on the conversion result; The Delta E value of each color block is used as characteristic data of color reproduction, and the average value is calculated as an evaluation index of the color reproduction degree of the display screen to obtain first index analysis information; A plurality of sampling points are set based on the specification characteristics of the display screen to be tested, the brightness value of each sampling point is obtained through the first analysis information, and the brightness mean and brightness standard deviation of all sampling points are calculated, and the ratio of the brightness standard deviation to the brightness mean is used as the brightness uniformity coefficient to obtain the second indicator analysis information; Extracting the test monitoring data of the resolution test item through the first analysis information, extracting the corresponding test pattern image, performing a two-dimensional Fourier transform on the extracted test pattern image to obtain a spectrum diagram and performing centralization processing; The high-frequency area is extracted according to the spectrum diagram after centralization and the total energy in the high-frequency area is counted. The square sum of the modulus values ​​of the Fourier coefficients in the high-frequency area is calculated as the high-frequency energy. The ratio of the high-frequency energy to the total energy is used as the high-frequency response measure to obtain the third indicator analysis information.

[0008] In this solution, the visual test index of the target display screen to be tested is analyzed based on the test monitoring information to obtain the visual test index analysis information, and further includes: Acquire defect-free display images and defective display images of the target display screen to be tested based on historical data retrieval, and annotate the defect types of the defective display images to form a defect data set; Building a defect detection model based on a generative adversarial network and training the defect detection model using the defect data set, obtaining first analysis information and inputting it into the trained defect detection model for analysis; Introducing a Markov algorithm, performing feature extraction on the first analysis information input to obtain display test monitoring image features, mapping the extracted display test monitoring image features to a low-dimensional latent space and performing sample extraction to generate an initial image; Using the initial image as the starting state input of the Markov chain, defining a state distribution and calculating a state transition probability, generating a latent variable based on the state transition probability, and remapping the generated latent variable to a low-dimensional latent space to obtain a generated image; Calculate the latent variable distribution of the initial image and the generated image in the low-dimensional latent space respectively, obtain the real distribution and the generated distribution and calculate the ratio, and make a judgment and analysis with the preset threshold whether to accept the generated image to obtain the final generated image; The final generated image is used as an input of the generative adversarial network to perform image reconstruction to obtain a reconstructed image, and a reconstruction error between the reconstructed image and the final generated image is calculated to perform defect detection to obtain fourth indicator analysis information; The first indicator analysis information, the second indicator analysis information, the third indicator analysis information and the fourth indicator analysis information are combined to form the visual test indicator analysis information.

[0009] In this solution, the visual quality assessment is performed to determine whether the display standard is met, specifically including: Obtain visual test index analysis information, extract display test standard information of each test item through the test scheme of the target display screen to be tested based on the test scheme database, and construct a visual quality assessment model; Inputting the visual test index analysis information into the visual test index analysis information to perform visual quality assessment, determining the visual quality of the target display screen to be tested in each display test item and display mode, and obtaining visual quality assessment information; Extracting a visual test defect feature of the target display screen to be tested according to the visual quality assessment information, wherein the visual test defect feature is that the visual quality of the target display screen to be tested in a certain display test item or display mode is lower than the corresponding display test standard; A visual test analysis report is generated based on the extracted visual test defect features. If the target display screen to be tested does not have visual test defects, a visual comfort evaluation is performed on the target display screen to be tested.

[0010] In this solution, if the target display screen to be tested meets the display standard, a visual comfort evaluation is performed on the target display screen to be tested, and it is determined whether the preset display control parameters need to be optimized according to the visual comfort evaluation result, and a control parameter optimization solution is generated, which specifically includes: Acquire first analysis information, perform feature extraction on the first analysis information to obtain test monitoring data of the target display screen under different display modes, and obtain first feature information; Define several visual comfort evaluation indicators, use the entropy method to assign the evaluation weights of each visual comfort evaluation indicator and construct visual comfort evaluation rules; Calculating visual data of a corresponding visual comfort evaluation index of the target display screen to be tested in each display mode based on the first feature information, and analyzing a visual comfort score of the target display screen to be tested in each display mode in combination with the visual comfort evaluation rule; Preset a visual comfort threshold for each display mode, judge the visual comfort evaluation of each display mode with the corresponding visual comfort threshold, analyze the display mode with visual discomfort, and obtain second analysis information; Extracting the display mode with visual discomfort and the visual data of the corresponding visual comfort evaluation index according to the second analysis information, performing visual discomfort item analysis, and obtaining visual discomfort item analysis information; According to the visual discomfort analysis information, preset display control parameters of the target display screen to be tested in the corresponding display mode are obtained, visual comfort optimization is performed, a control parameter optimization scheme is generated, and the preset display control parameters are adjusted.

[0011] In this solution, the visual comfort optimization, generation of a control parameter optimization solution and adjustment of preset display control parameters specifically include: Obtaining preset display control parameters of a display mode in which a target display screen to be tested has visual discomfort and display test standard information under the corresponding display mode; Obtain the specification information of the display screen to be tested, combine the display test standard information and the specification information of the display screen to be tested with the simulation software to perform control parameter inversion, analyze the control parameters of the target display screen to be tested when the display test standard is reached, and obtain the display test standard control parameters; The display test standard control parameter is used as the lower limit, and the preset display control parameter of the inappropriate display mode is used as the upper limit to construct the display control parameter optimization limit interval; An optimization model is constructed based on the GA algorithm, a population is initialized according to the display control parameter optimization restriction interval to generate an initialization population, an objective function and constraint conditions are preset, individual fitness in the initial population is calculated according to the objective function, selection, mutation and crossover operations are performed according to the individual fitness to obtain an initial solution; Introducing a taboo search algorithm, taking the initial solution as the input of the taboo search algorithm, initializing parameters and setting a taboo table, generating neighborhood solutions based on neighborhood movement rules, selecting the optimal solution based on the generated neighborhood solutions and obtaining the corresponding fitness value and neighborhood movement, and updating the taboo table; Perform iterative search and update the taboo table to obtain the optimized individuals after the search to update the population, perform iterative optimization based on the updated population, output the optimal solution, generate a control parameter optimization plan based on the optimal solution, and perform feasibility evaluation and comfort evaluation; If the generated control parameter optimization solution is not feasible, the corresponding optimized control parameter combination is marked, new constraints are generated to restrict the optimization model, and the iterative optimization is continued to obtain the next control parameter optimization solution; Obtain several control parameter optimization schemes that meet the feasibility criteria, conduct comfort evaluation on each scheme and sort them according to the comfort score of each scheme, and select the optimized control parameter optimization scheme with the highest comfort score to adjust the target display screen to be tested.

[0012] A second aspect of the present invention provides a visual test analysis system applied to a mobile phone display screen, the system comprising: a memory, a processor, the memory containing a visual test analysis method program applied to a mobile phone display screen, the visual test analysis method program applied to a mobile phone display screen when executed by the processor implements the following steps: Constructing a test solution database, obtaining the specification information of the display screen to be tested, formulating a test solution using the test solution database according to the specification information of the display screen to be tested, and performing a test according to the formulated test solution to obtain test monitoring information; Analyze visual test indicators of the target display screen to be tested during visual testing based on the test monitoring information to obtain visual test indicator analysis information, and perform visual quality assessment based on the visual test indicator analysis information to determine whether the display standard is met; If the target display screen to be tested meets the display standard, a visual comfort evaluation is performed on the target display screen to be tested, and based on the visual comfort evaluation result, it is determined whether the preset display control parameters need to be optimized, and a control parameter optimization plan is generated.

[0013] The present invention discloses a visual test analysis method and system applied to a mobile phone display screen, including: constructing a test scheme database, obtaining the specification information of the display screen to be tested, formulating a test scheme according to the specification information of the display screen to be tested, and testing and obtaining test monitoring information according to the formulated test scheme; analyzing the visual test index when the target display screen to be tested is subjected to a visual test based on the test monitoring information, obtaining the visual test index analysis information, and performing a visual quality assessment according to the visual test index analysis information to determine whether it meets the display standard; if the target display screen to be tested meets the display standard, then performing a visual comfort assessment on the target display screen to be tested, determining whether it is necessary to optimize the preset display control parameters according to the visual comfort assessment result, and generating a control parameter optimization scheme. The comprehensiveness of visual testing and the display comfort of the mobile phone display screen are improved, so that the mobile phone display screen can be adjusted more comprehensively. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] In order to more clearly illustrate the technical solutions in the embodiments or exemplary embodiments of the present invention, the drawings required for use in the embodiments or exemplary descriptions will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained according to the drawings without paying creative work.

[0015] Figure 1 A flow chart of a visual test analysis method applied to a mobile phone display screen provided by an embodiment of the present invention; Figure 2 A flow chart of a method for adjusting visual display parameters of a mobile phone display screen provided by an embodiment of the present invention; Figure 3 A block diagram of a visual test and analysis system applied to a mobile phone display screen provided by an embodiment of 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

[0016] In order to more clearly understand the above-mentioned purpose, features and advantages of the present invention, the present invention is further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be noted that the embodiments of the present application and the features in the embodiments can be combined with each other without conflict.

[0017] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention may also be implemented in other ways different from those described herein. Therefore, the protection scope of the present invention is not limited to the specific embodiments disclosed below.

[0018] Figure 1 A flow chart of a visual test analysis method applied to a mobile phone display screen provided by one embodiment of the present invention; like Figure 1 As shown, the present invention provides a flow chart of a visual test analysis method applied to a mobile phone display screen, comprising: S102: constructing a test solution database, obtaining specification information of the display screen to be tested, formulating a test solution using the test solution database according to the specification information of the display screen to be tested, and performing a test according to the formulated test solution to obtain test monitoring information; S104: analyzing visual test indicators of the target display screen to be tested during visual testing based on the test monitoring information to obtain visual test indicator analysis information, and performing visual quality assessment based on the visual test indicator analysis information to determine whether the display screen meets the display standard; S106: If the target display screen to be tested meets the display standard, a visual comfort evaluation is performed on the target display screen to be tested, and it is determined whether the preset display control parameters need to be optimized according to the visual comfort evaluation result, and a control parameter optimization scheme is generated.

[0019] It should be noted that the present invention provides a visual test analysis method and system applied to a mobile phone display screen, and uses big data retrieval technology to construct a test scheme database, in which display specification information corresponding to different models of mobile phone display screens, preset test schemes, and display test standard information corresponding to each item in the test scheme are stored. Based on the specification information of the display screen to be tested, the test scheme database is combined to formulate a test scheme and obtain the test monitoring information during the test. Subsequently, the visual test indicators are analyzed using the test monitoring information, including color reproduction, brightness uniformity, resolution, and visual defects. Then, the visual test indicators are used to evaluate the visual quality to determine whether the display standard is met. After the evaluation is completed, it is known in detail whether the corresponding display screen to be tested meets the visual test standard. At the same time, the display screen only meets the visual test standard, which may cause discomfort when used. Therefore, it is necessary to evaluate the visual comfort, analyze the indicators of discomfort, and then optimize the preset display control parameters, so as to achieve better visual adjustment of the display screen, ensuring that it can meet the user's high requirements for visual comfort in various display modes.

[0020] Further, in a preferred embodiment of the present invention, the construction of a test solution database, obtaining the specification information of the display screen to be tested, formulating a test solution using the test solution database according to the specification information of the display screen to be tested, and performing a test according to the formulated test solution to obtain the test monitoring information specifically includes: Obtain display specification information, preset test schemes, and display test standard information corresponding to each item in the test scheme corresponding to different models of mobile phone display screens, associate the display specification preset test schemes with the display test standards, and generate a test scheme database; Acquire specification information of the display screen to be tested, perform feature extraction on the specification information of the display screen to be tested, and perform similarity calculation based on the extracted specification features of the display screen to be tested and the display specification information stored in the test solution database; Sorting is performed according to the calculated similarities to obtain a sorting table, the display screen model with the greatest similarity is extracted from the sorting table, a search tag is generated, and a test scheme search is performed in the test scheme database to obtain a number of searched test schemes; Acquire the test requirements of the display screen to be tested, extract the corresponding display test standard from the test solution database based on the retrieved test solution, perform matching analysis with the test requirements of the display screen to be tested to select a final test solution, and obtain final test solution information; A test environment is constructed according to the final test solution information, a target display screen to be tested is placed in the constructed test environment for testing, a test process is set according to the final test solution information to perform visual testing, and test monitoring is performed to obtain test monitoring information.

[0021] It should be noted that, first, by collecting the display specification information, preset test schemes and specific display test standard information of different models of mobile phone display screens, the display specifications, preset test schemes and display test standards are associated to build a test scheme database. Subsequently, the key features are extracted through the specification information of the display screen to be tested, and the similarity is calculated with the display specification information stored in the test scheme database, similar display specifications are screened out and a ranking table is generated based on the similarity results, and the display screen model with the highest similarity is extracted from the ranking table to generate a search tag. The search tag will search for relevant test schemes in the test scheme database, and then obtain several retrieved test schemes. Subsequently, according to the specific test requirements of the display screen to be tested, the corresponding display test standards are extracted from the retrieved test schemes, and the display standards are matched and analyzed with the test requirements of the display screen to be tested, so as to select the most suitable final test scheme and obtain detailed information of the test scheme. After the final test scheme information is generated, a suitable test environment is built according to this information, and the display screen to be tested is placed in the environment for testing. During the test, the corresponding visual test will be performed on the display screen to be tested according to the test process set by the final test plan information, and various test data will be collected and the test monitoring information will be recorded, including important parameters such as brightness, contrast, color performance, and flicker characteristics, for further analysis and optimization.

[0022] Further, in a preferred embodiment of the present invention, the visual test index of the target display screen to be tested is analyzed based on the test monitoring information to obtain the visual test index analysis information, which specifically includes: Acquire test monitoring information, and extract test items based on the test scheme of the target display screen to be tested, wherein the test items are display test modes when the target display screen to be tested is subjected to visual testing; Performing data integration according to the extracted test items in combination with the test monitoring information, associating the test monitoring data of the target display screen to be tested with the corresponding test items, obtaining first analysis information, and performing visual test indicator analysis based on the first analysis information; Extracting test monitoring data of the color test item according to the first analysis information, converting the RGB color space data into the CIE Lab color space, and calculating the Delta E value based on the conversion result; The Delta E value of each color block is used as characteristic data of color reproduction, and the average value is calculated as an evaluation index of the color reproduction degree of the display screen to obtain first index analysis information; A plurality of sampling points are set based on the specification characteristics of the display screen to be tested, the brightness value of each sampling point is obtained through the first analysis information, and the brightness mean and brightness standard deviation of all sampling points are calculated, and the ratio of the brightness standard deviation to the brightness mean is used as the brightness uniformity coefficient to obtain the second indicator analysis information; Extracting the test monitoring data of the resolution test item through the first analysis information, extracting the corresponding test pattern image, performing a two-dimensional Fourier transform on the extracted test pattern image to obtain a spectrum diagram and performing centralization processing; The high-frequency area is extracted according to the spectrum diagram after centralization and the total energy in the high-frequency area is counted. The square sum of the modulus values ​​of the Fourier coefficients in the high-frequency area is calculated as the high-frequency energy. The ratio of the high-frequency energy to the total energy is used as the high-frequency response measure to obtain the third indicator analysis information.

[0023] It should be noted that after the visual test is performed on the display screen to be tested, the corresponding test monitoring information is obtained, and the test monitoring information is used to perform the next step of visual test analysis. Before the visual test analysis, it is necessary to analyze the specific values ​​or data of the corresponding visual test evaluation indicators through the test monitoring information; It should be noted that Delta E is calculated using the CIE76 formula, as follows: ; in, Decibels are the components of standard color and display color in Lab space.

[0024] Further, in a preferred embodiment of the present invention, the visual test index of the target display screen to be tested is analyzed based on the test monitoring information to obtain the visual test index analysis information, and further includes: Acquire defect-free display images and defective display images of the target display screen to be tested based on historical data retrieval, and annotate the defect types of the defective display images to form a defect data set; Building a defect detection model based on a generative adversarial network and training the defect detection model using the defect data set, obtaining first analysis information and inputting it into the trained defect detection model for analysis; Introducing a Markov algorithm, performing feature extraction on the first analysis information input to obtain display test monitoring image features, mapping the extracted display test monitoring image features to a low-dimensional latent space and performing sample extraction to generate an initial image; Using the initial image as the starting state input of the Markov chain, defining a state distribution and calculating a state transition probability, generating a latent variable based on the state transition probability, and remapping the generated latent variable to a low-dimensional latent space to obtain a generated image; Calculate the latent variable distribution of the initial image and the generated image in the low-dimensional latent space respectively, obtain the real distribution and the generated distribution and calculate the ratio, and make a judgment and analysis with the preset threshold whether to accept the generated image to obtain the final generated image; The final generated image is used as an input of the generative adversarial network to perform image reconstruction to obtain a reconstructed image, and a reconstruction error between the reconstructed image and the final generated image is calculated to perform defect detection to obtain fourth indicator analysis information; The first indicator analysis information, the second indicator analysis information, the third indicator analysis information and the fourth indicator analysis information are combined to form the visual test indicator analysis information.

[0025] It should be noted that in the process of visual test analysis, the visual defects of the target display screen to be tested are also an important indicator to measure its quality. A defect detection model is constructed using a generative adversarial network to detect the visual defects of the display screen to be tested, including dark spots and bad spots. The defect detection model is trained with defect-free images obtained through data retrieval. After inputting the real-time visual test image, the model will reconstruct the corresponding image. Since the model only learns defect-free images, it will reconstruct the real-time visual test image into a defect-free image, and then use the reconstruction error between the reconstructed image and the original image to determine the existing visual defects. At the same time, the Markov algorithm is introduced for image enhancement to improve the accuracy of the original image, thereby ensuring the credibility and quality of the final test results and providing a basis for subsequent analysis.

[0026] Furthermore, in a preferred embodiment of the present invention, the visual quality assessment to determine whether the display standard is met specifically includes: Obtain visual test index analysis information, extract display test standard information of each test item through the test scheme of the target display screen to be tested based on the test scheme database, and construct a visual quality assessment model; Inputting the visual test index analysis information into the visual test index analysis information to perform visual quality assessment, determining the visual quality of the target display screen to be tested in each display test item and display mode, and obtaining visual quality assessment information; Extracting a visual test defect feature of the target display screen to be tested according to the visual quality assessment information, wherein the visual test defect feature is that the visual quality of the target display screen to be tested in a certain display test item or display mode is lower than the corresponding display test standard; A visual test analysis report is generated based on the extracted visual test defect features. If the target display screen to be tested does not have visual test defects, a visual comfort evaluation is performed on the target display screen to be tested.

[0027] It should be noted that after obtaining the visual test index analysis information, the display test standard information of each test item is extracted based on the test scheme of the target display screen to be tested by querying the test scheme database. Based on these standard information, a visual quality assessment model is established to evaluate the visual performance of the display screen under different test conditions. After obtaining the visual quality assessment information, the performance of the display screen to be tested under each test item is further analyzed to identify the visual test defect characteristics therein. The visual defect feature refers to the performance of the display screen to be tested under a certain test item or display mode, in which the visual quality is lower than the display test standard defined in the database. The extraction of this feature helps to locate the shortcomings of the display screen in a specific environment or mode, which is convenient for subsequent targeted optimization. After identifying all possible defect features, a visual test analysis report is generated based on this information. The report not only records the visual performance of each test item in detail, but also indicates the specific visual defect features and their corresponding test standards, providing data support for production and quality management. If no visual test defects are found during the evaluation process, it means that the target display screen to be tested meets all display test standards and meets the expected visual quality requirements. In this case, the visual comfort of the target display screen to be tested is further evaluated to ensure that it will not cause discomfort to the user during long-term use. The visual comfort assessment takes into account factors such as flicker, color temperature, and brightness adjustment, and analyzes its comfort performance in different display modes to ensure that the display screen provides a good user experience while maintaining high-quality display effects.

[0028] Further, in a preferred embodiment of the present invention, if the target display screen to be tested meets the display standard, a visual comfort evaluation is performed on the target display screen to be tested, and it is determined whether the preset display control parameters need to be optimized according to the visual comfort evaluation result, and a control parameter optimization scheme is generated, which specifically includes: Acquire first analysis information, perform feature extraction on the first analysis information to obtain test monitoring data of the target display screen to be tested in different display modes, and obtain first feature information; Define several visual comfort evaluation indicators, use the entropy method to assign the evaluation weights of each visual comfort evaluation indicator and construct visual comfort evaluation rules; Calculating visual data of a corresponding visual comfort evaluation index of the target display screen to be tested in each display mode based on the first feature information, and analyzing a visual comfort score of the target display screen to be tested in each display mode in combination with the visual comfort evaluation rule; Preset a visual comfort threshold for each display mode, judge the visual comfort evaluation of each display mode with the corresponding visual comfort threshold, analyze the display mode with visual discomfort, and obtain second analysis information; Extracting the display mode with visual discomfort and the visual data of the corresponding visual comfort evaluation index according to the second analysis information, performing visual discomfort item analysis, and obtaining visual discomfort item analysis information; According to the visual discomfort analysis information, preset display control parameters of the target display screen to be tested in the corresponding display mode are obtained, visual comfort optimization is performed, a control parameter optimization scheme is generated, and the preset display control parameters are adjusted.

[0029] It should be noted that the test monitoring data of the display screen under different display modes is extracted through the first analysis information, and feature extraction is performed to form the first feature information, which describes the characteristic performance of the display screen to be tested under different display conditions, laying a data foundation for the subsequent comfort analysis. Next, several visual comfort evaluation indicators are defined to comprehensively cover the visual comfort performance of the display screen, such as brightness uniformity, color consistency, flicker frequency, blue light intensity and other factors affecting visual comfort. In order to achieve accurate indicator weight allocation, the entropy method is used to assign evaluation weights to each visual comfort evaluation indicator, and the visual comfort evaluation rules are constructed based on this. The entropy method helps to reasonably allocate weights according to the degree of variation of each indicator, so that high-variability indicators occupy a more important position in the evaluation, thereby improving the objectivity and accuracy of the comfort evaluation. Based on the first feature information, the visual comfort evaluation indicators under each display mode are calculated, and the corresponding visual data, such as the brightness uniformity coefficient and flicker frequency value under each mode, are extracted. Combined with the established visual comfort evaluation rules, the visual comfort score of each display mode is analyzed item by item and obtained. Subsequently, it is verified whether the visual comfort meets the standard, and the visual comfort threshold of each display mode is pre-set. The visual comfort score of each mode is compared with its threshold to identify the display mode that may have visual discomfort and obtain the corresponding second analysis information. The second analysis information contains a list of modes that do not meet the comfort requirements and their corresponding visual comfort evaluation data, indicating problems in visual comfort. According to the second analysis information, the display mode with visual discomfort and the visual data of the corresponding comfort evaluation index are extracted, and each discomfort item is analyzed in detail to generate visual discomfort item analysis information. This information provides specific causes of discomfort, such as uneven brightness and excessive flicker frequency in a certain mode, to provide guidance for optimization. After obtaining the visual discomfort item analysis information, the parameters are adjusted according to the preset display control parameters of each display mode to improve visual comfort. By analyzing the causes and effects of the discomfort items, an optimization plan is generated to propose specific control parameter adjustment suggestions, such as lowering the blue light intensity or optimizing the brightness distribution. Finally, the optimized control parameters are applied to the preset display control settings of the display screen to improve visual comfort and ensure a comfortable visual experience in different display modes.

[0030] Furthermore, in a preferred embodiment of the present invention, the visual comfort optimization, generating a control parameter optimization scheme and adjusting the preset display control parameters specifically include: Obtaining preset display control parameters of a display mode in which a target display screen to be tested has visual discomfort and display test standard information under the corresponding display mode; Obtain the specification information of the display screen to be tested, combine the display test standard information and the specification information of the display screen to be tested with the simulation software to perform control parameter inversion, analyze the control parameters of the target display screen to be tested when the display test standard is reached, and obtain the display test standard control parameters; The display test standard control parameter is used as the lower limit, and the preset display control parameter of the inappropriate display mode is used as the upper limit to construct the display control parameter optimization limit interval; An optimization model is constructed based on the GA algorithm, a population is initialized according to the display control parameter optimization restriction interval to generate an initialization population, an objective function and constraint conditions are preset, individual fitness in the initial population is calculated according to the objective function, selection, mutation and crossover operations are performed according to the individual fitness to obtain an initial solution; Introducing a taboo search algorithm, taking the initial solution as the input of the taboo search algorithm, initializing parameters and setting a taboo table, generating neighborhood solutions based on neighborhood movement rules, selecting the optimal solution based on the generated neighborhood solutions and obtaining the corresponding fitness value and neighborhood movement, and updating the taboo table; Perform iterative search and update the taboo table to obtain the optimized individuals after the search to update the population, perform iterative optimization based on the updated population, output the optimal solution, generate a control parameter optimization plan based on the optimal solution, and perform feasibility evaluation and comfort evaluation; if the generated control parameter optimization plan is infeasible, mark the corresponding optimized control parameter combination, generate new constraints to restrict the optimization model, and continue iterative optimization to obtain the next control parameter optimization plan; Obtain several control parameter optimization schemes that meet the feasibility criteria, conduct comfort evaluation on each scheme and sort them according to the comfort score of each scheme, and select the optimized control parameter optimization scheme with the highest comfort score to adjust the target display screen to be tested.

[0031] It should be noted that in the specific process of display control parameter optimization, the display test standard control parameters are used as the lower limit, the preset display control parameters of the display mode with inappropriate items are used as the upper limit, and the display control parameter optimization limit interval is constructed. The genetic algorithm (GA) is used to construct the optimization model, and the population is initialized based on the display control parameter optimization limit interval to generate an initial population containing different control parameter combinations. The objective function (such as improving visual comfort) and setting constraints (such as the operable range of parameters) are defined, and the fitness of the individuals in the initial population is calculated to determine its optimization effect. Based on the fitness evaluation, selection, mutation and crossover operations are performed to generate an initial solution with potential optimization effect. In order to further improve the optimization efficiency and avoid the trouble of local optimal solutions, the taboo search algorithm is introduced. The initial solution generated by the GA algorithm is used as input, and the taboo table and neighborhood movement rules are set through taboo search. The taboo search algorithm generates neighborhood solutions, evaluates the fitness value of each solution and performs updates, so that the taboo table records solutions that are not allowed to be repeatedly visited in each round of iteration, ensuring that the search process is more extensive and in-depth. The taboo table and population are updated through multiple iterations, and gradually converge to the global optimal solution. After obtaining the optimal solution, a control parameter optimization scheme is generated based on the solution, and a feasibility evaluation and comfort evaluation are performed. If the scheme is judged to be infeasible in the evaluation, the corresponding optimization control parameter combination will be marked as a taboo state, and new constraints will be generated to rebuild the optimization model and continue to iterate. This process ensures the practicality and effectiveness of the final scheme and avoids adverse effects in actual adjustments. After multiple rounds of optimization and screening, multiple control parameter optimization schemes that meet the feasibility criteria are generated. These schemes are scored for comfort and sorted from high to low according to the scores to ensure the optimal visual comfort. Finally, the optimized control parameter scheme with the highest comfort score is selected and applied to the actual adjustment of the target display screen to be tested, so that it exhibits the best visual comfort in all display modes.

[0032] Figure 2 A flow chart of a method for adjusting visual display parameters of a mobile phone display screen provided by an embodiment of the present invention; like Figure 2 As shown, the present invention provides a flow chart of a method for adjusting visual display parameters of a mobile phone display screen, comprising: S202, calculating the visual data of the corresponding visual comfort evaluation index of the target display screen to be tested in each display mode, and analyzing the visual comfort score of the target display screen to be tested in each display mode in combination with the visual comfort evaluation rule; S204, judging the visual comfort evaluation of each display mode with the corresponding visual comfort threshold, analyzing the display mode with visual discomfort, and obtaining second analysis information; S206, extracting the display mode with visual discomfort and the visual data of the corresponding visual comfort evaluation index according to the second analysis information, performing visual discomfort item analysis, and obtaining visual discomfort item analysis information; S208, obtaining preset display control parameters of the target display screen to be tested in the corresponding display mode according to the visual discomfort analysis information, and analyzing the control parameters of the target display screen to be tested when the display test standard is reached to obtain the display test standard control parameters; S210, constructing a display control parameter optimization restriction interval based on the display test standard control parameters and the preset display control parameters, and formulating an optimization plan using an optimization model.

[0033] In addition, in a visual test analysis method applied to a mobile phone display screen provided by the present invention, the following steps are also included: Obtain display screen specification information, test monitoring information, visual discomfort analysis information, and control parameter optimization scheme of the target display screen to be tested, extract specification features of the target display screen based on the display screen specification information, and obtain specification feature information; The test monitoring information and the visual discomfort item analysis information are extracted respectively, and a feature matrix with the visual discomfort items as categories is constructed according to the extracted features to obtain category feature information; The category feature information, specification feature information and control parameter optimization scheme are associated to generate a knowledge graph with specification feature-category feature-control parameter optimization scheme as entity triples; When the mobile phone display screen is tested next time, the specification features, test monitoring features and visual discomfort items of the corresponding display screen are input into the knowledge graph and the corresponding control parameter optimization scheme is obtained using the cosine metric algorithm; If there is no control parameter optimization solution that is compatible with the display screen that needs to be optimized in the knowledge graph, a new control parameter optimization solution is formulated using the optimization model and the knowledge graph is updated.

[0034] It should be noted that for display screens with visual discomfort, the corresponding specification features are used as prior conditions, and the test monitoring information and visual discomfort items during the visual test are used to form a category feature matrix, that is, a feature portrait, thereby generating a knowledge graph with specification features-category features-control parameter optimization scheme as entity triples. The next time the visual test is performed, the efficiency and intelligence of display control parameter optimization can be improved.

[0035] Figure 3A visual test analysis system 3 applied to a mobile phone display screen is provided in one embodiment of the present invention. The system comprises: a memory 31 and a processor 32. The memory 31 contains a visual test analysis method program applied to a mobile phone display screen. When the visual test analysis method program applied to a mobile phone display screen is executed by the processor 32, the following steps are implemented: Constructing a test solution database, obtaining the specification information of the display screen to be tested, formulating a test solution using the test solution database according to the specification information of the display screen to be tested, and performing a test according to the formulated test solution to obtain test monitoring information; Analyze visual test indicators of the target display screen to be tested during visual testing based on the test monitoring information to obtain visual test indicator analysis information, and perform visual quality assessment based on the visual test indicator analysis information to determine whether the display standard is met; If the target display screen to be tested meets the display standard, a visual comfort evaluation is performed on the target display screen to be tested, and based on the visual comfort evaluation result, it is determined whether the preset display control parameters need to be optimized, and a control parameter optimization plan is generated.

[0036] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as: multiple units or components can be combined, or can be integrated into another system, or some features can be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the components shown or discussed can be through some interfaces, and the indirect coupling or communication connection of the devices or units can be electrical, mechanical or other forms.

[0037] The units described above as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units; they may be located in one place or distributed on multiple network units; some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0038] In addition, all functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may be separately used as a unit, or two or more units may be integrated into one unit; the above-mentioned integrated units may be implemented in the form of hardware or in the form of hardware plus software functional units.

[0039] A person of ordinary skill in the art can understand that: all or part of the steps of implementing the above method embodiment can be completed by hardware related to program instructions, and the aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it executes the steps of the above method embodiment; and the aforementioned storage medium includes: a mobile storage device, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and other media that can store program codes.

[0040] Alternatively, if the above-mentioned integrated unit of the present invention is implemented in the form of a software function module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the embodiment of the present invention can be essentially or partly reflected in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the methods described in each embodiment of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as mobile storage devices, ROM, RAM, magnetic disks or optical disks.

[0041] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. A visual test analysis method applied to a mobile phone display screen, characterized in that: include: Constructing a test solution database, obtaining the specification information of the display screen to be tested, formulating a test solution using the test solution database according to the specification information of the display screen to be tested, and performing a test according to the formulated test solution to obtain test monitoring information; Analyze visual test indicators of the target display screen to be tested during visual testing based on the test monitoring information to obtain visual test indicator analysis information, and perform visual quality assessment based on the visual test indicator analysis information to determine whether the display standard is met; If the target display screen to be tested meets the display standard, a visual comfort evaluation is performed on the target display screen to be tested, and based on the visual comfort evaluation result, it is determined whether the preset display control parameters need to be optimized, and a control parameter optimization plan is generated.

2. A visual test analysis method for a mobile phone display screen according to claim 1, characterized in that: The step of constructing a test solution database, obtaining the specification information of the display screen to be tested, formulating a test solution using the test solution database according to the specification information of the display screen to be tested, and performing a test according to the formulated test solution to obtain the test monitoring information specifically includes: Obtain display specification information, preset test schemes, and display test standard information corresponding to each item in the test scheme corresponding to different models of mobile phone display screens, associate the display specification preset test schemes with the display test standards, and generate a test scheme database; Acquire specification information of the display screen to be tested, perform feature extraction on the specification information of the display screen to be tested, and perform similarity calculation based on the extracted specification features of the display screen to be tested and the display specification information stored in the test solution database; Sorting is performed according to the calculated similarities to obtain a sorting table, the display screen model with the greatest similarity is extracted from the sorting table, a search tag is generated, and a test scheme search is performed in the test scheme database to obtain a number of searched test schemes; Acquire the test requirements of the display screen to be tested, extract the corresponding display test standard from the test solution database based on the retrieved test solution, perform matching analysis with the test requirements of the display screen to be tested to select a final test solution, and obtain final test solution information; A test environment is constructed according to the final test solution information, a target display screen to be tested is placed in the constructed test environment for testing, a test process is set according to the final test solution information to perform visual testing, and test monitoring is performed to obtain test monitoring information.

3. The visual testing and analysis method for a mobile phone display screen according to claim 1, characterized in that: The step of analyzing the visual test indicators of the target display screen to be tested based on the test monitoring information to obtain the visual test indicator analysis information specifically includes: Acquire test monitoring information, and extract test items based on the test scheme of the target display screen to be tested, wherein the test items are display test modes when the target display screen to be tested is subjected to visual testing; Performing data integration according to the extracted test items in combination with the test monitoring information, associating the test monitoring data of the target display screen to be tested with the corresponding test items, obtaining first analysis information, and performing visual test indicator analysis based on the first analysis information; Extracting test monitoring data of the color test item according to the first analysis information, converting the RGB color space data into the CIE Lab color space, and calculating the Delta E value based on the conversion result; The Delta E value of each color block is used as characteristic data of color reproduction, and the average value is calculated as an evaluation index of the color reproduction degree of the display screen to obtain first index analysis information; A plurality of sampling points are set based on the specification characteristics of the display screen to be tested, the brightness value of each sampling point is obtained through the first analysis information, and the brightness mean and brightness standard deviation of all sampling points are calculated, and the ratio of the brightness standard deviation to the brightness mean is used as the brightness uniformity coefficient to obtain the second indicator analysis information; Extracting the test monitoring data of the resolution test item through the first analysis information, extracting the corresponding test pattern image, performing a two-dimensional Fourier transform on the extracted test pattern image to obtain a spectrum diagram and performing centralization processing; The high-frequency area is extracted according to the spectrum diagram after centralization and the total energy in the high-frequency area is counted. The square sum of the modulus values ​​of the Fourier coefficients in the high-frequency area is calculated as the high-frequency energy. The ratio of the high-frequency energy to the total energy is used as the high-frequency response measure to obtain the third indicator analysis information.

4. The visual testing and analysis method for a mobile phone display screen according to claim 1, characterized in that: The step of analyzing the visual test indicators of the target display screen to be tested based on the test monitoring information to obtain the visual test indicator analysis information further includes: Acquire defect-free display images and defective display images of the target display screen to be tested based on historical data retrieval, and annotate the defect types of the defective display images to form a defect data set; Building a defect detection model based on a generative adversarial network and training the defect detection model using the defect data set, obtaining first analysis information and inputting it into the trained defect detection model for analysis; Introducing a Markov algorithm, performing feature extraction on the first analysis information input to obtain display test monitoring image features, mapping the extracted display test monitoring image features to a low-dimensional latent space and performing sample extraction to generate an initial image; Using the initial image as the starting state input of the Markov chain, defining a state distribution and calculating a state transition probability, generating a latent variable based on the state transition probability, and remapping the generated latent variable to a low-dimensional latent space to obtain a generated image; Calculate the latent variable distribution of the initial image and the generated image in the low-dimensional latent space respectively, obtain the real distribution and the generated distribution and calculate the ratio, and make a judgment and analysis with the preset threshold whether to accept the generated image to obtain the final generated image; The final generated image is used as an input of the generative adversarial network to perform image reconstruction to obtain a reconstructed image, and a reconstruction error between the reconstructed image and the final generated image is calculated to perform defect detection to obtain fourth indicator analysis information; The first indicator analysis information, the second indicator analysis information, the third indicator analysis information and the fourth indicator analysis information are combined to form the visual test indicator analysis information.

5. The visual testing and analysis method for a mobile phone display screen according to claim 1, characterized in that: The visual quality assessment is performed to determine whether the display standard is met, specifically including: Obtain visual test index analysis information, extract display test standard information of each test item through the test scheme of the target display screen to be tested based on the test scheme database, and construct a visual quality assessment model; Inputting the visual test index analysis information into the visual test index analysis information to perform visual quality assessment, determining the visual quality of the target display screen to be tested in each display test item and display mode, and obtaining visual quality assessment information; Extracting a visual test defect feature of the target display screen to be tested according to the visual quality assessment information, wherein the visual test defect feature is that the visual quality of the target display screen to be tested in a certain display test item or display mode is lower than the corresponding display test standard; A visual test analysis report is generated based on the extracted visual test defect features. If the target display screen to be tested does not have visual test defects, a visual comfort evaluation is performed on the target display screen to be tested.

6. The visual testing and analysis method for a mobile phone display screen according to claim 1, characterized in that: If the target display screen to be tested meets the display standard, a visual comfort evaluation is performed on the target display screen to be tested, and it is determined whether the preset display control parameters need to be optimized according to the visual comfort evaluation result, and a control parameter optimization scheme is generated, which specifically includes: Acquire first analysis information, perform feature extraction on the first analysis information to obtain test monitoring data of the target display screen to be tested in different display modes, and obtain first feature information; Define several visual comfort evaluation indicators, use the entropy method to assign the evaluation weights of each visual comfort evaluation indicator and construct visual comfort evaluation rules; Calculating visual data of a corresponding visual comfort evaluation index of the target display screen to be tested in each display mode based on the first feature information, and analyzing a visual comfort score of the target display screen to be tested in each display mode in combination with the visual comfort evaluation rule; Preset a visual comfort threshold for each display mode, judge the visual comfort evaluation of each display mode with the corresponding visual comfort threshold, analyze the display mode with visual discomfort, and obtain second analysis information; Extracting the display mode with visual discomfort and the visual data of the corresponding visual comfort evaluation index according to the second analysis information, performing visual discomfort item analysis, and obtaining visual discomfort item analysis information; According to the visual discomfort analysis information, preset display control parameters of the target display screen to be tested in the corresponding display mode are obtained, visual comfort optimization is performed, a control parameter optimization scheme is generated, and the preset display control parameters are adjusted.

7. A visual test and analysis method for a mobile phone display screen according to claim 6, characterized in that: The visual comfort optimization, generating a control parameter optimization scheme and adjusting preset display control parameters specifically include: Obtaining preset display control parameters of a display mode in which a target display screen to be tested has visual discomfort and display test standard information under the corresponding display mode; Obtain the specification information of the display screen to be tested, combine the display test standard information and the specification information of the display screen to be tested with the simulation software to perform control parameter inversion, analyze the control parameters of the target display screen to be tested when the display test standard is reached, and obtain the display test standard control parameters; The display test standard control parameter is used as the lower limit, and the preset display control parameter of the inappropriate display mode is used as the upper limit to construct the display control parameter optimization limit interval; An optimization model is constructed based on the GA algorithm, a population is initialized according to the display control parameter optimization restriction interval to generate an initialization population, an objective function and constraint conditions are preset, individual fitness in the initial population is calculated according to the objective function, selection, mutation and crossover operations are performed according to the individual fitness to obtain an initial solution; Introducing a taboo search algorithm, taking the initial solution as the input of the taboo search algorithm, initializing parameters and setting a taboo table, generating neighborhood solutions based on neighborhood movement rules, selecting the optimal solution based on the generated neighborhood solutions and obtaining the corresponding fitness value and neighborhood movement, and updating the taboo table; Perform iterative search and update the taboo table to obtain the optimized individuals after the search to update the population, perform iterative optimization based on the updated population, output the optimal solution, generate a control parameter optimization plan based on the optimal solution, and perform feasibility evaluation and comfort evaluation; If the generated control parameter optimization solution is not feasible, the corresponding optimized control parameter combination is marked, new constraints are generated to restrict the optimization model, and the iterative optimization is continued to obtain the next control parameter optimization solution; Obtain several control parameter optimization schemes that meet the feasibility criteria, conduct comfort evaluation on each scheme and sort them according to the comfort score of each scheme, and select the optimized control parameter optimization scheme with the highest comfort score to adjust the target display screen to be tested.

8. A visual test and analysis system for a mobile phone display screen, characterized in that: The system includes: a memory and a processor, wherein the memory contains a visual test analysis method program applied to a mobile phone display screen, and when the visual test analysis method program applied to a mobile phone display screen is executed by the processor, the following steps are implemented: Constructing a test solution database, obtaining the specification information of the display screen to be tested, formulating a test solution using the test solution database according to the specification information of the display screen to be tested, and performing a test according to the formulated test solution to obtain test monitoring information; Analyze visual test indicators of the target display screen to be tested during visual testing based on the test monitoring information to obtain visual test indicator analysis information, and perform visual quality assessment based on the visual test indicator analysis information to determine whether the display standard is met; If the target display screen to be tested meets the display standard, a visual comfort evaluation is performed on the target display screen to be tested, and based on the visual comfort evaluation result, it is determined whether the preset display control parameters need to be optimized, and a control parameter optimization plan is generated.

Images