Mobile phone screen testing method, device, equipment and medium

Through the combination of machine vision positioning and association algorithm models, the problem of inefficient screen testing of existing mobile phones is solved, efficient and intelligent screen quality detection and abnormal traceability are achieved, and the management level of the production process is improved.

CN120343132AInactive Publication Date: 2025-07-18SHENZHEN SHENGSHI WEIYE OPTOELECTRONICS CO LTD
View PDF 0 Cites 1 Cited by

Patent Information

Application Number
CN202510666487.5
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2025-05-22
Publication Date
2025-07-18
Estimated Expiration
Not applicable · inactive patent

AI Technical Summary

Technical Problem

The existing mobile phone screen testing methods are inefficient, unable to quickly locate the causes of abnormalities, lack the ability to analyze the correlation between raw materials, equipment status and environmental parameters in the production process, and cannot achieve intelligent prediction and traceability.

Method used

Machine vision positioning technology is used to capture the screen to be tested, display and touch function tests are performed, production process data sets are obtained, correlation results are generated based on the association algorithm model, equipment control parameters are determined, and unique identification code is recorded.

Benefits of technology

It improves the reliability and stability of the test, comprehensively detects screen performance, realizes abnormal traceability and intelligent production management, and reduces the defective yield rate.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN120343132A_ABST
    Figure CN120343132A_ABST
Patent Text Reader

Abstract

The invention relates to a mobile phone screen testing method and device, equipment and a medium, and the mobile phone screen testing method comprises the steps: lightening a to-be-tested screen, and executing a display function test and a touch function test on the to-be-tested screen to generate a corresponding test result; acquiring a production process data set; based on the established association algorithm model, generating a corresponding association result according to the test result and the production process data set; and determining corresponding associated screens and equipment control parameters, generating and recording a unique identification code for each associated screen, and judging whether to execute retest operation of the associated screens. The display performance and the touch performance of the screen are comprehensively detected, so that the potential quality problem of the screen is effectively found; production related data are collected in time, a basis is provided for anomaly analysis, and therefore the anomaly traceability is improved; and associated factors and potential risks of the abnormal screen can be quickly identified, so that intelligent production process management and problem prediction can be realized.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of screen testing, and particularly to a mobile phone screen testing method, device, equipment and medium. Background Art

[0002] At present, with the wide application of smart phones and the rapid development of technology, the mobile phone screen, as a core component of the user experience, its quality inspection is particularly important. In order to ensure that the display function and touch function of the mobile phone screen meet the quality requirements, it is usually necessary to conduct functional tests on the screen.

[0003] Existing mobile phone screen testing methods usually detect the display performance and touch performance through separate functional modules. For example, artificial or image devices are used to detect the brightness, color accuracy and display abnormal points of the screen, and touch devices are used to detect the touch sensitivity and response accuracy of the screen. However, these methods have many deficiencies in practical applications, including low efficiency in the testing process, inability to quickly locate the specific reasons for abnormal screens, and insufficient ability to analyze the correlation of factors such as raw material batches, equipment status and environmental parameters in the production process. In addition, when an abnormality is detected, the existing methods lack the ability to dynamically adjust the operating parameters of the production equipment, and also cannot achieve intelligent prediction and traceability analysis of other potentially high-risk screens. Summary of the Invention

[0004] In order to solve the problems of inability to achieve the high efficiency, intelligence and abnormal traceability of the mobile phone screen testing process, the present application provides a mobile phone screen testing method, device, equipment and medium.

[0005] The first above-mentioned invention object of the present application is achieved through the following technical solutions: A mobile phone screen testing method, the mobile phone screen testing method includes: Based on the machine vision positioning technology, locate and grab the screen to be tested to the test bench; Light up the screen to be tested, and perform display function testing and touch function testing on the screen to be tested to generate corresponding test results; If the test result is that the screen is abnormal, obtain the production process data set; Based on the established correlation algorithm model, generate corresponding correlation results according to the test result and the production process data set; According to the correlation result, determine the corresponding correlation screen and device control parameters, the device control parameters at least include alarm parameters and operation adjustment parameters, generate and record a unique identification code for each of the correlation screens, and determine whether to perform the retest operation on the correlation screens.

[0006] By adopting the above technical solution, the to-be-tested screen is located and grabbed to the test bench based on the machine vision positioning technology, so that the position of the to-be-tested screen can be accurately located, the accuracy of the docking between the test device and the screen can be ensured, and the reliability and stability of the test can be improved; by lighting the to-be-tested screen and performing a display function test and a touch function test on the to-be-tested screen to generate corresponding test results, the display performance and touch performance of the screen can be comprehensively detected, and potential quality problems of the screen can be effectively discovered; by obtaining the production process data set if the test result is that the screen is abnormal, production-related data can be collected in time, providing a basis for anomaly analysis, and the anomaly tracing ability can be improved; by generating corresponding correlation results based on the established correlation algorithm model according to the test results and the production process data set, the correlation factors and potential risks of the abnormal screen can be quickly identified, and intelligent production process management and problem prediction can be realized.

[0007] In a preferred example of the present application, it can be further configured that: in the step of lighting the to-be-tested screen and performing a display function test and a touch function test on the to-be-tested screen to generate corresponding test results, the test results include a display test result and a touch test result, and the step further includes: Initializing the circuit module of the to-be-tested screen to make the to-be-tested screen enter a testable state, sending a lighting instruction to the to-be-tested screen to make the to-be-tested screen display a predetermined test image, and the test image includes a single-color image, a gradient-color image, and a complex pattern image; Based on an image capture device, the test image of the to-be-tested screen is captured in real time, and the captured test image is analyzed based on an image processing algorithm to generate corresponding display performance parameters, and the display performance parameters include a brightness parameter, a color accuracy parameter, and an abnormal point parameter, and it is determined whether the display performance parameters are qualified; If the display performance parameters are unqualified, it is determined that the display test result of the display function test is that the screen is abnormal; If the display performance parameters are qualified, touch signals are applied to different areas of the to-be-tested screen by simulating touch operations, and then corresponding touch performance parameters are generated, and the touch performance parameters include a response sensitivity parameter, a multi-touch function parameter, and a touch accuracy parameter, and it is determined whether the touch performance parameters are qualified; If the touch performance parameters are unqualified, it is determined that the touch test result of the touch function test is that the screen is abnormal; If the touch performance parameters are qualified, it is determined that both the display test result and the touch test result are that the screen is normal.

[0008] By adopting the above technical solutions, by initializing the circuit module of the screen to be tested, the screen to be tested is brought into a testable state, and a lighting instruction is sent to the screen to be tested to make the screen to be tested display a predetermined test image, which can ensure that the screen to be tested is in a normal working state, thereby providing a stable test environment for subsequent tests; by based on an image capture device, the test image of the screen to be tested is captured in real time, and the captured test image is analyzed based on an image processing algorithm to generate corresponding display performance parameters, the key indicators of the screen display performance can be accurately obtained, thereby accurately judging the display quality of the screen; by if the display performance parameters are unqualified, it is determined that the display test result of the display function test is that the screen is abnormal, the abnormal display screen can be marked in time, thereby effectively preventing unqualified screens from flowing into subsequent links; by if the display performance parameters are qualified, touch signals are applied to different areas of the screen to be tested by simulating touch operations, and then corresponding touch performance parameters are generated, the performance of the screen in various touch scenarios can be verified, thereby ensuring the reliability of the touch function; by if the touch performance parameters are unqualified, it is determined that the touch test result of the touch function test is that the screen is abnormal, the touch performance problems can be found in time, thereby improving the accuracy and comprehensiveness of the screen test.

[0009] In a preferred example of the present application, it can be further configured that: in the step of obtaining the production process data set if the test result is that the screen is abnormal, it includes: If the test result is that the screen is abnormal, it is determined that the screen to be tested that has passed the display function test and the touch function test is the target screen; Obtain the product serial number of the target screen and trace the corresponding raw material batch data; Obtain the device operation status data used by the target screen during the production process; Obtain the production environment data of various indicators of the production environment of the target screen during the production process; Perform feature extraction on the raw material batch data, the device operation status data, and the production environment data, convert the extracted key data into standardized data that can be directly calculated by the established association algorithm model, and integrate each standardized data to generate the production process data set.

[0010] By adopting the above technical solution, if the test result indicates a screen anomaly, it is determined that the screen to be tested that has undergone the display function test and the touch function test is the target screen, which can quickly locate the screen with anomalies, thereby providing an accurate basis for subsequent traceability and handling; by obtaining the product serial number of the target screen and tracing the corresponding raw material batch data, the screen anomaly can be associated with the raw material quality problem, thereby providing data support for the root cause analysis of the abnormal screen; by obtaining the equipment operation status data used in the production process of the target screen, the potential impact of the production equipment on the screen quality can be obtained, thereby improving the accuracy of the correlation analysis between the equipment operation parameters and the quality; by obtaining the production environment data of various indicators of the production environment during the production process of the target screen, the impact of environmental factors on the screen quality can be identified, thereby effectively reducing the interference of environmental anomalies on the screen quality; by performing feature extraction on the raw material batch data, the equipment operation status data, and the production environment data, and converting the extracted key data into standardized data that can be directly calculated by the established correlation algorithm model, and integrating each standardized data to generate the production process data set, the standardization of the input data and the accuracy of the model calculation can be ensured, thereby providing a reliable data basis for intelligent analysis.

[0011] In a preferred example of the present application, it can be further configured that in the step of generating the corresponding association result based on the established association algorithm model according to the test result and the production process data set, it includes: Substitute the test result and the production process data set into the established association algorithm model to generate the corresponding feature vector; Match the corresponding historical training data according to the feature vector; Call the association rule derivation module in the association algorithm model to derive at least the corresponding association rule and dynamic adjustment rule according to the historical training data; Integrate the association rule and the dynamic adjustment rule to generate the corresponding association result.

[0012] By adopting the above technical solution, by substituting the test results and the production process data set into the established correlation algorithm model to generate corresponding feature vectors, the core features in the screen test and the production process can be extracted, thus laying a foundation for intelligent analysis; by matching the corresponding historical training data according to the feature vectors, similarity analysis can be carried out with the help of historical data, thus improving the accuracy of abnormal problem analysis; by calling the correlation rule derivation module in the correlation algorithm model and at least deriving the corresponding correlation rules and dynamic adjustment rules according to the historical training data, the causal relationship and adjustment strategy between the screen abnormality and the production process can be automatically generated, thus improving the intelligent level of the production line; by integrating the correlation rules and the dynamic adjustment rules to generate corresponding correlation results, comprehensive guidance can be provided for subsequent production adjustment and screen abnormality prediction, thus optimizing the production process and reducing the defective product rate.

[0013] In a preferred example of the present application, it can be further configured that: in the step of determining the corresponding associated screen and device control parameters according to the correlation result, it includes: Determine the to-be-tested screen in the same batch as the target screen as the first-level key screen, and determine the to-be-tested screens in the adjacent batches to the target screen as the second-level key screens; According to the correlation rule, perform abnormal risk prediction on the first-level key screen and the second-level key screen to generate corresponding prediction results, and judge whether each of the first-level key screens and / or each of the second-level key screens is an associated screen according to the prediction results; After configuring the corresponding correlation weights for each of the standardized data according to the dynamic adjustment rule, calculate the sum of the products of each of the standardized data and the correlation weights, and then generate a corresponding calculation result, and determine the corresponding device control parameters according to the calculation result.

[0014] By adopting the above technical solution, by determining the to-be-tested screens in the same batch as the target screen as the first-level critical screens and the to-be-tested screens in adjacent batches to the target screen as the second-level critical screens, the associated range of abnormal screens can be clarified, so as to achieve accurate traceability and hierarchical management; by predicting the abnormal risks of the first-level critical screens and the second-level critical screens according to the association rules and generating corresponding prediction results, potential high-risk screens can be predicted, thus reducing the batch production of defective products caused by abnormal diffusion; by calculating the sum of the products of each standardized data and the associated weight after configuring the corresponding associated weight for each standardized data according to the dynamic adjustment rule, and then generating the corresponding calculation result, the impact of associated data on screen abnormality can be quantified, thus providing a scientific basis for the optimization of equipment control parameters; by determining the corresponding equipment control parameters according to the calculation result, the operating state of the production equipment can be adjusted in real time, thus effectively reducing the incidence of production abnormalities.

[0015] In a preferred example of the present application, it can be further configured as follows: in the step of generating and recording a unique identification code for each of the associated screens and determining whether to perform the retest operation on the associated screens, it includes: Determine the degree of association of each of the associated screens according to the prediction result; Classify each of the associated screens according to the degree of association to determine different screen sets; Assign a front-segment code to each of the screen sets and assign a back-segment code to each of the associated screens in the screen sets; Integrate the front-segment code and the back-segment code to generate and record a unique identification code; Judge whether to perform the retest operation on the associated screens according to the unique identification code.

[0016] By adopting the above technical solution, by determining the degree of association of each of the associated screens according to the prediction result, the relationship between the screen and the abnormality can be quantified, thereby providing a basis for further classification management; by classifying each of the associated screens according to the degree of association to determine different screen sets, the grouped management of the screens can be realized, thereby improving the processing efficiency of abnormal screens; by assigning a front-end code to each of the screen sets and assigning a back-end code to each of the associated screens in the screen set, the efficient combination of screen classification and individual identification can be realized, thereby ensuring the accuracy of the tracking process; by integrating the front-end code and the back-end code to generate and record a unique identification code, a unique identity identifier can be assigned to each associated screen, thereby facilitating subsequent data management and tracking; by judging whether to perform the retest operation on the associated screen according to the unique identification code, intelligent decision-making can be carried out based on the identification data, thereby effectively avoiding unnecessary retest operations, improving the test efficiency and saving costs.

[0017] The second invention object of the present application is achieved by the following technical solution: A mobile phone screen testing device, the mobile phone screen testing device includes: A positioning module, configured to locate and capture a screen to be tested to a test bench based on machine vision positioning technology; A testing module, configured to light the screen to be tested and perform a display function test and a touch function test on the screen to be tested to generate corresponding test results; An acquisition module, configured to acquire a production process data set if the test result is a screen abnormality; A generation module, configured to generate a corresponding association result based on the established association algorithm model according to the test result and the production process data set; A determination module, configured to determine corresponding associated screens and device control parameters according to the association result, where the device control parameters at least include alarm parameters and operation adjustment parameters, generate and record a unique identification code for each of the associated screens, and judge whether to perform the retest operation on the associated screen.

[0018] The third object of the present application is achieved by the following technical solution: A computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, where the processor implements the steps of the above mobile phone screen testing method when executing the computer program.

[0019] The fourth object of the present application is achieved by the following technical solution: A computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the above-mentioned mobile phone screen testing method are implemented.

[0020] In summary, the present application includes at least one of the following beneficial technical effects: 1. By using machine vision positioning technology to locate and grab the screen to be tested onto the test bench, the position of the screen to be tested can be accurately identified, ensuring that the screen is precisely placed at the designated position of the testing device, thus achieving seamless docking between the testing equipment and the screen. This positioning method not only avoids errors that may be caused by manual operation but also can adapt to screens of different sizes and specifications, making the testing process more efficient and flexible. At the same time, due to the high-precision characteristics of this technology, it can effectively reduce test failures caused by improper screen placement, thus significantly improving the reliability and stability of the testing; 2. By lighting the screen to be tested and performing display function testing and touch function testing on it, the core function detection requirements of the mobile phone screen can be comprehensively covered. In the display function testing, by analyzing performance parameters such as the brightness, color accuracy, and display anomaly points of the screen, the display quality of the screen can be accurately evaluated, and potential problems such as color difference, bright spots, or dark spots can be discovered. In the touch function testing, by detecting the touch response sensitivity, multi-touch function, and touch accuracy of the screen, it can be verified whether the touch performance of the screen meets the usage requirements. This comprehensive testing method ensures that the display and touch performance of the screen meet the factory standards, thus effectively discovering and marking potential quality problems of the screen and preventing unqualified screens from flowing into subsequent production or the hands of users; 3. If the test results show that there are abnormalities in the screen, by further obtaining the production process dataset, the test results can be associated with the data in the production process to achieve in-depth analysis and traceability processing of the abnormal screen. The production process dataset includes the raw material batch data of the screen, the operating status of the production equipment, and the key indicators of the production environment, etc. By collecting these data in a timely manner, it can provide a comprehensive and detailed basis for analyzing the root cause of the abnormal screen. In this way, not only can the source of the screen quality problem be traced, but also targeted improvement measures can be proposed, thereby greatly improving the abnormal traceability ability and providing data support for the optimization of the production line; based on the established correlation algorithm model, integrating and analyzing the test results and the production process dataset can generate corresponding correlation results, and the correlation between the screen abnormality and the relevant factors in the production process can be quickly identified through intelligent algorithms. By learning from historical training data, this model can deduce the key factors such as raw materials, equipment, or environmental parameters that may be affected by the abnormal screen, and predict other potential high-risk screens. In this way, it can effectively achieve the root cause location of the screen quality problem and the risk prediction of the associated screen, not only greatly improving the intelligent level of production management, but also taking timely measures to deal with it before the problem spreads, thereby improving the efficiency of the overall production process and the stability of product quality. Description of the Drawings

[0021] Figure 1 is a flowchart of a mobile phone screen testing method in an embodiment of the present application.

[0022] Figure 2 is an implementation flowchart of step S20 in a mobile phone screen testing method in an embodiment of the present application; Figure 3 is an implementation flowchart of step S30 in a mobile phone screen testing method in an embodiment of the present application; Figure 4 is another implementation flowchart of step S40 in a mobile phone screen testing method in an embodiment of the present application; Figure 5 is an implementation flowchart of step S50 in a mobile phone screen testing method in an embodiment of the present application; Figure 6 is another implementation flowchart of step S50 in a mobile phone screen testing method in an embodiment of the present application; Figure 7 is a principle block diagram of a mobile phone screen testing device in an embodiment of the present application; Figure 8 is a schematic diagram of the device in an embodiment of the present application. Detailed Description of the Embodiment

[0023] The following further describes the present application in detail with reference to the accompanying drawings.

[0024] In one embodiment, as Figure 1 shown, the present application discloses a method for testing a mobile phone screen. A method for testing a mobile phone screen includes: S10. Based on machine vision positioning technology, locate and grab the screen to be tested onto the test bench; in this embodiment, by loading a high-resolution industrial camera to capture the image information of the position where the screen to be tested is located, using image processing algorithms to perform edge detection and feature point extraction on the captured image, calculating the accurate position and angle of the screen to be tested in the working area, determining the coordinate information of the grabbing point; combining with the motion control module of the robotic arm, sending a grabbing instruction to the robotic arm, enabling the robotic arm to accurately grab the screen to be tested according to the calculated grabbing point coordinates, and placing the screen at the designated position on the test bench through motion path planning, while adjusting the pressure parameters in real time during the grabbing process to ensure that the screen will not be damaged during the grabbing and placing processes.

[0025] S20. Light up the screen to be tested, and perform a display function test and a touch function test on the screen to be tested to generate corresponding test results; in this embodiment, after the screen to be tested is placed on the test bench, by initializing the circuit module of the screen to be tested, sending a power-on signal to the screen to make it enter the testable state, and then sending a lighting instruction to make the screen display a preset test image, the test image includes a single-color screen, a gradient-color screen, and a complex pattern screen. Subsequently, capture the image displayed on the screen through a high-resolution imaging device, and analyze the captured image through image processing algorithms to extract display performance parameters including brightness distribution, color accuracy, and display anomaly points. At the same time, apply touch signals at different positions on the screen surface through a simulated touch device, collect the response data of the touch operation, analyze the touch performance parameters including touch sensitivity, touch position deviation, and multi-touch function, and generate the test results of the screen to be tested by integrating the display performance parameters and the touch performance parameters.

[0026] S30. If the test result shows that the screen is abnormal, obtain the production process dataset; in this embodiment, after the test result is determined to be abnormal, extract the production record of the screen to be tested by calling the traceability module, trace the corresponding production batch information based on the serial number of the screen, obtain the batch numbers of the raw materials used during production, the equipment numbers of the processing processes, and the relevant operating parameters, and at the same time extract the environmental parameters such as temperature, humidity, and electrostatic control status in the production environment. Format all the production data related to this screen to be tested and store it as a structured production process dataset to provide basic data for subsequent anomaly analysis.

[0027] S40. Based on the established correlation algorithm model, generate corresponding correlation results according to the test results and the production process data set. In this embodiment, by inputting the abnormal test results of the screen to be tested and the key parameters in the production process data set into the pre-trained correlation algorithm model, based on the feature extraction module in the algorithm model, extract the feature vectors of the abnormal screen from the input data. Subsequently, using the correlation rule library generated during the model training process, perform similarity matching between the feature vectors and the feature vectors in the historical data, and deduce the specific correlation factors between the abnormality of the screen to be tested and the production process, such as specific raw material batches or abnormal equipment operation conditions. At the same time, calculate the probability of other screens in the current batch having similar abnormalities through the prediction module of the model, and finally generate correlation results including the correlation reasons for the abnormal screen, a list of predicted high-risk screens, and recommended adjustment parameters.

[0028] S50. According to the correlation results, determine the corresponding correlated screens and device control parameters. The device control parameters at least include alarm parameters and operation adjustment parameters. Generate and record a unique identification code for each correlated screen, and determine whether to perform a retest operation on the correlated screens. In this embodiment, by analyzing the list of predicted high-risk screens in the correlation results, screen out other screens that have a strong correlation with the abnormal screen, determine these screens as correlated screens, and assign a risk level to them according to the degree of correlation of each screen. Set the device control parameters according to the risk level, including sending an alarm signal to the correlated screens with a high risk level and sending an operation adjustment instruction to the production equipment highly related to the abnormality to optimize its operation state. At the same time, generate a unique identification code for each correlated screen, which consists of the batch information and correlation features of the correlated screen. Subsequently, track the retest status of the correlated screens according to the unique identification code, and decide whether to re-perform the display function test and touch function test according to the screen risk level, and synchronize all operation records to the data management module.

[0029] In summary, by using the machine vision positioning technology to position and grab the screen to be tested onto the test bench, the position of the screen to be tested can be accurately located, ensuring the accuracy of the docking between the test device and the screen, thereby improving the reliability and stability of the test; by lighting the screen to be tested and performing display function tests and touch function tests on the screen to be tested to generate corresponding test results, the display performance and touch performance of the screen can be comprehensively detected, thereby effectively discovering potential quality problems of the screen; by obtaining the production process data set if the test result is that the screen is abnormal, production-related data can be collected in a timely manner, providing a basis for abnormality analysis, thereby improving the ability to trace the source of abnormalities; by generating corresponding correlation results based on the established correlation algorithm model according to the test results and the production process data set, the correlation factors and potential risks of the abnormal screen can be quickly identified, thereby realizing intelligent production process management and problem prediction.

[0030] In one embodiment, as Figure 2 shown, in step S20, that is, when lighting the screen to be tested and performing a display function test and a touch function test on the screen to be tested to generate corresponding test results, the test results include a display test result and a touch test result, and the step further includes: S201. Initialize the circuit module of the screen to be tested, make the screen to be tested enter a testable state, send a lighting instruction to the screen to be tested, and make the screen to be tested display a predetermined test image. The test image includes a single-color image, a gradient-color image, and a complex pattern image; in this embodiment, after the screen to be tested is placed on the test bench, first initialize the circuit module of the screen to be tested, perform a self-check process of electrical connection to confirm whether the screen interface works properly, and at the same time send a voltage stabilization signal to ensure that the power supply voltage and current meet the requirements for screen startup; then send an activation instruction to the screen to be tested, switch the screen from the standby mode to the test mode, and load a dedicated driver, send a lighting instruction to the screen to be tested, and make the screen start to display the test image; the test images are loaded in a predetermined order. Among them, single-color images (such as red, green, and blue) are used to evaluate the basic brightness uniformity and color purity of the screen; the gradient-color image evaluates the color reproduction ability and gamut performance of the screen by detecting the smoothness of the transition from one color area to another; the complex pattern image contains a variety of high-contrast lines, geometric figures, and detailed patterns, which are used to verify whether there are problems such as ghosting, distortion, blurring, or insufficient resolution when the screen displays a dynamic scene. These images are all generated through a color space model that meets the standards (such as sRGB or DCI-P3) to ensure the accuracy and consistency of the test results.

[0031] S202. Based on the image capture device, the test image of the screen to be tested is captured in real time, and the captured test image is analyzed based on the image processing algorithm to generate corresponding display performance parameters. The display performance parameters include brightness parameters, color accuracy parameters, and abnormal point parameters, and it is determined whether the display performance parameters are qualified. In this embodiment, by setting a high-resolution industrial camera or an optical capture device, the test image displayed on the screen to be tested is captured in real time, and the captured image data is transmitted to the image processing module, and the advanced image processing algorithm is used to perform multi-dimensional analysis on the image. The brightness parameter statistically analyzes the pixel brightness values of the test image to calculate the uniformity of the brightness distribution and detects whether there are over-bright or over-dark areas. The color accuracy parameter calculates the color difference value (such as ΔE value) by comparing the captured image color values (such as RGB or Lab color values) with the reference values of the standard test image to determine whether the screen can accurately restore colors. The abnormal point parameter detects whether there are bright points, dark points, or dead points in the screen image, and marks the specific positions, sizes, and distributions of these abnormal points. All these parameters are compared with the preset quality standards to generate a comprehensive analysis result of the display performance parameters, determine whether the display performance meets the qualified standard, and mark the unqualified parts in detail for subsequent analysis and processing.

[0032] S203. If the display performance parameters are unqualified, it is determined that the display test result of the display function test is screen abnormality. In this embodiment, when any one of the brightness, color accuracy, or abnormal point detection of the display performance parameters exceeds the preset standard range, the display performance of this screen is determined to be unqualified, specifically including that the deviation value of uneven brightness exceeds the allowable range, the ΔE color difference value exceeds the predetermined threshold, or there are abnormal points exceeding the specified size and quantity. A detailed report of the display abnormality is generated according to these unqualified parameters, the problem area is accurately marked, and the report data is stored for subsequent traceability and analysis. At the same time, the display test result of this display function test is determined to be "screen abnormality" for the next-step abnormal correlation analysis in the production process.

[0033] S204. If the display performance parameters are qualified, touch signals are applied to different areas of the screen to be tested through simulated touch operations, and corresponding touch performance parameters are generated. The touch performance parameters include response sensitivity parameters, multi-touch function parameters, and touch accuracy parameters. Determine whether the touch performance parameters are qualified. In this embodiment, after the display performance passes the determination, the touch function of the screen is tested through the simulated touch module. The simulated touch operations include various signal inputs such as single-touch, multi-touch, and continuous sliding. In the single-touch test, single-point signals are applied to different areas of the screen, and the touch response time of the screen is recorded to generate response sensitivity parameters for evaluating the touch response speed of the screen. In the multi-touch test, multiple touch signals (such as 2-point or 10-point touch) are applied simultaneously, and it is detected whether the screen can recognize multiple touch points simultaneously and the interaction performance between the touch points to generate multi-touch function parameters. The touch accuracy test evaluates the touch accuracy by comparing the predetermined position of the simulated touch point with the actual touch position feedback by the screen, calculating the deviation value. All touch performance parameters are compared with the preset standards to form a comprehensive analysis result of the touch performance, determine whether the touch function of the screen is qualified, and generate a marked record for unqualified items.

[0034] S205. If the touch performance parameters are unqualified, determine that the touch test result of the touch function test is that the screen is abnormal. In this embodiment, when any index in the touch performance parameters fails to pass the qualified standard, for example, the response time of the response sensitivity parameter exceeds the specified range, or the multi-touch function cannot recognize all touch points simultaneously, or the touch accuracy deviation value exceeds the allowable threshold, the touch performance is determined to be unqualified, and an exception report is generated, recording the position of the abnormal touch point, the type of abnormality, and the corresponding touch parameters. Determine that the touch test result of the touch function test is "screen abnormal", and at the same time store the abnormal data for subsequent use to provide data support for in-depth analysis and positioning of problems.

[0035] S206. If the touch performance parameters are qualified, determine that both the display test result and the touch test result are that the screen is normal. In this embodiment, when all indexes of the touch performance parameters meet the qualified standards, the touch test result of this screen is determined to be qualified. Combining the qualified judgment of the display test result, the comprehensive test result of this screen is generated, marked as "screen normal", and at the same time all test data are recorded and associated with the unique identifier of this screen to ensure that the quality data of this screen can be traced in subsequent links, and a complete quality analysis record is generated in the test report to support the quality management in subsequent production and logistics links.

[0036] In summary, by initializing the circuit module of the screen to be tested, enabling the screen to be tested to enter the testable state, and sending a lighting instruction to the screen to be tested to make the screen display a predetermined test image, it can ensure that the screen to be tested is in a normal working state, thereby providing a stable test environment for subsequent tests; by using an image capture device to capture the test image of the screen to be tested in real time and analyzing the captured test image based on an image processing algorithm to generate corresponding display performance parameters, it can accurately obtain the key indicators of the screen display performance, thereby accurately judging the display quality of the screen; if the display performance parameters are unqualified, determining that the display test result of the display function test is that the screen is abnormal can mark the abnormal display screen in time, thereby effectively preventing unqualified screens from flowing into subsequent processes; if the display performance parameters are qualified, by simulating touch operations to apply touch signals to different areas of the screen to be tested, and then generating corresponding touch performance parameters, it can verify the performance of the screen in various touch scenarios, thereby ensuring the reliability of the touch function; if the touch performance parameters are unqualified, determining that the touch test result of the touch function test is that the screen is abnormal can detect touch performance problems in time, thereby improving the accuracy and comprehensiveness of the screen test.

[0037] In one embodiment, as Figure 3 shown, in step S30, that is, if the test result is that the screen is abnormal, in the step of obtaining the production process data set, it includes: S301. If the test result is that the screen is abnormal, determine the screen to be tested that has passed the display function test and the touch function test as the target screen; in this embodiment, when the test result of the screen is determined to be abnormal, first record the test result in the abnormal data table, and at the same time extract the unique identification information of the screen from the test data, such as the product serial number of the screen, the test equipment number, the test station number, and the test time, to ensure that the identity of the screen can be uniquely determined; further combine the test process of the screen to confirm that it is determined to be abnormal due to the display function test, the touch function test, or both not passing; mark the screen as the target screen and classify its abnormal type, such as uneven brightness, excessive color difference, or too many abnormal points in the display function test, or low response sensitivity or multi-touch failure in the touch function test, and associate this information with the target screen together to ensure that the target screen can be quickly identified and located in the subsequent traceability and processing process, and at the same time provide a clear source of abnormality for subsequent data analysis.

[0038] S302. Obtain the product serial number of the target screen and trace the corresponding raw material batch data. In this embodiment, according to the product serial number of the target screen, by querying the production records of the screen, trace the raw material information used in the production process, including the batch number of the screen glass substrate, the supplier information of the touch sensor layer, the production date and batch number of the backlight module, and the batch identification of other key raw materials. Further retrieve the quality inspection reports of these raw materials to check whether they have passed the supplier's factory quality inspection and the factory's incoming inspection, and verify whether there are quality problems with the raw materials themselves. For example, whether there are thickness deviations in the glass substrate, whether the resistance value of the touch layer exceeds the standard, or whether the light emission uniformity of the backlight module meets the requirements. If there are defects in the raw material batch that may be related to the abnormal test of the target screen, mark this batch as a potential problem batch and record the usage of these raw materials in the production process to provide accurate raw material traceability data for subsequent analysis of the reasons for the target screen abnormality.

[0039] S303. Obtain the equipment operation status data used in the production process of the target screen. In this embodiment, in combination with the production records of the target screen, gradually trace all the key processes it has gone through in the production process, such as the lamination process, the coating process, the encapsulation process, and the subsequent inspection process. Extract the equipment numbers used in these processes and query the operation status data of the equipment when producing the target screen, including parameters such as the operation time, operation pressure, processing temperature, operation speed, and whether an alarm has occurred. For example, in the lamination process, the equipment pressure may be too high, resulting in damage to the touch layer, or in the coating process, the equipment temperature fluctuation may cause delamination problems in the backlight module. By analyzing these equipment parameters, further judge whether the target screen is affected by equipment abnormalities during the production process, such as whether it is processed before and after equipment maintenance, and whether there are situations where the operation parameters exceed the standard. Associate these data with the test results of the target screen to support the equipment-level analysis of the abnormal reasons.

[0040] S304. Obtain the production environment data of various indicators of the production environment during the production process of the target screen; in this embodiment, when tracing the production process of the target screen, extract the production environment data corresponding to the corresponding time period, including the temperature, humidity, air cleanliness, electrostatic control parameters, and light intensity of the production area, etc.; specifically, the environmental monitoring records corresponding to the production time of the target screen can be queried. For example, in the lamination process, check whether the electrostatic protection equipment is operating normally and whether the humidity is within the specified range to reduce the possibility of electrostatic damage; at the same time, check whether the air cleanliness level meets the requirements and whether there is a situation where the particulate matter exceeds the standard, which may cause micro-scratches or contaminants to adhere to the screen surface; if there are abnormal environmental parameters in the environmental monitoring records, such as too high temperature, insufficient humidity, abnormal electrostatic discharge, etc., associate these abnormalities with the production links of the target screen, mark them as possible abnormal influencing factors, and record the environmental data in the production information of the target screen to provide data support for subsequent correlation analysis from the environmental dimension.

[0041] S305. Extract features from the raw material batch data, equipment operation status data, and production environment data, convert the extracted key data into standardized data that can be directly calculated by the established correlation algorithm model, and integrate the standardized data to generate a production process dataset. In this embodiment, for the raw material batch data, equipment operation status data, and production environment data obtained during the tracing process of the target screen, extract key features item by item. For example, extract the supplier number, batch number, quality inspection status, and usage frequency from the raw material batch data; extract the processing temperature, pressure, operation time, alarm records, and maintenance records from the equipment operation status data; extract the temperature and humidity change curve, air cleanliness level, electrostatic control status, and parameter fluctuation range from the production environment data; the extracted feature data is processed by normalization and standardization. For example, convert the temperature and humidity data into relative change values, encode the boolean alarm data in the equipment operation status as 0 or 1, and at the same time perform a redundancy elimination operation on the multi-dimensional feature data to eliminate redundant or duplicate data structures; finally, integrate the standardized feature data of raw materials, equipment, and environment into a unified production process dataset, which has a unified format and a specific coding structure and can be directly used as the input of the correlation algorithm model to provide comprehensive data support for subsequent anomaly analysis, risk prediction, and production optimization.

[0042] In summary, if the test result indicates a screen anomaly, the screen to be tested that has passed the display function test and the touch function test is determined as the target screen, which can quickly locate the screen with anomalies and thus provide an accurate basis for subsequent traceability and handling. By obtaining the product serial number of the target screen and tracing the corresponding raw material batch data, the quality problem of the raw materials can be associated with the screen anomaly, thereby providing data support for the root cause analysis of the abnormal screen. By obtaining the equipment operation status data used in the production process of the target screen, the potential impact of the production equipment on the screen quality can be obtained, thereby improving the accuracy of the correlation analysis between the equipment operation parameters and the quality. By obtaining the production environment data of various indicators of the production environment during the production process of the target screen, the impact of environmental factors on the screen quality can be identified, thereby effectively reducing the interference of environmental anomalies on the screen quality. By performing feature extraction on the raw material batch data, the equipment operation status data, and the production environment data, and converting the extracted key data into standardized data that can be directly calculated by the established correlation algorithm model, and integrating the standardized data, a production process dataset can be generated, which can ensure the standardization of the input data and the accuracy of the model calculation, thereby providing a reliable data basis for intelligent analysis.

[0043] In one embodiment, as Figure 4 shown, in step S40, that is, in the step of generating the corresponding correlation result based on the established correlation algorithm model according to the test result and the production process dataset, it includes: S401. Substitute the test result and the production process dataset into the established correlation algorithm model to generate the corresponding feature vector. In this embodiment, by analyzing the data in the test result and the production process dataset, the abnormal information in the test result is extracted as high-dimensional features. For example, in the display function test, the brightness deviation value, the color accuracy deviation value, and the number of abnormal points, and in the touch function test, the response delay time, the multi-touch offset amount, etc. After these key parameters in the test result are normalized, they are used as part of the feature vector. At the same time, perform feature extraction on the raw material batch information, the equipment operation status parameters, and the production environment indicators in the production process dataset. For example, the supplier identifier of the raw material batch, the temperature fluctuation during equipment operation, and the offset degree of the humidity parameter, etc. All data is converted into a numerical feature representation through the feature mapping function. Finally, the test result features and the production process features are combined to form a complete high-dimensional feature vector. Each dimension of this feature vector represents the relationship between the screen quality and a certain production parameter, and is used for subsequent model calculation and matching analysis.

[0044] S402. Match the corresponding historical training data according to the feature vector. In this embodiment, by inputting the generated feature vector into the database module of the association algorithm model, calling the feature matching algorithm, calculating the similarity between the current feature vector and the feature vectors in the historical training data, the similarity calculation is based on multiple metrics, such as Euclidean distance or cosine similarity, and the closest set of feature vectors is selected from the historical data according to the calculation results. These historical training data include screen anomaly cases and corresponding production conditions. For example, the brightness problem of a certain batch of abnormal screens was once related to the raw material with the supplier number A123, or the touch layer failure occurred when the device operating temperature exceeded 50 degrees Celsius. Through this feature matching process, the historical cases most relevant to the current screen anomaly can be located, providing a reference basis for subsequent rule derivation and decision-making, and at the same time verifying whether there are potential risks similar to historical anomalies in the current production conditions.

[0045] S403. Call the association rule derivation module in the association algorithm model to derive at least the corresponding association rules and dynamic adjustment rules according to the historical training data. In this embodiment, based on the matched historical training data, call the association rule derivation module in the association algorithm model, analyze the feature combinations in the historical data using metrics such as support and confidence, and derive the potential association rules between the current abnormal screen and the production conditions. For example, the touch anomaly screens of a certain batch may be directly related to the environmental humidity being lower than 30%, or the occurrence probability of the multi-touch offset problem increases significantly after the device maintenance period exceeds 300 hours. In addition, the dynamic adjustment rules identify which production conditions can be adjusted to improve the anomaly by analyzing the fluctuation trend of production parameters. For example, reducing the pressure range of the lamination process from 500±50Pa to 500±20Pa may reduce the occurrence of screen surface defects. Through the derivation of association rules and dynamic adjustment rules, a reliable basis is provided for locating and solving the anomaly cause, and at the same time, the priority of the rules is marked through weight analysis for subsequent comprehensive processing of the results.

[0046] S404. Integrate the association rules and dynamic adjustment rules to generate corresponding association results. In this embodiment, by integrating the weights of the association rules and dynamic adjustment rules, the rules most relevant to the current abnormal screen features are preferentially selected. At the same time, considering the applicable scope of the rules and the historical verification effect, the optimal rule combination is generated to obtain the association results. The association results include the detailed relationship between the abnormal screen and production conditions. For example, the thickness deviation of a certain batch of glass substrates directly causes brightness anomalies, or the causal relationship between high equipment temperature and decreased touch sensitivity. At the same time, the association results also include production optimization suggestions generated based on dynamic adjustment rules, such as adjusting the temperature setting of the laminating equipment or replacing raw materials of a specific batch. The generation process of the association results focuses on logical consistency and executability, and provides precise operation guidance for subsequent production adjustments and risk warnings. Finally, structured association results are output to support subsequent production management and abnormal screen handling processes.

[0047] Specifically, during the process of generating the association rules, assume that the test results of the current target screen show uneven brightness and low touch sensitivity. By substituting the test results and the production process data set into the association algorithm model, the extracted feature vectors of the model include a brightness deviation value of +12%, a touch response delay of 50 ms, a touch offset of 1.2 mm, and relevant parameters during the production process, such as the raw material batch number M123, the running time of the laminating equipment of 1200 hours, the environmental humidity of 25%, and the processing temperature of 75°C. After these parameters are standardized and matched with the historical training data, it is found that in a group of historical data most similar to the current target screen, cases with brightness deviation values from +10% to +15% have occurred multiple times, and the raw material batch numbers in these cases all come from a specific batch with a supplier number of S001. At the same time, the situation where the equipment running time exceeds 1000 hours is highly correlated with the problem of decreased touch sensitivity.

[0048] The model further analyzes historical data, calculates by combining support and confidence, and derives a high-confidence association rule from multiple groups of feature combinations. That is, when using a glass substrate with a supplier number of S001 and the bonding equipment runs for more than 1000 hours, the probability of uneven screen brightness increases significantly, with a support of 85% and a confidence of 90%. At the same time, the model derives another dynamic adjustment rule, indicating that in the same production environment, when the processing temperature is in the range of 70°C to 72°C, the number of cases of decreased touch sensitivity decreases significantly. It is recommended to adjust the equipment temperature from the current 75°C to below 72°C. These rules are marked as the highest-priority rules through weight analysis and are finally integrated into the association results, indicating that the brightness and touch anomalies of the target screen are mainly related to the performance fluctuations of the raw materials in the current batch and the deviations of the equipment operation parameters. At the same time, specific dynamic adjustment suggestions are given, that is, shortening the equipment operation and maintenance cycle to within 800 hours and recalibrating the processing temperature to between 70°C and 72°C to avoid similar problems from occurring again.

[0049] In summary, by substituting the test results and production process data sets into the established association algorithm model to generate corresponding feature vectors, the core features in the screen test and production process can be extracted, laying a foundation for intelligent analysis; by matching the corresponding historical training data according to the feature vectors, similarity analysis can be carried out with the help of historical data, thereby improving the accuracy of anomaly problem analysis; by calling the association rule derivation module in the association algorithm model and deriving at least the corresponding association rules and dynamic adjustment rules based on the historical training data, the causal relationship and adjustment strategy between the screen anomalies and the production process can be automatically generated, thereby improving the intelligent level of the production line; by integrating the association rules and dynamic adjustment rules to generate corresponding association results, comprehensive guidance can be provided for subsequent production adjustments and screen anomaly predictions, thereby optimizing the production process and reducing the defective product rate.

[0050] In one embodiment, as Figure 5 shown, in step S50, that is, in the step of determining the corresponding associated screen and equipment control parameters according to the association result, it includes: S5011. Determine the to-be-tested screens in the same batch as the target screen as the first-level critical screens, and determine the to-be-tested screens in batches adjacent to the target screen as the second-level critical screens; in this embodiment, by querying the production batch information of the target screen, filter out all the to-be-tested screens with the same production batch as the target screen, and mark these screens as the first-level critical screens; further compare the production records of adjacent batches, extract all the to-be-tested screens adjacent to the target screen in the previous and next batches, and mark them as the second-level critical screens; during the division process, perform precise matching based on the production timeline to ensure the accurate division of the first-level critical screens and the second-level critical screens. For example, when the target screen belongs to the screen with batch number A001, other screens in the same batch, such as numbers A001-01 to A001-50, are all classified as the first-level critical screens, while the to-be-tested screens with the previous batch number A000 and the next batch number A002 are classified as the second-level critical screens; this division method can effectively screen out the screen range that may be affected by similar production conditions, laying a foundation for subsequent abnormal risk prediction and correlation analysis.

[0051] S5012. According to the association rules, perform abnormal risk prediction on the first-level critical screens and the second-level critical screens to generate corresponding prediction results, and based on the prediction results, determine whether each first-level critical screen and / or each second-level critical screen is an associated screen; in this embodiment, call the prediction module of the association algorithm model, and based on the abnormal association rules of the target screen, input the production data of the first-level critical screens and the second-level critical screens into the model, and calculate the abnormal risk probability of these screens one by one; the association rules are used to identify whether these screens have similar characteristics to the target screen, such as too high equipment temperature during production, the same raw material batch, or low environmental humidity. The model comprehensively calculates the characteristic weights of these data to predict the abnormal risk value of each screen; for example, when the touch response delay of number A001-20 in the first-level critical screens exceeds the threshold, which highly matches the abnormal characteristics of the target screen, the model sets its abnormal risk value to 95%, while for number A002-05 in the second-level critical screens, due to similar production environment parameters but different touch layer suppliers, its risk value may only be 60%; according to the prediction results of the risk values, determine the screens with risk values higher than the threshold as associated screens, and record their specific risk factors, providing a basis for subsequent adjustment and processing.

[0052] Specifically, by invoking the prediction module in the association algorithm model, the production data of the primary key screens and secondary key screens are input into the model, and the abnormal risk prediction is carried out in combination with the association rules of the target screen anomalies. First, the characteristic data of each screen are parsed, including its touch delay, brightness deviation, number of abnormal points, device operation parameters (such as pressure, temperature), and production environment parameters (such as humidity, cleanliness), etc. These characteristic data are compared one by one with the characteristic rules of the target screen, and by calculating the matching degree of these characteristics, the abnormal risk value of each screen is obtained. Specifically, the association rules will preferentially match the characteristics with the highest correlation according to the characteristic weights of the target screen. For example, if the main anomaly of the target screen comes from the touch delay, the touch delay characteristic will be given a higher weight. The model calculates the deviation value of the touch delay for each of the primary key screens and secondary key screens one by one, and at the same time comprehensively considers the correlation of the device operation status and environmental parameters, and finally generates the abnormal risk value through weighted calculation. Taking the primary key screen as an example, assuming that its touch delay characteristic is exactly the same as that of the target screen and the brightness deviation range is similar, combined with the high consistency of its device operation status, the model may generate a result with an abnormal risk value of 90%. For another screen, although the touch delay deviation is large but the environmental parameters are completely consistent, its abnormal risk value may be 70%. For the secondary key screens, the model will further reduce the matching weight threshold and calculate the risk value by analyzing the partial consistency of its device operation parameters or the indirect influence of environmental factors. For example, for a secondary key screen, although the device operation time is quite different from that of the target screen but the same raw materials are used, its risk value may be only 50%. Finally, according to the calculated abnormal risk value, the screens with risk values higher than the set threshold are determined as associated screens, and their specific risk sources are marked. For example, the associated screens may be marked as extremely high risk because the batches of the touch layer raw materials are the same or the bonding device operation time exceeds 1000 hours. All these results will be summarized as the prediction results of each screen and associated with the abnormal information of the target screen for subsequent retesting and production adjustment suggestions.

[0053] S5013. After configuring the corresponding association weights for each standardized data according to the dynamic adjustment rules, calculate the sum of the products of each standardized data and the association weights, and then generate the corresponding calculation result. Determine the corresponding equipment control parameters according to the calculation result. In this embodiment, according to the dynamic adjustment rules extracted from the association algorithm model, extract the features of the production data of the primary key screen and the secondary key screen, and perform weighted calculation on each feature data according to the preset weights of the model. For example, the running time of the laminating equipment, processing temperature, environmental humidity, raw material batch, etc. Each data is assigned a weight value related to its abnormal association strength. By calculating the product of each standardized data and the corresponding association weight, and accumulating all the product results to obtain the total abnormal score. Suppose the weight of the running time of the laminating equipment is 0.4, the weight of the environmental humidity is 0.3, and the weight of the raw material batch is 0.3. When the abnormal value of the running time of a certain primary key screen is 1000 hours, the deviation value of the environmental humidity is 5%, and the raw material matching probability is 80%, the calculated abnormal score is 0.4×1000 + 0.3×5 + 0.3×80 = 440.5. When the score result exceeds the set threshold, generate the corresponding equipment control parameters, such as reducing the running time of the laminating equipment, changing the environmental parameter monitoring strategy, or suspending the process associated with the high-risk screen, and at the same time send an alarm signal to the production line to prompt the operator to conduct a real-time inspection, and finally form a comprehensive equipment control and production adjustment suggestion.

[0054] In summary, by determining the test screens to be tested in the same batch as the target screen as the primary key screens, and determining the test screens to be tested in the adjacent batches to the target screen as the secondary key screens, the association range of the abnormal screens can be clarified, so as to achieve accurate traceability and hierarchical management; by predicting the abnormal risks of the primary key screens and the secondary key screens according to the association rules and generating the corresponding prediction results, potential high-risk screens can be predicted, thus reducing the batch production of defective products caused by abnormal diffusion; by calculating the sum of the products of each standardized data and the association weights after configuring the corresponding association weights for each standardized data according to the dynamic adjustment rules, and then generating the corresponding calculation result, the impact of the associated data on the screen abnormality can be quantified, thus providing a scientific basis for the optimization of the equipment control parameters; by determining the corresponding equipment control parameters according to the calculation result, the running state of the production equipment can be adjusted in real time, thus effectively reducing the incidence of production abnormalities.

[0055] In one embodiment, as Figure 6 shown, in step S50, the step of generating and recording a unique identification code for each associated screen and determining whether to perform the retest operation on the associated screen includes: S5021. Determine the degree of association of each associated screen according to the prediction result. In this embodiment, by parsing the abnormal risk prediction result generated by the association algorithm model and combining the association rules, calculate the feature weights of each associated screen to determine its degree of association with the target screen. The degree of association is expressed in the form of a percentage or a numerical value, which is used to measure the similarity of abnormal risks or potential causal relationships between each associated screen and the target screen. Specifically, extract the feature data of the associated screen, such as touch delay, display brightness deviation value, number of abnormal points, device operating temperature and humidity, etc., and perform similarity matching with the feature vector of the target screen, and calculate the weighted average score of these features to obtain the degree of association. For example, if the touch delay of a certain screen only differs from that of the target screen by 1 ms and the brightness deviation is 5%, the model will calculate its degree of association as 90%, while for another screen with a touch delay difference of 20 ms and a brightness deviation of 15%, its degree of association may only be 60%. At the same time, the feature weights are dynamically adjusted according to the priority in the prediction result. For example, the weight of the touch delay as the main feature may be set to 0.5, and the weight of the brightness deviation is set to 0.3. These weighted calculations ensure that the evaluation of the degree of association is more targeted and accurate, thus providing an accurate basis for subsequent classification.

[0056] S5022. Classify each associated screen according to the degree of association to determine different screen sets. In this embodiment, according to the degree of association of each associated screen, divide these screens into different screen sets, and achieve hierarchical classification by setting multiple threshold intervals. For example, screens with a degree of association above 80% are divided into the "high-risk screen set", screens with a degree of association between 50% and 80% are divided into the "medium-risk screen set", and screens with a degree of association below 50% are divided into the "low-risk screen set". During the classification process, not only the score of the degree of association is considered, but also the contribution degree of specific features is combined for adjustment. For example, if the touch features of a certain screen are highly similar but the display features are quite different, it can be classified into the medium-risk screen set according to the priority weight of the touch features. Specifically, for example, if the degree of association of screen A is 85% and both the touch delay and the display brightness deviation match the target screen highly, it is classified into the high-risk screen set, while for screen B with a degree of association of 65% but a touch feature matching degree lower than 50%, it is classified into the medium-risk screen set. The classification results form multiple screen sets, and each screen set contains screens with similar degrees of association within a certain range, which is convenient for subsequent coding and the formulation of retesting strategies.

[0057] S50223. Assign a front - end code to each screen set and a back - end code to each associated screen in the screen set; in this embodiment, assign a unique front - end code to each screen set to identify the classification and risk level of the screen set. For example, the front - end code for a "high - risk screen set" is "H01", the front - end code for a "medium - risk screen set" is "M01", and the front - end code for a "low - risk screen set" is "L01". While assigning the front - end code to the screen set, assign a unique back - end code to the associated screens in each screen set. For example, generate the back - end codes in sequence according to the production batch, serial number, and ranking order of the degree of association of the screens. The numbering rule can be consecutive increasing numbers or can be dynamically generated in combination with the specific characteristics of the screen. For example, the screen numbered A001 - 01, as the first associated screen in the high - risk screen set, can have its back - end code set to "001", while the screen numbered A002 - 15 is in the medium - risk screen set and its back - end code can be set to "015". This coding method ensures that each screen set and screen individual has a unique identifier, which is convenient for subsequent tracking and management.

[0058] S5024. Integrate the front - end code and the back - end code to generate and record a unique identification code; in this embodiment, by splicing the front - end code of the screen set with the back - end code of the associated screen, generate the unique identification code for each associated screen. For example, integrate the front - end code "H01" of the high - risk screen set with the back - end code "001" of the first associated screen to generate "H01 - 001", and integrate the front - end code "M01" of the medium - risk screen set with the back - end code "003" of the third screen to generate "M01 - 003". This integration method ensures the uniqueness of each associated screen in the entire production process and quality management. At the same time, store the generated unique identification code together with associated data such as the degree of association of the screen, test results, production batch information, and equipment parameters in the screen tracking database, and generate a QR code or laser - engraved information to physically embed the unique identification code on the screen surface, packaging, or label for subsequent tracking and data query.

[0059] S5025. Determine whether to perform retesting on the associated screen according to the unique identification code. In this embodiment, based on the generated unique identification code, combined with the classification result and the degree of association of the screen, it is determined whether retesting is required. For example, for the associated screens in the high-risk screen set "H01", a retesting instruction is directly generated according to its unique identification code. The specific items, parameters, and execution order of the test are specified in the instruction, such as display brightness deviation test or touch latency detection, and the unique identification code is associated with the retesting result to ensure the consistency of the tracked data. For the screens in the medium-risk screen set "M01", it is determined whether partial retesting is required according to the degree of association. For example, only a partial re-inspection of the touch function is performed, while the screens in the low-risk screen set "L01" are marked as "no retesting required", and the unique identification code is only used as a tracking record without generating actual operations. In this way, according to the coding information, the screens that need to be tested and the specific operation requirements can be quickly distinguished, and at the same time, the retesting results are recorded and sent back to the database to form a complete quality management closed loop.

[0060] In summary, by determining the degree of association of each associated screen according to the prediction result, the relationship between the screen and the abnormality can be quantified, providing a basis for further classification management; by classifying each associated screen according to the degree of association to determine different screen sets, grouped management of the screens can be achieved, thereby improving the processing efficiency of abnormal screens; by assigning a front-end code to each screen set and a back-end code to each associated screen in the screen set, an efficient combination of screen classification and individual identification can be achieved, thereby ensuring the accuracy of the tracking process; by integrating the front-end code and the back-end code to generate and record the unique identification code, a unique identity identifier can be assigned to each associated screen, facilitating subsequent data management and tracking; by determining whether to perform retesting on the associated screen according to the unique identification code, intelligent decision-making can be carried out based on the identification data, effectively avoiding unnecessary retesting operations, improving the testing efficiency and saving costs.

[0061] It should be understood that the magnitudes of the sequence numbers of the steps in the above embodiments do not mean the order of execution. The order of execution of each process should be determined according to its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of the present application.

[0062] In one embodiment, a mobile phone screen testing device is provided. The mobile phone screen testing device corresponds one-to-one to the mobile phone screen testing method in the above embodiment. As Figure 7 shown, the mobile phone screen testing device includes a positioning module, a testing module, an acquisition module, a generation module, and a determination module. The detailed description of each functional module is as follows: A mobile phone screen testing device, the mobile phone screen testing device includes: A positioning module, which is used to locate and grab the screen to be tested onto the test bench based on machine vision positioning technology; A testing module, which is used to light up the screen to be tested and perform display function testing and touch function testing on the screen to be tested, so as to generate corresponding test results; An acquisition module, which is used to obtain a production process data set if the test result is that the screen is abnormal; A generation module, which is used to generate corresponding association results based on the established association algorithm model according to the test result and the production process data set; A determination module, which is used to determine corresponding associated screens and device control parameters according to the association result. The device control parameters at least include alarm parameters and operation adjustment parameters, generate and record unique identification codes for each of the associated screens, and determine whether to perform a retest operation on the associated screens.

[0063] Optionally, the testing module includes: An initialization unit, which is used to initialize the circuit module of the screen to be tested, make the screen to be tested enter a testable state, send a lighting instruction to the screen to be tested, and make the screen to be tested display a predetermined test image. The test image includes a single-color image, a gradient-color image, and a complex pattern image; A capture unit, which is used to capture the test image of the screen to be tested in real time based on an image capture device, and analyze the captured test image based on an image processing algorithm to generate corresponding display performance parameters. The display performance parameters include a brightness parameter, a color accuracy parameter, and an abnormal point parameter, and determine whether the display performance parameters are qualified; A first determination unit, which is used to determine that the display test result of the display function test is that the screen is abnormal if the display performance parameters are unqualified; A generation unit, which is used to generate corresponding touch performance parameters by simulating touch operations to apply touch signals to different areas of the screen to be tested if the display performance parameters are qualified. The touch performance parameters include a response sensitivity parameter, a multi-touch function parameter, and a touch accuracy parameter, and determine whether the touch performance parameters are qualified; A second determination unit, which is used to determine that the touch test result of the touch function test is that the screen is abnormal if the touch performance parameters are unqualified; A third determination unit, which is used to determine that both the display test result and the touch test result are that the screen is normal if the touch performance parameters are qualified; Optionally, the acquisition module includes: A fourth determination unit, which is used to determine that the screen to be tested that has undergone the display function test and the touch function test is the target screen if the test result is that the screen is abnormal; The first acquisition unit is configured to acquire the product serial number of the target screen and trace the corresponding raw material batch data; The second acquisition unit is configured to acquire the device operation status data used in the production process of the target screen; The third acquisition unit is configured to acquire the production environment data of various indicators of the production environment during the production process of the target screen; The first integration unit is configured to perform feature extraction on the raw material batch data, the device operation status data, and the production environment data, convert the extracted key data into standardized data that can be directly calculated by the established association algorithm model, and integrate each piece of the standardized data to generate the production process data set; Optionally, the generation module includes: The first generation unit is configured to substitute the test result and the production process data set into the established association algorithm model to generate corresponding feature vectors; The matching unit is configured to match corresponding historical training data according to the feature vectors; The calling unit is configured to call the association rule derivation module in the association algorithm model and derive at least corresponding association rules and dynamic adjustment rules according to the historical training data; The second integration unit is configured to integrate the association rules and the dynamic adjustment rules to generate corresponding association results; Optionally, the determination module includes: The fifth determination unit is configured to determine the to-be-tested screens in the same batch as the target screen as first-level critical screens, and determine the to-be-tested screens in adjacent batches to the target screen as second-level critical screens; The second generation unit is configured to perform abnormal risk prediction on the first-level critical screens and the second-level critical screens according to the association rules, generate corresponding prediction results, and judge whether each of the first-level critical screens and / or each of the second-level critical screens is an associated screen according to the prediction results; The third generation unit is configured to, after configuring corresponding association weights for each piece of the standardized data according to the dynamic adjustment rules, calculate the sum of the products of each piece of the standardized data and the association weights, and further generate a corresponding calculation result, and determine corresponding device control parameters according to the calculation result; Optionally, the determination module further includes: The sixth determination unit is configured to determine the association degree of each of the associated screens according to the prediction results; The seventh determination unit is configured to classify each of the associated screens according to the association degree to determine different screen sets; An assignment unit for assigning a front - end code to each of the screen sets and assigning a back - end code to each of the associated screens in the screen sets; A third integration unit for integrating the front - end code and the back - end code to generate and record a unique identification code; A judgment unit for judging whether to perform a retest operation on the associated screen according to the unique identification code.

[0064] For the specific limitations of a mobile phone screen testing device, reference can be made to the limitations of a mobile phone screen testing method in the above text, which will not be elaborated here. Each module in the above - mentioned mobile phone screen testing device can be implemented in whole or in part by software, hardware, and their combinations. The above - mentioned modules can be embedded in the processor of the computer device in hardware form or be independent of it, or can be stored in the memory of the computer device in software form, so as to facilitate the processor to call and execute the operations corresponding to the above - mentioned modules.

[0065] In one embodiment, a computer device is provided. The computer device can be a server, and its internal structure diagram can be as Figure 8 shown. The computer device includes a processor, a memory, a network interface, and a database connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non - volatile storage medium and an internal memory. The non - volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non - volatile storage medium. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, it realizes a mobile phone screen testing method.

[0066] In one embodiment, a computer device is provided, including a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the computer program, the following steps are implemented: S10. Based on machine vision positioning technology, position and grab the screen to be tested onto the test bench; S20. Light up the screen to be tested and perform a display function test and a touch function test on the screen to be tested to generate corresponding test results; S30. If the test result is that the screen is abnormal, obtain the production process data set; S40. Based on the established association algorithm model, generate corresponding association results according to the test results and the production process data set; S50. Determine the corresponding associated screen and device control parameters according to the association result. The device control parameters at least include alarm parameters and operation adjustment parameters. Generate and record a unique identification code for each associated screen, and determine whether to perform a retest operation on the associated screen.

[0067] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the following steps are implemented: S10. Based on the machine vision positioning technology, locate and grab the screen to be tested onto the test bench. S20. Light up the screen to be tested, and perform a display function test and a touch function test on the screen to be tested to generate corresponding test results. S30. If the test result is that the screen is abnormal, obtain the production process data set. S40. Based on the established association algorithm model, generate corresponding association results according to the test results and the production process data set. S50. Determine the corresponding associated screen and device control parameters according to the association result. The device control parameters at least include alarm parameters and operation adjustment parameters. Generate and record a unique identification code for each associated screen, and determine whether to perform a retest operation on the associated screen.

[0068] Those of ordinary skill in the art can understand that all or part of the processes of implementing the methods in the above embodiments can be completed by instructing relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above methods. Among them, any reference to a memory, storage, database, or other medium used in the various embodiments provided in the present application can include non-volatile and / or volatile memories. Non-volatile memories can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memories can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0069] Those skilled in the art can clearly understand that, for the convenience and conciseness of description, only the above-mentioned division of each functional unit and module is used as an example. In actual applications, the above-mentioned functions can be allocated to different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above.

[0070] The above-described embodiments are only used to illustrate the technical solutions of the present application, rather than to limit it; although the present application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements for some of the technical features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.

Claims

1. A method for testing a mobile phone screen, characterized in that, The described mobile phone screen testing method includes: Based on machine vision positioning technology, position and capture the screen to be tested onto the test bench; Light up the screen to be tested, and perform display function testing and touch function testing on the screen to be tested to generate corresponding test results; If the test result indicates screen abnormality, obtain the production process data set; Based on the established correlation algorithm model, generate corresponding correlation results according to the test results and the production process data set; According to the correlation results, determine the corresponding correlated screens and device control parameters. The device control parameters at least include alarm parameters and operation adjustment parameters. Generate and record unique identification codes for each of the correlated screens, and determine whether to perform retesting operations on the correlated screens.

2. The mobile phone screen testing method according to claim 1, characterized in that In the step of lighting up the screen to be tested and performing display function testing and touch function testing on the screen to be tested to generate corresponding test results, the test results include display test results and touch test results. The step further includes: Initialize the circuit module of the screen to be tested to make the screen to be tested enter a testable state, send a lighting instruction to the screen to be tested to make the screen to be tested display a predetermined test image. The test image includes a single-color image, a gradient color image, and a complex pattern image; Based on an image capture device, capture the test image of the screen to be tested in real time, and analyze the captured test image based on an image processing algorithm to generate corresponding display performance parameters. The display performance parameters include brightness parameters, color accuracy parameters, and abnormality point parameters, and determine whether the display performance parameters are qualified; If the display performance parameters are unqualified, determine that the display test result of the display function test is screen abnormality; If the display performance parameters are qualified, apply touch signals in different areas of the screen to be tested through simulated touch operations, and then generate corresponding touch performance parameters. The touch performance parameters include response sensitivity parameters, multi-touch function parameters, and touch accuracy parameters, and determine whether the touch performance parameters are qualified; If the touch performance parameters are unqualified, determine that the touch test result of the touch function test is screen abnormality; If the touch performance parameters are qualified, determine that both the display test result and the touch test result are screen normal.

3. A mobile phone screen testing method according to claim 1, characterized in that, In the step of if the test result is screen abnormality, obtain the production process data set, it includes: If the test result is screen abnormality, determine the screen to be tested that has undergone the display function test and the touch function test as the target screen; Obtain the product serial number of the target screen and trace the corresponding raw material batch data; Obtain the device operation status data used by the target screen during the production process; Obtain the production environment data of various indicators of the production environment during the production process of the target screen; Extract features from the raw material batch data, the equipment operation status data, and the production environment data, convert the extracted key data into standardized data that can be directly calculated by the established association algorithm model, and integrate the standardized data to generate the production process dataset.

4. The mobile phone screen testing method according to claim 3, characterized in that In the step of generating the corresponding association result based on the established association algorithm model, according to the test result and the production process dataset, it includes: Substitute the test result and the production process dataset into the established association algorithm model to generate the corresponding feature vector; Match the corresponding historical training data according to the feature vector; Call the association rule derivation module in the association algorithm model to derive at least the corresponding association rule and dynamic adjustment rule according to the historical training data; Integrate the association rule and the dynamic adjustment rule to generate the corresponding association result.

5. The method for testing a mobile phone screen according to claim 4, characterized in that, In the step of determining the corresponding association screen and equipment control parameter according to the association result, it includes: Determine the to-be-tested screen in the same batch as the target screen as the first-level key screen, and determine the to-be-tested screens in the adjacent batches to the target screen as the second-level key screens; According to the association rule, perform abnormal risk prediction on the first-level key screen and the second-level key screen to generate the corresponding prediction result, and judge whether each of the first-level key screens and / or each of the second-level key screens is an association screen according to the prediction result; After configuring the corresponding association weight for each of the standardized data according to the dynamic adjustment rule, calculate the sum of the products of each of the standardized data and the association weight, and then generate the corresponding calculation result, and determine the corresponding equipment control parameter according to the calculation result.

6. The mobile phone screen testing method according to claim 5, wherein In the step of generating and recording a unique identification code for each of the association screens and judging whether to perform the retest operation on the association screens, it includes: Determine the association degree of each of the association screens according to the prediction result; Classify each of the association screens according to the association degree to determine different screen sets; Assign a front segment code to each of the screen sets, and assign a back segment code to each of the association screens in the screen set; Integrate the front segment code and the back segment code to generate and record the unique identification code; Judge whether to perform the retest operation on the association screens according to the unique identification code.

7. A mobile phone screen testing device, characterized in that, The mobile phone screen testing device includes: A positioning module for positioning and grasping the to-be-tested screen to the test bench based on machine vision positioning technology; A testing module for lighting the to-be-tested screen and performing a display function test and a touch function test on the to-be-tested screen to generate the corresponding test result; An acquisition module for acquiring the production process dataset if the test result is a screen anomaly; A generation module for generating the corresponding association result based on the established association algorithm model according to the test result and the production process dataset; A determination module, configured to determine corresponding associated screens and device control parameters according to the association result, where the device control parameters at least include alarm parameters and operation adjustment parameters, generate and record unique identification codes for each of the associated screens, and determine whether to perform a retest operation on the associated screens.

8. A mobile phone screen testing device according to claim 7, characterized in that, The test module includes: An initialization unit, configured to initialize the circuit module of the screen to be tested, put the screen to be tested into a testable state, send a lighting instruction to the screen to be tested, and cause the screen to be tested to display a predetermined test image, where the test image includes a single-color image, a gradient-color image, and a complex pattern image; A capture unit, configured to capture the test image of the screen to be tested in real time based on an image capture device, analyze the captured test image based on an image processing algorithm, generate corresponding display performance parameters, where the display performance parameters include a brightness parameter, a color accuracy parameter, and an abnormal point parameter, and determine whether the display performance parameters are qualified; A first determination unit, configured to determine that the display test result of the display function test is that the screen is abnormal if the display performance parameters are unqualified; A generation unit, configured to, if the display performance parameters are qualified, apply touch signals to different areas of the screen to be tested through a simulated touch operation, and then generate corresponding touch performance parameters, where the touch performance parameters include a response sensitivity parameter, a multi-touch function parameter, and a touch accuracy parameter, and determine whether the touch performance parameters are qualified; A second determination unit, configured to determine that the touch test result of the touch function test is that the screen is abnormal if the touch performance parameters are unqualified; A third determination unit, configured to determine that both the display test result and the touch test result are that the screen is normal if the touch performance parameters are qualified; The acquisition module includes: A fourth determination unit, configured to determine that the screen to be tested that has passed the display function test and the touch function test is a target screen if the test result is that the screen is abnormal; A first acquisition unit, configured to acquire the product serial number of the target screen and trace the corresponding raw material batch data; A second acquisition unit, configured to acquire the device operation status data used in the production process of the target screen; A third acquisition unit, configured to acquire the production environment data of various indicators of the production environment during the production process of the target screen; A first integration unit, configured to perform feature extraction on the raw material batch data, the device operation status data, and the production environment data, convert the extracted key data into standardized data that can be directly calculated by the established association algorithm model, and integrate each of the standardized data to generate the production process data set; The generation module includes: A first generation unit, configured to substitute the test result and the production process data set into the established association algorithm model to generate corresponding feature vectors; A matching unit, configured to match corresponding historical training data according to the feature vectors; A calling unit, configured to call an association rule derivation module in the association algorithm model to derive at least corresponding association rules and dynamic adjustment rules according to the historical training data; A second integration unit, configured to integrate the association rules and the dynamic adjustment rules to generate corresponding association results; The determination module includes: A fifth determination unit, configured to determine the to-be-tested screens in the same batch as the target screen as first-level critical screens, and determine the to-be-tested screens in adjacent batches to the target screen as second-level critical screens; A second generation unit, configured to perform abnormal risk prediction on the first-level critical screens and the second-level critical screens according to the association rules to generate corresponding prediction results, and determine whether each of the first-level critical screens and / or each of the second-level critical screens is an associated screen according to the prediction results; A third generation unit, configured to calculate the sum of the products of each of the standardized data and the association weights after configuring corresponding association weights for each of the standardized data according to the dynamic adjustment rules, and further generate a corresponding calculation result, and determine corresponding device control parameters according to the calculation result; The determination module further includes: A sixth determination unit, configured to determine the association degree of each of the associated screens according to the prediction results; A seventh determination unit, configured to classify each of the associated screens according to the association degree to determine different screen sets; An assignment unit, configured to assign a front-end code to each of the screen sets and assign a back-end code to each of the associated screens in the screen sets; A third integration unit, configured to integrate the front-end code and the back-end code to generate and record a unique identification code; A judgment unit, configured to judge whether to perform a retest operation on the associated screens according to the unique identification code.

9. A computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, the steps of a mobile phone screen testing method according to any one of claims 1 to 6 are implemented.

10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by a processor, the steps of a mobile phone screen testing method according to any one of claims 1 to 6 are implemented.

Citation Information

Cited By

  • Image quality test method, test system and computer readable storage medium

    CN121148265A