Display screen bottom shell intelligent assembly control method and device

Abstract

The invention discloses an intelligent assembly control method and device for a display screen bottom shell, and relates to the technical field of intelligent assembly, and the method comprises the steps: collecting an assembly image, and obtaining a preset assembly image; analyzing the deviation between the assembly image and a preset image to obtain assembly deviation distribution; analyzing the display error based on the assembly deviation distribution, obtaining a display error parameter, and calculating the assembly fitness; according to the error parameters and the deviation distribution, an assembly adjustment step length is configured, and assembly positioning optimization is carried out; and adjusting the assembly positions of the display module and the bottom shell according to the optimization scheme to complete accurate assembly. The technical problem that the accuracy is insufficient in the existing display screen assembling process is solved, and the technical effect of improving the display screen assembling accuracy is achieved through intelligent assembling deviation analysis, display error influence analysis and assembling positioning optimization.

Description

Technical Field

[0001] The present application relates to the field of intelligent assembly technology, and in particular to a method and device for intelligent assembly control of a display screen bottom shell. Background Art

[0002] In the manufacturing process of modern display screens, the precise assembly of the display module and the bottom shell is the core to ensure the display quality. However, the existing display screen assembly technology has problems such as insufficient precision, large deviation and low adjustment efficiency. Traditional methods mostly rely on manual or simple mechanical devices for assembly, which cannot guarantee the efficient and accurate docking of each device, resulting in impaired display effects, such as image offset and inaccurate alignment. The above problems not only affect product quality, but also increase production costs. Therefore, the industry urgently needs a new solution to improve assembly accuracy, optimize production efficiency, and solve the limitations of traditional technologies.

[0003] In the current related technologies, there is a technical problem of insufficient precision in the display screen assembly process. Summary of the invention

[0004] The present application solves the technical problem of insufficient precision in the existing display screen assembly process by providing a display screen bottom shell intelligent assembly control method and device.

[0005] The present application provides a display screen bottom shell intelligent assembly control method, comprising: When the display module is assembled and positioned on the bottom shell of the display screen, an assembly image is collected to obtain an assembly image; a preset assembly image is obtained, and an assembly deviation analysis is performed on the assembly image to obtain an assembly deviation distribution; a display error impact analysis is performed based on the assembly deviation distribution to obtain display error parameters, and assembly fitness is calculated; based on the display error parameters and in combination with the assembly deviation distribution, an assembly adjustment step is configured to adjust the assembly, perform assembly positioning optimization, and obtain an optimal assembly positioning solution; according to the optimal assembly positioning solution, the display module is assembled on the bottom shell of the display screen.

[0006] The present application provides a display screen bottom shell intelligent assembly control device, comprising: An assembly image acquisition module, the assembly image acquisition module is used to collect assembly images when the display module is assembled and positioned to the bottom shell of the display screen to obtain an assembly image; an assembly deviation distribution acquisition module, the assembly deviation distribution acquisition module is used to obtain a preset assembly image, perform assembly deviation analysis on the assembly image, and obtain assembly deviation distribution; a display error impact analysis module, the display error impact analysis module is used to perform display error impact analysis based on the assembly deviation distribution, obtain display error parameters, and calculate assembly fitness; an adjustment step configuration module, the adjustment step configuration module is used to configure the assembly adjustment step based on the display error parameters and the assembly deviation distribution, adjust the assembly, perform assembly positioning optimization, and obtain an optimal assembly positioning solution; a display screen bottom shell assembly module, the display screen bottom shell assembly module is used to assemble the display module to the bottom shell of the display screen according to the optimal assembly positioning solution.

[0007] The intelligent assembly control method and device for the bottom shell of a display screen proposed in this application first collect an assembly image and obtain a preset assembly image; analyze the deviation between the assembly image and the preset image to obtain the assembly deviation distribution; analyze the display error based on the assembly deviation distribution, obtain the display error parameters, and calculate the assembly fitness; configure the assembly adjustment step according to the error parameters and the deviation distribution, and perform assembly positioning optimization; adjust the assembly position of the display module and the bottom shell according to the optimization plan to complete precise assembly, and achieve the technical effect of improving the assembly accuracy of the display screen through intelligent assembly deviation analysis, display error impact analysis and assembly positioning optimization. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] In order to more clearly illustrate the technical solution of the embodiment of the present disclosure, the accompanying drawings of the embodiment of the present disclosure will be briefly introduced below. A flow chart is used in the present application to illustrate the operations performed by the system according to the embodiment of the present application. It should be understood that the preceding or following operations are not necessarily performed accurately in order. On the contrary, various steps can be processed in reverse order or simultaneously as needed. At the same time, other operations can also be added to these processes, or one or more operations can be removed from these processes.

[0009] Figure 1 A schematic flow chart of a method for controlling the intelligent assembly of a display screen bottom shell provided in an embodiment of the present application; Figure 2 A schematic structural diagram of a display screen bottom shell intelligent assembly control device provided in an embodiment of the present application.

[0010] Description of reference numerals: assembly image acquisition module 10 , assembly deviation distribution acquisition module 20 , display error influence analysis module 30 , adjustment step configuration module 40 , display screen bottom shell assembly module 50 . DETAILED DESCRIPTION

[0011] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below.

[0012] In order to make the objectives, technical solutions and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings. The described embodiments should not be regarded as limiting the present application. All other embodiments obtained by ordinary technicians in the field without making creative work are within the scope of protection of this application.

[0013] In the following description, reference is made to "some embodiments", which describe a subset of all possible embodiments, but it is understood that "some embodiments" may be the same subset or different subsets of all possible embodiments, and may be combined with each other without conflict, and the terms "first\second" involved are merely to distinguish similar objects and do not represent a specific ordering of objects. The terms "including" and "having" and any variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product, or server that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or modules that are not clearly listed or inherent to these processes, methods, products, or devices. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those generally understood by technicians in the technical field of this application. The terms used herein are for the purpose of describing the embodiments of the present application only.

[0014] The present application embodiment provides a display screen bottom shell intelligent assembly control method, such as Figure 1 As shown, the method includes: Step S100, when the display module is assembled and positioned to the bottom shell of the display screen, an assembly image is collected to obtain an assembly image. Specifically, when the display module is assembled and positioned to the bottom shell of the display screen, an assembly image is collected in real time by a high-resolution industrial camera to monitor the position deviation that may occur during the assembly process. Deviations include translation deviation (the horizontal or vertical movement of the module relative to the bottom shell, for example, the deviation distance between the module frame and the bottom shell reference line is 0.5mm), rotation deviation (the module is not parallel to the edge of the bottom shell, such as the rotation angle deviation reaches 1°), height deviation (the module is not completely fitted to the bottom shell, the height difference is about 0.2mm), and assembly misalignment (such as the fastener hole is not aligned with the bottom shell hole position, offset by 2 pixels). The collected image is grayed, and the reference points, edges and other features of the module and the bottom shell are extracted by edge detection (such as the Canny algorithm), the relative offset is calculated, and the specific deviation type and size are determined. For example, when it is detected that the upper and lower margins of the module edge are inconsistent with the distance of the bottom shell reference line, it can be identified as a translation deviation, and adjustment parameters are provided according to the position offset. The trigger mechanism automatically takes pictures when the assembly robot is positioned at the specified position, ensuring that image acquisition is synchronized with the assembly steps. The collected assembly images not only provide basic data for subsequent deviation distribution analysis, but are also used for assembly positioning optimization and final assembly result verification to ensure assembly accuracy and stability.

[0015] Step S200, obtain a preset assembly image, perform assembly deviation analysis on the assembly image, and obtain assembly deviation distribution. Specifically, in the display module assembly process, the SGBM algorithm (semi-global block matching) is used to perform assembly deviation analysis by obtaining the preset assembly image and combining it with the actual assembly image. First, the two images are grayed and divided into multiple 10×10 pixel assembly windows according to the assembly unit. For example, the window in the actual image Multiple candidate windows in the preset image To calculate the grayscale similarity, the formula is: in is the grayscale value of each pixel in the window. Select the one with the highest similarity As the best matching window, the mapping conflicts are eliminated through traversal optimization. The deviation value is calculated by the window center coordinates. For example, the deviation formula is like The deviation is 2.83 pixels. Finally, the assembly deviation distribution matrix is ​​formed, and the deviation size is visualized with a heat map (red represents high deviation areas), providing accurate data support for assembly adjustment and optimization.

[0016] In a possible implementation, a preset assembly image is obtained, and an assembly deviation analysis is performed on the assembly image to obtain the assembly deviation distribution. Step S200 further includes step S210, obtaining a preset assembly image, and the preset assembly image is an assembly image under standard conditions. Specifically, in the process of obtaining the preset assembly image, it is first necessary to ensure that the display module and the bottom shell are in a standard assembly state, that is, the edges of the module and the bottom shell are completely parallel, the alignment error is less than 0.1mm, and the ambient light is uniform without reflection or shadow. Use a high-resolution industrial camera (more than 2 million pixels) to vertically align the assembly area, combine with a ring LED light source to shoot, and collect high-quality images. Before acquisition, the camera is corrected for geometric distortion by a checkerboard calibration plate to ensure that the image is not distorted. After the acquisition is completed, the image is grayed (such as the pixel gray value of RGB values ​​100, 150, 200 is calculated as 142), and the reference points are aligned to map the four corners of the module frame to a fixed coordinate system. In addition, the image resolution is unified (such as 1920×1080 pixels) to match the subsequent analysis requirements and saved in a lossless format (such as PNG or TIFF). For example, the collected preset assembly image shows that the coordinates of the four corners of the module frame are (10,10), (190,10), (10,100), (190,100), which are used as a standard reference for comparison and analysis with the actual assembly image, providing a reliable basis for assembly deviation detection and optimization.

[0017] Step S220, grayscale the preset assembly image and the assembly image to obtain a grayscale assembly image and a grayscale preset assembly image. Specifically, when grayscale the preset assembly image and the assembly image, first convert the color pixel value (RGB) of each image into a single-channel grayscale value. The grayscale formula is: Where R, G, and B are the red, green, and blue components of the pixel, respectively. For example, the grayscale value of a pixel with R, G, and B values ​​of (100, 150, 200) is calculated to be 142. During processing, all pixels of the image are traversed one by one, the grayscale value of each pixel is calculated and updated to the grayscale image matrix, and finally a grayscale assembly image and a grayscale preset assembly image are generated. The grayscale image reduces the computational complexity and only retains the brightness information, making it easier to perform pixel position deviation analysis and assembly optimization. At the same time, in order to avoid the influence of uneven lighting or noise on the grayscale value, a ring LED light source should be used for fill light before grayscale conversion, and Gaussian filtering should be applied to the image for denoising to ensure brightness uniformity and data consistency. This processing process provides a unified brightness benchmark for subsequent pixel comparison and deviation calculation.

[0018] Step S230, performing pixel position deviation analysis on the grayscale assembly image and the grayscale preset assembly image to obtain multiple position deviation sets. Specifically, performing pixel position deviation analysis on the grayscale assembly image and the grayscale preset assembly image, first divide the two images into multiple pixel windows of fixed size (such as 10×10 pixels), and compare the windows in the grayscale assembly image with the candidate windows in the grayscale preset assembly image one by one. By calculating the window similarity, the window with the highest similarity is selected as the best match. For example, if the grayscale value set of a window is [120, 122, 125, 127], and the candidate windows are [118, 121, 124, 126] and [130, 133, 135, 138], and the similarities are 1 and 10.25 respectively, then the best matching window is [118, 121, 124, 126]. Subsequently, the pixel position deviation of the center of the matching window is calculated, and the formula is: For example, if the window center coordinates are (50,60) and (52,58), the deviation value is 2.83 pixels. Finally, a set containing the deviation values ​​of each window is generated. For example, (10,10,1.5)(10,10,1.5)(10,10,1.5) means that the deviation of a certain window is 1.5 pixels. The position deviation set clearly describes the error distribution of the assembly area and provides an accurate reference for optimizing the assembly position.

[0019] Step S240, traverse and combine the optimization of the multiple position deviation sets to obtain the assembly deviation distribution. Specifically, when traversing and combining the optimization of the multiple position deviation sets, first, for each window in the grayscale assembly image, randomly select one from the candidate matching windows as the initial match, and calculate its deviation value, and accumulate the deviation values ​​of all windows to form the initial total deviation. Then, all possible matching combinations are traversed, the total deviation value of each combination is calculated one by one, and the combination with the smallest deviation value is selected as the optimal matching solution. In this process, the optimal matching results of some windows can be recorded by dynamic programming to avoid repeated calculations and improve efficiency. In addition, the stability of the results is enhanced by setting smooth constraints on the deviations of adjacent windows (such as limiting the deviation changes of adjacent windows to a certain range). The assembly deviation distribution finally generated records the center position of each window and its optimized deviation value, for example, the center position of a window is (10,10), and the optimized deviation value is 1.5 pixels. This optimization method ensures the accuracy of the deviation distribution and provides an accurate reference for assembly adjustment.

[0020] In a possible implementation, the grayscale assembly image and the grayscale preset assembly image are subjected to pixel position deviation analysis to obtain multiple position deviation sets, and step S230 further includes step S231, setting an assembly pixel window according to the assembly unit size of the display module. Specifically, the assembly pixel window is set according to the assembly unit size of the display module, and the corresponding pixel size is first calculated according to the actual physical size of the assembly unit (such as the module frame width is 1mm, the fastener spacing is 5mm) and the image resolution (such as 200 pixels / mm). For example, a 1mm wide frame corresponds to 200 pixels, and the window size can be set to 200×200 pixels. Subsequently, the grayscale assembly image is divided into multiple non-overlapping windows according to the set window size, starting from the upper left corner and divided row by row and column by column to ensure that each window covers the key assembly feature area. For an image of 1920×1080 pixels, after setting a window of 200×200 pixels, it can be divided into 45 windows (9 horizontally and 5 vertically). Each window is used as an independent analysis unit to calculate the gray value similarity and position deviation. If a specific area (such as around a fastener) requires higher precision, the window size can be dynamically adjusted (such as reduced to 100×100 pixels). The above setting method not only accurately matches the assembly features, but also optimizes the calculation efficiency, providing reliable support for assembly deviation analysis and automated adjustment.

[0021] Step S232, according to the assembly pixel window, the first window is obtained by dividing in the grayscale assembly image. Specifically, in the process of dividing the grayscale assembly image according to the assembly pixel window to obtain the first window, the size of the assembly pixel window is first determined, and the window size is set to 200×200 pixels according to the actual size of the display module assembly unit (such as 1mm wide frame corresponds to 200 pixels). Then, starting from the upper left corner of the grayscale assembly image, it is divided row by row and column by column according to the window size, and each division generates a rectangular area as a window. Taking a 1920×1080 pixel image as an example, after division, 9 windows are generated in the horizontal direction and 5 windows are generated in the vertical direction, totaling 45 windows, of which the first rectangular area in the upper left corner is the first window, and its pixel range is 0 to 199 pixels horizontally and 0 to 199 pixels vertically. If the image edge cannot divide the window size, zero padding can be used to ensure that all window sizes are consistent. The grayscale value set of each window is stored independently, providing data support for subsequent similarity calculation and deviation analysis, and realizing refined partitioning of the assembly area.

[0022] Step S233, according to the assembly pixel window, traverse and divide the grayscale preset assembly image to obtain multiple preset windows. Specifically, in the process of traversing and dividing the preset windows according to the assembly pixel window in the grayscale preset assembly image, the window division range is first determined according to the size of the assembly pixel window (such as 200×200 pixels). In order to cover the possible assembly offset area, a traversal range is defined based on the center of the first window. For example, if the offset may be within ±20 pixels, the traversal range is ±20 pixels of the center coordinate (such as from 380 to 420 pixels). Then, the traversal range is divided row by row and column by column with the window size as the step size (such as 200 pixels) to generate multiple rectangular preset windows. If a more precise match is required, the step size can be set to be smaller than the window size (such as 100 pixels) to form overlapping windows. The center coordinates, boundary position and grayscale value set of each preset window are recorded for subsequent similarity calculation and position deviation analysis. For example, the center coordinates of a window are (410, 410), the boundaries are (310, 310) to (510, 510), and its grayscale value set is [120, 122, 125, ...]. This ensures that the assembly deviation analysis covers all possible offset ranges and provides sufficient data support for assembly accuracy optimization.

[0023] Step S234, taking the multiple first grayscale values ​​in the first window as a reference, calculate the similarity between the preset grayscale value set in the multiple preset windows and the multiple first grayscale values, and obtain the first window similarity set. Specifically, taking the grayscale value set of the first window as a reference, calculate its similarity with the grayscale value set of multiple preset windows, first extract the grayscale values ​​in the first window, such as 120, 122, 125, and traverse each preset window at the same time to extract its grayscale value set, such as 118, 121, 124 and 130, 133, 135. Then, use the similarity formula to perform window-by-window calculations, for example, use the absolute difference average formula to calculate, and the result is that the similarity between the first window and the preset windows 118, 121, 124 is 0.67, and the similarity with 130, 133, 135 is 0.33. By calculating the similarity values ​​of all preset windows, a similarity set is formed, such as {(preset window 1, 0.67), (preset window 2, 0.33)}, and sorting them in descending order according to the similarity value to select the preset window with the highest matching degree with the first window. This provides data support for assembly deviation analysis, ensuring that the preset window with the most similar features to the first window is selected, which facilitates accurate identification of assembly error areas.

[0024] Step S235, according to the coordinate values ​​of the plurality of preset windows and the first window in the preset assembly image and the first assembly image, calculate and obtain the plurality of first distances between the plurality of preset windows and the first window, and obtain the first position deviation set. Specifically, the first position deviation set is obtained by calculating the coordinate distances between the plurality of preset windows and the first window. First, the center coordinates of the first window are extracted. For example, if the upper left corner of the first window is (200, 200) and the size is 200×200 pixels, the center coordinates are (300, 300). Subsequently, all preset windows in the grayscale preset assembly image are traversed to extract their center coordinates. For example, if the upper left corner of a preset window is (280, 280), its center coordinates are (380, 380). The distance between the first window and each preset window is calculated using the Euclidean formula. The center coordinates of all preset windows and their calculated distances are recorded as a position deviation set, for example, {(preset window 1, 113.14), (preset window 2, 50.00)}. The position deviation set is used to intuitively reflect the physical offset in the assembly. Combined with the grayscale similarity analysis, the preset window that best matches the first window can be screened out to provide data support for assembly accuracy optimization.

[0025] Step S236, continue to divide multiple windows in the grayscale assembly image, combine the multiple preset windows, and calculate multiple window similarity sets and multiple position deviation sets. Specifically, continue to divide multiple windows in the grayscale assembly image, and calculate the similarity set and position deviation set in combination with the preset windows. The specific process is: first, divide the grayscale assembly image row by row and column by column according to the preset assembly pixel window size (such as 200×200 pixels), and extract the grayscale value set of each window. Then, each window is compared with multiple preset windows in the grayscale preset assembly image, and the grayscale value similarity is calculated using a similarity formula (such as an absolute difference average formula). For example, the grayscale value set of a certain window is 120, 122, 125, and the grayscale value set of the preset window is 118, 121, 124, and the similarity is 0.67. At the same time, the center coordinates of each window and the preset window are extracted, and the position deviation is calculated using the Euclidean formula. For example, the center of the window is (300, 300), the center of the preset window is (280, 280), and the position deviation is 28.28 pixels. Finally, a similarity set and a position deviation set for each window are formed, such as {(preset window 1, 0.67, 28.28), (preset window 2, 0.45, 45.00)}. These data are used to evaluate the distribution of assembly errors, screen the optimal matching preset window, and provide an accurate reference for assembly adjustment.

[0026] In a possible implementation, the plurality of position deviation sets are traversed and combined for optimization to obtain an assembly deviation distribution, and step S240 further includes step S241, randomly configuring a first mapping relationship between a plurality of windows in the grayscale assembly image and a plurality of preset windows in the preset grayscale assembly image, and extracting and obtaining a first assembly deviation distribution according to the plurality of position deviation sets. Specifically, the process of forming an assembly deviation distribution by randomly configuring a mapping relationship between a grayscale assembly image window and a preset assembly image window is as follows: first, a corresponding preset window is randomly assigned to each grayscale assembly image window, for example, a window Randomly map to preset windows Next, the deviation between the center positions of each pair of mapping windows is calculated. The deviation is obtained by comparing the square root of the sum of the squares of the differences in the horizontal and vertical coordinates of the centers of the two windows. For example, if The center position of is (200,200), and The center position of is (210,210), then its deviation can be described as: the square root of the sum of the squares of the horizontal coordinate difference 200−210200-210200−210 and the vertical coordinate difference 200−210200-210200−210, which is 14.14 pixels. The deviations of all mapping windows are recorded as the assembly deviation distribution, such as By randomly configuring mapping relationships multiple times, the sum or mean of the deviation distributions corresponding to all mapping relationships is calculated, and the group with the smallest deviation is selected as the optimal mapping relationship. Finally, the optimal assembly deviation distribution is generated to guide assembly optimization and error analysis.

[0027] Step S242, based on the plurality of window similarity sets, calculate the sum of the window similarities of the plurality of groups of windows mapped in the first assembly deviation distribution and the preset windows to obtain a first total window similarity. Specifically, the process of calculating the total similarity mapped in the first assembly deviation distribution is as follows: first, extract the mapping relationship between each pair of assembly windows and the preset windows based on the first assembly deviation distribution, for example, Map to preset window Map to Map to Next, the similarity value of each pair of mapping windows is extracted from the corresponding window similarity set, for example, The similarity is 0.94. The similarity is 0.88. The similarity is 0.91. Then, the similarity values ​​are added one by one. The total similarity value reflects the overall matching degree between all mapping windows. The higher the matching degree, the greater the total similarity. Finally, the total similarity value can be used to screen the best matching solution in different mapping relationships, providing data support for assembly optimization.

[0028] Step S243, continue to traverse the randomly configured mapping relationship, and calculate the total window similarity, output the mapping relationship with the largest window similarity, and extract the assembly deviation distribution. Specifically, by traversing the randomly configured mapping relationship and calculating the total window similarity of each group of mappings, the mapping scheme with the best matching degree can be screened out. The specific process is as follows: First, randomly generate a mapping relationship between a grayscale assembly image window and a preset assembly image window, for example, the first window in the assembly image is mapped to the second window in the preset image, the second window in the assembly image is mapped to the first window in the preset image, and so on. Then, extract the corresponding similarity value from the similarity set of each pair of mapping windows, for example, the similarity between the first assembly window and its corresponding preset window is 0.85, the similarity between the second assembly window and its corresponding preset window is 0.88, and the similarity between the third assembly window and its corresponding preset window is 0.90. After adding these similarity values, calculate the total similarity of the group of mapping relationships, for example, the total similarity is 2.63. Next, multiple groups of random mapping relationships are repeatedly generated, the total similarity of each group is calculated one by one, and the sizes of all total similarities are compared. Finally, the mapping relationship with the largest total similarity is selected as the optimal solution. For example, if the total similarity of another group of mapping relationships is 2.71, it is the best mapping solution. Based on the optimal mapping relationship, the assembly deviation of each pair of windows is further calculated. For example, the deviation between the first assembly window and its corresponding preset window is 15 pixels, forming an assembly deviation distribution, such as "the first assembly window is mapped to the second preset window, and the deviation is 15 pixels." In this way, the errors in the assembly process can be fully quantified and optimized, providing accurate data support for improving assembly accuracy.

[0029] Step S300, according to the assembly deviation distribution, the display error impact analysis is performed, the display error parameters are obtained, and the assembly fitness is calculated. Specifically, according to the assembly deviation distribution, the specific impact of the assembly deviation on the display content is analyzed and the assembly fitness is calculated. First, the deviation value of each window is extracted from the assembly deviation distribution, for example, the deviation of a certain window is 10 pixels. Then, in combination with the characteristics of the display content (such as text height, image resolution), the display error parameters are calculated. For example, if the text height is 50 pixels, the deviation of 10 pixels causes the text alignment error amplitude to be 20%. Next, the error parameters of all windows are normalized and the average error parameter is calculated. For example, the error parameters of the two windows are 0.20 and 0.30 respectively, and the average error parameter is 0.25. Finally, the assembly fitness is calculated according to the average error parameter. The formula is 1 minus the average error parameter. For example, the assembly fitness is 0.75, which means that the assembly quality is good. By displaying the error parameters and the assembly fitness, the impact of the assembly on the display content can be quantified, the optimization direction can be clarified, and data support can be provided for improving the assembly accuracy.

[0030] In a possible implementation, according to the assembly deviation distribution, the display error impact analysis is performed to obtain the display error parameters, and the assembly fitness is calculated. Step S300 further includes step S310, according to the historical display screen bottom shell assembly data, the sample assembly deviation distribution set is collected, and the change range of the display content under different sample assembly deviation distributions is obtained, which is marked as the sample display error parameter set. Specifically, according to the historical display screen bottom shell assembly data, the sample assembly deviation distribution set is first collected, and the offset value of each window is recorded. For example, the actual center coordinates of window 1 are (205, 210), and the deviation from the preset center coordinates (200, 200) is 11.18 pixels. Then, the impact of the assembly deviation on the display content is measured, and the change range of the display content is extracted. For example, the text alignment error is calculated by testing the change in the text line spacing. The standard line spacing is 50 pixels, while the actual line spacing is 55 pixels, resulting in an error range of 10%. Similarly, the degree of deformation of the image is calculated by edge detection. For example, the image edge offset is detected, and the deformation range is 15%. These changes are marked as display error parameters, such as 0.2 (normalized value) for text alignment offset parameter and 0.15 for image deformation parameter. Finally, the assembly deviation distribution of each sample and the corresponding display error parameter are stored as training data pairs, providing accurate data support for the construction of subsequent display error prediction models, and quantifying the actual impact of assembly deviation on display content.

[0031] Step S320, using the sample assembly deviation distribution set and the sample display error parameter set as supervised training data, training the display error prediction channel. Specifically, the sample assembly deviation distribution set and the display error parameter set are used as supervised training data to train the display error prediction channel, and establish an accurate mapping between assembly deviation and display error. The specific process is as follows: First, the assembly deviation distribution of each sample (for example, the window deviation is 10.5 pixels) is used as input, and the corresponding display error parameters (such as text offset is 20%, image deformation is 15%) are used as output to construct a training data pair. Then, a supervised learning model such as a multi-layer perceptron is used for training, and the display error parameters are predicted after the assembly deviation distribution is input. During the training process, the error between the model prediction result and the actual display error parameter, such as the mean square error (MSE), is calculated, and the model parameters are optimized by back propagation to gradually reduce the error. Finally, the prediction ability of the model is tested in the validation set, and the hyperparameters are adjusted or the sample diversity is increased to improve the generalization performance. The trained display error prediction channel can be used for real-time input deviation distribution in the actual assembly process. For example, when the current window deviations are 0.21 and 0.25, the model predicts that the text offset is 22% and the image deformation is 18%, providing data support for assembly adjustments and optimizing assembly quality.

[0032] Step S330, input the assembly deviation distribution into the display error prediction channel, and output the display error parameters. Specifically, the process of inputting the assembly deviation distribution into the display error prediction channel is as follows: First, collect the current assembly deviation distribution data, for example, the deviation of window 1 is 10.5 pixels, and the deviation of window 2 is 12.3 pixels. These deviation values ​​are normalized, for example, the maximum deviation is set to 20 pixels, then the normalized result is 0.525 for window 1 and 0.615 for window 2. The normalized deviation distribution is input into the trained display error prediction channel, and the model uses the learned mapping relationship between assembly deviation and display error to output normalized display error parameters, for example, the text offset is 0.18 and the image deformation is 0.12. Finally, the normalized error parameters are denormalized, for example, the text offset parameter 0.18 corresponds to an actual offset of 9 pixels under the maximum error range of 50 pixels, and the image deformation parameter 0.12 corresponds to an actual deformation of 3.6% under the maximum deformation amplitude of 30%. Through this process, the display error parameters can be quickly obtained, providing real-time data support for assembly quality evaluation and adjustment.

[0033] Step S340, calculate the assembly fitness according to the display error parameters, wherein the size of the display error parameters is negatively correlated with the size of the assembly fitness. Specifically, the process of calculating the assembly fitness according to the display error parameters is as follows: First, extract the display error parameters from the current assembly, such as a text offset of 15% and an image deformation of 10%. Normalize these error parameters. For example, if the maximum allowable text offset is 30%, the normalized text offset is 0.5 (15 / 30) and the image deformation is 0.33 (10 / 30). Next, assign weights to different error parameters. For example, the text offset weight is 0.6 and the image deformation weight is 0.4. Calculate the weighted values ​​respectively. The text offset is 0.5×0.6=0.3 and the image deformation is 0.33×0.4=0.132. Then, average the weighted values ​​to obtain a weighted average error of Finally, subtract the weighted average error from 1 to get the assembly fitness of 1-0.216 = 0.784. The higher the assembly fitness, the better the assembly quality; if the fitness is low, the display quality can be optimized by adjusting the assembly parameters.

[0034] Step S400, according to the display error parameters, combined with the assembly deviation distribution, configure the assembly adjustment step, adjust the assembly, optimize the assembly positioning, and obtain the optimal assembly positioning solution. Specifically, according to the display error parameters and the assembly deviation distribution, the process of optimizing the assembly positioning is as follows: First, according to the display error parameters (such as text offset 0.2, image deformation 0.15), select the closest deviation position in the assembly deviation distribution as the optimization target, for example, the assembly deviation corresponding to the text offset is 0.3, and the assembly deviation corresponding to the image deformation is 0.15. Next, configure the adjustment step, the step size is proportional to the display error parameter, for example, the text offset is normalized to 0.2, if the maximum allowable deviation is 20 pixels, then the step size is 0.2×20=40.2 pixels. Adjust the target position according to the step size, for example, adjust the window position from 10 pixels to 6 pixels, then re-collect the assembly image, update the assembly deviation distribution and display error parameters. This process is iterated until the display error parameters converge or the fitness reaches the threshold, and finally output the optimal assembly positioning solution. This method optimizes display quality by dynamically adjusting key points, improving assembly accuracy and achieving efficient assembly control.

[0035] In a possible implementation, according to the display error parameter, combined with the assembly deviation distribution, the assembly adjustment step is configured, the assembly is adjusted, the assembly positioning is optimized, and the optimal assembly positioning solution is obtained. Step S400 further includes step S410, clustering the same position deviations in the assembly deviation distribution to obtain multiple clustered position deviations as multiple candidate adjustment step lengths. Specifically, by performing cluster analysis on the assembly deviation distribution, positions with similar deviation values ​​are classified into one category, the mean of each category is extracted as the clustered position deviation, and these means are used as candidate adjustment step lengths. The specific process is: input assembly deviation distribution data, such as {10, 12, 15, 18, 20, 25, 28}, use a clustering algorithm (such as K-means), divide the data into two groups, for example, group 1 contains {10, 12, 15}, and group 2 contains {18, 20, 25, 28}. The mean of each group is calculated, and the mean of group 1 is 12.33 pixels, and the mean of group 2 is 22.75 pixels, and the cluster position deviation is obtained as {12.33, 22.75}. Finally, the cluster position deviation is used as a candidate adjustment step, providing an accurate adjustment basis for subsequent assembly optimization, which helps to simplify data processing, improve adjustment accuracy, and support dynamic optimization.

[0036] Step S420, calculate the ratio of each candidate adjustment step and the maximum candidate adjustment step, calculate the deviation of each ratio and the display error parameter, and select the candidate adjustment step with the smallest deviation as the assembly adjustment step. Specifically, according to the ratio of the candidate adjustment step and the maximum step, combined with the display error parameter, the process of selecting the optimal assembly adjustment step is as follows: First, calculate the ratio of each candidate adjustment step to the maximum step. For example, if the candidate step is {10, 15, 20, 25} pixels and the maximum step is 25 pixels, the ratio is {0.4, 0.6, 0.8, 1}. Then, calculate the deviation between each ratio and the display error parameter. The deviation formula is deviation = |ratio-display error parameter deviation = |ratio-display error parameter|. Taking the display error parameter of 0.7 as an example, the calculated deviation is {0.3, 0.1, 0.1, 0.3}. Finally, the candidate step size with the smallest deviation is selected as the final assembly adjustment step size. For example, a step size of 15 pixels (corresponding to a ratio of 0.6) is the best choice. This method ensures accurate and efficient assembly optimization by dynamically matching the adjustment step size with the display error, while avoiding over- or under-adjustment.

[0037] In a possible implementation, according to the display error parameter, combined with the assembly deviation distribution, the assembly adjustment step is configured, the assembly is adjusted, the assembly positioning is optimized, and the optimal assembly positioning scheme is obtained. Step S400 further includes step S430, according to the assembly adjustment step, the assembly positioning of the display module and the bottom shell of the display screen is adjusted, and the adjusted assembly image is continued to be collected. Specifically, after the display module and the bottom shell of the display screen are positioned and adjusted according to the assembly adjustment step, the adjusted assembly image needs to be re-collected to update the assembly status information. First, the assembly position is moved according to the adjustment step (such as 4 pixels), for example, the deviation of window 1 is reduced from 10 pixels to 6 pixels, and the deviation of window 2 is reduced from 12 pixels to 8 pixels. Subsequently, the adjusted assembly image is obtained by a high-precision camera device, the image is grayed and edge detected, the deviation value between the actual position of the current assembly window and the standard position is extracted, and the assembly deviation distribution is updated. The adjusted image provides real-time data support for the next round of optimization, ensuring that the assembly positioning gradually approaches the preset standard, and finally achieving precise assembly optimization.

[0038] Step S440, performs assembly deviation analysis and display error analysis on the adjusted assembly image, and calculates the assembly fitness. Specifically, the process of performing assembly deviation analysis and display error analysis on the adjusted assembly image is as follows: First, by comparing the adjusted assembly image with the standard image, calculate the deviation value between the actual position and the standard position of each assembly window, for example, the deviation of window 1 is 4.47 pixels. Next, analyze the display error, including parameters such as text alignment and image deformation, calculate the offset and deformation amplitude respectively, and normalize them. For example, the normalized value of text offset is 0.1, and the normalized value of image deformation is 0.13. Finally, calculate the assembly fitness based on the normalized error parameters and their weights. The formula is: Assuming the weights of text offset and image deformation are 0.6 and 0.4 respectively, the fitness is 0.888. This process fully quantifies the assembly effect and provides clear guidance for further optimization.

[0039] Step S450, continue to optimize the assembly positioning until convergence, and obtain the optimal assembly positioning solution with the maximum assembly fitness. Specifically, the assembly positioning optimization gradually reduces the assembly deviation and display error through multiple iterative adjustments, and calculates the assembly fitness after each adjustment to achieve high-precision assembly. First, the assembly position is adjusted according to the assembly adjustment step calculated in the previous step, and the adjusted assembly image is collected, and the assembly deviation distribution and display error parameters are updated. For example, the deviation of window 1 is reduced from 10 pixels to 6 pixels, and the text offset error is reduced from 0.15 to 0.12. Then, based on the normalized error parameters and weights, the assembly fitness is calculated, for example, from 0.85 to 0.904. The process continues to iterate until the convergence conditions are met, including the fitness reaching the target value (such as 0.95) and the error change is lower than the threshold (such as 0.01), or the maximum number of iterations is reached. Finally, the optimal assembly positioning solution is output, including the final deviation distribution, display error parameters and assembly fitness, to achieve efficient and accurate assembly optimization.

[0040] Step S500, assemble the display module to the bottom shell of the display screen according to the optimal assembly positioning scheme. Specifically, when assembling the display module according to the optimal assembly positioning scheme, first read the assembly deviation distribution, display error parameters and assembly fitness values ​​provided in the scheme, for example, the deviation of window 1 is 4 pixels, the text offset is 0.08, and the fitness is 0.95. Then, the module is preliminarily aligned according to the deviation distribution, and the module position is gradually adjusted by high-precision positioning equipment to reach the optimal deviation value, and the module position is fixed by a fastening device. After the assembly is completed, the assembly image is collected for verification, and by comparing the assembly deviation and display error parameters, it is ensured that the deviation and error are within the allowable range of the scheme, and the assembly quality is finally confirmed. After the assembly is completed, the actual assembly data, including the final deviation value, error parameters and fitness, are recorded for quality analysis and subsequent optimization. This process ensures high assembly accuracy and excellent display effect, while providing data support for continuous improvement.

[0041] The embodiment of the present application adopts the method of collecting assembly images and obtaining preset assembly images; analyzing the deviation between the assembly image and the preset image to obtain the assembly deviation distribution; analyzing the display error based on the assembly deviation distribution, obtaining the display error parameters, and calculating the assembly fitness; configuring the assembly adjustment step according to the error parameters and the deviation distribution, and performing assembly positioning optimization; adjusting the assembly position of the display module and the bottom shell according to the optimization scheme to complete the precise assembly, thereby achieving the technical effect of improving the assembly accuracy of the display screen through intelligent assembly deviation analysis, display error impact analysis and assembly positioning optimization.

[0042] In the above, refer to Figure 1 A display screen bottom shell intelligent assembly control method according to an embodiment of the present invention is described in detail. Figure 2 A display screen bottom shell intelligent assembly control device according to an embodiment of the present invention is described.

[0043] According to an embodiment of the present invention, a display screen bottom shell intelligent assembly control device is used to solve the technical problem of insufficient precision in the existing display screen assembly process, and achieves the technical effect of improving the display screen assembly precision through intelligent assembly deviation analysis, display error impact analysis and assembly positioning optimization. A display screen bottom shell intelligent assembly control device includes: an assembly image acquisition module 10, an assembly deviation distribution acquisition module 20, a display error impact analysis module 30, an adjustment step configuration module 40, and a display screen bottom shell assembly module 50.

[0044] The assembly image acquisition module 10 is used to collect an assembly image when the display module is assembled and positioned on the bottom shell of the display screen to obtain an assembly image.

[0045] The assembly deviation distribution acquisition module 20 is used to acquire a preset assembly image, perform assembly deviation analysis on the assembly image, and obtain assembly deviation distribution.

[0046] The display error influence analysis module 30 is used to perform display error influence analysis according to the assembly deviation distribution, obtain display error parameters, and calculate assembly fitness.

[0047] The adjustment step configuration module 40 is used to configure the assembly adjustment step according to the display error parameter and the assembly deviation distribution, adjust the assembly, optimize the assembly positioning, and obtain the optimal assembly positioning solution.

[0048] The display screen bottom shell assembly module 50 is used to assemble the display module to the display screen bottom shell according to the optimal assembly positioning solution.

[0049] The specific configuration of the assembly deviation distribution acquisition module 20 will be described in detail below. As described above, a preset assembly image is acquired, and assembly deviation analysis is performed on the assembly image to obtain assembly deviation distribution. The assembly deviation distribution acquisition module 20 further includes: a preset assembly image acquisition unit, the preset assembly image acquisition unit is used to acquire a preset assembly image, and the preset assembly image is an assembly image under standard conditions; a grayscale processing unit, the grayscale processing unit is used to grayscale the preset assembly image and the assembly image to obtain a grayscale assembly image and a grayscale preset assembly image; a position deviation set acquisition unit, the position deviation set acquisition unit is used to perform pixel position deviation analysis on the grayscale assembly image and the grayscale preset assembly image to obtain multiple position deviation sets; a traversal combination optimization unit, the traversal combination optimization unit is used to perform traversal combination optimization on the multiple position deviation sets to obtain assembly deviation distribution.

[0050] Wherein, the grayscale assembly image and the grayscale preset assembly image are subjected to pixel position deviation analysis to obtain a plurality of position deviation sets, and the position deviation set acquisition unit further comprises: an assembly pixel window setting subunit, the assembly pixel window setting subunit is used to set the assembly pixel window according to the assembly unit size of the display module; a first window division subunit, the first window division subunit is used to divide the grayscale assembly image according to the assembly pixel window to obtain a first window; a preset window division subunit, the preset window division subunit is used to traverse and divide the grayscale preset assembly image according to the assembly pixel window to obtain a plurality of preset windows; a similarity calculation subunit, the similarity calculation subunit is used to obtain a plurality of preset windows according to the assembly pixel window; The multiple first grayscale values ​​in the first window are used as a reference, and the similarities between the preset grayscale value set in the multiple preset windows and the multiple first grayscale values ​​are calculated to obtain a first window similarity set; a first distance calculation subunit, the first distance calculation subunit is used to calculate and obtain multiple first distances between the multiple preset windows and the first window according to the multiple preset windows and the coordinate values ​​of the first window in the preset assembly image and the first assembly image, and obtain a first position deviation set; a grayscale assembly image division subunit, the grayscale assembly image division subunit is used to continue to divide multiple windows in the grayscale assembly image, and combine the multiple preset windows to calculate and obtain multiple window similarity sets and multiple position deviation sets.

[0051] Among them, the multiple position deviation sets are traversed and combined for optimization to obtain the assembly deviation distribution, and the traversal and combined optimization unit further includes: a first mapping relationship configuration subunit, the first mapping relationship configuration subunit is used to randomly configure a first mapping relationship between multiple windows in the grayscale assembly image and multiple preset windows in the preset grayscale assembly image, and extract and obtain the first assembly deviation distribution according to the multiple position deviation sets; a window similarity sum calculation subunit, the window similarity sum calculation subunit is used to calculate the sum of window similarities of multiple groups of windows mapped in the first assembly deviation distribution and preset windows according to the multiple window similarity sets, and obtain the first total window similarity; a mapping relationship output subunit, the mapping relationship output subunit is used to continue to traverse the randomly configured mapping relationship, calculate the total window similarity, output the mapping relationship with the largest window similarity, and extract and obtain the assembly deviation distribution.

[0052] The specific configuration of the display error impact analysis module 30 will be described in detail below. As described above, according to the assembly deviation distribution, the display error impact analysis is performed to obtain the display error parameters and calculate the assembly fitness. The display error impact analysis module 30 further includes: a variation range acquisition unit, the variation range acquisition unit is used to collect the sample assembly deviation distribution set according to the historical display screen bottom shell assembly data, and obtain the variation range of the display content under different sample assembly deviation distributions, which is marked as a sample display error parameter set; a display error prediction channel training unit, the display error prediction channel training unit is used to use the sample assembly deviation distribution set and the sample display error parameter set as supervised training data to train the display error prediction channel; a display error parameter output unit, the display error parameter output unit is used to input the assembly deviation distribution into the display error prediction channel, and output the display error parameters; an assembly fitness calculation unit, the assembly fitness calculation unit is used to calculate the assembly fitness according to the display error parameters, wherein the size of the display error parameters is negatively correlated with the size of the assembly fitness.

[0053] The specific configuration of the adjustment step configuration module 40 will be described in detail below. As described above, according to the display error parameter, combined with the assembly deviation distribution, the assembly adjustment step is configured, the assembly is adjusted, the assembly positioning is optimized, and the optimal assembly positioning solution is obtained. The adjustment step configuration module 40 further includes: a cluster position deviation acquisition unit, the cluster position deviation acquisition unit is used to cluster the same position deviations in the assembly deviation distribution, and obtain multiple cluster position deviations as multiple candidate adjustment steps; an assembly adjustment step determination unit, the assembly adjustment step determination unit is used to calculate the ratio of each candidate adjustment step and the maximum candidate adjustment step, and calculate the deviation of each ratio and the display error parameter, and select the candidate adjustment step with the smallest deviation as the assembly adjustment step.

[0054] Among them, the adjustment step configuration module 40 further includes: an assembly positioning adjustment unit, which is used to adjust the assembly positioning of the display module and the display screen bottom shell according to the assembly adjustment step, and continue to collect the adjusted assembly image; an assembly image analysis unit, which is used to perform assembly deviation analysis and display error analysis on the adjusted assembly image, and calculate the assembly fitness; an optimal assembly positioning solution acquisition unit, which is used to continue to optimize the assembly positioning until convergence, and obtain the optimal assembly positioning solution with the maximum assembly fitness.

[0055] The display screen bottom shell intelligent assembly control device provided by the embodiment of the present invention can execute the display screen bottom shell intelligent assembly control method provided by any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0056] Although the present application makes various references to certain modules in the system according to the embodiments of the present application, any number of different modules may be used and run on the user terminal and / or server, and the various units and modules included are only divided according to functional logic, but are not limited to the above division, as long as the corresponding functions can be achieved; in addition, the specific names of the functional units are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of the present invention.

[0057] The above specific implementations do not constitute a limitation on the protection scope of this application. It should be understood by those skilled in the art that various modifications, combinations and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of this application should be included in the protection scope of this application.

Claims

1. A display screen bottom shell intelligent assembly control method, characterized in that: The method comprises: When the display module is assembled and positioned on the bottom shell of the display screen, an assembly image is collected to obtain an assembly image; Acquire a preset assembly image, perform assembly deviation analysis on the assembly image, and obtain assembly deviation distribution; According to the assembly deviation distribution, a display error influence analysis is performed to obtain a display error parameter, and an assembly fitness is calculated; According to the display error parameter and in combination with the assembly deviation distribution, the assembly adjustment step is configured, the assembly is adjusted, the assembly positioning is optimized, and the optimal assembly positioning solution is obtained; According to the optimal assembly and positioning scheme, the display module is assembled to the bottom shell of the display screen.

2. The display screen bottom shell intelligent assembly control method according to claim 1, characterized in that: Acquiring a preset assembly image, performing assembly deviation analysis on the assembly image, and obtaining assembly deviation distribution, including: Acquire a preset assembly image, where the preset assembly image is an assembly image under standard conditions; Gray-scale the preset assembly image and the assembly image to obtain a gray-scale assembly image and a gray-scale preset assembly image; Performing pixel position deviation analysis on the grayscale assembly image and the grayscale preset assembly image to obtain a plurality of position deviation sets; The multiple position deviation sets are traversed and combined for optimization to obtain assembly deviation distribution.

3. The display screen bottom shell intelligent assembly control method according to claim 2 is characterized in that: Performing pixel position deviation analysis on the grayscale assembly image and the grayscale preset assembly image to obtain multiple position deviation sets, including: According to the assembly unit size of the display module, set the assembly pixel window; According to the assembled pixel window, a first window is obtained by dividing the grayscale assembled image; According to the assembly pixel window, traverse and divide the grayscale preset assembly image to obtain a plurality of preset windows; Based on the multiple first grayscale values ​​in the first window, calculate the similarity between the preset grayscale value set in the multiple preset windows and the multiple first grayscale values ​​to obtain a first window similarity set; According to the coordinate values ​​of the plurality of preset windows and the first window in the preset assembly image and the first assembly image, a plurality of first distances between the plurality of preset windows and the first window are calculated to obtain a first position deviation set; Continue to divide a plurality of windows in the grayscale assembly image, combine the plurality of preset windows, and calculate to obtain a plurality of window similarity sets and a plurality of position deviation sets.

4. The display screen bottom shell intelligent assembly control method according to claim 3 is characterized in that: Performing traversal and combination optimization on the multiple position deviation sets to obtain assembly deviation distribution includes: Randomly configuring a first mapping relationship between a plurality of windows in the grayscale assembly image and a plurality of preset windows in the preset grayscale assembly image, and extracting and obtaining a first assembly deviation distribution according to the plurality of position deviation sets; According to the plurality of window similarity sets, calculating the sum of window similarities of the plurality of groups of windows mapped in the first assembly deviation distribution and the preset windows, to obtain a first total window similarity; Continue to traverse the random configuration mapping relationship, calculate the total window similarity, output the mapping relationship with the largest window similarity, and extract the assembly deviation distribution.

5. The display screen bottom shell intelligent assembly control method according to claim 1, characterized in that: According to the assembly deviation distribution, a display error influence analysis is performed to obtain a display error parameter, and the assembly fitness is calculated, including: According to the historical display bottom shell assembly data, a sample assembly deviation distribution set is collected, and the variation range of the display content under different sample assembly deviation distributions is obtained, which is marked as a sample display error parameter set; The sample assembly deviation distribution set and the sample display error parameter set are used as supervised training data to train a display error prediction channel; Input the assembly deviation distribution into the display error prediction channel, and output the display error parameter; The assembly fitness is calculated based on the display error parameter, wherein the size of the display error parameter is negatively correlated with the size of the assembly fitness.

6. The display screen bottom shell intelligent assembly control method according to claim 1, characterized in that: According to the display error parameter and in combination with the assembly deviation distribution, configuring the assembly adjustment step length includes: Clustering the same position deviations in the assembly deviation distribution to obtain a plurality of clustered position deviations as a plurality of adjustment step sizes to be selected; The ratio of each candidate adjustment step length to the maximum candidate adjustment step length is calculated, and the deviation of each ratio and the display error parameter is calculated, and the candidate adjustment step length with the smallest deviation is selected as the assembly adjustment step length.

7. The display screen bottom shell intelligent assembly control method according to claim 1, characterized in that: Adjust the assembly, optimize the assembly positioning, and obtain the optimal assembly positioning solution, including: According to the assembly adjustment step length, the assembly positioning of the display module and the display screen bottom shell is adjusted, and the adjusted assembly image is continued to be collected; Perform assembly deviation analysis and display error analysis on the adjusted assembly image, and calculate assembly fitness; Continue to optimize the assembly positioning until convergence, and obtain the optimal assembly positioning solution with the maximum assembly fitness.

8. A display screen bottom shell intelligent assembly control device, characterized in that: The device is used to implement a display screen bottom shell intelligent assembly control method according to any one of claims 1 to 7, and the device comprises: An assembly image acquisition module, the assembly image acquisition module is used to collect an assembly image when the display module is assembled and positioned on the bottom shell of the display screen to obtain an assembly image; An assembly deviation distribution acquisition module, the assembly deviation distribution acquisition module is used to acquire a preset assembly image, perform assembly deviation analysis on the assembly image, and obtain assembly deviation distribution; A display error impact analysis module, the display error impact analysis module is used to perform display error impact analysis according to the assembly deviation distribution, obtain display error parameters, and calculate assembly fitness; An adjustment step configuration module, wherein the adjustment step configuration module is used to configure the assembly adjustment step according to the display error parameter and the assembly deviation distribution, adjust the assembly, optimize the assembly positioning, and obtain the optimal assembly positioning solution; A display screen bottom shell assembly module is used to assemble the display module to the display screen bottom shell according to the optimal assembly positioning solution.

Images