Data processing method and device for defect detection, equipment and medium

Abstract

This invention relates to a data processing method, apparatus, device, and medium for defect detection. The invention acquires target screening parameters and, based on these parameters, obtains target defect information describing defects present in the target product corresponding to those parameters. Based on this target defect information, it displays an image display interface including a defect scatter plot. Responding to analysis commands on the defect scatter plot displayed in the image display interface, it acquires defect analysis data based on the equipment contact points of the target production equipment and the influence range thresholds set for these contact points. This defect analysis data indicates statistical information about the defects caused by each equipment contact point, thereby achieving automatic analysis of the correlation between product defects and equipment contact points and improving defect analysis efficiency.

Description

Technical Field

[0001] This invention relates to the field of industrial inspection and data processing technology, and in particular to a data processing method, apparatus, equipment and medium for defect detection. Background Technology

[0002] As a carrier of images and text input in the form of electronic signals, the display panel is an indispensable and important component in display technology, and is widely used in various types of devices such as computers, LCD TVs, mobile phones, and projection displays.

[0003] During the production of display panels, defects may occur due to various factors such as production processes, equipment, manual operation, and environment. Among the defects caused by these factors, those caused by equipment contact points account for a significant proportion. Therefore, there is an urgent need for a data processing method for defect detection to analyze the correlation between the defects and the contact points of various equipment, such as confirming whether the defects are caused by equipment contact points and which equipment contact point is responsible. Summary of the Invention

[0004] This invention provides a data processing method, apparatus, device, and medium for defect detection, in order to address the shortcomings of related technologies.

[0005] According to a first aspect of the present invention, a data processing method for defect detection is provided, the method comprising:

[0006] Obtain target filtering parameters to obtain target defect information based on the target filtering parameters. The target defect information is used to describe the defects existing in the target product corresponding to the target filtering parameters.

[0007] Based on the target defect information, an image display interface including a defect scatter plot is displayed. The defect scatter plot is used to show the location of the defects present in the target product on the target product.

[0008] In response to the analysis command of the defect scatter plot displayed in the image display interface, defect analysis data is obtained based on the equipment contact points of the target production equipment and the influence range threshold set for the equipment contact points. The target production equipment is the production equipment used to produce the target product, and the defect analysis data is used to indicate the statistical information of the defects caused by each equipment contact point.

[0009] According to a second aspect of the present invention, a data processing apparatus for defect detection is provided, the apparatus comprising:

[0010] The first acquisition module is used to acquire target screening parameters, and to acquire target defect information based on the target screening parameters. The target defect information is used to describe the defects existing in the target product corresponding to the target screening parameters.

[0011] The display module is used to display an image display interface including a defect scatter plot based on the target defect information. The defect scatter plot is used to show the location of the defects present in the target product on the target product.

[0012] The second acquisition module is used to respond to the analysis command of the defect scatter plot displayed in the image display interface, and acquire defect analysis data based on the equipment contact points of the target production equipment and the influence range threshold set for the equipment contact points. The target production equipment is the production equipment used to produce the target product, and the defect analysis data is used to indicate the statistical information of the defects caused by each equipment contact point.

[0013] According to a third aspect of the present invention, a computing device is provided, the computing device including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, it performs the operations performed by the data processing method for defect detection provided in the first aspect above.

[0014] According to a fourth aspect of the present invention, a computer-readable storage medium is provided, on which a program is stored, and when executed by a processor, the program performs the operations performed by the data processing method for defect detection provided in the first aspect above.

[0015] As can be seen from the above embodiments, the present invention obtains target screening parameters and target defect information based on the target screening parameters to describe the defects existing in the target product corresponding to the target screening parameters. Based on the target defect information, an image display interface including a defect scatter plot is displayed. In response to the analysis command of the defect scatter plot displayed in the image display interface, defect analysis data is obtained based on the equipment contact points of the target production equipment and the influence range threshold set for the equipment contact points. The defect analysis data is used to indicate the statistical information of the defects caused by each equipment contact point, so as to realize the automatic analysis of the correlation between product defects and equipment contact points and improve the efficiency of defect analysis.

[0016] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit the invention. Attached Figure Description

[0017] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with the invention and, together with the description, serve to explain the principles of the invention.

[0018] Figure 1 This is a flowchart illustrating a data processing method for defect detection according to an embodiment of the present invention.

[0019] Figure 2 This is a schematic diagram of an image generation interface according to an embodiment of the present invention.

[0020] Figure 3 This is a schematic diagram of an image display interface according to an embodiment of the present invention.

[0021] Figure 4 This is a schematic diagram of an image display interface according to an embodiment of the present invention.

[0022] Figure 5 This is a schematic diagram of a data analysis interface according to an embodiment of the present invention.

[0023] Figure 6 This is a schematic diagram of a contact point screening interface according to an embodiment of the present invention.

[0024] Figure 7 This is a schematic diagram of a data analysis interface according to an embodiment of the present invention.

[0025] Figure 8 This is a schematic diagram of a data analysis interface according to an embodiment of the present invention.

[0026] Figure 9 This is a schematic diagram of a data analysis interface according to an embodiment of the present invention.

[0027] Figure 10 This is a system architecture diagram of a data processing system for defect detection according to an embodiment of the present invention.

[0028] Figure 11 This is a flowchart illustrating a data processing method for defect detection according to an embodiment of the present invention.

[0029] Figure 12 This is a block diagram of a data processing apparatus for defect detection according to an embodiment of the present invention.

[0030] Figure 13 This is a schematic diagram of the structure of a computing device according to an embodiment of the present invention. Detailed Implementation

[0031] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numerals in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present invention. Rather, they are merely examples of apparatuses and methods consistent with some aspects of the invention as detailed in the appended claims.

[0032] In industrial production, production equipment may contain machine points that directly contact the product. These contact points are fixed in location and can be called equipment contact points. Because these contact points directly contact the product, their surrounding areas are prone to defects. However, due to various factors such as production processes, manual operation, and environment, not all defects are caused by equipment contact points. Therefore, this invention provides a data processing method for defect detection. This method offers a data processing approach based on a visual interface to display defects in the target product through data visualization. The visualization interface analyzes the correlation between product defects and equipment contact points, enabling automatic analysis of this correlation and improving defect analysis efficiency. Furthermore, it can quickly and visually display the correlation between product defects and equipment contact points, automatically hiding the display of data points corresponding to product defects unrelated to equipment contact points.

[0033] Optionally, the data processing method for defect detection provided by the present invention can be applied in the production process of display panels to analyze the correlation between product defects in display panels and equipment contact points.

[0034] The above is merely an exemplary description of the application scenarios of the present invention and does not constitute a limitation on the application scenarios of the present invention. In more possible implementations, the data processing method for defect detection provided by the present invention can also be applied to the production process of other types of products to realize the analysis of the correlation between product defects and equipment contact points in other types of products. The present invention does not limit this.

[0035] The data processing method for defect detection described above can be executed by a computing device, which can be a terminal device, such as a desktop computer, portable computer, laptop computer, tablet computer, etc. Alternatively, the computing device can be a server, such as a single server, multiple servers, or a server cluster. This invention does not limit the type or number of computing devices.

[0036] After introducing the application scenarios and implementation environment of the present invention, the data processing method for defect detection provided by the present invention will be described in detail below.

[0037] See Figure 1 , Figure 1 This is a flowchart illustrating a data processing method for defect detection according to an embodiment of the present invention, such as... Figure 1 As shown, the method includes:

[0038] Step 101: Obtain target screening parameters to obtain target defect information based on the target screening parameters. The target defect information is used to describe the defects existing in the target product corresponding to the target screening parameters.

[0039] It should be noted that in industrial production, a large number of products may be produced on the production line, and the defect information of all produced products can be stored, resulting in a large amount of stored product defect information data. By obtaining the parameter values ​​of the filtering parameters through the image generation interface, the stored product defect information can be filtered based on the obtained parameter values ​​to obtain the target defect information corresponding to the target product that meets the parameter values. This allows for subsequent correlation analysis of defect locations and equipment contact points based on the target defect information, improving data processing speed and efficiency.

[0040] Step 102: Based on the target defect information, display an image display interface including a defect scatter plot. The defect scatter plot is used to show the location of the defects present in the target product on the target product.

[0041] Optionally, after obtaining the target defect information, a defect scatter plot can be generated based on the obtained target defect information, so that an image display interface can be displayed to show the generated defect scatter plot.

[0042] Among them, the defect scatter plot can be used to show the location of defects in the target product. By generating the defect scatter plot based on the target defect information, the description of product defects can be converted from numerical to graphical, so that users can intuitively determine the location of the defects in the target product based on the displayed defect scatter plot, thus improving display efficiency.

[0043] Step 103: In response to the analysis command of the defect scatter plot displayed in the image display interface, based on the equipment contact points of the target production equipment and the influence range threshold set for the equipment contact points, obtain defect analysis data. The target production equipment is the production equipment used to produce the target product. The defect analysis data is used to indicate the statistical information of the defects caused by each equipment contact point.

[0044] It should be noted that the contact points between the target production equipment and the products it produces can be set when the target production equipment leaves the factory. As for the influence range of each contact point, this invention can provide a function to set the influence range threshold of the contact point through a visual interface, so that users can set the influence range threshold of the contact point according to actual technical requirements, thereby obtaining defect analysis data based on the set influence range threshold.

[0045] This invention acquires target screening parameters and, based on these parameters, obtains target defect information describing the defects present in the target product corresponding to those parameters. Then, based on this target defect information, it displays an image display interface including a defect scatter plot. In response to analysis commands on the defect scatter plot displayed in the image display interface, it acquires defect analysis data based on the equipment contact points of the target production equipment and the influence range threshold set for each contact point. This defect analysis data indicates statistical information about the defects caused by each equipment contact point, thereby achieving automatic analysis of the correlation between product defects and equipment contact points and improving defect analysis efficiency.

[0046] After introducing the basic implementation process of the data processing method for defect detection provided by the present invention, the following describes various optional embodiments of the present invention.

[0047] In some embodiments, step 101, when obtaining target filtering parameters to obtain target defect information based on the target filtering parameters, can be achieved through the following steps:

[0048] Step 1011: Display the image generation interface, which provides the function of setting target filtering parameters for at least one pre-configured product filtering dimension.

[0049] The product screening dimensions may include at least one of the following: product production time, production equipment identification, product model, product number, and product batch number. In many possible implementations, the product screening dimensions may include more types of parameters. This invention does not limit the specific parameter types of the product screening dimensions.

[0050] Optionally, an image generation interface may be displayed, and at least one product filtering dimension may be displayed in the image generation interface, so that users can set target filtering parameters based on at least one product filtering dimension displayed in the image generation interface.

[0051] Step 1012: In response to the parameter setting operation in the image generation interface, obtain the target filtering parameters set for at least one product filtering dimension.

[0052] Optionally, the image generation interface may include input controls so that users can set target filtering parameters for at least one product filtering dimension.

[0053] In one possible implementation, in response to an input operation in the input control, the parameters entered in the input control can be used as target filtering parameters set for at least one product filtering dimension.

[0054] By providing input controls in the image generation interface, the system offers the ability to set filtering parameters for product filtering dimensions. Users can input target filtering parameters for at least one product filtering dimension according to their actual technical needs, thereby improving the flexibility of the parameter acquisition process.

[0055] Optionally, an input control can be set for each product filtering dimension in the image generation interface, so that users can input the target filtering parameters for each product filtering dimension through the input control corresponding to each product filtering dimension.

[0056] In one possible implementation, for any product filtering dimension among at least one product filtering dimension, in response to an input operation in the input control corresponding to that product filtering dimension, the parameter entered in the input control can be used as the target filtering parameter set for that product filtering dimension. This process is repeated to obtain the target filtering parameter corresponding to each of the at least one product filtering dimensions.

[0057] By providing an input control for each product filtering dimension, the target filtering parameters for each product filtering dimension can be entered through the corresponding input control, which is simple to operate and can improve the efficiency of parameter acquisition.

[0058] See Figure 2 , Figure 2 This is a schematic diagram of an image generation interface according to an embodiment of the present invention. Figure 2 In the image generation interface shown, the product filtering dimensions include product production time (i.e., time), product batch number (i.e., batch number), production equipment identifier (i.e., equipment identifier), product model, and product number. Each product filtering dimension has a corresponding input control. Specifically, the input control corresponding to the product production time (a product filtering dimension) is control 201; the input control corresponding to the product batch number (a product filtering dimension) is control 202; the input control corresponding to the production equipment identifier (a product filtering dimension) is control 203; the input control corresponding to the product model (a product filtering dimension) is control 204; and the input control corresponding to the product number (a product filtering dimension) is control 205. Based on... Figure 2As shown in the image generation interface, users can input the target filtering parameters corresponding to the product production time and actual technical requirements in control 201, the target filtering parameters corresponding to the product batch number and actual technical requirements in control 202, the target filtering parameters corresponding to the production equipment identifier and actual technical requirements in control 203, the target filtering parameters corresponding to the product model and actual technical requirements in control 204, and the target filtering parameters corresponding to the product number and actual technical requirements in control 205, thereby realizing the setting of target filtering parameters corresponding to each product filtering dimension.

[0059] Step 1013: Obtain target defect information based on target screening parameters.

[0060] After obtaining the target filtering parameters through step 1012 above, the candidate defect information can be filtered based on the target filtering parameters to obtain the target defect information.

[0061] Candidate defect information can be obtained by processing products already produced on the production line. This information includes defect details for each produced product, describing the defects present in the product. For any produced product, the corresponding candidate defect information can be obtained through the following steps:

[0062] Step 1: Obtain the product image corresponding to the product.

[0063] It should be noted that during the product manufacturing process, a production line may include multiple production devices. These devices process the product sequentially or collaboratively to complete the production. Each production device on the production line can be equipped with a camera to capture images of the products manufactured by that device.

[0064] Optionally, multiple production equipment can be managed through a Manufacturing Execution System (MES). That is, after the production equipment collects product images of the products it produces, it can send the collected product images to the MES system, which will then store the product images of each produced product so that the product images of each produced product can be retrieved directly from the MES system later.

[0065] When storing images of various manufactured products, the MES system can store product images along with information such as product production time, product batch number, production equipment identification, product model, and product number. This allows the system to directly retrieve the required product images based on the information stored in the MES system.

[0066] Step 2: Perform optical inspection based on product images to obtain product defect data, which includes defect images and defect description data.

[0067] In one possible implementation, optical inspection can be performed based on product images to obtain initial defect data; the initial defect data can then be cleaned and processed, and the cleaned data can be used as the defect data for the product.

[0068] In the process of performing optical inspection based on product images to obtain initial defect data, automated optical inspection (AOI) can be performed on the product images to detect defects present in the product images. These defects are then automatically marked, allowing the acquisition of various types of data, such as defect location identifiers, defect location numbers, defect types, and defect location coordinates, based on the marked locations in the product images. The acquired data, including product images, defect location identifiers, defect location numbers, defect types, defect location coordinates, product production time, product batch number, production equipment identifier, product model, and product number, are used as initial defect data.

[0069] After obtaining the initial defect data, data cleaning can be performed to extract the required defect data based on the initial defect data. Optionally, data cleaning may include at least data filtering and / or data format conversion.

[0070] It should be noted that the initial defect data may include many types of data, but not all of these data will be used in the subsequent processing. Therefore, data filtering can be used to obtain the data required in the subsequent processing, so that only the filtered data can be processed, reducing the data processing pressure and improving the data processing efficiency.

[0071] The defect data required in subsequent processing generally includes product images, product production time, product batch number, production equipment identification, product model, product number, defect location identification, and defect location coordinates. Therefore, when filtering the initial defect data, only the above-mentioned types of data can be retained to achieve the filtering of the initial defect data.

[0072] It should be noted that defect data can be divided into image data and numerical data. Image data can include product images, while numerical data can include product production time, product batch number, production equipment identification, product model, product number, defect location identification, defect location number, and defect location coordinates.

[0073] Optionally, image data can be stored in the format of an img file, and numerical data can be stored in the format of an xml file.

[0074] In addition, the data format of the initial defect data may not be uniform, and the data format of the initial defect data may not meet the requirements of subsequent data processing. Therefore, data format conversion can be used to convert the data format of the initial defect data into the target data format to ensure that the defect data in the target data format can meet the requirements of subsequent data processing.

[0075] The target data format can be any type of data format. Users can set the type of target data format according to actual technical requirements. This invention does not limit the specific type of target data format.

[0076] It should be noted that the two processing methods included in data cleaning (i.e., data filtering and data format conversion) can be used individually or in combination. For example, data filtering can be performed only on the initial defective data to obtain the defective data; or, data format conversion can be performed only on the initial defective data to obtain the defective data; or, the initial defective data can be filtered first, and then the filtered data can be converted to obtain the defective data, and so on. In many possible implementations, even more methods can be used to clean the data; this invention does not limit the specific processing method of data cleaning.

[0077] Step 3: Perform defect detection and classification based on defect data to obtain candidate defect information.

[0078] In one possible implementation, an Automatic Defect Classification (ADC) system can be used to detect and classify defects in a product based on defect data to obtain candidate defect information.

[0079] The ADC system can be pre-trained based on the goal of defect detection and classification. For example, determining the location and type of defects in a product image can be assigned to the ADC system as an inference task, and a large number of training images can be provided to the ADC system (images from an open-source image database can be used as training images). This allows the ADC system to train based on the training images according to the inference task, so as to obtain an ADC system that can accurately locate and classify defects.

[0080] After obtaining the trained ADC system, the defect data can be input into the ADC system so that the ADC system can locate and classify the defects based on the defect data, thereby obtaining the location coordinates of the defect points and the defect type.

[0081] Compared to the location coordinates of defect points obtained through optical detection, the location coordinates of defect points obtained through ADC system processing are more accurate, thus ensuring the accuracy of subsequent data processing and improving the accuracy of the acquired defect analysis data.

[0082] After obtaining the defect type and more accurate defect location coordinates through the ADC system, the defect location coordinates and product model can be used as candidate defect information to achieve the acquisition of candidate defect information. Optionally, the candidate defect information can also include more types of information, such as product production time, product batch number, production equipment identification, product model, product number, defect location identification, defect location number, and the defect location coordinates and defect type obtained through the ADC system as candidate defect information.

[0083] After obtaining candidate defect information through the above process, the target defect information can be filtered based on the obtained target filtering parameters to obtain the target defect information.

[0084] After obtaining the target defect information, step 102 can be used to display an image display interface including a defect scatter plot based on the target defect information.

[0085] In some embodiments, when displaying an image display interface including a defect scatter plot based on the target defect information in step 102, it can be implemented in the following way:

[0086] Based on the target defect information, an image display interface is displayed, and at least one defect scatter plot is displayed in the image display interface. Each defect scatter plot corresponds to a target product, and the defect scatter plot includes multiple data points, with each data point corresponding to a defect in the target product.

[0087] It should be noted that, for any target product, after obtaining the target defect information, a defect in the target product can be used as a data point to generate a defect scatter plot that corresponds one-to-one with the defect in the target product. This process is repeated for each target product, resulting in at least one defect scatter plot, which can then be displayed through an image display interface.

[0088] Alternatively, when displaying a scatter plot of at least one defect, this can be achieved as follows:

[0089] For any target product, based on the product model and defect location coordinates included in the target defect information corresponding to the target product, the target coordinate system of the product size corresponding to the product model is displayed, and a scatter plot of the defects corresponding to the target product is displayed based on the target coordinate system.

[0090] It should be noted that product dimensions for multiple product models can be pre-stored. This allows the system to determine the corresponding product dimensions based on the product model, and then establish the target coordinate system. Taking the display panel as an example, the geometric center of the display panel can be used as the origin of the target coordinate system. The horizontal axis (x-axis) is determined based on the length of the display panel, and the vertical axis (y-axis) is determined based on the width of the display panel. Once the target coordinate system is established, a defect scatter plot corresponding to the target product can be displayed based on it.

[0091] The defect scatter plot includes multiple data points, each corresponding to a defect in the target product (i.e., a defect point in the product image). The coordinates of the data points can be determined based on the coordinates of the defect points included in the target defect information. The data points are then displayed at their corresponding positions in the target coordinate system based on the determined coordinates, thus realizing the display of the defect scatter plot.

[0092] Taking a display panel with dimensions of 1300*1100 as an example, the geometric center of the display panel can be used as the origin of the coordinate system. The x-axis range is (-650, 650), and the y-axis range is (-550, 550), thus determining the target coordinate system. Since the determined target coordinate system is consistent with the product dimensions, the coordinates of the defect points can be directly used as the coordinates of the data points to display each data point, thereby achieving the display of the defect scatter plot.

[0093] The above explanation uses the display process of a defect scatter plot corresponding to a single target product as an example. The display process for defect scatter plots corresponding to other target products is similar and will not be repeated here. It should be noted that one target product corresponds to one defect scatter plot; therefore, the number of defect scatter plots displayed on the image display interface will correspond to the number of target products.

[0094] Optionally, when generating a defect scatter plot based on the target defect information, Echarts (a dynamic visualization component) can be used. Echarts can convert the target defect information into parameters required for generating the defect scatter plot. Generally, the parameters required for generating a defect scatter plot can be found in Table 1 below:

[0095] Table 1

[0096] parameter type Remark defectCode String Defect location marking defectName String Defect location name defectNo Number Defect location number imagePath String Product Image Path x Number x-axis coordinates of defect location y Number y-axis coordinate of defect location equipmentId String Generate device identifier glassId String Display panel logo productId String Product Identification stepId String Process identification totalDefect Number Total number of defect points

[0097] It should be noted that when displaying defect scatter plots in the image display interface, if there are a large number of defect scatter plots to be displayed, the defect scatter plots can be displayed in pages, with a preset number of defect scatter plots displayed on each page. In this way, all defect scatter plots can be displayed through multiple pages, and users can turn the pages to view the defect scatter plots displayed on different pages.

[0098] See Figure 3 , Figure 3 This is a schematic diagram of an image display interface according to an embodiment of the present invention, in which the user... Figure 2 After entering the target filtering parameters corresponding to each product filtering dimension in the image generation interface shown, the image will be displayed as follows. Figure 3 The image display interface shown is as follows: Figure 3 The image display interface shown presents eight defect scatter plots, each corresponding to a target product. Users can also... Figure 3 Use the image generation interface shown to flip through pages to display more defect scatter plots, such as... Figure 3 The image generation interface shown comprises 82 pages, displaying 655 defect scatter plots. Each page can display a maximum of 8 defect scatter plots.

[0099] In other possible implementations, when displaying a defect scatter plot in the image generation interface, the production equipment identifier can also be displayed at a preset position corresponding to the defect scatter plot; or, the product number can be displayed at a preset position corresponding to the defect scatter plot; or, the product batch number can be displayed at a preset position corresponding to the defect scatter plot; or, based on the defect location identifier, the number of defects can be displayed at a preset position corresponding to the defect scatter plot.

[0100] The preset location can be any location, and this invention does not limit the specific location of the preset location. In addition, the defect point identifier can be a defect number, so that the number of defects can be determined according to the defect number, and then the number of defects can be displayed at the preset location corresponding to the defect scatter plot.

[0101] In addition, it should be noted that the above four additional display methods can be used individually or in combination, and the present invention does not limit this.

[0102] By displaying at least one of the following when showing a defect scatter plot: production equipment identification, product number, product batch number, and defect quantity, more information can be displayed in the image display interface to assist user analysis and improve user experience.

[0103] Still as Figure 3 Taking the image display interface shown as an example, in such a case... Figure 3 The image display interface shows not only defect scatter plots, but also the production equipment identifier, product number, and defect quantity above each defect scatter plot (i.e., at the preset position corresponding to the defect scatter plot). Taking "1450P-1A3E27005Q-295" displayed above the first defect scatter plot as an example, 1450P is the production equipment identifier, 1A3E27005Q is the product number, and 295 is the defect quantity.

[0104] After displaying the defect scatter plot through the image display interface, users can trigger analysis commands in the image display interface to analyze the correlation between equipment contact points and product defects based on the defect scatter plot displayed in the image display interface.

[0105] In some embodiments, for step 103, when obtaining defect analysis data based on the equipment contact points of the target production equipment and the influence range threshold set for the equipment contact points in response to the analysis command of the defect scatter plot displayed in the image display interface, the following steps can be taken:

[0106] Step 1031: In response to the selection operation in the defect scatter plot displayed in the image display interface, display the data analysis interface based on the selected defect scatter plot, and display the target scatter plot in the data analysis interface. The target scatter plot is obtained based on the selected defect scatter plot.

[0107] Optionally, a corresponding checkbox can be set for each defect scatter plot, allowing users to select the desired defect scatter plot by triggering the checkbox. For example, an analysis control can be set in the image display interface, allowing users to trigger the checkbox for each defect scatter plot in the image display interface. Alternatively, users can long-press any defect scatter plot in the image display interface to trigger the checkbox for each defect scatter plot. It should be noted that the checkbox for the long-pressed defect scatter plot is selected by default, and users can deselect the defect scatter plot according to actual technical needs.

[0108] Additionally, an image processing control can be set in the image display interface so that after the user selects a defect scatter plot, the image processing control can be triggered to generate a target scatter plot based on the selected defect scatter plot.

[0109] In one possible implementation, the user can select from at least one defect scatter plot displayed on the image display interface according to actual technical requirements. By checking the checkbox corresponding to the defect scatter plot to be selected, the user can select the defect scatter plot that meets the actual technical requirements. The computing device can respond to the selection operation in at least one defect scatter plot by displaying the checkbox corresponding to the selected defect scatter plot as selected. After the selection is completed, the user can trigger the image processing control. The computing device can respond to the trigger operation of the image processing control by generating a target scatter plot based on the selected defect scatter plot, thereby displaying the data analysis interface and showing the generated target scatter plot in the data analysis interface.

[0110] See Figure 4 , Figure 4 This is a schematic diagram of an image display interface according to an embodiment of the present invention, such as... Figure 4 As shown, the button labeled "Analysis" is the analysis control. Users can trigger the display of the checkboxes (check boxes) corresponding to each defect scatter plot by clicking the "Analysis" button. This allows users to perform various operations using these checkboxes. Figure 4 The selection is shown in the multiple defect scatter plots. The checkbox corresponding to the selected defect scatter plot will be displayed as selected, such as... Figure 4 As shown, the defect scatter plot that has a "√" in the corresponding check box is the selected defect scatter plot.

[0111] It should be noted that, Figure 4 The image display interface shown only displays the selected defect scatter plot on the first page. Users can also select from the remaining 81 defect scatter plots. Users can simply flip through the pages according to their actual needs to view more defect scatter plots and thus have more options to choose from.

[0112] In addition, in such Figure 4 In the image display interface shown, the button labeled "Map" is the image processing control. After selecting the defect scatter plot, the user can then... Figure 4 The button labeled "Map" in the image display interface triggers the process of generating a target scatter plot based on the selected defect scatter plot, and displaying the target scatter plot through the data analysis interface.

[0113] The process of generating the target scatter plot can be achieved in the following way:

[0114] In one possible implementation, if there is only one selected defect scatter plot, then the selected defect scatter plot is used as the target scatter plot.

[0115] It should be noted that if the user selects only one defect scatter plot, then that defect scatter plot can be used directly as the target scatter plot without further processing.

[0116] In another possible implementation, if there are multiple selected defect scatter plots, the multiple selected defect scatter plots are image composited to obtain a target scatter plot, in which the data points corresponding to different types of defects are displayed in different display styles in the target scatter plot.

[0117] Optionally, if the user selects multiple defect scatter plots, the data points in all the selected defect scatter plots can be statistically analyzed to combine the data points in all the scatter plots into a new data set. The information corresponding to each data point before merging (such as production equipment identification, product model, product number, defect type, defect point location coordinates, etc.) can be retained. Based on the new data set, a target scatter plot can be generated, which will include the data points in all the selected defect scatter plots, thus achieving the effect of superimposing multiple defect scatter plots together.

[0118] It should be noted that, in order to distinguish the data points corresponding to different types of defects in the target scatter plot, the data points corresponding to different types of defects can be displayed in different display styles for easy viewing by the user. The display style can be a display shape, display color, etc., and this invention does not limit this.

[0119] After generating the target scatter plot, you can display it through the data analysis interface. See also Figure 5 , Figure 5 This is a schematic diagram of a data analysis interface according to an embodiment of the present invention, such as... Figure 5 The target scatter plot in the data analysis interface shown includes four data points with different display colors (i.e., display styles). Based on this, the user can understand how... Figure 5 The target scatter plot in the data analysis interface shows data points corresponding to four types of defects, so that users can easily distinguish the data points corresponding to different types of defects based on the display colors.

[0120] Step 1032: In response to the analysis command for the target scatter plot, obtain defect analysis data based on the equipment contact points of the target production equipment and the influence range threshold set for the equipment contact points.

[0121] The data analysis interface includes target display controls and range adjustment controls. The target display controls bring up the display of device contact points, while the range adjustment controls adjust the influence range threshold for each device contact point. It's important to note that the influence range threshold is the distance between the edge of the area where each device contact point can cause a defect and the contact point itself. Generally, the area where each device contact point can cause a defect (i.e., the influence range of each contact point) is a circular area. Taking a circular influence range as an example, the influence range threshold is the maximum radius of the area where each device contact point can cause a defect.

[0122] In one possible implementation, step 1032 above can be achieved through the following steps:

[0123] Step 1032-1: In response to the trigger operation of the target display control, display the equipment contact points of the target production equipment in the target scatter plot.

[0124] In one possible implementation, a contact point filtering interface can be displayed in response to a trigger operation on a target display control. The contact point filtering interface is used to set the filtering criteria used when filtering device contact points. Based on the filtering criteria set in the contact point filtering interface, device contact points that meet the filtering criteria are displayed in the target scatter plot.

[0125] Still as Figure 5 Taking the data analysis interface shown as an example, in such a case... Figure 5 In the data analysis interface shown, the button labeled "Device Contact Point" is the target display control. Users can trigger the contact point filtering interface by clicking the button labeled "Device Contact Point," allowing them to set the filtering conditions used when filtering device contact points.

[0126] Optionally, the contact point filtering interface can provide multiple contact point filtering parameters, allowing users to set filtering conditions by configuring the parameter values ​​of each parameter. These parameters may include the department to which the equipment belongs, the equipment type, etc., and correspondingly, the filtering conditions may include departmental conditions, equipment type conditions, etc. This invention does not limit the specific types of the contact point filtering parameters or the filtering conditions obtained based on them.

[0127] Generally speaking, commonly used contact point screening parameters can be found in Table 2 below:

[0128] Table 2

[0129] parameter type Remark deptName String Department Name id String Contact point marking touchPointType Number Contact point type xaxis Number x-axis coordinate of contact point yaxi Number y-axis coordinate of contact point

[0130] See Figure 6 , Figure 6 This is a schematic diagram of a contact point filtering interface according to an embodiment of the present invention. Figure 6 The contact point filtering interface shown can display the department to which the equipment belongs (i.e., department selection) and the equipment type (i.e., category selection) as contact point filtering parameters. Each contact point filtering parameter has a corresponding input control, so that users can set the parameter value corresponding to each contact point filtering parameter through the input control corresponding to each contact point filtering parameter, thereby realizing the setting of filtering conditions.

[0131] The contact point filtering interface can provide a confirmation control, so that users can trigger the process of filtering the device contact points to be displayed based on the filtering criteria by triggering the confirmation control, thereby displaying the device contact points that meet the filtering criteria in the target scatter plot.

[0132] Still as Figure 6 Taking the contact point filtering interface shown as an example, in such a case... Figure 6 In the contact point filtering interface shown, the button labeled "Contact Point Comparison" is the confirmation control. Triggering this button will initiate the process of filtering device contact points based on the specified criteria.

[0133] Additionally, the contact point filtering interface can include a cancel control, allowing users to cancel filtering of device contact points. (The sentence is incomplete and ends abruptly.) Figure 6 Taking the contact point filtering interface shown as an example, in such a case... Figure 6 In the contact point filtering interface shown, the button labeled "Cancel" is the cancellation control.

[0134] After filtering the device contact points, those points that meet the filtering criteria can be displayed in the target scatter plot. It's important to note that the filtered device contact points can be of various types; therefore, different types of contact points can be displayed in different styles for easy user differentiation. Additionally, to further distinguish device contact points, they can be displayed in a different style than the data points for easier viewing; for example, they can be displayed with a different shape than the data points.

[0135] Generally, the shape of the influence range of the device contact point can be determined according to the actual business situation, and then the display shape of the device contact point can be determined according to the shape of the influence range. For example, if the influence range of the device contact point is a circular area, the device contact point can be displayed as a circle. In addition, the display shape of the device contact point can be adjusted according to the change of the shape of the influence range of the device contact point. For example, the device contact point can be displayed as a square, an ellipse, or other shapes that meet business requirements. This invention does not limit this.

[0136] See Figure 7 , Figure 7 This is a schematic diagram of a data analysis interface according to an embodiment of the present invention. Figure 7 The target scatter plot displayed in the data analysis interface shows the filtered device contact points. For easier differentiation, in... Figure 7 In the target scatter plot shown, data points are displayed as rectangles, and equipment contact points are displayed as circles. In addition, data points corresponding to different types of defects are displayed in different colors, and equipment contact points of different types are also displayed in different colors for easy viewing by the user.

[0137] It should be noted that in the scatter plot of the displayed devices, the device contact points can be displayed according to the default influence range threshold, that is, the device contact points are displayed at a size that matches the default influence range. Additionally, the default influence range threshold can be displayed in the range settings control for easy user viewing.

[0138] Still as Figure 7 Taking the data analysis interface shown as an example, in such a case... Figure 7 In the data analysis interface shown, control 701 is the range setting control. Taking the default influence range threshold of 10 as an example, "10" can be displayed in control 701 so that users can know the influence range threshold of the currently displayed device contact point based on the content displayed in control 701.

[0139] Step 1032-2: Adjust the display range of each device contact point in the target scatter plot according to the adjustment operation of the influence range threshold in the range adjustment control.

[0140] Optionally, the range adjustment control can provide users with the ability to adjust the impact range threshold, allowing users to dynamically adjust the impact range threshold according to actual technical requirements to meet the business needs of different services and effectively respond to business changes. Generally, the impact range threshold can be adjusted within a value range of 10-100. In many possible implementations, the impact range threshold can be larger or smaller, and the invention does not limit the specific value of the impact range threshold.

[0141] It should be noted that while users adjust the influence range threshold using the range adjustment controls, they can also adjust the display range (i.e., the size of the displayed device contact point) of each device contact point in real time in the target scatter plot to ensure that the display range of each device contact point remains consistent with the currently set influence range threshold.

[0142] Still as Figure 7 Taking the data analysis interface shown as an example, in such a case... Figure 7In the data analysis interface shown, users can directly input their desired influence range threshold in control 701 to adjust it. Control 701 also includes "+" and "-" buttons. Users can use the "+" button to increase the currently displayed influence range threshold, or the "-" button to decrease it. The adjustment step size can be set to a predetermined value; for example, a step size of 10 means that each press of the "+" button adds 10 to the currently displayed influence range threshold, and each press of the "-" button subtracts 10. Regardless of the method used to adjust the influence range threshold, the adjustment will be reflected in real-time on the display range of the device contact points in the target scatter plot.

[0143] It should be noted that for any device contact point, if there are data points within the display range of the device contact point, then the device contact point may be the cause of the defect corresponding to that data point; conversely, if there are no data points within the display range of the device contact point, then the device contact point may not have caused a product defect.

[0144] Therefore, when adjusting the display range of each device contact point in the target scatter plot based on the adjustment operation of the influence range threshold in the range adjustment control, for any device contact point, if there are data points in the display range of the device contact point before the adjustment but no data points in the display range of the device contact point after the adjustment, the display of the device contact point is hidden in the target scatter plot; conversely, if there are no data points in the display range of the device contact point before the adjustment but there are data points in the display range of the device contact point after the adjustment, the display of the hidden device contact point is restored in the target scatter plot.

[0145] Additionally, it should be noted that during the adjustment of the influence range threshold, the presence or absence of data points within the display range of a device contact point will change. Therefore, the computing device can adjust the display and hiding of device contact points in the target scatter plot in real time according to the actual situation, as long as it ensures that the device contact points displayed at each moment are those with data points within the display range.

[0146] The system adjusts the display range of each device contact point in real time, showing and hiding device contact points in the target scatter plot. It hides device contact points that do not have data points within the display range, while retaining device contact points that do have data points within the display range. In other words, it hides device contact points that do not cause product defects, and only retains device contact points that do cause product defects, making it easier for users to view and analyze.

[0147] add Figure 8 , Figure 8 This is a schematic diagram of a data analysis interface according to an embodiment of the present invention. Figure 7 Based on the data analysis interface shown, if the influence range threshold is adjusted to 30, the data analysis interface will be displayed as follows: Figure 8 As shown, the display range of the device contact point matches the set influence range threshold (i.e., 30), and... Figure 8 The device contact points shown in the target scatter plot are all device contact points with data points within the display range.

[0148] In such Figure 8 Based on the data analysis interface shown, users can further adjust the threshold for the scope of influence. Figure 9 , Figure 9 This is a schematic diagram of a data analysis interface according to an embodiment of the present invention. Figure 8 Based on the data analysis interface shown, if the influence range threshold is adjusted to 100, the data analysis interface will be displayed as follows: Figure 9 As shown, the display range of the device contact point matches the set influence range threshold (i.e., 100), and... Figure 9 The device contact points shown in the target scatter plot are all device contact points with data points within the display range.

[0149] In other possible implementations, the data analysis interface can also include a first reset control. When the user triggers the first reset control, the computing device can respond to the trigger operation of the first reset control and restore the target scatter plot to a form that only displays multiple data points.

[0150] Still as Figure 9 Taking the data analysis interface shown as an example, in such a case... Figure 9 In the data analysis interface shown, the button labeled "Reset" is the first reset control. If the user... Figure 9 When the button labeled "Reset" is triggered in the data analysis interface shown, the data analysis interface will revert to its previous state. Figure 5 As shown in the figure.

[0151] In addition, a second reset control can be set in the data analysis interface. When the user triggers the second reset control, the computing device can respond to the trigger operation of the second reset control, restore the display range of the device contact points displayed in the target scatter plot to the display range corresponding to the default influence range threshold, and display all device contact points completely in the target scatter plot.

[0152] Still as Figure 9 Taking the data analysis interface shown as an example, in such a case... Figure 9 In the data analysis interface shown, the button labeled "Reset Device Contact Points" is the second reset control. If the user... Figure 9 When the button labeled "Reset Device Contact Points" is triggered in the data analysis interface shown, the data analysis interface will revert to the state shown below. Figure 7 As shown in the figure.

[0153] Step 1032-3: In response to the analysis command for the target scatter plot, obtain defect analysis data based on the equipment contact points of the target production equipment and the currently set influence range threshold in the range adjustment control.

[0154] It should be noted that if the currently set impact range threshold meets the actual technical requirements, the user can trigger the analysis command in the data analysis interface to obtain defect analysis data based on the equipment contact points of the target production equipment and the currently set impact range threshold in the range adjustment control.

[0155] Optionally, the user can trigger an analysis command for the target scatter plot by pressing the Enter key on the keyboard.

[0156] In one possible implementation, when acquiring defect analysis data based on the equipment contact points of the target production equipment and the currently set influence range threshold in the range adjustment control in response to an analysis command for the target scatter plot, it can be achieved in the following way:

[0157] In response to the analysis command of the target scatter plot, the target defect information of the data points corresponding to the defects within the influence range of each device contact point is statistically analyzed according to the influence range threshold of each device contact point, so as to obtain defect analysis data.

[0158] The defect analysis data can be in tabular form, with equipment contact points as the table index and the target defect information of the data points within the influence range of each equipment contact point as the table data, in order to obtain the defect analysis data.

[0159] By acquiring defect analysis data, users can intuitively determine the detailed information of product defects caused by each device contact point, facilitating targeted handling in the future.

[0160] Optionally, the above-described data processing method for defect detection can be applied to the data processing system for defect detection described below.

[0161] See Figure 10 , Figure 10 This is a system architecture diagram of a data processing system for defect detection according to an embodiment of the present invention. The data processing system for defect detection can adopt a system architecture based on a Terminal Management System (TMS). Figure 10 As shown, a data processing system for defect detection may include AOI devices, a File Transfer Protocol (FTP) server, an ADC system, a Distributed File System (DFS) server, and a TMS client (i.e., a TMS client).

[0162] The AOI device can communicate with the FTP server, the FTP server with the ADC system, the ADC system with the DFS server, and the DFS server with the TMS Client via wired or wireless communication methods. This invention does not limit the communication methods.

[0163] After acquiring initial defect data, the AOI device can upload it to an FTP server for data cleaning to obtain the final defect data. Once the defect data is obtained, the FTP server uses a data loader to store it in a database (DB). This database can then distribute the defect data to the ADC system, which uses this data to retrieve candidate defect information. After obtaining the target defect information, the ADC system can transmit the candidate defect information to the DFS server. Optionally, the ADC system can use an interface to transmit the candidate defect information to the DFS server. After obtaining the target defect information, the DFS server stores the acquired candidate defect information in a database maintained by the TMS system (TMS DB). This allows the TMSClient to perform defect analysis based on the candidate defect information stored in the TMS DB to determine the correlation between defect locations and equipment contact points.

[0164] In addition, the ADC system can maintain a database. After obtaining the target defect information, the ADC system can not only transmit the target defect information to the DFS server, but also store the target defect information in the database maintained by the ADC system for subsequent reuse.

[0165] It should be noted that, through methods such as Figure 10 The flowchart illustrating the data processing system for defect detection that performs correlation analysis between defect locations and equipment contact points can be found in [reference needed]. Figure 11 , Figure 11 This is a flowchart illustrating a data processing method for defect detection according to an embodiment of the present invention, as shown below. Figure 11 As shown, users can set target filtering parameters corresponding to product filtering dimensions for filtering target defect information through the TMS client. The TMS client can then generate a Hypertext Transfer Protocol (HTTP) request based on the user-set target filtering parameters and send the generated HTTP request to the TMS server (i.e., the TMS Server). After receiving the HTTP request from the TMS client, the TMS Server can query the TMS database according to the target filtering parameters and return the query results (i.e., the target defect information) to the TMS client in the form of an HTTP message. After receiving the target defect information, the TMS client can input the target defect information into Echarts to generate at least one defect scatter plot, which is then displayed on the image display interface of the TMS client.

[0166] Users can select from at least one defect scatter plot displayed on the image display interface. The TMS client can then perform image synthesis processing based on the selected defect scatter plot to obtain the target scatter plot. The data analysis interface can then be displayed on the TMS client, and the target scatter plot can be shown through the data analysis interface.

[0167] Furthermore, users can set the parameter values ​​for contact point filtering through the TMS client. The TMS client can then generate an HTTP request based on these parameters and send it to the TMS Server. Upon receiving the HTTP request from the TMS client, the TMS Server can filter the device contact points to be displayed based on the parameter values ​​and return the retrieved contact points to the TMS client. The TMS client can simultaneously display data points and device contact points in the target scatter plot based on the received contact points. This allows users to adjust the threshold of the influence range of device contact points based on the data points and contact points displayed in the target scatter plot, thereby acquiring defect analysis data.

[0168] The above Figure 11 The described implementation process is merely a procedural description of the data processing method for defect detection provided by this invention. The specific implementation methods of each step can be found in the above embodiments, and will not be repeated here.

[0169] Corresponding to the embodiments of the aforementioned methods, the present invention also provides embodiments of a corresponding data processing apparatus for defect detection and the computing device on which it is applied.

[0170] See Figure 12 , Figure 12 This is a block diagram of a data processing apparatus for defect detection according to an embodiment of the present invention, such as... Figure 12 As shown, the device includes:

[0171] The first acquisition module 1201 is used to acquire target screening parameters, so as to acquire target defect information based on the target screening parameters. The target defect information is used to describe the defects existing in the target product corresponding to the target screening parameters.

[0172] Display module 1202 is used to display an image display interface including a defect scatter plot based on target defect information. The defect scatter plot is used to show the location of defects existing in the target product on the target product.

[0173] The second acquisition module 1203 is used to respond to the analysis command of the defect scatter plot displayed in the image display interface, and acquire defect analysis data based on the equipment contact points of the target production equipment and the influence range threshold set for the equipment contact points. The target production equipment is the production equipment used to produce the target product, and the defect analysis data is used to indicate the statistical information of the defects caused by each equipment contact point.

[0174] In some embodiments, the first acquisition module 1201, when acquiring target filtering parameters to acquire target defect information based on the target filtering parameters, is used to:

[0175] The image generation interface is displayed, which provides the function of setting target filtering parameters for at least one pre-configured product filtering dimension.

[0176] In response to parameter setting operations in the image generation interface, obtain the target filtering parameters set for at least one product filtering dimension;

[0177] Based on the target screening parameters, obtain target defect information.

[0178] In some embodiments, the first acquisition module 1201, when acquiring target defect information based on target filtering parameters, is used to:

[0179] Based on the target screening parameters, the candidate defect information is filtered to obtain the target defect information. The candidate defect information includes the defect information corresponding to each product that has been produced. The defect information is used to describe the defects that exist in the product.

[0180] In some embodiments, the first acquisition module 1201 is further configured to acquire candidate defect information corresponding to any product that has been produced;

[0181] The first acquisition module 1201, when acquiring candidate defect information corresponding to any of the manufactured products, is used for:

[0182] Obtain the product image corresponding to the product;

[0183] Optical inspection is performed based on product images to obtain product defect data, which includes defect images and defect description data.

[0184] Defect detection and classification are performed based on defect data to obtain candidate defect information.

[0185] In some embodiments, the first acquisition module 1201, when performing optical inspection based on a product image to obtain defect data of the product, is used for:

[0186] Initial defect data is obtained by performing optical inspection based on product images;

[0187] The initial defect data is cleaned, and the data obtained after data cleaning is used as the product's defect data. The data cleaning process includes at least data filtering and / or data format conversion.

[0188] In some embodiments, the image generation interface displays at least one product filtering dimension and input controls;

[0189] The first acquisition module 1201, when acquiring target filtering parameters set for at least one product filtering dimension in response to a parameter setting operation in the image generation interface, is used for:

[0190] In response to an input operation in the input control, the parameters entered in the input control are used as target filter parameters for at least one product filter dimension.

[0191] In some embodiments, the product screening dimensions include at least one of the following: product production time, production equipment identification, product model, product number, and product batch number.

[0192] In some embodiments, the display module 1202, when used to display an image display interface including a defect scatter plot based on target defect information, is configured to:

[0193] Based on the target defect information, an image display interface is displayed, and at least one defect scatter plot is displayed in the image display interface. Each defect scatter plot corresponds to a target product, and the defect scatter plot includes multiple data points, with each data point corresponding to a defect in the target product.

[0194] In some embodiments, the target defect information includes at least the product model and the coordinates of the defect location;

[0195] Display module 1202, when used to display at least one defect scatter plot, is used for:

[0196] For any target product, based on the product model and defect location coordinates included in the target defect information corresponding to the target product, the target coordinate system of the product size corresponding to the product model is displayed, and a scatter plot of the defects corresponding to the target product is displayed based on the target coordinate system.

[0197] In some embodiments, the target defect information may further include at least one of the following: production equipment identifier, product number, product batch number, and defect location identifier;

[0198] The display module 1202 is also used for at least one of the following:

[0199] Display the production equipment identifier at the preset location corresponding to the defect scatter plot;

[0200] Display the product number at the preset location corresponding to the defect scatter plot;

[0201] Display the product batch number at the preset location corresponding to the defect scatter plot;

[0202] Based on the defect location identifier, the number of defects is displayed at the preset location corresponding to the defect scatter plot.

[0203] In some embodiments, the second acquisition module 1203, when acquiring defect analysis data based on the equipment contact points of the target production equipment and the influence range threshold set for the equipment contact points in response to an analysis instruction for the defect scatter plot displayed in the image display interface, is configured to:

[0204] In response to the selection operation in the defect scatter plot displayed in the image display interface, the data analysis interface is displayed based on the selected defect scatter plot, and the target scatter plot is displayed in the data analysis interface. The target scatter plot is obtained based on the selected defect scatter plot.

[0205] In response to the analysis command for the target scatter plot, defect analysis data is obtained based on the equipment contact points of the target production equipment and the influence range threshold set for the equipment contact points.

[0206] In some embodiments, the defect scatter plot displayed in the image display interface is at least one, one defect scatter plot corresponds to one target product, the defect scatter plot includes multiple data points, and one data point corresponds to a defect in the target product.

[0207] The second acquisition module 1203 is also used to acquire the target scatter plot;

[0208] The second acquisition module 1203, when used to acquire the target scatter plot, is used for:

[0209] If there is only one selected defect scatter plot, then the selected defect scatter plot will be used as the target scatter plot.

[0210] If multiple defect scatter plots are selected, image synthesis processing is performed on the selected multiple defect scatter plots to obtain the target scatter plot. The data points in different defect scatter plots are displayed in different display styles in the target scatter plot.

[0211] In some embodiments, the data analysis interface includes a target display control and a range adjustment control;

[0212] The acquisition module 1203, in response to an analysis instruction for at least one defect scatter plot, acquires defect analysis data based on the equipment contact points of the target production equipment and an influence range threshold set for the equipment contact points, for the following purposes:

[0213] In response to a trigger operation on the target display control, display the equipment contact points of the target production equipment in the target scatter plot;

[0214] Adjust the display range of each device contact point in the target scatter plot based on the adjustment operation of the influence range threshold in the range adjustment control;

[0215] In response to the analysis command for the target scatter plot, defect analysis data is obtained based on the equipment contact points of the target production equipment and the currently set influence range threshold in the range adjustment control.

[0216] In some embodiments, the acquisition module 1203, when displaying the device contact points of the target production equipment in the target scatter plot in response to a trigger operation on the target display control, is configured to:

[0217] In response to a trigger operation on the target display control, the contact point filtering interface is displayed. The contact point filtering interface is used to set the filtering conditions used when filtering device contact points. The filtering conditions include the department to which the device belongs and / or the device type.

[0218] Based on the filtering criteria set in the contact point filtering interface, the device contact points that meet the filtering criteria are displayed in the target scatter plot.

[0219] In some embodiments, the second acquisition module 1203, when adjusting the display range of each device contact point in the target scatter plot according to the adjustment operation of the influence range threshold in the range adjustment control, is further configured to include at least one of the following:

[0220] For any device contact point, if there are data points within the display range of the device contact point before adjustment but no data points within the display range of the device contact point after adjustment, then the display of the device contact point will be hidden in the target scatter plot.

[0221] For any device contact point, if there are no data points within the display range of the device contact point before adjustment but there are data points within the display range of the device contact point after adjustment, then the display of the hidden device contact point will be restored in the target scatter plot.

[0222] In some embodiments, the data analysis interface further includes a first reset control;

[0223] The display module 1202 is also used to restore the target scatter plot to a form that only displays multiple data points in response to a trigger operation of the first reset control.

[0224] In some embodiments, the acquisition module 1203, when acquiring defect analysis data based on the equipment contact points of the target production equipment and the currently set influence range threshold in the range adjustment control in response to an analysis instruction for the target scatter plot, is configured to:

[0225] In response to the analysis command of the target scatter plot, the target defect information of the data points corresponding to the defects within the influence range of each device contact point is statistically analyzed according to the influence range threshold of each device contact point, so as to obtain defect analysis data.

[0226] For the device embodiments, since they basically correspond to the method embodiments, the relevant parts can be referred to in the description of the method embodiments. The device embodiments described above are merely illustrative. The modules described as separate components may or may not be physically separate, and the components shown as modules may or may not be physical modules, that is, they may be located in one place or distributed across multiple network modules. Some or all of the modules can be selected to achieve the purpose of the solution in this specification according to actual needs. Those skilled in the art can understand and implement this without creative effort.

[0227] The present invention also provides a computing device, see [link to relevant documentation]. Figure 13 , Figure 13 This is a schematic diagram of the structure of a computing device according to an embodiment of the present invention. Figure 13 As shown, the computing device includes a processor 1310, a memory 1320, and a network interface 1330. The memory 1320 stores computer instructions that can run on the processor 1310. The processor 1310 is used to implement the data processing method for defect detection provided in any embodiment of the present invention when executing the computer instructions. The network interface 1330 is used to implement input / output functions. In more possible implementations, the computing device may also include other hardware, which is not limited by the present invention.

[0228] This invention also provides a computer-readable storage medium, which can take many forms, such as RAM (Random Access Memory), volatile memory, non-volatile memory, flash memory, storage drives (e.g., hard disk drives), solid-state drives, any type of storage disk (e.g., optical discs, DVDs), or similar storage media, or combinations thereof. Specifically, the computer-readable medium can also be paper or other suitable media capable of printing programs. A computer program is stored on the computer-readable storage medium, and when executed by a processor, the computer program implements the data processing method for defect detection provided in any embodiment of this invention.

[0229] The present invention also provides a computer program product, including a computer program that, when executed by a processor, implements the data processing method for defect detection provided in any embodiment of the present invention.

[0230] Those skilled in the art will understand that one or more embodiments of this specification can be provided as a method, apparatus, computing device, computer-readable storage medium, or computer program product. Therefore, one or more embodiments of this specification can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, one or more embodiments of this specification can take the form of a computer program product implemented on one or more computer-readable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-readable program code.

[0231] The various embodiments in this specification are described in a progressive manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. In particular, the embodiments corresponding to computing devices are basically similar to the method embodiments, so the description is relatively simple; relevant parts can be referred to the descriptions of the method embodiments.

[0232] The foregoing has described specific embodiments of this specification. Other embodiments are within the scope of this invention. In some cases, the actions or steps described in this invention may be performed in a different order than those shown in the embodiments and still achieve the desired results. Furthermore, the processes depicted in the drawings do not necessarily require the specific or sequential order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0233] The embodiments of the subject matter and functional operation described in this specification can be implemented in the following ways: digital electronic circuits, tangibly embodied computer software or firmware, computer hardware including the structures disclosed in this specification and their structural equivalents, or combinations thereof. Embodiments of the subject matter described in this specification can be implemented as one or more computer programs, i.e., one or more modules of computer program instructions encoded on a tangible, non-transitory program carrier for execution by or control of the operation of a data processing apparatus for defect detection. Alternatively or additionally, the program instructions may be encoded on artificially generated propagation signals, such as machine-generated electrical, optical, or electromagnetic signals, which are generated to encode information and transmit it to a suitable receiving device for execution by the data processing apparatus for defect detection. The computer storage medium may be a machine-readable storage device, a machine-readable storage substrate, a random or serial access memory device, or combinations thereof.

[0234] The processing and logic flow described in this specification can be executed by one or more programmable computers that execute one or more computer programs to perform corresponding functions by operating on input data and generating output. The processing and logic flow can also be executed by dedicated logic circuitry—such as FPGAs (Field-Programmable Gate Arrays) or ASICs (Application-Specific Integrated Circuits), and the device can also be implemented as dedicated logic circuitry.

[0235] Suitable computers for executing computer programs include, for example, general-purpose and / or special-purpose microprocessors, or any other type of central processing unit. Typically, the central processing unit receives instructions and data from read-only memory and / or random access memory. The basic components of a computer include a central processing unit for implementing or executing instructions and one or more memory devices for storing instructions and data. Typically, a computer will also include one or more mass storage devices for storing data, such as disks, magneto-optical disks, or optical disks, or the computer will be operatively coupled to such mass storage devices to receive data from or transfer data to them, or both. However, a computer is not required to have such devices. Furthermore, a computer can be embedded in another device, such as a mobile phone, a personal digital assistant (PDA), a mobile audio or video player, a game console, a global positioning system (GPS) receiver, or a portable storage device such as a universal serial bus (USB) flash drive, to name a few.

[0236] Computer-readable media suitable for storing computer program instructions and data include all forms of non-volatile memory, media, and memory devices, such as semiconductor memory devices (e.g., EPROM, EEPROM, and flash memory devices), magnetic disks (e.g., internal hard disks or removable disks), magneto-optical disks, and CD-ROM and DVD-ROM disks. Processors and memory may be supplemented by or incorporated into dedicated logic circuitry.

[0237] While this specification contains numerous specific implementation details, these should not be construed as limiting the scope of any invention or the scope of the claims, but rather are primarily intended to describe features of specific embodiments of a particular invention. Certain features described in the various embodiments herein may also be implemented in combination in a single embodiment. Conversely, various features described in a single embodiment may also be implemented separately in various embodiments or in any suitable sub-combination. Furthermore, while features may function in certain combinations as described above and even initially claimed in this way, one or more features from a claimed combination may be removed from that combination in some cases, and a claimed combination may refer to a sub-combination or a variation thereof.

[0238] Similarly, although the operations are depicted in a specific order in the accompanying drawings, this should not be construed as requiring these operations to be performed in the specific order shown or sequentially, or requiring all illustrated operations to be performed to achieve the desired result. In some cases, multitasking and parallel processing may be advantageous. Furthermore, the separation of various system modules and components in the above embodiments should not be construed as requiring such separation in all embodiments, and it should be understood that the described program components and systems can generally be integrated together in a single software product or packaged into multiple software products.

[0239] Thus, specific embodiments of the subject matter have been described. Other embodiments are within the scope of the invention. In some cases, the actions described in the invention can be performed in a different order and still achieve the desired result. Furthermore, the processes depicted in the drawings are not necessarily shown in a specific order or sequence to achieve the desired result. In some implementations, multitasking and parallel processing may be advantageous.

[0240] Other embodiments of this specification will readily occur to those skilled in the art upon consideration of the specification and practice of the invention claimed herein. This specification is intended to cover any variations, uses, or adaptations that follow the general principles of this specification and include common knowledge or customary techniques in the art not claimed herein. That is, this specification is not limited to the precise structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope.

[0241] The above description is merely an optional embodiment of this specification and is not intended to limit this specification. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this specification shall be included within the scope of protection of this specification.

Claims

1. A data processing method for defect detection, characterized in that, The method includes: Obtain target filtering parameters, and obtain target defect information based on the target filtering parameters. The target defect information is used to describe the defects existing in the target product corresponding to the target filtering parameters. Based on the target defect information, an image display interface including a defect scatter plot is displayed, wherein the defect scatter plot is used to show the location of the defects present in the target product on the target product; In response to a selection operation in the defect scatter plot displayed on the image display interface, a data analysis interface is displayed based on the selected defect scatter plot, and a target scatter plot is displayed in the data analysis interface. The target scatter plot is obtained based on the selected defect scatter plot. The data analysis interface includes a target display control and a range adjustment control. In response to a triggering operation on the target display control, the device contact points of the target production equipment are displayed in the target scatter plot, wherein the target production equipment is the production equipment used to produce the target product; Based on the adjustment operation of the influence range threshold in the range adjustment control, adjust the display range of each device contact point in the target scatter plot; In response to the analysis command of the target scatter plot, based on the equipment contact points of the target production equipment and the currently set influence range threshold in the range adjustment control, defect analysis data is obtained. The defect analysis data is used to indicate the statistical information of the defects caused by each equipment contact point within the corresponding influence range.

2. The method according to claim 1, characterized in that, The step of obtaining target filtering parameters, and obtaining target defect information based on the target filtering parameters, includes: Display an image generation interface, which provides the function of setting target filtering parameters for at least one pre-configured product filtering dimension; In response to a parameter setting operation in the image generation interface, the target filtering parameters set for the at least one product filtering dimension are obtained; Based on the target screening parameters, the target defect information is obtained.

3. The method according to claim 2, characterized in that, The step of obtaining the target defect information based on the target screening parameters includes: Based on the target screening parameters, the candidate defect information is filtered to obtain the target defect information. The candidate defect information includes defect information corresponding to each product that has been produced. The defect information is used to describe the defects existing in the product.

4. The method according to claim 3, characterized in that, For any product that has been produced, the process of obtaining the candidate defect information corresponding to the product includes: Obtain the product image corresponding to the product; Optical inspection is performed on the product image to obtain defect data of the product, the defect data including defect images and defect description data; Based on the defect data, defect detection and classification are performed to obtain the candidate defect information.

5. The method according to claim 4, characterized in that, The process of performing optical inspection based on the product image to obtain defect data of the product includes: Optical inspection is performed based on the product image to obtain initial defect data; The initial defect data is cleaned, and the data obtained after the data cleaning process is used as the defect data of the product. The data cleaning process includes at least data filtering and / or data format conversion.

6. The method according to claim 2, characterized in that, The image generation interface displays at least one product filtering dimension and input controls; The step of obtaining the target filtering parameters set for the at least one product filtering dimension in response to the parameter setting operation in the image generation interface includes: In response to an input operation in the input control, the parameters entered in the input control are used as target filtering parameters set for the at least one product filtering dimension.

7. The method according to claim 6, characterized in that, The product screening dimensions include at least one of the following: product production time, production equipment identification, product model, product number, and product batch number.

8. The method according to claim 1, characterized in that, The image display interface based on the target defect information, including a defect scatter plot, includes: Based on the target defect information, an image display interface is displayed, and at least one defect scatter plot is displayed in the image display interface. Each defect scatter plot corresponds to a target product, and the defect scatter plot includes multiple data points, with each data point corresponding to a defect in the target product.

9. The method according to claim 8, characterized in that, The target defect information includes at least the product model and the coordinates of the defect location; The display of at least one defect scatter plot includes: For any target product, based on the product model and defect location coordinates included in the target defect information corresponding to the target product, the target coordinate system of the product size corresponding to the product model is displayed, so as to display the defect scatter plot corresponding to the target product based on the target coordinate system.

10. The method according to claim 9, characterized in that, The target defect information also includes at least one of the following: production equipment identification, product number, product batch number, and defect location number; The method further includes at least one of the following: The production equipment identifier is displayed at a preset location corresponding to the defect scatter plot; The product number is displayed at a preset position corresponding to the defect scatter plot; The product batch number is displayed at a preset position corresponding to the defect scatter plot; Based on the defect location number, the number of defects is displayed at the preset position corresponding to the defect scatter plot.

11. The method according to claim 1, characterized in that, The image display interface displays at least one defect scatter plot, with each defect scatter plot corresponding to a target product. The defect scatter plot includes multiple data points, with each data point corresponding to a defect in the target product. The process of obtaining the target scatter plot includes: If there is only one selected defect scatter plot, then the selected defect scatter plot will be used as the target scatter plot. If multiple defect scatter plots are selected, image synthesis processing is performed on the selected multiple defect scatter plots to obtain the target scatter plot, wherein the data points corresponding to different types of defects are displayed in different display styles in the target scatter plot.

12. The method according to claim 1, characterized in that, The step of displaying the device contact points of the target production equipment in the target scatter plot in response to a trigger operation on the target display control includes: In response to a trigger operation on the target display control, a contact point filtering interface is displayed. The contact point filtering interface is used to set the filtering conditions used when filtering device contact points. The filtering conditions include the device's department and / or device type. Based on the filtering conditions set in the contact point filtering interface, the device contact points that meet the filtering conditions are displayed in the target scatter plot.

13. The method according to claim 1, characterized in that, When adjusting the display range of each device contact point in the target scatter plot based on the adjustment operation of the influence range threshold in the range adjustment control, the method further includes at least one of the following: For any device contact point, if there are data points within the display range of the device contact point before adjustment but no data points within the display range of the device contact point after adjustment, then the display of the device contact point is hidden in the target scatter plot. For any device contact point, if there are no data points within the display range of the device contact point before adjustment but there are data points within the display range of the device contact point after adjustment, then the display of the hidden device contact point is restored in the target scatter plot.

14. The method according to claim 1, characterized in that, The data analysis interface also includes a first reset control; After displaying the equipment contact points of the target production equipment in the target scatter plot in response to a trigger operation on the target display control, the method further includes: In response to the triggering operation of the first reset control, the target scatter plot is restored to a form that displays only multiple data points.

15. The method according to claim 1, characterized in that, In response to the analysis command for the target scatter plot, the defect analysis data is obtained based on the equipment contact points of the target production equipment and the currently set influence range threshold in the range adjustment control, including: In response to the analysis command of the target scatter plot, the target defect information of the data points corresponding to the defects within the influence range of each device contact point is statistically analyzed according to the influence range threshold of each device contact point to obtain the defect analysis data.

16. A data processing device for defect detection, characterized in that, The device includes: The first acquisition module is used to acquire target screening parameters, and to acquire target defect information based on the target screening parameters. The target defect information is used to describe the defects existing in the target product corresponding to the target screening parameters. The display module is used to display an image display interface including a defect scatter plot based on the target defect information. The defect scatter plot is used to show the location of the defects existing in the target product on the target product. The second acquisition module is used to respond to the selection operation in the defect scatter plot displayed on the image display interface, display a data analysis interface based on the selected defect scatter plot, and display a target scatter plot in the data analysis interface. The target scatter plot is obtained based on the selected defect scatter plot. The data analysis interface includes a target display control and a range adjustment control. The second acquisition module is further configured to, in response to a trigger operation on the target display control, display the device contact points of the target production equipment in the target scatter plot, wherein the target production equipment is a production equipment used to produce the target product; The second acquisition module is further configured to adjust the display range of each device contact point in the target scatter plot according to the adjustment operation of the influence range threshold in the range adjustment control; The second acquisition module is further configured to, in response to the analysis instruction of the target scatter plot, acquire defect analysis data based on the equipment contact points of the target production equipment and the currently set influence range threshold in the range adjustment control, wherein the defect analysis data is used to indicate statistical information of defects caused by each equipment contact point within the corresponding influence range.

17. A computing device, characterized in that, The computing device includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to perform the operations performed by the data processing method for defect detection as described in any one of claims 1 to 15.

18. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a program that, when executed by a processor, performs the operations of the data processing method for defect detection as described in any one of claims 1 to 15.

Images