Scanning electron microscope image defect classification method and device based on design layout

Abstract

The present application provides a scanning electron microscope image defect classification method, device, electronic device and computer-readable storage medium based on a design layout, the method comprising: obtaining a scanning electron microscope image; obtaining defect information of the scanning electron microscope image using a defect recognition method based on the scanning electron microscope image; wherein the defect information comprises: at least one of defect location information, defect surrounding graphic grouping information and upper and lower layer connection relationship information of the defect location layout; and classifying defects based on the defect information. The present application can effectively improve the accuracy of defect classification.

Description

Technical Field

[0001] The present application relates to the technical field of defect classification, and in particular to a scanning electron microscope image defect classification method, device, electronic device and computer-readable storage medium based on a design layout. Background Art

[0002] Currently, in the chip production process, as the chip production technology nodes continue to advance, the defects generated in the production process are getting smaller and smaller, and the application of electron beam defect detection equipment is becoming more and more common.

[0003] In the prior art, defects in scanning electron microscope (SEM) images are generally classified based on the acquired image information. Specifically, the SEM image of the silicon wafer is first collected by an electron beam defect detection device; then the image comparison method is used to determine whether there is a defect; finally, the defect classification is performed based on the SEM image information (such as defect size information, whether the defect material is consistent with the silicon wafer pattern material, and whether the defect is located in the lower or upper layer of the silicon wafer pattern).

[0004] From image comparison and analysis, based on the existing production and process information, we can obtain information such as defect material, source, and size on the silicon wafer, and use this information to classify the defects. Figure 1-Figure 5 As shown, the existing technology classifies defects in SEM images into mainly three categories: graphic bridge type defects, graphic break type defects, graphic peeling type defects, surface foreign material type defects and embedded type defects.

[0005] However, the existing technology only classifies defects based on the defect material, source, and size information on the silicon wafer, and is unable to classify defects more effectively in combination with the silicon wafer design layout, resulting in low defect classification accuracy.

[0006] Therefore, how to effectively improve the accuracy of defect classification is a technical problem that technical personnel in this field urgently need to solve. Summary of the invention

[0007] The purpose of this application is to provide a scanning electron microscope image defect classification method, device, electronic device and computer-readable storage medium based on a design layout, which can effectively improve the accuracy of defect classification.

[0008] According to a first aspect of the present application, a scanning electron microscope image defect classification method based on a design layout is provided, the method comprising: acquiring a scanning electron microscope image;

[0009] Obtaining defect information of the scanning electron microscope image using a defect recognition method based on the scanning electron microscope image; wherein the defect information includes at least one of defect location information, defect surrounding pattern grouping information, and upper and lower layer connection relationship information of the defect location layout;

[0010] Defects are classified based on the defect information.

[0011] Optionally, defect information of the scanning electron microscope image is obtained by using a defect recognition method based on the scanning electron microscope image, including:

[0012] The defect location information of the scanning electron microscope image is obtained by using a defect detection algorithm based on the scanning electron microscope image.

[0013] Optionally, defect information of the scanning electron microscope image is obtained by using a defect recognition method based on the scanning electron microscope image, including:

[0014] Based on the scanning electron microscope image, an image grouping algorithm is used to obtain the defect surrounding graphic grouping information of the scanning electron microscope image.

[0015] Optionally, the image grouping algorithm is used based on the scanning electron microscope image to obtain the defect surrounding graphic grouping information of the electron microscope image, including:

[0016] Based on the scanning electron microscope image, using an image grouping algorithm according to a first preset range of the defect, obtaining first defect peripheral graphic grouping information; wherein the first preset range is used to characterize a comparative radius of the defect;

[0017] Based on the first defect surrounding graphic grouping information, the second defect surrounding graphic grouping information is obtained by using an image grouping algorithm according to a second preset range; wherein the second preset range is larger than the first preset range.

[0018] Optionally, the image grouping algorithm includes at least one of the following four items:

[0019] Greedy grouping strategy, orphan grouping strategy, rich grouping strategy, weak-rich grouping strategy.

[0020] Optionally, defect information of the scanning electron microscope image is obtained by using a defect recognition method based on the scanning electron microscope image, including:

[0021] Based on the scanning electron microscope image, the upper and lower layer connection relationship recognition algorithm of the layout position is used to obtain the upper and lower layer connection relationship information of the defect position layout of the scanning electron microscope image.

[0022] Optionally, classify defects based on defect information, including:

[0023] Defects are classified based on defect position information to generate a first classification result; wherein the first classification result is used to characterize that defects at the same position in the graphic lines are classified into one category, and defects at different positions in the graphic lines are classified into different categories.

[0024] Optionally, the first classification result includes at least one of the following six items:

[0025] Graphic line defects, blank defects, end defects, corner defects, connection hole defects and gate area defects.

[0026] Optionally, the graphic line type defect is a defect located on a graphic line.

[0027] Optionally, a blank type defect is a defect located at a blank position between two graphic lines.

[0028] Optionally, an end-type defect is a defect located at an end of a graphic line.

[0029] Optionally, a corner defect is a defect located at a corner of a graphic line.

[0030] Optionally, the connection hole type defect is a position where the defect is located within the connection hole.

[0031] Optionally, the gate-shaped area defect is a defect located at a gate-shaped area of ​​a graphic line.

[0032] Optionally, classify defects based on defect information, including:

[0033] The defects are classified based on the grouping information of the surrounding graphics of the defects to generate a second classification result; wherein the second classification result is used to characterize that defects with the same surrounding graphics are classified into one category, and defects with different surrounding graphics are classified into different categories.

[0034] Optionally, classify defects based on defect information, including:

[0035] The defects are classified based on the upper and lower layer connection relationship of the layout position to generate a third classification result; wherein the third classification result is used to characterize that the graphics with the same number of connection holes in the upper and lower layer connection relationship of the layout position are classified into one category, and the graphics with different numbers of connection holes are classified into different categories.

[0036] Optionally, the method further includes:

[0037] After there are defects with the same surrounding graphics in the second classification result, the upper and lower layer connection relationship information of the defect position layout of the scanning electron microscope image is obtained by using the upper and lower layer connection relationship recognition algorithm of the layout position based on the scanning electron microscope image.

[0038] According to a second aspect of the present application, a scanning electron microscope image defect classification device based on a design layout is provided, the device comprising: a first acquisition module, for acquiring a scanning electron microscope image;

[0039] An identification module is used to obtain defect information of a scanning electron microscope image by using a defect identification method based on the scanning electron microscope image; wherein the defect information includes at least one of defect location information, defect surrounding graphic grouping information, and upper and lower layer connection relationship information of the defect location layout;

[0040] The classification module is used to classify defects based on defect information.

[0041] Optionally, the identification module is used to obtain defect position information of the scanning electron microscope image using a defect detection algorithm based on the scanning electron microscope image.

[0042] Optionally, the identification module is used to obtain defect periphery graphic grouping information of the scanning electron microscope image by using an image grouping algorithm based on the scanning electron microscope image.

[0043] Optionally, an identification module is used to obtain a first defect peripheral graphic grouping information based on a scanning electron microscope image using an image grouping algorithm according to a first preset range of the defect; wherein the first preset range is used to characterize a comparative radius of the defect; and to obtain a second defect peripheral graphic grouping information based on the first defect peripheral graphic grouping information using an image grouping algorithm according to a second preset range; wherein the second preset range is larger than the first preset range.

[0044] Optionally, the image grouping algorithm includes at least one of the following four items:

[0045] Greedy grouping strategy, orphan grouping strategy, rich grouping strategy, weak-rich grouping strategy.

[0046] Optionally, a recognition module is used to obtain upper and lower layer connection relationship information of the defect position layout of the scanning electron microscope image using an upper and lower layer connection relationship recognition algorithm of the layout position based on the scanning electron microscope image.

[0047] Optionally, a classification module is used to classify defects based on defect position information to generate a first classification result; wherein the first classification result is used to characterize that defects in the same position in the graphic lines are classified into one category, and defects in different positions in the graphic lines are classified into different categories.

[0048] Optionally, the first classification result includes at least one of the following six items:

[0049] Graphic line defects, blank defects, end defects, corner defects, connection hole defects and gate area defects.

[0050] Optionally, the graphic line type defect is a defect located on a graphic line.

[0051] Optionally, a blank type defect is a defect located at a blank position between two graphic lines.

[0052] Optionally, an end-type defect is a defect located at an end of a graphic line.

[0053] Optionally, a corner defect is a defect located at a corner of a graphic line.

[0054] Optionally, the connection hole type defect is a position where the defect is located within the connection hole.

[0055] Optionally, the gate-shaped area defect is a defect located at a gate-shaped area of ​​a graphic line.

[0056] Optionally, a classification module is used to classify defects based on the grouping information of the defect surrounding graphics to generate a second classification result; wherein the second classification result is used to characterize that defects with the same surrounding graphics are classified into one category, and defects with different surrounding graphics are classified into different categories.

[0057] Optionally, a classification module is used to classify defects based on the upper and lower layer connection relationship of the layout position to generate a third classification result; wherein the third classification result is used to characterize that graphics with the same number of connecting holes in the upper and lower layer connection relationship of the layout position are classified into one category, and graphics with different numbers of connecting holes are classified into different categories.

[0058] Optionally, the device also includes: a second acquisition module, which is used to obtain the upper and lower layer connection relationship information of the defect position layout of the scanning electron microscope image based on the scanning electron microscope image using the upper and lower layer connection relationship recognition algorithm of the layout position after there is a defect with the same surrounding graphics in the second classification result.

[0059] According to a third aspect of the present application, an electronic device is provided, which includes a processor, a memory, and a program or instruction stored in the memory and executable on the processor, and when the program or instruction is executed by the processor, the steps of the scanning electron microscope image defect classification method based on the design layout as shown in the first aspect are implemented.

[0060] According to a fourth aspect of the present application, a readable storage medium is provided, on which a program or instruction is stored. When the program or instruction is executed by a processor, the steps of the scanning electron microscope image defect classification method based on the design layout as shown in the first aspect are implemented.

[0061] After acquiring a scanning electron microscope image, the present application uses a defect recognition method to acquire defect information of the scanning electron microscope image, wherein the defect information includes at least one of defect location information, defect surrounding graphic grouping information, and upper and lower layer connection relationship information of the defect location layout. That is, based on the design layout, defects are more effectively classified according to any one or more of the defect location information, defect surrounding graphic grouping information, and upper and lower layer connection relationship information of the defect location layout, thereby improving the accuracy of defect classification. BRIEF DESCRIPTION OF THE DRAWINGS

[0062] In order to more clearly illustrate the specific implementation methods of the present application or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0063] Figure 1-Figure 5 A schematic diagram of the classification of defects in scanning electron microscope images provided by the prior art;

[0064] Figure 6 A flowchart of a scanning electron microscope image defect classification method based on a design layout provided in an embodiment of the present application;

[0065] Figure 7 A schematic diagram of a scanning electron microscope image defect classification method based on a design layout provided in an embodiment of the present application;

[0066] Figure 8-Figure 13 A schematic diagram of a scanning electron microscope image defect classification method based on a design layout provided in an embodiment of the present application;

[0067] Fig.14 A schematic diagram of a scanning electron microscope image defect classification method based on a design layout provided in an embodiment of the present application; and

[0068] Fig.15 A schematic diagram of a scanning electron microscope image defect classification device based on a design layout provided in an embodiment of the present application. DETAILED DESCRIPTION

[0069] In order to make the above and other features and advantages of the present application more clear, the present application is further described below in conjunction with the accompanying drawings. It should be understood that the specific embodiments given herein are for the purpose of explaining to those skilled in the art and are only exemplary and not restrictive.

[0070] In the following description, many specific details are set forth to provide a thorough understanding of the present application. However, it will be apparent to one of ordinary skill in the art that specific details are not required to practice the present application. In other cases, well-known steps or services are not described in detail to avoid obscuring the present application.

[0071] Based on the content of the background technology section, it can be seen that in the prior art, the method of classifying defects only based on the defect material, source, and size information obtained on the silicon wafer cannot be combined with the silicon wafer design layout to more effectively classify the defects, resulting in low accuracy of defect classification.

[0072] In order to solve the above technical problems, the present application provides a scanning electron microscope image defect classification method based on a design layout, a device, an electronic device and a computer-readable storage medium. The scanning electron microscope image defect classification method based on a design layout provided by the present application is described in detail below through specific embodiments and application scenarios in conjunction with the accompanying drawings.

[0073] like Figure 6 As shown, the present application provides a scanning electron microscope image defect classification method based on a design layout, which may include:

[0074] Step S11: Acquire a scanning electron microscope image.

[0075] Step S13: obtaining defect information of the scanning electron microscope image using a defect recognition method based on the scanning electron microscope image; wherein the defect information includes at least one of defect location information, defect surrounding graphic grouping information, and upper and lower layer connection relationship information of the defect location layout.

[0076] In the embodiment of the present application, a scanning electron microscope image of a silicon wafer can be obtained by an electron beam defect detection device. After the scanning electron microscope image is obtained, defect information of the scanning electron microscope image can be obtained according to a defect recognition method. The defect information includes at least one of defect location information, defect surrounding graphic grouping information, and upper and lower layer connection relationship information of the defect location layout. That is, the present application classifies defects more accurately based on the above defect information.

[0077] In an optional embodiment, the defect location information of the scanning electron microscope image can be obtained by using a defect detection algorithm based on the scanning electron microscope image in the following manner:

[0078] The defect location information of the scanning electron microscope image is obtained by using a defect detection algorithm based on the scanning electron microscope image.

[0079] In this embodiment, the defect location information in the scanning electron microscope image can be accurately identified according to the defect detection algorithm, that is, the specific location of the defect in the graphic line is accurately identified by the defect detection algorithm, and then the defect is classified according to the specific location of the defect in the graphic line. This embodiment solves the technical problem in the prior art that design defects or mask defects that frequently occur in a certain type of graphic cannot be effectively identified, and therefore cannot achieve design improvements.

[0080] It should be noted that the specific steps of the defect detection algorithm may be: obtaining a first scanning electron microscope image of a position to be detected, and a second scanning electron microscope image of other positions except the position to be detected; based on the first scanning electron microscope image and the second scanning electron microscope image, aligning them with the design layout of the position to be detected, respectively, to obtain an alignment result; based on the alignment result, comparing the first scanning electron microscope image and the second scanning electron microscope image with the design layout of the position to be detected, respectively, to obtain difference information; based on the difference information and the recipe file, determining whether the first difference between the first scanning electron microscope image and the design layout is a defect.

[0081] In an optional embodiment, obtaining defect information of a scanning electron microscope image by using a defect recognition method based on the scanning electron microscope image includes:

[0082] Based on the scanning electron microscope image, an image grouping algorithm is used to obtain the defect surrounding graphic grouping information of the scanning electron microscope image.

[0083] In an optional embodiment, obtaining defect peripheral graphic grouping information of the scanning electron microscope image by using an image grouping algorithm based on the scanning electron microscope image includes:

[0084] Based on the scanning electron microscope image, an image grouping algorithm is used to obtain first defect peripheral graphic grouping information according to a first preset range of the defect; wherein the first preset range is used to characterize a comparative radius of the defect.

[0085] Based on the first defect surrounding graphic grouping information, the second defect surrounding graphic grouping information is obtained by using an image grouping algorithm according to a second preset range; wherein the second preset range is larger than the first preset range.

[0086] In this embodiment, when there are multiple defects, an image grouping algorithm can be used within a first preset range to obtain the first defect peripheral graphic grouping information, and then a second image grouping algorithm can be performed within a second preset range based on the first defect peripheral graphic grouping information to obtain the second defect peripheral graphic grouping information. It should be noted that the second preset range is larger than the first preset range, and the first preset range and the second preset range are used to characterize the comparison radius of the defect. Since the defects are classified by the image grouping algorithm using a smaller defect comparison radius, the range of the peripheral graphics of the defects is small, so the features of the peripheral graphics of the defects are less, and the range of the multiple classification results obtained is larger; therefore, it is necessary to use a larger comparison radius to classify the defects again through the image grouping algorithm to obtain more accurate results. The present application adopts multi-level classification to more accurately obtain the classification results of the peripheral graphics of the defects, so as to more accurately classify the defects.

[0087] In an optional embodiment, the image grouping algorithm includes at least one of the following four items: a greedy grouping strategy, an orphan grouping strategy, a rich grouping strategy, and a weak-rich grouping strategy.

[0088] In this embodiment, the above four image grouping algorithms can use the same image grouping algorithm to classify defects, or can use multiple image grouping algorithms to classify defects. For example: when there are multiple defects on the scanning electron microscope image, the orphan grouping strategy can be used to classify the defects within a relatively small radius for the first time, so as to obtain a relatively broad defect classification result; the orphan grouping strategy can be used to classify the defects within a relatively large radius for the second time, so as to obtain a relatively accurate defect classification result. For another example: when there are multiple defects on the scanning electron microscope image, the greedy grouping strategy can be used to classify the defects within a relatively small radius for the first time, so as to obtain a relatively broad defect classification result; the orphan grouping strategy can be used to classify the defects within a relatively large radius for the second time, so as to obtain a relatively accurate defect classification result.

[0089] In an optional embodiment, obtaining defect position information of a scanning electron microscope image using a defect detection algorithm based on the scanning electron microscope image includes:

[0090] Based on the scanning electron microscope image, the upper and lower layer connection relationship recognition algorithm of the layout position is used to obtain the upper and lower layer connection relationship information of the defect position layout of the scanning electron microscope image.

[0091] Figure 7 A schematic diagram of a scanning electron microscope image defect classification method based on a design layout provided in an embodiment of the present application. Figure 7As shown, in the design layout on the right, the upper and lower layer connection relationship at the layout position on the left includes Via holes with defects and Via holes without defects; the upper and lower layer connection relationship at the layout position on the right only includes Via holes with defects. If the Via hole with defects in the design layout on the right is broken, the upper and lower layer connection relationship at the layout position on the right will not be connected, and the upper and lower layer connection at the layout position on the left can still continue to be connected. Therefore, the upper and lower layer connection relationship at the layout position with only defective Via holes has a greater impact on electrical performance, so its defect is a key defect. The upper and lower layer connection relationship recognition algorithm of the layout position adopted in this application can accurately give an assessment of the destructiveness of the defects and increase attention to key defects.

[0092] It should be noted that the upper layer and the lower layer in the upper-lower layer connection relationship can be determined according to the direction of the image lines.

[0093] Step S15: Classify defects based on the defect information.

[0094] In an optional embodiment, the defects may be classified based on the defect information in the following manner:

[0095] Defects are classified based on defect position information to generate a first classification result; wherein the first classification result is used to characterize that defects at the same position in the graphic lines are classified into one category, and defects at different positions in the graphic lines are classified into different categories.

[0096] In this embodiment, defects are classified according to their positions in the graphic lines to generate a first classification result. It should be noted that the first classification result is used to characterize that defects in the same position in the graphic lines are classified into one category, and defects in different positions in the graphic lines are classified into different categories. For example: if the defects are in the same position in the graphic lines (all are graphic line defects), then the defects in the same position in the graphic lines are classified into one category; if there are 5 defects, and the positions of the 5 defects in the graphic lines are different, then the 5 defects are classified into 5 categories.

[0097] Combination Figure 8-Figure 13 As shown, in an optional embodiment, the first classification result includes at least one of the following six items:

[0098] Graphic line defects, blank defects, end defects, corner defects, connection hole defects and gate area defects.

[0099] Combination Figure 8 As shown, in an optional embodiment, the graphic line defect is a defect located on the graphic line.

[0100] Combination Fig. 9As shown, in an optional embodiment, the blank type defect is a defect located at a blank position between two graphic lines.

[0101] Combination Fig.10 As shown, in an optional embodiment, the end-type defect is a defect located at the end of the graphic line.

[0102] Combination Fig.11 As shown, in an optional embodiment, the corner defect is a defect located at the corner of the graphic line.

[0103] Combination Fig.12 As shown, in an optional embodiment, the connection hole type defect is a defect located within the connection hole.

[0104] Combination Fig.13 As shown, in an optional embodiment, the gate-shaped area defect is a defect located at the gate-shaped area of ​​the graphic line.

[0105] In an optional embodiment, classifying defects based on defect information includes:

[0106] The defects are classified based on the grouping information of the surrounding graphics of the defects to generate a second classification result; wherein the second classification result is used to characterize that defects with the same surrounding graphics are classified into one category, and defects with different surrounding graphics are classified into different categories.

[0107] In this embodiment, the defects are classified according to the defect surrounding pattern grouping information to generate a second classification result. Fig.14 As shown, the defects may include five defects A, B, C, D, and E. Through the first image grouping algorithm (i.e. Fig.14 The pattern grouping method in 1) identifies the surrounding patterns of defects, and classifies defects with the same surrounding patterns into one category, and defects with different surrounding patterns into different categories, that is, A, C, and E are defects with the same surrounding patterns, and A, C, and E are classified into one category (that is, Fig.14 In the middle group G—1#1); B and D are the same defects in the surrounding graphics, and B and D are classified into one category (i.e. Fig.14 In the group G-1#2), (A, C, E) and (B, D) are different defects of the surrounding graphics, that is, they are divided into two categories. Then, through the second image grouping algorithm (i.e. Fig.14 The graphic grouping method 2) further groups (A, C, E) and (B, D). Among them, A and E are divided into one category (that is, Fig.14 C is divided into one category (i.e. Fig.14 Group G—2#2); B and D are divided into one category (i.e. Fig.14In the group G-3#1), (A, E), C, (B, D) are different defects of the surrounding graphics, and (A, E), C, (B, D) are divided into three categories. The present application continuously applies different classification modes and classification settings to perform multi-level classification and obtain more effective classification results for the surrounding graphics.

[0108] In an optional embodiment, the image grouping algorithm of the present application may not be limited to twice, but may be 3 times or 4 times. The specific number is not limited here and may be set accordingly by those skilled in the art according to actual conditions.

[0109] In an optional embodiment, defects are classified based on defect information, including: classifying defects based on the upper and lower layer connection relationship of the layout position to generate a third classification result; wherein the third classification result is used to characterize that graphics with the same number of connecting holes in the upper and lower layer connection relationship of the layout position are classified into one category, and graphics with different numbers of connecting holes are classified into different categories.

[0110] In this embodiment, defects are classified according to the number of connection holes in the upper and lower layer connection relationship of the layout position. Among them, the fewer number of connection holes in the upper and lower layer connection relationship of the layout position has a greater impact on the electrical performance. The upper and lower layer connection relationship recognition algorithm used in this application can accurately give an assessment of the destructiveness of the defects and increase attention to key defects.

[0111] Combination Figure 7 and Fig.14 As shown, in an optional embodiment, the method also includes: after there is a defect with the same surrounding graphics in the second classification result, using the upper and lower layer connection relationship recognition algorithm of the layout position based on the scanning electron microscope image to obtain the upper and lower layer connection relationship information of the defect position layout of the scanning electron microscope image.

[0112] In this embodiment, the defects are first classified by the image grouping algorithm to obtain the second classification result. If there are defects with the same surrounding graphics in the second classification result, the upper and lower layer connection relationship recognition algorithm of the layout position is used to classify the defects with the same surrounding graphics again; because when the surrounding graphics of at least two defects are the same, the at least two defects cannot be classified more accurately. Therefore, this application uses a combination of the image grouping algorithm and the upper and lower layer connection relationship recognition algorithm of the layout position to classify the defects multiple times, so as to classify the defects more accurately.

[0113] Compared with the prior art, the present application is different from the prior art because the prior art generally classifies defects in scanning electron microscope images based on image information, but cannot classify defects more effectively in combination with silicon wafer design layouts. Moreover, the design defects or mask defects that frequently occur in a certain type of graphics in the prior art cannot be effectively identified, so no design improvements can be obtained. At the same time, since the prior art lacks connection information between upper and lower layers, it is impossible to determine the impact of defects on electrical performance, and it is impossible to give an assessment of the destructiveness of defects, thereby ignoring attention to key defects.

[0114] Therefore, the scanning electron microscope image defect classification method based on the design layout of the present application can obtain information on the defect material, source, and size on the silicon wafer, and additionally obtain information on the type of design layout graphics where the defect is located, graphic classification information near the location of the defect, and information on the degree of impact of the defect on electrical performance. The information obtained based on the design layout makes it easy to discover systematic and recurring defects, and it is also easy to pay attention to, correct, and improve. Moreover, the information on the degree of impact of defects on electrical performance allows defects that have a large impact on the electrical performance of the chip to be given special attention, accelerating the improvement of chip design and increasing the speed of improving chip yield.

[0115] Fig.15 The scanning electron microscope image defect classification device based on the design layout provided in the embodiment of the present application is shown. Fig.15 As shown, the device comprises:

[0116] A first acquisition module 151 is used to acquire a scanning electron microscope image;

[0117] The identification module 152 is used to obtain defect information of the scanning electron microscope image by using a defect identification method based on the scanning electron microscope image; wherein the defect information includes at least one of defect position information, defect surrounding pattern grouping information, and upper and lower layer connection relationship information of the defect position layout;

[0118] The classification module 153 is used to classify defects based on the defect information.

[0119] Optionally, the identification module 152 is used to obtain defect position information of the scanning electron microscope image using a defect detection algorithm based on the scanning electron microscope image.

[0120] Optionally, the identification module 152 is used to obtain defect peripheral graphic grouping information of the scanning electron microscope image by using an image grouping algorithm based on the scanning electron microscope image.

[0121] Optionally, the identification module 152 is used to obtain first defect peripheral graphic grouping information based on the scanning electron microscope image using an image grouping algorithm according to a first preset range of the defect; wherein the first preset range is used to characterize a comparative radius of the defect; and to obtain second defect peripheral graphic grouping information based on the first defect peripheral graphic grouping information using an image grouping algorithm according to a second preset range; wherein the second preset range is larger than the first preset range.

[0122] Optionally, the image grouping algorithm includes at least one of the following four items:

[0123] Greedy grouping strategy, orphan grouping strategy, rich grouping strategy, weak-rich grouping strategy.

[0124] Optionally, the recognition module 152 is used to obtain the upper and lower layer connection relationship information of the defect position layout of the scanning electron microscope image by using the upper and lower layer connection relationship recognition algorithm of the layout position based on the scanning electron microscope image.

[0125] Optionally, the classification module 153 is used to classify defects based on defect position information to generate a first classification result; wherein the first classification result is used to characterize that defects in the same position in the graphic lines are classified into one category, and defects in different positions in the graphic lines are classified into different categories.

[0126] Optionally, the first classification result includes at least one of the following six items:

[0127] Graphic line defects, blank defects, end defects, corner defects, connection hole defects and gate area defects.

[0128] Optionally, the graphic line type defect is a defect located on a graphic line.

[0129] Optionally, a blank type defect is a defect located at a blank position between two graphic lines.

[0130] Optionally, an end-type defect is a defect located at an end of a graphic line.

[0131] Optionally, a corner defect is a defect located at a corner of a graphic line.

[0132] Optionally, the connection hole type defect is a position where the defect is located within the connection hole.

[0133] Optionally, the gate-shaped area defect is a defect located at a gate-shaped area of ​​a graphic line.

[0134] Optionally, the classification module 153 is used to classify defects based on the grouping information of the defect surrounding graphics to generate a second classification result; wherein the second classification result is used to characterize that defects with the same surrounding graphics are classified into one category, and defects with different surrounding graphics are classified into different categories.

[0135] Optionally, the classification module 153 is used to classify defects based on the upper and lower layer connection relationship of the layout position to generate a third classification result; wherein the third classification result is used to characterize that the graphics with the same number of connecting holes in the upper and lower layer connection relationship of the layout position are classified into one category, and the graphics with different numbers of connecting holes are classified into different categories.

[0136] Optionally, the device also includes: a second acquisition module, which is used to obtain the upper and lower layer connection relationship information of the defect position layout of the scanning electron microscope image based on the scanning electron microscope image using the upper and lower layer connection relationship recognition algorithm of the layout position after there is a defect with the same surrounding graphics in the second classification result.

[0137] It should be understood that the various modules of the device of the present application can be implemented in whole or in part by software, hardware, firmware or a combination thereof. Each module can be embedded in the processor of the electronic device in the form of hardware or firmware or independent of the processor, or can be stored in the memory of the electronic device in the form of software for the processor to call to execute the services of each module. Each module can be implemented as an independent component or module, or two or more modules can be implemented as a single component or module.

[0138] In one embodiment, an electronic device is provided, which includes a memory and a processor, and the memory stores computer instructions executable by the processor, and the computer instructions instruct the processor to execute each step of the method of the present application when executed by the processor. The electronic device can be a server, a terminal, or any other electronic device with necessary computing and / or processing capabilities in a broad sense. In one embodiment, the electronic device may include a processor, a memory, a network interface, a communication interface, etc. connected via a system bus. The processor of the electronic device can be used to provide necessary computing, processing and / or control capabilities. The memory of the electronic device may include a non-volatile storage medium and an internal memory. A service system, a computer program, etc. may be stored in or on the non-volatile storage medium. The internal memory can provide an environment for the operation of the service system and the computer program in the non-volatile storage medium. The network interface and the communication interface of the electronic device can be used to connect and communicate with external devices via a network.

[0139] The present application may be implemented as a computer-readable storage medium having a computer program stored thereon, which causes the steps of the method of the present application to be executed when executed by a processor. In one embodiment, the computer program is distributed on a plurality of electronic devices or processors coupled to a network so that the computer program is stored, accessed, and executed in a distributed manner by one or more electronic devices or processors. A single method step / service, or two or more method steps / services, may be performed by a single electronic device or processor or by two or more electronic devices or processors. One or more method steps / services may be performed by one or more electronic devices or processors, and one or more other method steps / services may be performed by one or more other electronic devices or processors. One or more electronic devices or processors may perform a single method step / service, or perform two or more method steps / services.

[0140] It will be appreciated by those skilled in the art that the steps of the method of the present application can be performed by instructing related hardware such as an electronic device or a processor through a computer program, and the computer program can be stored in a non-temporary computer-readable storage medium, and the computer program, when executed, causes the steps of the method of the present application to be performed. Depending on the circumstances, any reference to memory, storage, database, or other media herein may include non-volatile and / or volatile memory. Examples of non-volatile memory include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), flash memory, magnetic tape, floppy disk, magneto-optical data storage device, optical data storage device, hard disk, solid state disk, etc. Examples of volatile memory include random access memory (RAM), external cache memory, etc.

[0141] The various technical features described above can be combined arbitrarily. Although all possible combinations of these technical features are not described, any combination of these technical features should be considered to be covered by this specification as long as there is no contradiction in such combination.

[0142] Although the present application is described in conjunction with the embodiments, it should be understood by those skilled in the art that the above description and the accompanying drawings are only exemplary and non-restrictive, and the present application is not limited to the disclosed embodiments. Various modifications and variations are possible without departing from the spirit of the present application.

Claims

1. A scanning electron microscope image defect classification method based on design layout, characterized in that: The method comprises: Acquire scanning electron microscope images; Obtaining defect information of the scanning electron microscope image using a defect recognition method based on the scanning electron microscope image; wherein the defect information includes at least one of defect location information, defect surrounding graphic grouping information, and upper and lower layer connection relationship information of the defect location layout; classifying the defect based on the defect information; The classifying the defects based on the defect information includes: Classifying the defects based on the defect surrounding pattern grouping information to generate a second classification result; wherein the second classification result is used to characterize that defects with the same surrounding patterns are classified into one category, and defects with different surrounding patterns are classified into different categories; After there is a defect with the same surrounding graphics in the second classification result, obtaining upper and lower layer connection relationship information of the defect position layout of the scanning electron microscope image by using an upper and lower layer connection relationship recognition algorithm of the layout position based on the scanning electron microscope image; The defects are classified based on the upper and lower layer connection relationship of the layout position to generate a third classification result; wherein the third classification result is used to characterize that the graphics with the same number of connection holes in the upper and lower layer connection relationship of the layout position are classified into one category, and the graphics with different numbers of connection holes are classified into different categories.

2. The scanning electron microscope image defect classification method based on design layout according to claim 1, characterized in that: The method of obtaining defect information of the scanning electron microscope image by using a defect recognition method based on the scanning electron microscope image includes: The defect position information of the scanning electron microscope image is acquired by using a defect detection algorithm based on the scanning electron microscope image.

3. The scanning electron microscope image defect classification method based on design layout according to claim 1, characterized in that: The method of obtaining defect information of the scanning electron microscope image by using a defect recognition method based on the scanning electron microscope image includes: The defect periphery graphic grouping information of the scanning electron microscope image is obtained by using an image grouping algorithm based on the scanning electron microscope image.

4. The scanning electron microscope image defect classification method based on design layout according to claim 3, characterized in that: The step of obtaining the defect surrounding graphic grouping information of the scanning electron microscope image by using an image grouping algorithm based on the scanning electron microscope image includes: Based on the scanning electron microscope image, using the image grouping algorithm according to a first preset range of the defect, obtaining first graphic grouping information of the periphery of the defect; wherein the first preset range is used to characterize a comparative radius of the defect; Based on the first defect surrounding graphic grouping information, the second defect surrounding graphic grouping information is obtained by using the image grouping algorithm according to a second preset range; wherein the second preset range is larger than the first preset range.

5. The scanning electron microscope image defect classification method based on design layout according to claim 1, characterized in that: The method of obtaining defect information of the scanning electron microscope image by using a defect recognition method based on the scanning electron microscope image includes: Based on the scanning electron microscope image, the upper and lower layer connection relationship information of the defect position layout of the scanning electron microscope image is obtained by using the upper and lower layer connection relationship recognition algorithm of the layout position.

6. The scanning electron microscope image defect classification method based on design layout according to claim 2, characterized in that: The classifying the defects based on the defect information includes: The defects are classified based on the defect position information to generate a first classification result; wherein the first classification result is used to characterize that defects at the same position in the graphic lines are classified into one category, and defects at different positions in the graphic lines are classified into different categories.

7. The scanning electron microscope image defect classification method based on design layout according to claim 6, characterized in that: The first classification result includes at least one of the following six items: Graphic line defects, blank defects, end defects, corner defects, connection hole defects and gate area defects.

8. The scanning electron microscope image defect classification method based on design layout according to claim 7, characterized in that: The graphic line defect is a defect located on a graphic line.

9. The scanning electron microscope image defect classification method based on design layout according to claim 7, characterized in that: The blank type defect is a defect located at a blank position between two graphic lines.

10. The scanning electron microscope image defect classification method based on design layout according to claim 7, characterized in that: The end-type defect is a defect located at the end of a graphic line.

11. The scanning electron microscope image defect classification method based on design layout according to claim 7, characterized in that: The corner defect is a defect located at a corner of a graphic line.

12. The scanning electron microscope image defect classification method based on design layout according to claim 7, characterized in that: The connection hole type defect is a position where the defect is located inside the connection hole.

13. The scanning electron microscope image defect classification method based on design layout according to claim 7, characterized in that: The gate-shaped area defect is a position where the defect is located in the gate-shaped area of ​​the graphic line.

14. A scanning electron microscope image defect classification device based on a design layout, characterized in that: The device comprises: A first acquisition module is used to acquire a scanning electron microscope image; An identification module, used to obtain defect information of the scanning electron microscope image by using a defect identification method based on the scanning electron microscope image; wherein the defect information includes at least one of defect position information, defect surrounding pattern grouping information, and upper and lower layer connection relationship information of the defect position layout; A classification module, used for classifying the defects based on the defect information; The classification module is specifically used to classify the defects based on the defect surrounding pattern grouping information to generate a second classification result; wherein the second classification result is used to characterize that defects with the same surrounding patterns are classified into one category, and defects with different surrounding patterns are classified into different categories; A second acquisition module is used to obtain upper and lower layer connection relationship information of the defect position layout of the scanning electron microscope image by using an upper and lower layer connection relationship recognition algorithm of the layout position based on the scanning electron microscope image after there is a defect with the same surrounding pattern in the second classification result; The classification module is also used to classify the defects based on the upper and lower layer connection relationship of the layout position to generate a third classification result; wherein the third classification result is used to characterize that the graphics with the same number of connection holes in the upper and lower layer connection relationship of the layout position are divided into one category, and the graphics with different numbers of connection holes are divided into different categories.

15. The scanning electron microscope image defect classification device based on design layout according to claim 14, characterized in that: The recognition module is used to obtain the defect position information of the scanning electron microscope image by using a defect detection algorithm based on the scanning electron microscope image.

16. The scanning electron microscope image defect classification device based on design layout according to claim 14, characterized in that: The recognition module is used to obtain the defect surrounding graphic grouping information of the scanning electron microscope image by using an image grouping algorithm based on the scanning electron microscope image.

17. The scanning electron microscope image defect classification device based on design layout according to claim 16, characterized in that: The identification module is used to obtain the first defect surrounding graphic grouping information based on the scanning electron microscope image and the first preset range of the defect by using the image grouping algorithm; wherein the first preset range is used to characterize the comparative radius of the defect; and to obtain the second defect surrounding graphic grouping information based on the first defect surrounding graphic grouping information and the second preset range by using the image grouping algorithm; wherein the second preset range is larger than the first preset range.

18. The scanning electron microscope image defect classification device based on design layout according to claim 14, characterized in that: The recognition module is used to obtain the upper and lower layer connection relationship information of the defect position layout of the scanning electron microscope image by using the upper and lower layer connection relationship recognition algorithm of the layout position based on the scanning electron microscope image.

19. The scanning electron microscope image defect classification device based on design layout according to claim 15, characterized in that: The classification module is used to classify the defects based on the defect position information to generate a first classification result; wherein the first classification result is used to characterize that defects in the same position in the graphic lines are classified into one category, and defects in different positions in the graphic lines are classified into different categories.

20. The scanning electron microscope image defect classification device based on design layout according to claim 19, characterized in that: The first classification result includes at least one of the following six items: Graphic line defects, blank defects, end defects, corner defects, connection hole defects and gate area defects.

21. The scanning electron microscope image defect classification device based on design layout according to claim 20, characterized in that: The graphic line defect is a defect located on a graphic line.

22. The scanning electron microscope image defect classification device based on design layout according to claim 20, characterized in that: The blank type defect is a defect located at a blank position between two graphic lines.

23. The scanning electron microscope image defect classification device based on design layout according to claim 20, characterized in that: The end-type defect is a defect located at the end of a graphic line.

24. The scanning electron microscope image defect classification device based on design layout according to claim 20, characterized in that: The corner defect is a defect located at a corner of a graphic line.

25. The scanning electron microscope image defect classification device based on design layout according to claim 20, characterized in that: The connection hole type defect is a position where the defect is located inside the connection hole.

26. The scanning electron microscope image defect classification device based on design layout according to claim 20, characterized in that: The gate-shaped area defect is a position where the defect is located in the gate-shaped area of ​​the graphic line.

27. An electronic device, characterized in that: The electronic device comprises: a processor and a memory storing computer program instructions; When the processor executes the computer program instructions, the scanning electron microscope image defect classification method based on the design layout as described in any one of claims 1 to 13 is implemented.

28. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer program instructions, and when the computer program instructions are executed by the processor, the scanning electron microscope image defect classification method based on the design layout as described in any one of claims 1 to 13 is implemented.

Images