Method, device and storage medium for predicting photomask imaging
By acquiring test masks and inspection images, using machine learning models to train auxiliary image imaging data, and combining post-development and post-etching inspection images, the problem of inaccurate auxiliary image imaging detection in existing technologies is solved, achieving efficient prediction and risk warning for auxiliary image imaging, and improving product yield.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- SHENZHEN PENGXIN MICRO INTEGRATED CIRCUIT MFG CO LTD
- Filing Date
- 2024-11-28
- Publication Date
- 2026-05-29
AI Technical Summary
Existing technologies for the detection and analysis of assisted image imaging suffer from problems such as limited data sources and inaccurate analysis results, making it difficult to effectively avoid the risks associated with assisted image imaging.
By acquiring test photomasks, test process conditions, and inspection images, test data for auxiliary pattern imaging is trained using machine learning models. Combined with post-development and post-etching inspection images, quantitative analysis is performed to output the imaging prediction results of the product photomask and identify the risk areas for auxiliary pattern imaging.
It improves the predictive accuracy of auxiliary graphic imaging, enabling early warning and reducing the adverse effects of auxiliary graphic imaging on products, thereby improving product yield.
Smart Images
Figure CN122115305A_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of integrated circuits, and specifically to a prediction method, apparatus, and storage medium for photomask imaging. Background Technology
[0002] In integrated circuit layout design, auxiliary features (also known as scattering bars or Sbars) are often required. Auxiliary features can improve the accuracy and efficiency of integrated circuit manufacturing, ensuring the performance and reliability of the final product. The auxiliary features are inserted around sparse patterns, and their size is smaller than the imaging resolution of the lithography system, ensuring that no lithographic patterns are formed during exposure.
[0003] In actual manufacturing processes, due to various reasons, auxiliary patterns still pose a risk of image formation; that is, auxiliary patterns can still be exposed and developed, forming photolithographic patterns. To mitigate the risks of auxiliary pattern imaging (AFPrinting), it is necessary to detect and analyze the auxiliary pattern imaging. However, current technologies for detecting and analyzing auxiliary pattern imaging often suffer from problems such as limited data sources and inaccurate analysis results. Summary of the Invention
[0004] In view of this, embodiments of this application provide a method, apparatus and storage medium for predicting photomask imaging, which can improve the prediction accuracy of auxiliary graphic imaging.
[0005] The technical solution of this application embodiment is implemented as follows:
[0006] This application provides a method for predicting photomask imaging, comprising: acquiring a test photomask, test process conditions, and a detection image; wherein the detection image is generated using the test photomask and the test process conditions; the detection image includes: a post-development detection image and a post-etching detection image; determining test data for auxiliary pattern imaging based on the test photomask and the detection image; using the test photomask data, the test process conditions, and the auxiliary pattern imaging test data as input datasets to train a machine learning model; acquiring a product photomask; and outputting an imaging prediction result for the product photomask based on the machine learning model.
[0007] In some embodiments of this application, the test mask includes: a first test mask; an auxiliary pattern is disposed in the first test mask; determining test data of the auxiliary pattern imaging based on the test mask and the detection image includes: forming a search box in the first test mask; wherein the search box contains the auxiliary pattern; determining a recognition area corresponding to the search box in the detection image; recognizing the auxiliary pattern imaging in the recognition area; and generating test data of the auxiliary pattern imaging.
[0008] In some embodiments of this application, forming a search box in the first test photomask includes: determining the coordinates of the auxiliary graphic in the first test photomask; forming the search box centered on the auxiliary graphic based on the coordinates of the auxiliary graphic; wherein the width of the search box is less than or equal to the standard distance value from the auxiliary graphic to the main graphic, and is less than or equal to the standard distance value between the auxiliary graphics.
[0009] In some embodiments of this application, the test mask further includes: a second test mask; the second test mask does not have an auxiliary pattern; the first test mask and the second test mask have the same main pattern; the detection image includes: a first detection image corresponding to the first test mask, and a second detection image corresponding to the second test mask; the step of identifying the auxiliary pattern image in the recognition area includes: performing grayscale conversion on the first detection image and the second detection image respectively for the same recognition area to obtain a first recognition area grayscale image and a second recognition area grayscale image; reading the grayscale values of the first recognition area grayscale image and the second recognition area grayscale image respectively; comparing the grayscale values of the first recognition area grayscale image and the second recognition area grayscale image to identify the auxiliary pattern image in the first detection image.
[0010] In some embodiments of this application, the test data for the auxiliary graphic imaging includes: the image and area of the auxiliary graphic imaging; the method for generating the area of the auxiliary graphic imaging includes: calculating the number of pixels with different gray values in the grayscale images of the first recognition region and the second recognition region; calculating the number of pixels in the auxiliary graphic imaging based on the number of pixels with different gray values; and calculating the area of the auxiliary graphic imaging based on the number of pixels in the auxiliary graphic imaging.
[0011] In some embodiments of this application, after the machine learning model is trained, the photomask imaging prediction method further includes: acquiring a verification photomask, verification process conditions, and a verification image; wherein the verification image is generated using the verification photomask and the verification process conditions; the data of the verification photomask, the verification process conditions, and the verification image are used as a verification dataset and input into the machine learning model for verification; if the matching degree between the imaging prediction result of the verification photomask and the verification image is lower than a threshold, the data of the verification photomask, the verification process conditions, and the verification image are used as an input dataset and input into the machine learning model for training.
[0012] In some embodiments of this application, the step of outputting the imaging prediction result of the product photomask includes: identifying a risk area for auxiliary graphic imaging on the graphic of the product photomask; and displaying the imaging prediction result of the target risk area in response to selecting a target risk area; the imaging prediction result includes: the imaging prediction graphic, the data of the product photomask, and the product process conditions.
[0013] In some embodiments of this application, the test process conditions include: photolithography conditions and etching conditions; wherein, the photolithography conditions include: exposure energy and focal length; the etching conditions include: the etching process formula; the test mask data includes: the pattern of the test mask and the placement conditions of the auxiliary pattern; wherein, the placement conditions of the auxiliary pattern include: the width of the auxiliary pattern, the minimum repetition period of the main pattern, the distance between the auxiliary pattern and the main pattern, and the distance between the auxiliary patterns.
[0014] This application embodiment also provides a photomask imaging prediction device, including: a data transmission module, a quantization analysis module, a model training module, and a prediction result display module; the data transmission module is configured to acquire a test photomask, test process conditions, and a detection image; wherein, the detection image is generated using the test photomask and the test process conditions; the detection image includes: a post-development detection image and a post-etching detection image; the quantization analysis module is configured to determine test data for auxiliary pattern imaging based on the test photomask and the detection image; the model training module is configured to input the data of the test photomask, the test process conditions, and the test data for auxiliary pattern imaging as input datasets into a machine learning model for training; the data transmission module is further configured to acquire a product photomask; the prediction result display module is configured to output the imaging prediction result of the product photomask based on the machine learning model.
[0015] This application also provides a computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the steps in the method described above.
[0016] It is understood that in this embodiment, both post-development and post-etching detection images are used as input datasets for training the machine learning model. This allows for a more comprehensive collection of training materials, enabling the model to perform quantitative analysis at both the post-development and post-etching detection image levels. Consequently, this effectively improves the prediction accuracy of assisted image imaging and provides early warnings of risks associated with assisted image imaging. Attached Figure Description
[0017] Figure 1 A schematic diagram of the implementation process of the photomask imaging prediction method provided in the embodiments of this application. Figure 1 ;
[0018] Figure 2 A schematic diagram of the implementation process of the photomask imaging prediction method provided in the embodiments of this application. Figure 2 ;
[0019] Figure 3 A schematic diagram of the implementation process of the photomask imaging prediction method provided in the embodiments of this application. Figure 3 ;
[0020] Figure 4 A graphical illustration of the prediction method for photomask imaging provided in the embodiments of this application. Figure 1 ;
[0021] Figure 5 A graphical illustration of the prediction method for photomask imaging provided in the embodiments of this application. Figure 2 ;
[0022] Figure 6 A graphical illustration of the prediction method for photomask imaging provided in the embodiments of this application. Figure 3 ;
[0023] Figure 7 A schematic diagram of the implementation process of the photomask imaging prediction method provided in the embodiments of this application. Figure 4 ;
[0024] Figure 8 A schematic diagram of the implementation process of the photomask imaging prediction method provided in the embodiments of this application. Figure 5 ;
[0025] Figure 9 A graphical illustration of the prediction method for photomask imaging provided in the embodiments of this application. Figure 4 ;
[0026] Figure 10 A schematic diagram of the implementation process of the photomask imaging prediction method provided in the embodiments of this application. Figure 6 ;
[0027] Figure 11 A schematic diagram of the implementation process of the photomask imaging prediction method provided in the embodiments of this application. Figure 7 ;
[0028] Figure 12 A graphical illustration of the prediction method for photomask imaging provided in the embodiments of this application. Figure 5 ;
[0029] Figure 13 A graphical illustration of the prediction method for photomask imaging provided in the embodiments of this application. Figure 6 ;
[0030] Figure 14 A graphical illustration of the prediction method for photomask imaging provided in the embodiments of this application. Figure 7 ;
[0031] Figure 15 A schematic diagram of the implementation process of the photomask imaging prediction method provided in the embodiments of this application. Figure 8 ;
[0032] Figure 16 A schematic diagram of the composition structure of the photomask imaging prediction device provided in the embodiments of this application;
[0033] Figure 17 A schematic diagram of the hardware entity of the computer device provided in the embodiments of this application. Detailed Implementation
[0034] To make the objectives, technical solutions, and advantages of this application clearer, the technical solutions of this application are further described in detail below with reference to the accompanying drawings and embodiments. The described embodiments should not be regarded as limitations on this application. All other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.
[0035] In the following description, references to "some embodiments" refer to a subset of all possible embodiments. It is understood that "some embodiments" may be the same or different subsets of all possible embodiments and may be combined with each other without conflict. The terms "first / second / third" are used merely to distinguish similar objects and do not represent a specific ordering of objects. It is understood that "first / second / third" may be interchanged in a specific order or sequence where permitted, so that the embodiments of this application described herein can be implemented in an order other than that illustrated or described herein.
[0036] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application pertains. The terminology used herein is for descriptive purposes only and is not intended to limit the scope of this application.
[0037] Figure 1 This is a schematic diagram of an optional implementation flow of the photomask imaging prediction method provided in this application embodiment. For example... Figure 1 As shown, the prediction method for photomask imaging includes steps S101 to S104. Each step will be explained in detail below.
[0038] S101. Obtain the test mask, test process conditions, and inspection images; wherein, the inspection images are generated using the test mask and test process conditions; the inspection images include: the inspection image after development and the inspection image after etching.
[0039] In this embodiment, the test mask may include a PDL (Pattern Design for Lithography), a PDM (Pattern Design for Model), or a PDV (Pattern Design for Verify). Some test masks (i.e., the first test mask) may have auxiliary patterns to collect data from the images formed by these patterns; other test masks (i.e., the second test mask) may not have auxiliary patterns and may be used for comparison.
[0040] In this embodiment, a semiconductor structure is obtained by processing a test mask under specific test process conditions. Electron microscopy is then used to inspect the semiconductor structure, yielding corresponding inspection images (i.e., electron microscope images). These inspection images may include an after-development inspection image (ADI) and an after-etching inspection image (AEI).
[0041] Accordingly, the test process conditions may include photolithography conditions and etching conditions. Photolithography conditions may include exposure energy (E) and focal length (F). Etching conditions may include the etching process recipe. Test process conditions may also include other process conditions that may affect the auxiliary pattern imaging, and are not limited thereto.
[0042] S102. Based on the test mask and the detected image, determine the test data for auxiliary graphic imaging.
[0043] In this embodiment, the test data for assisted graphic imaging may include: the image of the assisted graphic imaging, and the area of the assisted graphic imaging. Based on the first test mask with the assisted graphic, it can be determined whether assisted graphic imaging has occurred in the corresponding first detection image, and the test data for assisted graphic imaging can be determined. Furthermore, the first test mask without the assisted graphic and the corresponding second detection image can be used as a reference to further verify and determine the test data for assisted graphic imaging.
[0044] S103. The test data of the test photomask, the test process conditions, and the test data of auxiliary image imaging are used as the input dataset and input into the machine learning model for training.
[0045] In this embodiment, after determining the test data for auxiliary pattern imaging, the test mask data, test process conditions, and auxiliary pattern imaging test data can be used as input datasets to train a machine learning model. The test mask data may include: the pattern of the test mask, and the placement conditions of the auxiliary pattern.
[0046] refer to Figure 4 In the test photomask, a certain range is selected centered on the coordinates of the auxiliary graphic. Figure 4 The graphic within the dashed box (in the image) can be used as the graphic for testing the photomask.
[0047] refer to Figure 5 The placement conditions for auxiliary graphics may include: the width w of the auxiliary graphics, the minimum repetition period p of the main pattern, the distance d1 between the auxiliary graphics and the main pattern, and the distance d2 between the auxiliary graphics.
[0048] In this embodiment, the machine learning model can correlate and map the test mask data, test process conditions, and test data for auxiliary pattern imaging. In this way, for auxiliary patterns with different process conditions and different environmental types, the machine learning model can predict the results of auxiliary pattern imaging at the ADI and AEI levels.
[0049] S104. Obtain the product photomask.
[0050] S105. Based on the machine learning model, output the imaging prediction results of the product photomask.
[0051] In this embodiment, the product photomask is the same photomask used in actual production. The trained machine learning model can provide imaging prediction results for the product photomask at both the ADI and AEI levels. The imaging prediction results will display potential risk areas for auxiliary image imaging, along with corresponding quantitative analysis results. This allows engineers to assess the risk of auxiliary image imaging and take appropriate countermeasures.
[0052] It should be noted that after the photolithography process, auxiliary patterns may appear on the photoresist, resulting in auxiliary pattern imaging in ADI (Advanced Die-Consumer) etching. However, auxiliary pattern imaging in ADI may not necessarily affect subsequent etching processes, and therefore, auxiliary pattern imaging may not appear in AEI (Advanced Electron Irrigation). In other words, the situation regarding auxiliary pattern imaging in ADI and AEI may differ. Therefore, judging auxiliary pattern imaging solely based on ADI or AEI may lead to misjudgment.
[0053] It is understood that in this embodiment, both ADI and AEI are used as input datasets for training the machine learning model. This allows for a more comprehensive collection of training materials, enabling the model to perform quantitative analysis at both the ADI and AEI levels. Consequently, this effectively improves the prediction accuracy of assisted image imaging and provides early warnings of risks associated with assisted image imaging.
[0054] In some embodiments of this application, the test photomask includes: a first test photomask; the first test photomask has an auxiliary pattern disposed therein. This can be achieved through... Figure 2 The steps S201 to S204 shown are used to achieve the following: Figure 1 Step S102 shown will be explained in conjunction with each step.
[0055] S201. A search box is formed in the first test photomask; wherein, the search box contains auxiliary graphics.
[0056] S202. In the detected image, determine the recognition area corresponding to the search box.
[0057] S203. In the recognition area, identify auxiliary graphic imaging.
[0058] S204. Generate test data for auxiliary graphic imaging.
[0059] In this embodiment of the application, reference is made to Figure 6A search box containing the auxiliary graphic can be formed in the first test mask with the auxiliary graphic. Then, based on the test mask area surrounded by the search box, the corresponding area in the detection image is determined as the recognition area. Thus, in the recognition area, it is identified whether the auxiliary graphic imaging occurs, and test data of the auxiliary graphic imaging is generated.
[0060] In some embodiments of this application, it can be achieved through Figure 3 The steps S2011 to S2012 shown are used to achieve the following: Figure 2 Step S201 is shown. The explanation will follow each step.
[0061] S2011. Determine the coordinates of the auxiliary graphic within the first test photomask.
[0062] S2012. Based on the coordinates of the auxiliary graphic, a search box is formed with the auxiliary graphic as the center.
[0063] In this embodiment of the application, reference is made to Figure 6 The coordinates of the auxiliary graphic can be determined, and then, with these coordinates as the center, a certain distance can be extended outwards to form the edge of the search box; for example, the coordinates of the auxiliary graphic can be used as the center to extend a certain distance outwards to the surrounding main graphic.
[0064] In some embodiments of this application, reference is made to Figure 6 The width ws of the search box (i.e., the extended distance) is less than or equal to the standard distance between the auxiliary graphic and the main graphic, and is also less than or equal to the standard distance between the auxiliary graphics. The standard distance can be obtained from the placement rules of the auxiliary graphics.
[0065] Understandably, defining the recognition area by forming a search box allows for targeted recognition of auxiliary graphic images, preventing errors caused by an excessively large recognition area and thus improving the accuracy of auxiliary graphic image recognition. Furthermore, limiting the width of the search box based on standard distance values between the auxiliary and main graphics, as well as between the auxiliary graphics themselves, prevents the main graphic or other auxiliary graphics from being included within the search box and causing interference, thereby further improving the accuracy of auxiliary graphic image recognition.
[0066] In some embodiments of this application, the test mask further includes: a second test mask; the second test mask does not have auxiliary patterns. The first test mask and the second test mask have the same main pattern. The detection image includes: a first detection image corresponding to the first test mask, and a second detection image corresponding to the second test mask. This can be achieved through... Figure 7 The steps S2031 to S2033 shown are implemented. Figure 2Step S203 shown will be explained in conjunction with each step.
[0067] S2031. For the same recognition area, the first detection image and the second detection image are converted into grayscale images respectively to obtain the grayscale image of the first recognition area and the grayscale image of the second recognition area.
[0068] S2032. Read the grayscale values of the first recognition region grayscale image and the second recognition region grayscale image respectively.
[0069] S2033. Compare the grayscale values of the first recognition region grayscale image and the second recognition region grayscale image to identify the auxiliary graphic image in the first detection image.
[0070] In this embodiment, since no auxiliary pattern is provided in the second test mask, no auxiliary pattern image will appear in the second detection image corresponding to the second test mask. Therefore, the second detection image can be used as a blank control to identify the auxiliary pattern image in the first detection image.
[0071] refer to Figure 9 The grayscale images of the first and second recognition regions are outlined with dashed lines. By comparing the grayscale values, the differences between the two can be identified, thereby identifying the auxiliary graphic image.
[0072] Understandably, using the second test mask and the second detection image as a reference can quickly and accurately identify auxiliary imagery. This can improve the accuracy of the dataset input to the machine learning model, thereby effectively improving the prediction accuracy of auxiliary imagery.
[0073] In some embodiments of this application, the test data for assisted graphic imaging includes: the image and area of the assisted graphic imaging. Methods for generating the area of the assisted graphic imaging include... Figure 8 Steps S301 to S303 shown will be explained in conjunction with each step.
[0074] S301. Calculate the number of pixels with different grayscale values in the first recognition region grayscale image and the second recognition region grayscale image.
[0075] In this embodiment of the application, the grayscale value of the grayscale image of the second recognition region is used as a blank reference, and the number of pixels in the grayscale image of the first recognition region that are different from the blank reference can be calculated.
[0076] S302. Calculate the number of pixels that assist in image formation based on the number of pixels with different gray values.
[0077] In this embodiment, pixels with different grayscale values between the first and second recognition regions are likely to be pixels that assist in image formation. Therefore, by filtering pixels with different grayscale values, the number of pixels that assist in image formation can be further calculated.
[0078] S303. Calculate the area of the auxiliary graphic image based on the number of pixels in the auxiliary graphic image.
[0079] In this embodiment, the area of the auxiliary image can be calculated by multiplying the number of pixels in the auxiliary image by the area of each pixel. Alternatively, the area of the auxiliary image can be directly represented by the number of pixels in the auxiliary image; for example, if the number of pixels in the auxiliary image is 30, the area of the auxiliary image can be recorded as 30.
[0080] Understandably, calculating the area of the auxiliary image can enable more accurate quantitative analysis of the auxiliary image, thereby effectively improving the prediction accuracy of the auxiliary image.
[0081] In some embodiments of this application, Figure 1 Following step S103, the prediction method for photomask imaging further includes... Figure 10 The steps S401 to S403 are shown.
[0082] S401. Obtain the verification photomask, verification process conditions, and verification image; wherein, the verification image is generated using the verification photomask and verification process conditions.
[0083] S402. Use the data of the verification photomask, the verification process conditions, and the verification images as the verification dataset, and input them into the machine learning model for verification.
[0084] In this embodiment, the verification photomask, verification process conditions, and verification image can serve as a verification dataset to verify the training effect of the machine learning model. Specifically, a photomask closely resembling the product photomask is selected as the verification photomask; furthermore, random patterns that more closely resemble the pattern of the product photomask can be selected on the verification photomask as data for the verification photomask. Additionally, the verification process conditions can be selected to be similar to those in actual production. This effectively simulates the process of using the product photomask in actual production, thereby improving the verification effect.
[0085] S403. If the matching degree between the imaging prediction result of the verification mask and the verification image is lower than the threshold, the data of the verification mask, the verification process conditions and the verification image are used as the input dataset and input into the machine learning model for training.
[0086] In this embodiment of the application, if the matching degree between the imaging prediction result of the verification mask and the verification image is lower than the threshold, that is, the imaging prediction result of the machine learning model for the verification mask does not match the actual verification image, then the data of the verification mask, the verification process conditions and the verification image can be used as the input dataset and input into the machine learning model for further training.
[0087] In this embodiment, the matching degree between the imaging prediction result and the actual verification image can be determined by comparing the area of the auxiliary graphic imaging. For example, if the area of the auxiliary graphic imaging in the imaging prediction result is 30, while the area of the auxiliary graphic imaging in the actual verification image is 0, and the difference exceeds a threshold (i.e., the matching degree is lower than the threshold), then it can be determined that the imaging prediction result does not match the actual verification image.
[0088] In this embodiment of the application, if the relevant data of the verification mask is used as the input dataset, the relevant data of the test mask can be referenced to input the relevant data of the verification mask. That is, the data of the verification mask may include: the pattern of the verification mask and the placement conditions of the auxiliary pattern; the verification process conditions may include: photolithography conditions and etching conditions; the verification images may include: the post-development inspection image ADI and the post-etching inspection image AEI.
[0089] Understandably, for image types that do not meet the verification requirements, their relevant data can be added to the training input dataset. This can further improve the predictive ability of the machine learning model and increase the accuracy of predictions for assisted image imaging.
[0090] In some embodiments of this application, it can be achieved through Figure 11 The steps S501 to S502 shown are used to achieve the following: Figure 1 Step S105 is shown. The explanation will be based on each step.
[0091] S501. On the graphic of the product photomask, mark the risk areas for auxiliary graphic imaging.
[0092] In this embodiment of the application, reference is made to Figure 12 After the machine learning model has been trained, the product photomask can be input into the model, which will then provide corresponding imaging prediction results. Based on these prediction results, risk areas for auxiliary imaging can be identified on the product photomask graphic. Figure 12 The risk areas for auxiliary graphic imaging are marked with an "×".
[0093] S502. In response to the selected target risk area, display the imaging prediction results of the target risk area; the imaging prediction results include: imaging prediction graphics, product photomask data, and product process conditions.
[0094] In this embodiment of the application, imaging prediction results can be displayed for any selected risk area (i.e., target risk area). (See reference...) Figure 13 This can display an image prediction graphic of the target risk area. (Reference) Figure 14 It can also display data on product process conditions and product photomasks.
[0095] Understandably, for any input product photomask, the risk areas of auxiliary graphic imaging are identified, and the specific imaging prediction results are displayed. This makes it easier for engineers to assess the risks of auxiliary graphic imaging and take targeted measures. As a result, the adverse effects of auxiliary graphic imaging on the product can be reduced, and the product yield can be improved.
[0096] In this embodiment of the application, reference is made to Figure 15 The process conditions and auxiliary pattern (AF) settings of the test photomask, along with the corresponding ADI / AEI inspection images of the test photomask, are used as input datasets to train a machine learning model. Furthermore, the auxiliary pattern imaging is identified through grayscale value comparison. After the machine learning model is trained, it can output imaging prediction results, including the predicted imaging pattern, product photomask data, and product process conditions. This allows the machine learning model to perform quantitative analysis at the ADI and AEI levels, thereby effectively improving the prediction accuracy of auxiliary pattern imaging and enabling early warning of risks associated with auxiliary pattern imaging.
[0097] Figure 9 This is a schematic diagram illustrating the structural composition of a photomask imaging prediction device provided in an embodiment of this application. Figure 9 As shown, the photomask imaging prediction device 800 includes: a data transmission module 810, a quantization analysis module 820, a model training module 830, and a prediction result display module 840.
[0098] The data transmission module 810 is configured to acquire a test mask, test process conditions, and inspection images. The inspection images are generated using the test mask and test process conditions, and include post-development and post-etching inspection images. The quantitative analysis module 820 is configured to determine auxiliary image imaging test data based on the test mask and inspection images. The model training module 830 is configured to input the test mask data, test process conditions, and auxiliary image imaging test data as input datasets to a machine learning model for training. The data transmission module 810 is also configured to acquire a product mask. The prediction result display module 840 is configured to output imaging prediction results for the product mask based on the machine learning model.
[0099] In some embodiments of this application, the test photomask includes: a first test photomask; an auxiliary graphic is disposed in the first test photomask. The quantization analysis module 820 is further configured to form a search box in the first test photomask; wherein the search box contains the auxiliary graphic; determine the recognition area corresponding to the search box in the detection image; recognize the auxiliary graphic imaging in the recognition area; and generate test data of the auxiliary graphic imaging.
[0100] In some embodiments of this application, the quantization analysis module 820 is further configured to determine the coordinates of an auxiliary graphic in the first test photomask; and to form a search box centered on the auxiliary graphic based on the coordinates of the auxiliary graphic.
[0101] In some embodiments of this application, the width of the search box is less than or equal to the standard distance value between the auxiliary graphic and the main graphic, and is also less than or equal to the standard distance value between the auxiliary graphics.
[0102] In some embodiments of this application, the test mask further includes a second test mask; the second test mask does not have an auxiliary pattern. The first test mask and the second test mask have the same main pattern. The detection image includes a first detection image corresponding to the first test mask, and a second detection image corresponding to the second test mask. The quantization analysis module 820 is further configured to perform grayscale conversion on the first detection image and the second detection image for the same recognition area, respectively, to obtain a first recognition area grayscale image and a second recognition area grayscale image; read the grayscale values of the first recognition area grayscale image and the second recognition area grayscale image respectively; compare the grayscale values of the first recognition area grayscale image and the second recognition area grayscale image, and identify the auxiliary pattern image in the first detection image.
[0103] In some embodiments of this application, the test data for assisted graphic imaging includes: the image and area of the assisted graphic imaging. The quantization analysis module 820 is further configured to: calculate the number of pixels with different grayscale values in the first and second recognition region grayscale images; calculate the number of pixels for assisted graphic imaging based on the number of pixels with different grayscale values; and calculate the area of the assisted graphic imaging based on the number of pixels for assisted graphic imaging.
[0104] In some embodiments of this application, the data transmission module 810 is further configured to acquire a verification photomask, verification process conditions, and a verification image; wherein the verification image is generated using the verification photomask and verification process conditions. The model training module 830 is further configured to input the verification photomask data, verification process conditions, and verification image as a verification dataset into a machine learning model for verification.
[0105] In some embodiments of this application, the model training module 830 is further configured to, if the matching degree between the imaging prediction result of the verification mask and the verification image is lower than a threshold, use the data of the verification mask, the verification process conditions and the verification image as input datasets to train the machine learning model.
[0106] In some embodiments of this application, the prediction result display module 840 is further configured to identify risk areas for auxiliary graphic imaging on the graphic of the product photomask; in response to selecting a target risk area, display the imaging prediction result of the target risk area; the imaging prediction result includes: the imaging prediction graphic, the data of the product photomask, and the product process conditions.
[0107] In some embodiments of this application, the test process conditions include: photolithography conditions and etching conditions; wherein, the photolithography conditions include: exposure energy and focal length; and the etching conditions include: the etching process formulation. The test mask data includes: the pattern of the test mask and the placement conditions of the auxiliary patterns; wherein, the placement conditions of the auxiliary patterns include: the width of the auxiliary patterns, the minimum repeat period (pitch) of the main pattern, the distance between the auxiliary patterns and the main pattern, and the distance between the auxiliary patterns themselves.
[0108] The descriptions of the apparatus embodiments above are similar to those of the method embodiments above, and have similar beneficial effects. In some embodiments, the functions or modules included in the apparatus provided in this application can be used to perform the methods described in the method embodiments above. For technical details not disclosed in the apparatus embodiments of this application, please refer to the descriptions of the method embodiments of this application for understanding.
[0109] It should be noted that, in the embodiments of this application, if the above-described methods are implemented as software functional modules and sold or used as independent products, they can also be stored in a computer-readable storage medium. Based on this understanding, the technical solutions of the embodiments of this application, or the parts that contribute to related technologies, can be embodied in the form of a software product. This software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), magnetic disks, or optical disks. Thus, the embodiments of this application are not limited to any specific hardware, software, or firmware, or any combination of hardware, software, and firmware.
[0110] Figure 17 This application provides a hardware entity diagram of a computer device as an embodiment of the present application, such as... Figure 17As shown, the hardware entity of the computer device 1100 includes a processor 1101 and a memory 1102, wherein the memory 1102 stores a computer program that can run on the processor 1101, and the processor 1101 executes the program to implement the steps in the method of any of the above embodiments.
[0111] The memory 1102 stores computer programs that can run on the processor. The memory 1102 is configured to store instructions and applications that can be executed by the processor 1101. It can also cache data to be processed or already processed (e.g., image data, audio data, voice communication data, and video communication data) in the processor 1101 and various modules in the computer device 1100. It can be implemented by flash memory or random access memory (RAM).
[0112] When processor 1101 executes a program, it implements the steps of any of the methods described above. Processor 1101 typically controls the overall operation of computer device 1100.
[0113] This application provides a computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements some or all of the steps in the above-described method. The computer-readable storage medium can be transient or non-transient.
[0114] This application provides a computer program including computer-readable code, wherein when the computer-readable code is executed in a computer device, a processor in the computer device performs some or all of the steps in the above-described method.
[0115] This application provides a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program. When the computer program is read and executed by a computer, it implements some or all of the steps in the above-described method. This computer program product can be implemented specifically through hardware, software, or a combination thereof. In some embodiments, the computer program product is specifically embodied as a computer storage medium; in other embodiments, the computer program product is specifically embodied as a software product, such as a software development kit (SDK), etc.
[0116] It should be noted that the descriptions of the various embodiments above tend to emphasize the differences between them, while their similarities or commonalities can be referred to interchangeably. The descriptions of the above embodiments of the device, storage medium, computer program, and computer program product are similar to the descriptions of the above method embodiments and have similar beneficial effects. For technical details not disclosed in the embodiments of the device, storage medium, computer program, and computer program product of this application, please refer to the descriptions of the method embodiments of this application for understanding.
[0117] The aforementioned processor can be at least one of the following: Application Specific Integrated Circuit (ASIC), Digital Signal Processor (DSP), Digital Signal Processing Device (DSPD), Programmable Logic Device (PLD), Field Programmable Gate Array (FPGA), Central Processing Unit (CPU), Controller, Microcontroller, and Microprocessor. It is understood that other electronic devices can also implement the functions of the aforementioned processor, and this application does not specifically limit the specific implementation.
[0118] The aforementioned computer storage media / memory can be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), magnetic random access memory (FRAM), flash memory, magnetic surface memory, optical disc, or compact disc read-only memory (CD-ROM), etc.; or it can be various terminals that include one or any combination of the above-mentioned memories, such as mobile phones, computers, tablet devices, personal digital assistants, etc.
[0119] It should be understood that the phrase "one embodiment" or "an embodiment" throughout the specification means that a specific feature, structure, or characteristic related to the embodiment is included in at least one embodiment of this application. Therefore, "in one embodiment" or "in an embodiment" appearing throughout the specification does not necessarily refer to the same embodiment. Furthermore, these specific features, structures, or characteristics can be combined in any suitable manner in one or more embodiments. It should be understood that in the various embodiments of this application, the sequence numbers of the above steps / processes do not imply a sequential order of execution; the execution order of each step / process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application. The sequence numbers of the above embodiments of this application are merely descriptive and do not represent the superiority or inferiority of the embodiments.
[0120] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.
[0121] The above description is merely an embodiment of this application, but the scope of protection of this application is not limited thereto. Any changes or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application.
Claims
1. A prediction method for photomask imaging, characterized in that, include: Acquire a test mask, test process conditions, and inspection images; wherein, the inspection images are generated using the test mask and the test process conditions; the inspection images include: an inspection image after development and an inspection image after etching; Based on the test mask and the detected image, test data for auxiliary graphic imaging is determined; The data from the test photomask, the test process conditions, and the test data from the auxiliary image imaging are used as input datasets and fed into the machine learning model for training. Obtain the product photomask; Based on the machine learning model, the imaging prediction results of the product photomask are output.
2. The prediction method for photomask imaging according to claim 1, characterized in that, The test mask includes: a first test mask; the first test mask is provided with auxiliary patterns; The step of determining the test data for the auxiliary graphic imaging based on the test photomask and the detected image includes: A search box is formed in the first test photomask; wherein the search box contains the auxiliary graphic; In the detected image, determine the recognition area corresponding to the search box; In the recognition area, auxiliary graphic imaging is recognized; Generate the test data for the auxiliary graphic imaging.
3. The prediction method for photomask imaging according to claim 2, characterized in that, The process of forming a search box in the first test photomask includes: Within the first test photomask, the coordinates of the auxiliary graphic are determined; Based on the coordinates of the auxiliary graphic, a search box is formed with the auxiliary graphic as the center; wherein the width of the search box is less than or equal to the standard distance value from the auxiliary graphic to the main graphic, and is less than or equal to the standard distance value between the auxiliary graphics.
4. The prediction method for photomask imaging according to claim 2, characterized in that, The test mask further includes: a second test mask; the second test mask does not have auxiliary patterns; the first test mask and the second test mask have the same main pattern; The detection image includes: a first detection image corresponding to the first test mask, and a second detection image corresponding to the second test mask; The identification of auxiliary graphic imaging in the identification area includes: For the same recognition region, the first detection image and the second detection image are respectively converted into grayscale images to obtain a grayscale image of the first recognition region and a grayscale image of the second recognition region; Read the grayscale values of the first recognition region grayscale image and the second recognition region grayscale image respectively; The grayscale values of the first recognition region grayscale image and the second recognition region grayscale image are compared to identify the auxiliary graphic image in the first detection image.
5. The prediction method for photomask imaging according to claim 4, characterized in that, The test data for the assisted graphic imaging includes: the image and area of the assisted graphic imaging; The method for generating the area of the auxiliary graphic image includes: In the grayscale images of the first and second recognition regions, the number of pixels with different grayscale values is calculated. The number of pixels in the auxiliary image is calculated based on the number of pixels with different gray values. The area of the auxiliary graphic image is calculated based on the number of pixels in the auxiliary graphic image.
6. The prediction method for photomask imaging according to claim 1, characterized in that, After the machine learning model is trained, the prediction method for photomask imaging further includes: Obtain a verification photomask, verification process conditions, and a verification image; wherein the verification image is generated using the verification photomask and the verification process conditions; The data of the verification photomask, the verification process conditions, and the verification image are used as a verification dataset and input into the machine learning model for verification. If the matching degree between the imaging prediction result of the verification mask and the verification image is lower than a threshold, then the data of the verification mask, the verification process conditions, and the verification image are used as input datasets and input into the machine learning model for training.
7. The prediction method for photomask imaging according to claim 1, characterized in that, The output of the imaging prediction result of the product photomask includes: On the graphic of the product photomask, the risk areas for auxiliary graphic imaging are marked; In response to the selection of a target risk area, the imaging prediction results for the target risk area are displayed; the imaging prediction results include: imaging prediction graphics, data of the product photomask, and product process conditions.
8. The prediction method for photomask imaging according to claim 1, characterized in that, The test process conditions include: photolithography conditions and etching conditions; wherein, the photolithography conditions include: exposure energy and focal length; and the etching conditions include: the etching process formulation. The data of the test photomask includes: the pattern of the test photomask and the placement conditions of the auxiliary pattern; wherein, the placement conditions of the auxiliary pattern include: the width of the auxiliary pattern, the minimum repetition period of the main pattern, the distance between the auxiliary pattern and the main pattern, and the distance between the auxiliary patterns.
9. A predictive device for photomask imaging, characterized in that, include: The system includes a data transmission module, a quantitative analysis module, a model training module, and a prediction result display module. The data transmission module is configured to acquire a test mask, test process conditions, and a detection image; wherein the detection image is generated using the test mask and the test process conditions; the detection image includes: a detection image after development and a detection image after etching; The quantitative analysis module is configured to determine test data for auxiliary graphic imaging based on the test mask and the detection image; The model training module is configured to use the data of the test photomask, the test process conditions, and the test data of the auxiliary graphic imaging as input datasets to train the machine learning model. The data transmission module is also configured to acquire the product photomask; The prediction result display module is configured to output the imaging prediction result of the product photomask based on the machine learning model.
10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 8.