Method, device and equipment for generating training sample for training photoresist model

Abstract

The invention discloses a training sample generation method, device and equipment for training a photoresist model. The method comprises the following steps: acquiring a first training sample, wherein the first training sample comprises a first mask pattern and a first photoresist label pattern corresponding to the first mask pattern; inputting the first training sample into the photoresist model to obtain a defect area in the first mask pattern, the defect area being an area in which the difference between the photoresist pattern predicted according to the photoresist model and the first photoresist label pattern is greater than a preset difference threshold; determining a target layout area corresponding to the defect area in the first mask plate graph according to the defect area; and generating a second training sample for training the photoresist model according to the target layout area and the first photoresist label graph. According to the embodiment of the invention, the mask pattern with a poor model training effect is obtained by obtaining the photoresist pattern, and more training samples are obtained through the mask pattern, so that the training effect of the model is improved.

Description

Technical Field

[0001] The present application belongs to the field of semiconductor manufacturing technology, and in particular, relates to a method, device and equipment for generating training samples for training a photoresist model. Background Art

[0002] As the feature size of the design layout in the manufacturing of large-scale integrated circuits continues to shrink, the process equipment can only complete manufacturing under certain graphic conditions at increasingly extreme process sizes. However, the exposure cost in the chip manufacturing process is expensive and the manufacturing cycle is long. Therefore, in order to detect the manufacturability of the design layout with higher efficiency and quality, it is very necessary to determine the photoresist pattern corresponding to the design layout.

[0003] In the related art, the process from mask layout to photoresist pattern can be simulated by deep learning model. However, in the context of high cost and long cycle of chip exposure process, there is less data for training deep learning model, which leads to large error between the photoresist image determined by the deep learning model and the photoresist image in actual production. Therefore, how to increase the training samples of deep learning model is a technical problem that needs to be solved urgently by relevant technicians. Summary of the invention

[0004] The embodiments of the present application provide a method, device and equipment for generating training samples for training a photoresist model, which obtains a mask layout with poor model training effect by acquiring a photoresist pattern, and obtains more training samples through the mask layout, thereby improving the training effect of the model.

[0005] In a first aspect, an embodiment of the present application provides a method for generating training samples for training a photoresist model, comprising: obtaining a first training sample, the first training sample comprising a first mask pattern and a first photoresist label pattern corresponding thereto, the first mask pattern being a pattern obtained by sampling a first mask layout, the first photoresist label pattern being a photoresist pattern obtained by correcting the first mask layout through an optical proximity effect correction model; inputting the first training sample into the photoresist model to obtain a defective area in the first mask pattern, the defective area being an area where the difference between the photoresist pattern predicted by the photoresist model and the first photoresist label pattern is greater than a preset difference threshold; determining a target layout area corresponding to the defective area in the first mask layout according to the defective area; generating a second training sample for training the photoresist model according to the target layout area and the first photoresist label pattern.

[0006] In one embodiment, a first training sample is input into a photoresist model to obtain a defective area in a first mask pattern, including: predicting a photoresist pattern of the first mask pattern according to the photoresist model to obtain a first predicted photoresist pattern; determining deviation information between the first predicted photoresist pattern and the first photoresist label pattern; and determining the defective area according to the deviation information when it is determined that the deviation information is greater than a preset deviation threshold.

[0007] In one embodiment, determining the deviation information between a predicted photoresist pattern and a photoresist label pattern includes: obtaining a first coordinate value of a first feature point of the predicted photoresist pattern and a second coordinate value of a second feature point on the photoresist label pattern corresponding to the first feature point; calculating the distance between the first coordinate value and the first coordinate, and using the distance value as the deviation information.

[0008] In one embodiment, determining a defect area based on deviation information includes: counting the number of first feature points corresponding to deviation information greater than a preset deviation threshold; when it is determined that the number of first feature points is greater than the number threshold, determining the area including the first feature points as a defect area.

[0009] In one embodiment, a second training sample for training a photoresist model is generated based on a target layout area and a first photoresist label pattern, including: sampling the target layout area to obtain a second mask pattern; simulating the second mask pattern through an optical proximity effect correction model to obtain a photoresist pattern of the second mask pattern, and using it as a second photoresist label pattern of the second mask pattern; and generating a second training sample for training the photoresist model based on the second mask pattern and the corresponding second photoresist label pattern.

[0010] In one embodiment, the second mask pattern is simulated by an optical proximity effect correction model to obtain a photoresist pattern of the second mask pattern, including: acquiring optical information and photoresist parameter information; determining a light intensity distribution image corresponding to the second mask pattern by using the optical information and the photoresist parameter information; and intercepting the light intensity distribution image according to a preset light intensity threshold to obtain a photoresist pattern of the second mask pattern.

[0011] In one embodiment, before inputting the first training sample into the photoresist model, the method also includes: obtaining a training sample set, the training sample set including a plurality of third mask patterns and their corresponding third photoresist label patterns, the third mask pattern being a pattern obtained by sampling the third mask layout, and the third photoresist label pattern being a photoresist pattern obtained by simulating the third mask layout through an optical proximity effect correction model; predicting the photoresist pattern of the third mask pattern according to a preset photoresist model to obtain a third predicted photoresist pattern; determining a learning error of the predicted photoresist model according to an error between the third predicted photoresist pattern and the third photoresist label pattern; when it is determined that the learning error is greater than a preset error threshold, adjusting parameters in the preset photoresist pattern acquisition model, and returning to predicting the photoresist pattern of the third mask pattern according to the preset photoresist model to obtain a third predicted photoresist pattern, until the learning error is less than or equal to the preset error threshold, thereby obtaining a trained photoresist pattern acquisition model.

[0012] In one implementation, after obtaining the trained photoresist pattern acquisition model, the method further includes: updating the trained photoresist model using the training sample set and the second training sample.

[0013] In a second aspect, an embodiment of the present application provides a training sample generating device for training a photoresist model, the device comprising: a first acquisition module, used to acquire a first training sample, the first training sample comprising a first mask pattern and a first photoresist label pattern corresponding thereto, the first mask pattern being a pattern obtained by sampling a first mask layout, the first photoresist label pattern being a photoresist pattern obtained by correcting the first mask layout through an optical proximity effect correction model; a second acquisition module, used to input the first training sample into the photoresist model to obtain a defective area in the first mask pattern, the defective area being an area where the difference between the photoresist pattern predicted by the photoresist model and the first photoresist label pattern is greater than a preset difference threshold; a determination module, used to determine a target layout area corresponding to the defective area in the first mask layout according to the defective area; a generation module, used to generate a second training sample for training the photoresist model according to the target layout area and the first photoresist label pattern.

[0014] In a third aspect, an embodiment of the present application provides a training sample generating device for training a photoresist model, the device comprising: a processor and a memory storing computer program instructions; when the processor executes the computer program instructions, it implements the training sample generating method for training a photoresist model in the first aspect or any one of the embodiments of the first aspect.

[0015] In a fourth aspect, a computer-readable storage medium stores computer program instructions, which, when executed by a processor, implement the training sample generation method for training a photoresist model in the first aspect or any one of the embodiments of the first aspect.

[0016] In a fifth aspect, an embodiment of the present application provides a computer program product. When the instructions in the computer program product are executed by a processor of an electronic device, the electronic device executes a training sample generation method for training a photoresist model as described in the first aspect or any one of the embodiments of the first aspect.

[0017] The training sample generation method, device and apparatus for training the photoresist model of the embodiment of the present application inputs the acquired first training sample into the photoresist model, thereby determining the area in the first training sample where the photoresist model has a poor training effect, that is, the defective area, and determining the target layout area corresponding to the defective area. Furthermore, a second training sample for training the photoresist model is generated through the target layout area and the first photoresist label pattern in the first training sample, thereby increasing the training samples of the photoresist model and improving the accuracy of the model. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the technical solution of the embodiments of the present application, the following is a brief introduction to the drawings required for use in the embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0019] Figure 1 A schematic flow chart of a method for generating training samples for training a photoresist model provided by an embodiment of the present application is shown;

[0020] Figure 2 A schematic flow chart of a method for generating training samples for training a photoresist model provided in another embodiment of the present application is shown;

[0021] Figure 3 A schematic diagram of a C2C detector provided by an embodiment of the present application is shown;

[0022] Figure 4 A schematic flow chart of a method for generating training samples for training a photoresist model provided by another embodiment of the present application is shown;

[0023] Figure 5 A schematic diagram of a process of a photoresist patterning method of a second mask pattern provided by an embodiment of the present application is shown;

[0024] Figure 6A schematic flow chart of a method for generating training samples for training a photoresist model provided in yet another embodiment of the present application is shown;

[0025] Figure 7 is a structural schematic diagram of a training sample generating device for training a photoresist model provided by another embodiment of the present application;

[0026] Figure 8 It is a structural schematic diagram of a training sample generating device for training a photoresist model provided by yet another embodiment of the present application. DETAILED DESCRIPTION

[0027] The features and exemplary embodiments of various aspects of the present application will be described in detail below. In order to make the purpose, technical solutions and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described herein are only intended to explain the present application, rather than to limit the present application. For those skilled in the art, the present application can be implemented without the need for some of these specific details. The following description of the embodiments is only to provide a better understanding of the present application by illustrating the examples of the present application.

[0028] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the statement "include..." do not exclude the presence of other identical elements in the process, method, article or device including the elements.

[0029] In the field of semiconductor manufacturing technology, the manufacturability of a design layout can be determined more efficiently and with higher quality by determining the photoresist pattern corresponding to the mask layout.

[0030] In the related art, the photoresist pattern can be determined by the Optical Proximity Correction (OPC) model. However, as the chip moves towards a smaller process, the physical and chemical effects in the photolithography process become more complex and difficult to predict, so the process of determining the photoresist pattern by the OPC model is more cumbersome and takes longer. It is understandable that the photoresist pattern is the pattern formed on the wafer surface after the photoresist is subjected to the relevant photolithography process (for example, exposure, development and other processes). In addition, the photoresist pattern can usually accurately replicate the design pattern on the mask.

[0031] In addition, in the related technology, the process from mask layout to photoresist pattern can also be simulated through deep learning models. However, due to the high cost and long cycle of the exposure process in chip manufacturing, there is less training data for deep learning models, which leads to unsatisfactory training results of deep learning models. Therefore, how to increase the training samples of deep learning models is a technical problem that needs to be solved urgently by relevant technicians.

[0032] In order to solve the problems of the prior art, the embodiments of the present application provide a method, device, and apparatus for generating training samples for training a photoresist model. The following first introduces the method for generating training samples for training a photoresist model provided by the embodiments of the present application.

[0033] Figure 1 FIG. 1 is a flow chart of a method for generating training samples for training a photoresist model provided by an embodiment of the present application. Figure 1 As shown, the training sample generation method for training the photoresist model in the embodiment of the present application includes the following steps:

[0034] S110 , obtaining a first training sample, where the first training sample includes a first mask pattern and a first photoresist label pattern corresponding thereto.

[0035] The first mask pattern is a pattern obtained by sampling the first mask layout, and the first photoresist label pattern is a photoresist pattern obtained by correcting the first mask layout using an optical proximity effect correction model.

[0036] In an embodiment of the present application, the first mask pattern may be a pattern obtained by sampling the first mask layout. In one example, the first mask pattern may be obtained by randomly sampling the first mask layout. In another example, feature matching may be performed to determine the first mask pattern in the first mask layout. The first mask pattern obtained by feature matching may be a pattern that a technician pre-sets and needs to focus on, or may be some empirical patterns.

[0037] In an embodiment of the present application, the first photoresist label pattern corresponding to the first mask pattern can be a photoresist pattern obtained by correcting the first mask layout through an optical proximity correction (Optical Proximity Correction, OPC) model. It is understandable that due to the high cost and long cycle of the exposure process in chip manufacturing, obtaining the actual photoresist pattern corresponding to the first mask pattern will cause high costs and take a long time, which does not meet the needs of the chip manufacturing industry for efficient production and cost control. In addition, the OPC model can well simulate the process from the mask layout to the generation of the photoresist pattern, and the photoresist pattern obtained by the OPC model is also closer to the pattern in the design layout. Therefore, the photoresist pattern obtained by correcting the first mask layout with the OPC model can be used as the photoresist label pattern corresponding to the first mask layout.

[0038] S120, inputting the first training sample into the photoresist model to obtain a defective area in the first mask pattern.

[0039] The defective region is a region where the difference between the photoresist pattern predicted by the photoresist model and the first photoresist label pattern is greater than a preset difference threshold. The photoresist model may be a pre-trained photoresist model.

[0040] In an embodiment of the present application, the first training sample can be input into the photoresist training model, so that the photoresist model simulates the first training sample, thereby determining the defective area. It can be understood that the defective area can be an area where the photoresist model has a poor training effect on the first sample. That is, the defective area can be an area where the difference between the photoresist pattern predicted by the photoresist model and the first photoresist label pattern is greater than a preset difference threshold.

[0041] S130. According to the defective area, determine a target layout area corresponding to the defective area in the first mask layout.

[0042] In the embodiment of the present application, the area corresponding to the defective area in the first mask image can be used as the target layout area.

[0043] S140: Generate a second training sample for training a photoresist model according to the target layout area and the first photoresist label pattern.

[0044] In the embodiment of the present application, a second training sample can be generated according to the target layout area and the first photoresist label pattern corresponding to the target layout area, wherein the second training sample can be used to train the photoresist model.

[0045] In one example, a target mask pattern can be obtained in the target layout area by sampling the target layout area.

[0046] In the embodiment of the present application, a first training sample including a first mask pattern and a first photoresist label pattern corresponding thereto is obtained, and the first training sample is input into a photoresist model, thereby determining a defective region in the first mask pattern. Further, based on the determined defective region, a target layout region corresponding to the defective region can be determined in the first mask layout; and a second training sample for training the photoresist model can be generated using the target layout region and the first photoresist label pattern.

[0047] In the embodiment of the present application, the first training sample obtained is input into the photoresist model, thereby determining the area in the first training sample where the photoresist model has a poor training effect, that is, the defective area, and determining the target layout area corresponding to the defective area. Furthermore, a second training sample for training the photoresist model is generated through the target layout area and the first photoresist label pattern in the first training sample, thereby increasing the training samples of the photoresist model and improving the accuracy of the model.

[0048] In order to determine the defective area, as another implementation of the present application, the present application also provides another implementation of a training sample generation method for training a photoresist model, see the following embodiments for details.

[0049] Figure 2 FIG. 2 is a flow chart of a method for generating training samples for training a photoresist model provided by another embodiment of the present application. Figure 2 As shown, the training sample generation method for training the photoresist model in the embodiment of the present application includes the following steps:

[0050] S210: Acquire a first training sample, where the first training sample includes a first mask pattern and a first photoresist label pattern corresponding thereto.

[0051] Among them, step S210 is consistent with step S110, and steps S250-S260 are consistent with steps S130-S140, which will not be described in detail here.

[0052] S220 , predicting a photoresist pattern of the first mask pattern according to a photoresist model to obtain a first predicted photoresist pattern.

[0053] In the embodiment of the present application, the first mask pattern can be input into the photoresist model, and the first mask pattern can be predicted by the photoresist model to determine the first predicted photoresist pattern. It can be understood that the first predicted photoresist pattern can be predicted by the photoresist model, and the pattern that the photoresist can leave on the wafer surface after passing through the first mask pattern and related photolithography processes.

[0054] S230: Determine deviation information between the first predicted photoresist pattern and the first photoresist label pattern.

[0055] In the embodiment of the present application, the deviation information between the first predicted photoresist pattern and the first photoresist label pattern is determined by matching the first predicted photoresist pattern with the first photoresist label pattern.

[0056] In some optional embodiments, a first coordinate value of a first feature point of a first predicted photoresist pattern and a second coordinate value of a second feature point on a first photoresist label pattern corresponding to the first feature point can be obtained; the distance value between the first coordinate value and the first coordinate is calculated, and the distance value is used as deviation information.

[0057] Exemplarily, the first feature point and the second feature point may be the same position on the first predicted photoresist pattern and the first photoresist label pattern, respectively. Further, the difference between the coordinate values ​​corresponding to the same position on the first predicted photoresist pattern and the first photoresist label pattern is determined, and the difference in the coordinate values ​​is used as deviation information.

[0058] In one example, the deviation information may be calculated by a detector for comparing contours, for example, the deviation information may be calculated by a C2C (contour to contour) detector. Figure 3 FIG. 1 shows a schematic diagram of a C2C detector provided by an embodiment of the present application. Figure 3 As shown, contour 10 can be a first predicted photoresist pattern, contour 20 can be a first photoresist label pattern, and feature point 1, feature point 2 and feature point 3 can be set, and corresponding deviation information, that is, the distance between contour 10 and contour 20, can be calculated respectively.

[0059] In another example, the calculation of the deviation information can be implemented by an edge placement error (EPE) detector. It can be understood that the above method of calculating the deviation information is used for exemplary description, and can also be implemented by line end / space end (END) detection and critical dimension variation (CDV) detection, which is not limited in the embodiments of the present application.

[0060] S240: When it is determined that the deviation information is greater than a preset deviation threshold, determine a defective area according to the deviation information.

[0061] In the embodiment of the present application, when it is determined that the deviation information is greater than the preset deviation threshold, the defect area can be determined according to the deviation information. The preset deviation threshold can be preset by a technician, and the size of the preset deviation threshold can be related to the accuracy of the photoresist model. For example, if the photoresist model needs to be more accurate, the preset deviation threshold can be set to a smaller value; if the photoresist model needs to be more accurate, the preset deviation threshold can be set to a larger value.

[0062] In some optional embodiments, the number of first feature points corresponding to deviation information greater than a preset deviation threshold can be counted; when it is determined that the number of first feature points is greater than the number threshold, the area including the first feature points is determined as a defect area.

[0063] In the embodiment of the present application, the region with more defective positions in the first mask pattern can be regarded as the defective region. The defective position in the first mask pattern can be a position where the deviation information is greater than a preset deviation threshold.

[0064] It can be understood that in the embodiment of the present application, by counting the number of first feature points corresponding to deviation information greater than a preset deviation threshold, and when the number of first feature points is greater than the number threshold, the region including the first feature points is determined as a defective region. That is, in the embodiment of the present application, by taking the region with more defects in the first mask pattern as the defective region, the detection of the region with poor photoresist model training effect is achieved.

[0065] S250 . Determine, according to the defective area, a target layout area corresponding to the defective area in the first mask layout.

[0066] S260: Generate a second training sample for training a photoresist model according to the target layout area and the first photoresist label pattern.

[0067] In an embodiment of the present application, a first training sample including a first mask pattern and a first photoresist label pattern corresponding thereto is obtained, and the first training sample is input into a photoresist model, thereby obtaining a first predicted photoresist pattern, and calculating deviation information between the first predicted photoresist pattern and the first photoresist label pattern. When it is determined that the deviation information is greater than a preset deviation threshold, the defective region in the first mask pattern is determined according to the deviation information. Furthermore, according to the determined defective region, a target layout region corresponding to the defective region can be determined in the first mask layout; and then a second training sample is generated using the target layout region and the first photoresist label pattern.

[0068] In the embodiment of the present application, by taking the area with more defects in the first mask pattern as the defective area, the detection of the area with poor photoresist model training effect is achieved, and the area with poor photoresist model training effect is determined.

[0069] In order to determine the defective area, as another implementation of the present application, the present application also provides another implementation of a training sample generation method for training a photoresist model, see the following embodiments for details.

[0070] Figure 4 FIG. 2 is a flow chart of a method for generating training samples for training a photoresist model provided by another embodiment of the present application. Figure 4 As shown, the training sample generation method for training the photoresist model in the embodiment of the present application includes the following steps:

[0071] S410: Acquire a first training sample, where the first training sample includes a first mask pattern and a first photoresist label pattern corresponding thereto.

[0072] S420: Input the first training sample into the photoresist model to obtain a defective area in the first mask pattern.

[0073] S430. According to the defective area, determine a target layout area corresponding to the defective area in the first mask layout.

[0074] Among them, steps S410-S430 are consistent with steps S110-S130, and will not be described in detail here.

[0075] S440, sampling the target layout area to obtain a second mask pattern.

[0076] In the embodiment of the present application, the second mask pattern may be a pattern obtained by sampling the target layout area, wherein the sampling operation performed on the target layout area may be random sampling.

[0077] Exemplarily, a plurality of second mask patterns may be obtained by sampling the target layout area.

[0078] S450, simulating the second mask pattern through an optical proximity effect correction model to obtain a photoresist pattern of the second mask pattern, and using the photoresist pattern as a second photoresist label pattern of the second mask pattern.

[0079] In the embodiment of the present application, the second mask pattern can be input into the OPC model, and the OPC model is used to predict the photoresist pattern corresponding to the second mask pattern, so as to obtain the photoresist pattern corresponding to the second mask pattern. It can be understood that the photoresist model predicted by the OPC model has a high consistency with the pattern in the design layout. Therefore, the photoresist pattern predicted by the OPC model for the photoresist pattern corresponding to the second mask pattern can be used as the second photoresist label pattern.

[0080] Exemplarily, there is a corresponding relationship between the second mask pattern and the second photoresist label pattern.

[0081] S460: Generate a second training sample for training a photoresist model according to the second mask pattern and the corresponding second photoresist label pattern.

[0082] In the embodiment of the present application, the second mask pattern and its corresponding second photoresist label pattern may be used as second training samples to train the photoresist model.

[0083] In the embodiment of the present application, the target layout area can be sampled to obtain a second mask pattern, and the second photoresist label pattern corresponding to the second mask pattern can be determined. It can be understood that the target layout area is an area where the photoresist model training effect is poor. At this time, the second training sample obtained in the target layout area can make up for the problem of poor training effect in the target layout area when the photoresist model is trained according to the second training sample, thereby improving the accuracy of the model.

[0084] In order to obtain the second photoresist label pattern, as another implementation of the present application, the present application also provides another implementation of a training sample generation method for training a photoresist model, please refer to the following embodiments for details.

[0085] Figure 5 FIG. 1 is a schematic diagram showing a process of a photoresist pattern method for a second mask pattern provided by an embodiment of the present application. Figure 5 As shown, the photoresist pattern method of the second mask pattern in the embodiment of the present application includes the following steps:

[0086] S510, acquiring optical information and photoresist parameter information.

[0087] In an embodiment of the present application, the optical information may be optical information in a photolithography process. For example, the optical information may include information related to the light source, including the wavelength and power of the light.

[0088] In the embodiment of the present application, the photoresist parameter information may include relevant parameter information of the photoresist used in the photolithography process. For example, the photoresist parameter information may include parameter information such as sensitivity and viscosity.

[0089] S520: Determine a light intensity distribution image corresponding to the second mask pattern according to the optical information and the photoresist parameter information.

[0090] In the embodiment of the present application, the light intensity distribution image of light passing through the second mask pattern in the photoresist can be simulated through optical information and photoresist parameter information.

[0091] S530, intercepting the light intensity distribution image according to a preset light intensity threshold to obtain a photoresist pattern of a second mask pattern.

[0092] In the embodiment of the present application, the preset light intensity threshold value can be the light intensity value determined during the training process of the OPC model. It is understandable that the preset light intensity threshold value can reflect whether the photoresist will be exposed and chemically react. For example, the light intensity area above the threshold value in the light intensity distribution image can be regarded as the exposure area (that is, it can be the area where the photoresist needs to be removed), and the light intensity area below the threshold value in the light intensity distribution image can be regarded as the unexposed area (that is, the area where the photoresist is retained). In the above manner, the photoresist pattern of the second mask pattern can be intercepted from the light intensity distribution image, that is, the shape of the pattern on the photoresist after photolithography is predicted.

[0093] In the embodiment of the present application, by obtaining optical information and photoresist parameter information, and using the optical information and photoresist parameter information, the light intensity distribution image corresponding to the second mask pattern is determined. The light intensity distribution image is intercepted according to a preset light intensity threshold to obtain the photoresist pattern of the second mask pattern, thereby achieving the acquisition of the photoresist pattern. It can be understood that the photoresist pattern determined by the OPC model has a high degree of matching with the pattern in the design layout, and using it as the true value in the photoresist model training process can ensure the accuracy of the photoresist model.

[0094] In order to realize the training of the photoresist model, as another implementation method of the present application, the present application also provides another implementation method of the training sample generation method for training the photoresist model, please refer to the following embodiments for details.

[0095] Figure 6 FIG. 2 is a flow chart of a method for generating training samples for training a photoresist model provided by another embodiment of the present application. Figure 6 As shown, after the first training sample is input into the photoresist model, the training sample generation method for training the photoresist model in the embodiment of the present application further includes the following steps:

[0096] S610: Obtain a training sample set.

[0097] The training sample set includes a plurality of third mask patterns and their corresponding third photoresist label patterns. Furthermore, the third mask pattern is a pattern obtained by sampling the third mask layout, and the third photoresist label pattern is a photoresist pattern obtained by simulating the third mask layout through an optical proximity effect correction model.

[0098] In the embodiment of the present application, the third mask in the training sample set may be different from the first mask. Therefore, the third mask pattern obtained by sampling the third mask may be different from the first mask pattern.

[0099] In an embodiment of the present application, the training sample set can be used to implement the training of the photoresist model to obtain a trained photoresist model.

[0100] S620: predicting a photoresist pattern of the third mask pattern according to a preset photoresist model to obtain a third predicted photoresist pattern.

[0101] In the embodiment of the present application, the third mask pattern can be input into a preset photoresist model, so that the predicted photoresist pattern predicts the photoresist pattern corresponding to the third mask pattern to obtain a third predicted photoresist pattern.

[0102] In the embodiment of the present application, the preset photoresist model can be obtained by relevant technicians by combining some function expressions to simulate the process of light passing through the third mask pattern in the third mask plate to form an image in the photoresist.

[0103] S630: Determine a learning error of a preset photoresist model according to an error between the third predicted photoresist pattern and the third photoresist label pattern.

[0104] In an embodiment of the present application, the learning error of the predicted photoresist model can be determined by the error between the third predicted photoresist pattern and the third photoresist label pattern. In one example, the error between the third predicted photoresist pattern and the third photoresist label pattern can be calculated using a C2C detector. In another example, the error calculation between the third predicted photoresist pattern and the third photoresist label pattern can also be achieved by an EPE detector. It is understandable that the error between the third predicted photoresist pattern and the third photoresist label pattern can also be calculated by other means, which is not limited in the embodiments of the present application.

[0105] S640, determine whether the learning error is greater than a preset error threshold, if so, execute step S650; if not, end the training and obtain a trained photoresist model.

[0106] S650, adjusting parameters in the preset photoresist pattern acquisition model.

[0107] In the embodiment of the present application, the subsequent operation is determined by judging whether the calculated learning error is greater than the preset error threshold. Wherein, in the case where it is determined that the learning error is greater than the preset error threshold, it can be determined that the photoresist model does not meet the requirements. At this time, the parameters in the preset photoresist model can be adjusted, and the third photoresist pattern can be re-input into the photoresist model after the parameter adjustment, and the third predicted photoresist pattern can be re-predicted, and the difference between the re-predicted third predicted photoresist pattern and the third photoresist label pattern can be calculated to recalculate the learning error. Further, the relationship between the recalculated learning error and the preset error threshold is determined. If the recalculated learning error is still greater than the preset error threshold, the photoresist model parameters are continued to be adjusted until the learning error is less than or equal to the preset error threshold, and the model training is determined to be completed, and a trained photoresist model is obtained.

[0108] Among them, when it is determined that the learning error is less than or equal to a preset error threshold, the photoresist model can be determined and the model training is completed. At this time, the training can be ended to obtain a trained photoresist model.

[0109] In the embodiment of the present application, a third predicted photoresist pattern is obtained by inputting the third mask pattern in the training sample into a preset photoresist model. Further, the third predicted photoresist pattern and the third photoresist label pattern are used to determine the deviation and calculate the learning error. And by the learning error, it is determined whether the photoresist model is completed. It can be understood that the photoresist model trained by the above process has a high accuracy for its training sample, and inputting a mask pattern similar to the third mask pattern in the training sample into the trained model can quickly and accurately predict the photoresist pattern.

[0110] In some optional embodiments, the trained photoresist model can be updated using the training sample set and the second training sample. It is understandable that the second training sample is a training sample obtained from an area where the model training effect is not good. Therefore, retraining the trained photoresist model using the training sample set and the second training sample can make up for the defects of the photoresist model in the initial training process, thereby improving the accuracy of the model for predicting photoresist patterns.

[0111] Based on the training sample generation method for training a photoresist model provided in the above embodiment, accordingly, the present application also provides a specific implementation of a training sample generation device for training a photoresist model. Please refer to the following embodiment.

[0112] See first Figure 7 The training sample generating device 700 for training the photoresist model provided in the embodiment of the present application includes the following units:

[0113] A first acquisition module 701 is used to acquire a first training sample, wherein the first training sample includes a first mask pattern and a first photoresist label pattern corresponding thereto, wherein the first mask pattern is a pattern obtained by sampling the first mask layout, and the first photoresist label pattern is a photoresist pattern obtained by correcting the first mask layout using an optical proximity effect correction model;

[0114] The second acquisition module 702 is used to input the first training sample into the photoresist model to obtain a defective area in the first mask pattern, where the defective area is an area where the difference between the photoresist pattern predicted by the photoresist model and the first photoresist label pattern is greater than a preset difference threshold;

[0115] A determination module 703 is used to determine a target layout area corresponding to the defective area in the first mask layout according to the defective area;

[0116] The generating module 704 is used to generate a second training sample for training the photoresist model according to the target layout area and the first photoresist label pattern.

[0117] As an implementation method of the present application, the second acquisition module 702 inputs the first training sample into the photoresist model to obtain a defective area in the first mask pattern by: predicting the photoresist pattern of the first mask pattern according to the photoresist model to obtain a first predicted photoresist pattern; determining deviation information between the first predicted photoresist pattern and the first photoresist label pattern; and determining the defective area according to the deviation information when it is determined that the deviation information is greater than a preset deviation threshold.

[0118] As an implementation method of the present application, the second acquisition module 702 determines the deviation information between the predicted photoresist pattern and the photoresist label pattern in the following manner: obtain the first coordinate value of the first feature point of the first predicted photoresist pattern and the second coordinate value of the second feature point on the first photoresist label pattern corresponding to the first feature point; calculate the distance between the first coordinate value and the first coordinate, and use the distance value as the deviation information.

[0119] As an implementation method of the present application, the determination module 703 determines the defect area based on the deviation information in the following manner: the number of first feature points corresponding to the statistical deviation information being greater than a preset deviation threshold; when it is determined that the number of first feature points is greater than the number threshold, the area including the first feature points is determined as a defect area.

[0120] As an implementation method of the present application, the generation module 704 generates a second training sample for training a photoresist model according to a target layout area and a first photoresist label pattern in the following manner: sampling the target layout area to obtain a second mask pattern; simulating the second mask pattern through an optical proximity effect correction model to obtain a photoresist pattern of the second mask pattern, and using it as a second photoresist label pattern of the second mask pattern; and generating a second training sample for training a photoresist model according to the second mask pattern and the corresponding second photoresist label pattern.

[0121] As an implementation method of the present application, the generation module 704 simulates the second mask pattern through the optical proximity effect correction model to obtain the photoresist pattern of the second mask pattern in the following manner: obtain optical information and photoresist parameter information; determine the light intensity distribution image corresponding to the second mask pattern through the optical information and photoresist parameter information; intercept the light intensity distribution image according to a preset light intensity threshold to obtain the photoresist pattern of the second mask pattern.

[0122] As an implementation of the present application, the device also includes a training module 705. Before inputting the first training sample into the photoresist model, the training module 705 is used to: obtain a training sample set, the training sample set includes a plurality of third mask patterns and their corresponding third photoresist label patterns, the third mask pattern is a pattern obtained by sampling the third mask layout, and the third photoresist label pattern is a photoresist pattern obtained by simulating the third mask layout through an optical proximity effect correction model; predict the photoresist pattern of the third mask pattern according to the preset photoresist model to obtain a third predicted photoresist pattern;

[0123] According to the error between the third predicted photoresist pattern and the third photoresist label pattern, the learning error of the predicted photoresist model is determined; when it is determined that the learning error is greater than the preset error threshold, the parameters in the preset photoresist pattern acquisition model are adjusted, and the photoresist pattern of the third mask pattern is predicted according to the preset photoresist model to obtain the third predicted photoresist pattern, until the learning error is less than or equal to the preset error threshold, and a trained photoresist model is obtained.

[0124] As an implementation of the present application, after obtaining the trained photoresist model, the training module 705 is further used to: update the trained photoresist model using the training sample set and the second training sample.

[0125] Figure 8 A schematic diagram of the hardware structure of a training sample generation method for training a photoresist model provided in an embodiment of the present application is shown.

[0126] The training sample generation method device for training a photoresist model may include a processor 301 and a memory 302 storing computer program instructions.

[0127] Specifically, the processor 801 may include a central processing unit (CPU), or an application specific integrated circuit (ASIC), or may be configured to implement one or more integrated circuits of the embodiments of the present application.

[0128] The memory 802 may include a large capacity memory for data or instructions. By way of example and not limitation, the memory 802 may include a hard disk drive (HDD), a floppy disk drive, a flash memory, an optical disk, a magneto-optical disk, a magnetic tape, or a universal serial bus (USB) drive or a combination of two or more of these. In appropriate cases, the memory 802 may include a removable or non-removable (or fixed) medium. In appropriate cases, the memory 802 may be inside or outside the integrated gateway disaster recovery device. In a specific embodiment, the memory 802 is a non-volatile solid-state memory.

[0129] The memory may include read-only memory (ROM), random access memory (RAM), magnetic disk storage media devices, optical storage media devices, flash memory devices, electrical, optical or other physical / tangible memory storage devices. Thus, typically, the memory includes one or more tangible (non-transitory) computer-readable storage media (e.g., memory devices) encoded with software including computer-executable instructions, and when the software is executed (e.g., by one or more processors), it is operable to perform the operations described with reference to the method according to an aspect of the present disclosure.

[0130] The processor 801 reads and executes computer program instructions stored in the memory 802 to implement any one of the training sample generation methods for training a photoresist model in the above embodiments.

[0131] In one example, the training sample generation device for training the photoresist model may further include a communication interface 803 and a bus 810. Figure 8 As shown, the processor 801, the memory 802, and the communication interface 803 are connected via a bus 810 and communicate with each other.

[0132] The communication interface 803 is mainly used to implement communication between various modules, devices, units and / or equipment in the embodiments of the present application.

[0133] Bus 810 includes hardware, software or both, and the parts of online data flow billing equipment are coupled to each other. For example, but not limitation, bus may include accelerated graphics port (AGP) or other graphics bus, enhanced industrial standard architecture (EISA) bus, front-end bus (FSB), hypertransport (HT) interconnection, industrial standard architecture (ISA) bus, infinite bandwidth interconnection, low pin count (LPC) bus, memory bus, micro channel architecture (MCA) bus, peripheral component interconnection (PCI) bus, PCI-Express (PCI-X) bus, serial advanced technology attachment (SATA) bus, video electronics standard association local (VLB) bus or other suitable bus or two or more of these combinations. In appropriate cases, bus 810 may include one or more buses. Although the present application embodiment describes and shows a specific bus, the application considers any suitable bus or interconnection.

[0134] The training sample generation device for training the photoresist model can execute the training sample generation method for training the photoresist model in the embodiment of the present application with the first training sample, thereby realizing the combination Figure 1 and Figure 7 A method and apparatus for generating training samples for training a photoresist model are described.

[0135] In addition, in combination with the training sample generation method for training the photoresist model in the above embodiment, the embodiment of the present application can provide a computer storage medium for implementation. The computer storage medium stores computer program instructions; when the computer program instructions are executed by the processor, any one of the training sample generation methods for training the photoresist model in the above embodiment is implemented.

[0136] The present embodiment also provides a computer program product, including a computer program, which, when executed, implements any one of the methods for generating training samples for training a photoresist model in the above embodiments.

[0137] It should be clear that the present application is not limited to the specific configuration and processing described above and shown in the figures. For the sake of simplicity, a detailed description of the known method is omitted here. In the above embodiments, several specific steps are described and shown as examples. However, the method process of the present application is not limited to the specific steps described and shown, and those skilled in the art can make various changes, modifications and additions, or change the order between the steps after understanding the spirit of the present application.

[0138] The functional blocks shown in the above-described block diagram can be implemented as hardware, software, firmware or a combination thereof. When implemented in hardware, it can be, for example, an electronic circuit, an application specific integrated circuit (ASIC), appropriate firmware, a plug-in, a function card, etc. When implemented in software, the elements of the present application are programs or code segments that are used to perform the required tasks. The program or code segment can be stored in a machine-readable medium, or transmitted on a transmission medium or a communication link by a data signal carried in a carrier wave. "Machine-readable medium" can include any medium capable of storing or transmitting information. Examples of machine-readable media include electronic circuits, semiconductor memory devices, ROM, flash memory, erasable ROM (EROM), floppy disks, CD-ROMs, optical disks, hard disks, optical fiber media, radio frequency (RF) links, etc. The code segment can be downloaded via a computer network such as the Internet, an intranet, etc.

[0139] It should also be noted that the exemplary embodiments mentioned in this application describe some methods or systems based on a series of steps or devices. However, this application is not limited to the order of the above steps, that is, the steps can be performed in the order mentioned in the embodiment, or in a different order from the embodiment, or several steps can be performed simultaneously.

[0140] Aspects of the present disclosure are described above with reference to the flowchart and / or block diagram of the method, device (system) and computer program product according to the embodiment of the present disclosure. It should be understood that each box in the flowchart and / or block diagram and the combination of each box in the flowchart and / or block diagram can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device to produce a machine so that these instructions executed by the processor of the computer or other programmable data processing device enable the implementation of the function / action specified in one or more boxes of the flowchart and / or block diagram. Such a processor can be, but is not limited to, a general-purpose processor, a special-purpose processor, a special application processor, or a field programmable logic circuit. It can also be understood that each box in the block diagram and / or flowchart and the combination of boxes in the block diagram and / or flowchart can also be implemented by dedicated hardware that performs a specified function or action, or can be implemented by a combination of dedicated hardware and computer instructions.

[0141] The above is only a specific implementation of the present application. Those skilled in the art can clearly understand that for the convenience and simplicity of description, the specific working processes of the systems, modules and units described above can refer to the corresponding processes in the aforementioned method embodiments, and will not be repeated here. It should be understood that the protection scope of the present application is not limited to this. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed in this application, and these modifications or replacements should be included in the protection scope of this application.

Claims

1. A method for generating training samples for training a photoresist model, characterized in that: include: Acquire a first training sample, wherein the first training sample includes a first mask pattern and a first photoresist label pattern corresponding thereto, wherein the first mask pattern is a pattern obtained by sampling a first mask layout, and the first photoresist label pattern is a photoresist pattern obtained by correcting the first mask layout by using an optical proximity effect correction model; Inputting the first training sample into a photoresist model to obtain a defective area in a first mask pattern, wherein the defective area is an area where a difference between a photoresist pattern predicted by the photoresist model and the first photoresist label pattern is greater than a preset difference threshold; According to the defective area, determining a target layout area corresponding to the defective area in the first mask layout; A second training sample for training a photoresist model is generated according to the target layout area and the first photoresist label pattern.

2. The method according to claim 1, characterized in that The step of inputting the first training sample into a photoresist model to obtain a defective area in a first mask pattern includes: Predicting the photoresist pattern of the first mask pattern according to the photoresist model to obtain a first predicted photoresist pattern; Determining deviation information between the first predicted photoresist pattern and the first photoresist label pattern; When it is determined that the deviation information is greater than a preset deviation threshold, a defective area is determined according to the deviation information.

3. The method according to claim 2, characterized in that The determining of deviation information between the predicted photoresist pattern and the photoresist label pattern includes: Acquire a first coordinate value of a first feature point of the first predicted photoresist pattern and a second coordinate value of a second feature point on the first photoresist label pattern corresponding to the first feature point; A distance value between the first coordinate value and the first coordinate is calculated, and the distance value is used as the deviation information.

4. The method according to claim 2 or 3, characterized in that: The step of determining the defect area according to the deviation information includes: Counting the number of first feature points corresponding to which the deviation information is greater than a preset deviation threshold; In a case where it is determined that the number of the first feature points is greater than a number threshold, a region including the first feature points is determined as the defect region.

5. The method according to claim 1, characterized in that The step of generating a second training sample for training a photoresist model according to the target layout area and the first photoresist label pattern comprises: Sampling the target layout area to obtain a second mask pattern; Simulating the second mask pattern through an optical proximity effect correction model to obtain a photoresist pattern of the second mask pattern, and using the photoresist pattern as a second photoresist label pattern of the second mask pattern; A second training sample for training the photoresist model is generated according to the second mask pattern and the corresponding second photoresist label pattern.

6. The method according to claim 5, characterized in that The step of simulating the second mask pattern by using an optical proximity effect correction model to obtain a photoresist pattern of the second mask pattern includes: Obtain optical information and photoresist parameter information; Determining a light intensity distribution image corresponding to the second mask pattern according to the optical information and the photoresist parameter information; The light intensity distribution image is intercepted according to a preset light intensity threshold to obtain a photoresist pattern of the second mask pattern.

7. The method according to claim 1, characterized in that Before inputting the first training sample into the photoresist model, the method further includes: Acquire a training sample set, the training sample set comprising a plurality of third mask patterns and corresponding third photoresist label patterns, the third mask pattern being a pattern obtained by sampling a third mask layout, and the third photoresist label pattern being a photoresist pattern obtained by simulating the third mask layout through an optical proximity effect correction model; Predicting the photoresist pattern of the third mask pattern according to a preset photoresist model to obtain a third predicted photoresist pattern; Determining a learning error of the preset photoresist model according to an error between the third predicted photoresist pattern and the third photoresist label pattern; When it is determined that the learning error is greater than the preset error threshold, the parameters in the preset photoresist model are adjusted, and the photoresist pattern of the third mask pattern is predicted based on the preset photoresist model to obtain a third predicted photoresist pattern, until the learning error is less than or equal to the preset error threshold, and a trained photoresist model is obtained.

8. The method according to claim 7, characterized in that After obtaining the trained photoresist model, the method further includes: The trained photoresist model is updated using the training sample set and the second training sample.

9. A training sample generating device for training a photoresist model, characterized in that: The device comprises: A first acquisition module is used to acquire a first training sample, wherein the first training sample includes a first mask pattern and a first photoresist label pattern corresponding thereto, wherein the first mask pattern is a pattern obtained by sampling a first mask layout, and the first photoresist label pattern is a photoresist pattern obtained by correcting the first mask layout by using an optical proximity effect correction model; A second acquisition module is used to input the first training sample into a photoresist model to obtain a defect area in a first mask pattern, wherein the defect area is an area where the difference between the photoresist pattern predicted by the photoresist model and the first photoresist label pattern is greater than a preset difference threshold; A determination module, configured to determine, according to the defective area, a target layout area corresponding to the defective area in the first mask layout; A generating module is used to generate a second training sample for training a photoresist model according to the target layout area and the first photoresist label pattern.

10. A training sample generating device for training a photoresist model, characterized in that: The device comprises: a processor and a memory storing computer program instructions; When the processor executes the computer program instructions, it implements the training sample generation method for training the photoresist model as described in any one of claims 1-8.

11. 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 training sample generation method for training a photoresist model as described in any one of claims 1 to 8 is implemented.

12. A computer program product, characterized in that When the instructions in the computer program product are executed by a processor of an electronic device, the electronic device executes the training sample generation method for training a photoresist model as described in any one of claims 1 to 8.

Images