Mask image generation method, device, electronic device and storage medium

Abstract

The present application discloses a mask image generation method, device, electronic device and storage medium, which belong to the field of lithography. The mask image generation method for a lithography machine includes: obtaining multiple target process parameters; inputting the multiple target process parameters into the multi-layer perception layer of the target network model, and obtaining the target reconstructed image output by the multi-layer perception layer; inputting the target reconstructed image, the target desired mask image and the target illumination image into the generative adversarial network layer of the target network model, and obtaining the target mask image output by the generative adversarial network layer. The mask image generation method for a lithography machine of the present application can be applied to different lithography machines and lithography environments, and can be adaptively adjusted to obtain a more accurate mask image, thereby improving the resolution of the lithography system, and has high flexibility and universality.

Description

Technical Field

[0001] The present application relates to the field of photolithography, and in particular to a mask image generation method, device, electronic device and storage medium. Background Art

[0002] Photolithography is a core step in the chip manufacturing process. As the resolution of photolithography systems continues to increase, the diffraction and interference effects of light become increasingly pronounced, causing the lithographic patterns on the wafer to become distorted and blurred. Related technologies primarily use photolithography simulation methods to improve resolution, such as the model-based optical proximity correction (MB-OPC) method. This method uses an algorithm designed based on physical, chemical, and optical principles and performs multiple iterative calculations to improve the resolution of the photolithography system. However, this method is inefficient, difficult to implement, and difficult to apply to complex and changing photolithography scenarios. Summary of the Invention

[0003] This application aims to solve at least one of the technical problems existing in the prior art. To this end, this application proposes a mask image generation method, device, electronic device, and storage medium that can obtain more accurate mask images, improve the resolution of lithography systems, and have high flexibility and universality.

[0004] In a first aspect, the present application provides a mask image generation method for a lithography machine, the method comprising:

[0005] Obtain multiple target process parameters;

[0006] Inputting the plurality of target process parameters into a multi-layer perception layer of a target network model, and obtaining a target reconstructed image output by the multi-layer perception layer;

[0007] The target reconstructed image, the target desired mask image and the target illumination image are input into the generative adversarial network layer of the target network model to obtain the target mask image output by the generative adversarial network layer; wherein,

[0008] The target mask image is used for exposure by the lithography machine, and the output end of the multi-layer perception layer is connected to the input end of the generative adversarial network layer; the target network model is obtained based on training of multiple training samples.

[0009] According to the mask image generation method for a lithography machine of the present application, the target mask image is predicted by the target process parameters, the target expected mask image and the target illumination image, so that the target mask image can be adaptively adjusted based on different process parameters and different illumination images, thereby generating a target mask image that can obtain the target expected mask image in any lithography environment without the need for multiple iterations, and having high computational efficiency; and can be applied to different lithography machines and lithography environments, and can be adaptively adjusted to obtain a more accurate mask image, thereby improving the resolution of the lithography system, and having high flexibility and universality.

[0010] According to one embodiment of the present application, inputting the plurality of target process parameters into a multi-layer perception layer of a target network model and obtaining a target reconstructed image output by the multi-layer perception layer includes:

[0011] Inputting the plurality of target process parameters into a multi-layer perception layer of a target network model, allowing the multi-layer perception layer to learn an influence weight of each target process parameter, and mapping each target process parameter into a target feature vector, wherein the target feature vector is used to characterize an association relationship between each target process parameter;

[0012] The target feature vector is reconstructed into a single-channel image to obtain the target reconstructed image.

[0013] According to one embodiment of the present application, obtaining multiple target process parameters includes:

[0014] The multiple target process parameters are acquired according to the type of the lithography machine and the target lithography environment.

[0015] According to one embodiment of the present application, the plurality of target process parameters include: exposure dose and photoresist parameters.

[0016] According to one embodiment of the present application, the training samples are obtained based on the following steps:

[0017] Obtaining multiple sample process parameters corresponding to a sample lithography machine;

[0018] Acquire a lithography result image obtained by the sample lithography machine processing the sample mask image under the multiple sample process parameters and the sample illumination image;

[0019] The training samples are constructed by taking the multiple sample process parameters, the sample illumination image and the photolithography result image as samples and taking the sample mask image as a sample label.

[0020] According to one embodiment of the present application, the target network model is trained based on multiple training samples, including:

[0021] Input multiple sample process parameters in the training samples into the multi-layer perception layer; input the lithography result image, sample illumination image and sample mask image in the training samples into the generative adversarial network layer, and train the target network model with the sample reconstructed image output by the multi-layer perception layer and the predicted mask image output by the generative adversarial network layer as the target.

[0022] According to one embodiment of the present application, before obtaining the plurality of target process parameters, the method further includes:

[0023] Receiving a first input from a user on at least some of the multiple candidate configuration modules in the OpenMMLab configuration interface;

[0024] In response to the first input, the target network model is constructed based on the at least part of the modules.

[0025] In a second aspect, the present application provides a mask image generating device for a lithography machine, the device comprising:

[0026] A first processing module is used to obtain a plurality of target process parameters;

[0027] A second processing module is configured to input the plurality of target process parameters into a multi-layer perception layer of a target network model, and obtain a target reconstructed image output by the multi-layer perception layer;

[0028] The third processing module is configured to input the target reconstructed image, the target desired mask image, and the target illumination image into the generative adversarial network layer of the target network model, and obtain the target mask image output by the generative adversarial network layer; wherein,

[0029] The target mask image is used for image correction by the lithography machine, and the output end of the multi-layer perception layer is connected to the input end of the generative adversarial network layer; the target network model is obtained based on training of multiple training samples.

[0030] According to the mask image generation device for a lithography machine of the present application, the target mask image is predicted by the target process parameters, the target expected mask image and the target illumination image, so that the target mask image can be adaptively adjusted based on different process parameters and different illumination images, thereby generating a target mask image that can obtain the target expected mask image in any lithography environment without the need for multiple iterations, and having high computational efficiency; and can be applied to different lithography machines and lithography environments, and can be adaptively adjusted to obtain a more accurate mask image, thereby improving the resolution of the lithography system, and having high flexibility and universality.

[0031] In a third aspect, the present application provides an electronic device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein when the processor executes the computer program, the mask image generation method for a lithography machine as described in the first aspect above is implemented.

[0032] In a fourth aspect, the present application provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the mask image generation method for a lithography machine as described in the first aspect above.

[0033] In a fifth aspect, the present application provides a computer program product, comprising a computer program, which, when executed by a processor, implements the mask image generation method for a lithography machine as described in the first aspect above.

[0034] The above one or more technical solutions in the embodiments of the present application have at least one of the following technical effects:

[0035] By predicting the target mask image through the target process parameters, the target expected mask image and the target illumination image, the target mask image can be adaptively adjusted based on different process parameters and different illumination images, so that a target mask image that can obtain the target expected mask image can be generated in any lithography environment without the need for multiple iterations, and with high computational efficiency; and it can be applied to different lithography machines and lithography environments, and can be adaptively adjusted to obtain a more accurate mask image, thereby improving the resolution of the lithography system, and has high flexibility and universality.

[0036] Furthermore, by learning the correlation between each target process parameter and the importance score of the lithography result through multi-layer perception layers, a target reconstructed image is generated as one of the features to predict the target mask image. This can improve the accuracy and effect of the predicted target mask image, and can predict a matching mask image based on different process parameters, with high flexibility and a wide range of applicable scenarios.

[0037] Furthermore, by adopting the OpenMMLab framework for training, you only need to select the required modules, combine and adjust different modules to meet specific needs, and complete the model training by writing a configuration file and running it, reducing repetitive actions, improving model building efficiency, and lowering the usage threshold; in addition, you can also customize the deep learning network module to receive multiple process parameters and lighting patterns, and jointly optimize them with the target desired mask image, further improving the flexibility and efficiency of model construction.

[0038] Additional aspects and advantages of the present application will be given in part in the description below, and in part will become obvious from the description below, or will be learned through practice of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] The above and / or additional aspects and advantages of the present application will become apparent and easily understood from the description of the embodiments in conjunction with the following drawings, in which:

[0040] Figure 1 This is one of the flow diagrams of the mask image generation method for a lithography machine provided in an embodiment of the present application;

[0041] Figure 2 This is the second flow chart of the mask image generation method for a lithography machine provided in an embodiment of the present application;

[0042] Figure 3 Schematic diagram of the principle of a mask image generation method for a lithography machine provided in an embodiment of the present application;

[0043] Figure 4 This is the third flow chart of the mask image generation method for a lithography machine provided in an embodiment of the present application;

[0044] Figure 5 1 is a schematic structural diagram of a mask image generating device for a lithography machine provided in an embodiment of the present application;

[0045] Figure 6 It is a structural diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0046] The following will be combined with the accompanying drawings in the embodiments of the present application to clearly describe the technical solutions in the embodiments of the present application. Obviously, the embodiments described are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field are within the scope of protection of this application.

[0047] The terms "first," "second," and the like in the specification and claims of this application are used to distinguish similar objects, and are not used to describe a specific order or precedence. It should be understood that the terms used in this manner are interchangeable where appropriate, so that the embodiments of this application can be implemented in an order other than that illustrated or described herein, and that the objects distinguished by "first," "second," and the like are generally of the same type, and do not limit the number of objects; for example, the first object can be one or more. In addition, the term "and / or" in the specification and claims refers to at least one of the connected objects, and the character " / " generally indicates that the objects connected are in an "or" relationship.

[0048] Below, in combination with the accompanying drawings, the mask image generation method for a lithography machine, the mask image generation device for a lithography machine, the electronic device and the readable storage medium provided in the embodiments of the present application are described in detail through specific embodiments and their application scenarios.

[0049] Among them, the mask image generation method for a lithography machine can be applied to a terminal, and can be specifically executed by hardware or software in the terminal.

[0050] The terminal includes, but is not limited to, a portable communication device such as a mobile phone or tablet computer having a touch-sensitive surface (e.g., a touch screen display and / or a touch pad). It should also be understood that in some embodiments, the terminal may not be a portable communication device, but rather a desktop computer having a touch-sensitive surface (e.g., a touch screen display and / or a touch pad).

[0051] In the following embodiments, a terminal including a display and a touch-sensitive surface is described. However, it should be understood that the terminal may include one or more other physical user interface devices such as a physical keyboard, a mouse, and a joystick.

[0052] The mask image generation method for a lithography machine provided in an embodiment of the present application may be executed by an electronic device or a functional module or functional entity in the electronic device that can implement the mask image generation method for a lithography machine. The electronic devices mentioned in the embodiment of the present application include but are not limited to mobile phones, tablet computers, computers, cameras, and wearable devices. The mask image generation method for a lithography machine provided in an embodiment of the present application is described below using an electronic device as an example of the execution subject.

[0053] like Figure 1 As shown, the mask image generation method for a lithography machine includes: step 110, step 120 and step 130.

[0054] It should be noted that the mask image generation method for a lithography machine is applied in the field of lithography applications.

[0055] Step 110: Acquire multiple target process parameters;

[0056] In this step, the process parameters are the process parameters involved in the lithography process of the lithography machine, including but not limited to: exposure system parameters, resolution-related parameters, photoresist (photoresist) parameters, process control parameters, mask (mask) parameters and other key parameters.

[0057] The exposure system parameters may include: light source wavelength (Wavelength), numerical aperture (NA, Numerical Aperture), exposure dose (Exposure Dose), and lighting mode.

[0058] Photoresist parameters may include: photoresist type, sensitivity, and contrast, etc.

[0059] Process control parameters may include: focus depth, scanning speed, and environmental control.

[0060] Mask (reticle) parameters can include: mask magnification, phase shift mask, and optical proximity effect correction.

[0061] It is understandable that different types of lithography machines may involve different process parameters; different lithography environments may also correspond to different process parameters.

[0062] The target process parameters can be customized by the user, such as the user selecting corresponding process parameters as the target process parameters according to actual needs.

[0063] In some embodiments, step 110 may include:

[0064] According to the type of the lithography machine and the target lithography environment, multiple target process parameters are obtained.

[0065] In this embodiment, the target process parameters may be actual parameters in the current lithography scenario, and may be determined according to the type of lithography machine and the lithography environment, such as ambient temperature and humidity, and shock suppression capability.

[0066] In some embodiments, the plurality of target process parameters may include: exposure dose and photoresist parameters.

[0067] Of course, in other embodiments, the target process parameters may also include: exposure dose, light source wavelength, photoresist type, sensitivity, contrast, scanning speed, mask magnification, and ambient temperature and humidity, etc.

[0068] Step 120: Input multiple target process parameters into the multi-layer perception layer of the target network model to obtain a target reconstructed image output by the multi-layer perception layer;

[0069] In this step, the target network model may be a pre-built and trained neural network model, including three external input channels and one external output channel.

[0070] The target network model includes: a multi-layer perception layer and a generative adversarial network layer, wherein the multi-layer perception layer corresponds to one external input channel, the generative adversarial network layer corresponds to two external input channels and one external output channel, and the internal output end of the multi-layer perception layer is connected to the internal input end of the generative adversarial network layer.

[0071] Among them, the Multilayer Perceptron (MLP) layer is a feedforward artificial neural network, which includes multiple neuron layers, such as Figure 4 As shown, each circle corresponds to a neuron, which can learn complex nonlinear mapping relationships.

[0072] The Generative Adversarial Network (GAN) layer is a deep learning model that generates data through adversarial training, and may include but is not limited to image-to-image deep learning networks such as Pix2Pix or CycleGAN.

[0073] The target network model is trained based on multiple training samples. The specific training method will be described in the following embodiments and will not be described here in detail.

[0074] The target reconstructed image is an image that can characterize the nonlinear mapping relationship between the target process parameters, such as a 256×256 image; of course, in other embodiments, images of other sizes can be set based on actual needs, and this application does not limit this.

[0075] In some embodiments, step 120 may include:

[0076] Multiple target process parameters are input into the multi-layer perception layer of the target network model. The multi-layer perception layer learns the influence weight of each target process parameter and maps each target process parameter into a target feature vector. The target feature vector is used to represent the correlation between the target process parameters.

[0077] Reconstruct the target feature vector into a single-channel image to obtain the target reconstructed image.

[0078] In this embodiment, continue to refer to Figure 4 Taking multiple target process parameters including exposure dose, photoresist sensitivity and other parameters as an example, the exposure dose, photoresist sensitivity and other parameters are input into the multi-layer perception layer. By learning the influence weight of each parameter, each parameter is mapped into a target feature vector that can characterize the nonlinear relationship between various parameters, such as a 1×65536 tensor, whose total length is the same as the size of the target desired mask image and the target illumination image; then it is reconstructed into a target reconstructed image, such as a tensor arranged as 1×256×256.

[0079] The target reconstructed image obtained after reconstruction is concatenated with the target desired mask image and the target illumination image into a three-channel image, such as a 1×256×256 tensor, and then input into the generative adversarial network layer for processing to obtain the target mask image.

[0080] According to the mask image generation method for a lithography machine provided in an embodiment of the present application, the correlation between each target process parameter and the importance score of the lithography result are learned through a multi-layer perception layer, and a target reconstructed image is generated as one of the features to predict the target mask image. This can improve the accuracy and effect of the predicted target mask image, and can predict a matching mask image based on different process parameters, with high flexibility and a wide range of applicable scenarios.

[0081] Step 130: Input the target reconstructed image, the target expected mask image, and the target illuminated image into the generative adversarial network layer of the target network model to obtain the target mask image output by the generative adversarial network layer.

[0082] In this step, the target illumination image may be determined based on an illumination mode, including but not limited to: a traditional illumination image, an off-axis illumination (OAI) image, and an annular illumination image, etc., for optimizing image contrast and resolution.

[0083] Figure 2 An example of a photolithography flow chart is provided. In the photolithography process, light sources, optical systems, illumination images, mask images, lenses, photoresist, wafers for placing photoresist, and related process parameters (including but not limited to photoresist parameters, etc.) are involved. The mask image is placed on the mask. Under the process parameters and illumination images, the photolithography system processes the mask image to obtain the photolithography result image. In the physical process of simulating photolithography, a reverse photolithography technology (ILT) is involved, such as Figure 3 As shown, given a desired target mask pattern target, the model is required to output what kind of mask pattern M becomes the target mask pattern target after passing through the lithography system. The target mask pattern target corresponds to the target desired mask image of this application, and the mask pattern M corresponds to the target mask image output by the desired target network model of this application.

[0084] That is, the target expected mask image is the final mask result obtained by the expected lithography machine processing the mask image under target process parameters and target illumination image.

[0085] The target mask image is the desired wafer pattern, which is the image corresponding to the standard that the mask image needs to achieve when the lithography machine processes the mask image under the target process parameters and target illumination image to meet the expected mask results.

[0086] The target mask image is used for further exposure by the photolithography machine.

[0087] In actual application, continue to refer to Figure 4, it is only necessary to input the target process parameters, target expected mask image and target illumination image into the target network model, and the target network model can output the reverse lithography result that meets the requirements, that is, the target mask image.

[0088] The target mask image can be used in subsequent lithography scenarios. Under target process parameters and target illumination images, the lithography machine processes the target mask image to obtain desired lithography results.

[0089] During the research and development process, the inventors discovered that related techniques employ machine learning methods, such as deep learning and neural networks, to train a model to simulate the physical process of photolithography. Specifically, a target mask is input, and the model outputs a reverse photolithography result. However, this method produces roughly the same reverse photolithography result when the target mask is constant. However, processing the same mask image in different photolithography machines or photolithography environments can produce significantly different photolithography results, affecting the resolution of the photolithography system. This method is not applicable to different photolithography machines and photolithography environments, and therefore has certain limitations.

[0090] According to the mask image generation method for a lithography machine provided in an embodiment of the present application, the target mask image is predicted by target process parameters, target expected mask image and target illumination image, so that the target mask image can be adaptively adjusted based on different process parameters and different illumination images, thereby generating a target mask image that can obtain the target expected mask image in any lithography environment without the need for multiple iterations, and having high computational efficiency; and can be applied to different lithography machines and lithography environments, and can be adaptively adjusted to obtain a more accurate mask image, thereby improving the resolution of the lithography system, and having high flexibility and universality.

[0091] The following describes how to obtain training samples, build the target network model, and train the model.

[0092] In some embodiments, training samples may be obtained based on the following steps:

[0093] Obtaining multiple sample process parameters corresponding to a sample lithography machine;

[0094] Acquire a lithography result image obtained by processing a sample mask image with a sample lithography machine under multiple sample process parameters and sample illumination images;

[0095] Training samples are constructed using multiple sample process parameters, sample illumination images and lithography result images as samples and sample mask images as sample labels.

[0096] In this embodiment, a sample lithography machine can correspond to multiple training samples. By setting up multiple different sample lithography machines and using a similar method, multiple training samples can be obtained, thereby obtaining a dataset. The sample lithography machine is the lithography machine used to obtain sample data. There can be multiple sample lithography machines, and the types and models of different sample lithography machines may also vary.

[0097] It can be understood that when obtaining a sample mask image, the sample mask image can be corrected in turn by processing the obtained lithography result image until the sample lithography machine processes the final corrected sample mask image under multiple sample process parameters and sample illumination images, and a lithography result image with a higher resolution can be obtained. The multiple sample process parameters, sample illumination images, the final corrected sample mask image and the lithography result image with a higher resolution are used as a training sample.

[0098] Taking the use of the OpenMMLab module to build a dataset as an example, since the image in the paired format can only be composed of two parts, the left part is domain_a and the right part is domain_b, in the actual execution process, a Dataset class that meets the input requirements of the module can be written to adapt to the three-channel input features corresponding to this application (i.e., the target expected mask image, the target illumination image, and multiple target process parameters) and the corresponding output results (i.e., the target mask image).

[0099] Specifically, for each data sample, three corresponding data files are set, namely "sample name_target.png", "sample name_lightpattern.png", "sample name_otherparams.txt", and "sample name_ILT.png". The storage paths of these four types of files are the same.

[0100] In other embodiments, four folders named target, lightpattern, otherparams, and ILT may be created, and then files with the same name may be stored in these four folders respectively.

[0101] In some embodiments, the target network model is trained based on multiple training samples and may include:

[0102] Multiple sample process parameters in the training samples are input into the multi-layer perception layer; the lithography result image, sample illumination image and sample mask image in the training samples are input into the generative adversarial network layer, and the target network model is trained with the multi-layer perception layer outputting the sample reconstructed image and the generative adversarial network layer outputting the predicted mask image as the goal.

[0103] In this embodiment, the data set is input into the target network model, and the target network model is trained with the multi-layer perception layer outputting the sample reconstructed image and the adversarial network layer outputting the predicted mask image as the goal; during the training process, a cross entropy loss function or a mean square error loss function can be used to train the target network model as a whole based on the difference between the predicted mask image and the sample mask image to obtain the weights of each neuron in the multi-layer perception layer and the model parameters of the adversarial network layer.

[0104] In some embodiments, the data set can also be divided into a training set and a test set, such as according to a ratio of 7:3 or 8:2. The training set is used to train the target network model, and the test set is used to test and optimize the trained target network model.

[0105] In some embodiments, before step 110, the method may further include:

[0106] Receiving a first input from a user on at least some of the multiple candidate configuration modules in the OpenMMLab configuration interface;

[0107] In response to the first input, a target network model is constructed based on at least some of the modules.

[0108] In this embodiment, the first input is used to select a required module from a plurality of candidate configuration modules provided by the OpenMMLab tool, and configure the connection relationship between the modules.

[0109] The first input may be in at least one of the following ways:

[0110] First, the first input may be a touch operation, including but not limited to a click operation, a slide operation, and a press operation.

[0111] In this embodiment, receiving the first input from the user may be receiving a touch operation of the user on the display area of ​​the terminal display screen.

[0112] In order to reduce the user error rate, the effective area of ​​the first input can be limited to a specific area, such as the upper middle area of ​​the OpenMMLab configuration interface; or when the OpenMMLab configuration interface is displayed, the target control is displayed on the current interface, and the first input can be achieved by touching the target control; or the first input can be set to a continuous multiple tapping operation on the display area within a target time interval.

[0113] Secondly, the first input may be a physical key input.

[0114] In this embodiment, the terminal body is provided with a corresponding physical button, and receiving the user's first input can be receiving the operation of the user pressing the corresponding physical button; the first input can also be a combined operation of pressing multiple physical buttons at the same time.

[0115] Third, the first input may be voice input.

[0116] Of course, in other embodiments, the first input may also be in other forms, including but not limited to character input, etc., which can be determined according to actual needs and is not limited in this embodiment of the present application.

[0117] Modules may include but are not limited to: network layers, loss functions, and optimizers.

[0118] The specific implementation method is described below.

[0119] 1. Build the OpenMMLab environment.

[0120] (1) Anaconda creates the environment openmmlab_generate and switches to this environment

[0121] conda create -name openmmlab python=3.8 -y

[0122] conda activate openmmlab

[0123] (2) Install CUDA version 11.3

[0124] (3) Install PyTorch 1.11.0

[0125] conda install pytorch==1.11.0 torchvision==0.12.0 torchaudio==0.11.0cudatoolkit=11.3 -c pytorch

[0126] (4) Install openmim, then install mmcv-full

[0127] pip install -U openmim

[0128] mim install mmcv-full

[0129] (5) Use git to clone the mmgeneration project locally, enter the project's root directory, and then install mmgeneration in editable mode using pip install -v -e .

[0130] (6) Run the sample code to test whether the installation is successful or not to verify the installation.

[0131] 2. Configuration script writing and training of OpenMMLab.

[0132] (1) Dataset preparation:

[0133] 1) Write a program that generates a dataset in the form of paired images. The first two input parameters are the paths to the input and labels, and the last one is the location where the image will be saved after processing.

[0134] 2) Write a program that randomly samples files. The first parameter is the file path to be sampled, and the second and third parameters are the paths of the training set and test set.

[0135] 3) Download the dataset provided by Lithobench, then run the first program to convert the image format, and then execute the second program to generate the training set and test set.

[0136] (2) Write the configuration script (taking Pix2Pix as an example, the same applies to CycleGAN):

[0137] 1) Run the official The configuration script of different sizes will generate the entire configuration of the configuration script in the workdir. Change the file name to the appropriate file and paste it to the appropriate path. Then make modifications based on this configuration file.

[0138] 2) Model configuration modification: First, change the in_channel of the Generator to 3, the out_channel to 1, and the in_channel of the discriminator to 3, and change the configurations related to the input source and output source to target and ILT respectively.

[0139] 3) Dataset pipeline configuration: Both the training and test sets were changed to pair format, the flag was changed to grayscale, domain_a and domain_b were changed to target and ILT, respectively, and the random cropping was removed. The training and test set configurations were essentially the same, with the exception that the test set did not have a flip step.

[0140] 4) Set dataroot to the path of the training set and test set generated by (1)

[0141] 5) Configure checkpoint_config, log_config, custom_hooks, exp_name, work_dir, total_iters and other variables according to your needs.

[0142] (3) Model training:

[0143] Configure the IDE's run and debug configuration options.

[0144] (4) Model code writing:

[0145] The input parameters of the model constructor should include the number of process parameters, the shape of the fully connected layer (an array where each element represents the size of the layer), the size of the input image and the size of the output image, the parameters of the GAN architecture, etc.

[0146] The model's forward function should be forward(self, x, y, z). The three parameters (x, y, z) represent the target mask image, the target illumination image, and the tensors corresponding to the target process parameters. The vectors of these target process parameters are passed through the multilayer perceptron to obtain the target reconstructed image. This image, along with the target mask image and the target illumination image, is concatenated into a three-channel image and fed into the GAN model. The GAN model constructor already specifies 3 input channels and 1 output channel.

[0147] During the research and development process, the inventors also found that in related technologies, the codes of target network models are mostly written in Pytorch. Writing the code requires writing Dataset, Dataloader, training and testing codes from scratch. The operation is relatively complicated and difficult to implement, and has a high threshold for use.

[0148] According to the mask image generation method for a lithography machine provided in an embodiment of the present application, by adopting the OpenMMLab framework for training, it is only necessary to select the required modules therefrom, combine and adjust different modules to meet specific needs, and complete the model training by only writing a configuration file and running it, thereby reducing repetitive actions, improving model building efficiency, and lowering the usage threshold; in addition, the deep learning network module can also be customized to receive multiple process parameters and illumination images, and jointly optimize them with the target expected mask image, thereby further improving the flexibility and construction efficiency of the model construction.

[0149] The mask image generation method for a lithography machine provided in the embodiments of the present application can be executed by a mask image generation device for a lithography machine. In the embodiments of the present application, the mask image generation device for a lithography machine performing the mask image generation method for a lithography machine is used as an example to illustrate the mask image generation device for a lithography machine provided in the embodiments of the present application.

[0150] An embodiment of the present application also provides a mask image generating device for a lithography machine.

[0151] like Figure 5 As shown, the mask image generating device for a lithography machine includes: a first processing module 510 , a second processing module 520 and a third processing module 530 .

[0152] A first processing module 510 is used to obtain multiple target process parameters;

[0153] The second processing module 520 is used to input multiple target process parameters into the multi-layer perception layer of the target network model to obtain a target reconstructed image output by the multi-layer perception layer;

[0154] The third processing module 530 is used to input the target reconstructed image, the target desired mask image and the target illumination image into the generative adversarial network layer of the target network model to obtain the target mask image output by the generative adversarial network layer; wherein,

[0155] The target mask image is used for further exposure by the lithography machine, and the output of the multi-layer perception layer is connected to the input of the generative adversarial network layer; the target network model is trained based on multiple training samples.

[0156] According to the mask image generation device for a lithography machine provided in an embodiment of the present application, the target mask image is predicted by target process parameters, target expected mask image and target illumination image, so that the target mask image can be adaptively adjusted based on different process parameters and different illumination images, thereby generating a target mask image that can obtain the target expected mask image in any lithography environment without the need for multiple iterations, and having high computational efficiency; and can be applicable to different lithography machines and lithography environments, and can be adaptively adjusted to obtain a more accurate mask image, thereby improving the resolution of the lithography system, and having high flexibility and universality.

[0157] In some embodiments, the second processing module 520 may also be used to:

[0158] Multiple target process parameters are input into the multi-layer perception layer of the target network model. The multi-layer perception layer learns the influence weight of each target process parameter and maps each target process parameter into a target feature vector. The target feature vector is used to represent the correlation between the target process parameters.

[0159] Reconstruct the target feature vector into a single-channel image to obtain the target reconstructed image.

[0160] In some embodiments, the first processing module 510 may also be used to:

[0161] According to the type of the lithography machine and the target lithography environment, multiple target process parameters are obtained.

[0162] In some embodiments, the plurality of target process parameters include exposure dose and photoresist parameters.

[0163] In some embodiments, the apparatus may further include a fourth processing module configured to:

[0164] Obtaining multiple sample process parameters corresponding to a sample lithography machine;

[0165] Acquire a lithography result image obtained by processing a sample mask image with a sample lithography machine under multiple sample process parameters and sample illumination images;

[0166] Training samples are constructed using multiple sample process parameters, sample illumination images and lithography result images as samples and sample mask images as sample labels.

[0167] In some embodiments, the fourth processing module may further be configured to:

[0168] Multiple sample process parameters in the training samples are input into the multi-layer perception layer; the lithography result image, sample illumination image and sample mask image in the training samples are input into the generative adversarial network layer, and the target network model is trained with the multi-layer perception layer outputting the sample reconstructed image and the generative adversarial network layer outputting the predicted mask image as the goal.

[0169] In some embodiments, the apparatus may further include a fifth processing module configured to:

[0170] Before obtaining the plurality of target process parameters, receiving a first input from a user for at least some of the plurality of candidate configuration modules in the OpenMMLab configuration interface;

[0171] In response to the first input, a target network model is constructed based on at least some of the modules.

[0172] The mask image generating device for a lithography machine in the embodiments of the present application can be an electronic device or a component of an electronic device, such as an integrated circuit or chip. The electronic device can be a terminal or other device other than a terminal. For example, the electronic device can be a mobile phone, tablet computer, laptop computer, PDA, in-vehicle electronic device, mobile internet device (MID), augmented reality (AR) / virtual reality (VR) device, robot, wearable device, ultra-mobile personal computer (UMPC), netbook, or personal digital assistant (PDA). It can also be a server, network attached storage (NAS), personal computer (PC), television, ATM, or self-service machine, etc., and the embodiments of the present application are not specifically limited thereto.

[0173] The mask image generating device for a lithography machine in the embodiments of the present application may be a device having an operating system. The operating system may be an Android operating system, an iOS operating system, or other possible operating systems, which are not specifically limited in the embodiments of the present application.

[0174] The mask image generating device for a photolithography machine provided in the embodiment of the present application can achieve Figures 1 to 4 To avoid repetition, the various processes implemented in the method embodiment are not described here.

[0175] In some embodiments, as Figure 6 As shown, an embodiment of the present application also provides an electronic device 600, including a processor 601, a memory 602, and a computer program stored in the memory 602 and executable on the processor 601. When the program is executed by the processor 601, each process of the above-mentioned mask image generation method embodiment for a lithography machine is implemented, and the same technical effect can be achieved. To avoid repetition, it will not be described here.

[0176] It should be noted that the electronic devices in the embodiments of the present application include the mobile electronic devices and non-mobile electronic devices mentioned above.

[0177] An embodiment of the present application also provides a non-transitory computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, the various processes of the above-mentioned mask image generation method embodiment for a lithography machine are implemented, and the same technical effect can be achieved. To avoid repetition, it will not be repeated here.

[0178] The processor is the processor in the electronic device described in the above embodiment. The readable storage medium includes a computer-readable storage medium, such as a computer read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0179] An embodiment of the present application also provides a computer program product, including a computer program, which implements the above-mentioned mask image generation method for a lithography machine when executed by a processor.

[0180] The processor is the processor in the electronic device described in the above embodiment. The readable storage medium includes a computer-readable storage medium, such as a computer read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0181] An embodiment of the present application further provides a chip, which includes a processor and a communication interface, wherein the communication interface is coupled to the processor, and the processor is used to run programs or instructions to implement the various processes of the above-mentioned mask image generation method embodiment for a lithography machine, and can achieve the same technical effect. To avoid repetition, it will not be repeated here.

[0182] It should be understood that the chip mentioned in the embodiments of the present application can also be called a system-level chip, a system chip, a chip system or a system-on-chip chip, etc.

[0183] It should be noted that, in this article, the terms "comprise", "include" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device comprising 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, an element defined by the statement "comprises a ..." does not exclude the presence of other identical elements in the process, method, article or device comprising the element. In addition, it should be noted that the scope of the methods and devices in the embodiments of the present application is not limited to performing functions in the order shown or discussed, and may also include performing functions in a substantially simultaneous manner or in the opposite order according to the functions involved. For example, the described method may be performed in an order different from that described, and various steps may also be added, omitted, or combined. In addition, the features described with reference to certain examples may be combined in other examples.

[0184] Through the description of the above embodiments, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus the necessary general hardware platform. Of course, they can also be implemented by hardware, but in many cases the former is a better embodiment. Based on this understanding, the technical solution of this application, or the part that contributes to the existing technology, can be embodied in the form of a computer software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes a number of instructions for enabling a terminal (which can be a mobile phone, computer, server, or network device, etc.) to execute the methods described in each embodiment of this application.

[0185] The embodiments of the present application are described above in conjunction with the accompanying drawings, but the present application is not limited to the above-mentioned specific implementation methods. The above-mentioned specific implementation methods are merely illustrative and not restrictive. Under the guidance of this application, ordinary technicians in this field can also make many forms without departing from the purpose of this application and the scope of protection of the claims, all of which are within the protection of this application.

[0186] Throughout this specification, reference to terms such as "one embodiment," "some embodiments," "illustrative embodiments," "examples," "specific examples," or "some examples" means that the specific features, structures, materials, or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.

[0187] Although the embodiments of the present application have been shown and described, those skilled in the art will appreciate that various changes, modifications, substitutions, and variations may be made to the embodiments without departing from the principles and intent of the present application, and that the scope of the present application is defined by the claims and their equivalents.

Claims

1. A mask image generation method for a lithography machine, characterized in that: include: Obtain multiple target process parameters; Inputting the plurality of target process parameters into a multi-layer perception layer of a target network model, and obtaining a target reconstructed image output by the multi-layer perception layer; The target reconstructed image, the target desired mask image and the target illumination image are input into the generative adversarial network layer of the target network model to obtain the target mask image output by the generative adversarial network layer; wherein, The target mask image is used for exposure by the lithography machine, the output end of the multi-layer perception layer is connected to the input end of the generative adversarial network layer; the target network model is trained based on multiple training samples; Inputting the plurality of target process parameters into a multi-layer perception layer of a target network model to obtain a target reconstructed image output by the multi-layer perception layer includes: Inputting the plurality of target process parameters into a multi-layer perception layer of a target network model, allowing the multi-layer perception layer to learn an influence weight of each target process parameter, and mapping each target process parameter into a target feature vector, wherein the target feature vector is used to characterize an association relationship between each target process parameter; The target feature vector is reconstructed into a single-channel image to obtain the target reconstructed image.

2. The mask image generation method for a lithography machine according to claim 1, characterized in that: The obtaining of multiple target process parameters includes: The multiple target process parameters are acquired according to the type of the lithography machine and the target lithography environment.

3. The mask image generation method for a photolithography machine according to claim 1 or 2, characterized in that: The multiple target process parameters include: exposure dose and photoresist parameters.

4. The mask image generation method for a photolithography machine according to claim 1 or 2, characterized in that: The training samples are obtained based on the following steps: Obtaining multiple sample process parameters corresponding to a sample lithography machine; Acquire a lithography result image obtained by the sample lithography machine processing the sample mask image under the multiple sample process parameters and the sample illumination image; The training samples are constructed by taking the multiple sample process parameters, the sample illumination image and the photolithography result image as samples and taking the sample mask image as a sample label.

5. The mask image generation method for a photolithography machine according to claim 1 or 2, characterized in that: The target network model is trained based on multiple training samples, including: Input multiple sample process parameters in the training samples into the multi-layer perception layer; input the lithography result image, sample illumination image and sample mask image in the training samples into the generative adversarial network layer, and train the target network model with the sample reconstructed image output by the multi-layer perception layer and the predicted mask image output by the generative adversarial network layer as the target.

6. The mask image generation method for a photolithography machine according to claim 1 or 2, characterized in that: Before obtaining the plurality of target process parameters, the method further includes: Receiving a first input from a user on at least some of the multiple candidate configuration modules in the OpenMMLab configuration interface; In response to the first input, the target network model is constructed based on the at least part of the modules.

7. A mask image generating device for a photolithography machine, characterized in that: include: A first processing module is used to obtain a plurality of target process parameters; A second processing module is configured to input the plurality of target process parameters into a multi-layer perception layer of a target network model, and obtain a target reconstructed image output by the multi-layer perception layer; The third processing module is configured to input the target reconstructed image, the target desired mask image, and the target illumination image into the generative adversarial network layer of the target network model, and obtain the target mask image output by the generative adversarial network layer; wherein, The target mask image is used for image correction by the lithography machine, the output end of the multi-layer perception layer is connected to the input end of the generative adversarial network layer; the target network model is obtained by training based on multiple training samples; The second processing module is configured to: Inputting the plurality of target process parameters into a multi-layer perception layer of a target network model, allowing the multi-layer perception layer to learn an influence weight of each target process parameter, and mapping each target process parameter into a target feature vector, wherein the target feature vector is used to characterize an association relationship between each target process parameter; The target feature vector is reconstructed into a single-channel image to obtain the target reconstructed image.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the program, the mask image generation method for a lithography machine as described in any one of claims 1 to 6 is implemented.

9. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the mask image generation method for a lithography machine as described in any one of claims 1 to 6 is implemented.

Images