Photoresist model training method, device and equipment and computer storage medium

Abstract

The invention discloses a photoresist model training method, device and equipment and a computer storage medium. The method comprises the following steps: acquiring a photoetching design layout, a mask layout and a photoetching process parameter information set; constructing an initial photoresist model according to the first parameter; carrying out first training with a preset number of iterations on the initial photoresist model to obtain a first photoresist model; screening the index value of the graphic index in the last iteration process from the training log; under the condition that the index value of the graphic index is determined to be greater than a preset threshold value, updating a parameter in the initial photoresist model into a second parameter to obtain an updated initial photoresist model, and returning to carry out first training of a preset number of iterations on the initial photoresist model according to the mask layout and the photoetching design layout to obtain a first photoresist model, and obtaining a trained photoresist model until the index value is smaller than or equal to a preset threshold value. According to the embodiment of the invention, the photoresist model training efficiency can be improved.

Description

Technical Field

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

[0002] Computational lithography is an advanced technology that uses computers to simulate and optimize the lithography process. It simulates the optical, chemical and physical phenomena in the lithography process by establishing accurate mathematical models.

[0003] Computational lithography can include a variety of models, such as optical models and chemical models. Among them, the optical model can be used to describe the process of light starting from the light source, passing through optical elements such as masks and projection lenses, and forming an image on the wafer surface; the chemical model can be used to describe the photochemical reaction process that occurs after light is projected onto the photoresist.

[0004] When training the model in computational lithography according to the preset number of iterations, if the trained model does not meet the expected expectations, it is necessary to trace back to find the problem, adjust the corresponding parameters, and retrain the model. The number of iterations of model training is generally a large value. Therefore, if the parameters are adjusted multiple times and the model is trained with the preset number of iterations each time, a lot of time and resources will be wasted. Summary of the invention

[0005] The embodiments of the present application provide a method, apparatus, device and computer storage medium for training a photoresist model, which can achieve rapid training of the photoresist model through a relatively small number of iterations, and determine the influence of the parameters in the model on the photolithography pattern based on the indicator values ​​of the graphic indicators in the training log, thereby quickly eliminating the model parameters that have no optimization effect on the photolithography pattern, thereby improving the efficiency of photoresist model training.

[0006] In a first aspect, an embodiment of the present application provides a method for training a photoresist model, comprising: obtaining a set of information on a photolithography design layout, a mask layout, and photolithography process parameters that affect the photolithography design layout; constructing an initial photoresist model according to a first parameter in the set; performing a first training for a preset number of iterations on the initial photoresist model according to the mask layout and the photolithography design layout to obtain a first photoresist model; screening an index value of a graphic index in the last iteration process from a training log of the first training; when it is determined that the index value of the graphic index is greater than a preset threshold, updating the parameter in the initial photoresist model to a second parameter according to the set to obtain an updated initial photoresist model, and returning to performing a first training for a preset number of iterations on the initial photoresist model according to the mask layout and the photolithography design layout to obtain a first photoresist model, until the index value is less than or equal to the preset threshold to obtain a trained photoresist model; the first parameter and the second parameter are not completely the same.

[0007] In one embodiment, a first training of a preset number of iterations is performed on an initial photoresist model according to a mask layout and a lithography design layout to obtain a first photoresist model, including: predicting the lithography pattern of the mask layout according to the initial photoresist model to obtain a predicted layout; determining an index value of a graphic index between the predicted layout and the lithography design layout, and storing the index value in a training log; when it is determined that the number of iterations has not reached a preset number of iterations, adjusting the parameters in the initial photoresist model to obtain an adjusted initial photoresist model, accumulating the number of iterations, returning to input the spatial image into the initial photoresist model to obtain a predicted layout, until the number of iterations reaches a preset number of iterations to obtain the first photoresist model.

[0008] In one embodiment, the lithographic pattern of the mask layout is predicted according to the initial photoresist model to obtain a predicted layout, including: determining a cross-transmission matrix according to optical process parameter information in a lithography process parameter information set; calculating a spatial image corresponding to the mask layout according to the mask layout and the cross-transmission matrix; and inputting the spatial image into the initial photoresist model to obtain a predicted layout.

[0009] In one embodiment, the graphic index includes at least one of the following: a mean square error between a predicted layout and a photolithography design layout; and an over-specification amount of the predicted layout compared to the photolithography design layout.

[0010] In one implementation, the preset number of iterations is less than a preset number.

[0011] In a second aspect, an embodiment of the present application provides a training device for a photoresist model, the device comprising: an acquisition module for acquiring a set of information on a photolithography design layout, a mask layout, and photolithography process parameters that affect the photolithography design layout; a construction module for constructing an initial photoresist model according to a first parameter in the set; a training module for performing a first training of the initial photoresist model for a preset number of iterations according to the mask layout and the photolithography design layout to obtain a first photoresist model; a screening module for screening an index value of a graphic index in the last iteration process from a training log of the first training; a loop module for updating the parameters in the initial photoresist model to a second parameter according to the set when it is determined that the index value of the graphic index is greater than a preset threshold value to obtain an updated initial photoresist model, and returning to performing a first training of the initial photoresist model for a preset number of iterations according to the mask layout and the photolithography design layout to obtain a first photoresist model, until the index value meets the preset threshold value to obtain a trained photoresist model; the first parameter and the second parameter are not completely the same.

[0012] In a third aspect, an embodiment of the present application provides a method and 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, the method for training a photoresist model in the first aspect or any one of the embodiments of the first aspect is implemented.

[0013] In a fourth aspect, a computer-readable storage medium stores computer program instructions, and when the computer program instructions are executed by a processor, a method for training a photoresist model in the first aspect or any one of the embodiments of the first aspect is implemented.

[0014] 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 method for training a photoresist model such as the first aspect or any one of the embodiments of the first aspect.

[0015] The training method, device, equipment and computer storage medium of the photoresist model of the embodiment of the present application obtain a set of photolithography process parameter information, and construct an initial photoresist model based on the first parameter in the set of photolithography process parameter information. Further, the initial photoresist model is first trained with a preset number of iterations using a mask layout and a photolithography design layout to obtain a first photoresist model. Among them, the preset number of iterations can be a number of iterations with a smaller value, and through the training of the preset number of iterations, the initial photoresist model can reflect the influence of the first parameter on the photolithography pattern. The influence of the first parameter in the first photoresist model on the photolithography pattern can be determined by obtaining the index value of the graphic index in the training log. When it is determined that there is no optimization effect on the photolithography pattern by adjusting the first parameter, that is, when it is determined that the index value of the graphic index is greater than the preset threshold, the first parameter in the initial photoresist model is adjusted to the second parameter, and the initial photoresist model after the adjusted parameter is retrained to determine the influence of the second parameter on the photoresist pattern. It can be understood that in the embodiments of the present application, rapid training of the photoresist model is achieved through a smaller number of iterations, and the influence of the parameters in the model on the photolithography pattern is determined based on the indicator values ​​of the graphic indicators in the training log, thereby quickly eliminating the model parameters that have no optimization effect on the photolithography pattern, thereby improving the efficiency of photoresist model training. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] 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.

[0017] Figure 1A schematic diagram of a process of training a photoresist model provided by an embodiment of the present application is shown;

[0018] Figure 2 A schematic diagram of the process of S130 provided in one embodiment of the present application is shown;

[0019] Figure 3 A schematic diagram of the process of S131 provided in one embodiment of the present application is shown;

[0020] Figure 4 is a structural schematic diagram of a photoresist model training device provided by another embodiment of the present application;

[0021] Figure 5 A schematic diagram of the hardware structure of the photoresist model training method provided in an embodiment of the present application is shown. DETAILED DESCRIPTION

[0022] 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.

[0023] 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.

[0024] Computational lithography is an advanced technology that uses computers to simulate and optimize the lithography process. It establishes accurate mathematical models based on theoretical foundations such as optical imaging theory, photochemical theory, and thermal diffusion theory to simulate the optical, chemical, and physical phenomena in the lithography process.

[0025] Computational lithography can include optical models and chemical models. Through the training of the optical model and the chemical model, the process of light diffracting on the mask and finally imaging and the process of light projecting on the photoresist to stimulate chemical reactions can be simulated.

[0026] However, when training a model, the number of training iterations is not easy to grasp. Too many iterations or too few iterations may lead to an unsatisfactory model obtained through training. In addition, if the model obtained through training is not ideal, it is necessary to trace back to find the problem and make corresponding modifications. The adjusted model still needs to be trained according to the set number of iterations. For example, if it is determined that the reason why the training model is not ideal may be due to unreasonable parameter selection in the model, for example, a series of parameter configurations in the photoresist kernel function in the photoresist model are unreasonable, and when adjusting the parameters, multiple adjustments may be required. Therefore, multiple trainings need to be repeated during the training process, and each training is performed with a preset number of iterations, which results in a large amount of time and resource waste during the model training process.

[0027] In order to solve the problems of the prior art, the embodiments of the present application provide a method, device, equipment and computer storage medium for training a photoresist model. The following first introduces the method for training a photoresist model provided in the embodiments of the present application.

[0028] Figure 1 FIG. 1 is a flow chart of a method for training a photoresist model provided by an embodiment of the present application. Figure 1 As shown, the training method of the photoresist model includes the following steps:

[0029] S110, obtaining a photolithography design layout, a mask layout, and a set of photolithography process parameter information that affects the photolithography design layout.

[0030] For example, the photolithography design layout describes the logical functions and electrical connection relationships of various electronic components in the chip, thereby realizing various performances of the chip.

[0031] Exemplarily, the lithography process parameter information that affects the lithography design layout includes corresponding parameters corresponding to the chemical behavior of light in the photoresist during the exposure process. For example, the chemical behavior of light in the photoresist during the exposure process may include chemical reactions, diffusion, and dissolution of the photoresist, and correspondingly, the parameters in this process may include the acidity, alkalinity, and mechanical stress of the photoresist.

[0032] It is understandable that different photolithography process parameter information causes different chemical reactions of light in the photoresist, thereby affecting the shape of the graphics in the patterned layer on the wafer surface.

[0033] Exemplarily, the mask pattern can be used to control the projection area of ​​light, thereby controlling the area on the photoresist where light is irradiated.

[0034] Exemplarily, the photolithography process parameter information set may also include optical process parameter information, such as the light intensity and wavelength of the light source.

[0035] S120, constructing an initial photoresist model according to the first parameter in the set.

[0036] Exemplarily, the establishment of the initial photoresist model can be achieved through the first parameter in the photolithography process parameter information set, wherein the first parameter can be obtained by any combination of multiple parameters in the photolithography process parameter information set.

[0037] Exemplarily, any parameter in the photolithography process parameter information set can be represented by constructing a corresponding mathematical function. Therefore, in the photoresist model, the chemical behavior of light in the actual exposure of the photoresist can be simulated by constructing a mathematical function corresponding to each parameter in the first parameter. For example, the acidity in the photoresist model can be represented by a Gaussian function.

[0038] Exemplarily, the architectures of mathematical functions corresponding to different parameters may be different, and different parameter values ​​in the same parameter may be adjusted by modifying corresponding data in the mathematical function. For example, the weights in the mathematical function may be adjusted to characterize different parameter values ​​of the parameter.

[0039] Exemplarily, the mathematical functions corresponding to the first parameters can be collectively referred to as photoresist kernel functions. It can be understood that different first parameters correspond to different photoresist kernel functions. Similarly, different first parameters also describe different chemical processes of light exposure in photoresist.

[0040] S130 , performing a first training of a preset number of iterations on the initial photoresist model according to the mask layout and the lithography design layout to obtain a first photoresist model.

[0041] Exemplarily, the mask layout and the lithography design layout can be input into the initial photoresist model, and the initial photoresist model is trained until the number of iterations meets the preset iteration condition to obtain the first photoresist model, wherein the first photoresist model can reflect the influence of the first parameter on the lithography pattern.

[0042] In some optional embodiments, the preset number of iterations is less than the preset number. The preset number can be preset by relevant technicians based on experience. And the preset number is generally a smaller value. For example, relevant technicians can set the preset number to 5 times, or can set the preset number to 10 times.

[0043] S140: Filter the indicator value of the graphic indicator in the last iteration process from the training log of the first training.

[0044] Exemplarily, it can be understood that the first training process includes a preset number of iterations of training processes. And the data in each training process will be stored in the training log. That is, the training log of the first training can store each iteration of the first training process and important data in the training process. In addition, the last training process can be determined by screening the training log of the first training, and the important data in the last training process can be screened to screen the indicator value of the graphic indicator.

[0045] Exemplarily, the pattern index may characterize the influence of the first parameter in the initial photoresist model on the photolithography pattern.

[0046] In some optional embodiments, the graphic index may include a root mean square (RMS) and / or an out of spec number (OOS). The influence of the first parameter in the initial photoresist model on the photolithography pattern is characterized by the root mean square and / or the out of spec number. It is understandable that if the root mean square and the out of spec number are small, it can be determined that by adjusting the parameter value of the first parameter in the initial photoresist model, a better photolithography pattern can be obtained, that is, the first parameter has a beneficial influence on the photolithography pattern.

[0047] S150, determining whether the indicator value of the graphic indicator is greater than a preset threshold, if so, executing step S160; if not, the training ends and a trained photoresist model is obtained.

[0048] S160. Update the parameters in the initial photoresist model to second parameters according to the set to obtain an updated initial photoresist model, wherein the first parameter and the second parameter are not completely the same.

[0049] Exemplarily, it is possible to determine whether the index value of the graphic index is greater than a preset threshold value. If it is determined that the index value of the graphic index is greater than the preset threshold value, the parameters in the initial photoresist model are updated to the second parameters according to the set to obtain the updated initial photoresist model, and return to the first training of the initial photoresist model for a preset number of iterations according to the mask layout and the lithography design layout to obtain the first photoresist model, that is, retrain the photoresist model after the parameter adjustment until the graphic index value is less than or equal to the preset threshold value. If it is determined that the index value of the graphic index is less than or equal to the preset threshold value, it is determined that the training is completed and a trained photoresist model is obtained.

[0050] Exemplarily, updating the parameters in the initial photoresist model to the second parameters according to the set may be to select multiple parameters different from the first parameters in the set as the second parameters after the initial photoresist model is updated. Alternatively, the data in the training log of the first training may be analyzed to determine the parameters in the first parameters that have no effect or have an adverse effect on the photolithography pattern, and these parameters may be removed from the first parameters to obtain the second parameters. In one example, the data in the training log of the first training may be analyzed by the point-interval symmetry analysis method to determine the parameters in the first parameters that have no effect or have an adverse effect on the photolithography pattern.

[0051] In one example, the first parameter in the initial photoresist model includes the acidity, alkalinity and mechanical stress of the photoresist. After the first training, the first photoresist model is obtained. At this time, in the first photoresist model, the parameter value corresponding to the acidity can be m, the parameter value corresponding to the alkalinity can be n, and the parameter value corresponding to the mechanical stress can be p. In addition, the index value of the graphic index of the first photoresist model is greater than the preset threshold, and it is determined through analysis that setting the alkalinity in the photoresist has an adverse effect on the formation of the photolithography pattern. Therefore, the alkalinity is removed from the model parameters, and the updated second parameters are the acidity and mechanical stress of the photoresist. Then, the photoresist model with modified parameters is retrained.

[0052] In an embodiment of the present application, an initial photoresist model is constructed by obtaining a set of photolithography process parameter information and based on a first parameter in the set of photolithography process parameter information. Further, the initial photoresist model is first trained with a preset number of iterations using a mask layout and a photolithography design layout to obtain a first photoresist model. Among them, the preset number of iterations can be a number of iterations with a smaller value, and through the training of the preset number of iterations, the initial photoresist model can reflect the influence of the first parameter on the photolithography pattern. The influence of the first parameter in the first photoresist model on the photolithography pattern can be determined by obtaining the index value of the graphic index in the training log. When it is determined that there is no optimization effect on the photolithography pattern by adjusting the first parameter, that is, when it is determined that the index value of the graphic index is greater than a preset threshold, the first parameter in the initial photoresist model is adjusted to the second parameter, and the initial photoresist model after the adjusted parameter is retrained to determine the influence of the second parameter on the photoresist pattern. It can be understood that in the embodiments of the present application, rapid training of the photoresist model is achieved through a smaller number of iterations, and the influence of the parameters in the model on the photolithography pattern is determined based on the indicator values ​​of the graphic indicators in the training log, thereby quickly eliminating the model parameters that have no optimization effect on the photolithography pattern, thereby improving the efficiency of photoresist model training.

[0053] In order to implement the training of the initial photoresist model, as another implementation of the present application, the present application also provides another implementation of S130, and please refer to the following embodiments for details.

[0054] Figure 2 FIG. 1 shows a flow chart of S130 provided by an embodiment of the present application. Figure 2 As shown, S130 includes the following steps:

[0055] S131, predicting the photolithography pattern of the mask layout according to the initial photoresist model to obtain a predicted layout.

[0056] Exemplarily, the predicted layout may represent a layout that can be obtained under the photolithography process conditions corresponding to the first parameter. The mask layout may include multiple photolithography patterns. Further, the initial photoresist model is used to predict the photolithography pattern morphology of the mask layout, thereby obtaining the predicted layout.

[0057] S132, determining the index value of the graphic index between the predicted layout and the lithography design layout, and storing the index value in the training log.

[0058] Exemplarily, an index value of a graphic index between a predicted layout and a lithography design layout may be determined, and the index value may be stored in a training log.

[0059] Exemplarily, the graphic indicators between the predicted layout and the lithography design layout may include the mean square error between the predicted layout and the lithography design layout; and / or the amount of over-specification of the predicted layout compared to the lithography design layout. The mean square error is used to measure the degree of difference between the predicted layout and the lithography design layout at the critical dimensions, while the amount of over-specification focuses on whether these differences exceed the preset specification range.

[0060] Exemplarily, the mean square error and / or the excess amount corresponding to each iterative training may be stored in a training log.

[0061] S133, determine whether the number of iterations reaches the preset number of iterations, if so, end the training and obtain the first photoresist model; if not, execute step S134.

[0062] S134, adjusting the parameters in the initial photoresist model to obtain an adjusted initial photoresist model, and accumulating the number of iterations.

[0063] Exemplarily, for the initial photoresist model, the number of iterations can be used as its constraint condition. When it is determined that the number of training times of the initial photoresist model reaches a preset number of iterations, it is determined that the initial photoresist model has completed training, and a first photoresist model is obtained. If it is determined that the number of training times of the initial photoresist model does not reach the preset number of iterations, it is necessary to adjust the parameters in the initial photoresist model to obtain an adjusted initial photoresist model, and the number of iterations is accumulated, and then the initial photoresist model is retrained.

[0064] Exemplarily, the parameter value of the first parameter can be adjusted by adjusting the parameters in the initial photoresist model, so that the initial photoresist model can simulate the photolithography process conditions when the first parameter takes different parameter values.

[0065] Exemplarily, the first parameter may include multiple photolithography process parameters. Adjusting the parameters in the initial photoresist model may be used to adjust the parameter values ​​corresponding to multiple parameters simultaneously. Alternatively, adjusting the parameters in the initial photoresist model may be used to adjust the parameter value corresponding to a single parameter.

[0066] In an embodiment of the present application, the initial model is trained according to a preset number of iterations, thereby completing the training of the photoresist model, and then quickly determining whether the parameters of the initial photoresist model will affect the photolithography pattern, thereby avoiding the continuous training of models in which the parameters of the initial photoresist model have no effect or have a bad effect on the photolithography pattern, resulting in a waste of time and computing resources.

[0067] In order to achieve the acquisition of the predicted layout, which is another implementation method of the present application, the present application also provides another implementation method of training the photoresist model, please refer to the following embodiments for details.

[0068] Figure 3 FIG. 1 shows a flow chart of S131 provided by an embodiment of the present application. Figure 3 As shown, S131 includes the following steps:

[0069] S1311. Determine a cross-transmission matrix according to the optical process parameter information in the photolithography process parameter information set.

[0070] For example, the Transmission Cross Coefficient (TCC) can be used to characterize the transmission efficiency of light from the mask to each point on the photoresist. The light path system from the mask to the photoresist can be described by the Hopkins model and Abbe imaging theory, and then the cross transmission matrix can be determined.

[0071] Exemplarily, under the same photolithography process conditions, the cross-transmission matrix is ​​fixed.

[0072] S1312: Calculate and obtain the spatial image corresponding to the mask layout according to the mask layout and the cross-transmission matrix.

[0073] Exemplarily, a mask image (MI) corresponding to the mask layout may be convolved with a cross-transmission matrix to obtain an aerial image (AI) corresponding to the mask layout, wherein the mask image may be obtained by sampling the mask.

[0074] For example, an aerial image can be used to describe an image formed on the photoresist after light passes through the mask.

[0075] S1313. Input the spatial image into the initial photoresist model to obtain a predicted layout.

[0076] Exemplarily, the calculated aerial image may be input into a photoresist model, and a photoresist image (Resist Image, RI) may be obtained by performing convolution calculation on the aerial image and the photoresist kernel function.

[0077] Furthermore, by performing subsequent process steps, such as etching, on the photoresist image, a predicted layout is obtained.

[0078] In the embodiment of the present application, the predicted layout is acquired by acquiring a cross-transmission matrix, and using the cross-transmission matrix and the mask layout to calculate an aerial image corresponding to the mask layout, and then using the aerial image to determine the predicted layout.

[0079] Based on the photoresist model training method provided in the above embodiment, the present application also provides a specific implementation of the photoresist model training device. Please refer to the following embodiment.

[0080] See first Figure 4 , Figure 4 : is a structural schematic diagram of a photoresist model training device provided by another embodiment of the present application. The photoresist model training device provided by the embodiment of the present application includes the following units:

[0081] An acquisition module 401 is used to acquire a photolithography design layout, a mask layout, and a set of photolithography process parameter information that affects the photolithography design layout;

[0082] A construction module 402, configured to construct an initial photoresist model according to a first parameter in the set;

[0083] A training module 403 is used to perform a first training of a preset number of iterations on the initial photoresist model according to the mask layout and the lithography design layout to obtain a first photoresist model;

[0084] A screening module 404 is used to screen the index value of the graphic index in the last iteration process from the training log of the first training;

[0085] The loop module 405 is used to update the parameters in the initial photoresist model to the second parameters according to the set to obtain the updated initial photoresist model when it is determined that the index value of the graphic index is greater than the preset threshold value, and return to the first training of the initial photoresist model for a preset number of iterations according to the mask layout and the lithography design layout to obtain the first photoresist model, until the index value meets the preset threshold value, and a trained photoresist model is obtained; the first parameter and the second parameter are not completely the same.

[0086] As an implementation of the present application, the training module 403 performs a first training of a preset number of iterations on the initial photoresist model according to the mask layout and the lithography design layout in the following manner to obtain a first photoresist model:

[0087] As an implementation method of the present application, the training module 403 performs a first training of a preset number of iterations on the initial photoresist model according to the mask layout and the lithography design layout in the following manner to obtain a first photoresist model: predicting the lithography pattern of the mask layout according to the initial photoresist model to obtain a predicted layout; determining the index value of the graphic index between the predicted layout and the lithography design layout, and storing the index value in the training log; when it is determined that the number of iterations has not reached the preset number of iterations, adjusting the parameters in the initial photoresist model to obtain the adjusted initial photoresist model, and accumulating the number of iterations, returning to input the spatial image into the initial photoresist model to obtain a predicted layout, until the number of iterations reaches the preset number of iterations to obtain the first photoresist model.

[0088] As an implementation method of the present application, the training module 403 predicts the lithography pattern of the mask layout according to the initial photoresist model to obtain a predicted layout in the following manner: predicting the lithography pattern of the mask layout according to the initial photoresist model to obtain a predicted layout, including: determining the cross-transmission matrix according to the optical process parameter information in the lithography process parameter information set; calculating the spatial image corresponding to the mask layout according to the mask layout and the cross-transmission matrix; inputting the spatial image into the initial photoresist model to obtain a predicted layout.

[0089] As an implementation of the present application, the graphic index includes at least one of the following: a mean square error between a predicted layout and a photolithography design layout; and an over-specification amount of the predicted layout compared to the photolithography design layout.

[0090] As an implementation of the present application, the preset number of iterations is less than the preset number.

[0091] Figure 5A schematic diagram of the hardware structure of the photoresist model training method provided in an embodiment of the present application is shown.

[0092] The photoresist model training device may include a processor 501 and a memory 502 storing computer program instructions.

[0093] Specifically, the processor 501 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.

[0094] The memory 502 may include a large capacity memory for data or instructions. By way of example and not limitation, the memory 502 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 502 may include a removable or non-removable (or fixed) medium. In appropriate cases, the memory 502 may be inside or outside the integrated gateway disaster recovery device. In a specific embodiment, the memory 502 is a non-volatile solid-state memory.

[0095] 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.

[0096] The processor 501 implements any one of the photoresist model training methods in the above embodiments by reading and executing computer program instructions stored in the memory 502 .

[0097] In one example, the photoresist model training device may further include a communication interface 503 and a bus 510. Figure 5 As shown, the processor 501, the memory 502, and the communication interface 503 are connected via a bus 510 and communicate with each other.

[0098] The communication interface 503 is mainly used to implement communication between various modules, devices, units and / or equipment in the embodiments of the present application.

[0099] Bus 510 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 510 may include one or more buses. Although the present application embodiment describes and shows a specific bus, the present application considers any suitable bus or interconnection.

[0100] The photoresist model training device can perform the photoresist model training method in the embodiment of the present application at a preset number of iterations, thereby realizing the combination of Figure 1 and Figure 4 A method and apparatus for training a photoresist model is described.

[0101] In addition, in combination with the photoresist model training method in the above embodiment, the present application embodiment 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 photoresist model training methods in the above embodiment is implemented.

[0102] The present embodiment also provides a computer program product, including a computer program, which, when executed, implements any one of the photoresist model training methods in the above embodiments.

[0103] 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.

[0104] 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.

[0105] 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.

[0106] 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.

[0107] 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 training a photoresist model, characterized in that: include: Acquire a photolithography design layout, a mask layout, and a set of photolithography process parameter information affecting the photolithography design layout; constructing an initial photoresist model according to a first parameter in the set; According to the mask layout and the photolithography design layout, a first training of a preset number of iterations is performed on an initial photoresist model to obtain a first photoresist model; Filter the indicator values ​​of the graph indicators during the last iteration from the training log of the first training; When it is determined that the index value of the graphic index is greater than a preset threshold, the parameters in the initial photoresist model are updated to the second parameters according to the set to obtain an updated initial photoresist model, and the first training of the initial photoresist model for a preset number of iterations is returned to obtain a first photoresist model according to the mask layout and the lithography design layout, until the index value is less than or equal to the preset threshold, to obtain a trained photoresist model; the first parameter and the second parameter are not exactly the same.

2. The method for training a photoresist model according to claim 1, characterized in that: The first step of performing a first training of a preset number of iterations on the initial photoresist model according to the mask layout and the lithography design layout to obtain a first photoresist model includes: Predicting the photolithography pattern of the mask layout according to the initial photoresist model to obtain a predicted layout; Determining an index value of a graphic index between the predicted layout and the lithography design layout, and storing the index value in the training log; When it is determined that the number of iterations has not reached the preset number of iterations, the parameters in the initial photoresist model are adjusted to obtain the adjusted initial photoresist model, and the number of iterations is accumulated, and the photolithography pattern of the mask layout is predicted according to the initial photoresist model to obtain the predicted layout, until the number of iterations reaches the preset number of iterations to obtain the first photoresist model.

3. The method according to claim 2, characterized in that The step of predicting the photolithography pattern of the mask layout according to the initial photoresist model to obtain a predicted layout includes: Determining a cross-transmission matrix according to the optical process parameter information in the photolithography process parameter information set; According to the mask layout and the cross-transmission matrix, an aerial image corresponding to the mask layout is calculated; The aerial image is input into an initial photoresist model to obtain a predicted layout.

4. The method according to any one of claims 1 to 3, characterized in that: The graphic indicator includes at least one of the following: Mean square error between the predicted layout and the lithography design layout; The amount by which the predicted layout exceeds the lithographically designed layout.

5. The method according to any one of claims 1 to 3, characterized in that: The preset number of iterations is less than the preset number.

6. A photoresist model training device, characterized in that: The device comprises: An acquisition module, used to acquire a photolithography design layout, a mask layout, and a set of photolithography process parameter information affecting the photolithography design layout; A construction module, configured to construct an initial photoresist model according to a first parameter in the set; A training module, used for performing a first training of a preset number of iterations on an initial photoresist model according to a mask layout and a photolithography design layout to obtain a first photoresist model; A screening module, used for screening the indicator value of the graphic indicator in the last iteration process from the training log of the first training; A loop module is used to update the parameters in the initial photoresist model to the second parameters according to the set to obtain the updated initial photoresist model when it is determined that the index value of the graphic index is greater than a preset threshold, and return to the first training of the initial photoresist model for a preset number of iterations according to the mask layout and the lithography design layout to obtain the first photoresist model, until the index value meets the preset threshold, and a trained photoresist model is obtained; the first parameter and the second parameter are not completely the same.

7. A photoresist model training device, characterized in that: The device comprises: a processor and a memory storing computer program instructions; When the processor executes the computer program instructions, the method for training the photoresist model as described in any one of claims 1 to 5 is implemented.

8. 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 a processor, the method for training a photoresist model as described in any one of claims 1 to 5 is implemented.

9. 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 photoresist model training method as described in any one of claims 1 to 5.

Images