A mask pattern determination method, device, medium and product

Abstract

The present application discloses a mask pattern determination method, device, medium and product, which are applied to the field of semiconductor technology. In this method, the etching deviation is determined by the first etching pattern and the first photolithography pattern, and the first etching pattern is obtained based on the fusion of the first sub-image and the second sub-image. The first sub-image is generated by the physical effect simulation unit based on the first photolithography pattern, and the second sub-image is generated by the neural network unit based on the first photolithography pattern. Among them, the neural network unit can effectively improve the etching model's ability to fit the data, thereby improving the accuracy of the etching model to obtain an accurate first etching deviation. At the same time, the physical effect simulation unit of etching simulates the actual physical effect, which can prevent the etching model from overfitting.

Description

Technical Field

[0001] The present application belongs to the field of semiconductor technology, and in particular relates to a mask pattern determination method, device, medium and product. Background Art

[0002] The most core step in semiconductor chip manufacturing is to transfer the chip design pattern to the silicon wafer. Among the many process steps in chip manufacturing, the processes directly related to pattern transfer are mainly photolithography and etching. Both the photolithography process and the etching process will produce deviations, resulting in differences between the photolithography pattern, the etching pattern and the mask pattern. Therefore, when designing the mask pattern, it is necessary to compensate for the photolithography deviation and the etching deviation. At present, the photolithography deviation is mainly compensated by optical proximity correction (OPC). As for the etching deviation, the current main method is to establish an etching deviation table to save the etching deviation corresponding to different graphics, and then match the corresponding etching deviation in the etching deviation table based on the corresponding graphic style. For example, the corresponding etching deviation is determined according to the line width (width) and spacing (space) of the edge of the current polygon; and then the etching deviation compensation is completed.

[0003] However, etching differs from photolithography in that its physical and chemical processes are more complex. For patterns with varying line widths and spacing, the etch deviation will vary. For simple patterns, current methods based on etch deviation tables are suitable. However, in actual production, the line density of the pattern also affects the etch deviation. For complex patterns, current methods based on etch deviation table searches struggle to achieve good results, resulting in an inability to accurately determine the etch deviation, and consequently, the final designed mask pattern fails to meet actual requirements. Summary of the Invention

[0004] The embodiments of the present application provide a mask pattern determination method, device, medium and product, which can accurately obtain the first etching deviation of different photolithography patterns through an etching model, and then determine the actually required mask pattern.

[0005] In one aspect, an embodiment of the present application provides a method for determining a mask pattern, comprising:

[0006] Determining a first mask pattern based on a first target etching pattern;

[0007] Obtaining a first photolithography pattern after the first mask pattern is photolithographically processed;

[0008] Inputting the first photolithography pattern into at least one physical effect simulation unit of an etching model to obtain at least one first sub-image, and inputting the first photolithography pattern into a neural network unit of the etching model to obtain a second sub-image; the neural network unit is trained based on a photolithography pattern sample and a corresponding etching image label;

[0009] fusing the at least one first sub-image and the second sub-image based on the fusion unit of the etch model to obtain a first etched pattern after etching the first photolithographic pattern;

[0010] determining a first etching deviation of the first photolithographic pattern based on the first etching pattern and the first photolithographic pattern;

[0011] A first target mask pattern is determined based on the first etching deviation and the first target etching pattern.

[0012] On the other hand, determining a first target mask pattern based on the first etching deviation and the first target etching pattern includes:

[0013] Compensating the first target etch pattern based on the first etch deviation to obtain a first target photolithography pattern;

[0014] performing optical proximity effect correction based on the first target lithography pattern to obtain a second mask pattern;

[0015] If the first etching deviation does not satisfy the first preset condition, updating the first mask pattern to the second mask pattern; and returning to the step of obtaining the first photolithography pattern after the first mask pattern is photolithographically processed, until the first etching deviation satisfies the first preset condition;

[0016] When the first etching deviation satisfies the first preset condition, the current second mask pattern is determined as the first target mask pattern.

[0017] On the other hand, determining the first mask pattern based on the first target etching pattern includes:

[0018] Determining a corresponding second etching deviation based on the first target etching pattern and a first corresponding relationship; wherein the first corresponding relationship is a corresponding relationship between the etching pattern and the etching deviation;

[0019] Based on the second etching deviation, compensating the first target etching pattern to obtain the corresponding first target photolithography pattern;

[0020] Optical proximity effect correction is performed based on the first target photolithography pattern to obtain the first mask pattern.

[0021] On the other hand, after the fusion unit based on the etching model fuses the at least one first sub-image and the second sub-image, the method further includes:

[0022] Acquire a first target etching pattern corresponding to the first mask pattern;

[0023] constructing a training sample according to the first target etching pattern and the first etching pattern;

[0024] Model training is performed based on the training samples to obtain a photolithography compensation and photolithography etching model.

[0025] On the other hand, after performing model training according to the training samples to obtain the photolithography compensation and photolithography etching models, the method further includes:

[0026] determining a second target photolithography pattern based on the second target etching pattern;

[0027] Inputting the second target lithography pattern into the lithography compensation and lithography etching model to obtain a second etching pattern, and inputting the second target lithography pattern into a pre-trained lithography compensation and lithography model to obtain a second lithography pattern;

[0028] determining a third etching deviation based on the second etching pattern and the second photolithography pattern;

[0029] When the third etching deviation does not satisfy the second preset condition, compensating the second target etching pattern based on the third etching deviation to obtain a corrected second target photolithography pattern;

[0030] Updating the second target lithography pattern to the corrected second target lithography pattern; and returning to the steps of inputting the second target lithography pattern into the lithography compensation and lithography etching model to obtain a second etched pattern, and inputting the second target lithography pattern into the pre-trained lithography compensation and lithography model to obtain a second lithography pattern, until the third etch deviation satisfies the second preset condition;

[0031] When the third etching deviation satisfies the second preset condition, a second target mask pattern is determined based on the current corrected second target photolithography pattern.

[0032] On the other hand, determining the second target photolithography pattern based on the second target etch pattern includes:

[0033] Determining a corresponding fourth etching deviation based on the second target etching pattern and the first corresponding relationship, wherein the first corresponding relationship is a corresponding relationship between the etching pattern and the etching deviation;

[0034] Based on the fourth etching deviation, the second target etching pattern is compensated to obtain the corresponding second target photolithography pattern.

[0035] On the other hand, before inputting the first photolithography pattern into at least one physical effect simulation unit of the etching model to obtain at least one first sub-image, and inputting the first photolithography pattern into the neural network unit of the etching model to obtain a second sub-image, the method further includes:

[0036] Obtaining the photolithography pattern sample and the corresponding etching image label;

[0037] Inputting the photolithography pattern sample into the at least one physical effect simulation unit to obtain at least one third sub-image, and inputting the photolithography pattern sample into the initial neural network unit to obtain a fourth sub-image;

[0038] fusing the at least one third sub-image and the fourth sub-image based on the fusion unit to obtain a second etched image of the photolithography pattern sample after etching;

[0039] Obtaining a size difference between a first graphic key size of the etched image label and a second graphic key size of the second etched image;

[0040] Based on the size difference, training the initial neural network unit to obtain the neural network unit;

[0041] The etching model is determined based on the neural network unit, the physical effect simulation unit and the fusion unit.

[0042] In another aspect, an embodiment of the present application provides a mask pattern determination device, comprising: a processor and a memory storing computer program instructions;

[0043] When the processor executes the computer program instructions, the mask pattern determination method as described above is implemented.

[0044] On the other hand, an embodiment of the present application provides a computer-readable storage medium having computer program instructions stored thereon. When the computer program instructions are executed by a processor, the mask pattern determination method as described above is implemented.

[0045] On the other hand, an embodiment of the present application provides a computer program product. When instructions in the computer program product are executed by a processor of an electronic device, the electronic device executes the mask pattern determination method as described above.

[0046] An embodiment of the present application provides a method for determining a mask pattern. In this solution, the etching deviation used for etching deviation compensation is determined by a first etching pattern and a first photolithography pattern, and the first etching pattern is obtained based on the fusion of a first sub-image and a second sub-image. The first sub-image is generated by a physical effect simulation unit based on the first photolithography pattern, and the second sub-image is generated by a neural network unit based on the first photolithography pattern. Among them, the neural network unit can effectively improve the etching model's ability to fit the data, improve the accuracy of the etching model, and can obtain an accurate first etching deviation, thereby ensuring the final determination of the mask pattern actually required. At the same time, the physical effect simulation unit of etching simulates the actual physical effect, which can prevent the etching model from overfitting. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] In order to more clearly illustrate the technical solutions 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.

[0048] Figure 1 A schematic diagram showing a flow chart of a method for determining a mask pattern provided by one embodiment of the present application is shown;

[0049] Figure 2 A schematic diagram of a model simulation process provided by an embodiment of the present application is shown;

[0050] Figure 3 A first flow chart of designing a first target mask pattern according to an embodiment of the present application is shown;

[0051] Figure 4 A second flow chart of designing a first target mask pattern according to an embodiment of the present application is shown;

[0052] Figure 5 A first flow chart of designing a second target mask pattern according to an embodiment of the present application is shown;

[0053] Figure 6 A second flow chart of designing a second target mask pattern according to an embodiment of the present application is shown;

[0054] Figure 7 A schematic diagram of the training process of the etching model provided by one embodiment of the present application is shown;

[0055] Figure 8 A schematic structural diagram of a mask pattern determination device provided in an embodiment of the present application is shown;

[0056] Figure 9 A schematic diagram of the hardware structure of a mask pattern determination device provided in an embodiment of the present application is shown. DETAILED DESCRIPTION

[0057] 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 merely to provide a better understanding of the present application by illustrating the examples of the present application.

[0058] 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 "comprise", "include" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device that includes a series of elements includes not only those elements, but also other elements that are not explicitly listed, or also includes elements that are inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the sentence "comprise..." does not exclude the presence of other identical elements in the process, method, article or device that includes the element.

[0059] In the current mainstream integrated circuit production process, photolithography involves chemically transforming photoresist under exposure to light of a specific wavelength. Development then transfers the pattern designed on the mask into the photoresist topography on the silicon wafer. Etching, on the other hand, selectively removes unwanted material with the help of the photoresist topography, ultimately creating the desired fine patterns on the silicon wafer.

[0060] As chip technology continues to evolve, the size of designed patterns has become much smaller than the wavelength of photolithography (193nm), leading to the optical proximity effect and resulting in photolithography deviation. To compensate for this deviation, OPC is required.

[0061] During the integrated circuit manufacturing process, etching is required after photolithography. This etching process can cause etch deviation, which means that the line width of the photoresist before and after etching is inconsistent. For example, when a wafer contains both sparse and dense patterns to be etched, the etch rate of the dense areas is lower than that of the sparse areas. This is called the micro-loading effect. For another example, when etching high-aspect-ratio structures, such as deep holes or deep trenches, the smaller holes or trenches have a lower etch rate than the larger ones. This is called the aperture effect.

[0062] As can be seen, etching different areas will correspond to different etching rates. This will not only cause the overall pattern size to change after etching, but more importantly, patterns of the same size after photolithography will also have different sizes after etching. When designing the mask pattern, etching deviation must be considered. Otherwise, even if the size of the lithographic pattern obtained after photolithography exposure meets the expected size, it will still deviate from the target size after etching.

[0063] For etching bias, the current approach is to create a bias table to store the corresponding etching biases for different graphics. Based on the corresponding graphic style, the corresponding etching bias is matched in the bias table. The current bias table mainly determines the corresponding etching bias based on the line width and spacing of the current polygon. For simple graphics, this can barely meet the requirements, but as the graphics become more complex, the accuracy of the traditional method decreases.

[0064] For two edges with identical line widths and spacing, if the surrounding pattern density differs, the resulting etch bias will also differ. However, matching the etch bias using the existing bias-table approach inevitably results in errors. With the continuous evolution of semiconductor technology nodes, the demand for pattern transfer (lithography and etching) precision is becoming increasingly stringent; traditional methods cannot meet these demands.

[0065] The accuracy of the Bias-Table-based approach is limited. In order to solve this problem, the present application proposes to establish an etching model to simulate the etching process. After simulating the etching image, the etching deviation can be determined based on the graphics in the etching image. First, a physical effect simulation unit Term can be established to establish a partial model based on the physical effects actually generated during the etching process. Since the accuracy of etching simulation performed only by Term is insufficient, on this basis, in order to further improve the accuracy of the etching model, the present application also adds a neural network unit to the etching model, that is, introduces artificial intelligence (AI), and uses AI to assist in etching modeling, so that the etching model has higher accuracy, and thus can determine the accurate etching deviation.

[0066] Based on this, the embodiments of the present application provide a method, device, medium and product for determining a mask pattern. The following first introduces the method for determining a mask pattern provided by the embodiments of the present application. Figure 1 FIG. 1 shows a flow chart of a method for determining a mask pattern according to an embodiment of the present application. Figure 1 As shown, the method may include the following steps: S101 to S106.

[0067] S101: Determine a first mask pattern based on a first target etching pattern.

[0068] This application is often used in mask pattern design scenarios. Therefore, before obtaining a first lithography pattern after the first mask pattern undergoes lithography, a first target etch pattern can be obtained, and the first mask pattern can be determined based on the first target etch pattern.

[0069] In the mask pattern design scenario, the first target etch pattern is the actual desired wafer pattern. As an optional implementation, etch deviation compensation and OPC operations can be performed on the first target etch pattern to obtain the first mask pattern. In this case, the etch deviation can be determined using traditional methods. However, since the accuracy of the etch deviation determined by traditional methods is low, this implementation method, after obtaining the first mask pattern, re-obtains the first etch deviation based on this method. Then, the first target mask pattern can be re-determined based on the first etch deviation, and the first target mask pattern is used as the final designed mask pattern.

[0070] S102: Obtain a first photolithography pattern after the first mask pattern is photolithographically processed.

[0071] The first mask pattern is a pattern on the reticle, which can be a pattern in the design process or a pattern actually existing on the reticle. After the reticle containing the first mask pattern undergoes a photolithography process or a photolithography process simulation, a first photolithography image is obtained. The pattern in the first photolithography image is the first photolithography pattern.

[0072] This application is often used in mask pattern design scenarios. During the mask pattern design process, it is necessary to first obtain the desired wafer pattern (i.e., the pattern on the wafer after processes such as photolithography and etching), then perform etching deviation compensation and OPC on the wafer pattern to obtain the mask pattern; the above process is a common mask pattern design process. As some feasible implementations, the first mask pattern mentioned in this application can be the mask pattern mentioned above.

[0073] S103: Inputting the first photolithography pattern into at least one physical effect simulation unit of the etching model to obtain at least one first sub-image, and inputting the first photolithography pattern into the neural network unit of the etching model to obtain a second sub-image.

[0074] The etching model provided in the embodiment of the present application is used to process an image to simulate the etching process, thereby obtaining an etching image after etching. The first photolithography pattern obtained above mainly represents the graphic style and cannot be directly input into the etching model. Therefore, in order to simulate the etching process, a corresponding image needs to be generated. In practical applications, a processor can directly generate a corresponding optical image based on the graphic style of the first mask pattern, and then perform etching simulation based on the optical image of the first photolithography pattern to generate a corresponding sub-image.

[0075] The etching model in this embodiment consists of a neural network unit and at least one physical effect simulation unit.

[0076] The physical effect simulation unit simulates some of the physical effects of the actual etching process, such as microscopic loading effects and aperture effects. By inputting the mask pattern into different physical effect simulation units, a corresponding processed first sub-image can be obtained. For example, Gaussian convolution terms can be used to simulate the diffusion process.

[0077] The neural network unit is trained based on lithography pattern samples and corresponding etching image labels. Incorporating the neural network unit into the etching model significantly improves the model's ability to fit data. This solves the problem of existing modeling methods being unable to quickly obtain good model calibration results based on measurement results due to the complex etching process, thereby improving the speed and accuracy of model calibration.

[0078] In addition, the neural network unit may be overfitted. In this implementation, the physical effect simulation unit simulates the actual physical effect, which plays a role in preventing the model from overfitting. Moreover, when training the neural network unit, the model training can be based on a large amount of scanning electron microscope (SEM) image data, which can further reduce the problem of overfitting of the application network model.

[0079] S104: A fusion unit based on the etching model fuses at least one first sub-image and a second sub-image to obtain a first etching pattern after etching the first photolithography pattern.

[0080] After obtaining the first sub-image output by the physical effect simulation unit and the second sub-image output by the neural network unit, it is necessary to fuse the images to obtain the first etched image after the first photolithography pattern is etched. The fusion idea of ​​the etching model can be specifically referred to the following formula:

[0081]

[0082] Among them, OutputImage is the first etching image, InputImage is the optical image of the input etching model, Term i (InputImage) is the first sub-image, n is the number of first sub-images, and Neurom_NET(InputImage) is the second sub-image.

[0083] Figure 2 FIG. 1 shows a schematic diagram of a model simulation process provided by an embodiment of the present application. Figure 2As shown, a first photolithographic pattern 201 is first acquired, and then an optical image 202 of the first photolithographic pattern 201 is generated. Optical image 202 is input into each physical effect simulation unit to obtain corresponding first sub-images 203. Optical image 202 is then input into a neural network unit to obtain a second sub-image 204. Finally, a fusion unit based on an etching model fuses the first sub-images 203 and the second sub-image 204 to obtain a first etched image 205 after the first photolithographic pattern is etched.

[0084] For the first etched image obtained by fusing the first sub-image and the second sub-image, a first etched pattern is extracted from the first etched image. As an optional embodiment, the first etched image can be binarized based on a preset threshold to obtain the first etched pattern (i.e., etched outline).

[0085] S105: Determine a first etching deviation of the first photoresist pattern based on the first etching pattern and the first photoresist pattern.

[0086] After extracting the first etched pattern, the first etched pattern can be compared with the original first photolithographic pattern to identify any differences between the two and determine the difference, i.e., the etch deviation. In practical applications, the pattern is typically broken up, and then the first etch deviation corresponding to each edge is determined when determining the first etch deviation.

[0087] S106: Determine a first target mask pattern based on the first etching deviation and the first target etching pattern.

[0088] The specific implementation method for determining the first target mask pattern based on the first etch deviation and the first target etch pattern is not limited; a corresponding method can be selected based on actual circumstances. As an optional embodiment, the first target etch pattern can be compensated based on the first etch deviation to obtain a target photolithography pattern; then, optical proximity effect correction can be performed based on the target photolithography pattern to obtain the first target mask pattern.

[0089] In addition, after obtaining the first etching deviation, the first etching deviation and the etching deviation obtained based on the traditional scheme can be compared. When the difference between the two is small, it indicates that the etching deviation obtained based on the traditional scheme is sufficiently accurate. At this time, the first mask pattern can be directly used as the first target mask pattern.

[0090] Furthermore, as mentioned above, a pattern is usually broken into multiple edges, each of which corresponds to a first etching deviation. Therefore, as an optional implementation, the above process can be performed sequentially for each edge.

[0091] Since the etching deviation determined in the traditional solution is not accurate, in this implementation, after the first mask pattern is determined, the first etching deviation corresponding to the first mask pattern will be determined based on the etching model proposed above. Since the first etching deviation obtained based on the etching model is relatively accurate, a first target mask pattern that better meets actual needs can be determined.

[0092] Furthermore, in actual applications, because the OPC script, lithography compensation, and lithography model are responsible for generating all mask data for the process layer corresponding to this technology node, they are all closely linked and cannot be easily modified. Therefore, during actual process development and yield improvement of specific chip products, etch scripts are frequently adjusted. Therefore, in practice, when the etch script changes, the aforementioned etch model can be dynamically adjusted based on the collected silicon wafer data.

[0093] An embodiment of the present application provides a method for determining a mask pattern, wherein the etching deviation is determined by a first etching pattern and a first photolithography pattern, and a first etching image corresponding to the first etching pattern is obtained by fusing a first sub-image and a second sub-image. The first sub-image is generated by a physical effect simulation unit based on the first photolithography pattern, and the second sub-image is generated by a neural network unit based on the first photolithography pattern. Among them, the neural network unit can effectively improve the etching model's ability to fit the data, thereby improving the accuracy of the etching model to obtain an accurate first etching deviation. At the same time, the physical effect simulation unit of etching simulates the actual physical effect, which can prevent the etching model from overfitting.

[0094] The above embodiment mentions that a first target mask pattern can be determined based on a first etch deviation and a first target etch pattern, and provides a specific method for determining this. However, in actual applications, when initially determining the first etch deviation, the first photolithographic pattern input into the etch model is obtained based on traditional methods, which may be less accurate. This may result in the accuracy of the obtained first etch deviation not meeting requirements. Therefore, another feasible implementation is provided herein. Figure 3 A first flow chart of designing a first target mask pattern provided by an embodiment of the present application is shown.

[0095] like Figure 3 As shown, S106 may include the following steps:

[0096] S1061: Based on the first etching deviation, the first target etching pattern is compensated to obtain a first target photolithography pattern.

[0097] S1062: Perform optical proximity effect correction based on the first target photolithography pattern to obtain a second mask pattern.

[0098] S1063: Determine whether the first etching deviation does not meet the first preset condition; if the first etching deviation does not meet the first preset condition, execute S1064; if the first etching deviation meets the first preset condition, execute S1065.

[0099] S1064: Update the first mask pattern to the second mask pattern; and return to S102.

[0100] S1065: Determine the final second mask pattern as the first target mask pattern.

[0101] This implementation further improves the accuracy of the determined first etch deviation, thereby ensuring that the first target mask pattern better meets actual requirements. In this implementation, multiple iterations are performed to update the first mask pattern to a more accurate second mask pattern. Based on the second mask pattern, an even more accurate first etch deviation can be obtained. This cycle can continuously improve the accuracy of the second mask pattern.

[0102] As an optional embodiment, the first preset condition can be that the difference between the two corresponding first etching deviations in two adjacent iterations is less than a threshold. The threshold value here can be set as needed. If the difference between the first etching deviations corresponding to the two adjacent iterations is not large, it indicates that the first etching deviation obtained at this time is sufficiently accurate, so the iteration can be stopped and the final second mask pattern is determined to be the first target mask pattern.

[0103] Here, a specific implementation method for designing the first target mask pattern is provided. Figure 4 FIG. 2 shows a second flow chart of designing a first target mask pattern according to an embodiment of the present application. Figure 4 As shown, a first target etch pattern 401 is first obtained. An etch deviation can be determined based on a conventional solution and compensated for the first target etch pattern 401 to obtain a first target photoresist pattern 402. After OPC is performed, a mask pattern is obtained. A photoresist simulation is performed to obtain a first photoresist pattern. An etch model 403 is then input to perform an etch simulation to obtain the first etch pattern. A first etch deviation is obtained based on the first photoresist pattern and the first etch pattern.

[0104] Furthermore, after obtaining the first etching deviation, the first target etching pattern 401 is compensated based on the first etching deviation to obtain a new first target photoresist pattern 402. This process is repeated until the first etching deviation meets the first preset condition, and the final mask pattern is determined as the first target mask pattern.

[0105] In the above embodiment, when the first etch bias is initially determined, the first photolithographic pattern input into the etch model is obtained using a conventional method, which results in low accuracy. This may result in the first etch bias not being accurate enough to meet requirements. Therefore, in this implementation, the first etch bias is continuously calibrated through multiple iterations, resulting in a higher accuracy of the final first target mask pattern.

[0106] As mentioned above, when determining the etching deviation using the etching model provided in this application, it is necessary to obtain the first mask pattern in advance. However, in the process from the first target etching pattern to the first mask pattern, it is necessary to obtain the etching deviation to compensate for the first target etching pattern, which cannot be achieved based on the etching model. Therefore, in this implementation, the first etching deviation is determined by establishing a first corresponding relationship. As an optional embodiment, determining the first mask pattern based on the first target etching pattern may include:

[0107] Determining a corresponding second etching deviation based on the first target etching pattern and the first corresponding relationship;

[0108] Based on the second etching deviation, compensating the first target etching pattern to obtain a corresponding first target photolithography pattern;

[0109] An optical proximity effect correction is performed based on the first target photolithography pattern to obtain a first mask pattern.

[0110] In this embodiment, the first correspondence is the correspondence between the etched pattern and the etch deviation. As an optional implementation, the first correspondence can be implemented in a table format, which stores the correspondence between different graphic styles (including line width, spacing, etc.) and etch deviations. When the etch deviation needs to be determined, the graphic style corresponding to the first target etched pattern is first matched from the table, and then the corresponding second etch deviation is found.

[0111] In addition, in practical applications, the first correspondence can be corrected by using the etching deviation obtained from the etching model to improve accuracy.

[0112] In this implementation, the second etching deviation is first determined by the first corresponding relationship. Although the etching deviation obtained in this way has low accuracy, it can meet the basic accuracy requirement, and the solution is simple and efficient.

[0113] In actual applications, the process from the target etching pattern to the etching pattern requires etching deviation compensation, OPC, and simulation, which is time-consuming. Therefore, an optional implementation method is provided here. After the fusion unit based on the etching model fuses at least one first sub-image and the second sub-image, the method may further include:

[0114] Obtaining a first target etching pattern corresponding to the first mask pattern;

[0115] Constructing a training sample according to the first target etching pattern and the first etching pattern;

[0116] Model training is performed based on training samples to obtain lithography compensation and lithography etching models.

[0117] In this implementation, the lithography compensation and lithography etch models are used to complete processes such as OPC, lithography simulation, and etch simulation. The etch model described above can be used to obtain corresponding training data. Specifically, based on the etch model, a first etch pattern corresponding to a first mask pattern is obtained. Since the first mask pattern corresponds to a first target etch pattern, training samples can be constructed based on the correspondence between the first target etch pattern and the first etch pattern, thereby performing model training to obtain the lithography compensation and lithography etch models.

[0118] In this implementation, the lithography compensation and etching models are directly trained to complete the process of converting the lithography pattern to the etched pattern. However, training these models requires a large amount of labeled data for the first etch pattern. In practical applications, acquiring labeled data using a scanning electron microscope is extremely inefficient and cannot meet this requirement. Therefore, this implementation uses the etching model described above to obtain a large amount of training sample data, and then trains the lithography compensation and etching models.

[0119] In the above embodiment, it is mentioned that in order to obtain the final target mask pattern, the value of the first etch deviation can be calibrated multiple times. However, each iteration requires etch deviation compensation, OPC, and simulation, which is time-consuming and affects production efficiency. Therefore, a specific implementation method is provided here. Figure 5 FIG. 1 shows a first flow chart of designing a second target mask pattern according to an embodiment of the present application. Figure 5 As shown, after model training is performed based on the training samples to obtain the photolithography compensation and photolithography etching models, the method may further include the following steps:

[0120] S501: Determine a second target photolithography pattern based on a second target etching pattern.

[0121] S502: Inputting the second target lithography pattern into the lithography compensation and lithography etching model to obtain a second etching pattern, and inputting the second target lithography pattern into the pre-trained lithography compensation and lithography model to obtain a second lithography pattern.

[0122] In this implementation, the lithography compensation and lithography etching model are used to complete the processes of OPC, lithography simulation, etching simulation, etc. The lithography compensation and lithography model are used to implement the steps of OPC and lithography simulation.

[0123] Currently, when determining the second etch pattern from the second target lithographic pattern, it is necessary to first perform OPC to obtain the corresponding mask pattern, and then perform lithography and etching simulation to obtain the second etch pattern. However, this implementation method can directly obtain the second etch pattern based on the second target lithographic pattern through lithography compensation and lithography-etching model.

[0124] Accordingly, currently, when determining the second lithographic pattern based on the second target lithographic pattern, it is necessary to first perform OPC to obtain the corresponding mask pattern, and then perform lithography simulation to obtain the second lithographic pattern. However, this implementation method can directly obtain the second lithographic pattern based on the second target lithographic pattern through lithography compensation and lithography model.

[0125] S503: Determine a third etching deviation based on the second etching pattern and the second photoresist pattern.

[0126] S504: Based on the third etching deviation, the second target etching pattern is compensated to obtain a corrected second target photolithography pattern.

[0127] S505: Determine whether the third etching deviation meets the second preset condition; if the third etching deviation does not meet the second preset condition, execute S506; if the third etching deviation meets the second preset condition, execute S507.

[0128] S506: Update the second target photolithography pattern to the corrected second target photolithography pattern; and return to S501.

[0129] S507: Determine a second target mask pattern based on the corrected second target photolithography pattern finally obtained.

[0130] Corresponding to the first target etching pattern mentioned above, in the design scenario of the mask pattern, the second target etching pattern in this implementation is the actual desired wafer pattern. The etching deviation of the first target etching pattern can be compensated to obtain the second target photolithography pattern.

[0131] As mentioned above, the pattern is usually interrupted, and each edge corresponds to a third etching deviation. Therefore, as an optional implementation, the above process can be performed sequentially for each edge separately.

[0132] As an optional embodiment, the second preset condition can be that the difference between the two corresponding third etching deviations in two adjacent iterations is less than a threshold. The threshold value here can be set as needed. If the difference between the third etching deviations corresponding to the two adjacent iterations is not large, it indicates that the third etching deviation obtained at this time is sufficiently accurate, and therefore the iteration can be stopped.

[0133] When performing etching deviation compensation for the first time, the etching deviation can be determined by the traditional scheme. However, since the etching deviation determined by the traditional scheme has low accuracy, this implementation method updates the third etching deviation through multiple iterations of photolithography compensation and photolithography etching model, and photolithography compensation and photolithography model, and finally obtains a sufficiently accurate third etching deviation, thereby obtaining an accurate second target photolithography pattern, and then performing OPC to obtain the actually required second target mask pattern, and finally using the second target mask pattern as the final designed mask pattern.

[0134] Here, a specific implementation method for designing the second target mask pattern is provided. Figure 6 FIG. 2 shows a second flow chart of designing a second target mask pattern according to an embodiment of the present application. Figure 6 As shown, the second target etch pattern 601 is first obtained, and the etching deviation can be determined based on the traditional scheme and the second target etch pattern 601 is compensated to obtain the second target photolithography pattern 602. The second target photolithography pattern 602 is input into the photolithography compensation and photolithography etching model 603 and the photolithography compensation and photolithography model 604 respectively, and the second photolithography pattern and the second etched pattern are obtained accordingly, and then the third etching deviation is obtained.

[0135] Furthermore, after obtaining the third etching deviation, the second target etching pattern 601 is compensated based on the third etching deviation to obtain a new second target photolithography pattern 602, and the above process is repeated until the third etching deviation meets the second preset condition. Finally, based on the final obtained second target photolithography pattern 602, OPC is performed to obtain the actually required second target mask pattern.

[0136] In this implementation, the lithography compensation and lithography etching models established by the above-mentioned embodiments and the pre-trained lithography compensation and lithography models are used to directly complete the process from the second target lithography pattern to the second etching pattern and the second lithography pattern, thereby saving a lot of time in iteration, being able to quickly determine the second target mask pattern that meets the requirements, and improving production efficiency.

[0137] As mentioned above, when performing etching deviation compensation for the first time, the etching deviation can be determined by a conventional solution. As an optional embodiment, determining the second target photolithography pattern based on the second target etching pattern may include:

[0138] Determining a corresponding fourth etching deviation based on the second target etching pattern and the first corresponding relationship;

[0139] Based on the fourth etching deviation, the second target etching pattern is compensated to obtain a corresponding second target photolithography pattern.

[0140] In this embodiment, the first correspondence is the correspondence between the etched pattern and the etch deviation. As an optional implementation, the first correspondence can be implemented in a table format, which stores the correspondence between different graphic styles (including line width, spacing, etc.) and etch deviations. When the etch deviation needs to be determined, the graphic style corresponding to the second target etched pattern is first matched from the table, and then the corresponding fourth etch deviation is found.

[0141] In this implementation, the fourth etching deviation is first determined by the first corresponding relationship. Although the etching deviation obtained in this way has low accuracy, it can meet the basic accuracy requirement, and the solution is simple and efficient.

[0142] As mentioned in the above embodiment, the etching model provided by this application includes a neural network unit and at least one physical effect simulation unit. Among them, the neural network unit needs to be trained to ensure that the etching model outputs accurate results. Therefore, an optional implementation method is provided here. Figure 7 FIG. 1 shows a schematic diagram of the training process of the etching model provided by an embodiment of the present application. Figure 7 As shown, before using the etching model, the method further includes the following steps:

[0143] S701: Obtain a photolithography pattern sample and a corresponding etching image label.

[0144] S702: Input the photolithography pattern sample into at least one physical effect simulation unit to obtain at least one third sub-image, and input the photolithography pattern sample into the initial neural network unit to obtain a fourth sub-image.

[0145] S703: Fusing at least one third sub-image and the fourth sub-image based on a fusing unit to obtain a second etched image of the photolithography pattern sample after etching.

[0146] S704: Obtain a size difference between a first graphic key size of the etching image label and a second graphic key size of the second etching image.

[0147] S705: Based on the size difference, train the initial neural network unit to obtain a neural network unit.

[0148] S706: Determine the etching model based on the neural network unit, the physical effect simulation unit and the fusion unit.

[0149] In this implementation, the photolithography pattern samples correspond to the etched image labels, and the etched image labels are obtained after the photolithography pattern samples are etched. Therefore, the neural network unit is trained by the photolithography pattern samples and the corresponding etched image labels, so that the etching model can output accurate results.

[0150] The first graphic key size mentioned in this embodiment is the key size corresponding to the graphic in the etching image label, and the second graphic key size is the key size corresponding to the graphic in the second etching image, which can be calculated based on the corresponding graphics. The calculated first graphic key size and the second graphic key size are compared to obtain the size difference, and then the model is judged based on the evaluation function to determine whether it has converged. If the model does not converge, the parameters of the initial neural network unit can be iteratively adjusted multiple times to finally obtain a neural network unit that meets the requirements. In addition, in actual applications, the combination of physical effect simulation units can be adjusted through the above-mentioned training method to optimize the entire etching model.

[0151] In the process of judging whether the model has converged based on the evaluation function, evaluation can also be implemented for each edge of the graph. As an optional implementation method, evaluation points can be set on the edges that need to be evaluated, and then the positions of the evaluation points at the same position of the two graphs can be compared. The evaluation function value is determined based on the distance difference, and then whether the output result of the model is accurate can be judged.

[0152] The above embodiment also mentioned that in practice, etching scripts often change. When the etching script changes, the above etching model can be dynamically adjusted based on the collected silicon wafer data. Because the present application can train the model using actual data, a new etching model can be quickly obtained, thereby improving production efficiency.

[0153] Furthermore, automated continuous modeling can be achieved by continuously collecting SEM images from the actual production process, automatically updating the etching model after process changes. For example, SEM images of wafers after etching in actual production can be obtained, and the pattern outlines of each SEM image can be extracted as etching image labels, and the corresponding lithography patterns can be used as lithography pattern samples for training the model.

[0154] This embodiment provides a training method for an etching model, in which the initial neural network unit is trained through lithography pattern samples and corresponding etching pattern labels. When there is a difference between the simulated image and the label image, the neural network unit is adjusted so that the etching model can output results consistent with reality.

[0155] Based on the mask pattern determination method provided in the above embodiment, the embodiment of the present application also provides a mask pattern determination device. Figure 8 FIG. 1 shows a schematic structural diagram of a mask pattern determination device provided by an embodiment of the present application. Figure 8 As shown, the device includes the following modules:

[0156] A determination module 801 is configured to determine a first mask pattern based on a first target etching pattern;

[0157] An acquisition module 802 is configured to acquire a first lithographic pattern after the first mask pattern is photolithographically processed;

[0158] Input module 803 is configured to input the first photolithography pattern into at least one physical effect simulation unit of an etching model to obtain at least one first sub-image, and input the first photolithography pattern into a neural network unit of the etching model to obtain a second sub-image; the neural network unit is trained based on a photolithography pattern sample and a corresponding etching image label;

[0159] a fusion module 804 configured to fuse the at least one first sub-image and the second sub-image based on a fusion unit of the etching model to obtain a first etching pattern after etching the first photolithographic pattern;

[0160] The determining module 801 is further configured to determine a first etching deviation of the first photolithographic pattern based on the first etching pattern and the first photolithographic pattern;

[0161] The determination module 801 is further configured to determine a first target mask pattern based on the first etching deviation and the first target etching pattern.

[0162] The device provided in the embodiment of the present application is the same as the method in the above embodiment, so the two have the same embodiments and beneficial effects, which will not be repeated here.

[0163] In some embodiments, the determination module 801 is specifically configured to:

[0164] Compensating a first target etched pattern based on a first etch deviation to obtain a first target photolithographic pattern;

[0165] performing optical proximity effect correction based on the first target lithography pattern to obtain a second mask pattern;

[0166] Updating the first mask pattern to a second mask pattern; and returning to the step of obtaining a first photolithography pattern after the first mask pattern is photolithographically processed, until the first etching deviation satisfies a first preset condition;

[0167] The final second mask pattern is determined as the first target mask pattern.

[0168] In this implementation, the value of the first etching deviation is continuously calibrated through multiple iterations, so that the accuracy of the final first target mask pattern is higher.

[0169] In some embodiments, the determination module 801 is specifically configured to:

[0170] Determining a corresponding second etching deviation based on the first target etching pattern and a first corresponding relationship; the first corresponding relationship is a corresponding relationship between the etching pattern and the etching deviation;

[0171] Based on the second etching deviation, compensating the first target etching pattern to obtain a corresponding first target photolithography pattern;

[0172] An optical proximity effect correction is performed based on the first target photolithography pattern to obtain a first mask pattern.

[0173] In this implementation, the second etching deviation is first determined by the first corresponding relationship, which is simple and highly efficient.

[0174] In some embodiments, the acquisition module 802 is further configured to acquire a first target etching pattern corresponding to the first mask pattern after the fusion unit based on the etching model fuses the at least one first sub-image and the second sub-image;

[0175] The mask pattern determination device further includes: an etching module for constructing a training sample based on the first target etching pattern and the first etching pattern;

[0176] The training module is used to train the model based on the training samples to obtain the lithography compensation and lithography etching models.

[0177] This implementation method uses the etching model mentioned above to obtain a large amount of training sample data, and then trains to obtain a more accurate lithography compensation and lithography etching model.

[0178] In some embodiments, the determination module 801 is further configured to determine a second target lithography pattern based on the second target etch pattern after performing model training according to the training samples to obtain the lithography compensation and lithography etching model;

[0179] The input module 803 is further configured to input the second target lithography pattern into the lithography compensation and lithography etching model to obtain a second etching pattern, and to input the second target lithography pattern into the pre-trained lithography compensation and lithography model to obtain a second lithography pattern;

[0180] The determining module 801 is further configured to determine a third etching deviation based on the second etching pattern and the second photolithography pattern;

[0181] The mask pattern determination device further includes: a compensation module for compensating the second target etch pattern based on the third etch deviation to obtain a corrected second target lithography pattern;

[0182] an updating module, configured to update the second target lithography pattern to a corrected second target lithography pattern; and return to the steps of inputting the second target lithography pattern into a lithography compensation and lithography etching model to obtain a second etched pattern, and inputting the second target lithography pattern into a pre-trained lithography compensation and lithography model to obtain a second lithography pattern, until the third etch deviation satisfies the second preset condition;

[0183] Based on the finally obtained corrected second target photolithography pattern, a second target mask pattern is determined.

[0184] This implementation saves a lot of time in iteration, can quickly determine a second target mask pattern that meets the requirements, and improves production efficiency.

[0185] In some embodiments, the determination module 801 is specifically configured to:

[0186] Determining a corresponding fourth etching deviation based on the second target etching pattern and the first corresponding relationship; the first corresponding relationship is a corresponding relationship between the etching pattern and the etching deviation;

[0187] Based on the fourth etching deviation, the second target etching pattern is compensated to obtain a corresponding second target photolithography pattern.

[0188] The solution for determining the etching deviation in this implementation is simple and highly efficient.

[0189] In some embodiments, the acquisition module 802 is further configured to acquire a photolithographic pattern sample and a corresponding etching image label before inputting the first photolithographic pattern into at least one physical effect simulation unit of the etching model to obtain at least one first sub-image, and inputting the first photolithographic pattern into the neural network unit of the etching model to obtain a second sub-image.

[0190] The input module 803 is further configured to input the lithography pattern sample into at least one physical effect simulation unit to obtain at least one third sub-image, and input the lithography pattern sample into the initial neural network unit to obtain a fourth sub-image.

[0191] The fusion module 804 is further configured to fuse the at least one third sub-image and the fourth sub-image based on the fusion unit to obtain a second etched image of the lithography pattern sample after etching;

[0192] The acquisition module 802 is further configured to acquire a size difference between a first graphic key size of the etched image label and a second graphic key size of the second etched image;

[0193] The training module is further used to train the initial neural network unit based on the size difference to obtain the neural network unit;

[0194] The determination module 801 is further used to determine the etching model according to the neural network unit, the physical effect simulation unit and the fusion unit.

[0195] This implementation method trains the initial neural network unit through lithography pattern samples and corresponding etching pattern labels, so that the etching model can output accurate results that are consistent with reality.

[0196] Figure 9 FIG. 1 shows a hardware structure diagram of a mask pattern determination device provided by an embodiment of the present application. Figure 9 As shown, the mask pattern determination device may include a processor 901 and a memory 902 storing computer program instructions.

[0197] Specifically, the processor 901 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.

[0198] The memory 902 may include a large capacity memory for data or instructions. By way of example and not limitation, the memory 902 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. Where appropriate, the memory 902 may include removable or non-removable (or fixed) media. Where appropriate, the memory 902 may be inside or outside the integrated gateway disaster recovery device. In a specific embodiment, the memory 902 is a non-volatile solid-state memory.

[0199] The memory 902 may include a read-only memory (ROM), a random access memory (RAM), a magnetic disk storage medium device, an optical storage medium device, a flash memory device, an electrical, optical or other physical / tangible memory storage device. Thus, generally, the memory includes one or more tangible (non-transitory) computer-readable storage media (e.g., a memory device) 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.

[0200] The processor 901 reads and executes computer program instructions stored in the memory 902 to implement any one of the mask pattern determination methods in the above embodiments.

[0201] In one example, the mask pattern determination device may further include a communication interface 903 and a bus 904. The processor 901, the memory 902, and the communication interface 903 are connected via the bus 904 and communicate with each other.

[0202] The communication interface 903 is mainly used to implement communication between various modules, devices, units and / or equipment in the embodiments of the present application.

[0203] The bus 904 includes hardware, software, or both that couples the components of the mask pattern determination device to each other. By way of example and not limitation, the bus may include an Accelerated Graphical Port (AGP) or other graphics bus, an Enhanced Industry Standard Architecture (EISA) bus, a Front Side Bus (FSB), a Hyper Transport (HT) interconnect, an Industry Standard Architecture (ISA) bus, an InfiniBand interconnect, a Low Pin Count (LPC) bus, a memory bus, a Micro Channel Architecture (MCA) bus, a Peripheral Component Interconnect (PCI) bus, a PCI-Express (PCI-X) bus, a Serial Advanced Technology Attachment (SATA) bus, a Video Electronics Standards Association Local Bus (VLB) bus, or other suitable buses, or a combination of two or more of these. Where appropriate, the bus 904 may include one or more buses. Although embodiments herein describe and illustrate a particular bus, this application contemplates any suitable bus or interconnect.

[0204] In addition, in conjunction with the mask pattern determination method in the above embodiments, embodiments of the present application may provide a computer storage medium for implementation. The computer storage medium stores computer program instructions; when the computer program instructions are executed by a processor, any of the mask pattern determination methods in the above embodiments is implemented.

[0205] An embodiment of the present application further provides a computer program product, including a computer program, which implements any one of the mask pattern determination methods in the above embodiments when the computer program is processed and executed.

[0206] It should be understood that the present application is not limited to the specific configurations and processes described above and illustrated in the figures. For the sake of brevity, a detailed description of known methods is omitted here. In the above embodiments, several specific steps are described and illustrated as examples. However, the method process of the present application is not limited to the specific steps described and illustrated. Those skilled in the art can make various changes, modifications, and additions, or change the order of the steps after understanding the spirit of the present application.

[0207] The functional blocks shown in the block diagram above can be implemented as hardware, software, firmware or a combination thereof. When implemented in hardware, they can be, for example, electronic circuits, ASICs, appropriate firmware, plug-ins, function cards, 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 communication link via 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, ROMs, flash memories, erasable ROMs (Erasable ROM, EROMs), floppy disks, compact disc read-only memory (Compact Disc Read-Only Memory, CD-ROMs), optical discs, hard disks, optical fiber media, radio frequency (RF) links, etc. The code segments can be downloaded via computer networks such as the Internet, intranets, etc.

[0208] 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. In other words, the steps can be performed in the order mentioned in the embodiments, or in a different order, or several steps can be performed simultaneously.

[0209] The above describes various aspects of the present disclosure with reference to the flowcharts and / or block diagrams of a mask pattern determination method, device, medium, and product according to embodiments of the present disclosure. It should be understood that each box in the flowchart and / or block diagram and the combination of boxes 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 functions / actions specified in one or more boxes in 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 is also 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 the specified function or action, or can be implemented by a combination of dedicated hardware and computer instructions.

[0210] The above content is only a specific implementation method of the present application. Those skilled in the art can clearly understand that for the convenience and brevity 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 scope of protection of the present application is not limited to this. Any person skilled in the art 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 scope of protection of the present application.

Claims

1. A method for determining a mask pattern, characterized in that: include: Determining a first mask pattern based on a first target etching pattern; Obtaining a first photolithography pattern after the first mask pattern is photolithographically processed; Inputting the first photolithography pattern into at least one physical effect simulation unit of an etching model to obtain at least one first sub-image, and inputting the first photolithography pattern into a neural network unit of the etching model to obtain a second sub-image; the neural network unit is trained based on a photolithography pattern sample and a corresponding etching image label; fusing the at least one first sub-image and the second sub-image based on the etching model to obtain a first etching pattern after etching the first photolithographic pattern, wherein the fusion unit based on the etching model performs summation processing on the at least one first sub-image and the second sub-image to obtain a first etching image, and extracting the first etching pattern from the first etching image; determining a first etching deviation of the first photolithographic pattern based on the first etching pattern and the first photolithographic pattern; A first target mask pattern is determined based on the first etching deviation and the first target etching pattern.

2. The mask pattern determination method according to claim 1, wherein: The determining a first target mask pattern based on the first etching deviation and the first target etching pattern includes: Compensating the first target etch pattern based on the first etch deviation to obtain a first target photolithography pattern; performing optical proximity effect correction based on the first target lithography pattern to obtain a second mask pattern; If the first etching deviation does not satisfy the first preset condition, updating the first mask pattern to the second mask pattern; and returning to the step of obtaining the first photolithography pattern after the first mask pattern is photolithographically processed, until the first etching deviation satisfies the first preset condition; When the first etching deviation satisfies the first preset condition, the current second mask pattern is determined as the first target mask pattern.

3. The mask pattern determination method according to claim 1, wherein: The determining the first mask pattern based on the first target etching pattern includes: Determining a corresponding second etching deviation based on the first target etching pattern and a first corresponding relationship; wherein the first corresponding relationship is a corresponding relationship between the etching pattern and the etching deviation; Based on the second etching deviation, compensating the first target etching pattern to obtain a corresponding first target photolithography pattern; Optical proximity effect correction is performed based on the first target photolithography pattern to obtain the first mask pattern.

4. The mask pattern determination method according to claim 1, wherein: After the fusion unit based on the etching model fuses the at least one first sub-image and the second sub-image, the method further includes: Acquire a first target etching pattern corresponding to the first mask pattern; constructing a training sample according to the first target etching pattern and the first etching pattern; Model training is performed based on the training samples to obtain a photolithography compensation and photolithography etching model.

5. The mask pattern determination method according to claim 4, wherein: After performing model training according to the training samples to obtain the photolithography compensation and photolithography etching models, the method further includes: determining a second target photolithography pattern based on the second target etching pattern; Inputting the second target lithography pattern into the lithography compensation and lithography etching model to obtain a second etching pattern, and inputting the second target lithography pattern into a pre-trained lithography compensation and lithography model to obtain a second lithography pattern; determining a third etching deviation based on the second etching pattern and the second photolithography pattern; When the third etching deviation does not satisfy the second preset condition, compensating the second target etching pattern based on the third etching deviation to obtain a corrected second target photolithography pattern; Updating the second target lithography pattern to the corrected second target lithography pattern; and returning to the steps of inputting the second target lithography pattern into the lithography compensation and lithography etching model to obtain a second etched pattern, and inputting the second target lithography pattern into the pre-trained lithography compensation and lithography model to obtain a second lithography pattern, until the third etch deviation satisfies the second preset condition; When the third etching deviation satisfies the second preset condition, a second target mask pattern is determined based on the current corrected second target photolithography pattern.

6. The mask pattern determination method according to claim 5, wherein: The determining of the second target photolithography pattern based on the second target etching pattern includes: Determining a corresponding fourth etching deviation based on the second target etching pattern and the first corresponding relationship, wherein the first corresponding relationship is a corresponding relationship between the etching pattern and the etching deviation; Based on the fourth etching deviation, the second target etching pattern is compensated to obtain the corresponding second target photolithography pattern.

7. The mask pattern determination method according to any one of claims 1 to 6, characterized in that: Before inputting the first photolithography pattern into at least one physical effect simulation unit of an etching model to obtain at least one first sub-image, and inputting the first photolithography pattern into a neural network unit of the etching model to obtain a second sub-image, the method further includes: Obtaining the photolithography pattern sample and the corresponding etching image label; Inputting the photolithography pattern sample into the at least one physical effect simulation unit to obtain at least one third sub-image, and inputting the photolithography pattern sample into the initial neural network unit to obtain a fourth sub-image; fusing the at least one third sub-image and the fourth sub-image based on the fusion unit to obtain a second etched image of the photolithography pattern sample after etching; Obtaining a size difference between a first graphic key size of the etched image label and a second graphic key size of the second etched image; Based on the size difference, training the initial neural network unit to obtain the neural network unit; The etching model is determined based on the neural network unit, the physical effect simulation unit and the fusion unit.

8. A mask pattern determination device, characterized in that: include: a processor and a memory storing computer program instructions; When the processor executes the computer program instructions, the mask pattern determination method according to any one of claims 1 to 7 is implemented.

9. 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 mask pattern determination method according to any one of claims 1 to 7 is implemented.

10. 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 is caused to execute the mask pattern determination method according to any one of claims 1 to 7.

Images