SRAF Placement Method, Device, Storage Medium and Electronic Device

Abstract

The present application discloses a method, apparatus, storage medium and electronic device for SRAF placement. Among them, the SRAF placement method includes obtaining the graphic features and environmental features of the target graphics in the via layer; generating cross features according to the graphic features and environmental features; constructing a multi-dimensional information matrix according to the graphic features, environmental features and cross features; inputting the multi-dimensional information matrix into the SRAF parameter prediction model to obtain SRAF placement parameters; and placing the SRAF according to the SRAF placement parameters. This solution can improve the accuracy of SRAF placement.

Description

Technical Field

[0001] The embodiments of the present application relate to the field of lithography technology, and particularly to a method, device, storage medium and electronic device for placing SRAF (Sub-Resolution Assist Features). Background Art

[0002] As semiconductor manufacturing processes continue to evolve towards smaller process nodes, the challenges faced by lithography technology are increasing. Especially in high-resolution lithography, the imaging accuracy of target patterns has a crucial impact on the performance of final devices. However, due to the diffraction effect of the optical system and fluctuations in process parameters, traditional lithography methods often struggle to achieve the desired pattern edge accuracy, thus affecting the performance and yield of chips.

[0003] To address the above problems, the Sub-Resolution Assist Features (SRAF) technology has been introduced into mask design. By adding assist features around the target pattern, SRAF improves the interference and diffraction effects during the lithography imaging process, enhancing the contrast of the pattern edge and line width control. However, traditional SRAF placement methods usually rely on fixed design rules or experience-based heuristic algorithms, suffering from problems such as the inability to precisely express the coupling relationship between patterns, local optimality, and poor generality, making it difficult to achieve high-precision placement of assist features. Summary of the Invention

[0004] The embodiments of the present application provide a method, device, storage medium and electronic device for placing SRAF, which can improve the accuracy of SRAF placement.

[0005] In a first aspect, the embodiments of the present application provide a method for placing SRAF, including:

[0006] Obtaining the pattern features and environmental features of the target pattern in the via layer;

[0007] Generating cross features according to the pattern features and the environmental features;

[0008] Constructing a multi-dimensional information matrix according to the pattern features, the environmental features and the cross features;

[0009] Inputting the multi-dimensional information matrix into an SRAF parameter prediction model to obtain SRAF placement parameters;

[0010] Placing SRAF according to the SRAF placement parameters.

[0011] In the SRAF placement method provided by the embodiments of the present application, the pattern features include critical dimension, first pattern spacing, second pattern spacing and edge offset, and the environmental features include adjacent edge spacing and local density.

[0012] In the SRAF placement method provided by the embodiments of the present application, the generating of the cross features according to the graphic features and the environmental features includes:

[0013] Combining the graphic features and the environmental features by using a mathematical operation method to generate cross features.

[0014] In the SRAF placement method provided by the embodiments of the present application, the combining of the graphic features and the environmental features by using a mathematical operation method to generate cross features includes:

[0015] Multiplying the critical dimension by the edge offset to obtain a first cross feature;

[0016] Dividing the first graphic spacing by the adjacent side spacing to obtain a second cross feature;

[0017] Multiplying the second graphic spacing by the local density to obtain a third cross feature.

[0018] In the SRAF placement method provided by the embodiments of the present application, the constructing of the multi-dimensional information matrix according to the graphic features, the environmental features and the cross features includes:

[0019] Converting the graphic features, the environmental features and the cross features into column vectors respectively;

[0020] Performing a normalization process on each of the column vectors;

[0021] Concatenating the normalized column vectors into a multi-dimensional information matrix in a preset order.

[0022] In the SRAF placement method provided by the embodiments of the present application, the SRAF parameter prediction model is a multi-variable linear regression model.

[0023] In the SRAF placement method provided by the embodiments of the present application, it further includes:

[0024] Constructing an SRAF parameter prediction model.

[0025] In a second aspect, the embodiments of the present application provide an SRAF placement device, including:

[0026] A feature acquisition unit, configured to acquire the graphic features and the environmental features of a target graphic in a via hole layer;

[0027] A feature generation unit, configured to generate cross features according to the graphic features and the environmental features;

[0028] A matrix construction unit, configured to construct a multi-dimensional information matrix according to the graphic features, the environmental features and the cross features;

[0029] A parameter prediction unit, configured to input the multi-dimensional information matrix into an SRAF parameter prediction model to obtain SRAF placement parameters;

[0030] An SRAF placement unit, configured to place SRAF according to the SRAF placement parameters.

[0031] In a third aspect, the present application provides a storage medium storing multiple instructions, and the instructions are adapted to be loaded by a processor to execute the SRAF placement method described in any one of the above.

[0032] In a fourth aspect, the present application provides an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the computer program, the SRAF placement method described in any one of the above is implemented.

[0033] In summary, the SRAF placement method provided by the embodiments of the present application includes obtaining the graphic features and environmental features of target graphics in a via layer; generating cross features according to the graphic features and the environmental features; constructing a multi-dimensional information matrix according to the graphic features, the environmental features, and the cross features; inputting the multi-dimensional information matrix into an SRAF parameter prediction model to obtain SRAF placement parameters; and placing SRAF according to the SRAF placement parameters. This solution constructs a multi-dimensional information matrix by fusing graphic features, environmental features, and cross features, and introduces a multi-variable linear regression model for SRAF parameter prediction, solving the problem that the coupling relationship between graphics cannot be finely expressed in the traditional SRAF placement process, making the SRAF placement more in line with the actual imaging conditions and improving the accuracy of SRAF placement. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] To more clearly illustrate the technical solutions in the embodiments of the present application, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the following described drawings are only some embodiments of the present application. For those skilled in the art, other drawings can be obtained based on these drawings without creative efforts.

[0035] Figure 1 is a schematic flowchart of the SRAF placement method provided by the embodiments of the present application.

[0036] Figure 2 is a schematic structural diagram of the SRAF placement device provided by the embodiments of the present application.

[0037] Figure 3 is a schematic structural diagram of the electronic device provided by the embodiments of the present application. DETAILED DESCRIPTION

[0038] Exemplary embodiments will be described in detail herein, and examples thereof are shown in the accompanying drawings. When the following description refers to the accompanying drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present application. On the contrary, they are merely examples of devices and methods consistent with some aspects of the present application as detailed in the appended claims.

[0039] It should be noted that, in this document, the terms "comprising", "including" or any other variation thereof are intended to cover a non-exclusive inclusion, such that a process, method, article or device comprising a series of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article or device. Without further limitation, an element defined by the phrase "comprising a..." does not exclude the presence of additional identical elements in the process, method, article or device comprising such element. In addition, components, features, and elements with the same name in different embodiments of the present application may have the same meaning or different meanings, and their specific meanings need to be determined based on their explanations in the specific embodiments or further in combination with the context of the specific embodiments.

[0040] It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0041] In the following description, suffixes such as "module", "component" or "unit" used to represent elements are only for the convenience of describing the present application and have no specific meaning in themselves. Therefore, "module", "component" or "unit" can be used interchangeably.

[0042] In the description of the present application, it should be noted that the orientation or positional relationship indicated by the terms "upper", "lower", "left", "right", "inner", "outer", etc. is based on the orientation or positional relationship shown in the accompanying drawings, and is only for the convenience of describing the present application and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be construed as a limitation of the present application. In addition, terms such as "first" and "second" are only used for descriptive purposes and cannot be construed as indicating or implying relative importance.

[0043] Traditional SRAF placement methods usually rely on fixed design rules or experience-based heuristic algorithms, which have problems such as the inability to finely express the coupling relationship between patterns, local optimality, and poor generality, and it is difficult to achieve high-precision and automated auxiliary pattern placement.

[0044] Based on this, embodiments of the present application provide a method, apparatus, storage medium, and electronic device for SRAF placement. Specifically, the SRAF placement apparatus can be integrated into an electronic device, which can be a server or a terminal device, etc. Among them, the terminal can include a mobile phone, a wearable intelligent device, a tablet computer, a notebook computer, and a personal computer (PC), etc. The server can be a single server or a server cluster composed of multiple servers, and can be a physical server or a virtual server.

[0045] The following will separately elaborate on the technical solutions shown in the present application through specific embodiments. It should be noted that the description order of the following embodiments does not limit the priority order of the embodiments.

[0046] Please refer to Figure 1 , Figure 1 which is a flowchart of the SRAF placement method provided by an embodiment of the present application. The specific process of this SRAF placement method can be as follows:

[0047] 101. Obtain the graphic features and environmental features of the target graphic in the via layer.

[0048] First, the via layer (such as the VIA layer) can be selected from the integrated circuit layout data as the target layer, and the basic attributes of the target graphic can be extracted through a graphic recognition and data parsing tool to obtain its graphic features. The graphic features include but are not limited to the critical dimension (CD) of the target graphic, the first graphic pitch, the second graphic pitch, and the edge offset. Among them, the first graphic pitch refers to the x-direction graphic pitch Pitchx, and the second graphic pitch refers to the y-direction graphic pitch Pitchy.

[0049] Subsequently, based on the spatial retrieval and sliding window method, a neighborhood window with a certain range (such as 1μm × 1μm) is set around the target graphic, and the layout of other graphics within this window is statistically analyzed to obtain the environmental features. The environmental features include the adjacent edge pitch and the local density, etc., which can reflect the structural environment of the target graphic in the local area.

[0050] In some embodiments, after obtaining the graphic features and environmental features, the graphic features and environmental features can be standardized. Since the dimensions of each feature are different, it is necessary to standardize each feature so that all features are on the same scale to avoid a certain variable dominating the model training due to its large numerical range.

[0051] 102. Generate cross features according to the graphic features and environmental features.

[0052] The mathematical operation method can be used to combine the graphic features and the environmental features to generate cross features, so as to explore the coupling relationship between the two types of features.

[0053] Specifically, the critical dimension can be multiplied by the edge offset to obtain the first cross feature. This first cross feature can reflect the comprehensive effect of the critical dimension and the edge offset.

[0054] Divide the first graphic spacing by the adjacent edge spacing to obtain the second cross feature. This second cross feature can reflect the relative relationship between the target graphic and the surrounding graphics.

[0055] Multiply the second graphic spacing by the local density to obtain the third cross feature. This third cross feature can be used to capture the influence of the local environment on the lithography effect.

[0056] 103. Construct a multi-dimensional information matrix based on the graphic features, environmental features and cross features.

[0057] The graphic features, environmental features and cross features can be jointly constructed into a group of multi-dimensional information matrices. Each row in this multi-dimensional information matrix represents the comprehensive feature vector of a target graphic, and each column corresponds to a feature dimension. To enhance the consistency and processability of the data, all feature data are standardized to adapt to the input requirements of the machine learning model.

[0058] In some embodiments, the graphic features, environmental features and cross features can be respectively converted into column vectors; the column vectors are standardized; and the standardized column vectors are concatenated into a multi-dimensional information matrix in a preset order.

[0059] This preset order can be set according to the actual situation, and this embodiment does not limit it.

[0060] 104. Input the multi-dimensional information matrix into the SRAF parameter prediction model to obtain the SRAF placement parameters.

[0061] Among them, the SRAF parameter prediction model is a multi-variable linear regression model. Before step 101, constructing the SRAF parameter prediction model can also be included.

[0062] In some embodiments, representative target graphic samples and their optimal SRAF parameter configurations can be collected first, and their graphic features, environmental features and cross features are extracted to form the multi-dimensional feature vectors of the training samples. Then, taking the SRAF parameters as the model output labels, a supervised learning data set is constructed. By using the least squares method to model the linear mapping relationship between the input features and the target output, the SRAF parameter prediction model is obtained.

[0063] Specifically, the following mapping relationship can be established by using the multi-variable linear regression model: .

[0064] Here, Y is a vector that refers to all the sraf parameters that need to be predicted (e.g. [sraf size, sraf offset, sraf placement]). to Refers to all the aforementioned basic features, such as graphic features, environmental features, and cross-features. is the intercept, to is the regression coefficient of each feature, is the error term.

[0065] Then, using the least squares formula: The regression coefficient is solved to minimize the mean square error between the predicted value and the actual value, and the SRAF parameter prediction model is obtained.

[0066] The training and validation process of the SRAF parameter prediction model can be as follows:

[0067] (1) Dataset division: The collected dataset is divided into training set, validation set, and test set to ensure that the model can generalize well on new data.

[0068] (2) Model training: Use the training set to fit the model and calculate the regression coefficients using the least squares method. Use cross-validation (such as K-fold cross-validation) for optimization to reduce the risk of overfitting.

[0069] (3) Model evaluation:

[0070] Mean Squared Error (MSE): Measures the average squared difference between the model’s predictions and the actual values.

[0071] Coefficient of determination (R²): evaluates the model's ability to explain the variation in each sraf parameter.

[0072] Analyze the residual distribution and check whether it conforms to the normal distribution to ensure that the model assumptions are basically established.

[0073] 105. Place the SRAF according to the SRAF placement parameters.

[0074] In some embodiments, a layout tool interface may be called to place an SRAF at a compliant position outside the target graphic according to SRAF placement parameters to complete the auxiliary graphic layout.

[0075] For example, for each target pattern, its contour boundary information can be extracted; subsequently, based on the SRAF offset predicted by the SRAF parameter prediction model, the position coordinates of the SRAF relative to the edge of the target pattern are determined; then, according to the output SRAF size and position, a corresponding auxiliary pattern is generated; finally, a layout legality check is performed on the placed SRAF, and the legal SRAF is written into the final layout for subsequent lithography simulation and layout verification.

[0076] In summary, the SRAF placement method provided by the embodiments of the present application includes obtaining the pattern features and environmental features of the target pattern in the via layer; generating cross features according to the pattern features and environmental features; constructing a multi-dimensional information matrix according to the pattern features, environmental features, and cross features; inputting the multi-dimensional information matrix into the SRAF parameter prediction model to obtain SRAF placement parameters; and placing the SRAF according to the SRAF placement parameters. This solution constructs a multi-dimensional information matrix by integrating pattern features, environmental features, and cross features, and introduces a multi-variable linear regression model for SRAF parameter prediction, solving the problem that the coupling relationship between patterns cannot be finely expressed in the traditional SRAF placement process, making the SRAF placement more in line with the actual imaging conditions and improving the accuracy of SRAF placement. Moreover, by extracting the pattern features of the target pattern and its surrounding environmental features, generating cross features, and constructing a multi-dimensional information matrix, the changing trend of the layout environment of the target pattern can be comprehensively characterized. Compared with the traditional rule-based SRAF layout method, this solution can dynamically predict more appropriate SRAF placement parameters according to the context environment where the target pattern is located, thereby reducing the impact of lithography process variations on critical dimensions while ensuring resolution improvement, achieving the narrowing of the process window and the improvement of image formation consistency.

[0077] To facilitate better implementation of the SRAF placement method provided by the embodiments of the present application, the embodiments of the present application also provide an SRAF placement device. The meanings of the terms are the same as those in the above SRAF placement method, and the specific implementation details can refer to the description in the method embodiments.

[0078] Please refer to Figure 2 , Figure 2 which is a schematic structural diagram of the SRAF placement device provided by the embodiments of the present application. The SRAF placement device may include a feature acquisition unit 201, a feature generation unit 202, a matrix construction unit 203, a parameter prediction unit 204, and an SRAF placement unit 205. Among them,

[0079] The feature acquisition unit 201 is used to acquire the pattern features and environmental features of the target pattern in the via layer;

[0080] The feature generation unit 202 is used to generate cross features according to the pattern features and environmental features;

[0081] A matrix construction unit 203, configured to construct a multi-dimensional information matrix according to graphic features, environmental features, and cross features;

[0082] A parameter prediction unit 204, configured to input the multi-dimensional information matrix into an SRAF parameter prediction model to obtain SRAF placement parameters;

[0083] An SRAF placement unit 205, configured to place SRAFs according to the SRAF placement parameters.

[0084] For the specific implementation manners of each of the above units, reference may be made to the embodiments of the above SRAF placement method, which will not be elaborated herein one by one.

[0085] In summary, the SRAF placement device provided in the embodiment of the present application can obtain the graphic features and environmental features of the target graphics in the via layer through the feature acquisition unit 201; the feature generation unit 202 generates cross features according to the graphic features and environmental features; the matrix construction unit 203 constructs a multi-dimensional information matrix according to the graphic features, environmental features, and cross features; the parameter prediction unit 204 inputs the multi-dimensional information matrix into the SRAF parameter prediction model to obtain SRAF placement parameters; the SRAF placement unit 205 places SRAFs according to the SRAF placement parameters. This solution constructs a multi-dimensional information matrix by fusing graphic features, environmental features, and cross features, and introduces a multi-variable linear regression model for SRAF parameter prediction, solving the problem that the coupling relationship between graphics cannot be finely expressed in the traditional SRAF placement process, making the SRAF placement more in line with the actual imaging conditions and improving the accuracy of SRAF placement.

[0086] The embodiment of the present application further provides an electronic device, which may integrate the SRAF placement device of the embodiment of the present application. As Figure 3 shown, it shows a schematic structural diagram of the electronic device involved in the embodiment of the present application. Specifically:

[0087] The electronic device may include components such as a processor 301 with one or more processing cores and a memory 302 with one or more computer-readable storage media. Those skilled in the art can understand that Figure 3 the structural diagram of the electronic device shown in does not constitute a limitation on the electronic device, and may include more or fewer components than shown, or combine certain components, or have different component arrangements. Among them:

[0088] The processor 301 is the control center of the electronic device, connecting various parts of the entire electronic device through various interfaces and circuits. By running or executing software programs and / or this application stored in the memory 302, and by invoking the data stored in the memory 302, it executes various functions of the electronic device and processes data, thereby monitoring the electronic device as a whole. Optionally, the processor 301 may include one or more processing cores; preferably, the processor 301 may integrate an application processor and a modem processor. Among them, the application processor mainly processes operations on storage media, user interfaces, application programs, etc., and the modem processor mainly processes wireless communications. It can be understood that the above-mentioned modem processor may not be integrated into the processor 301 either.

[0089] The memory 302 can be used to store software programs and this application. The processor 301 executes various functional applications and data processing by running the software programs and this application stored in the memory 302. The memory 302 may mainly include a program storage area and a data storage area. Among them, the program storage area can store operation storage media, application programs required for at least one function, etc.; the data storage area can store data created according to the use of the electronic device. In addition, the memory 302 may include high-speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, a flash memory device, or other non-volatile solid-state storage devices. Correspondingly, the memory 302 may also include a memory controller to provide the processor 301 with access to the memory 302.

[0090] Although not shown, the electronic device may also include a display unit, an input unit, a power supply, etc., which will not be elaborated here. Specifically, in this embodiment, the processor 301 in the electronic device will load the executable files corresponding to the processes of one or more application programs into the memory 302 according to the following instructions, and the processor 301 will run the application programs stored in the memory 302 to achieve various functions as follows:

[0091] Obtain the graphic features and environmental features of the target graphic in the via layer;

[0092] Generate cross features according to the graphic features and environmental features;

[0093] Construct a multi-dimensional information matrix according to the graphic features, environmental features and cross features;

[0094] Input the multi-dimensional information matrix into the SRAF parameter prediction model to obtain the SRAF placement parameters;

[0095] Place the SRAF according to the SRAF placement parameters.

[0096] Those of ordinary skill in the art can understand that all or part of the steps in the various methods of the above embodiments can be completed by instructions, or by controlling related hardware through instructions. The instructions can be stored in a computer-readable storage medium and loaded and executed by a processor.

[0097] For this reason, an embodiment of the present application provides a storage medium in which multiple instructions are stored. The instructions can be loaded by a processor to execute the steps in any one of the methods provided by the embodiments of the present application. For example, the instructions can execute the following steps:

[0098] Obtain the graphic features and environmental features of the target graphic in the via layer;

[0099] Generate cross features according to the graphic features and environmental features;

[0100] Construct a multi-dimensional information matrix according to the graphic features, environmental features and cross features;

[0101] Input the multi-dimensional information matrix into the SRAF parameter prediction model to obtain the SRAF placement parameters;

[0102] Place the SRAF according to the SRAF placement parameters.

[0103] For the specific implementation of each of the above operations, reference can be made to the previous embodiments and will not be elaborated here.

[0104] Among them, the storage medium may include: Read Only Memory (ROM), Random Access Memory (RAM), magnetic disk or optical disc, etc.

[0105] Since the instructions stored in the storage medium can execute the steps in any one of the methods provided by the embodiments of the present application, the beneficial effects that can be achieved by any one of the methods provided by the embodiments of the present application can be realized. For details, refer to the previous embodiments and will not be elaborated here.

[0106] The SRAF placement method, device, storage medium and electronic device provided by the present application have been introduced in detail above. Specific examples are used in this article to elaborate on the principle and implementation manner of the present application. The description of the above embodiments is only used to help understand the core idea of the present application; at the same time, for those skilled in the art, according to the idea of the present application, there will be changes in the specific implementation manner and application scope. In summary, the content of this specification should not be construed as a limitation to the present application.

Claims

1. A SRAF placement method, characterized in that: include: Acquire graphic features and environmental features of a target graphic in a through-hole layer, wherein the graphic features include a critical dimension, a first graphic spacing, a second graphic spacing, and an edge offset, and the environmental features include an adjacent edge spacing and a local density; Generating a cross feature according to the graphic feature and the environmental feature, comprising: multiplying the critical dimension by the edge offset to obtain a first cross feature; dividing the first graphic spacing by the adjacent edge spacing to obtain a second cross feature; multiplying the second graphic spacing by the local density to obtain a third cross feature; Constructing a multidimensional information matrix according to the graphic features, the environmental features and the cross features; Inputting the multidimensional information matrix into a SRAF parameter prediction model to obtain SRAF placement parameters; The SRAF is placed according to the SRAF placement parameters.

2. The SRAF placement method according to claim 1, characterized in that: The constructing of a multidimensional information matrix according to the graphic features, the environmental features and the cross features comprises: Converting the graphic feature, the environment feature and the cross feature into column vectors respectively; Performing standardization processing on each of the column vectors; The standardized column vectors are serially connected into a multi-dimensional information matrix in a preset order.

3. The SRAF placement method according to claim 1, characterized in that: The SRAF parameter prediction model is a multivariate linear regression model.

4. The SRAF placement method according to claim 3, characterized in that: Also includes: Construct SRAF parameter prediction model.

5. A SRAF placement device, characterized in that: include: A feature acquisition unit, used to acquire graphic features and environmental features of a target graphic in the through-hole layer, wherein the graphic features include a critical dimension, a first graphic spacing, a second graphic spacing, and an edge offset, and the environmental features include an adjacent edge spacing and a local density; A feature generation unit, configured to generate a cross feature according to the graphic feature and the environmental feature, comprising: multiplying the critical dimension by the edge offset to obtain a first cross feature; dividing the first graphic spacing by the adjacent edge spacing to obtain a second cross feature; and multiplying the second graphic spacing by the local density to obtain a third cross feature; A matrix construction unit, used for constructing a multi-dimensional information matrix according to the graphic features, the environmental features and the cross features; A parameter prediction unit, used for inputting the multi-dimensional information matrix into a SRAF parameter prediction model to obtain SRAF placement parameters; The SRAF placement unit is used to place the SRAF according to the SRAF placement parameters.

6. A storage medium, characterized in that: The storage medium stores a plurality of instructions, and the instructions are suitable for being loaded by a processor to execute the SRAF placement method according to any one of claims 1 to 4.

7. An electronic device, characterized in that: The method comprises a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the SRAF placement method according to any one of claims 1 to 4 when executing the computer program.

Images