Method, device and medium for optimizing layout processing model

Abstract

Embodiments of the present disclosure relate to methods, devices, and media for optimizing layout processing models. The method proposed herein includes: determining multiple groups of simulation sampling points on a target object related to the layout processing model to be optimized, wherein the multiple groups of simulation sampling points are obtained by grouping multiple simulation sampling points on the target object; and determining at least one simulation performance indicator related to the layout processing model based on the first simulation sampling point in each group of simulation sampling points in the multiple groups of simulation sampling points, wherein in at least one group of simulation sampling points, the number of the first simulation sampling points is less than the total number of sampling points in the group of simulation sampling points. In this way, the number of simulation sampling points involved in the simulation calculation can be greatly reduced.

Description

Technical Field

[0001] Example embodiments of the present disclosure generally relate to the field of integrated circuit technology, and more particularly, to a method, apparatus, and medium for optimizing a layout processing model. Background Art

[0002] In semiconductor manufacturing, photolithography is a critical step in transferring circuit designs onto silicon wafers. However, due to light diffraction, interference, and chemical reactions in the photoresist, circuit patterns can sometimes become deformed or misaligned, adversely affecting circuit performance and product yield. To address this challenge, layout processing models can be used to calibrate and optimize photolithographic patterns, thereby improving chip manufacturing accuracy.

[0003] Before a layout processing model can be used, its parameters must be optimized. This process aims to find the best configuration among possible parameter combinations. This goal requires several iterations, and within each iteration, simulations are performed with the selected parameters to evaluate their performance.

[0004] However, these simulations are complex and resource-intensive, requiring significant computational resources and time. Therefore, while layout processing models have significantly improved the lithography process, the complexity and resource requirements of the optimization process have also limited the speed and scope of their application. Summary of the Invention

[0005] In a first aspect of the present disclosure, a method for optimizing a layout processing model is provided, the method comprising: determining a plurality of groups of simulation sampling points on a target object related to the layout processing model to be optimized, wherein the plurality of groups of simulation sampling points are obtained by grouping a plurality of simulation sampling points on the target object; and determining at least one simulation performance indicator related to the layout processing model based on a first simulation sampling point in each group of the plurality of groups of simulation sampling points, wherein in at least one group of simulation sampling points, the number of the first simulation sampling points is less than the total number of sampling points in the group of simulation sampling points.

[0006] In a second aspect of the present disclosure, an electronic device is provided. The device includes at least one processing unit; and at least one memory coupled to the at least one processing unit and storing instructions for execution by the at least one processing unit. When executed by the at least one processing unit, the instructions cause the device to perform the method for optimizing a layout processing model according to the first aspect.

[0007] In a third aspect of the present disclosure, a computer-readable storage medium is provided, wherein a computer program is stored on the computer-readable storage medium, and the computer program can be executed by a processor to implement the method for optimizing a layout processing model according to the first aspect.

[0008] In a fourth aspect of the present disclosure, a computer program product is provided, which includes computer-executable instructions, which, when executed by a processor, implement the method for optimizing a layout processing model according to the first aspect of the present disclosure.

[0009] According to an embodiment of the present disclosure, multiple simulation sampling points are first rationally grouped. Subsequently, at least one simulation performance metric related to the layout processing model is determined based on the first simulation sampling point in each group. In this way, while ensuring that the simulation sampling points cover key locations on the target object, the embodiment of the present disclosure significantly reduces the number of simulation sampling points involved in the simulation calculation. This effectively reduces the resource consumption and time cost of the simulation calculation, thereby improving the optimization speed of the layout processing model.

[0010] It should be understood that the content described in this summary section is not intended to limit the key features or important features of the embodiments of the present disclosure, nor is it intended to limit the scope of the present disclosure. Other features of the present disclosure will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] The above and other features, advantages and aspects of the embodiments of the present disclosure will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. In the accompanying drawings, the same or similar reference numerals represent the same or similar elements, wherein:

[0012] Figure 1 A schematic diagram illustrating an example environment according to some embodiments of the present disclosure is shown;

[0013] Figure 2 A flowchart illustrating an example process for optimizing a layout processing model according to some embodiments of the present disclosure is shown;

[0014] Figure 3 A schematic diagram illustrating an example of multiple iterations according to some embodiments of the present disclosure;

[0015] Figure 4 A schematic diagram illustrating an example of constructing historical simulation data according to some embodiments of the present disclosure;

[0016] Figure 5 A schematic diagram illustrating an example of constructing historical simulation data according to some embodiments of the present disclosure; and

[0017] Figure 6 A block diagram of an electronic device is shown in which one or more embodiments of the present disclosure may be implemented. DETAILED DESCRIPTION

[0018] The following describes embodiments of the present disclosure in more detail with reference to the accompanying drawings. Although certain embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as limited to the embodiments described herein. Rather, these embodiments are provided to provide a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are for illustrative purposes only and are not intended to limit the scope of protection of the present disclosure.

[0019] It should be noted that the titles of any section / subsection provided herein are not limiting. Various embodiments are described throughout this document, and any type of embodiment may be included under any section / subsection. Furthermore, the embodiments described in any section / subsection may be combined in any manner with any other embodiments described in the same section / subsection and / or in different sections / subsections.

[0020] In the description of the embodiments of the present disclosure, the term "including" and similar terms should be understood as open inclusion, that is, "including but not limited to". The term "based on" should be understood as "based at least in part on". The term "one embodiment" or "the embodiment" should be understood as "at least one embodiment". The term "some embodiments" should be understood as "at least some embodiments". Other explicit and implicit definitions may be included below. The terms "first", "second", etc. may refer to different or the same objects. Other explicit and implicit definitions may be included below.

[0021] As briefly described above, simulation is complex and resource-intensive, requiring significant computational resources and time. For clarity, the following example uses the Optical Proximity Correction (OPC) layout processing model as an example.

[0022] Specifically, during the simulation process, for each model sample (including one or more parameters of the OPC model), the error between the simulated value of the model sample and the target value for a certain simulation parameter can be calculated. Based on this error, a simulation performance indicator for the model sample (this simulation performance indicator can be represented by a loss value, for example) is determined. Through multiple iterations, the model sample with the most appropriate simulation performance indicator can be determined, thereby finding the target parameters of the OPC model and optimizing the OPC model.

[0023] In the process of calculating the loss value (cost) of each model sample, the simulation software needs to calculate the above-mentioned errors at multiple simulation sampling points (or measurement point gauges). These simulation sampling points need to be able to cover various key locations on the target object (such as the wafer), so the number of simulation sampling points is often very large. Since error calculations need to be performed at each simulation sampling point, and these calculations involve complex physical and chemical effect simulations, they consume a lot of computing resources and time. With the continuous advancement of technology nodes and the increase in pattern complexity, this resource consumption and time cost are also increasing, becoming a major factor restricting the speed of OPC model optimization.

[0024] In view of this, the present disclosure provides a solution for optimizing a layout processing model. According to the solution of the present disclosure, multiple groups of simulation sampling points are first determined on a target object related to the layout processing model to be optimized, wherein the multiple groups of simulation sampling points are obtained by grouping multiple simulation sampling points on the target object. Then, based on the first simulation sampling point in each of the multiple groups of simulation sampling points, at least one simulation performance indicator related to the layout processing model is determined, wherein, in at least one group of simulation sampling points, the number of the first simulation sampling points is less than the total number of sampling points in the group of simulation sampling points.

[0025] As will be more clearly understood from the following description, according to the disclosed solution, multiple simulation sampling points are first rationally grouped, and then at least one simulation performance metric related to the layout processing model is determined based on the first simulation sampling point in each group. In this way, the disclosed solution significantly reduces the number of simulation sampling points involved in the simulation calculation while ensuring that the simulation sampling points cover key locations on the target object. This can effectively reduce the resource consumption and time cost of the simulation calculation, thereby improving the optimization speed of the layout processing model.

[0026] Various example implementations of this solution will be described in detail below with reference to the accompanying drawings.

[0027] Figure 1 FIG2 shows a schematic diagram of an example environment 100 according to some embodiments of the present disclosure. Figure 1 , the example environment 100 may include an electronic device 120 and a layout processing model 140 .

[0028] In this example environment 100, electronic device 120 may be used to optimize parameters of layout processing model 140. As an example, layout processing model 140 may include any relevant processing model in the layout processing process. For example, layout processing models may include, but are not limited to, OPC models, mask process correction (MPC) models, and electron beam lithography (Ebeam) models.

[0029] As an example, the OPC model is mainly used in layout processing to correct imaging distortion problems caused by the optical proximity effect. The optical proximity effect is caused by the diffraction of light. When the feature size of the mask pattern is close to or smaller than the wavelength of light used by the lithography system, the imaging on the wafer will deviate from the original design pattern. This effect can cause distortion problems such as edge rounding, line end indentation, and line width deviation, which in turn affects the reliability and performance of the chip. The OPC model compensates for these optical effects by adjusting the shape and size of the mask pattern. Specifically, it may change the topology of the light-transmitting area on the mask, or add small sub-resolution auxiliary patterns to the mask to make the lithography imaging result as close as possible to the original design pattern. This correction process is crucial to ensuring the reliability and accuracy of the lithography pattern.

[0030] For example, the MPC model is primarily used in layout processing to address issues such as electron beam blurring, photoresist diffusion, and lateral etching deviations in the mask process. The MPC model aims to predict and correct these nonlinear effects through a series of algorithms and models, ensuring that the circuit layout on the mask is as consistent as possible with the mask layout after optical proximity correction (OPC). The MPC model considers factors such as electron beam energy distribution, the chemical and physical properties of the photoresist material, and various parameters in the etching process. By simulating these processes, the MPC model can predict the impact of nonlinear effects on the pattern and generate corresponding correction data. This data is then used to adjust the mask layout or process parameters to minimize the deviations caused by nonlinear effects.

[0031] As an example, the Ebeam model is a process model related to electron-beam lithography. Electron-beam lithography uses a high-energy electron beam to create nanoscale patterns directly on silicon wafers or other substrates. Compared to optical lithography, electron-beam lithography offers higher resolution and precision, making it suitable for manufacturing more advanced and smaller integrated circuits. In layout processing, the Ebeam model can be used to simulate and optimize the electron-beam lithography process to ensure high-quality, high-precision patterns on silicon wafers.

[0032] For clarity, unless otherwise specified, the following description will take the layout processing model 140 being an OPC model as an example to illustrate various embodiments of the present disclosure.

[0033] As an example, the layout processing model 140 has multiple parameters, including but not limited to lithography wavelength and numerical aperture, etc. To optimize these parameters, in the example environment 100 , the electronic device 120 may find the most appropriate combination of parameters through multiple iterations.

[0034] As an example, the electronic device 120 may randomly generate a series of model samples to obtain a plurality of initial model samples 110 (the plurality of initial model samples 110 may also be referred to as an initial population of a first iteration). For example, each initial model sample includes at least one parameter of the layout processing model 140 , and the parameter values ​​in different initial model samples may differ.

[0035] Subsequently, the electronic device 120 may use the multiple initial model samples 110 as a starting point and search for the target parameter 130 through multiple iterations. In at least one iteration, unlike the simulation process described above, the electronic device 120 utilizes a predetermined strategy during the simulation process to reduce the number of simulation sampling points, thereby reducing the simulation calculation time in each iteration and improving the speed of a single iteration.

[0036] After multiple iterations, the electronic device 120 can finally determine the target parameters 130 for the layout processing model 140 .

[0037] Once the target parameters 130 of the layout processing model 140 are found, they will be applied to the layout processing model 140, so that the layout processing model 140 can perform the corresponding tasks with higher efficiency and accuracy.

[0038] In some embodiments, a user can interact with the electronic device 120 via a terminal device. For example, the terminal device can be any type of mobile, fixed, or portable terminal, including a mobile phone, desktop computer, laptop computer, notebook computer, netbook computer, tablet computer, media computer, multimedia tablet, personal communication system (PCS) device, personal navigation device, personal digital assistant (PDA), audio / video player, digital camera / camcorder, positioning device, television receiver, radio receiver, e-book device, gaming device, or any combination thereof, including accessories and peripherals of these devices, or any combination thereof. In some embodiments, the terminal device can also support any type of user-specific interface (such as "wearable" circuitry).

[0039] The electronic device 120 may be a standalone physical server, a server cluster or distributed system consisting of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content distribution networks, and big data and artificial intelligence platforms. The electronic device 120 may include, for example, a computing system / server, such as a mainframe, an edge computing node, a computing device in a cloud environment, and the like.

[0040] As an example, a communication connection may be established between the electronic device 120 and the terminal device. The communication connection may be established via a wired or wireless method. The communication connection may include, but is not limited to, a Bluetooth connection, a mobile network connection, a Universal Serial Bus connection, a Wi-Fi connection, etc., and the embodiments of the present disclosure are not limited in this respect. In the embodiments of the present disclosure, the electronic device 120 and the terminal device may exchange data and / or signaling via the communication connection between them.

[0041] It should be understood that the structure and function of the various elements in the environment 100 are described for illustrative purposes only and do not imply any limitation on the scope of the present disclosure.

[0042] Figure 2 A flow chart illustrating an example process 200 for optimizing a layout processing model 140 according to some embodiments of the present disclosure is shown. The process 200 may be implemented at the electronic device 120. Figure 3 A schematic diagram of an example 300 of multiple iterations according to some embodiments of the present disclosure is shown. Figure 3 The process 200 will be described.

[0043] like Figure 2 As shown, in block 210 , a plurality of groups of simulation sampling points are determined on a target object related to the layout processing model 140 to be optimized, wherein the plurality of groups of simulation sampling points are obtained by grouping a plurality of simulation sampling points on the target object.

[0044] As described above, the electronic device 120 can find the target parameters 130 of the layout processing model 140 through multiple iterations. Figure 3 The multiple iterations include at least the 1st iteration shown by box 310-1, the 2nd iteration shown by box 310-2, the Nth iteration shown by box 310-N, and the N+1th iteration shown by box 310-N+1, etc., where N can be any appropriate positive integer.

[0045] As an example, the process 200 may be implemented in any one of blocks 310 - 1 to 310 -N+1. For clarity, unless otherwise specified, various embodiments of the present disclosure are described below by taking the process 200 being implemented in block 310 -N as an example.

[0046] In some embodiments, during each iteration, electronic device 120 needs to select multiple simulation sampling points from a target object (e.g., a wafer) associated with layout processing model 140 for simulation testing and performance evaluation. However, directly simulating all sampling points consumes significant computing resources and time. To improve efficiency, electronic device 120 divides these simulation sampling points into multiple groups.

[0047] As an example, the multiple simulation sampling points may refer to a series of representative points selected on a target object. These simulation sampling points are used to simulate and test the performance of the layout processing model 140 at different locations and conditions after applying a certain model sample (e.g., the first model sample described below). For example, in semiconductor manufacturing, these simulation sampling points may correspond to different locations on a wafer.

[0048] As an example, the grouping method of the simulation sampling points can be determined according to actual needs. For example, the electronic device 120 can determine multiple groups of simulation sampling points by randomly grouping multiple simulation sampling points. For another example, the electronic device 120 can also group the simulation sampling points based on factors such as the spatial position, feature similarity, or the weight of the performance impact on the layout processing model 140. In this way, the electronic device 120 can group similar simulation sampling points together, thereby reducing unnecessary repeated simulations and improving the pertinence and efficiency of the simulation. As an example, assume that the electronic device 120 selects 100 simulation sampling points on the wafer. According to a predetermined strategy, these simulation sampling points may be divided into 10 groups, each group containing 10 simulation sampling points with similar features. In this way, the electronic device 120 can perform independent simulation tests on each group of simulation sampling points, rather than performing a separate simulation on each simulation sampling point, thereby greatly reducing the amount of calculation.

[0049] For example, each group of simulation sampling points represents a specific area on a target object. Electronic device 120 performs simulation testing based on these grouped simulation sampling points to evaluate at least one simulation performance metric related to layout processing model 140 (e.g., simulation performance metric 330-1 of layout processing model 140 after applying model sample 320-1, or simulation performance metric 330-M of layout processing model 140 after applying model sample 320-M), and optimizes parameters based on the simulation performance metric.

[0050] In some embodiments, the plurality of simulation sampling points may be grouped as follows: the electronic device 120 groups the plurality of simulation sampling points based on corresponding historical simulation data related to optimization of the layout processing model 140 to determine a plurality of groups of simulation sampling points.

[0051] In some embodiments, the corresponding historical simulation data may include past simulation results, performance indicators, or other historical information related to model optimization. These corresponding historical simulation data provide a reference for the electronic device 120, enabling the electronic device 120 to understand the performance of each simulation sampling point in the past simulation.

[0052] In some embodiments, the electronic device 120 determines, based on the similarity between the corresponding historical simulation data of the multiple simulation sampling points, the degree of correlation of at least two simulation sampling points among the multiple simulation sampling points with respect to the layout processing model 140. The electronic device 120 then clusters the multiple simulation sampling points based on the degree of correlation of at least two simulation sampling points among the multiple simulation sampling points with respect to the layout processing model 140.

[0053] For example, based on these corresponding historical simulation data, the electronic device 120 clusters multiple simulation sampling points to group simulation sampling points with similar historical simulation performances into one category. Through clustering, the electronic device 120 can identify which simulation sampling points have historically exhibited similar characteristics, and thus group them together for subsequent processing.

[0054] As an example, a clustering algorithm can be performed based on the similarity or distance between historical simulation data. For example, a clustering algorithm can include, but is not limited to, K-means clustering, hierarchical clustering, or other suitable clustering methods. By calculating the similarity or distance between the corresponding historical simulation data of each simulation sampling point, the clustering algorithm can divide them into several groups. The simulation sampling points within each group have similar historical simulation characteristics, while the simulation sampling points between different groups can show greater differences.

[0055] In this way, the electronic device 120 can group multiple simulation sampling points more efficiently, thereby facilitating subsequent optimization work.

[0056] The clustering process of the embodiment of the present disclosure is described below using the K-means clustering algorithm as an example. Before starting clustering, the electronic device 120 first determines the number of clusters K in the cluster. The value of K will be described in detail below and will not be detailed here.

[0057] As an example, after determining the number of clusters K, the electronic device 120 initializes the cluster center of each cluster. The cluster center represents the average position of all data points in the same cluster. In the initial stage of the K-means algorithm, the electronic device 120 can randomly select K data points from the data set as the initial cluster centers. In an embodiment of the present disclosure, the data set can be, for example, corresponding historical simulation data related to the optimization of the layout processing model 140 for multiple simulation sampling points, and each data point can be corresponding historical simulation data related to the optimization of the layout processing model 140 for each simulation sampling point.

[0058] Next, the electronic device 120 calculates the distance between each data point in the data set and each initial cluster center. As an example, the distance calculation here can use Euclidean distance as a distance metric, but other distance metrics can also be selected according to specific circumstances.

[0059] Each data point is assigned to the cluster to which the initial cluster center is closest. After this step is completed, the electronic device 120 obtains K preliminary clusters, and the data points in each cluster are relatively close to the cluster center of the cluster.

[0060] Once the data points are assigned to the K preliminary clusters, the electronic device 120 may recalculate the cluster center of each cluster. The new cluster center may be the average value of all data points in the cluster.

[0061] After recalculating the cluster center, the electronic device 120 can check whether the distance between the new cluster center and the initial cluster center is less than a set threshold. If the distance is less than the threshold, the electronic device 120 can consider that the new cluster center has stabilized or converged, and the clustering process can be terminated.

[0062] If the distance between the new cluster center and the initial cluster center still changes greatly (that is, exceeds the set threshold), it means that the clustering result has not yet stabilized. At this time, the above steps need to be repeated until the stopping condition is met.

[0063] In some embodiments, the electronic device 120 may collect historical simulation data for each simulation sampling point, including simulation results obtained at different time points and under different model sample settings, such as error values ​​and / or performance indicators.

[0064] Next, electronic device 120 can calculate the similarity between these historical simulation data. As an example, similarity calculation can be based on various methods, such as Euclidean distance, Pearson correlation coefficient, cosine similarity, etc. The specific method selected may depend on the characteristics of the data and the application context, and the embodiments of the present disclosure do not impose any restrictions on this. By calculating the similarity, electronic device 120 can quantify the degree of similarity in model performance between different simulation sampling points.

[0065] Once the similarity calculation is completed, the electronic device 120 can determine the degree of correlation between the at least two simulation sampling points with respect to the layout processing model 140 based on the similarities. For example, if the historical simulation data of two simulation sampling points are very similar, the electronic device 120 can determine that they have a high degree of correlation with respect to the layout processing model 140, which means that different model samples may have similar performance at the two simulation sampling points.

[0066] As an example, after determining the correlation between each simulation sampling point and the layout processing model 140, the electronic device 120 may perform a clustering operation. Through the clustering operation, the electronic device 120 can group simulation sampling points with high correlation into the same cluster, and assign simulation sampling points with low correlation to different clusters.

[0067] In this way, the electronic device 120 is helped to identify simulation sampling points with similar performance characteristics to the layout processing model 140 .

[0068] In some embodiments, at least one simulation performance metric is determined in a first iteration of a plurality of iterations associated with the optimization of the layout processing model 140 . Figure 4 A schematic diagram illustrating an example 400 of constructing historical simulation data according to some embodiments of the present disclosure is shown.

[0069] Reference Figure 4 The historical simulation data associated with the layout processing model 140 at a second simulation sampling point among the plurality of simulation sampling points can be determined as follows. At block 401, the electronic device 120 determines a plurality of second model samples involved in a second iteration preceding the first iteration among the plurality of iterations. At block 402, the electronic device 120 determines corresponding second simulation data associated with the second simulation sampling point for each second model sample among the plurality of second model samples. At block 403, the electronic device 120 constructs corresponding historical simulation data associated with the second simulation sampling point and the layout processing model 140 based on the corresponding second simulation data for each second model sample among the plurality of second model samples.

[0070] As an example, the first iteration may refer to Figure 3 For clarity, unless otherwise specified, the following description of various embodiments of the present disclosure takes the first iteration as the Nth iteration as an example. In this case, the second iteration may refer to one or more iterations from the 1st iteration to the N-1th iteration.

[0071] It should be noted that, in the embodiments of the present disclosure, "model samples involved in iteration" or similar expressions may specifically refer to model samples that have undergone at least the simulation operations described above in the iteration. Such model samples correspond to historical simulation data.

[0072] As an example, the plurality of second model samples may be all model samples that have been simulated from the 1st iteration to the N-1th iteration. As an example, the second simulation sampling point may be any one of the plurality of simulation sampling points.

[0073] For example, during iterations 1 to (N-1), the electronic device 120 determines, for each second model sample, second simulation data generated by the second model sample at the second simulation sampling point. The second simulation data reflects the performance of the layout processing model 140 at the second simulation sampling point when the model sample is used as input during iterations 1 to (N-1).

[0074] As an example, based on the collected second simulation data of multiple second model samples, the electronic device 120 may integrate these data to construct corresponding historical simulation data related to the second simulation sampling point and the layout processing model 140 .

[0075] In this way, the corresponding historical simulation data of the second simulation sampling point is a cumulative record, which contains key simulation data related to the model performance at the second simulation sampling point during multiple iterations.

[0076] As an example, assume that 300 iterations are performed, each involving 200 model samples, and 1000 locations on the wafer are selected as 1000 simulation sample points. This means that in each iteration, 200 different model configurations or parameters are generated or evaluated.

[0077] The model samples involved in iterations 1 through 3 (a total of 600 model samples, also known as the second model samples) and their corresponding simulation data at the second simulation sampling point (also known as the corresponding second simulation data) are used to determine the corresponding simulation history data for the second simulation sampling point among the 1000 simulation sampling points. By performing the above operation for each of the 1000 simulation sampling points, the corresponding simulation history data for each of the 1000 simulation sampling points can be obtained.

[0078] In some embodiments, the electronic device 120 determines a simulation value for a target simulation parameter at a second simulation sampling point for each of the plurality of second model samples to obtain a plurality of simulation values ​​corresponding to the plurality of second model samples. The electronic device 120 then determines corresponding second simulation data for each of the plurality of second model samples based on differences between the plurality of simulation values ​​and a reference value related to the target simulation parameter.

[0079] As an example, the electronic device 120 may determine, for each of the plurality of second model samples, a simulation value for a target simulation parameter of the second model sample at the second simulation sampling point. For example, the target simulation parameter may be a pre-set key indicator for evaluating the performance of the layout processing model 140, such as a critical dimension of a certain device or pattern. The target simulation parameter may be determined based on actual needs and is not limited in the embodiments of the present disclosure.

[0080] For each second model sample, electronic device 120 can simulate applying the parameters of the second model sample to layout processing model 140 to observe and record the specific performance of the target simulation parameters at the second simulation sampling point, i.e., the simulation value. After this process is completed, electronic device 120 will obtain a set of simulation values ​​corresponding to the plurality of second model samples (for the second simulation sampling points).

[0081] As an example, a reference value is a standard value or expected value related to a target simulation parameter and used to compare and evaluate model performance. For example, the reference value can be derived from various sources, such as industry standards, historical best performance, user requirements, or expert judgment.

[0082] Next, for each second model sample, electronic device 120 may perform a calculation based on the simulated value of the second model sample at the second simulation sampling point and the reference value, thereby determining the second simulation data for each second model sample at the second simulation sampling point. As an example, the second simulation data E may be determined based on the difference between the simulated value of the second model sample and the reference value. Exemplarily, this process can be represented by Formula 1.

[0083] E=(simA– waferA)×B

[0084] Formula 1

[0085] Wherein, simA represents the simulation value of the second model sample, waferA represents the reference value, and B is a predetermined coefficient, for example, B may be a transmitted light parameter, etc.

[0086] As described above, the model samples involved in the first to third iterations total 600. Therefore, for one second simulation sampling point, 600 second simulation data E are calculated using Formula 1. As an example, the electronic device 120 can vectorize the 600 second simulation data E to construct a vector feature with 600 dimensions, where each dimension corresponds to one second simulation data E, and different dimensions correspond to different second simulation data E.

[0087] Next, the electronic device 120 may use the 600-dimensional vector feature to represent corresponding historical simulation data related to the second simulation sampling point and the layout processing model 140 .

[0088] Similarly, electronic device 120 can determine a 600-dimensional vector feature for each of the 1,000 simulation sampling points described above. Furthermore, electronic device 120 can use these 1,000 600-dimensional vector features as corresponding historical simulation data related to the optimization of the multiple simulation sampling points and layout processing model 140, and then input them into a machine learning model capable of clustering (or grouping) the 1,000 simulation sampling points.

[0089] As an example, by setting an appropriate value of K, a corresponding number of groups can be obtained. For example, when K is set to 100, the electronic device 120 can divide 1000 simulation sampling points into 100 groups of simulation sampling points.

[0090] In the next 297 iterations, the electronic device 120 can use the simulation data that will focus on using these 100 sets of simulation sampling points (rather than the entire 1000) to calculate the model samples. As a result, the embodiment of the present disclosure can significantly reduce the amount of calculation in each subsequent iteration, effectively eliminating redundant data (which may have little or no contribution to the evaluation of model performance), thereby accelerating the model optimization process.

[0091] In some embodiments, electronic device 120 determines multiple clustering strategies related to grouping the multiple simulation sampling points based on corresponding historical simulation data of the multiple simulation sampling points, wherein at least two of the multiple clustering strategies define different numbers of cluster centers. Then, electronic device 120 determines a target clustering strategy from the multiple clustering strategies based on evaluation results related to each of the multiple clustering strategies. Subsequently, electronic device 120 groups the multiple simulation sampling points based on the target clustering strategy to obtain multiple groups of simulation sampling points corresponding to the multiple cluster centers.

[0092] As an example, the electronic device 120 may determine multiple clustering strategies based on corresponding historical simulation data of the multiple simulation sampling points to group the multiple simulation sampling points. The clustering strategies define how to cluster similar simulation sampling points together to form different clusters or groups.

[0093] As an example, at least two strategies among the multiple clustering strategies define different numbers of cluster centers, thereby exploring different grouping granularities or optimal grouping granularity in the structure.

[0094] For example, for each clustering strategy, electronic device 120 executes the corresponding clustering algorithm and evaluates the clustering results. For example, the evaluation may include internal evaluation metrics (such as silhouette coefficient, Davies-Bouldin index, etc.) and external evaluation metrics (such as accuracy and recall rate of labeled data, etc.).

[0095] Through the evaluation, the electronic device 120 can understand the pros and cons of each clustering strategy in revealing the similarity of the simulation sampling points.

[0096] Based on the above evaluation results, the electronic device 120 determines a target clustering strategy from the multiple clustering strategies. As an example, the target clustering strategy is the strategy that performs best under the current data and task context and can most effectively group the simulation sampling points.

[0097] Once the target clustering strategy is determined, electronic device 120 can use it to group the multiple simulated sampling points. This grouping process is performed according to the algorithm and parameter settings defined by the target clustering strategy, ensuring that similar simulated sampling points are clustered into the same group. After the grouping is complete, electronic device 120 obtains multiple groups of simulated sampling points corresponding to the multiple cluster centers.

[0098] In this way, the electronic device 120 can effectively determine a clustering strategy based on historical simulation data and group simulation sampling points.

[0099] In some embodiments, the evaluation result associated with a clustering strategy among the plurality of clustering strategies indicates a silhouette coefficient of the clustering strategy.

[0100] For example, in cluster analysis, the silhouette coefficient is used to measure the quality of clustering. It takes into account the cohesion and separation of clusters, giving a score between -1 and 1 to quantitatively assess the quality of the clustering results.

[0101] As an example, the silhouette coefficient can be calculated by Equation 2.

[0102] s=(ba) / max(a,b);

[0103] Formula 2

[0104] Here, a represents the average distance between a sample point (for example, the vector feature of a simulation sampling point) and the other sample points in its cluster, reflecting the compactness of the cluster. An optimal clustering result should minimize a, meaning that the sample points within the same cluster are more compact and have higher similarity. b represents the average distance between a sample point and all sample points in the closest cluster, reflecting the degree of separation between clusters. An ideal clustering result should maximize b, indicating clear differentiation between clusters.

[0105] For example, electronic device 120 may determine a silhouette coefficient for each clustering strategy. This coefficient directly reflects the clustering effect under the strategy. For example, the closer the silhouette coefficient is to 1, the better the clustering effect; conversely, if the silhouette coefficient is close to -1, it indicates that the clustering effect is poor.

[0106] Among multiple clustering strategies, electronic device 120 calculates the silhouette coefficient of each clustering strategy and uses these silhouette coefficients as evaluation results. These evaluation results directly indicate the performance of each clustering strategy. By comparing the silhouette coefficients of different clustering strategies, electronic device 120 can select the clustering strategy with the best performance, that is, the clustering strategy with the highest silhouette coefficient, as the target clustering strategy.

[0107] As an example, after determining the target clustering strategy, the electronic device 120 may further verify the number n of cluster centers.

[0108] Figure 5 FIG. 5 is a schematic diagram illustrating an example 500 of constructing historical simulation data according to some embodiments of the present disclosure. Figure 5 As an example, in box 501, the electronic device 120 determines the target number n of cluster centers of the target clustering strategy. In box 502, if the target number n is greater than the predetermined number m, the electronic device 120 will use the predetermined number m as the final number of cluster centers, where the predetermined number m is a settable value that specifically indicates the maximum number of cluster centers. In box 503, if the target number n is similar to or equal to the predetermined number m, the electronic device 120 may use either the target number n or the predetermined number m as the final number of cluster centers. In box 504, if the target number n is less than the predetermined number m, the electronic device 120 may use the target number n as the final number of cluster centers.

[0109] Then, in block 505 , the electronic device 120 performs a clustering operation based on the final number of cluster centers to group the plurality of simulation sampling points.

[0110] In block 220 , the electronic device 120 determines at least one simulation performance indicator related to the layout processing model 140 based on a first simulation sampling point in each of the plurality of groups of simulation sampling points, wherein in at least one group of simulation sampling points, the number of the first simulation sampling points is less than the total number of sampling points in the group of simulation sampling points.

[0111] In some embodiments, the first simulation sampling points may be random simulation sampling points within the respective groups, or may be representative or critical simulation sampling points within the respective groups. As an example, in block 506, the electronic device 120 may select a certain number of simulation sampling points from each group of simulation sampling points according to a predetermined ratio as the first simulation sampling points, or the electronic device 120 may select one simulation sampling point from each group of simulation sampling points as the first simulation sampling point.

[0112] In some embodiments, the electronic device 120 determines a first model sample related to the layout processing model 140, wherein the first model sample includes at least one parameter of the layout processing model 140. Then, the electronic device 120 determines a simulation performance indicator of the first model sample for the layout processing model 140 based on first simulation data related to the first simulation sampling point of the first model sample, wherein the first simulation data is determined based at least on a simulation value of the first model sample for a target simulation parameter at the first simulation sampling point.

[0113] As an example, the first model sample may refer to Figure 3Any model sample among the M model samples 320 - 1 to model samples 320 -M shown, where M is any appropriate positive integer, may be determined by the electronic device 120 based on the model sample output in the previous iteration.

[0114] As an example, the target simulation parameters are key indicators of concern when evaluating the performance of the layout processing model 140, such as key dimensions of certain devices or patterns, etc., which can be determined according to actual needs and are not limited in the embodiments of the present disclosure.

[0115] For each first model sample, electronic device 120 can simulate the application of the parameters in the first model sample to layout processing model 140, observing and recording the specific performance of the target simulation parameters at each first simulation sampling point, thereby obtaining the simulation value of layout processing model 140 (after applying the first model sample) at each first simulation sampling point. After this process is completed, electronic device 120 will obtain multiple simulation values ​​corresponding to the first model sample (for example, the multiple simulation values ​​here correspond one-to-one to the multiple first simulation points).

[0116] As an example, a reference value is a standard value or expected value related to a target simulation parameter and used to compare and evaluate model performance. For example, the reference value can be derived from various sources, such as industry standards, historical best performance, user requirements, or expert judgment.

[0117] Next, the electronic device 120 can perform calculations based on the simulation value and the reference value of the first model sample to determine the first simulation data of the first model sample. As an example, as an example, the electronic device 120 can calculate the difference between the simulation value and the reference value of the first model sample at each first simulation sampling point to determine the error value of the first model sample at each first simulation sampling point to obtain a plurality of error values ​​corresponding to the plurality of first simulation sampling points respectively. Furthermore, the electronic device 120 determines the first simulation data of the first model sample at each first simulation sampling point based on the product of each error value and a predetermined coefficient such as B to obtain a plurality of first simulation data corresponding to the plurality of first simulation sampling points respectively. Further, the electronic device 120 can integrate all the collected first simulation data to form a simulation performance indicator of the first model sample for the layout processing model 140.

[0118] Once the simulation performance index is determined, the electronic device 120 can use the simulation performance index to guide subsequent model optimization decisions. For example, by comparing the simulation performance indexes of different model samples, the electronic device 120 can select the best-performing model sample to determine the target parameters 130 of the layout processing model 140 or guide the next iteration (e.g., the N+1th iteration).

[0119] In some embodiments, electronic device 120 clusters the plurality of simulation sampling points based on corresponding historical simulation data of the plurality of simulation sampling points to obtain a plurality of groups of simulation sampling points corresponding to a plurality of cluster centers. For each simulation sampling point in a group of simulation sampling points, electronic device 120 determines a first simulation sampling point in the group of simulation sampling points based on a distance between each simulation sampling point and the cluster center corresponding to the group of simulation sampling points.

[0120] As described above, through clustering, electronic device 120 can divide a large number of simulation sampling points into a number of clusters, each of which is represented by a cluster center, which is the average or center position of all data points within the cluster. As an example, after completing the above clustering, electronic device 120 can determine the simulation sampling points clustered into the same cluster as a group of simulation sampling points.

[0121] As an example, for a group of simulated sampling points corresponding to each cluster center, the electronic device 120 can calculate the distance between each simulated sampling point in the group and the cluster center. For example, the distance can be calculated using different metrics, such as Euclidean distance, Manhattan distance, etc., depending on the characteristics of the data.

[0122] After calculating the distance between the simulated sampling point and the cluster center, the electronic device 120 can determine the first simulated sampling point in the group of simulated sampling points based on an appropriate strategy (e.g., minimizing the distance). The first simulated sampling point can be considered the most representative point in the group of simulated sampling points, and its characteristics can better reflect the characteristics of the entire group.

[0123] As an example, the process of determining the first simulation sampling point may include operations such as sorting, comparing, and selecting distances, which may be determined based on actual needs and is not limited in the embodiments of the present disclosure.

[0124] In this way, the electronic device 120 can perform effective cluster analysis on a large number of simulation sampling points based on historical simulation data, and determine the key first simulation sampling point therefrom.

[0125] In some embodiments, the electronic device 120 determines the target parameters 130 for the layout processing model 140 based on at least the simulation performance indicators of the first model sample for the layout processing model 140 .

[0126] As described above, when electronic device 120 optimizes layout processing model 140, it needs to go through multiple iterations to find the most appropriate model sample. During this process, electronic device 120 uses the simulation performance indicators of the model sample for layout processing model 140 in each iteration to determine whether the current iteration meets the termination condition.

[0127] As an example, in the Nth iteration, if the simulation performance index of at least one of the M model samples 320-1 to 320-M meets the termination condition, the electronic device 120 may select the model sample with the best simulation performance index (or the model sample with the smallest loss value) as the most appropriate model sample for the layout processing model 140 and determine the target parameters 130 based on this model sample. If the simulation performance index of each of the M model samples 320-1 to 320-M does not meet the termination condition, the electronic device 120 may select at least a portion of the M model samples 320-1 to 320-M based on the simulation performance index to construct inputs for the next iteration, and execute the next iteration based on the constructed inputs, until the model samples in a certain iteration meet the termination condition, at which point the electronic device 120 will determine the target parameters 130 based on the model samples that meet the termination condition.

[0128] Through the above embodiments, it can be more clearly understood that according to the embodiments of the present disclosure, a predetermined strategy is first used to group the simulation sampling points, and then the simulation performance indicators of the model samples are calculated based on the grouped simulation data. In this way, the embodiments of the present disclosure significantly reduce the number of simulation sampling points involved in the simulation calculation while ensuring that the simulation sampling points can cover key locations on the target object. This can effectively reduce the resource consumption and time cost of the simulation calculation (the time cost can be reduced by 40% or more), thereby improving the optimization speed of the layout processing model 140.

[0129] Figure 6 1 is a block diagram of an electronic device 600 in which one or more embodiments of the present disclosure may be implemented. The electronic device 600 may be used to implement, for example, Figure 1 The electronic device 120 is shown. It should be understood that Figure 6 The illustrated electronic device 600 is merely exemplary and should not be construed as limiting the functionality and scope of the embodiments described herein.

[0130] like Figure 6 As shown, electronic device 600 is in the form of a general electronic device. Components of electronic device 600 may include, but are not limited to, one or more processors or processing units 610, memory 620, storage device 630, one or more communication units 640, one or more input devices 650, and one or more output devices 660. Processing unit 610 may be a real or virtual processor and is capable of performing various processes according to programs stored in memory 620. In a multi-processor system, multiple processing units execute computer-executable instructions in parallel to increase the parallel processing capabilities of electronic device 600.

[0131] The electronic device 600 typically includes a plurality of computer storage media. Such media can be any available media accessible to the electronic device 600, including but not limited to volatile and non-volatile media, removable and non-removable media. The memory 620 can be a volatile memory (e.g., registers, cache, random access memory (RAM)), a non-volatile memory (e.g., read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory), or some combination thereof. The storage device 630 can be a removable or non-removable medium and can include a machine-readable medium, such as a flash drive, a disk, or any other medium that can be used to store information and / or data and can be accessed within the electronic device 600.

[0132] The electronic device 600 may further include additional removable / non-removable, volatile / non-volatile storage media. Figure 6 As shown in FIG, a magnetic disk drive for reading from or writing to a removable, non-volatile magnetic disk (e.g., a "floppy disk") and an optical disk drive for reading from or writing to a removable, non-volatile optical disk may be provided. In these cases, each drive may be connected to a bus (not shown) by one or more data media interfaces. Memory 620 may include a computer program product 625 having one or more program modules configured to perform various methods or actions of various embodiments of the present disclosure.

[0133] The communication unit 640 enables communication with other electronic devices via a communication medium. Additionally, the functions of the components of the electronic device 600 can be implemented in a single computing cluster or multiple computing machines that can communicate via a communication connection. Thus, the electronic device 600 can operate in a networked environment using a logical connection with one or more other servers, a network personal computer (PC), or another network node.

[0134] The input device 660 may be one or more input devices, such as a mouse, keyboard, or trackball. The output device 660 may be one or more output devices, such as a display, a speaker, or a printer. The electronic device 600 may also communicate with one or more external devices (not shown) via the communication unit 640 as needed, such as a storage device, a display device, or the like, with one or more devices that allow a user to interact with the electronic device 600, or with any device that allows the electronic device 600 to communicate with one or more other electronic devices (e.g., a network card, a modem, etc.). Such communication may be performed via an input / output (I / O) interface (not shown).

[0135] According to an exemplary implementation of the present disclosure, a computer-readable storage medium is provided, on which computer-executable instructions are stored, wherein the computer-executable instructions are executed by a processor to implement the method described above. According to an exemplary implementation of the present disclosure, a computer program product is also provided, which is tangibly stored on a non-transitory computer-readable medium and includes computer-executable instructions, and the computer-executable instructions are executed by a processor to implement the method described above.

[0136] Various aspects of the present disclosure are described herein with reference to flowcharts and / or block diagrams of methods, apparatuses, devices, and computer program products implemented according to the present disclosure. It should be understood that each block of the flowcharts and / or block diagrams, and combinations of blocks in the flowcharts and / or block diagrams, can be implemented by computer-readable program instructions.

[0137] These computer-readable program instructions can be provided to a processing unit of a general-purpose computer, a special-purpose computer, or other programmable data processing device, thereby producing a machine, such that when these instructions are executed by the processing unit of the computer or other programmable data processing device, a device is generated that implements the functions / actions specified in one or more blocks in the flowchart and / or block diagram. These computer-readable program instructions can also be stored in a computer-readable storage medium, where these instructions cause the computer, programmable data processing device, and / or other device to operate in a specific manner. Thus, the computer-readable medium storing the instructions comprises an article of manufacture that includes instructions for implementing various aspects of the functions / actions specified in one or more blocks in the flowchart and / or block diagram.

[0138] Computer-readable program instructions can be loaded onto a computer, other programmable data processing apparatus, or other device so that a series of operational steps are performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, thereby causing the instructions executed on the computer, other programmable data processing apparatus, or other device to implement the functions / actions specified in one or more boxes in the flowchart and / or block diagram.

[0139] The flow charts and block diagrams in the accompanying drawings show the possible architecture, functions and operations of the systems, methods and computer program products according to multiple implementations of the present disclosure. In this regard, each box in the flow chart or block diagram can represent a part for a module, program segment or instruction, and a part for a module, program segment or instruction comprises one or more executable instructions for realizing the logical function of the specification. In some alternative implementations, the functions marked in the box can also occur in a sequence different from that marked in the accompanying drawings. For example, two continuous boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flow chart, and the combination of the boxes in the block diagram and / or flow chart can be realized by a special hardware-based system that performs the function or action of the specification, or can be realized by a combination of special hardware and computer instructions.

[0140] While various implementations of the present disclosure have been described above, the foregoing description is intended to be illustrative, non-exhaustive, and not limited to the disclosed implementations. Many modifications and variations will be apparent to those skilled in the art without departing from the scope and spirit of the described implementations. The terminology used herein is intended to best explain the principles of the implementations, their practical applications, or improvements to existing technologies, or to enable others skilled in the art to understand the various implementations disclosed herein.

Claims

1. A method for optimizing a layout processing model, characterized in that: include: Determining a plurality of groups of simulation sampling points on a target object related to a layout processing model to be optimized, wherein the plurality of groups of simulation sampling points are obtained by grouping a plurality of simulation sampling points on the target object; determining a first model sample related to the layout process model, wherein the first model sample includes at least one parameter of the layout process model; as well as Based on first simulation data related to the first simulation sampling point in each group of simulation sampling points, a simulation performance indicator of the first model sample for the layout processing model is determined, wherein the first simulation data is determined based at least on a simulation value of a target simulation parameter of the first model sample at the first simulation sampling point, and in at least one group of simulation sampling points, the number of the first simulation sampling points is less than the total number of sampling points in the group of simulation sampling points.

2. The method for optimizing a layout processing model according to claim 1, characterized in that: The plurality of simulation sampling points are grouped in the following manner: The plurality of simulation sampling points are grouped based on corresponding historical simulation data related to the optimization of the layout processing model, so as to determine the plurality of groups of simulation sampling points.

3. The method for optimizing a layout processing model according to claim 2, wherein: The plurality of simulation sampling points are grouped based on corresponding historical simulation data related to the optimization of the layout processing model, including: Determining, based on the similarities between the corresponding historical simulation data of the plurality of simulation sampling points, a degree of relevance of at least two simulation sampling points among the plurality of simulation sampling points with respect to the layout processing model; and The plurality of simulation sampling points are clustered based on the correlation degree of at least two simulation sampling points among the plurality of simulation sampling points with respect to the layout processing model.

4. The method for optimizing a layout processing model according to claim 2, characterized in that: The at least one simulation performance indicator is determined in a first iteration of a plurality of iterations associated with the optimization of the layout process model, and wherein corresponding historical simulation data associated with the layout process model at a second simulation sampling point of the plurality of simulation sampling points is determined in the following manner: determining a plurality of second model samples involved in a second iteration before the first iteration among the plurality of iterations; Determine corresponding second simulation data related to the second simulation sampling point for each second model sample in the plurality of second model samples; as well as Based on the corresponding second simulation data of each second model sample in the plurality of second model samples, corresponding historical simulation data related to the second simulation sampling point and the layout processing model are constructed.

5. The method for optimizing a layout processing model according to claim 4, characterized in that: Determining second simulation data related to the second simulation sampling point for each second model sample in the plurality of second model samples includes: Determining a simulation value of a target simulation parameter for each second model sample in the plurality of second model samples at the second simulation sampling point to obtain a plurality of simulation values ​​respectively corresponding to the plurality of second model samples; and Based on the differences between the plurality of simulation values ​​and a reference value related to the target simulation parameter, second simulation data corresponding to each second model sample in the plurality of second model samples is determined.

6. The method for optimizing a layout processing model according to claim 3, characterized in that: Clustering the plurality of simulation sampling points based on corresponding historical simulation data of the plurality of simulation sampling points comprises: Based on the corresponding historical simulation data of the multiple simulation sampling points, the multiple simulation sampling points are clustered to obtain multiple groups of simulation sampling points corresponding to multiple cluster centers respectively; and the method further includes: For each simulation sampling point in a group of simulation sampling points, the first simulation sampling point in the group of simulation sampling points is determined based on a distance between each simulation sampling point and a cluster center corresponding to the group of simulation sampling points.

7. The method for optimizing a layout processing model according to claim 3, characterized in that: Clustering the plurality of simulation sampling points based on corresponding historical simulation data of the plurality of simulation sampling points comprises: Determining, based on corresponding historical simulation data of the plurality of simulation sampling points, a plurality of clustering strategies related to grouping the plurality of simulation sampling points, wherein at least two of the plurality of clustering strategies define different numbers of cluster centers; determining a target clustering strategy among the plurality of clustering strategies based on evaluation results related to each of the plurality of clustering strategies; and Based on the target clustering strategy, the multiple simulation sampling points are grouped to obtain multiple groups of simulation sampling points corresponding to multiple cluster centers respectively.

8. The method for optimizing a layout processing model according to claim 7, characterized in that: The evaluation result related to a clustering strategy among the plurality of clustering strategies indicates a silhouette coefficient of the clustering strategy.

9. The method for optimizing a layout processing model according to claim 1, characterized in that: The method further comprises: Based at least on the at least one simulation performance indicator, target parameters for the layout processing model are determined.

10. An electronic device, characterized in that: include: at least one processing unit; as well as at least one memory coupled to the at least one processing unit and storing instructions for execution by the at least one processing unit, the instructions, when executed by the at least one processing unit, causing the electronic device to perform a method for optimizing a layout process model, the method comprising: Determining a plurality of groups of simulation sampling points on a target object related to a layout processing model to be optimized, wherein the plurality of groups of simulation sampling points are obtained by grouping a plurality of simulation sampling points on the target object; determining a first model sample related to the layout process model, wherein the first model sample includes at least one parameter of the layout process model; and Based on first simulation data related to the first simulation sampling point in each group of simulation sampling points, a simulation performance indicator of the first model sample for the layout processing model is determined, wherein the first simulation data is determined based at least on a simulation value of a target simulation parameter of the first model sample at the first simulation sampling point, and in at least one group of simulation sampling points, the number of the first simulation sampling points is less than the total number of sampling points in the group of simulation sampling points.

11. The electronic device according to claim 10, characterized in that: The plurality of simulation sampling points are grouped in the following manner: The plurality of simulation sampling points are grouped based on corresponding historical simulation data related to the optimization of the layout processing model, so as to determine the plurality of groups of simulation sampling points.

12. The electronic device according to claim 11, characterized in that: The plurality of simulation sampling points are grouped based on corresponding historical simulation data related to the optimization of the layout processing model, including: Determining, based on the similarities between the corresponding historical simulation data of the plurality of simulation sampling points, a degree of relevance of at least two simulation sampling points among the plurality of simulation sampling points with respect to the layout processing model; and The plurality of simulation sampling points are clustered based on the correlation degree of at least two simulation sampling points among the plurality of simulation sampling points with respect to the layout processing model.

13. The electronic device according to claim 11, characterized in that: The at least one simulation performance indicator is determined in a first iteration of a plurality of iterations associated with the optimization of the layout process model, and wherein corresponding historical simulation data associated with the layout process model at a second simulation sampling point of the plurality of simulation sampling points is determined in the following manner: determining a plurality of second model samples involved in a second iteration before the first iteration among the plurality of iterations; Determine corresponding second simulation data related to the second simulation sampling point for each second model sample in the plurality of second model samples; as well as Based on the corresponding second simulation data of each second model sample in the plurality of second model samples, corresponding historical simulation data related to the second simulation sampling point and the layout processing model are constructed.

14. The electronic device according to claim 13, characterized in that: Determining second simulation data related to the second simulation sampling point for each second model sample in the plurality of second model samples includes: Determining a simulation value of a target simulation parameter for each second model sample in the plurality of second model samples at the second simulation sampling point to obtain a plurality of simulation values ​​respectively corresponding to the plurality of second model samples; and Based on the differences between the plurality of simulation values ​​and a reference value related to the target simulation parameter, second simulation data corresponding to each second model sample in the plurality of second model samples is determined.

15. The electronic device according to claim 12, characterized in that: Clustering the plurality of simulation sampling points based on corresponding historical simulation data of the plurality of simulation sampling points comprises: Based on the corresponding historical simulation data of the multiple simulation sampling points, the multiple simulation sampling points are clustered to obtain multiple groups of simulation sampling points corresponding to multiple cluster centers respectively; and the method further includes: For each simulation sampling point in a group of simulation sampling points, the first simulation sampling point in the group of simulation sampling points is determined based on a distance between each simulation sampling point and a cluster center corresponding to the group of simulation sampling points.

16. The electronic device according to claim 12, characterized in that: Clustering the plurality of simulation sampling points based on corresponding historical simulation data of the plurality of simulation sampling points comprises: Determining, based on corresponding historical simulation data of the plurality of simulation sampling points, a plurality of clustering strategies related to grouping the plurality of simulation sampling points, wherein at least two of the plurality of clustering strategies define different numbers of cluster centers; determining a target clustering strategy among the plurality of clustering strategies based on evaluation results related to each of the plurality of clustering strategies; and Based on the target clustering strategy, the multiple simulation sampling points are grouped to obtain multiple groups of simulation sampling points corresponding to multiple cluster centers respectively.

17. The electronic device according to claim 16, characterized in that: The evaluation result related to a clustering strategy among the plurality of clustering strategies indicates a silhouette coefficient of the clustering strategy.

18. The electronic device according to claim 10, characterized in that: The method further comprises: Based at least on the at least one simulation performance indicator, target parameters for the layout processing model are determined.

19. A computer-readable storage medium, characterized in that: A computer program is stored thereon, and the computer program can be executed by a processor to implement the method for optimizing a layout processing model according to any one of claims 1 to 9.

20. A computer program product, characterized in that The method comprises computer executable instructions, wherein the computer executable instructions implement the method for optimizing a layout processing model according to any one of claims 1 to 9 when being executed by a processor.

Images