Method and device for classifying optical defects in semiconductor layout and medium

Abstract

The invention provides a method and equipment for classifying optical defects in a semiconductor layout and a medium. The method for classifying the optical defects in the semiconductor layout comprises the following steps: acquiring the optical defects detected in a target semiconductor layout, and generating identification values of the optical defects; importing a pre-constructed defect library, wherein the defect library is used for storing identification values of allowable optical defects; matching the detected optical defects in a defect library according to the identification values of the detected optical defects, and classifying the successfully matched optical defects and the unsuccessfully matched optical defects to obtain a classification result; and outputting related information of the optical defect according to a classification result. According to the scheme, the known allowable optical defects are automatically identified and screened through the pre-constructed defect library, so that the number of defects needing to be re-judged is remarkably reduced, and the defect processing efficiency and the automation level are improved; and related information of the optical defects is output according to the classification result, so that specific conditions of the optical defects can be intuitively known.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of semiconductor, and particularly relates to a method, device and medium for classifying optical defects in a semiconductor layout. BACKGROUND

[0002] In the past few decades, the development of integrated circuit manufacturing has been following Moore's Law, i.e. the number of transistors per unit area doubles every 18 to 24 months. In order to realize the continuous reduction of transistor size, the industry widely uses a light source with a wavelength of 193 nanometers for photolithography. However, as the process node enters the deep submicron or even nanometer level, the minimum feature size of the transistor is much smaller than the wavelength of the photolithography light source, resulting in a significant increase in optical proximity effect (OPE), which seriously reduces the quality of photolithography imaging and brings great challenges to the photolithography process.

[0003] In order to cope with these challenges and improve the chip manufacturing yield, the industry has proposed a variety of resolution enhancement techniques (RETs). Among them, optical proximity correction (OPC) is a widely used technology. The basic principle of OPC is to simulate and model the photolithography process, and iteratively adjust the mask pattern using numerical optimization methods, so that the final simulation exposure profile is as close as possible to the original design pattern.

[0004] As the performance, power consumption and integration requirements of integrated circuits continue to improve, chip manufacturers continue to increase the transistor density per unit area, making the circuit element patterns in the layout become smaller and smaller and the spacing between them become closer and closer. Affected by factors such as wavelength limitations of light sources, increasing design complexity, and limitations of RET technology itself, even after OPC optimization, abnormal phenomena such as shrinkage and bridging may still occur in local areas in the photolithography simulation results. Such problems are referred to as optical defects or lithography hotspots.

[0005] These optical defects or lithography hotspots will directly affect the quality of the patterns finally transferred to the wafer, and then affect the circuit performance, and may even cause the chip to malfunction. Therefore, lithography rule check (LRC) has become an indispensable important part of the modern photolithography process simulation flow, and has key significance for improving chip yield and ensuring product reliability.

[0006] With the continuous evolution of the integrated circuit manufacturing process node, the transistor structure is increasingly complex, and the process window required to be defined and detected is more and more numerous and more and more fine. In the photolithography simulation and verification link, the number of optical defects detected by the LRC increases sharply, sometimes even up to millions or even tens of millions. This greatly increases the workload and difficulty of defect rejudgment, seriously affecting the overall process efficiency. SUMMARY

[0007] An object of the present application is to improve the defect processing efficiency and automation level.

[0008] A further object of the present application is to intuitively understand the specific situation of optical defects.

[0009] In particular, the present application provides a method for classifying optical defects in a semiconductor layout, comprising: obtaining detected optical defects in a target semiconductor layout, and generating an identification value of the optical defects; importing a pre-constructed defect library, wherein the defect library is used to store the identification values of allowable optical defects; matching the detected optical defects in the defect library according to the identification values of the detected optical defects, classifying the optical defects that match successfully and the optical defects that fail to match, and obtaining a classification result; and outputting the related information of the optical defects according to the classification result.

[0010] Optionally, the step of generating the identification value of the optical defects comprises: obtaining line segment information of a circuit element pattern near the optical defects; determining a hash point of the optical defects according to the line segment information; preprocessing the line segments within a preset range of the hash point; and calculating the hash value of the optical defects as the identification value according to the preprocessed line segments.

[0011] Optionally, the step of outputting the related information of the optical defects according to the classification result further comprises: judging whether there is a new allowable optical defect in the optical defects that fail to match; and if so, saving the new allowable optical defect and the corresponding identification value to the defect library to update the defect library.

[0012] Optionally, the step of outputting the related information of the optical defects according to the classification result comprises: outputting the position information and size information of the optical defects that match successfully and the optical defects that fail to match through a preset graphical user interface.

[0013] Optionally, the step of pre-constructing the defect library comprises: obtaining a pre-collected optical defect sample set, generating an identification value for each optical defect in the optical defect sample set; and screening out the allowable optical defects in the optical defect sample set and saving the corresponding identification values to construct the defect library.

[0014] Optionally, the step of saving the identification value corresponding to the allowable optical defect further comprises saving the graphic information corresponding to the allowable optical defect and the criterion for determining whether the optical defect is allowable.

[0015] Optionally, the criterion for determining whether the optical defect is allowable comprises: determining that the optical defect is not allowable when the optical defect is a bridge; and determining that the optical defect is not allowable when the optical defect is a pinch and the pinch range exceeds a preset range.

[0016] According to another aspect of the present application, there is also provided a computer device comprising a memory, a processor, and a computer program stored in the memory and running on the processor, and the processor implements the classification method of optical defects in a semiconductor layout when executing the computer program.

[0017] According to another aspect of the present application, there is also provided a computer readable storage medium having a computer program stored thereon, and the computer program implements the classification method of optical defects in a semiconductor layout when executed by a processor.

[0018] According to another aspect of the present application, there is also provided a computer program product comprising a computer program, and the computer program implements the classification method of optical defects in a semiconductor layout when executed by a processor.

[0019] The classification method of optical defects in a semiconductor layout according to the present application obtains optical defects detected in a target semiconductor layout, generates an identification value of the optical defects, imports a pre-constructed defect library, matches the detected optical defects in the defect library according to the identification value of the detected optical defects, classifies optical defects that are successfully matched and optical defects that are not successfully matched, obtains a classification result, and outputs related information of the optical defects according to the classification result. The known allowable optical defects are automatically identified and screened through the pre-constructed defect library, thereby significantly reducing the number of defects that need to be re-judged and improving the defect processing efficiency and automation level.

[0020] Further, the classification method of optical defects in a semiconductor layout according to the present application classifies the detected optical defects and outputs related information according to the classification result, which facilitates intuitive understanding of the specific conditions of the optical defects. After the step of outputting the related information of the optical defects according to the classification result, it is determined whether there is a new allowable optical defect in the optical defects that are not successfully matched, and when the result is yes, the new allowable optical defect and the corresponding identification value are saved to the defect library to update the defect library, effectively implementing iteration of the defect library, and ensuring the accuracy of classification and screening of the optical defects.

[0021] The above and other objects, advantages and features of the present application will become more apparent after a reading of the following detailed description of the embodiments thereof, given simply by way of illustration to provide a broad understanding of the principles of the application, where the same reference numerals are used to refer to the same components throughout the several drawings. BRIEF DESCRIPTION OF DRAWINGS

[0022] Some specific embodiments of the present application will now be described in detail by way of illustration, but not limitation, with reference to the drawings in which:

[0023] Figure 1 is a schematic diagram of a method for classifying optical defects in a semiconductor layout according to an embodiment of the present application;

[0024] Figure 2 is a detailed flowchart of a method for classifying optical defects in a semiconductor layout according to an embodiment of the present application;

[0025] Figure 3 is a schematic diagram of a computer program product according to an embodiment of the present application;

[0026] Figure 4 is a schematic diagram of a computer-readable storage medium according to an embodiment of the present application; and

[0027] Figure 5 is a schematic diagram of a computer device according to an embodiment of the present application. DETAILED DESCRIPTION

[0028] The present embodiment provides a method for classifying optical defects in a semiconductor layout, which automatically identifies and filters known allowable optical defects through a pre-constructed defect library, thereby significantly reducing the number of defects that need to be re-judged and improving defect processing efficiency and automation level. Figure 1 is a schematic diagram of a method for classifying optical defects in a semiconductor layout according to an embodiment of the present application. As shown in Figure 1 , the method for classifying optical defects in a semiconductor layout of the present embodiment can generally include:

[0029] Step S102, obtaining detected optical defects in a target semiconductor layout, and generating an identification value of the optical defects;

[0030] Step S104, importing a pre-constructed defect library;

[0031] Step S106, matching the detected optical defects in the defect library according to the identification value of the detected optical defects, classifying the optical defects that match successfully and the optical defects that fail to match, and obtaining a classification result;

[0032] Step S108, outputting related information of the optical defects according to the classification result.

[0033] In the above steps, the optical defects detected in step S102 can be allowable optical defects or can not be allowable optical defects. Allowable optical defects refer to optical defects that do not affect the quality of patterns and the performance of circuits finally transferred onto a wafer, or affect the quality of patterns and the performance of circuits finally transferred onto a wafer to a small extent that can be accepted, ignored, and absolutely do not cause chip functional failure.

[0034] In a preferred embodiment, generating the identification value of the optical defect in step S102 can include: obtaining line segment information of a circuit element pattern near the optical defect; determining a hash point of the optical defect according to the line segment information; preprocessing line segments within a preset range of the hash point; and calculating a hash value of the optical defect as the identification value according to the preprocessed line segments.

[0035] The defect library in step S104 is used to store identification values of allowable optical defects. Step S106 matches the detected optical defects in the defect library according to the identification values of the detected optical defects, classifies the optical defects that match successfully and the optical defects that match unsuccessfully, and obtains a classification result. Since the defect library stores identification values of allowable optical defects, the optical defects that match successfully can be classified as allowable optical defects, and the optical defects that match unsuccessfully can be classified as not allowable optical defects.

[0036] Step S108 outputs related information of the optical defects according to the classification result. In a specific embodiment, the position information and size information of the optical defects that match successfully and the optical defects that match unsuccessfully can be output through a preset graphical user interface. Since the optical defects that match successfully are allowable optical defects, they can be directly filtered. The optical defects that match unsuccessfully are not allowable optical defects, and need to be re-judged or analyzed.

[0037] The classification method of optical defects in a semiconductor layout of the present embodiment obtains optical defects detected in a target semiconductor layout, generates an identification value of the optical defects, imports a pre-constructed defect library, matches the detected optical defects in the defect library according to the identification values of the detected optical defects, classifies the optical defects that match successfully and the optical defects that match unsuccessfully, obtains a classification result, and outputs related information of the optical defects according to the classification result. By using the pre-constructed defect library, known allowable optical defects can be automatically recognized and screened, thereby significantly reducing the number of defects that need to be re-judged and improving the defect processing efficiency and automation level.

[0038] In some optional embodiments, higher technical effects can be achieved through further optimization and configuration of the above steps. The classification method of optical defects in a semiconductor layout according to an optional execution flow of the present embodiment will be described in detail below. This embodiment is only an example of the execution flow, and in specific implementation, the execution order and running conditions of some steps can be modified according to specific implementation requirements. Figure 2 is a detailed flowchart of the classification method of optical defects in a semiconductor layout according to an embodiment of the present application. The classification method of optical defects in a semiconductor layout includes the following steps:

[0039] Step S202, obtaining the detected optical defects in the target semiconductor layout;

[0040] Step S204, obtaining line segment information of circuit element patterns near the optical defects;

[0041] Step S206, determining the hash point of the optical defects according to the line segment information;

[0042] Step S208, preprocessing the line segments within the preset range of the hash point;

[0043] Step S210, calculating the hash value of the optical defects as the identification value according to the preprocessed line segments;

[0044] Step S212, importing a pre-constructed defect library;

[0045] Step S214, matching the detected optical defects in the defect library according to the identification value of the detected optical defects, classifying the matched optical defects and the unmatched optical defects, and obtaining a classification result;

[0046] Step S216, outputting the position information and size information of the matched optical defects and the unmatched optical defects through a preset graphical user interface;

[0047] Step S218, determining whether there is a new allowable optical defect in the unmatched optical defects, if yes, executing Step S220, and if no, executing Step S222;

[0048] Step S220, saving the new allowable optical defect and the corresponding identification value to the defect library to update the defect library;

[0049] Step S222, the defect library remains unchanged.

[0050] In the above steps, first, step S202 is performed to obtain a detected optical defect in a target semiconductor layout, wherein the detected optical defect can or can not be an allowable optical defect. Then, steps S204 to S210 can be performed to obtain line segment information of a circuit element pattern near the optical defect, determine a hash point of the optical defect according to the line segment information, pre-process line segments within a preset range of the hash point, and calculate a hash value of the optical defect as an identification value according to the pre-processed line segments, i.e., generate an identification value of the detected optical defect.

[0051] In step S210, the hash value of the optical defect is used as the identification value, because the hash value is a fixed-length string obtained by calculating data through a hash function, and has high efficiency, security, and uniqueness. Through the fixed-length simplified representation, fast comparison, secure verification, efficient storage and retrieval are achieved. The performance of the hash value depends on the design of the hash function, and the hash function needs to balance the calculation speed, collision resistance and security to adapt to different scene requirements. It should be noted that for optical defects with the same pattern characteristics and context information in the same process and simulation environment, the hash values remain the same, thereby realizing standardized identification of optical defects.

[0052] The defect library in step S212 is used to store identification values of allowable optical defects. In a specific embodiment, pre-constructing the defect library can include: obtaining a pre-collected optical defect sample set, generating an identification value for each optical defect in the optical defect sample set, and screening allowable optical defects in the optical defect sample set and saving the corresponding identification values to construct the defect library. In a preferred embodiment, the step of saving the identification values corresponding to the allowable optical defects can also include saving the pattern information corresponding to the allowable optical defects and the standard for determining whether the optical defect is allowable.

[0053] In a specific embodiment, the standard for determining whether the optical defect is allowable can include: determining that the optical defect is not allowable in the case of a bridge; and determining that the optical defect is not allowable in the case of a contraction with a contraction range exceeding a preset range. It should be noted that the above standard for determining whether the optical defect is allowable is only an example and is not a limitation of the present application. In other embodiments, other standards can also be set according to actual conditions. For example, in the case of a broken line segment of a circuit element pattern, it is determined that the optical defect is not allowable.

[0054] Step S214, according to the identification value of the detected optical defect, the detected optical defect is matched in the defect library, and the optical defects matched successfully and the optical defects matched unsuccessfully are classified to obtain a classification result. Since the defect library stores the identification values of the allowable optical defects, the optical defects matched successfully can be classified as the allowable optical defects, and the optical defects matched unsuccessfully can be classified as the optical defects not allowable.

[0055] It should be noted that, in the case of the identification value being a hash value, only when the hash value of the detected optical defect and the hash value in the defect library are completely consistent, it is considered that the detected optical defect and the allowable optical defect in the defect library are the same kind of defect, and it is determined that the detected optical defect is matched successfully. As long as the hash value of the detected optical defect and the hash value in the defect library are not completely consistent, it is considered that the detected optical defect and the allowable optical defect in the defect library are different defects, and it is determined that the detected optical defect is matched unsuccessfully.

[0056] Step S216, the position information and size information of the optical defects matched successfully and the optical defects matched unsuccessfully are output through a preset graphical user interface. Since the optical defects matched successfully are the allowable optical defects, they can be directly filtered. The optical defects matched unsuccessfully are not the allowable optical defects, and need to be rejudged or analyzed.

[0057] Step S218, it is judged whether there is a new allowable optical defect in the optical defects matched unsuccessfully. In the case that the judgment result of step S218 is yes, i.e. there is a new allowable optical defect in the optical defects matched unsuccessfully, step S220 is executed to save the new allowable optical defect and the corresponding identification value to the defect library to update the defect library.

[0058] The defect library constructed in advance is based on the optical defect sample set collected in advance. There can be other new optical defects outside the optical defect sample set, i.e. there can be other new allowable optical defects outside the defect library. If there is a new allowable optical defect in the optical defects matched unsuccessfully, the new allowable optical defect and the corresponding identification value are saved to the defect library, which can effectively update the defect library and guarantee the accuracy of the classification and screening of the optical defects.

[0059] In the case that the judgment result of step S218 is no, i.e. there is no new allowable optical defect in the optical defects matched unsuccessfully, step S222 is executed to keep the defect library unchanged. If there is no new allowable optical defect in the optical defects matched unsuccessfully, it is indicated that the defect library does not need to be updated and iterated, and the current state of the defect library can be kept unchanged.

[0060] The classification method of optical defects in the semiconductor layout of the embodiment can automatically identify and screen known allowable optical defects through the pre-constructed defect library, thereby significantly reducing the number of defects that need to be re-judged, improving the defect processing efficiency and automation level; the detected optical defects are classified and relevant information is output according to the classification results, so that the specific situation of the optical defects can be intuitively understood; whether there is a new allowable optical defect in the optical defects that fail to match after the step of outputting the relevant information of the optical defects according to the classification results, and when the result is yes, the new allowable optical defect and the corresponding identification value are saved to the defect library to update the defect library, effectively realizing iteration of the defect library, and guaranteeing the accuracy of classification and screening of the optical defects.

[0061] The embodiment also provides a computer program product, a computer readable storage medium and a computer device. Figure 3 Fig. 5 is a schematic diagram of a computer program product 500 according to an embodiment of the present application. Figure 4 Fig. 3 is a schematic diagram of a computer readable storage medium 300 according to an embodiment of the present application. Figure 5 Fig. 4 is a schematic diagram of a computer device 400 according to an embodiment of the present application.

[0062] The computer program product 500 includes a computer program 310, which, when executed by the processor 410, implements any of the above-mentioned classification methods of optical defects in a semiconductor layout. The computer readable storage medium 300 has the above-mentioned computer program 310 stored thereon, and the computer program 310, when executed by the processor 410, implements any of the above-mentioned classification methods of optical defects in a semiconductor layout. The computer device 400 can include a memory 420, a processor 410, and a computer program 310 stored on the memory 420 and running on the processor 410, and the processor 410, when executing the computer program 310, implements any of the above-mentioned classification methods of optical defects in a semiconductor layout.

[0063] The computer program 310 for executing the operation of the present application can be assembly instructions, Instruction Set Architecture (ISA) instructions, machine instructions, machine-related instructions, microcode, firmware instructions, state setting data, configuration data of integrated circuits, or source code or object code written in any combination of one or more programming languages and process programming languages.

[0064] The computer program 310 can execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the latter scenario, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or the connection can be made to an external computer (for example, through the Internet using an Internet Service Provider).

[0065] In some embodiments, an electronic circuit comprising, for example, a programmable logic circuit, a Field-Programmable Gate Array (FPGA) or a Programmable Logic Array (PLA) can execute the computer readable program instructions by utilizing the state of the computer readable program instructions to personalize the electronic circuit, in order to perform aspects of the present application.

[0066] For the purposes of this description, the computer program product 500 is a product, such as a computer program 310, tangibly embodying a computer-readable storage medium 300. For the purposes of this description, the computer-readable storage medium 300 is a tangible device that can retain and store computer-readable program instructions 310, which can be any kind of instructions that can be executed by an instruction execution system, apparatus or device, or any kind of instructions that can be used in combination with an instruction execution system, apparatus or device.

[0067] More specific examples (a non-exhaustive list) of the computer-readable storage medium 300 include the following: a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), a static random access memory (SRAM), a portable compact disc read-only memory (CD-ROM), a digital versatile disk (DVD), a memory stick, a floppy disk, a mechanically encoded device such as punch-cards or raised structures in a groove having instructions recorded thereon, and any suitable combination of the foregoing. A computer-readable storage medium 300, as used herein, is expressly intended to include a computer-readable storage medium 300 that is tangible.

[0068] It is to be appreciated that the logical and / or steps represented in the flow diagrams, or otherwise described herein, can be considered as a list of executable instructions for implementing the logical function represented by the steps, and can be embodied in any machine-readable storage medium for use by or in connection with an instruction execution system, apparatus, or device, such as a computer-based system, processor-containing system, or other system that can fetch the instructions from the instruction execution system, apparatus, or device and execute the instructions, or combination thereof.

[0069] It should be understood that parts of the application can be implemented in hardware, software, firmware or a combination thereof. In the above embodiments, several steps or methods can be implemented in software or firmware stored in a memory and executed by a suitable instruction execution system.

[0070] The computer device 400 can be, for example, a server, a desktop computer, a notebook computer, a tablet computer, or a smartphone. In some examples, the computer device 400 can be a cloud computing node. The computer device 400 can be described in the general context of computer system-executable instructions, such as program modules, being executed by a computer system. Generally, program modules can include routines, programs, objects, components, logic, data structures, and the like, that perform particular tasks or implement particular abstract data types. The computer device 400 can be implemented in a distributed cloud computing environment where tasks are performed by remote processing devices that are linked through a communications network. In a distributed cloud computing environment, program modules can be located in local or remote computer system storage media including storage devices.

[0071] The computer device 400 can include a processor 410 suitable for executing stored instructions, a memory 420 that provides temporary storage for operations of the instructions during operation. The processor 410 can be a single-core processor, a multi-core processor, a computing cluster, or any number of other configurations. The memory 420 can include random access memory (RAM), read only memory, flash memory, or any other suitable storage system.

[0072] The processor 410 can be connected to an I / O interface (input / output interface) suitable for connecting the computer device 400 to one or more I / O devices (input / output devices) through a system interconnect (for example, PCI, PCI-Express, etc.). The I / O devices can include, for example, a keyboard and a pointing device, where the pointing device can include a touchpad or a touch screen, and the like. The I / O devices can be built-in components of the computer device 400, or can be devices externally connected to the computer device.

[0073] The processor 410 can also be linked through the system interconnect to a display interface adapted to connect the computer device 400 to a display device. The display device can include a display screen that is a built-in component of the computer device 400. The display device can also include a computer monitor, television, or projector, among others, that is externally connected to the computer device 400. Further, a network interface controller (NIC) can be adapted to connect the computer device 400 to a network through the system interconnect. In some embodiments, the NIC can use any suitable interface or protocol, such as an Internet Small Computer Systems Interface, among others, to transfer data. The network can be a cellular network, a radio network, a wide area network (WAN), a local area network (LAN), or the Internet, among others. Remote devices can be connected to the computing device through the network.

[0074] To this end, those skilled in the art will recognize that the foregoing description has been presented for the sake of illustration and description only. It is not intended to be exhaustive or to limit the application to the precise form disclosed. Many modifications and variations are possible in light of the above teaching. It is intended that the scope of the application encompass all technically feasible combinations of features relating to the principles of the application.

Claims

1. A method for classifying optical defects in a semiconductor layout, comprising: Obtain the optical defects detected in the target semiconductor layout and generate the identification value of the optical defects; Import a pre-built defect library, wherein the defect library is used to store identification values ​​that allow optical defects; Based on the identifier value of the detected optical defect, the detected optical defect is matched in the defect database, and the successfully matched optical defects and the unmatched optical defects are classified to obtain the classification result; as well as Output relevant information about the optical defects based on the classification results.

2. The method of claim 1, wherein the step of generating the identifier value of the optical defect comprises: Obtain line segment information of the circuit element pattern near the optical defect; The hash point of the optical defect is determined based on the line segment information; Preprocess the line segments within the preset range of the hash points; as well as The hash value of the optical defect is calculated based on the preprocessed line segment and used as the identifier value.

3. The method of claim 1, further comprising, after the step of outputting the relevant information of the optical defect according to the classification result: Determine whether there are any new permissible optical defects among the optical defects that failed to match; as well as If so, the new permissible optical defects and their corresponding identifier values ​​are saved to the defect database to update the defect database.

4. The method according to claim 1, wherein the step of outputting relevant information about the optical defect according to the classification result includes: The location and size information of the successfully matched optical defects and the unmatched optical defects are output through a preset graphical user interface.

5. The method of claim 1, wherein the step of pre-constructing the defect library comprises: Obtain a pre-collected set of optical defect samples, and generate the identification value for each optical defect in the set of optical defect samples; as well as The permissible optical defects in the optical defect sample set are selected and their corresponding identifier values ​​are saved to construct the defect library.

6. The method of claim 5, wherein the step of saving the identifier value corresponding to the permissible optical defect further comprises: The graphic information corresponding to the permissible optical defects and the criteria for determining whether they are permissible optical defects are saved.

7. The method of claim 6, wherein the criteria for determining whether an object is a permissible optical defect include: If the optical defect is a bridging defect, it is determined that it is not an acceptable optical defect. If the optical defect is shrinkage and the shrinkage range exceeds a preset range, it is determined that it is not an acceptable optical defect.

8. A computer device comprising a memory, a processor, and a computer program stored in the memory and running on the processor, wherein the processor, when executing the computer program, implements the method for classifying optical defects in a semiconductor layout as described in any one of claims 1 to 7.

9. A computer-readable storage medium having a computer program stored thereon, the computer program being executed by a processor to implement the method for classifying optical defects in a semiconductor layout according to any one of claims 1 to 7.

10. A computer program product, comprising a computer program, characterized in that, When executed by a processor, the computer program implements a method for classifying optical defects in a semiconductor layout as described in any one of claims 1 to 7.

Images