Space array UV LED light source and AI time domain control photoetching method

Abstract

The embodiment of the invention discloses a space array UV LED light source and an AI time domain control photoetching method, and relates to the technical field of photoetching. The method comprises the following steps: acquiring a mask file, and decomposing the mask file to obtain a plurality of basic patterns; based on a preset basic pattern algorithm database, a plurality of UV LED lamp bead control algorithms corresponding to the basic patterns of the mask plate file are obtained respectively, and an initial space array UV LED light source control algorithm is formed; based on a preset neural network, the initial space array UV LED light source control algorithm is optimized in a mechanical learning mode, and an artificial intelligence light source-mask joint optimization algorithm is obtained; and controlling the space array UV LED light source to penetrate through the mask plate to expose a wafer based on the artificial intelligence light source-mask joint optimization algorithm. Compared with a traditional photoetching method, the method has the technical effects of small calculation amount and high product yield.

Description

Technical Field

[0001] The present invention relates to the field of lithography technology, and in particular to a spatial array UV LED light source and an AI time-domain controlled lithography method. Background Art

[0002] The light source structure of a traditional lithography machine is an integral light source, and the scattered light is adjusted to parallel light through energy regulators, multiple groups of refractors, and lens groups. Due to the diffraction of light, the light passing through the edge of the mask pattern diffracts, making the edge pattern blurred. Traditional lithography machines use computational lithography (CL) to achieve source mask optimization (SMO). Although the method of guiding the energy regulator to increase the brightness of the light source and multiple lithography with different masks can partially improve the edge clarity of the mask pattern, the compensation method of computational lithography requires the use of a large amount of empirical data and multiple lithography with different masks, which requires a large amount of calculation and low product yield. Summary of the invention

[0003] The embodiments of the present invention provide a spatial array UV LED light source and an AI time-domain controlled lithography method, aiming to solve the problems of large computational complexity and low product yield of traditional lithography methods.

[0004] In a first aspect, an embodiment of the present invention provides an AI time-domain controlled lithography method, wherein a lithography device includes a spatially arrayed UV LED light source and a mask, and the method includes:

[0005] Acquire a mask file, and decompose the mask file to obtain a plurality of basic patterns;

[0006] Based on a preset basic pattern algorithm database, a plurality of UV LED lamp bead control algorithms corresponding to the plurality of basic patterns of the mask file are respectively obtained to form an initial spatial array UV LED light source control algorithm;

[0007] Based on a preset neural network, the initial spatial array UV LED light source control algorithm is optimized by machine learning to obtain an artificial intelligence light source-mask joint optimization algorithm;

[0008] Based on the artificial intelligence light source-mask joint optimization algorithm, the spatial arrayed UV LED light source is controlled to expose the wafer through the mask plate.

[0009] A further technical solution is that, based on a preset basic pattern algorithm database, a plurality of UV LED lamp bead control algorithms corresponding to the plurality of basic patterns are obtained respectively, including:

[0010] Determine whether there is a UV LED lamp bead control algorithm corresponding to the basic pattern in the basic pattern algorithm database:

[0011] If the basic pattern algorithm database contains a UV LED lamp bead control algorithm corresponding to the basic pattern, the UV LED lamp bead control algorithm corresponding to the basic pattern is read from the basic pattern algorithm database.

[0012] A further technical solution is that, based on a preset basic pattern algorithm database, a plurality of UV LED lamp bead control algorithms corresponding to the plurality of basic patterns are obtained respectively, and further includes:

[0013] If the UV LED lamp bead control algorithm corresponding to the basic pattern does not exist in the basic pattern algorithm database, split the basic pattern into multiple sub-patterns, wherein the UV LED lamp bead control algorithm corresponding to the sub-pattern exists in the basic pattern algorithm database;

[0014] A plurality of UV LED lamp bead control algorithms corresponding to the plurality of sub-patterns are read from the basic pattern algorithm database to form a UV LED lamp bead control algorithm of the basic pattern.

[0015] A further technical solution is that the preset neural network is used to optimize the initial spatial array UV LED light source control algorithm by machine learning to obtain an artificial intelligence light source-mask joint optimization algorithm, including:

[0016] Based on a preset neural network, the lithography results of the initial spatial arrayed UV LED light source control algorithm under a variety of different light source parameter conditions are repeatedly iterated by machine learning until the lithography results converge, thereby obtaining the artificial intelligence light source-mask joint optimization algorithm.

[0017] A further technical solution is that the generation process of the UV LED lamp bead control algorithm of the basic pattern includes:

[0018] Based on a preset neural network, the lithography results of the initial UV LED lamp bead control algorithm preset for the basic pattern under a variety of different light source parameter conditions are repeatedly iterated by machine learning until the lithography results converge, thereby obtaining the UV LED lamp bead control algorithm for the basic pattern.

[0019] A further technical solution is that the method further comprises:

[0020] The UV LED lamp bead control algorithm of the basic pattern is stored in a database to obtain the basic pattern algorithm database.

[0021] In the second aspect, an embodiment of the present invention further provides a spatial arrayed UV LED light source, which is applied to the method described in the first aspect, wherein the spatial arrayed UV LED light source includes a control unit and a plurality of UV LED lamp beads arranged in an array, wherein the control unit is composed of an FTF thin-film transistor, and the control unit can independently control each of the UV LED lamp beads, and the switching of the UV LED lamp beads is controlled by a PWM signal.

[0022] In a third aspect, an embodiment of the present invention further provides an AI time-domain controlled lithography device, which includes a unit for executing the above method.

[0023] In a fourth aspect, an embodiment of the present invention further provides a computer device, which includes a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the above method when executing the computer program.

[0024] In a fifth aspect, an embodiment of the present invention further provides a computer-readable storage medium, wherein the storage medium stores a computer program, and the computer program can implement the above method when executed by a processor.

[0025] The embodiments of the present invention provide a spatial array UV LED light source, AI time-domain controlled lithography method, device, equipment and medium. The method includes: obtaining a mask file, decomposing the mask file to obtain a plurality of basic patterns; based on a preset basic pattern algorithm database, respectively obtaining a plurality of UV LED lamp bead control algorithms corresponding to the plurality of basic patterns of the mask file to form an initial spatial array UV LED light source control algorithm; based on a preset neural network, optimizing the initial spatial array UV LED light source control algorithm by machine learning to obtain an artificial intelligence light source-mask joint optimization algorithm; based on the artificial intelligence light source-mask joint optimization algorithm, controlling the spatial array UV LED light source to expose the wafer through the mask. Compared with traditional computational lithography methods, the present invention does not need to repeat calculations for different mask plates, which greatly saves equipment computing power, equipment storage space and algorithm formation time. In addition, unlike traditional lithography machines that can only use fixed computational lithography compensation methods and apply a large amount of empirical data for correction during the calculation process, the present invention can adjust the light source information in a timely manner through iterative optimization of the light source-mask joint optimization algorithm based on artificial intelligence (AI), provide theoretical guidance for the selection of lithography data, and improve the overall exposure effect of the lithography pattern, thereby increasing the product yield. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying any creative work.

[0027] Figure 1 A schematic flow chart of an AI time-domain controlled lithography method provided in an embodiment of the present invention;

[0028] Figure 2 This is a simplified diagram of the optical path principle of the photolithography machine when all UV LED lamp beads of the spatial array UV LED light source are turned on;

[0029] Figure 3 This is a simplified diagram of the optical path principle of the lithography machine when some UV LED lamp beads of the spatial array UV LED light source are turned on;

[0030] Figure 4 A schematic diagram of the structure of a spatial array UV LED light source is provided for an embodiment of the present invention;

[0031] Figure 5 A schematic block diagram of an AI time-domain controlled lithography device provided by an embodiment of the present invention;

[0032] Figure 6 A schematic block diagram of a computer device provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0033] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0034] It should be understood that when used in this specification and the appended claims, the terms "include" and "comprises" indicate the presence of described features, integers, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or combinations thereof.

[0035] It should also be understood that the terms used in this specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. As used in the specification of the present invention and the appended claims, unless the context clearly indicates otherwise, the singular forms "a", "an" and "the" are intended to include plural forms.

[0036] It should be further understood that the term "and / or" used in the present description and the appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0037] As used in this specification and the appended claims, the term "if" may be interpreted as "when" or "upon" or "in response to determining" or "in response to detecting," depending on the context. Similarly, the phrases "if it is determined" or "if [described condition or event] is detected" may be interpreted as meaning "upon determination" or "in response to determining" or "upon detection of [described condition or event]" or "in response to detecting [described condition or event]," depending on the context.

[0038] See also Figure 1 , an embodiment of the present invention provides an AI time-domain controlled lithography method. Different from the prior art, in the embodiment of the present invention, the lithography equipment includes a spatial arrayed UV LED light source and a mask. The spatial arrayed UVLED light source includes a control unit and a plurality of UV LED lamp beads arranged in an array, the control unit is composed of FTF thin-film transistors, the control unit can independently control each of the UV LED lamp beads, and the switch of the UV LED lamp beads is controlled by a PWM signal. Figure 1 As shown, the method includes the following steps S1-S4.

[0039] S1, obtaining a mask file, and decomposing the mask file to obtain a plurality of basic patterns.

[0040] In a specific implementation, the mask file can be uploaded by the user. After receiving the mask file, the mask pattern in the mask file is feature extracted, and the data in the basic pattern database (the basic pattern database stores a variety of basic patterns) is compared to divide the mask pattern into a plurality of different basic patterns, that is, to obtain a basic pattern group. The basic patterns include circles, rectangles, triangles, trapezoids, squares, diamonds, stars, quadrilaterals, pentagons and polygons, etc., which are not specifically limited in the present invention.

[0041] Taking a circle as an example, when the mask pattern includes a circle, since the circle is a pattern in the basic pattern database, the circle in the mask pattern is directly extracted as its basic pattern.

[0042] Taking the pentagram as an example, when the mask pattern includes the pentagram, since the pentagram is not a pattern in the basic pattern database, but the isosceles triangle and the pentagon are both patterns in the basic pattern database, the pentagram is extracted and compared with the data in the basic pattern database, and the pentagram is divided into five isosceles triangles and one pentagon as its basic pattern.

[0043] S2, based on a preset basic pattern algorithm database, respectively obtain a plurality of UV LED lamp bead control algorithms corresponding to a plurality of the basic patterns of the mask file to form an initial spatial array UV LED light source control algorithm.

[0044] In a specific implementation, the basic pattern algorithm database stores UV LED lamp bead control algorithms corresponding to all basic patterns.

[0045] It can be understood that in the present invention, the UV LED lamp bead control algorithm of the basic pattern is obtained in advance, and the basic pattern algorithm database is constructed based on the UV LED lamp bead control algorithm of the basic pattern.

[0046] The generation process of the UV LED lamp bead control algorithm of the basic pattern includes: based on a preset neural network, the photolithography results of the initial UV LED lamp bead control algorithm preset for the basic pattern under a variety of different light source parameter conditions are repeatedly iterated by machine learning until the photolithography results converge, thereby obtaining the UV LED lamp bead control algorithm of the basic pattern. The initial UV LED lamp bead control algorithm includes a source-mask collaborative optimization algorithm, an optical proximity effect correction algorithm, and a computational lithography algorithm.

[0047] The neural network may be specifically a BP neural network, and the generation process of the UV LED lamp bead control algorithm of the basic pattern specifically includes:

[0048] First, a digital file of the basic pattern of the mask is uploaded to the device;

[0049] The lithography results optimized by lithography algorithms such as "light source-mask collaborative optimization algorithm", "optical proximity effect correction algorithm" and "computational lithography algorithm" under different set light source parameter conditions are collected; the artificial intelligence model (AI) constructed by machine learning based on the BP neural network is modeled and iteratively calculated to obtain the light source parameter data when the lithography result is optimal and the correspondence between the lithography result and the light source parameters; the UV LED lamp bead control algorithm of the basic pattern is formed.

[0050] Taking the basic pattern as a circle as an example, the digital file of the circular mask is uploaded to the device, and the lithography results optimized by lithography algorithms such as "light source-mask collaborative optimization algorithm", "optical proximity effect correction" and "computational lithography" under different preset light source parameter conditions are collected. The artificial intelligence model (AI) built based on BP neural network machine learning models the lithography results and light source parameters and iterates the calculations. The light source parameter data when the lithography result is optimal and the corresponding relationship between the lithography result and the light source parameters are obtained to form a UV LED lamp bead control algorithm for the circular mask pattern.

[0051] Further, the UV LED lamp bead control algorithm of the basic pattern is stored in a database to obtain the basic pattern algorithm database. Specifically, the UV LED lamp bead control algorithms of all basic patterns are stored in a database to obtain the basic pattern algorithm database.

[0052] Furthermore, a plurality of UVLED lamp bead control algorithms corresponding to the plurality of basic patterns are respectively obtained from the basic pattern algorithm database to form an initial spatial array UV LED light source control algorithm.

[0053] In one embodiment, the above step of "obtaining a plurality of UV LED lamp bead control algorithms corresponding to a plurality of the basic patterns of the mask file based on a preset basic pattern algorithm database" specifically includes the following steps S21-S24:

[0054] S21, determining whether there is a UV LED lamp bead control algorithm corresponding to the basic pattern in the basic pattern algorithm database.

[0055] In the specific implementation, first, determine whether there is a UV LED lamp bead control algorithm corresponding to the basic pattern in the basic pattern algorithm database. If there is a UV LED lamp bead control algorithm corresponding to the basic pattern in the basic pattern algorithm database, call it directly. Under normal circumstances, the UV LED lamp bead control algorithm corresponding to the basic pattern exists in the basic pattern algorithm database, but the situation that it does not exist is not ruled out. If there is no UV LED lamp bead control algorithm corresponding to the basic pattern in the basic pattern algorithm database, it is necessary to split the basic pattern.

[0056] S22: If the basic pattern algorithm database contains a UV LED lamp bead control algorithm corresponding to the basic pattern, read the UV LED lamp bead control algorithm corresponding to the basic pattern from the basic pattern algorithm database.

[0057] In a specific implementation, if the basic pattern algorithm database contains a UV LED lamp bead control algorithm corresponding to the basic pattern, the UV LED lamp bead control algorithm corresponding to the basic pattern is directly read from the basic pattern algorithm database.

[0058] S23, if the UV LED lamp bead control algorithm corresponding to the basic pattern does not exist in the basic pattern algorithm database, split the basic pattern into multiple sub-patterns, wherein the UV LED lamp bead control algorithm corresponding to the sub-patterns exists in the basic pattern algorithm database.

[0059] In a specific implementation, if the UV LED lamp bead control algorithm corresponding to the basic pattern does not exist in the basic pattern algorithm database, the basic pattern is split into multiple sub-patterns, wherein the UV LED lamp bead control algorithm corresponding to the sub-pattern exists in the basic pattern algorithm database; that is, the principle of splitting the sub-pattern is that the UV LED lamp bead control algorithm corresponding to the sub-pattern must be in the basic pattern algorithm database.

[0060] S24, reading a plurality of UV LED lamp bead control algorithms corresponding to the plurality of sub-patterns from the basic pattern algorithm database to form a UV LED lamp bead control algorithm of the basic pattern.

[0061] In a specific implementation, after the basic pattern is split into multiple sub-patterns, multiple UV LED lamp bead control algorithms corresponding to the multiple sub-patterns are read from the basic pattern algorithm database to form the UV LED lamp bead control algorithm of the basic pattern.

[0062] S3, based on a preset neural network, the initial spatial array UV LED light source control algorithm is optimized by machine learning to obtain an artificial intelligence light source-mask joint optimization algorithm.

[0063] In a specific implementation, based on a preset neural network, the lithography results of the initial spatial arrayed UV LED light source control algorithm under a variety of different light source parameter conditions are repeatedly iterated by machine learning until the lithography results converge, thereby obtaining the artificial intelligence light source-mask joint optimization algorithm.

[0064] The neural network can be specifically a BP neural network, and the above step S3 specifically includes: based on the BP neural network mechanical learning, the lithography results under the preset light source parameters such as light source intensity and incident angle are established, and the relationship between the light source parameters and the lithography results is established, and the light source parameters when the best lithography results are obtained by repeated loop calculation. Iterative calculation refers to: the calculation process of the light source parameters when the best lithography results are obtained by repeated loop calculation. Due to the inherent characteristics of the BP neural network in the process of constructing an artificial intelligence model (AI) through mechanical learning, the entire process cannot be trained through a single calculation. It is necessary to repeat the calculation between the lithography results and the lithography data for many times to finally obtain a convergence result, so it is necessary to repeat the calculation process. Taking the mask pattern as a five-pointed star as an example, after obtaining the initial spatial array UV LED light source control algorithm with a mask pattern as a five-pointed star pattern, based on the BP neural network, the lithography results under the preset light source parameters such as light source intensity and incident angle are collected, sorted, repeatedly iterated, and the light source parameters when the lithography results are optimal are determined through mechanical learning, and finally the artificial intelligence (AI) light source-mask joint optimization algorithm is determined.

[0065] It can be understood that the BP neural network is only an example of a neural network provided by the present invention, and those skilled in the art may also adopt other types of neural networks to implement the technical solution of the present invention, which does not exceed the protection scope of the present invention.

[0066] S4, based on the artificial intelligence light source-mask joint optimization algorithm, controlling the spatial arrayed UV LED light source to expose the wafer through the mask plate.

[0067] In a specific implementation, the artificial intelligence light source-mask joint optimization algorithm is used to control the spatial arrayed UVLED light source to expose the wafer through the mask plate.

[0068] Specifically, the spatially arrayed UV LED light source is controlled by an artificial intelligence (AI) light source-mask joint optimization algorithm to achieve spatial regulation and temporal regulation.

[0069] The specific performance of spatial adjustment is that the UV LED lamp beads in the parts that need to be exposed are turned on to perform photolithography on the device, and the UV LED lamp beads in the parts that do not need to be exposed are turned off to avoid device photolithography. Figure 2-Figure 3 , Figure 2 This is a simplified diagram of the optical path principle of the lithography machine when all UV LED lamp beads of the spatial array UV LED light source are turned on. Figure 3 This is a simplified diagram of the optical path principle of the lithography machine when some UV LED lamp beads of the spatial array UVLED light source are turned on. Figure 2-Figure 3 In the figure, 10 refers to the spatial arrayed UV LED light source, 11 refers to the UV LED lamp beads, 20 refers to the first row of compound eye arrays, 30 refers to the second row of compound eye arrays, 40 refers to the mask plate, 50 refers to the focusing lens, and 60 refers to the wafer.

[0070] The time domain regulation is specifically manifested in that the UV LED lamp beads use pulse width modulation (PWM) to set the UV LED lighting cycle to a high-frequency flashing state, and adjust the brightness of each UV LED lamp bead in each pulse interval. At the parts that need to be exposed and the edge of the exposure pattern, the UV LED lamp beads are controlled by PWM to inject a large current into the UV LED lamp beads when they are on, so that the UV LED lamp beads are in the highest brightness and power range when they are working. At the parts that do not need to be exposed, the UV LED lamp beads are controlled by PWM to be in the off state, and the UV LED lamp beads do not work.

[0071] The technical solution of the embodiment of the present invention is to obtain a mask file, decompose the mask file to obtain multiple basic patterns; based on a preset basic pattern algorithm database, obtain multiple UV LED lamp bead control algorithms corresponding to the multiple basic patterns of the mask file respectively, and form an initial spatial array UV LED light source control algorithm; based on a preset neural network, optimize the initial spatial array UV LED light source control algorithm by machine learning to obtain an artificial intelligence light source-mask joint optimization algorithm; based on the artificial intelligence light source-mask joint optimization algorithm, control the spatial array UV LED light source to expose the wafer through the mask. Compared with traditional computational lithography, the present invention does not need to repeat calculations for different masks, which greatly saves equipment computing power, equipment storage space and algorithm formation time. In addition, unlike the traditional lithography machine that can only use a fixed computational lithography compensation method and apply a large amount of empirical data to make corrections during the calculation process, the present invention can timely adjust the light source information through the iterative optimization of the light source-mask joint optimization algorithm based on artificial intelligence (AI), provide theoretical guidance for the selection of lithography data, and improve the overall exposure effect of the lithography pattern, so that the product yield is higher.

[0072] See also Figure 4 An embodiment of the present invention provides a spatial arrayed UV LED light source, which is applied to the AI ​​time-domain controlled lithography method provided in any of the above embodiments. The spatial arrayed UV LED light source 10 includes a control unit and a plurality of UV LED lamp beads 11 arranged in an array. The control unit is composed of FTF thin-film transistors. The control unit can independently control each of the UV LED lamp beads 11, and the switch of the UV LED lamp beads 11 is controlled by a PWM signal.

[0073] See also Figure 5 , Figure 5 is a schematic block diagram of an AI time-domain controlled lithography apparatus provided by an embodiment of the present invention. Corresponding to the above AI time-domain controlled lithography method, the present invention also provides an AI time-domain controlled lithography apparatus 200. The AI ​​time-domain controlled lithography apparatus 200 includes a unit for executing the above AI time-domain controlled lithography method, and the AI ​​time-domain controlled lithography apparatus 200 can be configured in a desktop computer, a tablet computer, a laptop computer, and other terminals. Specifically, the AI ​​time-domain controlled lithography apparatus 200 includes:

[0074] A first acquisition unit 210 is used to acquire a mask file and decompose the mask file to obtain a plurality of basic patterns;

[0075] The second acquisition unit 220 is used to respectively acquire a plurality of UV LED lamp bead control algorithms corresponding to a plurality of the basic patterns of the mask file based on a preset basic pattern algorithm database to form an initial spatial array UV LED light source control algorithm;

[0076] The optimization unit 230 is used to optimize the initial spatial array UV LED light source control algorithm by machine learning based on a preset neural network to obtain an artificial intelligence light source-mask joint optimization algorithm;

[0077] The exposure unit 240 is used to control the spatial arrayed UV LED light source to expose the wafer through the mask plate based on the artificial intelligence light source-mask joint optimization algorithm.

[0078] In one embodiment, the method of obtaining a plurality of UV LED lamp bead control algorithms corresponding to a plurality of basic patterns based on a preset basic pattern algorithm database includes:

[0079] Determine whether there is a UV LED lamp bead control algorithm corresponding to the basic pattern in the basic pattern algorithm database:

[0080] If the basic pattern algorithm database contains a UV LED lamp bead control algorithm corresponding to the basic pattern, the UV LED lamp bead control algorithm corresponding to the basic pattern is read from the basic pattern algorithm database.

[0081] In one embodiment, the method of obtaining a plurality of UV LED lamp bead control algorithms corresponding to a plurality of the basic patterns based on a preset basic pattern algorithm database further includes:

[0082] If the UV LED lamp bead control algorithm corresponding to the basic pattern does not exist in the basic pattern algorithm database, split the basic pattern into multiple sub-patterns, wherein the UV LED lamp bead control algorithm corresponding to the sub-pattern exists in the basic pattern algorithm database;

[0083] A plurality of UV LED lamp bead control algorithms corresponding to the plurality of sub-patterns are read from the basic pattern algorithm database to form a UV LED lamp bead control algorithm of the basic pattern.

[0084] In one embodiment, the preset neural network is used to optimize the initial spatial array UV LED light source control algorithm by machine learning to obtain an artificial intelligence light source-mask joint optimization algorithm, including:

[0085] Based on a preset neural network, the lithography results of the initial spatial arrayed UV LED light source control algorithm under a variety of different light source parameter conditions are repeatedly iterated by machine learning until the lithography results converge, thereby obtaining the artificial intelligence light source-mask joint optimization algorithm.

[0086] In one embodiment, the generation process of the basic pattern UV LED lamp bead control algorithm includes:

[0087] Based on a preset neural network, the lithography results of the initial UV LED lamp bead control algorithm preset for the basic pattern under a variety of different light source parameter conditions are repeatedly iterated by machine learning until the lithography results converge, thereby obtaining the UV LED lamp bead control algorithm for the basic pattern.

[0088] In one embodiment, the AI ​​time-domain controlled lithography apparatus 200 further includes:

[0089] A construction unit is used to store the UV LED lamp bead control algorithm of the basic pattern into a database to obtain the basic pattern algorithm database.

[0090] It should be noted that technical personnel in the relevant field can clearly understand that the specific implementation process of the above-mentioned AI time-domain control lithography device 200 and each unit can refer to the corresponding description in the aforementioned method embodiment, and for the convenience and conciseness of the description, it will not be repeated here.

[0091] The above-mentioned AI time-domain controlled lithography apparatus 200 can be implemented in the form of a computer program. The computer program can be used in Figure 6 Runs on the computer device shown.

[0092] See also Figure 6 , Figure 6 5 is a schematic block diagram of a computer device provided in an embodiment of the present application. The computer device 500 may be a terminal or a server, wherein the terminal may be an electronic device with communication functions such as a smart phone, a tablet computer, a laptop computer, a desktop computer, a personal digital assistant, and a wearable device. The server may be an independent server or a server cluster composed of multiple servers.

[0093] The computer device 500 includes a processor 502 , a memory, and a network interface 505 connected via a system bus 501 , wherein the memory may include a non-volatile storage medium 503 and an internal memory 504 .

[0094] The non-volatile storage medium 503 can store an operating system 5031 and a computer program 5032. When the computer program 5032 is executed, the processor 502 can execute an AI time-domain controlled lithography method.

[0095] The processor 502 is used to provide computing and control capabilities to support the operation of the entire computer device 500 .

[0096] The internal memory 504 provides an environment for the operation of the computer program 5032 in the non-volatile storage medium 503. When the computer program 5032 is executed by the processor 502, the processor 502 can execute an AI time-domain controlled lithography method.

[0097] The network interface 505 is used to communicate with other devices over the network. Those skilled in the art will appreciate that the above structure is only a block diagram of a portion of the structure related to the present application solution, and does not constitute a limitation on the computer device 500 to which the present application solution is applied. The specific computer device 500 may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0098] The processor 502 is used to run a computer program 5032 stored in a memory to implement the steps of an AI time-domain controlled lithography method provided in any of the above method embodiments.

[0099] It should be understood that in the embodiment of the present application, the processor 502 may be a central processing unit (CPU), and the processor 502 may also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. Among them, the general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0100] It is understood by those skilled in the art that all or part of the processes in the method for implementing the above embodiment can be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a storage medium, which is a computer-readable storage medium. The computer program is executed by at least one processor in the computer system to implement the process steps of the embodiment of the above method.

[0101] Therefore, the present invention also provides a storage medium. The storage medium may be a computer-readable storage medium. The storage medium stores a computer program. When the computer program is executed by a processor, the processor executes the steps of an AI time-domain controlled lithography method provided in any of the above method embodiments.

[0102] The storage medium is a physical, non-transient storage medium, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a magnetic disk, or an optical disk, etc., which can store program codes. The computer-readable storage medium can be non-volatile or volatile.

[0103] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in terms of function in the above description. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0104] In the several embodiments provided by the present invention, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of each unit is only a logical function division, and there may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed.

[0105] The steps in the method of the embodiment of the present invention can be adjusted in order, combined and deleted according to actual needs. The units in the device of the embodiment of the present invention can be combined, divided and deleted according to actual needs. In addition, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0106] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a storage medium. Based on this understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, terminal, or network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention.

[0107] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0108] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

[0109] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed by the present invention, and these modifications or replacements should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention shall be based on the protection scope of the claims.

Claims

1. An AI time-domain controlled lithography method, characterized in that: The lithography device includes a spatially arrayed UV LED light source and a mask plate, and the method includes: Acquire a mask file, and decompose the mask file to obtain a plurality of basic patterns; Based on a preset basic pattern algorithm database, a plurality of UV LED lamp bead control algorithms corresponding to the plurality of basic patterns of the mask file are respectively obtained to form an initial spatial array UV LED light source control algorithm; Based on a preset neural network, the initial spatial array UV LED light source control algorithm is optimized by machine learning to obtain an artificial intelligence light source-mask joint optimization algorithm; Based on the artificial intelligence light source-mask joint optimization algorithm, the spatial arrayed UV LED light source is controlled to expose the wafer through the mask plate.

2. The AI ​​time-domain controlled lithography method according to claim 1, characterized in that: The method of obtaining a plurality of UV LED lamp bead control algorithms corresponding to a plurality of basic patterns based on a preset basic pattern algorithm database comprises: Determine whether there is a UV LED lamp bead control algorithm corresponding to the basic pattern in the basic pattern algorithm database: If the basic pattern algorithm database contains a UV LED lamp bead control algorithm corresponding to the basic pattern, the UV LED lamp bead control algorithm corresponding to the basic pattern is read from the basic pattern algorithm database.

3. The AI ​​time-domain controlled lithography method according to claim 2, characterized in that: The method of obtaining a plurality of UV LED lamp bead control algorithms corresponding to a plurality of the basic patterns based on a preset basic pattern algorithm database also includes: If the UV LED lamp bead control algorithm corresponding to the basic pattern does not exist in the basic pattern algorithm database, split the basic pattern into multiple sub-patterns, wherein the UV LED lamp bead control algorithm corresponding to the sub-pattern exists in the basic pattern algorithm database; A plurality of UV LED lamp bead control algorithms corresponding to the plurality of sub-patterns are read from the basic pattern algorithm database to form a UV LED lamp bead control algorithm of the basic pattern.

4. The AI ​​time-domain controlled lithography method according to claim 1, characterized in that: The preset neural network is based on which the initial spatial array UV LED light source control algorithm is optimized by machine learning to obtain an artificial intelligence light source-mask joint optimization algorithm, including: Based on a preset neural network, the lithography results of the initial spatial arrayed UV LED light source control algorithm under a variety of different light source parameter conditions are repeatedly iterated by machine learning until the lithography results converge, thereby obtaining the artificial intelligence light source-mask joint optimization algorithm.

5. The method according to claim 1, characterized in that The generation process of the basic pattern UV LED lamp bead control algorithm includes: Based on a preset neural network, the lithography results of the initial UV LED lamp bead control algorithm preset for the basic pattern under a variety of different light source parameter conditions are repeatedly iterated by machine learning until the lithography results converge, thereby obtaining the UV LED lamp bead control algorithm for the basic pattern.

6. The method according to claim 5, characterized in that The method further comprises: The UV LED lamp bead control algorithm of the basic pattern is stored in a database to obtain the basic pattern algorithm database.

7. A spatial array UV LED light source, characterized in that: Applied to the method described in any one of claims 1 to 6, the spatially arrayed UV LED light source includes a control unit and a plurality of UV LED lamp beads arranged in an array, the control unit is composed of FTF thin-film transistors, the control unit can independently control each of the UV LED lamp beads, and the switching of the UV LED lamp beads is controlled by a PWM signal.

8. An AI time-domain controlled lithography device, characterized in that: The method comprises a unit for executing the method according to any one of claims 1 to 6.

9. A computer device, characterized in that: The computer device includes a memory and a processor, the memory stores a computer program, and the processor implements the method according to any one of claims 1 to 6 when executing the computer program.

10. A computer-readable storage medium, characterized in that: The storage medium stores a computer program, and when the computer program is executed by a processor, the method according to any one of claims 1 to 6 can be implemented.

Images