Information processing apparatus, imprint device, and article manufacturing method

Abstract

To provide an information processing apparatus that facilitates setting of processing conditions for imprint processing.SOLUTION: An information processing apparatus comprises an acquisition unit that acquires a third processing condition by inputting a first processing condition and a second processing condition to a learning model acquired through learning with, as learning data, processing conditions for imprint processing performed on a plurality of shot regions on a substrate. The first processing condition is a condition including information on the size and arrangement of the plurality of shot regions. The second processing condition is a condition set in common to first shot regions of the plurality of shot regions. The third processing condition is a condition set individually to second shot regions different from the first shot regions out of the plurality of shot regions.SELECTED DRAWING: Figure 4

Description

[Technical Field]

[0001] The present invention relates to an information processing apparatus, an imprint apparatus, and a method for manufacturing an article. [Background technology]

[0002] As demand for miniaturization of semiconductor devices and MEMS continues to grow, microfabrication techniques, such as conventional photolithography, are gaining attention. These techniques involve forming an imprint material on a substrate using a mold (master plate, mold) and then forming a pattern of the imprint material on the substrate. This technique, also known as imprinting, can form microstructures on the order of a few nanometers on a substrate. One example of such imprinting techniques is the photocuring method. In an imprinting device employing this photocuring method, a photocurable imprint material is first applied to a shot area on the substrate, which is an imprint region. Next, while aligning the pattern portion of the mold with the shot area, the imprint material is brought into contact with (imprinted onto) the pattern portion of the mold, thereby filling the pattern area with the imprint material. The imprint material is then irradiated with light to harden it, and the pattern portion of the mold is then separated from the imprint material, forming a pattern of the imprint material in the shot area on the substrate.

[0003] Patent Document 1 discloses a method for estimating an alignment correction value using a neural network (multilayer perceptron). The neural network is trained using device information when the pattern was formed and the amount of pattern misalignment (alignment error) measured using an overlay inspection device or the like, and thereafter the amount of pattern misalignment is estimated from the device information to calculate an alignment correction value. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Japanese Patent Application Publication No. 2019-102495 Summary of the Invention [Problem to be solved by the invention]

[0005] In imprinting devices in which the imprint material on the substrate comes into contact with the mold, advance consideration may be required when setting the processing conditions. In particular, for shot areas located on the periphery of the substrate that are partially missing, the processing conditions appropriate for each shot area vary depending on the shape and other characteristics of the shot area. These processing conditions are often determined experimentally, which can be time-consuming. Furthermore, shot areas on the periphery of the substrate may require different processing conditions to be set for each shot, which can make the user's task of inputting processing conditions into the device cumbersome.

[0006] SUMMARY OF THE INVENTION It is therefore an object of the present invention to provide an information processing apparatus that can easily set processing conditions for imprint processing. [Means for solving the problem]

[0007] The information processing device of the present invention includes an acquisition unit that acquires a third processing condition by inputting a first processing condition and a second processing condition into a learning model acquired by learning using processing conditions for imprint processing performed on multiple shot areas on a substrate as learning data, wherein the first processing condition is a condition that includes information regarding the size and arrangement of the multiple shot areas, the second processing condition is a condition that is set commonly to a first shot area among the multiple shot areas, and the third processing condition is a condition that is set individually to a second shot area among the multiple shot areas that is different from the first shot area. [Effects of the Invention]

[0008] According to the present invention, an information processing apparatus that can easily set processing conditions for imprint processing is provided. [Brief explanation of the drawings]

[0009] [Figure 1] FIG. 1 is a diagram illustrating the configuration and operation of an imprint apparatus. [Figure 2] FIG. 1 is a diagram illustrating a configuration of an information processing device. [Figure 3] FIG. 1 is a diagram showing the configuration of an article manufacturing system for manufacturing articles such as semiconductor devices. [Figure 4] 1 is a flowchart showing an imprint method in the imprint apparatus. [Figure 5] FIG. 2 is a diagram showing a plurality of shot areas on a substrate. [Figure 6] FIG. 10 illustrates contact between the imprint material on the substrate and the mold. [Figure 7] 10 is a flowchart illustrating a method for acquiring processing conditions for imprint processing. [Figure 8] FIG. 1 is a diagram illustrating an overview of learning and estimation. [Figure 9] 1 is a flowchart illustrating a learning method for obtaining a learning model. [Figure 10] 10 is a flowchart showing an acquisition method for acquiring a third processing condition using a learning model. DETAILED DESCRIPTION OF THE INVENTION

[0010] Hereinafter, embodiments will be described in detail with reference to the accompanying drawings. Note that the following embodiments do not limit the invention according to the claims. Although multiple features are described in the embodiments, not all of these multiple features are necessarily essential to the invention, and multiple features may be combined arbitrarily. Furthermore, in the accompanying drawings, the same reference numerals are used to designate the same or similar components, and redundant explanations will be omitted. Furthermore, in the accompanying drawings, the drawings may be drawn at a scale different from the actual scale in order to facilitate understanding of the present embodiments.

[0011] First Embodiment Fig. 1 is a diagram showing the configuration and operation of an imprint apparatus. Fig. 1(a) shows an imprint apparatus IMP, which is part of one embodiment of the present invention, performing an imprint process in which an imprint material IM on a substrate S is brought into contact with a pattern region MP of a mold M to harden the imprint material IM, and the hardened imprint material IM is separated from the mold M. A pattern is formed on the substrate S by this imprint process.

[0012] The imprint material is a curable composition (sometimes referred to as an uncured resin) that cures upon application of curing energy. Examples of curing energy include electromagnetic waves and heat. Electromagnetic waves can be, for example, light with a wavelength selected from the range of 10 nm to 1 mm, such as infrared light, visible light, and ultraviolet light. The curable composition can be a composition that cures upon irradiation with light or heat. Among these, photocurable compositions that cure upon irradiation with light contain at least a polymerizable compound and a photopolymerization initiator and may further contain a non-polymerizable compound or solvent, as necessary. The non-polymerizable compound is at least one selected from the group consisting of sensitizers, hydrogen donors, internal mold release agents, surfactants, antioxidants, and polymer components. The imprint material can be arranged on the substrate in the form of droplets, or in the form of islands or films formed by connecting multiple droplets. The viscosity of the imprint material (at 25°C) can be, for example, 1 mPa·s to 100 mPa·s. Examples of materials that can be used for the substrate include glass, ceramics, metals, semiconductors, and resins. If necessary, a member made of a material different from the substrate may be provided on the surface of the substrate. Examples of the substrate include a silicon wafer, a compound semiconductor wafer, and quartz glass.

[0013] In this specification and the accompanying drawings, directions are indicated in an XYZ coordinate system, with the direction parallel to the surface of the substrate S being the XY plane. The directions parallel to the X-axis, Y-axis, and Z-axis in the XYZ coordinate system are the X direction, Y direction, and Z direction, respectively, and rotation around the X-axis, Y-axis, and Z-axis are referred to as θX, θY, and θZ, respectively. Control or drive about the X-axis, Y-axis, and Z-axis refers to control or drive about the direction parallel to the X-axis, Y-axis, and Z-axis, respectively. Control or drive about the θX-axis, θY-axis, and θZ-axis refers to control or drive about the rotation around an axis parallel to the X-axis, Y-axis, and Z-axis, respectively. Position refers to information that can be determined based on coordinates of the X-axis, Y-axis, and Z-axis, and orientation refers to information that can be determined by values ​​of the θX-axis, θY-axis, and θZ-axis. Positioning refers to controlling the position and / or orientation. Alignment may include controlling the position and / or orientation of at least one of the substrate and mold.

[0014] The imprint apparatus IMP may include a substrate holding unit 102 that holds the substrate S, a substrate driving mechanism 105 that drives the substrate holding unit 102 to drive the substrate S, a base 104 that supports the substrate holding unit 102, and a position measurement unit 103 that measures the position of the substrate holding unit 102. The substrate driving mechanism 105 may include a motor such as a linear motor. The imprint apparatus IMP may include a sensor 151 that detects the substrate driving force (alignment load) required for the substrate driving mechanism 105 to drive the substrate S (substrate holding unit 102) during alignment. The substrate driving force during alignment, which is performed while the imprint material IM on the substrate S is in contact with the pattern region MP of the mold M, corresponds to, for example, a shear force acting between the substrate S and the mold M. The shear force is a force that mainly acts in the planar direction of the substrate S and the mold M. The substrate driving force during alignment correlates with, for example, the magnitude of the current supplied to the motor of the substrate driving mechanism 105 during alignment, and the sensor 151 can detect the substrate driving force based on the magnitude of the current. The sensor 151 is an example of a sensor that measures the influence (shear force) that the mold M receives during pattern formation. Furthermore, a drive request (command value) that the control unit 110, which will be described later, issues to the substrate driving mechanism 105 is called a stage control value.

[0015] The imprint apparatus IMP may include a mold holding unit 121 that holds a mold (mold) M, a mold driving mechanism 122 that drives the mold holding unit 121 to drive the mold M, and a support structure 130 that supports the mold driving mechanism 122. The mold driving mechanism 122 may include a motor such as a voice coil motor. The imprint apparatus IMP may include a sensor 152 that detects a release force (separation load) and / or a pressing force. The release force is the force required to separate the mold M from the cured product of the imprint material IM on the substrate S. The pressing force is the force with which the original M is pressed to bring the original M into contact with the imprint material IM on the substrate S. The release force and pressing force are forces that act primarily in a direction perpendicular to the planar direction of the substrate S and the mold M. The release force and pressing force are correlated, for example, to the magnitude of the current supplied to the motor of the mold driving mechanism 122, and the sensor 152 can detect the separation force and pressing force based on the magnitude of the current. The sensor 152 is an example of a sensor that measures the influence (mold release force and / or pressing force) that the mold M receives during pattern formation. In addition, a drive request (command value) that the control unit 110, which will be described later, issues to the mold drive mechanism 122 is also called a stage control value.

[0016] The substrate driving mechanism 105 and the mold driving mechanism 122 constitute driving mechanisms that adjust the relative position and relative attitude of the substrate S and the mold M. Adjustment of the relative position of the substrate S and the mold M by the driving mechanisms includes driving to bring the mold into contact with the imprint material on the substrate S and to separate the mold from the hardened imprint material (the pattern of the hardened material). The substrate driving mechanism 105 can be configured to drive the substrate S about multiple axes (e.g., three axes: X-axis, Y-axis, and θZ-axis, or preferably six axes: X-axis, Y-axis, Z-axis, θX-axis, θY-axis, and θZ-axis). The mold driving mechanism 122 can be configured to drive the mold M about multiple axes (e.g., three axes: Z-axis, θX-axis, and θY-axis, or preferably six axes: X-axis, Y-axis, Z-axis, θX-axis, θY-axis, and θZ-axis).

[0017] The imprint apparatus IMP may include a mold transport mechanism 140 that transports the mold M, and a mold cleaner 150. The mold transport mechanism 140 may be configured to transport the mold M to the mold holding unit 121, or to transport the mold M from the mold holding unit 121 to an original stocker (not shown) or the mold cleaner 150. The mold cleaner 150 cleans the mold M with ultraviolet light, a chemical solution, or the like.

[0018] The mold holding unit 121 may include a window member 125 that forms a pressure-controlled space CS on the back surface of the mold M (the surface opposite to the pattern region MP where the pattern to be transferred to the substrate S is formed). The imprint apparatus IMP may include a deformation mechanism 123 that controls the pressure in the pressure-controlled space CS (hereinafter referred to as the cavity pressure) to deform the pattern region MP of the mold M into a convex shape toward the substrate S, as schematically shown in FIG. 1(b). The imprint apparatus IMP may also include an alignment measurement instrument 106, a curing unit 107, an imaging unit 112, and an optical member 111. The alignment measurement instrument 106 measures the relative position between the alignment marks on the substrate S and the mold M by illuminating them and capturing their images. The imprint apparatus IMP is equipped with multiple alignment measurement instruments 106 and can simultaneously observe multiple alignment marks formed in the shot region of the substrate S and the mold M. For example, the system includes four alignment measurement instruments 106 that observe alignment marks formed in the shot area of ​​the substrate S and at the four corners of the mold M. The alignment measurement instruments 106 can be positioned by a drive mechanism (not shown) according to the position of the alignment mark to be observed. Hereinafter, an image captured by the alignment measurement instruments is referred to as an alignment image, and the alignment mark position measured by the alignment measurement instruments is referred to as an alignment measurement value. An example of an alignment image observed by the alignment measurement instruments is an image captured of reflected light from alignment marks on the substrate and the original. Alternatively, an image captured of an image resulting from moire fringes of the alignment marks on the substrate and the original may be used. The curing unit 107 irradiates the imprint material IM with energy (e.g., ultraviolet light) for curing the imprint material IM via the optical member 111, thereby curing the imprint material IM. The imaging unit 112 images the substrate S, the mold M, and the imprint material IM via the optical member 111 and the window member 125. Hereinafter, the image captured by the image capturing unit 112 will be referred to as a spread image.

[0019] The imprint apparatus IMP may include a dispenser 108 that places the imprint material IM on the substrate S. The dispenser 108 dispenses the imprint material IM so that the imprint material IM is placed on the substrate S, for example, according to a drop recipe that indicates the placement of the imprint material IM. The imprint apparatus IMP may include a control unit 110 (information processing device) that controls the substrate driving mechanism 105, the mold driving mechanism 122, the deformation mechanism 123, the mold transport mechanism 140, the mold cleaner 150, the alignment measurement instrument 106, the curing unit 107, the imaging unit 112, the dispenser 108, and the like. The control unit 110 may be configured, for example, by a PLD (abbreviation for Programmable Logic Device) such as an FPGA (abbreviation for Field Programmable Gate Array), an ASIC (abbreviation for Application Specific Integrated Circuit), a general-purpose computer with an embedded program, or a combination of all or part of these.

[0020] FIG. 2 is a diagram illustrating the configuration of an information processing device. The configuration of the information processing device of the control unit 110 will be described as an example, but the control device 1003 and information processing device 1007 (described later) may also have a similar configuration. The processing unit 113 is a central processing unit (CPU) that executes an operating system (OS) and various application programs. The processing unit 113 is not limited to a central processing unit, but may be a processor or circuit such as a microprocessing unit (MPU), a graphics processing unit (GPU), or an application-specific integrated circuit (ASIC). The processing unit 113 may also be a processor or circuit such as a digital signal processor (DSP), a data flow processor (DFP), or a neural processing unit (NPU). The processing unit 113 may also be a combination of these processors or circuits. The ROM 114 is a memory that stores fixed data, such as programs executed by the processing unit 113 and parameters for calculation. The RAM 115 is a memory that provides a working area for the processing unit 113 and a temporary storage area for data. The input unit 116 is an input device including a mouse, a keyboard, etc., and the display unit 117 is a display device such as a CRT or a liquid crystal display. The input unit 116 and the display unit 117 may be an integrated device such as a touch panel. The input unit 116 and the display unit 117 may be configured as devices separate from the information processing device. The memory unit 118 is a storage device such as a hard disk drive, CD, DVD, or memory card, and stores various programs and various data. The communication unit 119 connects to a network to perform communication. The communication unit 119 is used, for example, to connect to a LAN to perform data communication using a communication protocol such as TCP / IP and to communicate with other communication devices. The bus 120 is connected to each unit in the information processing device, such as the processing unit 113, the ROM 114, the RAM 115, the input unit 116, the display unit 117, the memory unit 118, and the communication unit 119, and is used to perform data communication between the units. For example, data received by the communication unit 119 from another communication device is transmitted to the storage unit 118 via the bus 120 and stored therein.

[0021] 3 shows the configuration of an article manufacturing system 1001 for manufacturing an article such as a semiconductor device. The article manufacturing system 1001 may include, for example, one or more imprint apparatuses IMP or exposure apparatuses, one or more inspection apparatuses 1005 (e.g., an overlay inspection apparatus, a foreign substance inspection apparatus), and one or more processing apparatuses 1006 (etching apparatus, film formation apparatus). It may also include an information processing apparatus 1007 that creates a learning model, which will be described later. These apparatuses are connected via a network 1002 to a control apparatus 1003, which is one of external systems different from the imprint apparatus IMP, and may be controlled by the control apparatus 1003. Examples of the control apparatus 1003 include an MES (Manufacturing Execution System) and an EES (Equipment Engineering System). The information processing devices such as the control unit 110, the control device 1003, and the information processing device 1007 may be configured, for example, by a PLD (abbreviation for Programmable Logic Device) such as an FPGA (abbreviation for Field Programmable Gate Array), an ASIC (abbreviation for Application Specific Integrated Circuit), a general-purpose computer with a built-in program, or a combination of all or part of these. An example of the information processing device 1007 is an information processing device such as a server. Furthermore, the generation of a learning model may be realized using (or in combination with) the control unit 110, the control device 1003, etc.

[0022] The imprint method of this embodiment will be described below. FIG. 4 is a flowchart illustrating the imprint method in the imprint apparatus IMP. The operations illustrated in FIG. 4 can be executed by the control unit 110. In step S101, a substrate S is transported from a transport source (e.g., an intermediary unit to a preprocessing unit) onto the substrate holding unit 102 by a substrate transport mechanism (not shown). Multiple shot areas are set (arranged) on the substrate S. FIG. 5 is a diagram illustrating the multiple shot areas on the substrate. In the imprint apparatus, a pattern is formed in each shot area in a single imprint process (steps S102 to S106, which will be described later). Furthermore, patterns are formed in the multiple shot areas on the substrate S by repeating the imprint process for each shot area. The shot areas include common shot areas (first shot areas) where imprint processing is performed under common processing conditions and special shot areas (second shot areas) where imprint processing is performed under individual processing conditions. For example, an example of a common shot area is a shot area (referred to here as common shot area 201) that has the same shape and size as a pattern area on the original. Another example of a special shot area is a shot area (herein referred to as special shot area 202) that is located near the outer periphery of the substrate, has a portion of its shape missing, and is different in shape and size from the pattern area of ​​the original. In imprint processing in which the imprint material on the original and the substrate come into contact, the processing conditions suitable for the imprint processing differ between the common shot area 201 and the special shot area 202. Furthermore, the processing conditions suitable for the imprint processing may also differ between special shot areas 202 with different shapes. In these imprint processing, pre-set processing conditions (sometimes called recipes) are read from the storage unit 118, and the processing is carried out in accordance with these processing conditions.

[0023] In step S102, the dispenser 108 places the imprint material IM on a shot area to be imprinted, among the multiple shot areas on the substrate S. This process can be performed by discharging the imprint material IM from the dispenser 108 while the substrate S is driven by the substrate driving mechanism 105. The amount and arrangement of the imprint material to be discharged from the dispenser are set in advance. Here, the information on the amount and arrangement of the imprint material that is set in advance is called a drop recipe. The drop recipe is naturally set to match the shape of the shot area, but it is not simply a matter of matching it to the shape (with unnecessary portions removed); adjustments are also required at the boundary portions of the substrate to prevent overflow of the imprint material, etc. For this reason, setting the drop recipe for the special shot area 202 often requires prior consideration based on past experience, etc.

[0024] In step S103, the substrate S and the mold M are driven relatively by at least one of the mold driving mechanism 122 and the substrate driving mechanism 105 so that the pattern region MP of the mold M comes into contact with the imprint material IM above the shot area to be imprinted. In one example, the mold M is driven by the mold driving mechanism 122 so that the pattern region MP of the mold M comes into contact with the imprint material IM above the shot area to be imprinted. In the process of bringing the pattern region MP of the mold M into contact with the imprint material IM, the deformation mechanism 123 can deform the pattern region MP of the mold M into a convex shape toward the substrate S. At this time, the cavity pressure is controlled, and the value thereof is accumulated. Furthermore, in the process of bringing the pattern region MP of the mold M into contact with the imprint material IM, imaging is performed by the imaging unit 112, and the captured image (spread image) is accumulated.

[0025] Here, the appropriate operation when bringing the pattern region MP of the mold M into contact with the imprint material IM generally varies depending on the shape of the shot region, etc. For example, in the common shot region 201, as shown in FIG. 6( a), the substrate S and the mold M are kept parallel to each other, and the imprint material IM is brought into contact with the pattern region MP of the mold M from the center C of the shot region. On the other hand, in the special shot region 202, as shown in FIG. 6( b), the mold M is tilted with respect to the substrate S, and the imprint material IM is brought into contact with the pattern region MP of the mold M from a position offset from the center C of the shot region. Here, the tilt of the mold M is referred to as the mold tilt. Also, the position where the pattern region MP of the mold M is first brought into contact with the imprint material IM is referred to as the contact start position. Processing conditions such as the preferred mold tilt and contact start position in the special shot region vary depending on the shape and arrangement of the special shot region, etc. In addition, there are processing conditions that differ depending on the special shot region. An example of processing conditions that differ in the special shot region is processing conditions related to the contact profile, which is the trajectory of the mold M when the mold M is brought into contact with the imprint material IM. Another example of processing conditions that differ in the special shot region is processing conditions related to the method of supplying gas to fill the space between the imprint material IM and the mold M so as not to trap the gas between them.

[0026] In step S104, alignment (positioning) can be performed between the shot area to be imprinted on the substrate S and the pattern area MP of the mold M. The alignment can be performed by measuring the relative position between the alignment mark of the shot area to be imprinted and the alignment mark of the mold M using multiple alignment measurement instruments 106, so that the relative position falls within an allowable range of the target relative position. In the alignment, the substrate S and the mold M are driven relatively by at least one of the mold driving mechanism 122 and the substrate driving mechanism 105. The target drive amount of the alignment mark of the shot area to be imprinted and the alignment mark of the mold M is determined from the alignment mark position measured from the alignment mark image.

[0027] Here too, the processing conditions for the alignment marks used in alignment differ in the special shot areas. Generally, selecting a combination of alignment marks with wide spacing between them is advantageous in terms of accuracy. For example, in the common shot area, marks close to the four corners of the shot area are selected. In contrast, in the special shot area, it is not always possible to select marks close to the four corners, and a combination of marks with wide spacing between marks is selected for each shape. Furthermore, in the special shot area, since the spacing between marks cannot be sufficiently secured, interference with the alignment measurement instrument may occur, which may limit the number of alignment marks that can be observed. In this way, the selection of appropriate alignment marks differs depending on the shape, arrangement, etc. of the special shot area.

[0028] In step S105, the curing unit 107 irradiates the imprint material IM between the substrate S and the pattern region MP of the mold M with energy for curing the imprint material IM, thereby curing the imprint material IM and forming a cured product of the imprint material IM. In step S106, the substrate S and the mold M are driven relatively by at least one of the mold driving mechanism 122 and the substrate driving mechanism 105 so that the cured product of the imprint material IM and the pattern region MP of the mold M are separated. In one example, the mold M is driven by the mold driving mechanism 122 so that the cured product of the imprint material IM and the pattern region MP of the mold M are separated. When the cured product of the imprint material IM and the pattern region MP of the mold M are separated, the pattern region MP of the mold M can also be deformed into a convex shape toward the substrate S. In addition, the imaging unit 112 captures an image, and the state of separation between the imprint material IM and the mold M can be observed based on the captured image.

[0029] Here too, similar to when the imprint material IM and the pattern region MP of the mold M come into contact with each other, the preferred mold tilt and separation start position in the special shot region differ depending on the shape of the special shot region and other factors.

[0030] As an example, as described above, the processes performed in steps S102 to S105 are performed under conditions set for each target shot area. Common shot areas are generally processed under the same conditions, while special shot areas are generally processed under different conditions according to their shape and other characteristics.

[0031] In step S107, the control unit 110 determines whether the imprint processing of steps S102 to S106 has been performed on all shot areas of the substrate S. If the imprint processing of steps S102 to S106 has been performed on all shot areas of the substrate S, the control unit 110 proceeds to step S108, and if there are any unprocessed shot areas, the control unit 110 returns to step S102. In this case, the imprint processing of steps S102 to S106 is performed on a selected shot area from the unprocessed shot areas.

[0032] In step S108, the substrate S is transported from the substrate holding unit 102 to a destination (e.g., an intermediary unit to a post-processing device) by a substrate transport mechanism (not shown). When a lot consisting of multiple substrates is processed, the method shown in Fig. 4 is performed for each of the multiple substrates.

[0033] In the above-described imprint process, it is necessary to set processing conditions in advance. In this embodiment, the process of setting these processing conditions is also referred to as the imprint process. Next, a method for setting these processing conditions will be described.

[0034] The imprint processing conditions include three processing conditions: a first processing condition, a second processing condition, and a third processing condition.

[0035] The first processing condition is a processing condition related to a plurality of shot areas on the substrate S, and will be referred to as the first processing condition hereinafter. The first processing condition is determined in advance depending on the manufacturing process, the device to be manufactured, and the like. For example, the first processing condition includes information related to the size and arrangement (position) of each of the plurality of shot areas. The first processing condition may also include processing conditions related to the position of an alignment mark that can be determined from the size and arrangement of the shot areas. Here, the first processing condition includes information related to the size and arrangement of not only the common shot areas but also the special shot areas. In other words, the first processing condition is a processing condition that includes information related to the size and arrangement of the plurality of shot areas on the substrate S.

[0036] The second processing conditions are processing conditions that are set commonly to the common shot area, and are hereinafter referred to as the second processing conditions. For example, the second processing conditions include processing conditions related to the drop recipe, mold tilt, contact start position, contact profile, gas supply method, etc. in the common shot area.

[0037] The third processing condition is a processing condition set individually for each special shot area, and will be referred to hereinafter as the third processing condition. For example, in the case of a peripheral shot area located in the peripheral area of ​​the substrate S, the second processing condition may be a processing condition that needs to be determined depending on the shape of the peripheral shot area. The second processing condition includes, for example, processing conditions related to the drop recipe, mold tilt, contact start position, contact profile, gas supply method, etc., in the special shot area. Furthermore, although the third processing condition is set individually for each special shot area, depending on the special shot area, it may be the same processing condition as the second processing condition of the common shot area or the same processing condition as another special shot area. In other words, the third processing condition of a certain special shot area may be the same as the second processing condition of the common shot area or the same as the third processing condition of another special shot area.

[0038] A method for acquiring the processing conditions for the imprint processing will be described with reference to Fig. 7. The method shown in Fig. 7 can be executed by the control unit 110 functioning as an acquisition unit. The method shown in Fig. 7 may also be executed by the control device 1003, the information processing device 1007, or the like. In step S301, a file for saving the processing conditions for the imprint processing in the storage unit 118 is created.

[0039] In step S302, first and second processing conditions related to the common shot area (first area) are acquired. The first and second processing conditions may be acquired from processing conditions input by a user using an input unit, or may be acquired from processing conditions transmitted from an external information processing device. Furthermore, as the first processing conditions, for example, processing conditions related to the size and arrangement of the shot area related to the common shot area are acquired. Furthermore, as the second processing conditions, processing conditions related to a common drop recipe in the common shot area, etc. are acquired.

[0040] Next, steps S303 to S307 are performed on all special shot areas (second areas), and processing conditions for the special shot areas are set.

[0041] In step S303, first processing conditions for the special shot area are acquired. The first processing conditions for the special shot area include, for example, information on at least one of the size, arrangement, and position of the alignment mark of the special shot area.

[0042] In step S304, a third processing condition for the special shot region is acquired. Details of how the third processing condition is acquired will be described later.

[0043] In step S305, it is confirmed whether steps S303 to S304 have been performed for all special shot areas. If not, the process returns to step S303 and sets processing conditions for the remaining special shot areas. If all special shot areas have been performed, the process proceeds to step S306.

[0044] In step S306, the acquired processing conditions including the first processing condition, the second processing condition, and the third processing condition are saved in a file in the storage unit 118.

[0045] The set processing conditions may also be displayed on the screen (user interface) of the display unit 117 (not shown) so that the user can check and modify them.

[0046] Here, the acquisition of the third processing condition for the special shot region in step S304 will be described. In step S304, the third processing condition is acquired using a learning model acquired using machine learning. The learning model receives the first processing condition and the second processing condition as input and outputs the third processing condition. In the step of acquiring the learning model (learning), an optimized learning model is acquired using processing conditions used in the past. Next, in the step of acquiring the third processing condition (estimation), the first processing condition and the second processing condition are input into the acquired learning model to acquire the third processing condition.

[0047] An overview of learning and estimation will be explained using Figure 8. In the pre-learning process, input data 402 including multiple sets of first and second processing conditions read from processing condition data 401 including multiple processing conditions used in the past is used as input learning data. Also, output data 403 including multiple third processing conditions read from processing condition data 401 is used as output learning data. An optimized learning model is obtained by machine learning using these learning data.

[0048] In step S304, input data 405, which is a set of the first processing condition and the second processing condition of the corresponding special shot area, is input to the learning model, and the third processing condition of the special shot area is obtained (estimated) as output data 406 output from the learning model.

[0049] Here, specific techniques for learning and estimation are described. One example of a specific learning and estimation technique is a technique that uses a neural network composed of multi-layer perceptrons as a learning model to optimize internal variables and perform estimation. Another example is a Bayesian estimation technique using Gaussian process regression, which treats variables as probabilities as a learning model to perform estimation that takes uncertainty into account. Depending on the learning data used, a technique using decision tree analysis, which is robust against outliers, may be applied as the learning model. If it is necessary to reduce the amount of calculation required for estimation, a statistical model with low computational load, such as multiple regression analysis, may be used as the learning model. Furthermore, the learning model may be a combination of neural networks, Gaussian process regression, decision tree analysis, and multiple regression analysis.

[0050] In the above explanation, an example was given in which the third processing condition was calculated using machine learning, but this is not the only option. The third processing condition may be obtained by accumulating rules that describe the relationship between at least one of the size and shape of the special shot area and the third processing condition, and searching for the case with the closest size and shape based on the accumulated rules.

[0051] Next, a learning method for acquiring a learning model will be described with reference to Fig. 9. The method shown in Fig. 9 can be executed by the control unit 110 functioning as a learning unit. The method shown in Fig. 9 may also be executed by the control device 1003, the information processing device 1007, or the like.

[0052] In step S501, processing condition data 401 including a plurality of processing conditions used in the past is obtained from the storage unit 118. Here, the processing condition data 401 may be obtained from an external information processing device via a communication line. Note that it is advantageous to have as many past processing conditions as possible to use for learning.

[0053] In step S502, a plurality of combinations of the first processing condition and the second processing condition included in the processing condition data 401 are acquired as input data for the learning data.

[0054] In step S503, a plurality of third processing conditions included in the target processing conditions are acquired as output data of the learning data.

[0055] In step S504, learning is performed using the input data and output data of the learning data acquired in steps S502 and S503, and a learning model is acquired. Here, steps S502 to S504 may be repeated for each of the multiple processing conditions included in the processing condition data 401 to update the learning model, and a final optimized learning model may be acquired.

[0056] In step S505, the updated learning model is stored in the storage unit 118.

[0057] Next, a method for acquiring a third processing condition using a learning model will be described with reference to Fig. 10. This corresponds to step S304 described above. The operations shown in Fig. 10 can be executed by the control unit 110 functioning as a learning unit. The method shown in Fig. 10 may also be executed by the control device 1003, the information processing device 1007, or the like.

[0058] In step S601, the first and second processing conditions acquired in steps S302 and S303 are read.

[0059] In step S602, the learning model saved in step S506 is obtained.

[0060] Next, step S603 is repeated for the special shot area in the substrate S.

[0061] In step S603, the first processing condition and the second processing condition are input to the input side of the learning model, and the third processing condition is obtained from the output side of the learning model.

[0062] In step S604, it is confirmed whether the third processing condition has been acquired for all special shot areas in step S603. If the third processing condition has not been acquired for all special shot areas, the process returns to step S603 and continues. If the third processing condition has been acquired for all special shot areas, the process proceeds to step S605.

[0063] In step S605, the third processing conditions acquired in step S604 are stored in the storage unit 118.

[0064] Among the machine learning techniques, there is a known technique that can calculate the reliability of the estimation at the same time. When this technique is used to calculate the third processing condition, the reliability may also be presented to the user. For example, a numerical value representing the reliability may be presented at the same time, or a color representing the reliability may be added to the presented value.

[0065] In the present embodiment, an example has been described in which the creation of the learning model and the acquisition of the third processing conditions are executed by the control unit 110 of the imprint apparatus, but this is not limitative. For example, these processes may be executed by the information processing device 1007.

[0066] As described above, according to the information processing apparatus of this embodiment, processing conditions can be easily set for shot areas for which processing conditions need to be set individually.

[0067] <Other embodiments> The present invention can also be realized by providing a program that realizes one or more functions of the above-described embodiments to a system or device via a network or a storage medium, and having the computer of the system or device read and execute the program. The computer has one or more processors or circuits, and may include multiple separate computers or a network of multiple separate processors or circuits to read and execute computer-executable instructions.

[0068] <Summary of the embodiment> The disclosure of this specification includes the following information processing device, acquisition method, learning method, program, exposure apparatus, and method for manufacturing an article.

[0069] (Item 1) An information processing device, an acquisition unit that acquires a third processing condition by inputting the first processing condition and the second processing condition into a learning model acquired by learning using processing conditions for imprint processing performed on a plurality of shot areas on a substrate as learning data; the first processing condition is a condition including information about the size and arrangement of the plurality of shot areas, the second processing condition is a condition set in common to a first shot area among the plurality of shot areas, and the third processing condition is a condition set individually to a second shot area, different from the first shot area, among the plurality of shot areas. 1. An information processing device comprising:

[0070] (Item 2) a learning unit that acquires the learning model by learning using the learning data; 2. The information processing device according to item 1,

[0071] (Item 3) 3. The information processing apparatus according to item 1 or 2, wherein the first processing condition includes information about positions of alignment marks in the plurality of shot areas.

[0072] (Item 4) the second processing conditions include conditions relating to a drop recipe, a mold tilt, a contact start position, a contact profile, and a gas supply method that are commonly set for the first shot region; The information processing device described in any one of items 1 to 3, characterized in that the third processing conditions include conditions related to a drop recipe, mold inclination, contact start position, contact profile, and gas supply method that are individually set for the second shot area.

[0073] (Item 5) 5. The information processing device according to any one of items 1 to 4, wherein the learning model uses at least one of a neural network, a Gaussian process regression, a decision tree analysis, and a multiple regression analysis.

[0074] (Item 6) An information processing device, a learning unit that acquires a learning model by learning using processing conditions for imprint processing performed on a plurality of shot areas on a substrate as learning data; the learning data includes a first processing condition, a second processing condition input to the learning model, and a third processing condition output from the learning model; the first processing condition is a condition including information about the size and arrangement of the plurality of shot areas, the second processing condition is a condition set in common to a first shot area among the plurality of shot areas, and the third processing condition is a condition set individually to a second shot area, different from the first shot area, among the plurality of shot areas. 1. An information processing device comprising:

[0075] (Item 7) an acquisition step of acquiring third processing conditions by inputting the first processing conditions and the second processing conditions into a learning model acquired by learning using processing conditions of imprint processing performed on a plurality of shot areas on a substrate as learning data; the first processing condition is a condition including information about the size and arrangement of the plurality of shot areas, the second processing condition is a condition set in common to a first shot area among the plurality of shot areas, and the third processing condition is a condition set individually to a second shot area, different from the first shot area, among the plurality of shot areas. An acquisition method characterized by:

[0076] (Item 8) a learning step of acquiring a learning model by learning using processing conditions of imprint processing performed on a plurality of shot areas on a substrate as learning data; the learning data includes a first processing condition, a second processing condition input to the learning model, and a third processing condition output from the learning model; the first processing condition is a condition including information about the size and arrangement of the plurality of shot areas, the second processing condition is a condition set in common to a first shot area among the plurality of shot areas, and the third processing condition is a condition set individually to a second shot area, different from the first shot area, among the plurality of shot areas. A learning method characterized by:

[0077] (Item 9) an acquisition step of acquiring third processing conditions by inputting the first processing conditions and the second processing conditions into a learning model acquired by learning using processing conditions of imprint processing performed on a plurality of shot areas on a substrate as learning data; the first processing condition is a condition including information about the size and arrangement of the plurality of shot areas, the second processing condition is a condition set in common to a first shot area among the plurality of shot areas, and the third processing condition is a condition set individually to a second shot area, different from the first shot area, among the plurality of shot areas. A program that causes a computer to execute the acquisition method.

[0078] (Item 10) a learning step of acquiring a learning model by learning using processing conditions of imprint processing performed on a plurality of shot areas on a substrate as learning data; the learning data includes a first processing condition, a second processing condition input to the learning model, and a third processing condition output from the learning model; the first processing condition is a condition including information about the size and arrangement of the plurality of shot areas, the second processing condition is a condition set in common to a first shot area among the plurality of shot areas, and the third processing condition is a condition set individually to a second shot area, different from the first shot area, among the plurality of shot areas. A program for causing a computer to execute a learning method characterized by the above.

[0079] (Item 11) An imprint apparatus that performs imprint processing on a plurality of shot areas on a substrate, 7. An imprinting apparatus comprising the information processing apparatus according to any one of items 1 to 6.

[0080] (Item 12) an acquisition step of acquiring third processing conditions by inputting the first processing conditions and the second processing conditions into a learning model acquired by learning using conditions of imprint processing performed on a plurality of shot areas on a substrate as learning data; the first processing condition is a condition including information about the size and arrangement of the plurality of shot areas, the second processing condition is a condition set in common to a first shot area among the plurality of shot areas, and the third processing condition is a condition set individually to a second shot area, different from the first shot area, among the plurality of shot areas; performing the imprint processing on a plurality of shot areas on the substrate under conditions including the first processing condition, the second processing condition, and the third processing condition; manufacturing an article from the substrate that has undergone the imprint process; A method for manufacturing an article, comprising:

Claims

1. An information processing device, an acquisition unit that acquires a third processing condition by inputting the first processing condition and the second processing condition into a learning model acquired by learning using processing conditions for imprint processing performed on a plurality of shot areas on a substrate as learning data; the first processing condition is a condition including information about the size and arrangement of the plurality of shot areas, the second processing condition is a condition set in common to a first shot area among the plurality of shot areas, and the third processing condition is a condition set individually to a second shot area, different from the first shot area, among the plurality of shot areas.

1. An information processing device comprising:

2. a learning unit that acquires the learning model by learning using the learning data; 2. The information processing device according to claim 1, wherein:

3. 2. The information processing apparatus according to claim 1, wherein the first processing condition includes information about positions of alignment marks in the plurality of shot areas.

4. the second processing conditions include conditions relating to a drop recipe, a mold tilt, a contact start position, a contact profile, and a gas supply method that are set in common to the first shot region; 2. The information processing apparatus according to claim 1, wherein the third processing conditions include conditions relating to a drop recipe, a mold tilt, a contact start position, a contact profile, and a gas supply method that are individually set for the second shot area.

5. The information processing device according to claim 1 , wherein the learning model uses at least one of a neural network, a Gaussian process regression, a decision tree analysis, and a multiple regression analysis.

6. An information processing device, a learning unit that acquires a learning model by learning using processing conditions for imprint processing performed on a plurality of shot areas on a substrate as learning data; the learning data includes a first processing condition, a second processing condition input to the learning model, and a third processing condition output from the learning model; the first processing condition is a condition including information about the size and arrangement of the plurality of shot areas, the second processing condition is a condition set in common to a first shot area among the plurality of shot areas, and the third processing condition is a condition set individually to a second shot area, different from the first shot area, among the plurality of shot areas.

1. An information processing device comprising:

7. an acquisition step of acquiring third processing conditions by inputting the first processing conditions and the second processing conditions into a learning model acquired by learning using processing conditions of imprint processing performed on a plurality of shot areas on a substrate as learning data; the first processing condition is a condition including information about the size and arrangement of the plurality of shot areas, the second processing condition is a condition set in common to a first shot area among the plurality of shot areas, and the third processing condition is a condition set individually to a second shot area, different from the first shot area, among the plurality of shot areas. An acquisition method characterized by:

8. a learning step of acquiring a learning model by learning using processing conditions of imprint processing performed on a plurality of shot areas on a substrate as learning data; the learning data includes a first processing condition, a second processing condition input to the learning model, and a third processing condition output from the learning model; the first processing condition is a condition including information about the size and arrangement of the plurality of shot areas, the second processing condition is a condition set in common to a first shot area among the plurality of shot areas, and the third processing condition is a condition set individually to a second shot area, different from the first shot area, among the plurality of shot areas. A learning method characterized by:

9. an acquisition step of acquiring third processing conditions by inputting the first processing conditions and the second processing conditions into a learning model acquired by learning using processing conditions of imprint processing performed on a plurality of shot areas on a substrate as learning data; the first processing condition is a condition including information about the size and arrangement of the plurality of shot areas, the second processing condition is a condition set in common to a first shot area among the plurality of shot areas, and the third processing condition is a condition set individually to a second shot area, different from the first shot area, among the plurality of shot areas. A program that causes a computer to execute the acquisition method.

10. a learning step of acquiring a learning model by learning using processing conditions of imprint processing performed on a plurality of shot areas on a substrate as learning data; the learning data includes a first processing condition, a second processing condition input to the learning model, and a third processing condition output from the learning model; the first processing condition is a condition including information about the size and arrangement of the plurality of shot areas, the second processing condition is a condition set in common to a first shot area among the plurality of shot areas, and the third processing condition is a condition set individually to a second shot area, different from the first shot area, among the plurality of shot areas. A program for causing a computer to execute a learning method characterized by the above.

11. An imprint apparatus that performs imprint processing on a plurality of shot areas on a substrate, An imprinting apparatus comprising the information processing apparatus according to claim 1.

12. an acquisition step of acquiring third processing conditions by inputting the first processing conditions and the second processing conditions into a learning model acquired by learning using conditions of imprint processing performed on a plurality of shot areas on a substrate as learning data; the first processing condition is a condition including information about the size and arrangement of the plurality of shot areas, the second processing condition is a condition set in common to a first shot area among the plurality of shot areas, and the third processing condition is a condition set individually to a second shot area, different from the first shot area, among the plurality of shot areas; performing the imprint processing on a plurality of shot areas on the substrate under conditions including the first processing condition, the second processing condition, and the third processing condition; manufacturing an article from the substrate that has undergone the imprint process; A method for manufacturing an article, comprising:

Images