Information processing device, exposure device, and acquiring method

Abstract

To provide an information processing device that is capable of acquiring exposure quantity-related information in an exposure device more easily, based on original plate-related information.SOLUTION: An information processing device inputs, to a learning model created through machine learning based on training data that includes information on a first original plate used to expose a first substrate and information on a first exposure quantity during the exposure of the first substrate, information on a second original plate used to expose a second substrate, thereby acquiring information on a second exposure quantity during the exposure of the second substrate.SELECTED DRAWING: Figure 7

Description

[Technical field]

[0001] The present invention relates to an information processing apparatus, an exposure apparatus, and an acquisition method. [Background technology]

[0002] 2. Description of the Related Art Conventionally, in order to form a pattern having a desired line width on a substrate, it is required that an exposure apparatus exposes the substrate with a desired exposure amount.

[0003] Patent Document 1 discloses an exposure condition setting device that sets an optimal exposure amount based on at least one of the type and film thickness of the resist, and the type, minimum dimension, and density of the pattern. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Japanese Patent Application Publication No. 4-72711 Summary of the Invention [Problem to be solved by the invention]

[0005] The original (reticle, mask) used in the exposure to form a pattern on a substrate correlates with the pattern formed, and it is important to set the exposure dose taking into account information about the original.

[0006] However, the information about the original includes many parameters, and it is not easy to quantify the effect on the exposure amount for each of such many parameters and obtain the exposure amount based on the information about the original.

[0007] SUMMARY OF THE PRESENTLY PREFERRED EMBODIMENTS An object of the present invention is to provide an information processing apparatus, an exposure apparatus, and an acquisition method that more easily acquire information regarding the exposure amount in an exposure apparatus based on information about an original. [Means for solving the problem]

[0008] The information processing device of the present invention obtains information regarding the second exposure dose when exposing the second substrate by inputting information regarding a second original used to expose a second substrate into a learning model generated by machine learning using learning data including information regarding a first original used to expose a first substrate and information regarding a first exposure dose when the first substrate is exposed. Effect of the Invention

[0009] According to the present invention, it is possible to provide an information processing apparatus, an exposure apparatus, and an acquisition method that more simply acquire information about the exposure amount in an exposure apparatus based on information about an original. [Brief description of the drawings]

[0010] [Figure 1] FIG. 1 is a diagram showing a schematic configuration of an exposure apparatus. [Diagram 2] FIG. 4 is a diagram showing the relationship between the line width of a substrate pattern and the line width of a mask pattern. [Diagram 3] FIG. 2 is a diagram showing a cross-sectional view of a pattern on a substrate. [Figure 4] FIG. 1 is a schematic diagram illustrating a coating and developing apparatus. [Diagram 5] FIG. 1 is a schematic configuration diagram of a substrate processing system. [Figure 6] 1 is a flowchart showing a method for obtaining a learning model. [Figure 7] 1 is a flowchart illustrating a method for determining an exposure amount using a learning model. [Figure 8] 1 is a flowchart for explaining the manufacture of a device using an exposure apparatus. [Figure 9] 9 is a detailed flowchart of the wafer process in step 4 of the flowchart shown in FIG. 8. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0011] Hereinafter, the 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 the embodiments describe a plurality of features, not all of these features are essential to the invention, and the plurality of features may be combined in any manner. Furthermore, in the accompanying drawings, the same reference numbers are given to the same or similar configurations, and duplicated descriptions are omitted. In addition, in the accompanying drawings, the drawings may be drawn at a scale different from the actual scale in order to make the present embodiment easy to understand.

[0012] In the following, the direction parallel to the optical axis AX of the projection optical system 101 described below is referred to as the Z axis, the direction in which the reticle R and substrate W are scanned during exposure within a plane perpendicular to the Z axis (scanning direction) is referred to as the Y axis, and the direction perpendicular to the Y axis within the same plane (non-scanning direction) is referred to as the X axis.

[0013] First Embodiment 1 shows a schematic configuration diagram of an exposure apparatus 100. The exposure apparatus 100 is a projection type exposure apparatus that projects (transfers) an image of a pattern formed (drawn) on an original R by, for example, a scan-and-repeat system onto a substrate W. In other words, the exposure apparatus 100 exposes the substrate W to light from the original R on which the pattern is formed. The exposure apparatus 100 includes an illumination optical system 106, an original stage 103, a projection optical system 101, a substrate stage 105, a measurement device (measurement means), and a control unit.

[0014] The illumination optical system 106 adjusts light emitted from a light source that generates pulsed light, such as an excimer laser (not shown), and then guides the light to the original R, thereby illuminating the original R.

[0015] The original stage 103 can move at least parallel to the X-axis and Y-axis while holding an original R made of, for example, quartz glass on which a pattern (for example, a circuit pattern) to be transferred onto a substrate W is formed. During exposure, the original stage 103 performs scanning movement at a constant speed in a direction parallel to the Y-axis within an XY plane perpendicular to the optical axis AX of the projection optical system 101, and performs correction movement in a direction parallel to the X-axis so as to perform scanning while maintaining a target position. The original stage 103 is also provided with a bar mirror 120. A first interferometer 121 emits light toward the bar mirror 120 and measures the distance between the bar mirror 120, thereby making it possible to constantly measure position information of the original stage 103 in directions parallel to each axis.

[0016] The projection optical system 101 guides light that has passed through the original R onto the substrate W so that an image of the pattern formed on the original R is projected onto the substrate W at a predetermined magnification (e.g., 1 / 2). As a result, the image of the pattern formed on the original R is projected onto the substrate W, which is made of, for example, single crystal silicon and has a resist (photosensitive agent) applied on its surface. Here, the image plane of the projection optical system 101 is perpendicular to the Z axis (i.e., a direction parallel to the optical axis AX of the projection optical system 101).

[0017] The substrate stage 105 holds the substrate W via a chuck (not shown) and can move (rotate) in directions parallel to the X-axis, Y-axis, and Z-axis, and further in the θX, θY, and θZ directions, which are rotational directions around each axis. The substrate stage 105 is also provided with a bar mirror 123. A second interferometer 124 emits light toward the bar mirror 123 and measures the distance to the bar mirror 123, thereby making it possible to constantly measure position information of the substrate stage 105 in directions parallel to each axis.

[0018] The measurement device (measurement means) measures the position and inclination (hereinafter, these may be collectively referred to as "surface position") in a direction parallel to the Z axis of the surface of the substrate W held by the substrate stage 105. The measurement device also includes a light projecting system that projects a measurement light beam toward the substrate W, and a light receiving system that receives the light beam reflected from the substrate W.

[0019] The light projection system of the measurement device is composed of a measurement light source 110, a collimator lens 111, a slit member 112, a light projection side optical system 113, and a light projection side mirror 114. The measurement light source 110 is a light source such as a lamp or a light emitting diode, and emits a measurement light beam toward the substrate W. The collimator lens 111 converts the light beam emitted from the measurement light source 110 into a parallel light beam with a substantially uniform intensity distribution in a cross section. The slit member 112 is, for example, a pair of prisms bonded together so that their inclined surfaces face each other, and a light-shielding film having a plurality of openings (for example, nine pinholes) and made of chrome or the like is provided on the bonded surface. The collimator lens 111 splits the parallel light beam into, for example, nine light beams. The light projection side optical system 113 is a bi-telecentric optical system, and guides the nine light beams that have passed through the slit member 112 to nine measurement points on the substrate W via the light projection side mirror 114. Here, the plane having the pinhole of the slit member 112 and the plane including the surface of the substrate W satisfy the Scheimpflug condition with respect to the light-projecting side optical system 113. Also, in the exposure apparatus 100, nine light beams from the light-projecting system of the measurement device are incident on the substrate W so that the angle of incidence Φ (angle with respect to the optical axis AX of the projection optical system 101) is 70° or more. Then, the nine light beams are incident on the substrate W from a direction rotated by θ (for example, 22.5°) with respect to the Y axis in the XY plane so that the light-receiving system of the measurement device described next can observe the nine measurement points on the substrate W independently of one another.

[0020] Next, the light receiving system of the measurement device is composed of a light receiving side mirror 115, a light receiving side optical system 116, a correction optical system 118, and a photoelectric conversion means 119. The light receiving side optical system 116 is a bi-telecentric optical system, and guides nine light beams from the substrate W reflected by the light receiving side mirror 115 to the photoelectric conversion means 119. The light receiving side optical system 116 is provided with a stopper aperture (not shown), which can cut high-order diffracted light (noise light) generated by a pattern already formed on the substrate W at each of the nine measurement points. The correction optical system 118 includes nine correction lenses, and collects the nine light beams, the optical axes of which are parallel to each other as a result of passing through the light receiving side optical system 116, into spot lights having the same size on the detection surface of the photoelectric conversion means 119. The photoelectric conversion means 119 is composed of, for example, a group of nine one-dimensional CCD line sensors, and detects the intensity of each light beam incident on the detection surface, and then outputs the detection result to the arithmetic circuit 126 .

[0021] The photoelectric conversion means 119 may be one in which a plurality of two-dimensional position measurement elements are arranged. The light receiving optical system 116, the correction optical system 118, and the photoelectric conversion means 119 in the light receiving system of the measurement device are previously subjected to tilt correction so that each measurement point on the substrate W and the detection surface of the photoelectric conversion means 119 are conjugate with each other. This makes it possible to suppress position changes in the pinhole image on the detection surface of the photoelectric conversion means 119 caused by local tilts at each measurement point on the substrate W. This makes it possible to detect changes in height along the optical axis AX at each measurement point on the substrate W from changes in the pinhole image on the detection surface of the photoelectric conversion means 119.

[0022] The control unit is composed of a main control unit 127, an original position control system 122, a substrate position control system 125, and an arithmetic circuit 126. The main control unit 127 is composed of, for example, a computer including a processor and a memory, and is connected to each component of the exposure apparatus 100 (and the control system that controls them) via a line to centrally control the operation of each component according to a program or the like. At least one of the components of the control unit may be provided integrally with the other components of the exposure apparatus 100, that is, in the same housing as the housing in which the other components of the exposure apparatus 100 are provided. At least one of the components of the control unit may be provided separately from the other components of the exposure apparatus 100, that is, in a housing different from the housing in which the other components of the exposure apparatus 100 are provided.

[0023] The original position control system 122 controls the operations of the original stage 103 and the first interferometer 121 based on a drive command from the main controller 127. The substrate position control system 125 controls the operations of the substrate stage 105 and the second interferometer 124 based on a drive command from the main controller 127. The arithmetic circuit 126 calculates the intensity values ​​of each of the light beams reflected from the nine measurement points on the substrate W based on the detection results obtained from the photoelectric conversion means 119.

[0024] The main controller 127 can adjust the position of the substrate W in the XY plane and in the direction parallel to the Z axis so that the slit image of the original R is formed in a predetermined area on the substrate W. Here, the position in the XY plane means the position in the direction parallel to the X axis and the Y axis and the rotation angle θZ around the Z axis, and the position in the direction parallel to the Z axis means the height in the direction parallel to the Z axis and the rotation angles θX and θY around the X axis and the Y axis. The main controller 127 transmits drive commands to the original position control system 122 and the substrate position control system 125 to perform scanning exposure for forming the pattern on the original R on the substrate W while synchronously scanning the original stage 103 and the substrate stage 105 with each other. When scanning the original stage 103 in the Y direction, the main controller 127 scans the substrate stage 105 in the Y direction at a speed corrected by the reduction magnification of the projection optical system 101. In addition, the scanning speed of the original stage 103 is determined in advance to be advantageous for productivity, based on the width in the scanning direction of a masking blade (not shown) provided in the illumination optical system 106, the sensitivity of the resist applied to the surface of the substrate W, and the like.

[0025] Next, a description will be given of the control performed by the controller in the exposure apparatus 100 to align the pattern formed on the original R onto the substrate W. With regard to each position in the XY plane, the main controller 127 first obtains position data of the original stage 103 and the substrate stage 105 from the first interferometer 121 and the second interferometer 124, and also obtains position data of the substrate W from an alignment microscope (not shown).

[0026] Next, the main controller 127 creates control data based on the acquired position data, and sends drive commands to the original position control system 122 and the substrate position control system 125 based on the created control data, thereby moving the original stage 103 and the substrate stage 105 to desired positions.

[0027] On the other hand, the main controller 127 acquires the intensity values ​​of the light beams reflected from nine measurement points on the substrate W from the arithmetic circuit 126 for control of the position (height) in the direction parallel to the Z axis, that is, the focus operation.

[0028] Next, the main controller 127 creates control data based on the acquired intensity values. Then, the main controller 127 moves (changes) the substrate stage 105 to a desired position (or posture) by sending a drive command to the substrate position control system 125 based on the created control data. Specifically, the main controller 127 calculates the position of the substrate stage 105 in a direction parallel to the Z axis based on a measurement result from a measurement device (and the arithmetic circuit 126) arranged near an exposure slit (not shown) in the scanning direction (Y direction).

[0029] Then, the main controller 127 controls the substrate stage 105 based on the calculated position in the direction parallel to the Z axis so that the exposure position on the substrate W becomes the optimal image plane position.

[0030] Next, the process performed by the information processing device according to the present embodiment will be described. Note that the information processing device according to the present embodiment is assumed to be the same as the main control unit 127 described above, but is not limited thereto and may be configured with a control unit different from the main control unit 127.

[0031] Figure 2 shows the relationship between the line width of the pattern of the substrate W (Wafer-CD) and the line width of the pattern of the original R (Reticle-CD). As shown in Figure 2, there is a correlation between the line width of the pattern of the substrate W and the line width of the pattern of the original R. Specifically, there is a correlation between the line width of the pattern of the substrate W and the line width of the original R that can be expressed by a linear (first-order) approximation.

[0032] FIG. 3 shows a cross-sectional view of a pattern on a substrate W. In FIG. 3, there are some locations where pattern collapse has occurred in some of the multiple patterns. Even if factors determined by the process, such as film thickness and development method, are the same, pattern collapse may occur depending on the line width of the pattern on the substrate W, and there is a correlation between the line width of the pattern on the substrate W and the line width of the pattern on the original R. Therefore, even if factors determined by the process, such as film thickness and coating and development method, are the same, pattern collapse may occur depending on information about the original R, such as the type and attributes of the original R. Therefore, in order to suppress the occurrence of pattern collapse, it is necessary to take information about the original R into consideration.

[0033] FIG. 4 shows a schematic configuration diagram of a coating and developing apparatus 400. The coating and developing apparatus 400 is used to coat a resist on a substrate W and to develop the exposed substrate W. As shown in FIG. 4, the coating and developing apparatus 400 is provided with a coating unit 401 and a developing unit 402, which are separated from each other. The coating unit 401 has a coating cup unit 403 and a coating and baking unit 404. A plurality of coating cup units 403 are provided so that they can be used according to the type of resist to be coated on the substrate W. A plurality of coating and baking units 404 are also provided so that they can be used according to the temperature at which the substrate W is baked. Similarly, the developing unit 402 is provided with a plurality of developing and baking units 405 and a plurality of developing cup units 406 that perform PEB after exposure and before development. As described above, the coating and developing apparatus 400 generally has a plurality of each unit in order to achieve high throughput.

[0034] FIG. 5 shows a schematic configuration diagram of the substrate processing system 1000. Pattern formation information of the exposure apparatus 100 is input to the substrate processing system 1000 of FIG. 5. As shown in FIG. 5, in the substrate processing system 1000, the exposure apparatus 100 and the coating and developing apparatus 400 are connected to each other via an interface block 500. In the substrate processing system 1000, the substrate W coated with resist by the coating and developing apparatus 400 is transported to the exposure apparatus 100 by passing through the interface block 500. Then, the substrate W exposed by the exposure apparatus 100 is transported to the coating and developing apparatus 400 by passing through the interface block 500 again, and is developed by the coating and developing apparatus 400. Also, as shown in FIG. 5, in the substrate processing system 1000, information is transmitted and received between the exposure apparatus 100 and the coating and developing apparatus 400 via a network 501. Also, the network 501 may be a wired connection or a wireless connection, and may be further connected to other devices.

[0035] 6 is a flowchart showing a method for acquiring a learning model. Here, the main control unit 127, which is an information processing device, acquires a learning model that outputs output data representing information related to the exposure amount by machine learning. Also, a method for acquiring a learning model in which information related to the original R used for exposure in the exposure apparatus 100 is input data and output data representing information related to the exposure amount when exposing the substrate W through the original R is described. Here, when forming a pattern by exposing the substrate W through the original R, the desired exposure amount differs depending on the type, attributes, etc. of the original R, so there is a correlation between the information related to the original R and the exposure amount.

[0036] In step S601, the main controller 127 creates learning data for generating a learning model by machine learning. First, the main controller 127 acquires information about the original R (first original) used to expose the substrate W (first substrate) in the exposure apparatus 100.

[0037] Here, the information on the original R will be specifically described. The information on the original R may include information on the type (category) of the pattern formed on the original R and the dimensions of the pattern formed on the original R. The type of the pattern formed on the original R may include, for example, either a line-and-space pattern or a hole pattern. The type of the pattern formed on the original R may include, for example, either a device pattern that constitutes a circuit of a device or an auxiliary pattern provided around the device pattern. Here, the auxiliary pattern includes, for example, a pattern provided around the device pattern to enhance the resolution by emphasizing the edge of the device pattern. The auxiliary pattern also includes a pattern provided around the device pattern to form a mark used for aligning the substrate W.

[0038] Furthermore, the information indicating the dimensions of the pattern formed on the original R may include, for example, at least one of the dimensions of each line included in the pattern formed on the original R and the dimensions of each hole included in the pattern formed on the original R (for example, information on the average value, standard deviation, in-plane distribution, etc. of those dimensions). Furthermore, the information indicating the dimensions of the pattern formed on the original R may include, for example, information on the spacing between each line or the spacing between each hole included in the pattern formed on the original R (for example, information on the average value, standard deviation, in-plane distribution, etc. of those spacings).

[0039] The information on the original R may include information on the type of the original R. The information on the type of the original R may include, for example, at least one of a positive reticle, a negative reticle, a binary reticle, and a phase shift reticle. Here, a positive reticle is a reticle manufactured using a positive resist, and a negative reticle is a reticle manufactured using a negative resist. If the information on the type of the original R includes a phase shift reticle, the information on the original R may include information on the transmittance of a film formed as a pattern on the original R (for example, information on the average value, standard deviation, in-plane distribution, etc. of the transmittance). If the original R is a phase shift reticle, the information on the phase of light changed by a film formed as a pattern on the original R (for example, information on the average value, standard deviation, in-plane distribution, etc. of the phase) may be included.

[0040] In addition, the information about the original R may include information about the cross-sectional shape of the pattern formed on the original R, and information about the film thickness of the film (Cr film, MoSi film, Si film, etc.) formed as a pattern on the original R (e.g., information about the average film thickness, standard deviation, distribution within the surface, etc.).

[0041] In addition, the information regarding the master R may include information regarding the manufacturing conditions when the master R was manufactured (e.g., the conditions for pattern formation, the conditions for dry etching, etc.), and information regarding the usage history of the master R (e.g., the number of times the master R was used in the exposure process, the number of times the master R was cleaned, and time series data thereof).

[0042] Next, the main controller 127 acquires information about the exposure dose when the substrate W (first substrate) is exposed using the original R (first original) in the exposure apparatus 100. Here, the information about the exposure dose is used as teacher data for the learning model. The information about the exposure dose can be created by actually measuring the line width of the pattern on the substrate W that has been exposed as described above, and acquiring information about the exposure dose that achieves the desired line width. The information about the exposure dose can also include the average value and standard deviation of the exposure dose in multiple shot areas on the substrate W, and information about the distribution of the exposure dose on the substrate W.

[0043] Then, the main control unit 127 creates input data from the information on the original R, creates teacher data from the information on the exposure dose, and creates learning data for generating a learning model by machine learning. Here, the information on the original R and the information on the exposure dose may be acquired in advance and stored in a storage device (not shown) of the main control unit 127 or an external storage device (not shown), and the main control unit 127 may acquire the information from the storage device (not shown) of the main control unit 127 or the external storage device (not shown).

[0044] In step S602, the main controller 127 judges whether the process of step S601 has been executed for all substrates W. If the process of step S601 has been executed for all substrates W (Yes in step S602), the process proceeds to step S604. On the other hand, if there is a substrate W for which the process of step S601 has not been executed (No in step S602), the process returns to step S601. That is, if there is information on the original R and information on the exposure dose to be acquired for multiple substrates W, the process of step S601 is repeated for each of the substrates W.

[0045] In step S603, the main control unit 127 generates a learning model by machine learning using the learning data acquired in step S601. Here, the learning model is a model in which internal random variables are optimized by machine learning using an algorithm such as backpropagation in a neural network composed of, for example, a multilayer perceptron.

[0046] Then, as described below, by inputting input data including information about the original R obtained for a new substrate W into the learning model generated in step S603, output data representing the exposure dose for the substrate W can be obtained.

[0047] Here, when the information about the master R includes image information such as an image showing a film thickness distribution, the main control unit 127 may generate a learning model including a convolutional neural network. When the information about the master R includes time-series data information such as the number of times the master R is used, the main control unit 127 may generate a learning model including a recurrent neural network. When the amount of learning data is small, the main control unit 127 may generate a learning model including a support vector machine.

[0048] In step S604, the main control unit 127 saves the information of the learning model generated in step S603 in a storage device (not shown) of the main control unit 127 or an external storage device (not shown). Here, the information of the learning model may include, for example, information representing the structure of a neural network, such as the number of layers and the number of neurons of a perceptron, and information of optimized random variables.

[0049] As described above, the main control unit 127 generates a learning model by learning using learning data including information about the master R (first master) used to expose the substrate W (first substrate) and information about the exposure dose when the substrate W was exposed.

[0050] 7 is a flowchart showing a method for determining the amount of exposure using the learning model. Here, the main control unit 127 is assumed to determine the amount of exposure using the learning model generated in step S603.

[0051] In step S701, the main control unit 127 acquires information on the learning model stored in step S604, i.e., information representing the structure of the neural network and information on optimized random variables, for example. Then, the main control unit 127 constructs a learning model based on the acquired information.

[0052] In step S702, the main controller 127 acquires information about the original R (second original) when the substrate W (second substrate) is exposed in the exposure apparatus 100. The information about the original R acquired here may include the same information as the information about the original R acquired in step S601. Here, in step S702, the main controller 127 may acquire information about the original R for each substrate W sequentially, or may acquire information about the originals R for multiple substrates W all at once.

[0053] In step S703, the main control unit 127 inputs input data consisting of information about the original R acquired in step S702 to the learning model constructed in step S701. Then, information about the exposure amount to be output as output data from the learning model is acquired. The information about the exposure amount acquired here may include information similar to the information about the exposure amount acquired in step 601.

[0054] In step S704, the main controller 127 outputs the acquired information on the exposure amount, so that the exposure apparatus 100 exposes the substrate W at the exposure amount determined based on the output information on the exposure amount. At this time, the main controller 127 may calculate a statistical value indicating the variation between the exposure amounts for each substrate W from the results output from the learning model. This makes it possible to set a threshold value for the exposure amount based on the calculated statistical value, and not to adopt the exposure amount determined from the information on the exposure amount output from the learning model if it exceeds the threshold value.

[0055] The above series of processes are performed by the main controller 127 provided in the exposure apparatus 100, but are not limited thereto, and may be performed, for example, using an information processing device external to the exposure apparatus 100. Also, the above series of processes may be performed by combining the main controller 127 provided in the exposure apparatus with an external information processing device. In this case, for example, the main controller 127 acquires a learning model and outputs information about the learning model to an external information processing device. Then, the external information processing device can construct the learning model and use the learning model to determine the exposure amount. Also, for example, the external information processing device acquires a learning model and outputs information about the learning model to the main controller 127. Then, the main controller 127 can construct the learning model and use the learning model to determine information about the exposure amount (second exposure amount).

[0056] As described above, the main control unit 127 acquires information regarding the exposure amount (second exposure amount) when exposing the substrate W (second substrate) by inputting information regarding the original R (second original) used to expose the substrate W (second substrate) into the learning model.

[0057] As described above, according to the information processing apparatus of this embodiment, information about the original is input to the learning model as input data, so that information about the exposure amount can be obtained.

[0058] <Production method> As an example of an article, a method for manufacturing a device (semiconductor device, magnetic storage medium, liquid crystal display element, etc.), a color filter, or a hard disk will be described. The manufacturing method includes a step of forming a pattern on a substrate (wafer, glass plate, film-like substrate, etc.) by irradiating light from a light source unit to the substrate using a lithography apparatus (for example, an exposure apparatus, a drawing apparatus, etc.) having a light source unit. The manufacturing method further includes a step (processing step) of processing the substrate on which the pattern is formed. The processing step may include a step of removing a residual film of the pattern. The processing step may also include a step of etching the substrate using the pattern as a mask. The processing step may also include other well-known steps such as dicing, bonding, and packaging. The manufacturing method of the article in this embodiment is advantageous in at least one of the performance, quality, productivity, and production cost of the article compared to the conventional method.

[0059] Next, as an example of a method for manufacturing an article, an embodiment of a device manufacturing method using the above-mentioned exposure apparatus will be described with reference to Figures 8 and 9. Figure 8 is a flow chart for explaining the manufacture of devices (semiconductor chips such as ICs and LSIs, LCDs, CCDs, etc.). Here, a method for manufacturing semiconductor chips will be described as an example.

[0060] In step S1 (circuit design), the circuit of the semiconductor device is designed. In step S2 (mask production), a mask (master) is produced based on the designed circuit pattern. In step S3 (wafer production), a wafer (substrate) is produced using a material such as silicon. Step S4 (wafer process) is called the pre-process, in which the mask and wafer are used to form an actual circuit on the wafer using lithography technology with the exposure device described above. Here, the exposure device forms a circuit pattern on the wafer by illuminating the master on which the circuit pattern is formed and projecting an image of the circuit pattern of the master onto the wafer. Step S5 (assembly) is called the post-process, in which the wafer produced in step S4 is used to make a semiconductor chip, and includes assembly processes such as assembly processes (dicing, bonding) and packaging processes (chip encapsulation). In step S6 (inspection), the semiconductor device produced in step S5 is inspected, such as an operation confirmation test and a durability test. After going through these processes, the semiconductor device is completed and shipped (step S7).

[0061] FIG. 9 is a detailed flowchart of the wafer process in step 4. In step S11 (oxidation), the surface of the wafer is oxidized. In step S12 (CVD), an insulating film is formed on the surface of the wafer. In step S13 (electrode formation), electrodes are formed on the wafer by deposition. In step S14 (ion implantation), ions are implanted into the wafer. In step S15 (resist processing), a photosensitive agent is applied to the wafer. In step S16 (exposure), the circuit pattern of the mask is exposed onto the wafer by an exposure device. In step S17 (development), the exposed wafer is developed. In step S18 (etching), the parts other than the developed resist image are scraped off. In step S19 (resist stripping), the resist that is no longer needed after etching is removed. By repeating these steps, multiple circuit patterns are formed on the wafer.

[0062] Although the preferred embodiments of the present invention have been described above, it goes without saying that the present invention is not limited to these embodiments, and various modifications and changes are possible within the scope of the gist of the present invention.

[0063] Although an exposure apparatus that exposes a substrate by irradiating the substrate with light from an original plate on which a pattern is formed has been described as an example of an exposure apparatus, the present invention is not limited to this. Also, an example of an exposure apparatus may be a drawing apparatus that draws on a substrate with a charged particle beam (such as an electron beam or an ion beam) via a charged particle optical system to form a pattern on the substrate.

[0064] <Other embodiments> The present invention can also be realized by a process in which a program for implementing one or more of the functions of the above-described embodiments is supplied to a system or device via a network or a storage medium, and one or more processors in a computer of the system or device read and execute the program. The present invention can also be realized by a circuit (e.g., ASIC) for implementing one or more of the functions.

[0065] <Summary of the embodiment> The disclosure of this specification includes the following information processing device, exposure device, acquisition method, program, and method for manufacturing an article.

[0066] (Item 1) An information processing apparatus characterized by acquiring information regarding a second exposure dose when exposing a second substrate by inputting information regarding a second original used to expose a second substrate into a learning model generated by machine learning using learning data including information regarding a first original used to expose a first substrate and information regarding a first exposure dose when the first substrate is exposed.

[0067] (Item 2) generating the learning model by machine learning using the learning data; 2. The information processing device according to item 1,

[0068] (Item 3) the information about the first master includes information about a type of a first pattern formed on the first master, The information about the second master includes information about a type of a second pattern formed on the second master. 3. The information processing device according to item 1 or 2.

[0069] (Item 4) 4. The information processing device according to item 3, wherein the first pattern type and the second pattern type include either a line and space pattern or a hole pattern.

[0070] (Item 5) 4. The information processing device according to item 3, wherein the first pattern type and the second pattern type include either a device pattern or an auxiliary pattern provided around the device pattern.

[0071] (Item 6) the information about the first master includes information about a dimension of a first pattern formed on the first master; The information about the second master includes information about a dimension of a second pattern formed on the second master. 6. An information processing device according to claim 5, characterized in that:

[0072] (Item 7) The dimensions of the first pattern include at least one of the following: a dimension of each line included in the first pattern, a dimension of each hole included in the first pattern, and information regarding an interval between each line or each hole included in the first pattern; The dimensions of the second pattern include at least one of the following: dimensions of each line included in the second pattern, dimensions of each hole included in the second pattern, and information regarding the intervals between each line or each hole included in the second pattern. 7. The information processing device according to item 6,

[0073] (Item 8) the information about the first master includes information about a type of the first master, The information on the second master includes information on the type of the second master. 8. The information processing device according to any one of items 1 to 7,

[0074] (Item 9) 9. The information processing device according to item 8, wherein the type of the first master and the type of the second master include at least one of a positive reticle, a negative reticle, a binary reticle, and a phase shift reticle.

[0075] (Item 10) When the type of the first master includes a phase-shift reticle, the information about the first master includes information about a transmittance of a film formed as a first pattern on the first master; 10. The information processing device of item 9, wherein when the type of the second original includes a phase shift reticle, the information about the second original includes information about the transmittance of a film formed as a second pattern on the second original.

[0076] (Item 11) When the type of the first master includes a phase-shift reticle, the information about the first master includes information about a phase of light that is changed by a film formed as a first pattern on the first master; 10. The information processing device of item 9, wherein when the type of the second original includes a phase-shift reticle, the information about the second original includes information about the phase of light that changes due to a film formed as a first pattern on the first original.

[0077] (Item 12) the information about the first master includes information about a cross-sectional shape of a first pattern formed on the first master, The information about the second master includes information about a cross-sectional shape of a second pattern formed on the second master. 12. The information processing device according to any one of items 1 to 11,

[0078] (Item 13) the information about the first master includes information about a film thickness of a film formed as a first pattern on the first master, The information about the second master includes information about a film thickness of a film formed as a second pattern on the second master. 13. The information processing device according to any one of items 1 to 12.

[0079] (Item 14) the information about the first master includes information about manufacturing conditions when the first master was manufactured; The information about the second master includes information about manufacturing conditions when the second master was manufactured. 14. The information processing device according to any one of items 1 to 13,

[0080] (Item 15) the information about the first master includes information about a usage history of the first master, The information about the second master includes information about the usage history of the second master. 15. The information processing device according to any one of items 1 to 14.

[0081] (Item 16) An exposure apparatus that exposes a substrate to light from an original on which a pattern is formed, comprising: 16. An exposure apparatus comprising the information processing apparatus according to any one of items 1 to 15.

[0082] (Item 17) a first step of generating a learning model by machine learning using learning data including information on a first master used to expose a first substrate and information on a first exposure dose when the first substrate is exposed; An acquisition method characterized by comprising a second step of acquiring information regarding a second exposure dose when exposing a second substrate by inputting information regarding a second original used to expose the second substrate into the learning model.

[0083] (Item 18) a first step of generating a learning model by machine learning using learning data including information on a first master used to expose a first substrate and information on a first exposure dose when the first substrate is exposed; A program for causing a computer to execute an acquisition method characterized by having a second step of acquiring information regarding a second exposure amount when exposing the second substrate by inputting information regarding a second original used to expose the second substrate into the learning model.

[0084] (Item 19) a first step of generating a learning model by machine learning using learning data including information on a first master used to expose a first substrate and information on a first exposure dose when the first substrate is exposed; a second step of acquiring information about a second exposure dose when exposing a second substrate by inputting information about a second original used for exposing the second substrate into the learning model; a third step of exposing the second substrate to an exposure dose determined based on information relating to the second exposure dose; a fourth step of developing the exposed second substrate; A fifth step of producing an article from the developed second substrate; A method for producing an article, comprising the steps of:

Claims

1. An information processing apparatus characterized by obtaining information regarding a second exposure amount when exposing a second substrate by inputting information regarding a second original used to expose a second substrate into a learning model generated by machine learning using learning data including information regarding a first original used to expose a first substrate and information regarding a first exposure amount when the first substrate is exposed.

2. generating the learning model by machine learning using the learning data; 2. The information processing apparatus according to claim 1,

3. the information about the first master includes information about a type of a first pattern formed on the first master, The information about the second master includes information about a type of a second pattern formed on the second master.

2. The information processing apparatus according to claim 1,

4. 4. The information processing apparatus according to claim 3, wherein the first pattern type and the second pattern type include either a line and space pattern or a hole pattern.

5. 4. The information processing apparatus according to claim 3, wherein the first pattern type and the second pattern type include either a device pattern or an auxiliary pattern provided around the device pattern.

6. the information about the first master includes information about a dimension of a first pattern formed on the first master, The information about the second original includes information about a dimension of a second pattern formed on the second original.

2. The information processing apparatus according to claim 1,

7. the dimensions of the first pattern include at least one of the following: a dimension of each line included in the first pattern, a dimension of each hole included in the first pattern, and information regarding an interval between each line or each hole included in the first pattern; The dimensions of the second pattern include at least one of the following: a dimension of each line included in the second pattern, a dimension of each hole included in the second pattern, and information regarding an interval between each line or each hole included in the second pattern.

7. The information processing apparatus according to claim 6,

8. the information about the first master includes information about a type of the first master, The information on the second master includes information on the type of the second master.

2. The information processing apparatus according to claim 1,

9. 9. The information processing apparatus according to claim 8, wherein the type of the first original and the type of the second original include at least one of a positive type reticle, a negative type reticle, a binary reticle, and a phase shift reticle.

10. When the type of the first master includes a phase shift reticle, the information about the first master includes information about a transmittance of a film formed as a first pattern on the first master; 10. The information processing apparatus according to claim 9, wherein, when the type of the second original includes a phase shift reticle, the information regarding the second original includes information regarding the transmittance of a film formed as a second pattern on the second original.

11. When the type of the first original includes a phase-shift reticle, the information about the first original includes information about a phase of light that is changed by a film formed as a first pattern on the first original, 10. The information processing apparatus according to claim 9, wherein when the type of the second original includes a phase-shift reticle, the information about the second original includes information about the phase of light that is changed by a film formed as a first pattern on the first original.

12. the information about the first master includes information about a cross-sectional shape of a first pattern formed on the first master, The information about the second original includes information about a cross-sectional shape of a second pattern formed on the second original.

2. The information processing apparatus according to claim 1,

13. the information about the first master includes information about a film thickness of a film formed as a first pattern on the first master, The information about the second master includes information about a film thickness of a film formed as a second pattern on the second master.

2. The information processing apparatus according to claim 1,

14. the information about the first master includes information about manufacturing conditions when the first master was manufactured; The information about the second master includes information about manufacturing conditions when the second master was manufactured.

2. The information processing apparatus according to claim 1,

15. the information about the first master includes information about a usage history of the first master, The information about the second master includes information about the usage history of the second master.

2. The information processing apparatus according to claim 1,

16. An exposure apparatus that exposes a substrate to light from an original on which a pattern is formed, comprising: An exposure apparatus comprising the information processing apparatus according to claim 1.

17. a first step of generating a learning model by machine learning using learning data including information on a first original used to expose a first substrate and information on a first exposure dose when the first substrate is exposed; An acquisition method characterized by comprising a second step of acquiring information regarding a second exposure amount when exposing a second substrate by inputting information regarding a second original used to expose the second substrate into the learning model.

18. a first step of generating a learning model by machine learning using learning data including information on a first original used to expose a first substrate and information on a first exposure dose when the first substrate is exposed; A program for causing a computer to execute an acquisition method characterized by having a second step of acquiring information regarding a second exposure amount when exposing the second substrate by inputting information regarding a second original plate used to expose the second substrate into the learning model.

19. a first step of generating a learning model by machine learning using learning data including information on a first original used to expose a first substrate and information on a first exposure dose when the first substrate is exposed; a second step of acquiring information about a second exposure dose when exposing a second substrate by inputting information about a second original used for exposing the second substrate into the learning model; a third step of exposing the second substrate to an exposure dose determined based on information relating to the second exposure dose; a fourth step of developing the exposed second substrate; A fifth step of producing an article from the developed second substrate; A method for producing an article, comprising the steps of:

Images