Information processing apparatus, method, molding device, lithography system, method for manufacturing article, and program

Abstract

To provide technique advantageous for evaluating molding processing of forming a cured product of a moldable material on a substrate.SOLUTION: An information processing apparatus evaluates molding processing of bringing a moldable material on a substrate and a mold into contact with each other, and curing the moldable material to form the cured product of the moldable material on the substrate. The information processing apparatus has: an acquisition unit that acquires an image including the moldable material on the substrate while the molding processing is performed; a detection unit that detects the presence or absence of a defect in the image acquired by the acquisition unit; and a determination unit that determines the type of the defect in the image acquired by the acquisition unit. The detection unit generates defect data indicating a defective portion where the defect is present, from the image acquired by the acquisition unit, according to a first inference model. The determination unit generates characteristic data indicating the characteristics of the defect, from the defective portion indicated by the defect data in the image acquired by the acquisition unit, according to a second inference model different from the first inference model, and determines the type of the defect on the basis of the characteristic data.SELECTED DRAWING: Figure 7

Description

Technical Field

[0001] The present invention relates to an information processing apparatus, method, molding apparatus, lithography system, method for manufacturing an article, and program.

Background Art

[0002] As a technique for forming a fine pattern on a substrate, an imprint apparatus using imprint technology has been put into practical use. In imprint technology, one of the curing methods of the imprint material is a photocuring method. In the photocuring method, light such as ultraviolet light is irradiated in a state where the imprint material disposed (supplied) on the substrate is in contact with the mold to cure the imprint material, and the mold is separated from the cured imprint material to form a pattern of the imprint material on the substrate.

[0003] In an imprint apparatus, defects may occur in the pattern formed on the substrate due to entrapment of foreign matter between the mold and the substrate, remaining of air bubbles when the mold and the imprint material on the substrate are brought into contact, peeling of the pattern (imprint material) when the mold is separated, and the like. Therefore, an imprint apparatus has been proposed that includes an imaging unit that images a state where the imprint material on the substrate is in contact with the mold, and detects defects in the pattern formed on the substrate from the image obtained by the imaging unit (see Patent Document 1).

[0004] The influence of defects in the pattern formed on the substrate on subsequent processes varies, and countermeasures for such defects also vary, such as those that require immediate stoppage of processing, those that require stoppage of processing of the next substrate, and those that can continue processing without problems. Therefore, when detecting defects in the pattern formed on the substrate, it is required to distinguish and classify the characteristics of such defects (determine the type of defects).

[0005] On the one hand, in an imprint apparatus, phenomena such as the imprint material protruding from the shot area on the substrate ("seepage"), the imprint material not spreading over the entire shot area and the pattern not being partially formed ("unfilled") may occur. Therefore, techniques for inspecting such seepage and unfilled conditions to detect and classify abnormalities (defects) in the pattern formed on the substrate have also been proposed (see Patent Documents 2 and 3). In such techniques, defect detection and classification are performed using an inference model that outputs the characteristics of pattern defects. The inference model is generated by performing machine learning using data in which the positions and classifications of defects are labeled for images including pattern defects as teacher data.

Prior Art Documents

Patent Documents

[0006]

Patent Document 1

Patent Document 2

Patent Document 3

Summary of the Invention

Problems to be Solved by the Invention

[0007] However, when generating an inference model from machine learning using teacher data as in the prior art, it is difficult not only to classify but also to detect defects in patterns not included in the teacher data. This is because the inference model cannot distinguish between pattern defects, noise, contrast, the substrate background (pattern), etc. contained in the image. The images used for detecting pattern defects vary depending on the substrate background, mold design (pattern), reflectivity of the substrate (imprint material) or mold, film thickness of the pattern formed on the substrate, etc., regardless of the presence or absence of pattern defects. Therefore, it is possible to detect pattern defects to some extent by considering the factors that vary such images, but it must be within a range that does not affect defect detection. In other words, an inference model capable of detecting and classifying defects is required even for pattern defects not included in the teacher data.

[0008] The present invention has been made in view of such problems of the prior art, and an exemplary object is to provide a technique advantageous for evaluating a molding process for forming a cured product of a moldable material on a substrate.

Means for Solving the Problems

[0009] To achieve the above object, an information processing apparatus according to one aspect of the present invention is an information processing apparatus that evaluates a forming process of bringing a formable material on a substrate into contact with a mold and curing the formable material to form a cured product of the formable material on the substrate, the information processing apparatus including: an acquisition unit that acquires an image including the formable material on the substrate while the forming process is being performed; a detection unit that detects the presence or absence of a defect in the image acquired by the acquisition unit; and a determination unit that determines the type of the defect in the image acquired by the acquisition unit, wherein the detection unit generates defect data indicating a defective portion where the defect exists from the image acquired by the acquisition unit according to a first inference model, the determination unit generates feature data indicating the characteristics of the defect from the defective portion indicated by the defect data in the image acquired by the acquisition unit according to a second inference model different from the first inference model, and determines the type of the defect based on the feature data.

[0010] A further object or other aspect of the present invention will be clarified by the embodiments described below with reference to the accompanying drawings.

Effects of the Invention

[0011] According to the present invention, for example, it is possible to provide a technique advantageous for evaluating a forming process of forming a cured product of a formable material on a substrate.

Brief Description of the Drawings

[0012]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Figure 8

Figure 9

Figure 10

Figure 11

Figure 12

Figure 13

Mode for Carrying Out the Invention

[0013] 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 a plurality of features are described in the embodiments, not all of these plurality of features are essential for the invention, and the plurality of features may be arbitrarily combined. Further, in the accompanying drawings, the same or similar configurations are denoted by the same reference numerals, and redundant descriptions are omitted.

[0014] FIGS. 1(a) and 1(b) are schematic diagrams showing the configuration of an imprint apparatus IMP as one aspect of the present invention. The imprint apparatus IMP is a lithography apparatus that forms a pattern on a substrate using a mold. In the present embodiment, the imprint apparatus IMP performs an imprint process as a forming process of bringing a mold into contact with a moldable material on the substrate and curing the moldable material to form a cured product of the moldable material on the substrate. The imprint apparatus IMP brings an uncured imprint material (moldable material) disposed on the substrate into contact with the mold, and gives energy for curing to the imprint material, thereby forming a pattern of a cured product in which the pattern of the mold is transferred.

[0015] As the imprint material, a material (curable composition) that cures when energy for curing is applied is used. As the energy for curing, electromagnetic waves, heat, or the like is used. The electromagnetic waves include, for example, light selected from the range of wavelengths of 10 nm or more and 1 mm or less, specifically, infrared rays, visible rays, ultraviolet rays, and the like. Thus, the curable composition is a composition that cures by light irradiation or heating. The photocurable composition that cures by light irradiation contains at least a polymerizable compound and a photoinitiator, and may further contain a non-polymerizable compound or a solvent as necessary. The non-polymerizable compound is at least one selected from the group consisting of a sensitizer, a hydrogen donor, an internal release agent, a surfactant, an antioxidant, a polymer component, and the like. The viscosity (viscosity at 25°C) of the curable composition is, for example, 1 mPa·s or more and 100 mPa·s or less.

[0016] As the material of the substrate, for example, glass, ceramics, metal, semiconductor, resin, or the like is used. As necessary, a member made of a material different from that of the substrate may be provided on the surface of the substrate. The substrate includes, for example, a silicon wafer, a compound semiconductor wafer, and quartz glass.

[0017] In this specification and the accompanying drawings, directions are indicated in an XYZ coordinate system where the direction parallel to the surface of the substrate S is 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 the rotations around the X-axis, Y-axis, and Z-axis are θX, θY, and θZ, respectively. Control or drive related to the X-axis, Y-axis, and Z-axis means control or drive related to the directions parallel to the X-axis, Y-axis, and Z-axis, respectively. Also, control or drive related to the θX-axis, θY-axis, and θZ-axis means control or drive related to the rotations around the axes parallel to the X-axis, Y-axis, and Z-axis, respectively. Further, the position is information specified based on the coordinates of the X-axis, Y-axis, and Z-axis, and the orientation is information specified by the values of the θX-axis, θY-axis, and θZ-axis. Positioning means controlling the position and / or orientation. Alignment includes controlling the position and orientation of at least one of the substrate and the mold.

[0018] The imprint apparatus IMP includes a substrate holding unit 102 that holds the substrate S, a substrate driving mechanism 105 that drives the substrate S by driving the substrate holding unit 102, a base 104 that supports the substrate holding unit 102, and a position measuring unit 103 that measures the position of the substrate holding unit 102. The substrate driving mechanism 105 includes a motor such as a linear motor, for example.

[0019] The imprint apparatus IMP includes a sensor 151 that measures 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 in alignment performed with the imprint material IM on the substrate S and the pattern region MP of the mold M in contact is, for example, equivalent to the shearing force acting between the substrate S and the mold M. The shearing force is mainly a force acting in the plane direction of the substrate S and the mold M. The substrate driving force in alignment has a correlation with, for example, the magnitude of the current supplied to the substrate driving mechanism 105 (the motor thereof) during alignment. Therefore, the sensor 151 can obtain the substrate driving force by detecting the current (magnitude) supplied to the substrate driving mechanism 105. Thus, the sensor 151 functions as a sensor for measuring the influence (shearing force) received by the mold M in pattern formation. Note that the drive request (command value) output from the control unit 110 to the substrate driving mechanism 105, which will be described later, is referred to as a stage control value.

[0020] The imprint apparatus IMP includes a mold holding unit 121 that holds the mold M, a mold driving mechanism 122 that drives the mold M by driving the mold holding unit 121, and a support structure 130 that supports the mold driving mechanism 122. The mold driving mechanism 122 includes, for example, a motor such as a voice coil motor.

[0021] The imprint apparatus IMP has a sensor 152 that measures a release force (separation load) and / or a pressing force (pressing pressure). The release force is the force required to separate (release) the cured imprint material IM on the substrate S from the mold M. The pressing force is the force for pressing the mold M against the imprint material IM on the substrate S. The release force and the pressing force mainly act in a direction perpendicular to the plane direction of the substrate S and the mold M. The release force and the pressing force are correlated with, for example, the magnitude of the current supplied to the mold driving mechanism 122 (the motor thereof). Therefore, the sensor 152 can obtain the release force and / or the pressing force by detecting the current (magnitude) supplied to the mold driving mechanism 122. Thus, the sensor 152 functions as a sensor for measuring the influence (release force and / or pressing force) received by the mold M in pattern formation. Note that the drive request (command value) output from the control unit 110 to the mold driving mechanism 122, which will be described later, is referred to as a stage control value.

[0022] The substrate driving mechanism 105 and the mold driving mechanism 122 constitute a driving mechanism that drives at least one of the substrate S and the mold M so that the relative position (and relative attitude) between the substrate S and the mold M is adjusted. The adjustment of the relative position between the substrate S and the mold M by such a driving mechanism includes driving for the contact between the imprint material IM on the substrate S and the mold M, and driving for the separation of the mold M from the cured imprint material IM (pattern of the cured product) on the substrate S. Further, the adjustment of the relative position between the substrate S and the mold M by the driving mechanism includes the alignment between the substrate S and the mold M. The substrate driving mechanism 105 is configured to drive the substrate S with respect to a plurality of axes (for example, three axes of the X axis, Y axis, and θZ axis, preferably six axes of the X axis, Y axis, Z axis, θX axis, θY axis, and θZ axis). The mold driving mechanism 122 is configured to drive the mold M with respect to a plurality of axes (for example, three axes of the Z axis, θX axis, and θY axis, preferably six axes of the X axis, Y axis, Z axis, θX axis, θY axis, and θZ axis).

[0023] The imprinting apparatus IMP includes a mold transfer mechanism 140 that transfers the mold M and a mold cleaner 150. The mold transfer mechanism 140 is configured to transfer the mold M to the mold holding portion 121, for example, or to transfer the mold M from the mold holding portion 121 to a stocker (not shown) or the mold cleaner 150. The mold cleaner 150 cleans the mold M using, for example, ultraviolet rays or a chemical solution.

[0024] The imprinting apparatus IMP has a window member 125 for forming a pressure control space CS on the side of the back surface of the mold M (the surface opposite to the pattern region MP of the substrate S). The window member 125 is made of a material that transmits the curing energy from the curing unit 107 and enables the application of the curing energy to the imprinting material IM on the substrate S. The imprinting apparatus IMP has a deformation mechanism 123 that deforms the pattern region MP of the mold M into a convex shape toward the substrate S by controlling the pressure in the pressure control space CS (hereinafter referred to as the "cavity pressure"), as schematically shown in FIG. 1(b).

[0025] The imprinting apparatus IMP has an alignment measurement system 106 that illuminates the alignment marks provided on each of the substrate S (the shot region) and the mold M and images their images to measure the relative positions between those marks. The imprinting apparatus IMP may have a plurality of alignment measurement systems 106 in order to simultaneously observe a plurality of alignment marks provided on each of the substrate S and the mold M.

[0026] The imprinting apparatus IMP has a curing unit 107 for curing the imprinting material IM on the substrate S. The curing unit 107 cures the imprinting material IM by irradiating the imprinting material IM with energy for curing the imprinting material IM, for example, light such as ultraviolet light, through an optical member 111.

[0027] The imprint apparatus IMP includes an imaging unit 112 that images a mold M, a substrate S, and an imprint material IM on the substrate S via an optical member 111 and a window member 125. Note that the image captured by the imaging unit 112 is also referred to as a spread image.

[0028] The imprint apparatus IMP includes a dispenser 108 for disposing, supplying, or distributing the imprint material IM onto the substrate S. The dispenser 108 discharges the imprint material IM such that droplets of the imprint material IM are disposed on the substrate S according to, for example, a drop recipe indicating positions on the substrate S where the droplets of the imprint material IM are to be disposed.

[0029] The imprint apparatus IMP includes a control unit 110 that comprehensively controls each part of the imprint apparatus IMP to operate the imprint apparatus IMP. The control unit 110 is configured by, for example, a PLD (abbreviation for Programmable Logic Device) such as an FPGA (abbreviation for Field Programmable Gate Array), or an ASIC (abbreviation for Application Specific Integrated Circuit), or a general-purpose computer in which a program is incorporated, or a combination of all or part of these.

[0030] In the present embodiment, as will be described later, the imprint apparatus IMP is also an inspection apparatus that evaluates the imprint process using the image captured by the imaging unit 112. Specifically, the inspection apparatus detects the presence or absence of defects in the pattern formed on the substrate and determines the type of defect. The inspection apparatus may be configured outside the imprint apparatus IMP, or a part of the inspection apparatus may be configured outside the imprint apparatus IMP as an information processing apparatus.

[0031] FIG. 2 is a schematic diagram showing the configuration of a lithography system 1001 for manufacturing articles such as semiconductor devices. The lithography system 1001 includes one or more imprint apparatuses IMP, one or more inspection apparatuses 1005, one or more processing apparatuses 1006, one or more generation apparatuses 1007, and a control apparatus 1003. Note that the lithography system 1001 may further include one or more exposure apparatuses.

[0032] The inspection apparatus 1005 includes, for example, an overlay inspection apparatus, a foreign matter inspection apparatus, and the like. The processing apparatus 1006 includes, for example, an etching apparatus, a film forming apparatus, and the like. The imprint apparatus IMP, the inspection apparatus 1005, the processing apparatus 1006, the generation apparatus 1007, and the control apparatus 1003 are connected to each other via a network 1002. In the lithography system 1001, the imprint apparatus IMP, the inspection apparatus 1005, the processing apparatus 1006, and the generation apparatus 1007 are controlled by a control apparatus 1003, which is an external apparatus different from the imprint apparatus IMP. The control apparatus 1003 includes, for example, a Manufacturing Execution System (MES), an Electronic Engine Control (EEC), and the like.

[0033] The generation apparatus 1007 is an apparatus that generates inference models (a first inference model and a second inference model) used in defect detection processing described later by machine learning. The generation apparatus 1007 is configured by, for example, 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 in which a program is incorporated, or a combination of all or part of these, similar to the control unit 110 of the imprint apparatus IMP. The generation apparatus 1007 is embodied by, for example, an information processing apparatus such as a server. Further, the generation apparatus 1007 may be realized using (in combination with) the control unit 110 of the imprint apparatus IMP and the control apparatus 1003.

[0034] Referring to FIG. 3, the operation of the imprint apparatus IMP and the lithography system 1001 including the imprint apparatus IMP will be described. Such operation is controlled by at least one of the control unit 110 and the control device 1003. Also, it is assumed that the mold M has been previously carried into the imprint apparatus IMP and is held by the mold holding unit 121.

[0035] In S101, the substrate S is carried into the imprint apparatus IMP. Specifically, using a substrate transfer mechanism (not shown), the substrate S is transferred from the transfer source (the relay part with the pretreatment apparatus) to the substrate holding unit 102, and the substrate S is held by the substrate holding unit 102.

[0036] S102 to S106 show each step of the imprint process (pattern formation) for the shot area to be imprinted among the plurality of shot areas on the substrate.

[0037] In S102, the imprint material IM is arranged (supplied) to the shot area to be imprinted on the substrate. Specifically, while driving the substrate S by the substrate driving mechanism 105, the imprint material IM is discharged from the dispenser 108, thereby arranging the imprint material IM in the shot area to be imprinted.

[0038] In S103, the imprint material IM on the shot area to be imprinted and the mold M (the pattern area MP thereof) are brought into contact. Specifically, the substrate S and the mold M are relatively driven by at least one of the substrate driving mechanism 105 and the mold driving mechanism 122, so that the imprint material IM on the shot area to be imprinted and the mold M are brought into contact. For example, the mold M is driven by the mold driving mechanism 122 so that the mold M contacts the imprint material IM on the shot area to be imprinted. When bringing the imprint IM on the shot area to be imprinted into contact with the mold M, the pattern area MP of the mold M may be deformed into a convex shape toward the substrate S by the deformation mechanism 123. At this time, in the present embodiment, the imaging unit 112 continuously images the mold M, the substrate S, and the imprint material IM on the substrate S to obtain a spread image, and a defect detection process described later is performed using such a spread image. The inference models (the first inference model and the second inference model) used in the defect detection process are pre-generated in the generation device 1007 and can be obtained from the generation device 1007. Further, the spread image obtained in S103 is transmitted to the generation device 1007 in order to generate or update the inference model in the generation device 1007.

[0039] In S104, alignment (positioning) of the substrate S and the mold M is performed, specifically, alignment of the shot area to be imprinted and the pattern area MP of the mold M is performed. Specifically, while measuring the relative position between the alignment mark of the shot area to be imprinted and the alignment mark of the mold M by the alignment measurement system 106, alignment is performed so that such a relative position falls within the allowable range of the target relative position. For example, the substrate S and the mold M are relatively driven by at least one of the substrate driving mechanism 105 and the mold driving mechanism 122 so that their relative position is within the allowable range of the target relative position. The target device position is set according to a correction value determined from, for example, past results obtained by an overlay inspection device (inspection device 1005).

[0040] In S105, the imprint material IM on the shot area to be imprinted is cured while the imprint material IM and the mold M are in contact with each other. Specifically, energy for curing the imprint material IM is irradiated onto the imprint material IM between the curing unit 107 and the pattern area MP of the substrate S and the mold M. As a result, the imprint material IM is cured, and a cured product (pattern) of the imprint material IM is formed in the shot area to be imprinted.

[0041] In S106, the mold M is separated (released) from the cured imprint material IM on the shot area to be imprinted. Specifically, the substrate S and the mold M are relatively driven by at least one of the substrate driving mechanism 105 and the mold driving mechanism 122 so that the cured product of the imprint material IM and the pattern area MP of the mold M are separated. For example, the mold M is driven by the mold driving mechanism 122 so that the mold M is separated from the cured product of the imprint material IM on the shot area to be imprinted. When separating the mold M from the cured imprint IM on the shot area to be imprinted, the pattern area MP of the mold M may be deformed into a convex shape toward the substrate S by the deformation mechanism 123. At this time, in this embodiment, the imaging unit 112 continuously images the mold M, the substrate S, and the imprint material IM on the substrate S to obtain a spread image, and a defect detection process described later is performed using such a spread image. Further, the spread image obtained in S106 is transmitted to the generation device 1007 in order to generate or update an inference model in the generation device 1007.

[0042] In S107, it is determined whether imprinting processes (S102 to S106) have been performed on all the shot areas on the substrate. If the imprinting processes have not been performed on all the shot areas, the process proceeds to S102 to perform an imprinting process on the next shot area to be imprinted. On the other hand, if the imprinting processes have been performed on all the shot areas, the process proceeds to S108.

[0043] In S108, the substrate S is unloaded from the imprint apparatus IMP. Specifically, using a substrate transfer mechanism (not shown), the substrate S is transferred from the substrate holding unit 102 to a transfer destination (for example, a relay unit with a post-processing apparatus).

[0044] When processing a lot composed of a plurality of substrates, each of the plurality of substrates undergoes each process shown in FIG. 3.

[0045] Here, as an example of a defect to be detected in the defect detection process, "foreign object entrapment", "unfilled imprint material", and "abnormal release" will be described.

[0046] First, referring to FIGS. 4(a), 4(b), and 4(c), "foreign object entrapment" will be described. The imprint apparatus IMP is generally installed in a clean environment for manufacturing semiconductor devices and the like, but it is difficult to realize an environment where no foreign objects are generated at all. In reality, in the environment where the imprint apparatus IMP is installed, there are foreign objects generated from the members themselves constituting the imprint apparatus IMP, foreign objects generated by the sliding of the members against each other, and foreign objects adhering to and entering the mold M and the substrate S from outside the apparatus. For example, when the imprint material IM on the substrate and the mold M are brought into contact with each other with a foreign object attached to the substrate S, the foreign object is entrapped between the substrate S and the mold M, and defects occur in the pattern formed on the substrate. Also, depending on the size and hardness of the foreign object, the pattern of the mold M may be damaged.

[0047] FIG. 4(a) shows a state where a foreign object P is entrapped between the substrate S and the mold M together with the imprint material IM. Since the substrate S is held by the substrate holding unit 102, it maintains a flat state (plane). On the other hand, since a pressure control space CS (deformable part) is formed on the back side of the mold M, the part in contact with the foreign object P deforms according to the foreign object P.

[0048] FIG. 4(b) shows a spread image obtained by imaging the mold M, the substrate S, and the imprint material IM with the imaging unit 112 in a state where a foreign object P is sandwiched between the substrate S and the mold M. In the spread image, the portion corresponding to the foreign object P has a brightness determined by the reflectivity of the surface of the foreign object P, and interference fringes due to light interference are present around it. This is because, as described above, the portion of the mold M in contact with the foreign object P is deformed. As shown in FIG. 4(c), the light irradiated from the imaging unit 112 onto the mold M or the substrate S is reflected on the surface of the substrate S and also on the surface of the mold M facing the substrate S. Therefore, these reflected lights interfere with each other due to the optical path difference 2d, resulting in interference fringes.

[0049] Thus, when a foreign object P is sandwiched between the substrate S and the mold M, although the image in the spread image differs depending on the size and shape of the foreign object P, a spread image having the characteristic that the above-described interference fringes appear can be obtained.

[0050] Next, with reference to FIGS. 5(a) and 5(b), "unfilled imprint material" will be described. In the imprint apparatus IMP, when the imprint material IM on the substrate and the mold M are brought into contact with each other, the pressure in the pressure control space CS formed on the back side of the mold M is controlled to deform the pattern region MP of the mold M into a convex shape toward the substrate S. Thereby, although the remaining of bubbles (gases) between the substrate S and the mold M is suppressed, depending on the pattern of the mold M, a defect due to a so-called "unfilled imprint material" in which bubbles remain between the substrate S and the mold M occurs.

[0051] FIG. 5(a) shows a state in which air bubbles AB remain between the substrate S and the mold M, resulting in unfilling of the imprint material IM. Further, FIG. 5(b) shows a spread image obtained by imaging the mold M, the substrate S, and the imprint material IM by the imaging unit 112 in a state where unfilling of the imprint material IM has occurred. In the region filled with the imprint material IM and the region where air bubbles AB, which are regions where the imprint material IM is not filled, exist, they are imaged as regions with different brightnesses due to the difference in the transmittance of the imprint material IM and the air bubbles AB with respect to the light irradiated from the imaging unit 112. Further, since the air bubbles AB remain along the pattern (recess) of the mold M in the region where the imprint material IM is not filled, it has a shape along the pattern of the mold M. The pattern of the mold M for manufacturing a semiconductor device often has a linear shape, and the region where the imprint material IM is not filled also has the same characteristics.

[0052] Thus, when unfilling of the imprint material IM occurs, although the image in the spread image differs depending on the shape of the pattern of the mold M, a spread image having the characteristics in which the above-described shape appears is obtained.

[0053] Next, referring to FIGS. 6(a) and 6(b), "abnormal release" will be described. In the imprint apparatus IMP, when separating the mold M from the imprint material IM on the substrate, by controlling the pressure in the pressure control space CS formed on the back side of the mold M, the pattern region MP of the mold M is deformed into a convex shape toward the substrate S. Thereby, the separation between the imprint material IM on the substrate and the mold M is facilitated. However, due to the degree of deformation (deformation amount, shape, curing state of the imprint material IM, speed of separating the mold M (release speed), etc.) of the pattern region MP of the mold M, a defect due to a so-called "abnormal release" occurs in which the imprint material IM on the substrate remains attached to the mold M and is separated from the substrate S.

[0054] FIG. 6(a) shows a state in which the imprint material IM (a part thereof) is peeled off from the substrate S, and an abnormal release has occurred. Further, FIG. 6(b) shows a spread image obtained by imaging the mold M, the substrate S, and the imprint material IM by the imaging unit 112 in a state where an abnormal release has occurred. In the region RB where the imprint material IM is peeled off and the region where the imprint material IM is not peeled off, they are imaged as regions with different brightnesses due to the difference between the reflected light from the imprint material IM and the reflected light from the substrate S (region RB). Further, the region RB where the imprint material IM is peeled off has a random shape without depending on the pattern of the mold M.

[0055] As described above, when an abnormal release occurs, although the image in the spread image differs depending on the size and shape of the region RB where the imprint material IM is peeled off, a spread image having the characteristics in which the above-described shape appears can be obtained.

[0056] Therefore, when defects due to "foreign object entrapment", "unfilled imprint material", or "abnormal release" occur, the images in the spread image are not the same, and spread images having their respective characteristics can be obtained.

[0057] Hereinafter, the defect detection process in the present embodiment will be described. The defect detection process is a process for detecting defects such as "foreign object entrapment", "unfilled imprint material", and "abnormal release", and is also a process for evaluating the imprint process (molding process).

[0058] FIG. 7 is a diagram for explaining the defect detection process in the present embodiment. As shown in FIG. 7, the imprint apparatus IMP (control unit 110 thereof) or the control apparatus 1003 has a defect detection unit 705 and a defect determination unit 707 as functional blocks for performing the defect detection process. The defect detection unit 705 has a function of detecting the presence or absence of a defect using a first inference model. The defect determination unit 707 has a function of determining the type of defect (classifying the defect) using a second inference model different from the first inference model. In the present embodiment, the defect detection process is performed by utilizing the defect detection unit 705 and the defect determination unit 707.

[0059] The defect detection unit 705 generates a defect detection result 706 based on an image 701 (spread image) to be defect-detected, device data 702, substrate data 703, and mold data 704. The image 701 is an image including the imprint material IM on the substrate S during the imprint process, and is, for example, an image obtained by the imaging unit 112 in S103 or S106 as described above. The device data 702 includes information regarding the imaging conditions of the image 701, and includes, for example, information regarding the imaging position of the image 701 and information regarding the illumination conditions at the time of imaging the image 701. The substrate data 703 includes information regarding the substrate S, and includes, for example, information regarding a pattern (underlying pattern) existing on the substrate S before the imprint process and information regarding the film thickness of the pattern (cured product) of the imprint material IM to be formed on the substrate S. The mold data 704 includes information regarding the mold M, and includes, for example, information regarding the pattern (design data) of the mold M. Note that in the present embodiment, the defect detection unit 705 also has a function as an acquisition unit that acquires the image 701 from the imaging unit 112, but such an acquisition unit may be provided separately from the defect detection unit 705. Further, the imaging unit 112 may be regarded as an acquisition unit that acquires the image 701, or a part of the acquisition unit.

[0060] The defect determination unit 707 generates a defect determination result 708 based on the image 701 to be defect-detected and the defect detection result 706 output from the defect detection unit 705. Further, the defect determination unit 707 may generate the defect determination result 708 based on the device data 702, the substrate data 703, and the mold data 704 in addition to the image 701 and the defect detection result 706. The defect detection result 706 may be input data for the defect determination unit 707 or an execution condition for the defect determination unit 707. Note that the execution condition is, for example, a condition for surely classifying defects in the defect determination unit 707.

[0061] Referring to FIG. 8, the processing in the defect detection unit 705 will be described in detail. In the defect detection unit 705, as shown in FIG. 8, by inputting the image 701 into the first inference model 751, abnormal information 752 output from the first inference model 751 is obtained. The abnormal information 752 is intermediate data before the defect detection unit 705 generates the defect detection result 706. The defect detection unit 705 generates the defect detection result 706 of the image 701 based on the abnormal information 752 output from the first inference model 751, the device data 702, the substrate data 703, and the mold data 704.

[0062] In the present embodiment, as described above, in the generation device 1007, the first inference model 751 is generated by machine learning. However, the generation unit that generates the first inference model 751 may be provided in the imprint device IMP (control unit 110 thereof) or the control device 1003. The generation device 1007 performs machine learning using, for example, an image without defects among the images acquired by the imaging unit 112 as the input of the first inference model 751. Specifically, the generation device 1007 generates the first inference model 751 using an auto encoder, which is a method of machine learning.

[0063] FIGS. 9(a) and 9(b) are diagrams for explaining the outline of the auto encoder. As shown in FIG. 9(a), the auto encoder uses normal data 901 (for example, an image without defects, that is, an image without formation defects) as learning data to generate an inference model 904 (first inference model). Note that the normal data 901 is, for example, an image without defects, that is, an image without formation defects.

[0064] When abnormal data 903 is input as input data to an inference model 904 generated using a sufficient amount of normal data 901 as learning data, as shown in Fig. 9(b), normal data 906 with the abnormal part removed is output (estimated) as output data. Note that the abnormal data 903 is, for example, an image including a defect, that is, an image with a forming defect. On the other hand, when normal data 902 is input as input data to the inference model 904, as shown in Fig. 9(b), the same normal data 905 as the input data is output as output data.

[0065] In this embodiment, the defect detection unit 705 pre-gets a first inference model 751 from the generation device 1007. In the defect detection process, the defect detection unit 705 inputs an image 701 to be detected for defects to the first inference model 751 and obtains abnormal information 752. As described above, in the first inference model 751, when an image not including a defect (foreign matter entrapment, unfilled imprint material, abnormal mold release) is input as input data, data identical to the input data, that is, an image not including a defect, is output as output data. On the other hand, in the first inference model 751, when an image including a defect is input as input data, normal data inferred from the input data, that is, an image not including a defect, is output as output data. Therefore, as shown in Fig. 9(b), the difference between the input data (input image) and the output data (output image) represents the defective part included in the image and is generated as the abnormal information 752. The defect detection unit 705 detects (inspects) the presence or absence of a defect based on the presence or absence of the difference between the input data and the output data.

[0066] In this embodiment, it is assumed that the first inference model 751 (autoencoder) converts only the defects included in the image to be inspected for defects into normal data, that is, removes the defective parts. However, depending on the images used as learning data, there is a possibility that parts corresponding to the patterns (base patterns) existing on the substrate S and the patterns of the mold M before the imprint process may be removed as defective parts. Furthermore, differences in brightness due to imaging conditions (imaging position, lighting conditions, etc.) of the image to be inspected for defects become the difference between the input data and the output data, and there is also a possibility of removing them as defective parts. Therefore, in addition to the abnormality information 752 output from the first inference model 751, the defect detection unit 705 may detect the presence or absence of defects based on the device data 702, the substrate data 703, and the mold data 704. At this time, the contrast and brightness of the image to be inspected for defects may be changed (adjusted) in consideration of the device data 702 and the substrate data 703. Also, in consideration of the substrate data 703 and the mold data 704, the threshold value for detecting a defect by the difference between the normal data (image without defects) output from the first inference model 751 and the input image exceeding a certain value may be changed (adjusted). In this way, the defect detection result 706 may be generated by correcting the abnormality information 752 output from the first inference model 751 based on at least one of the substrate data 703, the mold data 704, and the device data 702.

[0067] With reference to FIG. 10, the processing in the defect determination unit 707 will be described in detail. In the defect determination unit 707, as shown in FIG. 10, an image 701 to be inspected for defects is input to the second inference model 1102. In addition to the image 701, the execution condition 1101 derived from the defect detection result 706 generated by the defect detection unit 705 is input to the second inference model 1102 together with the device data 702, the substrate data 703, and the mold data 704, which are the attached information of the image 701. Thereby, the defect determination unit 707 obtains a defect determination result 708 output from the second inference model 1102.

[0068] In this embodiment, as described above, in the generation device 1007, the second inference model 1102 is generated by machine learning. However, the generation unit that generates the second inference model 1102 may be provided in the imprint device IMP (control unit 110) or the control device 1003. The generation device 1007 uses, for example, the image acquired by the imaging unit 112 as the input to the second inference model 1102, and performs machine learning using, as teacher data, data indicating the relationship between a plurality of previously obtained images and the characteristics of the defects of each of the plurality of images. Specifically, the generation device 1007 generates the second inference model 1102 using R-CNN (Region Based Convolutional Neural Networks), which is a method of machine learning.

[0069] FIGS. 11(a) and 11(b) are diagrams for explaining the outline of R-CNN, which is machine learning using supervised learning. As shown in FIG. 11(a), an image 1111 including a defect is acquired from the image captured by the imaging unit 112 during the imprint process, and the defects included in the image 1111 are labeled with the type, size, position, etc. of the defects. Using these defect characteristics 1112 and the image 1111 as learning data, an inference model 1113 (second inference model) is generated.

[0070] When an image 1114 that is the target of defect detection is input as input data to the inference model 1113, as shown in FIG. 11(b), abnormal information 1115, which is feature data indicating the characteristics of the defects included in the image 1114, is output as output data.

[0071] In this embodiment, the defect determination unit 707 pre-gets the second inference model 1102 from the generation device 1007. In the defect detection process, the defect determination unit 707 inputs the image 701 to be detected for defects into the second inference model 1102 and obtains the abnormal information 1115. As described above, since the abnormal information 1115 is feature data indicating the features of the defects included in the image 701, the defect determination unit 707 determines the type of the defect based on the abnormal information 1115. At this time, in addition to the abnormal information 1115, the defect determination unit 707 may also determine the type of the defect based on at least one of the substrate data 703, the mold data 704, and the device data 702.

[0072] The execution condition 1101 will be described. In this embodiment, the execution condition 1101 of the defect determination unit 707 is changed according to the defect detection result 706 from the defect detection unit 705. For example, for the defect part detected as a defect by the defect detection unit 705, the defect determination unit 707 adjusts the threshold for determining the type of the defect included in the image 701 so that the type of the defect can be determined more easily than the part other than the defect part. Thereby, in the defect detection process, the defect determination unit 707 can easily determine the type of the defect (classification of the defect) for the defect part, and assign a defect type with high similarity to the features of the defect that would normally be buried, and determine the type of the defect. Note that the defect determination unit 707 may also perform weighting (emphasis) on the data of the defect part so that the type of the defect can be determined more easily than the part other than the defect part for the defect part detected as a defect by the defect detection unit 705.

[0073] With reference to FIGS. 12(a), 12(b), 12(c), and 12(d), the defect detection process in this embodiment will be specifically described. FIG. 12(a) is an image (spread image) to be subjected to defect detection. In the defect detection unit 705, by inputting the image shown in FIG. 12(a) into the first inference model 751, the output image shown in FIG. 12(b) is output. As described above, the output image shown in FIG. 12(b) is the difference from the normal data (image without defects) obtained by inputting the image shown in FIG. 12(a) into the first inference model 751, that is, the abnormal information 752. The defect detection unit 705 detects the presence or absence of defects from the output image shown in FIG. 12(b), and generates defect data indicating the defect portions PC and PD where defects exist as the defect detection result 706. Note that the defect data may be data including only the defect portions PC and PD in the image shown in FIG. 12(a), or may be data obtained by masking the portions of the image other than the defect portions PC and PD (portions other than the defect portions), as shown in FIG. 12(d). When the defect data includes only the defect portions PC and PD, it is possible to determine the types of defects existing in the defect portions PC and PD without being affected by the portions other than the defect portions.

[0074] The defect determination unit 707 determines the types of defects present in the defective portions PC and PD respectively, based on the defect detection result 706 generated from the output image shown in FIG. 12(b). In the defect determination unit 707, even if the image of the defect detection target shown in FIG. 12(a) is input to the second inference model 1102, it may not be possible to determine the types of defects present in the defective portions PC and PD respectively. Therefore, in the defect determination unit 707, as described above, for the defective portions PC and PD detected as defects by the defect detection unit 705, the threshold value for determining the type of defect is adjusted so that the type of defect can be easily determined. As a result, in the defect determination unit 707, feature data (abnormal information 1115) indicating the features of the defects present in the defective portion PC and the features of the defects present in the defective portion PD is output from the second inference model 1102. Based on such feature data, the defect determination unit 707 can determine the type DE of the defect present in the defective portion PC and the type DF of the defect present in the defective portion PD as shown in FIG. 12(c), and outputs them as the defect determination result 708.

[0075] Thus, according to the present embodiment, it is possible to detect and determine the type of a defect having a pattern not included in the training data, which is advantageous for evaluating the imprint process.

[0076] In the present embodiment, the description has been made with respect to the defects in the imprint apparatus IMP (imprint process), but the present invention is not limited thereto, and it is also applicable to other molding apparatuses using the imprint technology. For example, it can also be applied to a planarization apparatus that performs a planarization process of forming a flat film (flat surface) of a moldable material on a substrate. The planarization apparatus forms a flat film on the substrate by curing the moldable material in a state where the moldable material disposed on the substrate is in contact with a mold having a flat surface, similar to the imprint apparatus. Also in the planarization apparatus, there are problems such as entrapment of foreign matter, unfilling of the moldable material, and abnormal release, and an imaging unit that images an image including the moldable material on the substrate can also be configured, and the same effects can be obtained.

[0077] The pattern of the cured material formed using the imprint apparatus IMP or the lithography system 1001 is used permanently for at least a part of various articles or temporarily when manufacturing various articles. The articles include electric circuit elements, optical elements, MEMS, recording elements, sensors, or molds. Examples of the electric circuit elements include volatile or non-volatile semiconductor memories such as DRAM, SRAM, flash memory, and MRAM, and semiconductor elements such as LSI, CCD, image sensors, and FPGA. Examples of the mold include a mold for imprinting.

[0078] The pattern of the cured material is used as it is or temporarily used as a resist mask as a constituent member of at least a part of the above-mentioned articles. After etching or ion implantation is performed in the substrate processing step, the resist mask is removed.

[0079] Next, a specific manufacturing method of the article will be described. As shown in Fig. 13(a), a substrate such as a silicon wafer on which a material to be processed such as an insulator is formed on the surface is prepared, and then an imprint material is applied to the surface of the material to be processed by an inkjet method or the like. Here, a state where a plurality of droplet-shaped imprint materials are applied on the substrate is shown.

[0080] As shown in Fig. 13(b), an imprint mold is opposed with the side on which the concavo-convex pattern is formed facing the imprint material on the substrate. As shown in Fig. 13(c), the substrate on which the imprint material is applied and the mold are brought into contact with each other and pressure is applied. The imprint material is filled in the gap between the mold and the material to be processed. When light is irradiated through the mold as energy for curing in this state, the imprint material cures.

[0081] As shown in Fig. 13(d), after the imprint material is cured and the mold and the substrate are separated, a pattern of the cured material of the imprint material is formed on the substrate. The pattern of this cured material has a shape in which the concave portion of the mold corresponds to the convex portion of the cured material and the convex portion of the mold corresponds to the concave portion of the cured material, that is, the concavo-convex pattern of the mold is transferred to the imprint material.

[0082] As shown in FIG. 13(e), when etching is performed using the cured material pattern as an etching mask, among the surfaces of the workpiece, portions where the cured material is absent or remains thinly are removed to form grooves. As shown in FIG. 13(f), when the cured material pattern is removed, an article having grooves formed on the surface of the workpiece can be obtained. Here, the cured material pattern has been removed, but it may not be removed after processing and may be used, for example, as a film for interlayer insulation included in a semiconductor element or the like, that is, as a constituent member of the article.

[0083] The present invention can also be realized by supplying 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 one or more processors in a computer of the system or device read and execute the program. It can also be realized by a circuit (for example, an ASIC) that realizes one or more functions.

[0084] The disclosure of this specification includes the following information processing apparatus, method, molding apparatus, lithography system, method for manufacturing an article, and program.

[0085] (Item 1) An information processing apparatus for evaluating a molding process of bringing a moldable material on a substrate into contact with a mold and curing the moldable material to form a cured product of the moldable material on the substrate, an acquisition unit that acquires an image including the moldable material on the substrate while the molding process is being performed; a detection unit that detects the presence or absence of defects in the image acquired by the acquisition unit; a determination unit that determines the type of the defect in the image acquired by the acquisition unit; and having the detection unit generates defect data indicating a defective portion where the defect exists from the image acquired by the acquisition unit according to a first inference model, The determination unit generates feature data indicating the characteristics of the defect from the defective part indicated by the defect data among the images acquired by the acquisition unit according to a second inference model different from the first inference model, and determines the type of the defect based on the feature data. An information processing apparatus characterized by the above.

[0086] (Item 2) The determination unit adjusts a threshold value for determining the type of the defect so that the type of the defect can be more easily determined for the defective part than for the part other than the defective part. The information processing apparatus according to Item 1, characterized by the above.

[0087] (Item 3) The determination unit weights the data of the defective part so that the type of the defect can be more easily determined for the defective part than for the part other than the defective part. The information processing apparatus according to Item 1 or 2, characterized by the above.

[0088] (Item 4) The defect data is data including only the defective part of the image acquired by the acquisition unit. The information processing apparatus according to any one of Items 1 to 3, characterized by the above.

[0089] (Item 5) The defect data is data obtained by masking the part other than the defective part of the image acquired by the acquisition unit. The information processing apparatus according to any one of Items 1 to 3, characterized by the above.

[0090] (Item 6) The information processing apparatus according to any one of Items 1 to 5, further comprising a generation unit that generates the first inference model and the second inference model by machine learning, characterized by the above.

[0091] (Item 7) The generation unit performs machine learning using an image that does not include the defect among the images acquired by the acquisition unit as an input to the first inference model. The information processing apparatus according to Item 6, characterized by the above.

[0092] (Item 8) The information processing apparatus according to item 7, wherein the machine learning includes an autoencoder.

[0093] (Item 9) The generation unit uses the image acquired by the acquisition unit as the input of the second inference model, and performs machine learning using, as teacher data, data indicating the relationship between a plurality of previously obtained images and the features of the defects of each of the plurality of images. The information processing apparatus according to item 6, characterized in that

[0094] (Item 10) The information processing apparatus according to item 9, wherein the machine learning includes R-CNN.

[0095] (Item 11) The detection unit generates the defect data by correcting the data output from the first inference model based on at least one of substrate data including information on patterns existing on the substrate before the forming process, mold data including information on patterns of the mold, and apparatus data including information on imaging conditions of the image. The information processing apparatus according to any one of items 1 to 10, characterized in that

[0096] (Item 12) The determination unit determines the type of the defect based on at least one of substrate data including information on patterns existing on the substrate before the forming process, mold data including information on patterns of the mold, and apparatus data including information on imaging conditions of the image, in addition to the feature data. The information processing apparatus according to any one of items 1 to 11, characterized in that

[0097] (Item 13) The substrate data includes information on the film thickness of the cured product of the formable material to be formed on the substrate. The information processing apparatus according to item 11 or 12, characterized in that

[0098] (Item 14) A method for evaluating a forming process of bringing a formable material on a substrate into contact with a mold and curing the formable material to form a cured product of the formable material on the substrate, a first step of acquiring an image including the formable material on the substrate while the forming process is being performed; a second step of detecting the presence or absence of a defect in the image acquired in the first step; a third step of determining the type of the defect in the image acquired in the first step; comprising: in the second step, defect data indicating a defective portion where the defect exists is generated from the image acquired in the first step according to a first inference model; in the third step, feature data indicating the features of the defect is generated from the defective portion indicated by the defect data in the image acquired in the first step according to a second inference model different from the first inference model, and the type of the defect is determined based on the feature data. A method characterized by the above.

[0099] (Item 15) A forming apparatus for performing a forming process of bringing a formable material on a substrate into contact with a mold and curing the formable material to form a cured product of the formable material on the substrate, comprising an information processing apparatus for evaluating the forming process; the information processing apparatus includes the information processing apparatus according to any one of Items 1 to 13. A forming apparatus characterized by the above.

[0100] (Item 16) A forming apparatus for performing a forming process of bringing a formable material on a substrate into contact with a mold and curing the formable material to form a cured product of the formable material on the substrate, and an information processing apparatus for evaluating the forming process; comprising: the information processing apparatus includes the information processing apparatus according to any one of Items 1 to 13. A lithography system characterized by the following.

[0101] (Item 17) A step of forming a pattern on a substrate using the molding device according to Item 15; A step of processing the substrate on which the pattern has been formed in the above step; A step of manufacturing an article from the processed substrate; A method for manufacturing an article, characterized by comprising the above steps.

[0102] (Item 18) A program characterized by causing a computer to execute the method according to Item 14.

[0103] The invention is not limited to the above embodiments, and various changes and modifications can be made without departing from the spirit and scope of the invention. Therefore, the claims are attached to disclose the scope of the invention.

Explanation of Reference Numerals

[0104] IMP: Imprint device S: Substrate M: Mold 110: Control unit 102: Substrate holding unit 105: Substrate driving unit 121: Mold holding unit 122: Mold driving unit 705: Defect detection unit 751: First inference model 707: Defect determination unit 1102: Second inference model

Claims

1. An information processing apparatus for evaluating a forming process of forming a cured product of a formable material on a substrate by bringing the formable material on the substrate into contact with a mold and curing the formable material, an acquisition unit that acquires an image including the formable material on the substrate during the forming process; a detection unit that detects the presence or absence of defects in the image acquired by the acquisition unit; a determination unit that determines the type of the defect from the defect portion indicated by the defect data in the image acquired by the acquisition unit according to a second inference model different from the first inference model, and determines the type of the defect based on the feature data; comprising: The detection unit generates defect data indicating a defect portion where the defect exists from the image acquired by the acquisition unit according to a first inference model, The determination unit generates feature data indicating the features of the defect from the defect portion indicated by the defect data in the image acquired by the acquisition unit according to a second inference model different from the first inference model, and determines the type of the defect based on the feature data. An information processing apparatus characterized by the above.

2. The determination unit adjusts a threshold value for determining the type of the defect so that the type of the defect can be more easily determined for the defect portion than for portions other than the defect portion. The information processing apparatus according to claim 1, characterized by this.

3. The determination unit weights the data of the defect portion so that the type of the defect can be more easily determined for the defect portion than for portions other than the defect portion. The information processing apparatus according to claim 1, characterized by this.

4. The defect data is data including only the defect portion in the image acquired by the acquisition unit. The information processing apparatus according to claim 1, characterized by this.

5. The defect data is data obtained by masking portions other than the defect portion in the image acquired by the acquisition unit. The information processing apparatus according to claim 1, characterized by this.

6. The information processing apparatus according to claim 1, further comprising a generation unit that generates the first inference model and the second inference model by machine learning.

7. The information processing apparatus according to claim 6, wherein the generation unit performs machine learning using, as an input to the first inference model, an image that does not include the defect among the images acquired by the acquisition unit.

8. The information processing apparatus according to claim 7, wherein the machine learning includes an autoencoder.

9. The information processing apparatus according to claim 6, wherein the generation unit uses, as an input to the second inference model, the image acquired by the acquisition unit, and performs machine learning using, as teacher data, data indicating a relationship between a plurality of previously obtained images and characteristics of respective defects of the plurality of images.

10. The information processing apparatus according to claim 9, wherein the machine learning includes R-CNN.

11. The information processing apparatus according to claim 1, wherein the detection unit generates the defect data by correcting data output from the first inference model based on at least one of substrate data including information on patterns existing on the substrate before the forming process, mold data including information on patterns of the mold, and apparatus data including information on imaging conditions of the image.

12. The information processing apparatus according to claim 1, wherein the determination unit determines the type of the defect based on at least one of substrate data including information on patterns existing on the substrate before the forming process, mold data including information on patterns of the mold, and apparatus data including information on imaging conditions of the image, in addition to the feature data.

13. The information processing apparatus according to claim 11 or 12, wherein the substrate data includes information regarding the film thickness of the cured product of the formable material to be formed on the substrate.

14. A method for evaluating a forming process of forming a cured product of a formable material on a substrate by bringing the formable material on the substrate into contact with a mold and curing the formable material, comprising: a first step of acquiring an image including the formable material on the substrate while the forming process is being performed; a second step of detecting the presence or absence of a defect in the image acquired in the first step; a third step of determining the type of the defect in the image acquired in the first step; and having In the second step, defect data indicating a defective portion where the defect exists is generated from the image acquired in the first step according to a first inference model. In the third step, feature data indicating the characteristics of the defect is generated from the defective portion indicated by the defect data in the image acquired in the first step according to a second inference model different from the first inference model, and the type of the defect is determined based on the feature data. A method characterized by the above.

15. A forming apparatus for performing a forming process of forming a cured product of a formable material on a substrate by bringing the formable material on the substrate into contact with a mold and curing the formable material, comprising: an information processing apparatus for evaluating the forming process; wherein the information processing apparatus includes the information processing apparatus according to claim 1. A forming apparatus characterized by the above.

16. A forming apparatus for performing a forming process of forming a cured product of a formable material on a substrate by bringing the formable material on the substrate into contact with a mold and curing the formable material, and an information processing apparatus for evaluating the forming process; and having The information processing apparatus includes the information processing apparatus according to claim 1, A lithography system characterized by the above.

17. A step of forming a pattern on a substrate using the molding apparatus according to claim 15, A step of processing the substrate on which the pattern is formed in the above step, A step of manufacturing an article from the processed substrate, A method for manufacturing an article, characterized by including the above steps.

18. A program characterized by causing a computer to execute the method according to claim 14.

Images