EVALUATION APPARATUS, PROGRAM, EVALUATION METHOD, MOLDING SYSTEM, AND ARTICLE MANUFACTURING METHOD

Abstract

To provide a technology advantageous for detecting abnormalities in a composition on a substrate obtained by a molding process and confirming the type with high efficiency.SOLUTION: An evaluation device includes an acquisition unit that acquires an image containing a composition formed on a substrate by a molding process, and a processing unit that processes the acquired image for evaluation. The processing unit outputs one or more abnormality features in the acquired image according to an inference model, determines the type of each abnormality on the basis of each output abnormality feature, and makes a final determination as to whether the image is a normal image or an image containing an abnormality on the basis of the determination result.SELECTED DRAWING: Figure 7

Description

[Technical field]

[0001] The present invention relates to an evaluation device, a program, an evaluation method, a molding system, and an article manufacturing method. [Background technology]

[0002] Imprint technology is being put to practical use as a technology that allows the production of microstructure devices according to nanometer-order design rules and is suitable for mass production. Imprint technology is a technology in which a mold (also called a template) having a nanometer-scale uneven structure pattern produced using an electron beam lithography device or exposure device is brought into contact with a moldable material (imprint material) on a substrate to transfer the pattern. One imprint technology is, for example, the photocuring method. An imprint device that employs the photocuring method forms a photocurable imprint material supplied to a shot area on a substrate with a mold, irradiates light to harden the imprint material, and forms a pattern on the substrate by separating the mold from the hardened imprint material. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] JP 2019-080047 A Summary of the Invention [Problem to be solved by the invention]

[0004] When forming a pattern on a substrate using the imprinting technique, seepage may occur, where the imprinting material spills out of the shot area. Conversely, non-filling may occur, where the imprinting material does not spread and a pattern cannot be formed in some areas. When seepage occurs, the area where the imprinting material spills out may become defective, and when a pattern is formed in the shot area beyond the spilled imprinting material, the spilled imprinting material may come into contact with the mold, damaging the pattern on the mold. Furthermore, when non-filling occurs, a pattern is not formed in some areas on the shot area, which may result in a defective semiconductor device.

[0005] Therefore, it is necessary to observe (confirm) the presence or absence of seepage or non-filling after the imprint process and adjust the amount and position of the imprint material supplied onto the substrate to prevent the occurrence of seepage or non-filling. Since the areas where seepage or non-filling occurs are very small, the observation range is narrow and it is necessary to check a huge number of observation images obtained with a high-magnification microscope, but it is not realistic for a person to check such a huge number of observation images. Therefore, there is a demand for a technology that can inspect the observation images for seepage or non-filling without manual intervention and determine pattern abnormalities (formation defects) caused by seepage or non-filling.

[0006] Pattern formation defects have various characteristics such as types and sizes, and since the impact on the process and measures to be taken differ depending on the characteristics of the formation defects, it is necessary to distinguish between these characteristics. In addition, the treatment of formation defects may differ depending on information other than image information, such as the location where the image was taken.

[0007] The present invention provides an advantageous technique for efficiently detecting and confirming the type of anomaly in a composition on a substrate obtained by a molding process. [Means for solving the problem]

[0008] According to one aspect of the present invention, there is provided an evaluation apparatus for evaluating a composition formed on a substrate by a molding process, the molding process comprising: Shot Areaand forming the composition on the substrate by contacting the moldable material with a mold and curing the moldable material. The evaluation device has an acquisition unit that acquires an image including the composition formed on the substrate by the molding process, and a processing unit that processes the acquired image for the evaluation. The processing unit detects the shape of the image in the acquired image. Location and size of the anomaly is output according to the inference model, A relationship between a boundary between a device area and a non-device area in the shot area and the position and the size of the abnormality Based on The above There is provided an evaluation device which judges the type of abnormality and then makes a final judgment as to whether the image is a normal image or an image including an abnormality based on the result of the judgment. Effect of the Invention

[0009] According to the present invention, it is possible to provide an advantageous technique for efficiently detecting and confirming the type of abnormality in a composition on a substrate obtained by a molding process. [Brief description of the drawings]

[0010] [Figure 1] FIG. 1 is a diagram showing the configuration of an imprint apparatus. [Diagram 2] FIG. 2 is a diagram showing the configuration of a wide-area alignment measuring instrument. [Diagram 3] FIG. 1 is a diagram showing a configuration of an article manufacturing system. [Figure 4] 1 is a flowchart of a lithography method using the imprint apparatus. [Diagram 5] FIG. 1 illustrates seepage and underfilling. [Figure 6] FIG. 13 illustrates an image including seepage and non-filling. [Figure 7] 1 is a flow chart of the evaluation method. [Figure 8] Schematic representation of the method carried out during training and testing. [Figure 9] 1 is a flowchart of a method for creating a learning model. [Figure 10] FIG. 1 is a diagram illustrating a classification of seepage. [Figure 11] FIG. 13 is a diagram illustrating classification of unfilled. [Figure 12] FIG. 13 is a diagram illustrating classification of unfilled marks. [Figure 13] FIG. [Figure 14] FIG. 1 is a diagram showing the configuration of an evaluation device. [Figure 15] 1A to 1C are diagrams illustrating a method for manufacturing an article according to an embodiment. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0011] Hereinafter, the embodiments will be described in detail with reference to the attached drawings. Note that the following embodiments do not limit the invention according to the claims. Although the embodiments describe a number of features, not all of these features are essential to the invention, and the features may be combined in any manner. Furthermore, in the attached drawings, the same reference numbers are used for the same or similar configurations, and duplicated descriptions are omitted.

[0012] The following embodiments relate to a molding system including a molding device that performs a molding process to mold a moldable material (curable composition) on a substrate. The molding process includes a contacting step of bringing the moldable material supplied on the substrate into contact with a mold (master plate, template). This contact molds the moldable material. The molding process may further include a curing step of curing the moldable material while the moldable material is in contact with the mold. This forms a composition made of a cured product of the moldable material on the substrate. The molding process may further include a demolding step of separating the composition made of a cured product of the moldable material from the mold.

[0013] The molding device can be used as an imprinting device that transfers a pattern of a mold to an imprinting material, which is a moldable material supplied onto a shot area on a substrate where a pattern is to be formed, by contacting the imprinting material with a pattern portion of a mold. The pattern can be, for example, a semiconductor device pattern (device pattern). In the imprinting device, imprinting can be performed for each of a plurality of shot areas formed on the substrate. Alternatively, the imprinting device can be configured to imprint (i.e., contact) a plurality of shot areas of the substrate collectively (over the entire substrate, or in units of one or more rows of shot areas).

[0014] Alternatively, the molding device can be used as a planarizing device to form a planarized film of moldable material on a substrate by contacting the moldable material on the substrate with a member having a flat surface (the flat surface of a mold).

[0015] In the following, in order to provide a specific example, a system including an imprint apparatus, which is an example of a molding apparatus, will be described.

[0016] 1(a) shows a schematic configuration of an imprint apparatus IMP in an embodiment. The imprint apparatus IMP performs an imprint process in which an imprint material IM on a substrate S is brought into contact with a pattern region MP of a mold M, the imprint material IM is cured, and the cured product of the imprint material IM is separated from the mold M. A pattern made of the cured product of the imprint material IM is formed on the substrate S by this imprint process.

[0017] As the imprint material, a curable composition (sometimes called an uncured resin) that is cured by applying energy for curing is used. As the energy for curing, electromagnetic waves, heat, etc. can be used. The electromagnetic waves can be, for example, light having a wavelength selected from the range of 10 nm to 1 mm, such as infrared rays, visible light, and ultraviolet rays. The curable composition can be a composition that is cured by irradiation with light or by heating. Among these, the photocurable composition that is cured by irradiation with light contains at least a polymerizable compound and a photopolymerization initiator, 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 mold release agent, a surfactant, an antioxidant, and a polymer component. The imprint material can be arranged on the substrate in the form of droplets, or in the form of islands or a film formed by connecting a plurality of droplets. The viscosity of the imprint material (at 25° C.) can be, for example, 1 mPa·s to 100 mPa·s. Examples of the material of the substrate include glass, ceramics, metals, semiconductors, and resins. If necessary, a member made of a material different from that of the substrate may be provided on the surface of the substrate. The substrate may be, for example, a silicon wafer, a compound semiconductor wafer, or quartz glass.

[0018] In this specification and the drawings, directions are indicated in an XYZ coordinate system with the horizontal plane as the XY plane. In general, the substrate S is placed on the substrate holder 102 so that its surface is parallel to the horizontal plane (XY plane). Therefore, in the following, the directions perpendicular to each other in a plane along the surface of the substrate S are referred to as the X-axis and Y-axis, and the direction perpendicular to the X-axis and Y-axis is referred to as the Z-axis. In addition, in the following, the directions parallel to the X-axis, Y-axis, and Z-axis in the XYZ coordinate system are referred to as the X-direction, Y-direction, and Z-direction, respectively. Rotation around the X-axis, rotation around the Y-axis, and rotation around the Z-axis are respectively indicated as θX, θY, and θZ. Positioning means controlling the position and / or orientation. Alignment can include controlling the position and / or orientation of at least one of the substrate and the mold.

[0019] The imprint apparatus IMP may include a substrate holding unit 102 that holds a 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 measurement unit 103 that measures the position of the substrate holding unit 102. The substrate driving mechanism 105 may include, for example, a motor such as a linear motor.

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

[0021] The substrate driving mechanism 105 and the mold driving mechanism 122 constitute a driving mechanism that adjusts the relative position and relative attitude of the substrate S and the mold M. The adjustment of the relative position of the substrate S and the mold M by the driving mechanism includes driving for contacting the mold with the imprint material on the substrate S and separating the mold from the hardened imprint material (pattern of the hardened material). The substrate driving mechanism 105 can be a driving mechanism having multiple degrees of freedom (for example, three axes of X, Y, and θZ, preferably six axes of X, Y, Z, θX, θY, and θZ). The mold driving mechanism 122 can also be a driving mechanism having multiple degrees of freedom (for example, three axes of Z, θX, and θY, preferably six axes of X, Y, Z, θX, θY, and θZ).

[0022] The imprint apparatus IMP may include a mold transport mechanism 140 that transports the mold M, and a mold cleaner 150. The mold transport mechanism 140 may be configured to, for example, transport the mold M to the mold holding unit 121, or transport the mold M from the mold holding unit 121 to an original plate stocker (not shown) or the mold cleaner 150. The mold cleaner 150 cleans the mold M with ultraviolet light, a chemical solution, or the like.

[0023] The mold holding part 121 may include a window member 125 that forms a pressure-controlled space CS on the back surface (the surface opposite to the pattern area MP in which the pattern to be transferred to the substrate S is formed) of the mold M. The imprint apparatus IMP may include a deformation mechanism 123 that controls the pressure in the pressure-controlled space CS (hereinafter referred to as cavity pressure) to deform the pattern area MP of the mold M into a convex shape toward the substrate S, as shown typically in FIG. 1(b).

[0024] The imprint apparatus IMP may include an alignment measurement instrument 106, a wide-angle alignment measurement instrument 151, a curing unit 107, an imaging unit 112, and an optical member 111. The alignment measurement instrument 106 measures the relative position between the alignment marks of the substrate S and the mold M by illuminating the marks and capturing an image of the marks. The alignment measurement instrument 106 may be positioned by a driving mechanism (not shown) according to the position of the alignment mark to be observed. The wide-angle alignment measurement instrument 151 is a measurement instrument having a wider field of view than the alignment measurement instrument 106, and measures the position of the substrate S by illuminating the alignment mark of the substrate S and capturing an image of the marks. By measuring the position of the substrate S with the wide-angle alignment measurement instrument, the alignment mark of the substrate S can be moved within the field of view of the alignment measurement instrument 106.

[0025] The curing unit 107 irradiates the imprint material IM with energy for curing the imprint material IM (for example, light such as ultraviolet light) via the optical member 111, thereby curing the imprint material IM. The imaging unit 112 captures images of the substrate S, the mold M, and the imprint material IM via the optical member 111 and the window member 125.

[0026] The wide-angle alignment measuring instrument 151 may have a mechanism for switching the wavelength of the illumination light. For example, the wide-angle alignment measuring instrument 151 has a wavelength filter arranged on the optical path and has a mechanism for switching the wavelength filter. Alternatively, the wide-angle alignment measuring instrument 151 may have a configuration capable of simultaneously capturing images of multiple wavelengths, as shown in FIG. 2. The measuring instrument in FIG. 2 includes a light source LS, multiple half mirrors 162 branching off from the optical path, multiple wavelength filters 163 each transmitting different wavelengths, and multiple image sensors 164, and can capture images of different wavelengths simultaneously. The wide-angle alignment measuring instrument 151 may also have a mechanism for switching the amount of light of the illumination light. For example, the wide-angle alignment measuring instrument 151 has a mechanism for placing an ND filter on the optical path and switching the ND filter. The wide-angle alignment measuring instrument 151 may also have multiple optical systems, such as a bright-field optical system and a dark-field optical system, and a mechanism for switching the optical system through which the image to be captured passes. The wide-angle alignment measurement instrument 151 may also include a mechanism for switching the polarization of the illumination light or the received light. For example, a polarizing filter may be placed in the optical path, and the wide-angle alignment measurement instrument 151 may also include a mechanism for switching the polarizing filter.

[0027] The imprint apparatus IMP may include a dispenser 108 that disposes the imprint material IM on the substrate S. The dispenser 108, for example, dispenses the imprint material IM so that the imprint material IM is disposed on the substrate S according to a drop recipe that indicates the placement of the imprint material IM. The imprint apparatus IMP may include a control unit 110 that controls the substrate driving mechanism 105, the mold driving mechanism 122, the deformation mechanism 123, the mold transport mechanism 140, the mold cleaner 150, the alignment measuring instrument 106, the curing unit 107, the imaging unit 112, the dispenser 108, and the like. The control unit 110 may be configured, for example, by a PLD (abbreviation for Programmable Logic Device) such as an FPGA (abbreviation for Field Programmable Gate Array), an ASIC (abbreviation for Application Specific Integrated Circuit), a general-purpose computer with a program built in, or a combination of all or part of these.

[0028] 3 illustrates an example of the configuration of an article manufacturing system 401 for manufacturing an article such as a semiconductor device. The article manufacturing system 401 may include, for example, one or more imprint apparatuses IMP and one or more inspection apparatuses 405 (for example, an overlay inspection apparatus, a CD inspection apparatus, a defect inspection apparatus, an electrical property inspection apparatus). The article manufacturing system 401 may also include one or more substrate processing apparatuses 406 (etching apparatus, film formation apparatus). The article manufacturing system 401 may also include an evaluation apparatus 407, which will be described later. These apparatuses may be connected to a control server 403, which is an external apparatus different from the imprint apparatus IMP, via a network 402, and may be controlled by the control server 403.

[0029] The evaluation device 407 is configured by an information processing device, and the information processing device can be 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 with a program embedded therein, or a combination of all or part of these.

[0030] FIG. 14 shows an example of the configuration of the evaluation device 407. The evaluation device 407 may include a control unit 4071, a RAM 4072 that stores temporary data and provides a work area for the control unit 4071, and a ROM 4073 that stores fixed data and programs. The evaluation device 407 may further include a storage device 4072, a display device 4076, and an input device 4075. The storage device 4072 stores a program 4074a for executing the evaluation method according to this embodiment. The network I / F 4077 is an interface for connecting to the network 402. In this embodiment, the network I / F 4077 may function as an acquisition unit that acquires an image including a composition formed on a substrate by a molding process. In addition, the control unit 4071 may function as a processing unit that processes the acquired image for evaluation. In addition, the control unit 4071 may also function as a display control unit that controls the display of the display unit 4076.

[0031] The evaluation apparatus 407 may be realized using (in combination with) the control unit 110 of the imprint apparatus IMP, the control server 403, or the inspection apparatus 405. A system including the imprint apparatus IMP and the evaluation apparatus 407 may be understood as a molding system or a lithography system.

[0032] The lithography method according to this embodiment will be described below. In this embodiment, after performing the imprint process, an image including a shot area, which is an area where a pattern is to be formed, and its surroundings is captured by imaging. This image is used to detect seepage and non-filling. Machine learning is used to detect seepage and non-filling. In machine learning, an abnormality can be detected by using an object detection algorithm.

[0033] A lithography method performed in the imprint apparatus IMP is shown in Fig. 4. The operations shown in Fig. 4 can be controlled by the control unit 110.

[0034] In step S101, a substrate S is transported by a substrate transport mechanism (not shown) from a transport source (for example, an intermediary between a pre-processing device and an imprint device IMP) onto the substrate holding part 102. A wide-angle alignment measuring instrument 151 observes a mark on the substrate S to measure the position of the transported substrate S on the substrate holding part 102. The control part 110 positions the substrate S based on the position obtained by the measurement.

[0035] In steps S102 to S106, an imprint process (formation of a pattern) on a selected shot area from among a plurality of shot areas (imprint areas) on the substrate S is performed.

[0036] In step S102, the imprint material IM is placed on the selected shot area by the dispenser 108. This process can be performed by discharging the imprint material IM from the dispenser 108 while the substrate S is driven by the substrate driving mechanism 105.

[0037] In step S103, the substrate S and the mold M are driven relatively by at least one of the mold driving mechanism 122 and the substrate driving mechanism 105 so that the pattern region MP of the mold M comes into contact with the imprint material IM on the shot region. In one example, the mold M is driven by the mold driving mechanism 122 so that the pattern region MP of the mold M comes into contact with the imprint material IM on the shot region. In the process of bringing the pattern region MP of the mold M into contact with the imprint material IM, the deformation mechanism 123 can deform the pattern region MP of the mold M into a convex shape toward the substrate S. In the process of bringing the pattern region MP of the mold M into contact with the imprint material IM, imaging is performed by the imaging unit 112, and the captured image (spread image) can be accumulated.

[0038] In step S104, alignment may be performed between the shot area of ​​the substrate S and the pattern area MP of the mold M. The alignment may be performed by measuring the relative position between the alignment mark of the shot area and the alignment mark of the mold M by the alignment measurement device 106 so that the relative position falls within a tolerance range of the target relative position. In the alignment, the substrate S and the mold M may be driven relatively by at least one of the mold driving mechanism 122 and the substrate driving mechanism 105. The target relative position between the alignment mark of the shot area and the alignment mark of the mold M may be determined by a correction value determined from past results of an overlay inspection device or the like.

[0039] In step S105, the curing unit 107 irradiates the imprint material IM between the substrate S and the pattern region MP of the mold M with energy for curing the imprint material IM. This cures the imprint material IM, and a cured product of the imprint material IM is formed.

[0040] In step S106, the substrate S and the mold M are driven relatively by at least one of the mold driving mechanism 122 and the substrate driving mechanism 105 so that the cured product of the imprint material IM and the pattern region MP of the mold M are separated. In one example, the mold M is driven by the mold driving mechanism 122 so that the cured product of the imprint material IM and the pattern region MP of the mold M are separated. When the cured product of the imprint material IM and the pattern region MP of the mold M are separated, the pattern region MP of the mold M can also be deformed into a convex shape toward the substrate S. Furthermore, imaging is performed by the imaging unit 112, and the state of separation between the imprint material IM and the mold M is observed based on the captured image.

[0041] In step S107, the control unit 110 determines whether the imprint processing of steps S102 to S106 has been performed on all shot areas of the substrate S. If the imprint processing of steps S102 to S106 has been performed on all shot areas of the substrate S, the control unit 110 proceeds to step S108, and if there are any unprocessed shot areas, the control unit 110 returns to step S102. In this case, the imprint processing of steps S102 to S106 is performed on a shot area selected from the unprocessed shot areas.

[0042] In step S108, an image including the shot area after imprinting is acquired. For example, the control unit 110 uses the wide-angle alignment measuring instrument 151 to capture an image of the shot area and its periphery. When the field of view of the wide-angle alignment measuring instrument 151 is narrow with respect to the shot area, the substrate driving mechanism 105 may be driven to change the position of the substrate S, and multiple images may be captured to capture a desired area. The image captured in step S108 may be used as a learning image to be described later. The image captured in step S108 may also be used as an image for detecting anomalies. Here, an example of capturing an image using the wide-angle alignment measuring instrument 151 will be described, but the present invention is not limited to this. For example, the image may be captured using the alignment measuring instrument 106 or the imaging unit 112.

[0043] In the above procedure, step S108 is executed after the imprint process is performed on all of the multiple shot areas, but this is not limited to the above. For example, after a pattern is formed in each shot area (after step S106), an image of the pattern after imprinting may be captured for each shot area. As will be described later, an image of the pattern may be captured by an apparatus other than the imprint apparatus in a manner similar to step S108 on a substrate carried out from the imprint apparatus.

[0044] In step S109, the substrate S is transported from the substrate holding unit 102 to a destination (e.g., an intermediary unit to a post-processing device) by a substrate transport mechanism (not shown). When a lot consisting of a plurality of substrates is processed, the operation shown in FIG. 4 is performed for each of the plurality of substrates.

[0045] Next, abnormalities in the imprint result will be described. Fig. 5 is a side view of a state in which the mold M and the imprint material IM on the substrate S are in contact (after completion of step S103, for example, in steps S104 and S105). "Seeping out" refers to a state in which the imprint material IM protrudes from the contact area between the mold M and the imprint material IM, as shown in Fig. 5(a). "Unfilled" refers to a state in which there are portions between the mold M and the substrate S that are not filled with the imprint material IM, as shown in Fig. 5(b).

[0046] 6 shows an example of an image captured in step S108 when seepage and underfilling have occurred. FIG. 6 shows an image of a state in which a pattern of the imprint material IM has been formed in the shot area by the imprint process. Normally, as shown in FIG. 6(a), the imprint material IM is filled up to the boundary 601 of the shot area to form a pattern. On the other hand, in the case of underfilling, as shown in FIG. 6(b), the imprint material IM does not reach the boundary 601 of the shot area, and the unfilled part is imaged as white (or black). Also, in the case of seepage, as shown in FIG. 6(c), the imprint material IM protrudes from the boundary 601 of the shot area and goes beyond the boundary 601, and is imaged as black (or white).

[0047] Next, an image evaluation method executed by the evaluation device 407 will be described with reference to the flowchart of Fig. 7. The evaluation method detects an abnormality (pattern formation failure) contained in the image acquired in step S108, and determines the type of the abnormality (seepage / non-filling). A program for the evaluation method corresponding to the flowchart of Fig. 7 is stored in, for example, the storage device 4074, and is executed by the control unit 4071 (processing unit) after being loaded into the RAM 4072.

[0048] In step S201, the control unit 4071 reads an inference model for inspection (learning model, hereinafter also simply referred to as "model") that outputs one or more abnormal features in an image. The inference model is a model created in advance from an image acquired under the conditions of the material (imprint material) to be inspected and the conditions that are the same as or similar to the measurement conditions of the image acquired in S108. The procedure for creating the inference model will be described later. In step S202, the control unit 4071 reads the image acquired in step S108.

[0049] In step S203, the control unit 4071 provides the image acquired in step S202 as an input to the inference model acquired in step S201, and obtains one or more abnormality features on the image as an output. The abnormality features are obtained for each abnormality on the image. The obtained abnormality features may include at least one of the position of the abnormality in the image, the type of the abnormality, the coordinates of the vertices of the rectangle surrounding the abnormality, and the certainty of the detected abnormality. Here, the certainty of the detected abnormality is a value representing the likelihood and / or reliability of the detection of the abnormality, and is automatically calculated by the model for each detected abnormality. The types of abnormalities that can be detected may include seepage that has hardened beyond the shot area, and unfilled, which is an area in the shot area that has not been completely filled with the imprint material. Other abnormalities can also be detected by having the model learn.

[0050] In step S204, the control unit 4071 reads device information (pattern information) on the image given as input in step S203. The device information may include information such as the boundary position between the shot area to be inspected and the adjacent shot area in the image, and the boundary position between the device area and the non-device area in the shot area. These can be found from the coordinates with the center of the shot area as the origin when the input image was captured, and the design information of the mold used in the imprint process.

[0051] In step S205, the control unit 4071 judges the type of the anomaly (classifies the anomaly) based on the features of the anomaly output from the model obtained in step S203. In step S203, the type of anomaly is detected using only image information, but in step S205, whether the anomaly is normal or abnormal is judged comprehensively based on the position and size of the anomaly. Also, in step S205, even if the anomaly looks the same on the image, it is handled differently depending on the position of the anomaly on the substrate S. For this reason, in step S205, the anomaly detected in S203 is further classified. At this time, the information read in step S204 may be used. In step S205, classification is performed based on the size of the anomaly, or using the pattern information read in step S204 and the position of the anomaly.

[0052] The method of classifying anomalies performed in step S205 will be described below.

[0053] First, referring to FIG. 10, an example of classification of seepage will be described. Classification (determination) can be performed based on the relationship between the boundary of the shot area and the position and size of the anomaly. FIGS. 10(a), (b), and (c) show examples of images IMG of the shot area, respectively. The gray areas in each image are areas filled with the imprint material IM. Area D is the seepage area output by the model as an anomaly in step S203. The seepage area D varies. It may appear as a black dot, or it may appear differently depending on the measurement conditions of the image and the characteristics of the material. The shot boundary 1001 is the boundary between the shot area to be inspected and the adjacent shot area, and its position is defined from the information read in step S204. The category of the anomaly can be further categorized from this information. In the case of FIG. 10(a), the seepage area D exists on the shot area side to be inspected and does not exceed the shot boundary 1001. The seepage in this case can be classified as a small seepage. In the case of FIG. 10(b), seepage area D exists on the side of the shot area adjacent to the shot area to be inspected. Since this seepage is from an adjacent shot area, it can be classified as an anomaly that is not to be detected. In the case of FIG. 10(c), seepage area D exists on the side of the shot area to be inspected and exceeds the shot boundary 1001. This type of seepage can be classified as a large seepage.

[0054] Next, a method for making the judgment shown in FIG. 10 will be described. The position, size, and type of the abnormality detected by the model, and the position of the shot boundary are used during the judgment. The control unit 4071 obtains the coordinates of the abnormality in the region D output by the model, and uses these as the position and size of the abnormality. The type of the abnormality may also be obtained as an output of the model. The information of the shot boundary 1001 may be obtained from a predefined value, or may be obtained by calculation from design information of the mold. The information of the shot boundary 1001 may be expressed as a group of coordinates of pixels at the position that is the boundary in the image. In the case of FIG. 10, the coordinates of the pixel group on the line of the shot boundary 1001 and the coordinates in the region D are used as information for judging the position and size of the abnormality (seepage).

[0055] In FIG. 10(a), all of the coordinates in the abnormality region D output by the model do not exceed the coordinates of the shot boundary 1001, i.e., they are coordinates within the shot region to be inspected, so it is determined that the abnormality is small. In FIG. 10(b), all of the coordinates in the abnormality region D output by the model exceed the coordinates of the shot boundary 1001, i.e., they are coordinates included in the adjacent shot region, so it is determined that the abnormality is in the adjacent shot region. In FIG. 10(c), some of the coordinates in the abnormality region D output by the model exceed the coordinates of the shot boundary 1001, i.e., part of the region D is included in the adjacent shot region, so it can be determined that the extrusion is large. At this time, a threshold value is set in advance for the size of the extrusion, and the abnormality can be classified from the vertical or horizontal length calculated from the coordinates in the region D.

[0056] An example of classification of unfilled areas will be described with reference to FIG. 11. Classification (determination) can be performed based on the relationship between the device boundary, which indicates the boundary between the device area and the non-device area in the shot area, and the position and size of the anomaly. In each of FIGS. 11(a) and (b), an image IMG of the shot area is shown. The areas shown in gray in each image are areas filled with the imprint material IM. The white area N is an unfilled area output by the model as an anomaly in step S203. The device boundary 1101 is the boundary between the device area and the non-device area in the shot area. Since the device boundary 1101 cannot be determined only from the image information, it is defined from the information read in step S204. The category of anomalies can be further categorized from these pieces of information. In the case of FIG. 11(a), the unfilled area N is in the non-device area beyond the device boundary 1101, so the area N can be classified as unfilled in the non-device area. 11(b), the unfilled region N exists within the device region without crossing the device boundary 110, so the region N can be classified as an unfilled region within the device region. The classification criteria and categories listed above are merely examples, and different classifications can be made by combining with other design information and conditions.

[0057] Next, a method for making the judgment shown in FIG. 11 will be described. When making the judgment, the position, size, type, shot boundary, and device boundary positions detected by the model are used. The control unit 4071 obtains the coordinates of the abnormality in the region N output by the model, and uses these as the position and size of the abnormality. The type of abnormality is also obtained as an output of the model. The information on the device boundary 1101 can be obtained from a predefined value, or may be obtained by calculation from the design information of the mold. The information on the device boundary 1101 is expressed by a group of coordinates of pixels at the position that becomes the boundary in the image. In the case of FIG. 11, the coordinates of the pixel group on the line of the device boundary 1101 and the coordinates in the region N are used as information for judging the position and size of the abnormality (unfilled).

[0058] In Fig. 11(a), all of the coordinates in the abnormal region N output by the model exceed the coordinates of the device boundary 1101, i.e., they are on the non-device region side, so they are determined to be unfilled outside the device region. In Fig. 11(b), all of the coordinates in the abnormal region N output by the model do not exceed the coordinates of the device boundary 1101, i.e., they are on the device region side, so they can be classified as unfilled on the device region.

[0059] With reference to FIG. 12, an example of classification of unfilled marks will be described. Classification (determination) can be performed based on the relationship between the position of the mark included in the shot area and the position and size of the abnormality. FIGS. 12(a) and 12(b) each show an image IMG of the shot area. The area shown in gray in each image is an area filled with the imprint material IM. The shot area includes a first mark 1201 and a second mark 1202, which are different in shape from each other. In FIG. 12(a), the first mark 1201 and the second mark 1202 are shown in black, which is a normal state in which the imprint material IM is filled inside the mark. On the other hand, in FIG. 12(b), the first marks 1201 and 1202 are partially shown in white, which is a state in which the imprint material IM is not sufficiently filled inside the mark (unfilled). The area shown in white is the unfilled N that the model outputs as an abnormality in step S203.

[0060] In FIG. 12(b), 1205 and 1206 indicate design information for each mark, which is one of the pieces of pattern information on the image read in S104. The design information for each mark 1205 and 1206 each include information on the position and type of the mark. In step S205, by combining the information on the presence or absence of unfilled N obtained in step S203 with the information on the position and type of the mark obtained in step S204, it is possible to classify in which type of mark the unfilled N occurs. The classification conditions and categories listed above are examples, and can be changed depending on conditions such as the material and design information of the inspection target, and device data such as the light control conditions and mode at the time of imaging.

[0061] Next, a method for making the judgment shown in FIG. 12 will be described. The position, size, and type of the abnormality detected by the model, and the position of the mark on the image are used during the judgment. The control unit 4071 obtains the coordinates of the abnormality in the region N output by the model, and uses these as the position and size of the abnormality. The type of the abnormality is also obtained as an output of the model. Information on the type and position of the mark present on the image can be obtained from predefined values, or may be obtained by calculation from the design information of the mold. The design information 1205 and 1206 are actually expressed as a combination of the coordinates in the region N and the type of the mark. In the case of FIG. 12, when the model detects an unfilled portion in the first mark 1203 and the second mark 1202, the coordinates of the region surrounding the unfilled portion are obtained. By comparing the coordinates obtained here with the coordinates of the region of the mark, it is possible to determine whether the detected abnormality exists within the region of the mark.

[0062] In addition, the detected anomalies can be classified based on a comparison between the certainty and a predetermined threshold. For example, when the certainty is expressed as a value between 0 and 1, if the certainty of the detected anomaly is lower than a predetermined threshold (e.g., threshold = 0.5), the anomaly may be excluded from the final judgment. The classification conditions such as the threshold when classifying based on the certainty can be changed depending on conditions such as the material and design information of the inspection target, and device data such as the dimming conditions and the mode when capturing images.

[0063] The explanation will return to the flowchart of Fig. 7. In step S206, the control unit 4071 determines whether classification has been completed for all abnormalities on the image. If classification has not been completed for all abnormalities on the image, the process returns to step S205, and classification is performed for the next abnormality. If classification has been completed for all abnormalities on the image, the process proceeds to step S207.

[0064] In step S207, the control unit 4071 performs a final judgment on the image. For example, the control device 4701 determines a final judgment value indicating whether the image is normal or abnormal based on the conditions and purpose of the material to be inspected, and the classification results of each abnormality in the image in step S205. For example, when a final judgment is made that an image is abnormal when it contains a large abnormality, the images in Figs. 10(a) and (b) are finally judged to be normal because the abnormal region D does not exist beyond (across) the shot boundary 1001 from the shot area side. Also, the image in Fig. 10(c) can be finally judged to be abnormal because the abnormal region D exists beyond (across) the shot boundary 1001 from the shot area side. At this time, the size of the abnormal region can be distinguished by a method of distinguishing the size of the abnormal region in the image by the number of pixels. Alternatively, when a final judgment is made that an image is abnormal when there is an unfilled area on the device area, the final judgment of abnormality can be made by comparing the position of the device area with the position of the abnormality. In this case, for example, the image in FIG. 11(a) is finally determined to be a normal image because there is no abnormal region N in the device region. Also, the image in FIG. 11(b) is finally determined to be an abnormal image because there is an abnormal region N in the device region. When there are multiple abnormalities in an image, the image may be classified as normal / abnormal based on a single abnormality based on a pre-set condition. Alternatively, when there are multiple abnormalities in an image, a judgment for the image may be determined for each type of abnormality. When determining a final judgment value for an image, the final judgment value may be determined based on the height, type, certainty, etc. of various abnormalities present in the image. The criteria for judgment based on various classification results are not limited to the above examples.

[0065] Next, the parameters for judgment that can be set by the user will be described. For example, the user can set the size of seepage and the reliability threshold for judging an abnormality as parameters for an abnormality judgment. FIG. 13 is an example of a user interface (UI) screen DISP (setting section) displayed on the display device 4076. The image IMG of the inspection target and the judgment result 1303 for that image are displayed at the top of the screen. The user can switch the image of the inspection target by performing an operation such as pressing or tapping the forward button BTN via the input device 4075, which is a user interface. If there is no image of the inspection target, these are not displayed.

[0066] The user can set the value of the seepage size to be determined as an anomaly by inputting a value into the text box 1302 or by moving the slider 1301 using the input device 4075. The user can also set a predetermined threshold value for the confidence level to be determined as an anomaly by inputting a value into the text box 1304 or by moving the slider 1305 using the input device 4075. At this time, the positions of the sliders 1301 and 1305 and the values ​​displayed in the text boxes 1302 and 1304 can change in conjunction with each other. When the determination result 1303 is displayed, if the user changes any of these parameters, the determination result 1303 can change according to the changed parameters. Thus, according to this embodiment, a setting unit and a display unit are provided as a user interface, and the user can input a desired value into the setting unit, and the image and the result of the final determination are displayed on the display unit. Therefore, the user can set the parameters while checking the determination result. The user can set these parameters in advance using this UI before performing an anomaly inspection. The user can apply the currently set parameters to the image data of the inspection target by pressing or tapping the apply button 1306.

[0067] Next, a method for calculating (learning) an inference model (learning model) for anomaly detection by the evaluation device 407 will be described with reference to Figs. 8 and 9. Fig. 8 is a schematic diagram of a method executed during learning and inspection, and Fig. 9 is a flowchart of learning for anomaly detection. The evaluation device 407 may include a machine learning unit that generates an inference model by machine learning. The machine learning unit uses an image containing a composition formed on a substrate by a molding process as input for the inference model, and performs machine learning using the relationship between a plurality of images obtained in advance and characteristic information on anomalies in each of the plurality of images as training data. A specific description will be given below.

[0068] In step S301, the control unit 4071 acquires (for example, by capturing) a learning image 801 in the same manner as in step S108. Specifically, the control unit 4071 collects an image 801 similar to an image during inspection based on the conditions of the material used when capturing the image during inspection and the measurement conditions. In addition, the control unit 4071 uses multiple substrates to collect learning images 801 in multiple shot regions therein. It is desirable to use as many images as possible for learning, and it is assumed that a sufficient amount of samples of the abnormality to be detected are included.

[0069] In step S302, feature information of anomalies corresponding to each image acquired in step S301 is created. Specifically, each acquired image is visually inspected, and feature information 802 including information on the category, size, position, etc. of anomalies is created for all anomalies present in each image.

[0070] In step S303, the control unit 4071 performs model learning based on the image acquired in step S301 and the anomaly characteristic information created in step S302. Optimization is performed by using the image 801 as input data for a neural network created in advance and the anomaly characteristic information 802 as output (teacher). As a result, a learning model (neural network) 803 is created.

[0071] In step S404, the control unit 4071 stores the created learning model 803 in the memory unit 804.

[0072] According to the embodiment described above, it is possible to automate the detection of abnormalities in a shot area, and to classify the abnormalities in more detail.

[0073] <Embodiment of the article manufacturing method> The article manufacturing method according to the embodiment of the present invention is suitable for manufacturing articles such as microdevices such as semiconductor devices and elements having a microstructure. The article manufacturing method of the present embodiment may include a step of forming a layer of a composition on a substrate by a molding device in a molding system, and a step of processing the substrate on which the layer is formed. Furthermore, such a manufacturing method may include other well-known steps (oxidation, film formation, deposition, doping, planarization, etching, resist stripping, dicing, bonding, packaging, etc.). The article manufacturing method of the present embodiment is advantageous in at least one of the performance, quality, productivity, and production cost of the article compared to conventional methods.

[0074] The pattern of the cured product formed by using the imprinting apparatus is used permanently on 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, and 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 molds include molds for imprinting.

[0075] The pattern of the cured product is used as it is as at least a part of a component of the article, or is used temporarily as a resist mask, which is removed after etching or ion implantation in a substrate processing step.

[0076] Next, a method for manufacturing an article will be described. In step SA of Fig. 15, a substrate 1z such as a silicon substrate having a workpiece 2z such as an insulator formed on its surface is prepared, and then an imprint material 3z is applied to the surface of the workpiece 2z by an inkjet method or the like. Here, a state in which the imprint material 3z in the form of multiple droplets is applied onto the substrate is shown.

[0077] In step SB in Fig. 15, the mold 4z for imprinting is placed facing the imprint material 3z on the substrate with the side on which the concave-convex pattern is formed. In step SC in Fig. 15, the substrate 1z to which the imprint material 3z has been applied is brought into contact with the mold 4z, and pressure is applied. The imprint material 3z fills the gap between the mold 4z and the workpiece 2z. When light is irradiated through the mold 4z in this state as energy for curing, the imprint material 3z is cured.

[0078] 15, after the imprint material 3z is cured, the mold 4z and the substrate 1z are separated, and a pattern of the cured product of the imprint material 3z is formed on the substrate 1z. In this cured product pattern, the recesses of the mold correspond to the protrusions of the cured product, and the protrusions of the mold correspond to the recesses of the cured product, i.e., the recessed and protruding patterns of the mold 4z are transferred to the imprint material 3z.

[0079] In step SE of Fig. 15, etching is performed using the pattern of the cured material as an etching-resistant mask, and the portions of the surface of the workpiece 2z where there is no cured material or where only a thin layer remains are removed to form grooves 5z. In step SF of Fig. 15, the pattern of the cured material is removed to obtain an article in which grooves 5z are formed on the surface of the workpiece 2z. Here, the pattern of the cured material is removed, but it may be used as an interlayer insulating film included in a semiconductor element or the like, that is, a component of an article, without being removed after processing.

[0080] (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.

[0081] The invention is not limited to the above-described embodiments, and various modifications and variations are possible without departing from the spirit and scope of the invention. Accordingly, the following claims are appended to apprise the public of the scope of the invention. [Explanation of symbols]

[0082] IMP: imprint device, S: substrate, M: mold, 110: control unit, 102: substrate holder, 105: substrate drive mechanism, 121: mold holder, 122: mold drive mechanism, 407: evaluation device

Claims

1. An evaluation device for evaluating a composition formed on a substrate by a molding process, the molding process being a process for forming the composition on the substrate, the composition being a cured product of the moldable material, by curing the moldable material on a shot region of the substrate while the mold is in contact with the mold, the evaluation device comprising: an acquisition unit that acquires an image including the composition formed on the substrate by the molding process; a processing unit for processing the acquired image for the evaluation; The processing unit includes: outputting the location and size of the anomaly in the acquired image according to an inference model; determining a type of the abnormality based on a relationship between a boundary between a device area and a non-device area in the shot area and the position and the size of the abnormality; and making a final determination as to whether the image is a normal image or an image including an abnormality based on the result of the determination. An evaluation device comprising:

2. The evaluation device according to claim 1 , further comprising a machine learning unit that generates the inference model through machine learning.

3. The evaluation device described in claim 2, characterized in that the machine learning unit uses an image containing the composition formed on the substrate by the molding process as an input to the inference model, and performs machine learning using the relationship between a plurality of previously obtained images and characteristic information of abnormalities in each of the plurality of images as training data.

4. The evaluation device according to any one of claims 1 to 3, characterized in that the inference model calculates a certainty factor representing the likelihood and / or reliability of anomaly detection.

5. The evaluation device of claim 4 , wherein the inference model outputs information on the type of the anomaly in addition to the position, size, and confidence level of the anomaly in the image.

6. the molding process is an imprint process in which an imprint material, which is the moldable material supplied onto a shot area on a substrate where a pattern is to be formed, is brought into contact with a pattern portion of the mold, thereby transferring a pattern of the mold to the imprint material; the determination is made based on a relationship between a boundary of the shot area and the position and the size of the anomaly.

6. The evaluation device according to claim 5.

7. the molding process is an imprint process in which an imprint material, which is the moldable material supplied onto a shot area on a substrate where a pattern is to be formed, is brought into contact with a pattern portion of the mold, thereby transferring a pattern of the mold to the imprint material; the determination is made based on a relationship between a position of a mark included in the shot area and the position and size of the abnormality.

6. The evaluation device according to claim 5.

8. the type of abnormality includes overflow of the imprint material; When the portion of the abnormality determined to be the protrusion is present beyond the boundary of the shot area, the final determination is made to determine that the image is an image including an abnormality.

7. The evaluation device according to claim 6.

9. the type of abnormality includes an underfill of the moldable material; When the anomaly determined to be the non-filling among the anomalies exists within the device region, the final determination is made by determining that the image is an image including an anomaly.

2. The evaluation device according to claim 1 .

10. 9. The evaluation device according to claim 5, wherein the processing unit excludes the abnormality from the targets of the final determination when the certainty factor is lower than a predetermined threshold value.

11. 11. The evaluation device according to claim 10, further comprising a setting unit that sets the size and the predetermined threshold value in accordance with values ​​input via a user interface.

12. 12. The evaluation device according to claim 1, further comprising a control unit that causes the image and the result of the final judgment to be displayed on a display unit.

13. An evaluation device for evaluating a composition formed on a substrate by a molding process, the molding process being a process for forming the composition on the substrate, the composition being a hardened product of the moldable material, by hardening the moldable material on a shot region of the substrate while the mold is in contact with the mold, the evaluation device comprising: an acquisition unit that acquires an image including the composition formed on the substrate by the molding process; a processing unit for processing the acquired image for the evaluation; The processing unit includes: outputting the location and size of the anomaly in the acquired image according to an inference model; determining a type of the abnormality based on a relationship between a position of a mark included in the shot area and the position and size of the abnormality; and making a final determination as to whether the image is a normal image or an image including an abnormality based on the result of the determination. An evaluation device comprising:

14. A program for causing a computer to function as each unit of the evaluation device according to any one of claims 1 to 13.

15. A method for evaluating a composition formed on a substrate by a molding process, the molding process being a process for forming the composition on the substrate, the composition being a cured product of the moldable material, by curing the moldable material on a shot region of the substrate while the mold is in contact with the mold, the method comprising: obtaining an image including the composition formed on the substrate by the molding process; outputting a location and a size of the anomaly in the acquired image according to an inference model; determining a type of the abnormality based on a relationship between a boundary between a device area and a non-device area in the shot area and the position and size of the abnormality; making a final judgment as to whether the image is a normal image or an image including an abnormality based on a result of the judgment; The evaluation method according to claim 1,

16. a molding apparatus for performing a molding process in which a moldable material on a substrate is contacted with a mold and the moldable material is cured to form a composition on the substrate, the composition comprising a cured product of the moldable material; An evaluation device according to any one of claims 1 to 13; A molding system comprising:

17. forming a layer of the composition on a substrate with the molding device of claim 16; treating the substrate on which the layer is formed; and manufacturing an article from the processed substrate.

Images