Shape characteristic value calculation device, shape characteristic value calculation method and storage medium

Abstract

The present invention relates to a shape characteristic value estimation device, a shape characteristic value estimation method and a storage medium. The shape characteristic value estimation device includes: a processed image acquisition unit that acquires a processed image, the processed image includes image information of the surface of a substrate on which a target film is formed; an estimation unit that estimates the shape characteristic value by applying an estimation model for estimating the shape characteristic value of the target film to the processed image, the estimation model involving the correlation between the information of the color of the substrate surface in the processed image and the shape characteristic value of the target film; a base influence model generation unit that generates a base influence model, the base influence model involving the correlation between the estimation result of the shape characteristic value of the target film and the difference of the shape characteristic value obtained without using the estimation model and the color information of the base substrate surface; and an estimation result correction unit that corrects the estimation result based on the base influence model. The present invention can estimate the characteristic value of the shape of the film formed on the target substrate with higher accuracy.

Description

Technical Field

[0001] The present invention relates to a shape characteristic value estimating device, a shape characteristic value estimating method and a storage medium. Background Art

[0002] Patent document 1 discloses a technique for calculating the film thickness of a film formed on a substrate based on an image obtained by photographing the substrate surface. In this case, the technique discloses a technique for using correlation data obtained by correlating pixel values ​​obtained from an image to be photographed with film thickness measurement values ​​at each coordinate corresponding to the pixel values.

[0003] Prior art literature

[0004] Patent Literature

[0005] Patent Document 1: Japanese Patent Application Publication No. 2015-215193 Summary of the invention

[0006] Technical problem to be solved by the invention

[0007] The present invention provides a technology capable of estimating a characteristic value related to the shape of a target film formed on a substrate with high accuracy.

[0008] Technical solutions for solving technical problems

[0009] A shape characteristic value estimation device according to one aspect of the present invention includes: a processed image acquisition unit that acquires a processed image, wherein the processed image includes image information related to a surface of a substrate on which a target film is formed; an estimation unit that estimates the shape characteristic value of the target film by applying an estimation model for estimating the shape characteristic value of the target film to the processed image, wherein the estimation model involves a correlation between information on the color of the surface of the substrate contained in the processed image and the shape characteristic value, wherein the shape characteristic value is a characteristic value related to the shape of the target film formed on the substrate; a base influence model generation unit that generates a base influence model, wherein the base influence model is a model involving a correlation between a difference between an estimation result of the shape characteristic value of the target film obtained by the estimation unit and the shape characteristic value of the target film obtained without using the estimation model, and information on the color of the surface of a base substrate, wherein the base substrate is a substrate before the target film is formed; and an estimation result correction unit that corrects the estimation result of the shape characteristic value of the target film obtained by the estimation unit based on the base influence model.

[0010] Effects of the Invention

[0011] According to the present invention, a technique is provided that can accurately estimate a characteristic value related to the shape of a target film formed on a substrate. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] Figure 1 FIG. 1 is a schematic diagram showing an example of a schematic configuration of a substrate processing system.

[0013] Figure 2 It is a schematic diagram showing an example of a coating and developing device.

[0014] Figure 3 : is a schematic diagram showing an example of an inspection unit.

[0015] Figure 4 This is a block diagram showing an example of the functional structure of the control device.

[0016] Figure 5 This is a diagram schematically showing changes in information related to color acquired from image data obtained by imaging a plurality of wafers.

[0017] Figure 6 This is a block diagram showing an example of the hardware configuration of the control device.

[0018] Figure 7 This is a flowchart showing an example of a film thickness estimation method.

[0019] Figure 8 This is a flowchart showing an example of a film thickness estimation method.

[0020] Fig. 9 This is a schematic diagram for explaining an example of the deviation of the estimation result of the film thickness estimation model.

[0021] Fig.10 is a schematic diagram illustrating an example of a substrate influence model.

[0022] Fig.11 It is a schematic diagram explaining an example of the state of the wafer after the patterning process.

[0023] Fig.12 This is a schematic diagram for explaining an example of a method of generating a shape characteristic value estimation model.

[0024] Fig.13 is a schematic diagram illustrating an example of a method for generating a substrate influence model.

[0025] Description of Reference Numerals

[0026] 1...substrate processing system; 2...coating and developing device (shape characteristic value estimation device); 3...exposure device; 4...carrier block; 5...processing block; 6...interface block; 11-14...processing module; 30...housing; 31...holding unit; 32...linear driving unit; 33...shooting unit; 34...reflecting unit; 35...camera; 36...semi-reflecting mirror; 37...light source; 100...control device; 101...base image acquisition unit; 102...processed image acquisition unit; 103...image information storage unit; 104...estimation unit; 105...estimation model storage unit; 106...shape characteristic value information storage unit; 107...base influence model generation unit; 108...estimation result correction unit. DETAILED DESCRIPTION

[0027] Various exemplary embodiments are described below.

[0028] A shape characteristic value estimation device according to one aspect of the present invention includes: a processed image acquisition unit that acquires a processed image, wherein the processed image includes image information related to the surface of a substrate on which a target film is formed; an estimation unit that estimates the shape characteristic value of the target film by applying an estimation model for estimating the shape characteristic value of the target film to the processed image, wherein the estimation model involves a correlation between information on the color of the surface of the substrate contained in the processed image and the shape characteristic value, wherein the shape characteristic value is a characteristic value related to the shape of the target film formed on the substrate; a base influence model generation unit that generates a base influence model, wherein the base influence model is a model involving a correlation between a difference between an estimation result of the shape characteristic value of the target film obtained by the estimation unit and the shape characteristic value of the target film obtained without using the estimation model, and information on the color of the surface of a base substrate, wherein the base substrate is a substrate before the target film is formed; and an estimation result correction unit that corrects the estimation result of the shape characteristic value of the target film obtained by the estimation unit based on the base influence model.

[0029] According to the above-mentioned shape characteristic value estimation device, first, the shape characteristic value of the object film is estimated using the estimation model. Then, a base influence model is generated, which is a model of the correlation between the estimation result of the shape characteristic value of the object film and the difference between the shape characteristic value of the object film obtained without using the estimation model and the information of the color of the surface of the base substrate before the object film is formed. Then, based on the base influence model, the estimation result is corrected. With such a configuration, the variable component of the estimation result caused by the color of the base substrate, etc. can be corrected based on the base influence model. Therefore, the shape characteristic value related to the shape of the object film formed on the substrate can be estimated with high accuracy.

[0030] The shape characteristic value of the target film obtained without using the estimation model may be a measured value of the shape characteristic value of the substrate on which the target film is formed.

[0031] By using the shape characteristic values ​​of the target film used in generating the base influence model as the measured values ​​of the shape characteristic values ​​of the substrate on which the target film is formed, the base influence model can be generated with higher accuracy, thereby enabling the shape characteristic values ​​of the target film formed on the substrate to be estimated with high accuracy.

[0032] The estimation model may be a model generated based on information related to the color of the surface of the base substrate.

[0033] In the case where the estimation model is also generated based on information related to the color of the surface of the base substrate, the estimation result of the shape characteristic value obtained by the estimation model also takes into account the influence of the color of the base substrate to a certain extent, so the accuracy is very good. On this basis, by further performing correction using the base influence model, the variation component of the estimation result caused by the color of the base substrate, etc. that cannot be fully captured in the estimation model can be further corrected, so the accuracy of the estimation result can be further improved.

[0034] It may be possible to further include a base image acquisition unit, which acquires a base image related to image information of the surface of the above-mentioned base substrate, and the above-mentioned base influence model generation unit generates the above-mentioned base influence model using information related to the color of the surface of the above-mentioned base substrate contained in the above-mentioned base image.

[0035] The invention also includes a base image acquisition unit. When the base influence model is generated by using information related to the surface of the base substrate contained in the base image obtained by the base image acquisition unit, information related to the surface of the base substrate of a larger area contained in the base image can be used. Therefore, the base influence model can be generated with higher accuracy.

[0036] The base influence model generating unit may generate the base influence model using information related to the color of the surface of the base substrate included in the processed image.

[0037] When the base influence model is generated using information related to the color of the surface of the base substrate contained in the processed image, the base influence model can be generated even without separately providing a structure for acquiring information related to the color of the surface of the base substrate. Therefore, the base influence model can be generated with a simpler device structure.

[0038] In an exemplary embodiment, a shape characteristic value estimation method estimates a shape characteristic value, wherein the shape characteristic value is a characteristic value related to the shape of an object film formed on a substrate, and the shape characteristic value estimation method includes: a step of acquiring a processed image, wherein the processed image includes image information related to the surface of a substrate on which the object film is formed; a step of estimating the shape characteristic value of the object film by applying an estimation model for estimating the shape characteristic value of the object film to the processed image, wherein the estimation model involves a correlation between information on the color of the surface of the substrate contained in the processed image and the shape characteristic value of the object film formed on the substrate; a step of generating a base influence model, wherein the base influence model is a model involving a correlation between a difference between an estimation result of the shape characteristic value of the object film and the shape characteristic value of the object film obtained without using the estimation model and information on the color of the surface of a base substrate, wherein the base substrate is a substrate before the object film is formed; and a step of correcting the estimation result of the shape characteristic value of the object film based on the base influence model.

[0039] According to the above-mentioned shape characteristic value estimation method, first, the shape characteristic value of the object film is estimated using the estimation model. Then, a base influence model is generated, which is a model of the correlation between the estimation result of the shape characteristic value of the object film and the difference between the shape characteristic value of the object film obtained without using the estimation model and the information of the color of the surface of the base substrate before the object film is formed. Then, based on the base influence model, the estimation result is corrected. With such a configuration, the variable component of the estimation result caused by the color of the base substrate, etc. can be corrected based on the base influence model. Therefore, the shape characteristic value related to the shape of the object film formed on the substrate can be estimated with high accuracy.

[0040] In an exemplary embodiment, the storage medium is a computer-readable storage medium storing a program for causing a device to execute the above-described shape characteristic value estimation method.

[0041] Hereinafter, various exemplary embodiments will be described in detail with reference to the accompanying drawings. In addition, in each of the drawings, the same or corresponding parts are denoted by the same reference numerals.

[0042] [Substrate processing system]

[0043] The substrate processing system 1 is a system for forming a photosensitive coating on a substrate, exposing the photosensitive coating, and developing the photosensitive coating. The substrate to be processed is, for example, a semiconductor wafer W.

[0044] The substrate processing system 1 includes a coating and developing device 2 and an exposure device 3. The exposure device 3 performs an exposure process of a resist film (photosensitive coating) coated on a wafer W (substrate). Specifically, the exposure device 3 irradiates an energy line to an exposure target portion of the resist film by a method such as liquid immersion exposure. The coating and developing device 2 performs a process of coating a resist film on the surface of the wafer W (substrate) before the exposure process of the exposure device 3, and performs a development process of the resist film after the exposure process. By performing a series of processes, a resist film of a predetermined pattern is formed.

[0045] [Substrate processing device]

[0046] Next, as an example of a substrate processing device, the structure of the coating and developing device 2 will be described. Figure 1 and 2 As shown, the coating and developing device 2 includes a carrier block 4, a processing block 5, an interface block 6 and a control device 100 (control unit). The coating and developing device 2 as a substrate processing device described in this embodiment is equivalent to a shape characteristic value estimating device that estimates a shape characteristic value related to the shape of an object film formed on a substrate. The "shape characteristic value" related to the shape of the object film in this embodiment is equivalent to a feature quantity related to the shape of the object film. As an example, the shape characteristic value can cite a critical dimension (CD: Critical Dimension) such as the film thickness, line width or pore size of the object film. In the following embodiment, the coating and developing device 2 is described as a shape characteristic value estimating device that estimates the film thickness of the object film. The function of estimating the film thickness of the coating and developing device 2 will be described later.

[0047] The carrier block 4 is used to introduce the wafer W into the coating and developing device 2 and to guide the wafer W out of the coating and developing device 2. For example, the carrier block 4 can support a plurality of carriers C (storage units) for the wafer W, and has a conveying device A1 including a transfer arm built therein. The carrier C, for example, stores a plurality of circular wafers W. The conveying device A1 takes out the wafer W from the carrier C and delivers it to the processing block 5, and takes the wafer W from the processing block 5 and returns it to the carrier C. The processing block 5 has a plurality of processing modules 11, 12, 13, 14.

[0048] The processing module 11 is equipped with a plurality of coating units U1, a plurality of heat treatment units U2, a plurality of inspection units U3, and a conveying device A3 equipped with a conveying arm for conveying the wafer W to these units. The processing module 11 forms a lower film on the surface of the wafer W through the coating unit U1 and the heat treatment unit U2. The coating unit U1 of the processing module 11, for example, rotates the wafer W at a predetermined rotation speed while applying a processing liquid for forming the lower film on the wafer W. The heat treatment unit U2 of the processing module 11 performs various heat treatments accompanying the formation of the lower film. The heat treatment unit U2, for example, is equipped with a heating plate and a cooling plate, and the heating plate is used to heat the wafer W to a predetermined heating temperature, and the cooling plate is used to cool the heated wafer W for heat treatment. The inspection unit U3 performs a process for inspecting the state of the surface of the wafer W, and obtains information such as a surface image or information related to a shape characteristic value (film thickness) as information indicating the state of the surface of the wafer W.

[0049] The processing module 12 is equipped with a plurality of coating units U1, a plurality of heat treatment units U2, a plurality of inspection units U3, and a conveying device A3 for conveying the wafer W to these units. The processing module 12 forms an intermediate film on the lower film through the coating unit U1 and the heat treatment unit U2. The coating unit U1 of the processing module 12 applies a processing liquid for forming the intermediate film on the lower film, thereby forming a coating film on the surface of the wafer W. The heat treatment unit U2 of the processing module 12 performs various heat treatments accompanying the formation of the intermediate film. The heat treatment unit U2, for example, is equipped with a heating plate and a cooling plate, and the wafer W is heated to a predetermined heating temperature by the heating plate, and the heated wafer W is cooled by the cooling plate to perform heat treatment. The inspection unit U3 performs processing for inspecting the state of the surface of the wafer W, and obtains information such as a surface image or information related to a shape characteristic value (film thickness) as information indicating the state of the surface of the wafer W.

[0050] The processing module 13 is equipped with a plurality of coating units U1, a plurality of heat treatment units U2, a plurality of inspection units U3, and a conveying device A3 for conveying the wafer W to these units. The processing module 13 forms a resist film on the intermediate film through the coating unit U1 and the heat treatment unit U2. The coating unit U1 of the processing module 13, for example, applies a processing liquid for forming a resist film on the intermediate film while rotating the wafer W at a predetermined rotation speed. The heat treatment unit U2 of the processing module 13 performs various heat treatments accompanying the formation of the resist film. The heat treatment unit U2 of the processing module 13 forms a resist film by performing a heat treatment (PAB: Post Applied Bake) at a predetermined heating temperature on the wafer W formed with the coating film. The inspection unit U3 performs a process for inspecting the state of the surface of the wafer W, and obtains information related to, for example, a shape characteristic value (film thickness) as information indicating the state of the surface of the wafer W.

[0051] The processing module 14 is equipped with a plurality of coating units U1, a plurality of heat treatment units U2, and a conveying device A3 for conveying the wafer W to these units. The processing module 14 performs a development process on the resist film R after exposure through the coating unit U1 and the heat treatment unit U2. For example, the coating unit U1 of the processing module 14 rotates the wafer W at a predetermined rotation speed while applying a developer on the surface of the exposed wafer W, and then washes it with a rinse solution, thereby performing a development process on the resist film R. The heat treatment unit U2 of the processing module 14 performs various heat treatments accompanying the development process. As specific examples of the heat treatment, a heat treatment before the development process (PEB: Post Exposure Bake), a heat treatment after the development process (PB: Post Bake), etc. can be cited.

[0052] A shelf unit U10 is provided on the side of the carrier block 4 in the processing block 5. The shelf unit U10 is divided into a plurality of small chambers arranged side by side in the vertical direction. A conveying device A7 including a lifting arm is provided near the shelf unit U10. The conveying device A7 lifts and lowers the wafer W between the small chambers of the shelf unit U10.

[0053] A shelf unit U11 is provided on the interface block 6 side in the processing block 5. The shelf unit U11 is divided into a plurality of small chambers arranged side by side in the vertical direction.

[0054] The interface block 6 transfers wafers W between the interface block 6 and the exposure device 3. For example, the interface block 6 has a conveyor device A8 including a transfer arm built therein, and is connected to the exposure device 3. The conveyor device A8 transfers wafers W arranged in the shelf unit U11 to the exposure device 3, receives wafers W from the exposure device 3 and returns them to the shelf unit U11.

[0055] [Inspection unit]

[0056] The inspection unit U3 included in the processing modules 11 to 13 will be described. The inspection unit U3 has a function of capturing images of the surface of a film (eg, an underlayer film, an intermediate film, a resist film, etc.) formed by the coating unit U1 and the heat treatment unit U2 to obtain image data.

[0057] like Figure 3As shown, the inspection unit U3 includes a housing 30, a holding part 31, a linear drive part 32, a photographing part 33, and a light projection and reflection part 34. The holding part 31 holds the wafer W horizontally. The linear drive part 32 uses, for example, a motor as a power source to move the holding part 31 along a horizontal linear path. The photographing part 33 includes a camera 35 such as a CCD camera. The camera 35 is arranged at one end side in the inspection unit U3 in the moving direction of the holding part 31 and faces the other end side in the moving direction. The light projection and reflection part 34 projects light in the photographing range and guides the reflected light from the photographing range to the camera 35 side. For example, the light projection and reflection part 34 includes a half mirror 36 and a light source 37. The half mirror 36 is arranged in the middle of the moving range of the linear drive part 32 at a position higher than the holding part 31, and reflects the light from below to the camera 35 side. The light source 37 is arranged above the half mirror 36 and irradiates the illumination light downward through the half mirror 36.

[0058] The inspection unit U3 operates as follows to obtain image data of the surface of the wafer W. First, the linear drive unit 32 moves the holding unit 31. As a result, the wafer W passes under the half mirror 36. During this passage, the reflected light from each part of the surface of the wafer W is sent to the camera 35 in sequence. The camera 35 images the reflected light from each part of the surface of the wafer W and obtains image data of the surface of the wafer W. When the shape (for example, film thickness, line width, etc.) of the film formed on the surface of the wafer W changes, for example, the color, i.e., the color of the surface of the wafer W changes according to the change in shape, and the image data of the surface of the wafer W captured by the camera 35 changes. That is, obtaining the image data of the surface of the wafer W is equivalent to obtaining information related to the shape of the film formed on the surface of the wafer W. This point will be explained later.

[0059] The image data acquired by the camera 35 is sent to the control device 100. The control device 100 can estimate the shape characteristic value of the film on the surface of the wafer W based on the image data, and the estimation result is stored as an inspection result in the control device 100. In addition, the image data is also stored in the control device 100.

[0060] [Control device]

[0061] An example of the control device 100 is described in detail. The control device 100 controls the various elements included in the coating and developing device 2. The control device 100 can perform a process including a step of forming the above-mentioned various films on the surface of the wafer W and a step of performing a developing process. In addition, the control device 100 can perform a process for estimating the shape characteristic value of the formed film as a main part of the shape characteristic value estimation device. Here, a structural example of the control device 100 in the case of estimating the film thickness of the target film as the shape characteristic value in the coating and developing device 2 is described.

[0062] like Figure 4 As shown, the control device 100 includes a base image acquisition unit 101, a processed image acquisition unit 102, an image information storage unit 103, an estimation unit 104, an estimation model storage unit 105, and a shape characteristic value information storage unit 106 as a functional structure. In addition, the control device 100 has a base influence model generation unit 107 and an estimation result correction unit 108. Figure 4 Each functional unit shown is a functional unit for realizing a function as a film thickness estimating means as a form of shape characteristic value estimating means.

[0063] Before describing each functional unit, an overview of the processing (inspection) performed by the coating and developing device 2 including the control device 100 as a device (shape characteristic value estimation device) for inspecting a substrate is described. In the coating and developing device 2, a process of estimating the film thickness of a film formed on the surface of the wafer W is performed based on an image obtained by photographing the surface of the wafer W. When a film is formed on the surface of the wafer W, the color of the surface changes depending on the thickness. Taking advantage of this, the coating and developing device 2 estimates the film thickness of each point on the surface of the wafer W based on the image data including information related to the color of the surface of the wafer W.

[0064] As an example, the process of estimating the film thickness is as follows. That is, first, prepare a plurality of wafers whose film thicknesses are known for the films (object films) to be estimated. Then, generate a film thickness estimation model (shape characteristic value estimation model) based on the correlation between the information related to the color of each pixel in the image information obtained by photographing the surface of the above-mentioned wafer and the film thickness of the film on the surface of the wafer at the position where the pixel is photographed. After that, obtain an image obtained by photographing the surface of a wafer on which an object film to be estimated is formed, and estimate the film thickness of the film on the surface of the wafer based on the information related to the color of each pixel contained in the image data and the film thickness estimation model. Thus, the film thickness of the object film on the surface of the wafer can be estimated.

[0065] Figure 5 FIG. 2 is a diagram schematically showing changes in color-related information obtained from image data obtained by photographing a plurality of wafers. Figure 5 , information related to the color of the surface (here, grayscale value) obtained by photographing the image data obtained by forming the target film on the surface of the wafer is shown. Figure 5 As shown, each wafer is displayed in a different color, and therefore the film thickness of the film on the wafer surface is estimated by utilizing the difference in color.

[0066] However, in the above method, it may not be possible to generate a film thickness estimation model that takes into account the condition of the lower layer of the film to be estimated. As described above, a plurality of films are formed on a wafer. Therefore, when the film to be estimated is a resist film, a lower film and an intermediate film are stacked under the resist film. Therefore, Figure 5 The difference in the color of the wafer surface of each wafer shown may reflect not only the change caused by the film thickness of the target film whose film thickness is to be estimated, but also the difference in the state of the underlying portion (i.e., in a state where no processing related to the target film has been performed). When the film thickness of the film formed on the surface is sufficiently thin, as in the case of the target substrate in this embodiment, the difference in the state of the underlying portion can reflect the difference in the change in the color of the wafer surface.

[0067] The above-mentioned film thickness estimation model is a model for estimating the correlation between the film thickness of the resist film and the color information in the image data. However, it can be said that it does not take into account the situation where the film thickness of each film below the resist film is different. For example, when the film thickness of the intermediate film below the resist film changes, there is a possibility that the color of the wafer surface changes due to the film thickness of the intermediate film in the state before the resist film is applied. However, in the film thickness estimation model, the influence of the lower film may not be fully reflected. Considering the above-mentioned problems, it is also a method to generate a film thickness estimation model using a wafer that changes the condition of the lower film (film thickness, etc.). However, it is difficult to prepare a large number of wafers corresponding to the various conditions required to generate a model with high estimation accuracy.

[0068] Therefore, in the coating and developing device 2 described in this embodiment, a model is generated, that is, using the image information (base image) obtained by photographing the surface of the base portion below the target film (in a state where the target film is not formed), to estimate the extent to which the difference in the base portion affects the estimated result of the film thickness. Specifically, for a wafer formed with a target film, a model is generated based on the estimated result (estimated value) of the film thickness using the film thickness estimation model, the film thickness value obtained by a method not using the film thickness estimation model, and the image information (base image) of the surface of the wafer before the target film is coated. This model (base influence model) is a model that estimates whether the base portion affects the estimated result of the film thickness of the target film based on the film thickness estimation model based on the image of the base portion. In the coating and developing device 2 described in this embodiment, a process of using the base influence model to remove the error of the estimated film thickness caused by the uneven film thickness of the base portion and calculate a film thickness estimation result with higher accuracy is realized. The control device 100 performs such a process of estimating the film thickness with high accuracy.

[0069] Figure 4The base image acquisition unit 101 of the control device 100 shown in the figure has a function of acquiring image information (base image) of the surface of a wafer before the target film is formed on which the target film whose film thickness is to be estimated is formed. The base image acquisition unit 101 acquires the base image of the target wafer W by controlling the inspection unit U3, for example.

[0070] The processed image acquisition unit 102 has a function of acquiring image information (processed image) of the surface of the wafer W after the target film is formed. The processed image acquisition unit 102 acquires the processed image of the target wafer W by controlling the inspection unit U3, for example.

[0071] The image information storage unit 103 has a function of storing the base image acquired by the base image acquisition unit 101 and the processed image acquired by the processed image acquisition unit 102. The image information stored in the image information storage unit 103 is used to estimate the film thickness of the target film formed on the wafer W.

[0072] The estimation unit 104 has a function of estimating the film thickness of the target film based on the processed image stored in the image information storage unit 103. The estimation of the film thickness by the estimation unit 104 can use a film thickness estimation model.

[0073] The estimation model holding unit 105 has a function of holding a film thickness estimation model used for estimation of film thickness by the estimation unit 104. The film thickness estimation model is a model for calculating film thickness based on information on the color of each pixel in image data obtained by photographing the surface of the wafer W when a predetermined film is formed (the change in color before and after the predetermined film is formed), and is a model that represents the correspondence between the color information and the film thickness. Such a model is prepared in advance and held by the estimation model holding unit 105 to obtain information related to the color of the surface of the wafer W at each position of the image data, thereby being able to estimate the film thickness based on the information related to the color. The method for generating the film thickness estimation model is not particularly limited, and it can be generated using a known statistical processing method or the like. For example, information related to the color of the surface of the base substrate contained in the base image acquired by the base image acquisition unit 101 and information related to the color of the surface of the processed substrate contained in the processed image acquired by the processed image acquisition unit 102 is used to obtain information related to the change in the color of the substrate surface caused by the formation of the film. On this basis, a film thickness estimation model can be generated by calculating the correlation between the color change and the film thickness. However, the above method is an example and is not limited to the above example. For example, instead of using information related to the color of the surface of the base substrate, only information related to the color of the surface of the processed substrate can be used to calculate the correlation between the color change and the film thickness to generate a model. In addition, the film thickness estimation model can also be generated by the coating and developing device 2, and can also be generated by, for example, other devices.

[0074] The shape characteristic value information holding unit 106 has a function of holding information related to the film thickness of the object film (film thickness value: sometimes referred to as film thickness information), and the information on the film thickness of the object film is equivalent to the shape characteristic value of the object film obtained without using the film thickness estimation model. As the film thickness value of the object film obtained without using the film thickness estimation model, for example, it can be a measured value of the film thickness of the object film measured by any method. In addition, under the condition that the coating and developing device 2 works stably, for example, during the detailed inspection (QC inspection) of the working confirmation of the device, a film is formed on the inspection substrate and evaluated, so the inspection result at this time can be used as the film thickness value (film thickness information). In addition, as long as the characteristics of the multiple units (coating unit, heat treatment unit, etc.) related to film formation included in the coating and developing device 2 can be grasped to a certain extent, the film thickness value can be obtained based on which unit has been processed. In addition, as long as it is known in advance that the thickness of the film after film formation gradually changes according to the characteristics of the device, the value obtained by adding the measured value measured regularly to the predicted value that changes over time can be used as the film thickness value. The film thickness value used as film thickness information is a value with high reliability to a certain extent, and as long as it is a value obtained (or calculated) without using a film thickness estimation model, it can be obtained using various methods. Regarding the film thickness value maintained in the shape characteristic value information holding unit 106, the film thickness value can be obtained while performing the film formation process on the chip W as in the case of actual measurement by any method, or it can be obtained in advance (calculated) when the predicted value is used as the film thickness value. In addition, regarding the film thickness value, one value can be set for each chip W, or multiple values ​​can be defined for one chip W (for example, per shot or per coating).

[0075] The base influence model generation unit 107 has a function of generating a base influence model based on the estimation result (estimated value) of the film thickness using the film thickness estimation model, the film thickness value obtained by a method not using the film thickness estimation model, and the image information (base image) of the surface of the wafer before the target film is applied. The base influence model is generated after the estimation results of the film thickness estimation model are accumulated to a certain extent. The details of the base influence model will be described later.

[0076] The estimation result correction unit 108 has a function of correcting the film thickness value estimated by the film thickness estimation model based on the base influence model generated by the base influence model generation unit 107. The base influence model can be used to estimate whether the base portion has an influence on the estimated result of the film thickness, and thus, based on the film thickness value estimated by the film thickness estimation model, the component affected by the base portion is removed, thereby obtaining a more accurate film thickness estimation result.

[0077] The control device 100 is composed of one or more control computers. For example, the control device 100 has Figure 6The circuit 120 shown in . The circuit 120 includes one or more processors 121, a memory 122, a storage 123 and an input / output port 124. The storage 123 has, for example, a computer-readable storage medium such as a hard disk. The storage medium stores a program for causing the control device 100 to execute the substrate inspection process described later. The storage medium can also be a removable medium such as a non-volatile semiconductor memory, a magnetic disk, and an optical disk. The memory 122 temporarily stores the program loaded from the storage medium of the storage 123 and the calculation results of the processor 121. The processor 121 constitutes the above-mentioned functional modules by executing the above-mentioned program in cooperation with the memory 122. The input / output port 124 inputs and outputs electrical signals between it and the component that is the control object according to the instruction from the processor 121.

[0078] The hardware configuration of the control device 100 is not necessarily limited to the configuration in which each functional block is configured by a program. For example, each functional block of the control device 100 may be configured by a dedicated logic circuit or an ASIC (Application Specific Integrated Circuit) in which these are integrated.

[0079] In the following embodiments, the control device 100 includes the above-mentioned configurations, but the control device 100 may not include all of the above-mentioned functions. For example, a functional unit serving as a database such as the image information storage unit 103, the estimated model storage unit 105, and the shape characteristic value information storage unit 106 may be provided in an external device.

[0080] [Processing flow]

[0081] Next, as an example of coating and developing processing, a process flow executed in the coating and developing device 2 will be described.

[0082] In the process flow, first, the control device 100 controls the conveying device A1 to convey the wafer W in the carrier C to the shelf unit U10 , and controls the conveying device A7 to place the wafer W in the chamber for the process module 11 .

[0083] Next, the control device 100 controls the conveying device A3 to convey the wafer W of the shelf unit U10 to the coating unit U1 and the heat treatment unit U2 in the processing module 11. Then, the control device 100 controls the coating unit U1 and the heat treatment unit U2 to form a lower film on the surface of the wafer W. After that, the control device 100 controls the conveying device A3 to return the wafer W with the lower film formed thereon to the shelf unit U10, and controls the conveying device A7 to place the wafer W in the small chamber for the processing module 12.

[0084] Next, the control device 100 controls the conveying device A3 to convey the wafer W of the shelf unit U10 to the coating unit U1 and the heat treatment unit U2 in the processing module 12. Then, the control device 100 controls the coating unit U1 and the heat treatment unit U2 to form an intermediate film on the lower film of the wafer W. For example, the control device 100 controls the coating unit U1 so that the processing liquid for forming the intermediate film is coated on the lower film of the wafer W to form the intermediate film. Next, the control device 100 controls the heat treatment unit U2 to perform heat treatment on the intermediate film. After the intermediate film is formed, the control device 100 controls the conveying device A3 to convey the wafer W to the inspection unit U3, and controls to use the inspection unit U3 to photograph the surface of the wafer W to obtain image information (base image). After that, the control device 100 controls the conveying device A3 to return the wafer W to the shelf unit U10, and controls the conveying device A7 to configure the wafer W in the small chamber for the processing module 13.

[0085] Next, the control device 100 controls the conveying device A3 to convey the wafer W of the shelf unit U10 to each unit in the processing module 13, and controls the coating unit U1 and the heat treatment unit U2 to form a resist film on the intermediate film of the wafer W. For example, the control device 100 controls the coating unit U1 to form a resist film by coating the processing liquid used for resist film formation on the intermediate film of the wafer W. Next, the control device 100 controls the heat treatment unit U2 to perform heat treatment on the resist film. Next, the control device 100 controls so that the resist film is subjected to heat treatment. In addition, after the resist film is formed, the control device 100 controls the conveying device A3 to convey the wafer W to the inspection unit U3, and controls to use the inspection unit U3 to shoot the surface of the wafer W to obtain image information (processed image). Afterwards, the control device 100 controls the conveying device A3 to convey the wafer W to the shelf unit U11.

[0086] Next, the control device 100 controls the conveyor device A8 to convey the wafer W in the shelf unit U11 to the exposure device 3. Thereafter, the control device 100 controls the conveyor device A8 to receive the wafer W subjected to the exposure process from the exposure device 3 and place the wafer W in the chamber for the processing module 14 in the shelf unit U11.

[0087] Next, the control device 100 controls the conveying device A3 to convey the wafer W of the shelf unit U11 to each unit U8 in the processing module 14, and controls the coating unit U1 and the heat treatment unit U2 to perform a development process on the resist film R of the wafer W. After that, the control device 100 controls the conveying device A3 to return the wafer W to the shelf unit U10, and controls the conveying device A7 and the conveying device A1 to return the wafer W to the carrier C. Above, the process is completed.

[0088] [Film thickness estimation method]

[0089] Below, refer to Figure 7 to Figure 10 , a film thickness estimation method in the processing modules 11 to 13 performed by the control device 100 is described. The film thickness estimation method is a method related to the inspection of the wafer W after film formation performed in the inspection unit U3 provided in the processing modules 11 to 13. In the inspection unit U3, by estimating the film thickness, it is evaluated whether the desired film formation is performed on the wafer W after film formation, especially whether the film is formed to a desired film thickness.

[0090] In addition, in the following embodiments, the case of estimating the film thickness of the resist film is described. Therefore, the object film is a resist film, and the wafer W before the resist film is formed (that is, the wafer until the intermediate film is formed) is described as the base substrate. However, the object film is not limited to the resist film. For example, the object film can also be used as the intermediate film to estimate the film thickness of the intermediate film. In this case, the base substrate becomes the wafer before the intermediate film is formed, that is, the wafer formed with the base film. As described above, the setting of the base substrate can be changed according to the object film that becomes the object of the film thickness to be estimated. In addition, the base substrate can also be a substrate that has been processed (for example, film forming, etching, cleaning, etc.) by other devices. As described above, the base substrate can be any substrate before the object film is formed, and there is no special limitation.

[0091] Figure 7 1 is a flowchart of a series of steps in a film thickness estimation method, which are steps until the estimation of the film thickness using a film thickness estimation model. First, the control device 100 executes step S01. In step S01, a base substrate is prepared and sent to the inspection unit U3. The base substrate is a wafer W that has been film-formed up to the intermediate film in the coating unit U1 and the heat treatment unit U2 as described above. The sent base substrate is held in the holding portion 31.

[0092] Next, the base image acquisition unit 101 of the control device 100 executes step S02. In step S02, the surface of the base substrate is photographed by the imaging unit 33. Specifically, while the holding unit 31 is moved in a predetermined direction by the driving of the linear driving unit 32, the surface of the base substrate is photographed by the imaging unit 33. Thus, image information (base image) related to the surface of the base substrate can be obtained in the imaging unit 33. The base image is held in the image information holding unit 103 of the control device 100.

[0093] Next, the control device 100 executes step S03. In step S03, a resist film is formed on the base substrate. The wafer W formed in the coating unit U1 and the heat treatment unit U2 is sent to the inspection unit U3. The sent wafer W after film formation is held in the holding unit 31.

[0094] Next, the processed image acquisition unit 102 of the control device 100 executes step S04. In step S04, the surface of the processed wafer W is photographed by the imaging unit 33 in the same manner as step S02. Specifically, the surface of the wafer W is photographed by the imaging unit 33 while the holding unit 31 is moved in a predetermined direction by the driving of the linear driving unit 32. Thus, image information (processed image) related to the surface of the wafer W can be obtained in the imaging unit 33. The processed image is stored in the image information storage unit 103 of the control device 100.

[0095] Next, the estimation unit 104 of the control device 100 executes step S05. In step S05, the film thickness of the target film on the surface of the wafer W is estimated based on the processed image related to the surface of the wafer W. In the estimation of the film thickness by the estimation unit 104, the film thickness estimation model held in the estimation model holding unit 105 is used.

[0096] The method for estimating the film thickness based on the processed image is specifically described as follows. First, information related to the color of the surface of the chip W is obtained for each pixel from the processed image. At this time, a process of calculating the correlation with the base image before film formation can be performed. Whether to perform this step can be appropriately changed according to which condition the film thickness estimation model is a model for. After that, a comparison is made with the film thickness model maintained by the estimation model holding unit 105. Thus, the film thickness of the area where the pixel is photographed can be estimated for each pixel. Thus, the film thickness of the target film at each position on the surface of the chip W can be estimated for each pixel. The series of processes so far is a method commonly used in the estimation of film thickness using a film thickness estimation model.

[0097] Next, in the film thickness estimation method described in this embodiment, the following is performed using Figure 8 Correction of the substrate-affected model is shown.

[0098] like Figure 8 As shown, the substrate influence model generation unit 107 of the control device 100 sequentially executes steps S11 to S13 related to the generation of the substrate influence model. In step S11, first, the film thickness estimation result y of the corresponding film based on the film thickness estimation model (F) and the film thickness information Y of the corresponding film in a specific pixel are obtained. In step S12, a substrate image related to the wafer W whose film thickness is estimated is prepared. Then, in step S13, a substrate influence model (G) is generated involving the correlation between the difference between the film thickness estimation result y and the film thickness information Y and the color information contained in the substrate image. Then, after the substrate influence model (G) is generated, the estimation result correction unit 108 of the control device 100 executes step S14. In step S14, the substrate influence element y' calculated according to the substrate influence model (G) is subtracted from the film thickness estimation result y of the corresponding film to correct the film thickness estimation result. These steps are explained below.

[0099] The film thickness estimation result of the film thickness estimation model in the processed image is set to y, and the film thickness information of the corresponding film is set to Y. In addition, the film thickness estimation model generated based on the image after film formation (processed image) is set to F (processed image). The film thickness estimation result y is calculated based on the film thickness estimation model, and therefore should satisfy the relationship of the following formula (1).

[0100] y=F(processed image)……(1)

[0101] Here, when the accuracy of the film thickness estimation model is sufficiently high, the film thickness estimation result y should be consistent with the film thickness information Y. However, in reality, the following equation (2) is obtained.

[0102] Y=F(processed image)+error1……(2)

[0103] exist Fig. 9 In the equation (2), it is schematically shown that the film thickness estimation result may contain the error "error1". Fig. 9 In the diagram, for each wafer W as the target, the relationship between the film thickness estimation result y in a specific pixel and the film thickness information Y is plotted as a graph. When the film thickness estimation result y and the film thickness information Y are consistent, the points should be arranged in Fig. 9 However, in reality, the film thickness estimation result y is inconsistent with the film thickness information Y. There are group T1 where the film thickness estimation result y is larger than the film thickness information Y and group T2 where the film thickness estimation result y is smaller than the film thickness information Y. In addition to the simple error, the "error1" in formula (2) may also include errors caused by insufficient accuracy of the film thickness estimation model F. One of the reasons for the reduction in accuracy of the film thickness estimation model F is that the variation caused by the base substrate below the target film as described above cannot be fully eliminated.

[0104] Therefore, as the base influence model, the correlation between the color information obtained from the base image and the portion corresponding to "error 1" is grasped. When the base influence model is G, the base influence model is a model that satisfies the following equation (3).

[0105] y-Y=G(base image)+error2……(3)

[0106] "Error1" in equation (2) includes the variation caused by the base substrate as described above, and the component caused by the base substrate as described above is used as the base influence model G. As a result, "error2" in equation (3) includes only the so-called simple error in addition to the component caused by the base substrate.

[0107] exist Fig.10In FIG. 1 , the base influence model G is schematically shown. The base influence model G is a model that represents the correlation between information related to the color of the base substrate surface in the base image (for example, the brightness value in the base image) and y-Y. Fig.10 As shown, by modeling the correlation between the color information of the base substrate surface (e.g., the brightness value in the base image) and y-Y, it is possible to increase the correction corresponding to the color of the base substrate surface. That is, the variation amount (equivalent to y-Y) caused by the base substrate included in the estimated value of the film thickness estimated using the film thickness estimation model F can be grasped based on the base influence model G.

[0108] When a base influence factor obtained from a base influence model in a specific pixel is defined as y′, y′ satisfies the relationship of the following equation (4).

[0109] y'=G(base image)……(4)

[0110] When the base influence factor y' is subtracted from the film thickness estimation result y estimated using the film thickness estimation model F, as shown in formula (5), the film thickness estimation result y can be made closer to the film thickness information Y, that is, a more accurate value. As shown in formula (5), this y-y' includes error2 as a simple error. However, as mentioned above, error2 does not include the model error, so y-y' can remove the model error that may be included in the estimation result only when the film thickness estimation model F is used.

[0111] Y-y'=y-(y-Y)+error2=Y-error2......(5)

[0112] In addition, Fig.10 In FIG. 1 , the base influence model G is shown to be a linear function of the brightness value of the base image, but this is a simpler example for the purpose of explanation. Fig.10 As shown, a linear function can be obtained by using only one value as information related to the color of the base image, but a complex statistical method can also be used to achieve a more accurate modeling. That is, instead of using only the brightness value as information related to the color of the base image when generating the base influence model G, multiple parameters such as RGB values ​​can be used, and a statistical method using these feature quantities can be used to generate the model. The base influence model G can be generated using, for example, statistical methods such as multivariate regression analysis, nonlinear analysis, decision tree analysis, and well-known regression analysis.

[0113] The generation of the base effect model G and the correction of the film thickness estimation result using the base effect model G described above ( Figure 8The series of processing shown in FIG. 1 can be performed at a stage where the estimated results of the film thickness of the target film using the film thickness estimation model F have accumulated to a certain extent. This is because, at the stage of preparing the film thickness estimation model F, it is impossible to grasp to what extent the film thickness estimation model F includes the variation caused by the base substrate (i.e., the component equivalent to the base influence model G). Therefore, after the film thickness of a plurality of wafers W is estimated using the film thickness estimation model F, the above-mentioned generation of the base influence model G and the correction of the film thickness estimation results using the base influence model G are performed. In order to improve the accuracy of the base influence model G to a certain extent, the amount of data generated for the base influence model G can be increased to several tens of times, but it is not limited to this amount.

[0114] In addition, the base influence model G may be corrected at predetermined intervals. For example, when the number of wafers W processed in the coating and developing device 2 exceeds a predetermined number, the base influence model G may be regenerated using the information related to the latest several dozen wafers W to reflect the estimation of the film thickness of the subsequent wafers W. In this way, the generation timing of the base influence model G and its change may be appropriately changed in consideration of the operating conditions of the coating and developing device 2, the characteristics of the wafers W, and the like.

[0115] Furthermore, the data used to generate the base influence model G is not limited to one for one wafer W. Since the film thickness estimation model F is used to estimate the film thickness for each exposure, the base influence model G can be generated by taking in the estimation results for each pixel.

[0116] [effect]

[0117] According to the above-mentioned shape characteristic value estimation device (film thickness estimation device) and shape characteristic value estimation method (film thickness estimation method), first, the film thickness of the object film is estimated using a film thickness estimation model. Next, a base influence model is generated, which is a model of the correlation between the difference between the estimated result of the film thickness of the object film and the film thickness value of the object film obtained without using the film thickness estimation model, and the information on the color of the surface of the base substrate contained in the base image. Then, based on the base influence model, the estimated result is corrected. By adopting the above-mentioned structure, the variable component of the estimated result caused by the color of the base substrate, etc. can be corrected based on the base influence model. Therefore, the film thickness of the object film formed on the substrate can be estimated with higher accuracy.

[0118] In addition, by using the film thickness value of the target film used when generating the base effect model as the measured value of the film thickness of the substrate on which the target film is formed, the base effect model can be generated with higher accuracy, thereby enabling the film thickness of the target film formed on the substrate to be estimated with higher accuracy.

[0119] Even when the measured value is not used, the film thickness value can be obtained with high accuracy based on the operating conditions of the coating and developing device 2 or the difference in accuracy of a method different from the actual measurement of the substrate. In such a case, the same effect as the measured value can be obtained.

[0120] In addition, in the case where the film thickness estimation model is a model generated based on information related to the color of the surface of the base substrate contained in the base image, the estimation result of the film thickness based on the film thickness estimation model takes into account the influence of the color of the base substrate to a certain extent. Therefore, the estimation result obtained using the film thickness estimation model is sufficiently accurate. On this basis, correction using the base influence model is further performed, thereby further correcting the variable components of the estimation result caused by the color of the base substrate, etc. that are not fully captured in the film thickness estimation model, thereby further improving the accuracy of the estimation result.

[0121] In addition, in the above-mentioned shape characteristic value estimation device (film thickness estimation device), there is a base image acquisition unit 101, and the base influence model is generated using information related to the surface of the base substrate contained in the base image acquired by the base image acquisition unit 101. In this case, the base influence model can be generated using information about the surface of the base substrate that is completely unaffected by the film thickness to be processed, etc. Therefore, the base influence model can be generated with higher accuracy.

[0122] [When the shape characteristic value is CD]

[0123] In the above-mentioned embodiment, the case where the "shape characteristic value" is the film thickness of the object film is described, but the critical dimension (CD) such as the line width can also be used as the shape characteristic value as described above. In this case, the CD can be estimated by the same method as described above. Specifically, the CD of the object film is estimated using an estimation model for estimating CD. Next, a base influence model is generated, which is a model of the correlation between the difference between the estimated result of the CD of the object film and the CD of the object film obtained without using the above-mentioned estimation model, and the information on the color of the surface of the base substrate contained in the base image. Then, based on the base influence model, the estimated result is corrected. By adopting such a structure, the variable component of the estimated result caused by the color of the base substrate, etc. can be corrected based on the base influence model, and the CD of the object film formed on the substrate can be estimated with higher accuracy. In the following, after explaining that the CD can be estimated using the above-mentioned method described in the estimation of the film thickness, the changes in the estimation of the film thickness when estimating the CD are explained.

[0124] The CD of the line width is the minimum width of the pattern of the target film (for example, resist) after development, and is in the range of several nm to several μm. Here, the imaging unit 33 of the inspection unit U3 used in acquiring the base image and the processed image does not have the resolving power (resolution) to the extent that the CD of the pattern can be accurately measured based on the captured image. In the image captured by the imaging unit 33, the color of the pattern portion changes according to the CD size. Therefore, the information related to the color of the surface acquired for each pixel (here, the grayscale value) changes according to the shape of the pattern formed on the target film. Therefore, by the same method as the film thickness estimation model described in the above embodiment, a model for estimating the CD of the line width, aperture, etc., i.e., a CD estimation model, can be generated. In addition, CD estimation using the CD estimation model can be performed in the same manner as the film thickness estimation using the film thickness estimation model.

[0125] However, the processing related to the target film is not the coating of the target film on the substrate, but the removal of a part of the target film (as an example, the development processing after the exposure of the resist film). Therefore, the base image before the processing of the target film becomes an image obtained by photographing the area before the removal of the target film, that is, the surface in the state of coating the target film. In addition, the processed image becomes an image obtained by photographing the area after the removal of the target film (after the pattern is formed).

[0126] In addition, when the process related to the target film is to remove a part of the target film (as an example, the development process after the exposure of the resist film), there is also a region where the target film remains on the surface of the wafer after the process (after pattern formation). Fig.11 Provide explanation. Fig.11 (a) shows a state where a pattern based on a resist as a target film is formed on a wafer W. In addition, Fig.11 (b) schematically shows the photographing of Fig.11 (a) is a diagram showing a portion of an image obtained from the surface of a wafer in the region shown. Fig.11 (a) shows a state where a resist film PR is formed on the uppermost surface after a plurality of layers are formed on the lower portion. Fig.11 As shown in (a), on the upper surface of the wafer W after pattern formation, there may be an area R1 where no pattern is formed, an area R2 where a pattern is formed, and an area R3 where no resist is present. The area R1 where no pattern is formed is an area where the applied resist remains as it is, and the area R2 where a pattern is formed is an area where part of the resist is removed. In the image obtained by photographing the wafer W in this state, as shown in FIG. Fig.11As shown in (b), there may be an image area PA1 obtained by photographing the area R1 where no pattern is formed, an image area PA2 obtained by photographing the area where the pattern is formed, and an image area PA3 obtained by photographing the area where no resist is present. Among them, the image area PA2 is an area containing image information related to the surface of the substrate on which the target film is formed, which is used when estimating the CD, and is equivalent to the "processed image".

[0127] On the other hand, the image area PA1 is an area obtained by photographing the area R1 where no pattern is formed, and therefore, can be referred to as an area containing image information related to the surface of the base substrate before the object film is formed. Therefore, this area is the same as the information obtained from the "base image". That is, Fig.11 As shown in (b), the image obtained by photographing the surface of the wafer W after the pattern forming process includes both image information related to the surface of the substrate on which the target film is formed and image information related to the surface of the base substrate. Therefore, it is possible to obtain both information included in the "processed image" and information included in the "base image" based only on the image obtained by photographing the processed wafer W. In this case, it is possible to obtain both the "shape characteristic value estimation model" and the "base influence model" described in the above embodiment based only on the processed image as the image obtained by photographing the processed wafer W.

[0128] For example, the "shape characteristic value estimation model" is a model based on the correlation between the color-related information of each pixel in the image information obtained by photographing the surface of the wafer and the shape characteristic value of the film on the wafer surface at the position where the pixel was photographed. Ideally, the shape characteristic value estimation model can be generated based on the information related to the color of the base substrate surface contained in the image information of the base substrate surface and the information related to the color of the processed substrate surface contained in the image information of the processed substrate surface. In this case, Fig.12 As shown in (a), assuming such a situation, the shape characteristic value estimation model M1 is generated based on the image information related to the surface of the base substrate contained in the base image D1 and the image information related to the surface of the processed substrate contained in the processed image D2. On the other hand, as described above, in the image obtained by photographing the wafer W after processing, when there is an image area PA1 obtained by photographing the area R1 after processing and an image area PA2 obtained by photographing the area before processing, the base image D1 may not be used. For example, Fig.12 As shown in (b), the image information related to the surface of the base substrate before processing and the image information related to the surface of the substrate after processing can be obtained from the processed image D2' containing the state of the substrate surface before and after processing, and the shape characteristic value estimation model M1 can be generated. Fig.12In the example shown in (b), only one image is used to generate the shape characteristic value estimation model M1, but two types of image information are obtained from a processed image D2' to generate the model, so it is possible to generate Fig.12 In addition, in the case where image information related to the surface of the base substrate before processing is obtained from the processed image D2' ( Fig.12 In the case of the example shown in (b), the accuracy varies depending on the determination of the area of ​​the base substrate to be imaged and the size of its area.

[0129] The “base effect model” can be processed in the same way as the shape characteristic value estimation model. As mentioned above, the “base effect model” is a model that estimates the extent to which the difference in the base part affects the estimated result of the film thickness. Specifically, Fig.13 As shown in (a), for a wafer formed with a target film, the estimation result (estimated value) of the shape characteristic value using the shape characteristic value estimation model and the shape characteristic value (true value) obtained without using the shape characteristic value estimation model are obtained, and the residual difference is calculated. Fig.13 As shown in (a), the image information related to the surface of the base substrate contained in the base image D1 is used as the image information of the surface of the wafer before the film as the object is formed, and the base influence model M2 is generated using them. On the other hand, in the case where there is a processed image D2' containing the state of the substrate surface before and after the processing, the image information related to the surface of the base substrate before the processing can be obtained from the processed image D2' to generate the base influence model M2. In this way, the image information related to the surface of the base substrate used in the base influence model M2 can be obtained from either the base image D1 or the processed image D2'. For example, when it is possible to obtain an image related to the surface of the base substrate in the state before the formation of the object film such as coating of the object film, pattern formation, etc., a base influence model can be generated.

[0130] In addition, if Fig.12 and Fig.13In the case where image information related to the surface of the base substrate before processing and image information related to the surface of the base substrate after processing can be obtained from the image obtained by photographing the wafer surface after processing, as shown in the processed image D2', the configuration described in the above embodiment can be realized even without using the base image D1. That is, both the shape characteristic value estimation model M1 and the base influence model M2 can be generated using only the processed image D2'. Therefore, even if the acquisition of the base image D1 is omitted in the coating and developing device 2, the characteristic value related to the shape of the object film formed on the base can be estimated with high accuracy. In this case, the photographing of the wafer W before processing in the inspection unit U3 can be omitted. In this way, when the base influence model is generated using the information related to the color of the surface of the base substrate contained in the processed image D2', the base influence model can be generated even without separately providing a structure for acquiring the information related to the color of the surface of the base substrate. Therefore, the base influence model can be generated with a simpler device structure.

[0131] However, when the processed image D2' includes image information on the surface of the base substrate before processing and image information on the surface of the base substrate after processing, it is of course possible to adopt a configuration in which the above-mentioned model is generated using the base image D1.

[0132] [Other embodiments]

[0133] Various exemplary embodiments have been described above, but the present invention is not limited to the exemplary embodiments described above, and various omissions, substitutions, and changes may be made. In addition, elements in different exemplary embodiments may be combined to form other exemplary embodiments.

[0134] For example, in the above embodiment, the shape characteristic value of the target film is described as "film thickness" or "critical dimension", but the shape characteristic value is not limited to the above two. The method described in this embodiment can be applied to the shape characteristic value that has a correlation with the color of the wafer W surface.

[0135] For example, in the above embodiment, the case where the inspection unit U3 is provided in each of the processing modules 11, 12, and 13 is described. However, the inspection unit U3 may be provided not in each module but independently of each module.

[0136] In addition, the film formed by the above-mentioned processing modules 11, 12, and 13 is an example and can be appropriately changed. For example, a film can also be formed above the resist film. That is, the film inspection method described in this embodiment is not limited to the type and number of films, and can be applied to various films formed on the substrate.

[0137] According to the above description, various embodiments of the present invention are described in this specification for illustration, and it should be understood that various changes can be made without departing from the scope and spirit of the present invention. Therefore, the various embodiments disclosed in this specification are not limited, and the true scope and spirit are given by the scope of the attached claims.

Claims

1. A shape characteristic value estimation device, characterized in that: include: a processed image acquisition section for acquiring a processed image, wherein the processed image includes image information related to a surface of a substrate on which a target film is formed; an estimating unit that estimates the shape characteristic value of the target film by applying an estimating model for estimating the shape characteristic value of the target film to the processed image, the estimating model involving a correlation between information on the color of the surface of the substrate included in the processed image and the shape characteristic value, wherein the shape characteristic value is a characteristic value related to the shape of the target film formed on the substrate; a base influence model generating unit for generating a base influence model, wherein the base influence model is a model involving correlation between a difference between an estimation result of the shape characteristic value of the target film obtained by the estimation unit and the shape characteristic value of the target film obtained without using the estimation model, and information on the color of the surface of a base substrate, the base substrate being a substrate before forming the target film; and An estimation result correction unit corrects the estimation result of the shape characteristic value of the target film obtained by the estimation unit based on the base influence model.

2. The shape characteristic value estimation device according to claim 1, characterized in that: The shape characteristic value of the target film obtained without using the estimation model is a measured value of the shape characteristic value of the substrate on which the target film is formed.

3. The shape characteristic value estimation device according to claim 1, characterized in that: The estimated model is a model generated also based on information related to the color of the surface of the base substrate.

4. The shape characteristic value estimation device according to claim 1 or 2, characterized in that: It also has a base image acquisition unit that acquires a base image related to image information of the surface of the base substrate, The base influence model generation unit generates the base influence model using information on the color of the surface of the base substrate included in the base image.

5. The shape characteristic value estimation device according to claim 1 or 2, characterized in that: The base influence model generation unit generates the base influence model using information on the color of the surface of the base substrate included in the processed image.

6. A method for estimating shape characteristic values, characterized in that: estimating a shape characteristic value, the shape characteristic value being a characteristic value related to the shape of a target film formed on a substrate, The shape characteristic value estimation method comprises: a step of acquiring a processed image, wherein the processed image includes image information related to the surface of the substrate on which the object film is formed; A step of estimating the shape characteristic value of the target film by applying an estimation model for estimating the shape characteristic value of the target film to the processed image, wherein the estimation model involves a correlation between information on the color of the substrate surface contained in the processed image and the shape characteristic value of the target film formed on the substrate; a step of generating a base influence model, wherein the base influence model is a model involving correlation between a difference between an estimated result of the shape characteristic value of the target film and the shape characteristic value of the target film obtained without using the estimated model, and information on the color of the surface of a base substrate, the base substrate being a substrate before forming the target film; and A step of correcting the estimated result of the shape characteristic value of the target film based on the base influence model.

7. A computer-readable storage medium, characterized in that: A program for causing the device to execute the shape characteristic value estimating method according to claim 6 is stored.

Images