Information processing system, information processing device, learning device, information processing method, learning method, and program

Abstract

An information processing system includes a storage unit that stores correspondence information that associates material information indicating a material of a composition, a process condition in a prescribed process using the composition, and performance information of the composition obtained by the process; a performance estimation unit that acquires the performance information based on input material information, the process condition, and the correspondence information; and an output unit that outputs the performance information.

Description

Technical Field

[0001] This invention relates to information processing systems, information processing devices, learning devices, information processing methods, learning methods, and programs.

[0002] This application claims priority based on Japanese Patent Application No. 2019-165263, filed on September 11, 2019, the contents of which are incorporated herein by reference. Background Technology

[0003] With the advancement of nanotechnology, there is an increasing demand for improved performance of photoresists, EB (Electron Beam) resists, and other resists. Therefore, developers are attempting to develop new resists by repeatedly experimenting with various materials (see, for example, Non-Patent Literature 1).

[0004] Existing technical documents

[0005] Non-patent literature

[0006] Non-Patent Literature 1: Latest Development and Process Optimization Technology of Photoresist Materials (CMC Publishing, Editor-in-Chief: Akira Kawai) Summary of the Invention

[0007] The problem that the invention aims to solve

[0008] However, the wide variety of materials available and the diverse applications of photoresists place a heavy burden on developers working on new photoresists. Furthermore, this problem is not limited to photoresists; it is a common challenge in the development of compositions with numerous material options and diverse applications.

[0009] In view of the above, the object of the present invention is to provide a technique that reduces the workload of developers in developing new compositions.

[0010] Methods for solving problems

[0011] One aspect of the present invention is an information processing system comprising: a storage unit that stores corresponding information, the corresponding information being information that associates material information representing a material of a composition with process conditions in a predetermined process of using the composition and performance information of the composition obtained through the process; a performance estimation unit that obtains the performance information based on the input material information, the process conditions, and the corresponding information; and an output unit that outputs the performance information.

[0012] One aspect of the present invention is an information processing apparatus comprising: a performance estimation unit that reads corresponding information from a storage unit and obtains performance information based on the read material information and process conditions and the corresponding information, wherein the corresponding information is information that associates the material information representing the material of the photoresist, the process conditions in a predetermined process of using the photoresist, and the performance information representing the performance of the photoresist obtained through the process; and an output unit that outputs the performance information.

[0013] One aspect of the present invention is a learning device comprising a learning unit that generates first corresponding information by performing machine learning based on material information representing a material of a photoresist, process conditions in a specified process using the photoresist, and property information representing the physical properties of the photoresist in the process representing the material information and the process conditions.

[0014] One aspect of the present invention is an information processing method, comprising: a performance estimation step, obtaining performance information based on assigning associated corresponding information to material information representing the material of the photoresist, process conditions in a specified process of using the photoresist, and performance information representing the performance of the photoresist obtained through the process; and an output step, outputting the performance information.

[0015] One aspect of the present invention is a program for enabling a computer to function as the aforementioned information processing system.

[0016] One aspect of the present invention is a learning method comprising a learning step in which machine learning is performed based on material information representing the material of the resist and process conditions in a specified process using the resist, and property information representing the physical properties of the resist in the process representing the material information and the process conditions, thereby generating first corresponding information.

[0017] One aspect of the present invention is a program for enabling a computer to function as the aforementioned learning device.

[0018] The effects of the invention

[0019] According to the present invention, the workload of developers in developing new compositions can be reduced. Attached Figure Description

[0020] Figure 1 This is a conceptual diagram used to illustrate the implementation method.

[0021] Figure 2 This is a diagram illustrating an example of the system structure of an information processing system according to an embodiment.

[0022] Figure 3 This is a diagram illustrating an example of learning data in an implementation method.

[0023] Figure 4 This is a graph illustrating an example of regression data in an implementation method.

[0024] Figure 5 This is a diagram illustrating an example of the functional structure of the learning device in the embodiment.

[0025] Figure 6 This is a flowchart illustrating an example of the process performed by the learning device in the embodiment to generate the first model.

[0026] Figure 7 This is a flowchart illustrating an example of the process performed by the learning device in the embodiment to generate the second model.

[0027] Figure 8 This is a diagram illustrating an example of presumed object information in an implementation method.

[0028] Figure 9 This is a diagram illustrating an example of the functional structure of the control unit in an embodiment.

[0029] Figure 10 This is a flowchart illustrating an example of the processing flow performed by the information processing device in the embodiment.

[0030] Figure 11 This is a figure showing the first example of experimental results relating the estimated performance information obtained by the information processing system in the embodiment to the measured performance.

[0031] Figure 12 This is a second example of experimental results showing the relationship between the estimated performance information obtained by the information processing system in the embodiment and the measured performance. Detailed Implementation

[0032] Hereinafter, embodiments of the present invention will be described with reference to the accompanying drawings.

[0033] Figure 1 This is a conceptual diagram used to illustrate the embodiments. More specifically, it is a conceptual diagram used to illustrate the information processing system 100 of the embodiments described later. The information processing system 100 of the embodiments receives material information representing the material of the composition and input process conditions, wherein the process conditions are the process conditions in a prescribed process performed on the composition composed of the material shown in the material information. The composition is, for example, a substance used for patterning an object. More specifically, examples of compositions include photoresist, developer, phase separation structure forming material, etchant, cleaning solution, stripping solution, optical material, nanoimprint material, substrate material, hard mask material, hydrophobic material, separation layer forming composition, adhesive composition, etc. Among these, photoresist is preferred as the composition.

[0034] The photoresist is, for example, a photolithographic photoresist. The photoresist can be either a positive type, where the exposed portion of the photoresist film is soluble in the developer, or a negative type, where the exposed portion of the photoresist film is insoluble in the developer. Furthermore, the photoresist can also be used with any of the following photolithography methods: ArF excimer laser, KrF excimer laser, ghi-ray, F2 excimer laser, EUV (extreme ultraviolet), VUV (vacuum ultraviolet), EB (electron ray), X-ray, and soft X-ray.

[0035] The information processing system 100 obtains performance information based on input material information and process conditions, and pre-stored corresponding information. Performance information represents the performance obtained through a process under the specified process conditions, and is information about the performance of the composition shown in the material information. Performance refers to, for example, the performance of a photoresist used for patterning (hereinafter referred to as "patterning performance"). Patterning performance is, for example, photolithography performance. Photolithography performance is, for example, the dimensional deviation of the pattern.

[0036] The corresponding information indicates the relationship between material information, process conditions, and performance information. The corresponding information includes the first corresponding information and the second corresponding information.

[0037] The first correspondence information is information that associates material information and process conditions with the physical property information of the resist in the process representing the material information and process conditions. The first correspondence information is information pre-obtained by the information processing system 100 through methods such as basic arithmetic operations and machine learning. For example, the first correspondence information is a learned model obtained by performing machine learning on multiple learning data sets, using material information and process conditions as input learning data and physical property information as supervision data.

[0038] A completed learning model is a machine learning model that meets a termination condition at the point in time during the learning process. The termination condition can be any condition related to the end of learning. For example, a termination condition could be that learning has been performed on a specified amount of data, or it could be that the change in the learned parameters is less than a specified amount.

[0039] A machine learning model refers to a machine learning model used in machine learning, including deep learning. A machine learning model can be, for example, a neural network with encoder / decoder capabilities, a convolutional neural network, a gradient boosting decision tree, or reinforcement learning. Learning refers to appropriately adjusting the parameters of the machine learning model. In the case of a neural network, this adjustment can be achieved using algorithms such as backpropagation.

[0040] The second corresponding information is information that associates material information, process conditions, physical property information, and performance information. This second corresponding information is information obtained in advance by the information processing system 100 using methods such as regression analysis. In the case of a photoresist, the second corresponding information is, for example, information that associates performance information with physical property information. This performance information represents the patterning properties of the photoresist after processing according to the process conditions, and is composed of the material shown in the material information. The processing conditions described are, for example, processing using a photoresist. The processing conditions described may be, for example, drying the photoresist by a heating process after performing a prescribed treatment on the photoresist. The processing conditions described may be, for example, a treatment that causes a chemical change in the photoresist after processing the photoresist. The prescribed treatment for the photoresist is, for example, applying the photoresist to the object to be coated. The second type of information, for example, is a regression model obtained through regression analysis methods such as multiple regression, PCA regression (principal component regression), Lasso regression (minimum absolute contraction and selection operator regression), Ridge regression, Elastic Net regression, PLS (partial least squares) regression, and support vector regression. This model uses material information, process conditions, and physical property information as explanatory variables and performance information as the target variable.

[0041] Regarding the processing flow up to the point where the information processing system 100 obtains performance information, the process will be described using first correspondence information and second correspondence information, as follows. Specifically, the information processing system 100 first obtains physical property information based on the input material information, process conditions, and first correspondence information. Next, the information processing system 100 obtains performance information based on the input material information, process conditions, physical property information, and second correspondence information. The first correspondence information is, for example, a learned model (hereinafter referred to as the "first model") that uses material information and process conditions as explanatory variables and physical property information as the target variable. The first correspondence information can also be, for example, a relational database representing the relationship between material information and process conditions, and physical property information representing the physical properties of the resist measured under the process conditions. The second correspondence information is, for example, a regression model (hereinafter referred to as the "second model") that uses material information, process conditions, and physical property information as explanatory variables and performance information as the target variable. The second correspondence information can also be, for example, a relational database representing the relationship between material information, process conditions, physical property information, and performance information.

[0042] Figure 2This diagram illustrates an example of the system structure of the information processing system 100 according to an embodiment. Hereinafter, for ease of understanding, the information processing system 100 will be described using the case where the composition is a photoresist and the properties are patterning properties as an example. Furthermore, the information processing system 100 will be described hereinafter using the case where the first corresponding information is a first model as an example. Furthermore, the information processing system 100 will be described hereinafter using the case where the second corresponding information is a second model as an example.

[0043] The information processing system 100 includes a learning device 1 and an estimation device 2. The learning device 1 learns first corresponding information. The learning device 1 executes a program and includes a control unit 10, which includes a processor 91 (such as a CPU, Central Processing Unit) and a memory 92 connected via a bus. The learning device 1 functions as a device including the control unit 10, an interface unit 1, an input unit 12, a storage unit 13, and an output unit 14 by executing the program. More specifically, the processor 91 reads the program stored in the storage unit 13 and stores the read program in the memory 92. By executing the program stored in the memory 92, the learning device 1 functions as a device including the control unit 10, an interface unit 11, an input unit 12, a storage unit 13, and an output unit 14.

[0044] The interface unit 11 is configured to include a communication interface for connecting the device to the estimation device 2 and external devices. The interface unit 11 communicates with the estimation device 2 and external devices via wired or wireless means.

[0045] The input unit 12 is configured to include input devices such as a mouse, keyboard, and touch panel. The input unit 12 may also be configured as an interface connecting these input devices to this device. The input unit 12 accepts various types of information input to this device. For example, the input unit 12 accepts the input of learning data.

[0046] Storage unit 13 is constructed using a non-volatile computer-readable storage medium such as a magnetic hard disk drive or a semiconductor storage device. Storage unit 13 stores various information related to the learning device 1. Storage unit 13 stores learning data input via input unit 12. Storage unit 13, for example, stores a machine learning model before the termination condition is met. Storage unit 13 stores information that associates learning data with performance information (hereinafter referred to as "regression data").

[0047] Figure 3 This is a diagram illustrating an example of learning data in an implementation method.

[0048] Regarding the learning data, the input-side learning data and the monitoring data are associated with each item. The input-side learning data stores information on materials and process conditions. The monitoring data stores physical property information.

[0049] Figure 4 This is a graph illustrating an example of regression data in an implementation method.

[0050] In terms of regression data, for example, learning data is correlated with performance information. Learning data stores various information such as material information, process conditions, and physical properties.

[0051] Output unit 14 outputs various information. For example, output unit 14 outputs the first corresponding information of the learning result. Output unit 14 is configured to include display devices such as CRT (Cathode Ray Tube) displays, liquid crystal displays, and organic EL (Electro-Luminescence) displays. Output unit 14 may also be configured as an interface for connecting these display devices to this device.

[0052] The control unit 10 controls the operation of each functional unit of the learning device 1. In addition, the control unit 10 generates the first model and the second model.

[0053] Figure 5 This diagram illustrates an example of the functional structure of the control unit 10 in the embodiment. The control unit 10 includes a learned model generation unit 101, a regression model generation unit 102, and a communication control unit 103.

[0054] After learning is complete, the model generation unit 101 reads out multiple learning data stored in the storage unit 13. Based on the multiple learning data, the model generation unit 101 generates a first model. Generating the first model means reading out the machine learning model stored in the storage unit 13 and learning using the multiple learning data until a termination condition is met. The model generation unit 101 then stores the first model in the storage unit 13.

[0055] The regression model generation unit 102 reads the first model and multiple regression data stored in the storage unit 13. Based on the multiple regression data and the first model, the regression model generation unit 102 generates a second model. Generating the second model means performing a prescribed regression analysis on the multiple regression data to obtain a regression model.

[0056] The communication control unit 103 controls the operation of the interface unit 11 and sends the first model generated by the learning model generation unit 101 and the second model generated by the regression model generation unit 102 to the estimation device 2.

[0057] Figure 6 This is a flowchart illustrating an example of the process performed by the learning device 1 in the embodiment to generate the first model.

[0058] After the learning is completed, the model generation unit 101 reads multiple learning data from the storage unit 13 (step S101). Based on the read learning data, the model generation unit 101 performs machine learning to generate the first model (step S102).

[0059] Figure 7 This is a flowchart illustrating an example of the process performed by the learning device 1 in the embodiment to generate the second model.

[0060] The regression model generation unit 102 reads multiple regression data from the storage unit 13 (step S201). The regression model generation unit 102 performs a prescribed regression analysis on the read multiple regression data to generate a second model (step S202).

[0061] Back Figure 2 The presumption device 2 executes a program and includes a control unit 20, which includes a processor 93 (such as a CPU, Central Processing Unit) and a memory 94 connected via a bus. The presumption device 2 functions as a device including the control unit 20, interface unit 21, input unit 22, storage unit 23, and output unit 24 through program execution. More specifically, the processor 93 reads the program stored in the storage unit 23 and stores the read program in the memory 94. The processor 93 executes the program stored in the memory 94, thereby enabling the presumption device 2 to function as a device including the control unit 20, interface unit 21, input unit 22, storage unit 23, and output unit 24.

[0062] The interface unit 21 is configured to include a communication interface for connecting the device to the learning device 1 and external devices. The interface unit 21 communicates with the learning device 1 and external devices via wired or wireless means.

[0063] The input unit 22 is configured to include input devices such as a mouse, keyboard, and touch panel. The input unit 22 may also be configured as an interface connecting these input devices to this device. The input unit 22 accepts various types of information input to this device. For example, the input unit 22 accepts input of estimated object information. Estimated object information is information that associates estimated object material information with estimated object process conditions. Estimated object material information is material information representing the material of the composition, which is the object to which the estimation device 2 estimates the patterning performance. Estimated object process conditions are process conditions for obtaining the composition, which is the object to which the estimation device 2 estimates the patterning performance.

[0064] The storage unit 23 is constructed using a non-volatile computer-readable storage medium such as a magnetic hard disk drive or a semiconductor storage device. The storage unit 23 stores various information related to the estimation device 2. For example, the storage unit 23 stores corresponding information. That is, for example, the storage unit 23 stores the first model and the second model. The storage unit 23 also stores estimation object information input via the input unit 22.

[0065] Figure 8 This is a diagram illustrating an example of presumed object information in an implementation method.

[0066] Regarding the information on the presumed object, the material information of the presumed object is associated with each item of the process conditions of the presumed object.

[0067] Output unit 24 outputs various information. For example, output unit 24 outputs performance information as the estimation result of estimation device 2. Output unit 24 is configured to include display devices such as CRT (Cathode Ray Tube) displays, liquid crystal displays, and organic EL (Electro-Luminescence) displays. Output unit 24 may also be configured as an interface connecting these display devices to this device.

[0068] Based on the corresponding information, the control unit 20 estimates the patterning performance of the resist composed of the material shown in the estimated object material information, obtained by the process under the estimated object process conditions.

[0069] Figure 9 This diagram illustrates an example of the functional structure of the control unit 20 in the embodiment. The control unit 20 includes a performance estimation unit 201 and an output control unit 202.

[0070] The performance estimation unit 201 reads the estimation object information and corresponding information stored in the storage unit 23. Based on the corresponding information, the performance estimation unit 201 obtains performance information representing the performance obtained by the process under the process conditions shown in the estimation object information, and the performance of the composition shown in the estimation object information.

[0071] The output control unit 202 controls the operation of the output unit 24, causing the output unit 24 to output the performance information obtained by the performance estimation unit 201.

[0072] Figure 10 This is a flowchart illustrating an example of the process performed by the estimation device 2 in the embodiment.

[0073] Storage unit 23 stores the estimated object information input via input unit 22 (step S301). Next, performance estimation unit 201 reads the estimated object information and corresponding information stored in storage unit 23 (step S302). Next, performance estimation unit 201 estimates the performance of the composition shown in the estimated object information based on the corresponding information, obtained through the process under the process conditions shown in the estimated object information (step S303). For example, performance estimation unit 201 first obtains the physical property information corresponding to the estimated object information based on the estimated object information and the first corresponding information. Next, performance estimation unit 201 obtains the performance information corresponding to the estimated object information and the physical property information corresponding to the estimated object information based on the estimated object information, the physical property information corresponding to the estimated object information, and the second corresponding information. The performance information obtained in this way is the estimation result of the processing in step S303. After step S303, output control unit 202 causes output unit 24 to output the performance of the estimation result (step S304).

[0074] Figure 11 This is a figure showing the first example of experimental results relating the estimated performance information of the information processing system 100 in the embodiment to the measured performance.

[0075] Figure 11 The horizontal axis represents the measured value, and the vertical axis represents the estimated value. Figure 11 The RMSE (Root Mean Squared Error) is shown to be 0.1747. Figure 11 The correlation coefficient is shown to be 0.8863. Figure 11 The coefficient of determination is shown to be 0.7855. The RMSE is 0.1747, the correlation coefficient is 0.8863, and the coefficient of determination is 0.7855, indicating that the indicator information processing system 100 is able to reliably estimate the performance of new compositions with high accuracy.

[0076] Figure 12 This is a second example of experimental results showing the relationship between the estimated performance information of the information processing system 100 in the embodiment and the measured performance.

[0077] Figure 12 The horizontal axis represents the measured value, and the vertical axis represents the estimated value. Figure 12 Shown in Figure 11 The result is the result after adding more data to the existing data. Figure 12 This also demonstrates that the information processing system 100 can reliably estimate performance with high accuracy in the development of new compositions.

[0078] The information processing system 100 configured in this way estimates the properties of a composition made of materials shown in the object material information, obtained through processing under the specified process conditions, based on corresponding information. Therefore, it can reduce the workload of developers creating new compositions.

[0079] (Modified Example)

[0080] Material information may include, for example, the surface area of ​​molecules that constitute the material, the volume of molecules that constitute the material, the molecular weight of molecules that constitute the material, the value representing the charge density distribution of molecules that constitute the material, the value representing the molecular descriptor, the molar heat capacity of the material, the coefficient of thermal expansion of the material, the dielectric constant of the material, the surface tension of the material, the viscosity of the material, the refractive index of the material, the transmittance of the material, the absorbance of the material, the density of the material, the glass transition temperature of the material, the melting point of the material, the partition coefficient of the material, the acidity constant of the material, the solubility parameter of the material, the ABC parameters of the material described in Reference 1 below, and the activation energy of the deprotection reaction of the protecting group of the material.

[0081] Reference 1: FHDill, ARNeureuther, JATuttle and EJWalker "Modelingprojection printing of positive photoresists", IEEE Trans.Electron.Dev., 22, (1975), pp.456-464

[0082] The physical property information can be any information used to output performance information based on the second corresponding information. For example, physical property information could be information about the physical properties of the resist before and / or after processing under certain process conditions, and the resist as shown in the material information. More specifically, physical property information could be information about the characteristics of the protective film formed on a specified object after the resist is processed. Resist processing could be, for example, the process of coating the resist onto a coating object. In this case, the specified object to which the protective film is formed is the coating object to which the resist is coated. More specifically, physical property information could be information about the characteristics of the protective film formed on a specified object after the resist is processed and dried by a heating process. Physical property information could also be information about the characteristics of the protective film formed on a specified object after the resist undergoes a chemical change during processing.

[0083] Physical property information may also include, for example, at least one selected from the following: surface area of ​​molecules forming the material; volume of molecules forming the material; molecular weight of molecules forming the material; value representing the charge density distribution of molecules forming the material; value representing the molecular descriptor; molar heat capacity of the material; coefficient of thermal expansion of the material; dielectric constant of the material; surface tension of the material; viscosity of the material; refractive index of the material; transmittance of the material; absorbance of the material; density of the material; glass transition temperature of the material; melting point of the material; boiling point of the material; ignition point of the material; vapor pressure of the material; Darcy parameter of the material; pKa value of the material; decomposition point of the material; partition coefficient of the material; acidity constant of the material; solubility parameter of the material; as described in Reference 1. The material's ABC parameters; the activation energy of the deprotection reaction of the material's protecting groups; the acid diffusion length of the material; the molecular weight of the polymer that forms the material; the molecular weight dispersion of the polymer that forms the material; information indicating the composition ratio of the polymeric materials (polymer units) that form the material; information indicating the amount of added components such as photoacid generator (PAG) and photodisintegrating base (PDB); information indicating the dissolution rate of the resist film in the unexposed state when the composition is a photoresist; information indicating the dissolution rate of the resist film in the exposed state when the composition is a photoresist; information selected from at least one of the following: information obtained by comparing the state of the resist film before and after exposure when the composition is a photoresist. Information obtained by comparing the state of the resist film before and after exposure when the composition is a photoresist, such as changes in film thickness, weight, film density, dissolution rate, refractive index, etc.

[0084] Process conditions may include, for example, at least one of the following: coating thickness, heat treatment conditions, exposure conditions, electron microscope observation conditions, mask information, and NILS (Normalized Image Log-Slope). Mask information is information related to the photomask. Heat treatment conditions may include, for example, the temperature for PAB (Post Applied Bake), the temperature for PEB (Post Exposure Bake), or the temperature and time conditions for baking PAB, PEB, etc. Electron microscope observation conditions specifically include magnification, current value, accelerating voltage, frame rate, etc.

[0085] Patterning performance can also be selected from at least one of the following: sensitivity, CDU (Critical Dimension Uniformity), limiting resolution, LER (Line Edge Roughness), LWR (Line Width Roughness), DOF (Depth of Focus), exposure margin (EL margin), MEF (Mask Error Factor), rectangularity of the pattern cross-sectional shape, and roundness of the holes in the contact hole pattern (CH pattern).

[0086] It should be noted that the first corresponding information does not necessarily have to be the first model, but it is preferred to be a nonlinear model that represents the relationship between material information and process conditions and physical property information that represents the physical properties of the resist determined by the process based on the material information and process conditions.

[0087] It should be noted that the second corresponding information does not necessarily have to be the second model, but it is preferable to obtain information through a method that has higher extrapolation accuracy than the method used to generate the first corresponding information. For example, the second corresponding information is preferably a linear model representing the relationship between material information, process conditions and physical property information and performance information representing patterning performance. As a linear model, it can also be, for example, multiple regression, PCA regression (principal component regression), Lasso regression (minimum absolute shrinkage and selection operator regression), Ridge regression, Elastic Net regression, PLS (partial least squares) regression, and support vector regression.

[0088] In one implementation, the learning-complete model generation unit 101 generates a first model, but the first model is ultimately just one example of the first corresponding information; the learning-complete model generation unit 101 is a functional unit that generates the first corresponding information. Similarly, in another implementation, the regression model generation unit 102 generates a second model, but the second model is ultimately just one example of the second corresponding information; the regression model generation unit 102 is a functional unit that generates the second corresponding information. Furthermore, in another implementation, the performance estimation unit 201 estimates performance information based on the first model and the second model. However, the first model and the second model are ultimately just one example of the first and second corresponding information, respectively; the performance estimation unit 201 is a functional unit that estimates performance information based on the first and second corresponding information.

[0089] It should be noted that learning data can also be input from an external device via interface 11. Predicted object information can also be input from an external device via interface 21.

[0090] It should be noted that all or part of the functions of learning device 1 and estimation device 2 can also be implemented using hardware such as ASIC (Application Specific Integrated Circuit), PLD (Programmable Logic Device), and FPGA (Field Programmable Gate Array). The program can also be recorded on a computer-readable recording medium. Such media include removable media such as floppy disks, optical disks, ROMs, CD-ROMs, and storage devices such as hard drives built into computer systems. The program can be transmitted via telecommunications lines.

[0091] It should be noted that the learning device 1 and the estimation device 2 can also be installed using multiple information processing devices that are communicatively connected via a network. In this case, the functional units of the learning device 1 and the estimation device 2 can also be distributed and installed in multiple information processing devices. For example, the learning completed model generation unit 101 and the regression model generation unit 102 can also be installed in different information processing devices.

[0092] The learning device 1 and the estimation device 2 do not necessarily have to be installed in different housings. The learning device 1 and the estimation device 2 can also be a device consisting of a single housing. In addition, the estimation device 2 does not necessarily have to read the corresponding information from the storage unit 23, but can also read it from the storage unit 13 via the interface unit 11 and the interface unit 21.

[0093] It should be noted that the model generation unit 101 after learning is an example of a learning unit.

[0094] The embodiments of the present invention have been described in detail above with reference to the accompanying drawings. However, the specific structure is not limited to these embodiments, and may include designs that do not depart from the spirit and scope of the present invention. Therefore, the scope of the present invention is defined only by the claims and their equivalents.

[0095] Explanation of reference numerals in the attached figures

[0096] 100 Information processing system, 1 learning device, 2 estimation device, 10 control unit, 11 interface unit, 12 input unit, 13 storage unit, 14 output unit, 20 control unit, 21 interface unit, 22 input unit, 23 storage unit, 24 output unit, 91 processor, 92 memory, 93 processor, 94 memory, 101 learning completed model generation unit, 102 regression model generation unit, 103 communication control unit.

Claims

1. An information processing system, which possesses: The storage unit stores corresponding information, which is information that associates material information representing the material of the composition with process conditions in the process of using the composition and performance information of the composition obtained through the process. The performance estimation unit obtains the performance information based on the input material information, process conditions, and corresponding information; as well as The output unit outputs the performance information. The composition is a resist for patterning objects, and the performance information indicates the performance of the composition in the case of patterning. The storage unit stores the first corresponding information and the second corresponding information as the corresponding information. The first corresponding information is information that associates the material information, the process conditions, and the physical property information of the resist in the process representing the process conditions. The second corresponding information is information that associates the material information, the process conditions, the physical property information, and the performance information. The performance estimation unit outputs the physical property information based on the input material information, process conditions, and the first corresponding information, and obtains the performance information based on the output physical property information, the material information, process conditions, and the second corresponding information.

2. The information processing system according to claim 1, wherein, The first corresponding information is a nonlinear model that uses the material information and the process conditions as explanatory variables and the physical property information as the target variable.

3. The information processing system according to claim 1, wherein, The second corresponding information is represented by a linear model that uses the material information, the process conditions, and the physical property information as explanatory variables and the performance information as the target variable.

4. The information processing system according to claim 1, comprising a learning unit, The learning unit performs machine learning based on the material information and process conditions, and the physical property information of the resist in the process representing the material information and process conditions, thereby generating the first corresponding information.

5. The information processing system according to claim 4, wherein, The second corresponding information is obtained by a method whose extrapolation accuracy is higher than that of the method by which the learning unit generates the first corresponding information.

6. The information processing system according to claim 1, wherein, The physical property information refers to the physical properties of the resist before and / or after being treated under the process conditions, and is the resist of the material indicated in the material information.

7. The information processing system according to claim 1, wherein, The performance information refers to information representing the photolithographic properties of the resist.

8. The information processing system according to claim 6, wherein, The physical property information refers to the characteristics of the protective film formed on the specified object as a result of the treatment of the resist.

9. The information processing system according to claim 8, wherein, The physical property information refers to the characteristics of the resist being treated and dried through a heating process, resulting in a protective film formed on a specified object.

10. The information processing system according to claim 8, wherein, The physical property information refers to the characteristics of the protective film formed on the specified object after the resist has been treated and undergone a chemical change.

11. An information processing device, comprising: A performance estimation unit reads corresponding information from a storage unit and obtains performance information based on the read material information, process conditions, and corresponding information. The corresponding information is information that associates the material information representing the material of the composition, the process conditions in a specified process using the composition, and the performance information representing the performance of the composition obtained through the process. The output unit outputs the performance information. The composition is a resist for patterning objects, and the performance information indicates the performance of the composition in the case of patterning. The storage unit stores the first corresponding information and the second corresponding information as the corresponding information. The first corresponding information is information that associates the material information, the process conditions, and the physical property information of the resist in the process representing the process conditions. The second corresponding information is information that associates the material information, the process conditions, the physical property information, and the performance information. The performance estimation unit outputs the physical property information based on the input material information, process conditions, and the first corresponding information, and obtains the performance information based on the output physical property information, the material information, process conditions, and the second corresponding information.

12. A learning device, comprising a learning section, The learning unit generates the first corresponding information by performing machine learning based on material information representing the material of the resist, process conditions in a specified process using the resist, and physical property information representing the physical properties of the resist in the process of the material information and process conditions. The physical property information refers to the characteristics of the protective film formed on the specified object as a result of the treatment of the resist. The physical property information associated with the material information and process conditions in the first corresponding information is used to output performance information representing the performance of the resist obtained through the process based on the second corresponding information. The second corresponding information is information that associates the physical property information with the performance information. Based on the input material information, process conditions, and first corresponding information, the physical property information is output. Based on the output physical property information, the material information, process conditions, and second corresponding information, the performance information is obtained.

13. Information processing methods, including: The performance estimation step involves obtaining the performance information by assigning associated corresponding information to material information representing the material of the composition, process conditions in a specified process using the composition, and performance information representing the performance of the composition obtained through the process; and The output step is to output the performance information. The composition is a resist for patterning objects, and the performance information indicates the performance of the composition in the case of patterning. The corresponding information includes a first corresponding information and a second corresponding information. The first corresponding information is information that associates the material information, the process conditions, and the physical property information of the resist in the process representing the process conditions. The second corresponding information is information that associates the material information, the process conditions, the physical property information, and the performance information. In the performance estimation step, the physical property information is output based on the input material information, process conditions, and the first corresponding information. The performance information is obtained based on the output physical property information, the material information, process conditions, and the second corresponding information.

14. A computer-readable storage medium containing a program for enabling a computer to function as an information processing system according to any one of claims 1 to 10.

15. Learning methods, including learning steps. In this learning step, machine learning is performed based on material information representing the resist material, process conditions in the specified process of using the resist, and physical property information representing the physical properties of the resist in the process of the material information and process conditions, thereby generating the first corresponding information. The physical property information refers to the characteristics of the protective film formed on the specified object as a result of the treatment of the resist. The physical property information associated with the material information and process conditions in the first corresponding information is used to output performance information representing the performance of the resist obtained through the process based on the second corresponding information. The second corresponding information is information that associates the physical property information with the performance information. Based on the input material information, process conditions, and first corresponding information, the physical property information is output. Based on the output physical property information, the material information, process conditions, and second corresponding information, the performance information is obtained.

16. A computer-readable storage medium containing a program for enabling a computer to function as the learning device of claim 12.

Images