Learning device, information processing device, substrate processing device, substrate processing system, learning method, and processing condition determination method

Abstract

To perform machine learning of a condition which is changed in accordance with the lapse of time for processing a substrate.SOLUTION: A learning device comprises: an examination data acquisition part 261 that acquires a first processing amount indicating a difference in film thickness between before and after a processing of a film, after the processing of the film formed on a substrate by driving a substrate processing apparatus under a processing condition including a fluctuation condition indicating a relative position of a nozzle fluctuated with respect to the substrate in accordance with the lapse of time; a first conversion part 263 that converts a fluctuation condition into compression data indicating an operation amount related to the nozzle with respect to each of a plurality of movement divisions obtained by dividing a movement range of the nozzle into a number smaller than the number of pieces of data on the fluctuation condition in a scanning period from when a nozzle operation is started to when it is terminated; and a prediction device generation part 265 that generates a learning model for estimating a second processing amount by performing machine learning of the learning data containing the compression data and the first processing amount corresponded to the processing condition.SELECTED DRAWING: Figure 4

Description

Technical Field

[0001] The present invention relates to a learning device, an information processing device, a substrate processing device, a substrate processing system, a learning method, and a processing condition determination method, and to a learning device that generates a learning model for simulating processing according to processing conditions by a substrate processing device, an information processing device that determines processing conditions using the learning model, a substrate processing device including the information processing device, a substrate processing system including the learning device and the information processing device, a learning method executed by the learning device, and a processing condition determination method executed by the information processing device.

Background Art

[0002] In the semiconductor manufacturing process, there is a cleaning process. In the cleaning process, the film thickness of the film formed on the substrate is adjusted by an etching process of applying a chemical solution to the substrate. In this film thickness adjustment, it is important to perform the etching process so that the surface of the substrate becomes uniform, or to flatten the surface of the substrate by the etching process. When discharging the etching solution from the nozzle to a part of the substrate, it is necessary to move the nozzle in the radial direction with respect to the substrate. However, the etching process is a complicated process in which the amount of film processed varies depending on the difference in the operation of moving the nozzle. Also, the amount of film processed by the etching process is determined after processing the substrate. Therefore, the work of setting the operation of moving the nozzle requires trial and error by engineers. It takes a great deal of cost and time to determine the optimal operation of the nozzle.

[0003] Japanese Patent Application Laid-Open No. 2021-108367 describes a device that determines scan speed information from a target processing amount using a learned model obtained by machine learning with learning data having "input" as the processing amount (etching amount) and "output" as the scan speed information. According to this technique, one scan speed information is determined from the target processing amount.

Prior Art Documents

Patent Documents

[0004] [Patent Document 1] Japanese Patent Publication No. 2021-108367 [Overview of the Initiative] [Problems that the invention aims to solve]

[0005] On the other hand, it is desirable to make the nozzle movement more complex. The nozzle movement represents time-series data indicating the position that changes over time. Making the nozzle movement more complex shortens the sampling interval, thus increasing the dimensionality of the time-series data. In general, as the dimensionality of the training data increases, the amount of data required for machine learning increases exponentially. Therefore, as the dimensionality of the training data increases, it becomes difficult to optimize the learning model obtained by machine learning. Also, since etching is a complex process, there may not be just one nozzle movement suitable for the target processing volume, but rather multiple such movements may exist.

[0006] One of the objectives of the present invention is to provide a learning device, a learning method, and a substrate processing system suitable for machine learning the conditions that change over time when processing a substrate.

[0007] Another object of the present invention is an information processing apparatus, a substrate processing apparatus, a substrate processing system, and an information processing apparatus capable of presenting multiple processing conditions for the processing results of a complex process for processing a substrate. The objective is to provide a method for determining processing conditions. [Means for solving the problem]

[0008] A learning device according to one aspect of the present invention includes: an experimental data acquisition unit that acquires a first processing amount indicating the difference in film thickness before and after processing a film formed on a substrate by driving a substrate processing device that supplies a processing liquid to a substrate by moving a nozzle that supplies a processing liquid to the substrate with processing liquid to the substrate under processing conditions that include a fluctuation condition indicating the relative position of the nozzle with respect to the substrate which fluctuates over time; a conversion unit that converts the fluctuation condition into compressed data indicating the amount of operation of the nozzle for each of a plurality of movement intervals obtained by dividing the movement range of the nozzle during the scanning period from when the nozzle operation in which the substrate processing device moves the nozzle with respect to the substrate ends into a number smaller than the number of data points for the fluctuation condition; and a model generation unit that performs machine learning on learning data including the compressed data and the first processing amount corresponding to the processing conditions to generate a learning model that estimates a second processing amount indicating the difference in film thickness before and after processing a film formed on a substrate before it is processed by the substrate processing device.

[0009] An information processing apparatus according to another aspect of the present invention is an information processing apparatus for managing a substrate processing apparatus, wherein the substrate processing apparatus processes a film formed on a substrate by supplying a processing liquid to the substrate on which a film has been formed, using processing conditions that include a fluctuation condition indicating the relative position of a nozzle that fluctuates with respect to the substrate over time, and a conversion unit that converts the fluctuation condition into compressed data indicating the amount of operation of the nozzle for each of a plurality of movement intervals obtained by dividing the movement range of the nozzle during the scanning period from when the nozzle operation in which the substrate processing apparatus moves the nozzle relative to the substrate ends into a number smaller than the number of data points for the fluctuation condition, and for the film formed on the substrate before the film processing by the substrate processing apparatus, the film thickness before and after the film processing The system includes a processing condition determination unit that determines processing conditions for driving a substrate processing apparatus using a learning model that estimates a second processing amount that shows the difference, the learning model is an inference model that has been machine-trained on learning data that includes compressed data that has been converted in the same way as the conversion unit and a first processing amount that shows the difference in film thickness before and after processing of the film formed on the substrate processed by the substrate processing apparatus, the processing condition determination unit provides the compressed data from which the provisional fluctuation conditions have been converted by the conversion unit to the learning model, and determines the processing conditions including the provisional fluctuation conditions as the processing conditions for driving the substrate processing apparatus if the second processing amount estimated by the learning model satisfies the acceptable conditions.

[0010] A substrate processing system according to yet another aspect of the present invention is a substrate processing system for managing a substrate processing apparatus, comprising a learning device and an information processing device, wherein the substrate processing apparatus processes a film formed on a substrate by supplying a processing liquid to the substrate on which the film has been formed, under processing conditions that include a variation condition indicating the relative position of a nozzle that changes with respect to the substrate over time, and the learning device includes an experimental data acquisition unit that acquires a first processing amount indicating the difference in film thickness before and after processing the film after driving the substrate processing apparatus with the processing conditions, and an experimental data acquisition unit that acquires a first processing amount indicating the difference in film thickness before and after processing the film, and the variation condition is the operation amount of the nozzle for each of a plurality of movement intervals obtained by dividing the movement range in which the nozzle moves during the scanning period from when the nozzle operation in which the substrate processing apparatus moves the nozzle relative to the substrate starts to when it ends into a number smaller than the number of data points for the variation condition. The information processing device comprises a first conversion unit that converts the data into compressed data, and a model generation unit that uses machine learning on training data including the compressed data from which the variable conditions have been converted by the first conversion unit and a first processing amount corresponding to the processing conditions to generate a learning model that estimates a second processing amount indicating the difference in film thickness before and after processing for a film formed on a substrate before processing by the substrate processing device. The information processing device comprises a second conversion unit identical to the first conversion unit and a processing condition determination unit that uses the learning model generated by the learning device to determine processing conditions for driving the substrate processing device. The processing condition determination unit provides the conversion result from which the provisional variable conditions have been converted by the second conversion unit to the learning model, and determines the processing conditions including the provisional variable conditions as the processing conditions for driving the substrate processing device if the second processing amount estimated by the learning model satisfies the acceptable conditions.

[0011] A learning method according to yet another aspect of the present invention involves having a computer perform the following steps: moving a nozzle that supplies a processing liquid to a substrate on which a film has been formed, and driving the substrate processing apparatus that supplies the processing liquid to the substrate with processing conditions that include a fluctuation condition indicating the relative position of the nozzle with respect to the substrate which fluctuates over time, thereby processing the film formed on the substrate, and then obtaining a first processing amount indicating the difference in film thickness before and after processing the film; converting the fluctuation condition into compressed data indicating the amount of movement for the nozzle for each of a plurality of movement intervals obtained by dividing the movement range of the nozzle during the scanning period from when the nozzle movement of the substrate processing apparatus starts to when it ends into a number smaller than the number of data points for the fluctuation condition; and machine learning the training data including the compressed data and the first processing amount corresponding to the processing conditions to generate a learning model that estimates a second processing amount indicating the difference in film thickness before and after processing the film for a film formed on a substrate before it is processed by the substrate processing apparatus.

[0012] A method for determining processing conditions according to yet another aspect of the present invention is a method for determining processing conditions executed by a computer that manages a substrate processing apparatus, wherein the substrate processing apparatus processes a film formed on a substrate by supplying a processing liquid to the substrate on which a film has been formed, using processing conditions that include a variable condition indicating the relative position of a nozzle that changes with respect to the substrate over time, and converts the variable condition into compressed data indicating the amount of movement of the nozzle for each of a plurality of movement intervals obtained by dividing the movement range of the nozzle during the scanning period from when the nozzle operation in which the substrate processing apparatus moves the nozzle relative to the substrate to when it ends into a number smaller than the number of data points for the variable condition, and processes the film formed on the substrate before the film processing is performed by the substrate processing apparatus. The process includes determining processing conditions for driving a substrate processing apparatus using a learning model that estimates a second processing amount indicating the difference in film thickness before and after processing. The learning model is an inference model that has been machine-trained on training data that includes compressed data that has undergone the same transformation as the transformation process and a first processing amount indicating the difference in film thickness before and after processing of the film formed on the substrate processed by the substrate processing apparatus. The process for determining processing conditions is to provide the learning model with compressed data into which the provisional fluctuation conditions have been transformed by the transformation process, and if the second processing amount estimated by the learning model satisfies the acceptable conditions, the processing conditions including the provisional fluctuation conditions are determined as the processing conditions for driving the substrate processing apparatus. [Effects of the Invention]

[0013] We can provide a learning device, a learning method, and a substrate processing system suitable for machine learning to process substrate conditions that change over time.

[0014] Furthermore, it is possible to provide an information processing device, a substrate processing device, a substrate processing system, and a method for determining processing conditions that can present multiple processing conditions for the processing results of a complex process for processing substrates. [Brief explanation of the drawing]

[0015] [Figure 1]It is a diagram for explaining the configuration of a substrate processing system according to an embodiment of the present invention. [Figure 2] It is a diagram showing an example of the configuration of an information processing device. [Figure 3] It is a diagram showing an example of the configuration of a learning device. [Figure 4] It is a diagram showing an example of the functional configuration of a substrate processing system in one of the present embodiments of the present invention. [Figure 5] It is a diagram for explaining the change in the relative position of the nozzle with respect to the substrate. [Figure 6] It is a diagram showing an example of the operation pattern of the nozzle. [Figure 7] It is a diagram showing an example of film thickness characteristics. [Figure 8] It is a diagram for explaining a divided region. [Figure 9] It is a diagram showing an example of compressed data. [Figure 10] It is a diagram for explaining a predictor. [Figure 11] It is a flowchart showing an example of the flow of predictor generation processing. [Figure 12] It is a flowchart showing an example of the flow of processing condition determination processing. [Figure 13] It is a flowchart showing an example of the flow of compressed data generation processing. [Figure 14] It is a flowchart showing an example of the flow of additional learning processing. [Figure 15] It is a diagram showing an example of the processing liquid supply amount that changes over time. [Figure 16] It is a diagram showing another example of compressed data.

Embodiments for Carrying Out the Invention

[0016] Hereinafter, a substrate processing system according to one embodiment of the present invention will be described in detail with reference to the drawings. In the following description, "substrate" refers to semiconductor substrates (semiconductor wafers), substrates for FPDs (Flat Panel Displays) such as liquid crystal display devices or organic EL (Electro Luminescence) display devices, substrates for optical discs, substrates for magnetic discs, substrates for magneto-optical discs, substrates for photomasks, ceramic substrates, or substrates for solar cells.

[0017] 1. Overall configuration of the substrate processing system Figure 1 is a diagram illustrating the configuration of a substrate processing system according to one embodiment of the present invention. The substrate processing system 1 in Figure 1 includes an information processing device 100, a learning device 200, and a substrate processing device 300. The learning device 200 is, for example, a server, and the information processing device 100 is, for example, a personal computer.

[0018] The learning device 200 and the information processing device 100 are used to manage the substrate processing device 300. Note that the substrate processing device 300 managed by the learning device 200 and the information processing device 100 is not limited to one unit; multiple substrate processing devices 300 may be managed.

[0019] In the substrate processing system 1 according to this embodiment, the information processing device 100, the learning device 200, and the substrate processing device 300 are connected to each other by wired or wireless communication lines or a communication network. The information processing device 100, the learning device 200, and the substrate processing device 300 are each connected to a network and are capable of sending and receiving data to and from each other. The network may be, for example, a local area network (LAN) or a wide area network (WAN). Alternatively, the network may be the internet. Furthermore, the information processing device 100 and the substrate processing device 300 may be connected by a dedicated communication network. The network connection may be wired or wireless.

[0020] Furthermore, the learning device 200 does not necessarily need to be connected to the substrate processing device 300 and the information processing device 100 by a communication line or communication network. In this case, data generated by the substrate processing device 300 may be passed to the learning device 200 via a recording medium. Alternatively, data generated by the learning device 200 may be passed to the information processing device 100 via a recording medium.

[0021] The substrate processing apparatus 300 is equipped with a display device, an audio output device, and an operating unit (not shown). The substrate processing apparatus 300 is operated according to predetermined processing conditions (processing recipe) of the substrate processing apparatus 300.

[0022] 2. Overview of substrate processing equipment The substrate processing apparatus 300 comprises a control device 10 and a plurality of substrate processing units WU. The control device 10 controls the plurality of substrate processing units WU. The plurality of substrate processing units WU process the substrate by supplying a constant flow rate of processing liquid to the substrate W on which a film has been formed. In this embodiment, the substrate W to be processed has a diameter of 300 mm, but the present invention is not limited thereto. The processing liquid includes an etching solution, and the substrate processing units WU perform the etching process. The etching solution is a chemical solution. The etching solution is, for example, nitric acid. These are a mixture of hydrofluoric acid (HF) and nitric acid (HNO3), hydrofluoric acid, buffered hydrofluoric acid (BHF), ammonium fluoride, HFEG (a mixture of hydrofluoric acid and ethylene glycol), or phosphoric acid (H3PO4).

[0023] The substrate processing unit WU comprises a spin chuck SC, a spin motor SM, a nozzle 311, and a nozzle moving mechanism 301. The spin chuck SC holds the substrate W horizontally. The substrate W is held in the spin chuck SC such that the center of the substrate W coincides with the first rotation axis AX1 of the spin motor SM. The spin motor SM has a first rotation axis AX1. The first rotation axis AX1 extends in the vertical direction. The spin chuck SC is attached to the upper end of the first rotation axis AX1 of the spin motor SM. When the spin motor SM rotates, the spin chuck SC rotates around the first rotation axis AX1. The spin motor SM is a stepping motor. The substrate W held in the spin chuck SC rotates around the first rotation axis AX1. Therefore, the rotation speed of the substrate W is the same as the rotation speed of the stepping motor. If an encoder that generates a rotation speed signal indicating the rotation speed of the spin motor is provided, the rotation speed of the substrate W may be obtained from the rotation speed signal generated by the encoder. In this case, the spin motor SM can use a motor other than a stepping motor.

[0024] The nozzle 311 supplies etching solution to the substrate W. The nozzle 311 receives etching solution from an etching solution supply unit (not shown) and discharges the etching solution toward the rotating substrate W.

[0025] The nozzle moving mechanism 301 moves the nozzle 311 in a substantially horizontal direction. Specifically, the nozzle moving mechanism 301 includes a nozzle motor 303 having a second rotation axis AX2 and a nozzle arm 305. The nozzle motor 303 is positioned so that the second rotation axis AX2 is aligned substantially vertically. The nozzle arm 305 has a linear longitudinal shape. One end of the nozzle arm 305 is attached to the upper end of the second rotation axis AX2 such that the longitudinal direction of the nozzle arm 305 is different from that of the second rotation axis AX2. The nozzle 311 is attached to the other end of the nozzle arm 305 so that its discharge port faces downward.

[0026] When the nozzle motor 303 operates, the nozzle arm 305 rotates in the horizontal plane about the second rotation axis AX2. As a result, the nozzle 311 attached to the other end of the nozzle arm 305 moves horizontally (rotates) about the second rotation axis AX2. The nozzle 311 discharges etching solution toward the substrate W while moving horizontally. The nozzle motor 303 is, for example, a stepping motor.

[0027] The control device 10 includes a CPU (Central Processing Unit) and memory, and the CPU controls the entire substrate processing device 300 by executing a program stored in the memory. The control device 10 controls the spin motor SM and the nozzle motor 303.

[0028] The learning device 200 receives experimental data from the substrate processing device 300, uses the experimental data to train a learning model, and outputs the trained learning model to the information processing device 100.

[0029] The information processing device 100 uses a pre-trained model to determine the processing conditions for the substrate that the substrate processing device 300 is scheduled to process. The information processing device 100 outputs the determined processing conditions to the substrate processing device 300.

[0030] Figure 2 shows an example of the configuration of an information processing device. Referring to Figure 2, the information processing device 100 consists of a CPU 101, RAM (random access memory) 102, ROM (read-only memory) 103, storage device 104, operation unit 105, display device 106, and input / output interface. It is comprised of (interface) 107. The CPU 101, RAM 102, ROM 103, storage device 104, operation unit 105, display device 106, and input / output I / F 107 are connected to the bus 108.

[0031] RAM 102 is used as the working area for CPU 101. ROM 103 stores the system program. Storage device 104 includes a storage medium such as a hard disk or semiconductor memory and stores the program. The program may also be stored in ROM 103 or other external storage devices.

[0032] A CD-ROM 109 is removable from the storage device 104. The recording medium for storing the program executed by the CPU 101 is not limited to the CD-ROM 109, but may also be an optical disc (MO (Magnetic Optical Disc) / MD (Mini Disc) / DVD (Digital Versatile Disc)), an IC card, an optical card, a mask ROM, an EPROM (Erasable Programmable ROM), or other semiconductor memory. Furthermore, the CPU 101 may download a program from a computer connected to the network and store it in the storage device 104, or a computer connected to the network may write a program to the storage device 104, load the program stored in the storage device 104 into the RAM 102, and execute it on the CPU 101. The program referred to here includes not only programs that can be directly executed by the CPU 101, but also source programs, compressed programs, encrypted programs, etc.

[0033] The operation unit 105 is an input device such as a keyboard, mouse, or touch panel. The user can give predetermined instructions to the information processing device 100 by operating the operation unit 105. The display device 106 is a display device such as a liquid crystal display device, and displays a GUI (Graphical User Interface) or the like to receive instructions from the user. The input / output I / F 107 is connected to a network.

[0034] Figure 3 shows an example of the configuration of a learning device. Referring to Figure 3, the learning device 200 consists of a CPU 201, RAM 202, ROM 203, storage device 204, operation unit 205, display device 206, and input / output I / F 207. The CPU 201, RAM 202, ROM 203, storage device 204, operation unit 205, display device 206, and input / output I / F 207 are connected to a bus 208.

[0035] RAM202 is used as the working area for CPU201. ROM203 stores the system program. Storing device204 includes a storage medium such as a hard disk or semiconductor memory and stores the program. The program may also be stored in ROM203 or other external storage devices. A CD-ROM209 is removable from storage device204.

[0036] The control unit 205 is an input device such as a keyboard, mouse, or touch panel. The input / output interface 207 is connected to a network.

[0037] 3. Functional configuration of the substrate processing system Figure 4 shows an example of the functional configuration of a substrate processing system in one embodiment of the present invention. Referring to Figure 4, the control device 10 of the substrate processing apparatus 300 controls the substrate processing unit WU to process the substrate W according to processing conditions. The processing conditions are the conditions for processing the substrate W during a predetermined processing time. The processing time is the time determined for processing the substrate. In this embodiment, the processing time is the time while the nozzle 311 is discharging the etching solution onto the substrate W.

[0038] The processing conditions include the temperature of the etching solution, the concentration of the etching solution, the flow rate of the etching solution, the rotation speed of the substrate W, and the relative position between the nozzle 311 and the substrate W. The processing conditions also include variable conditions that change over time. In this embodiment, the variable condition is the relative position between the nozzle 311 and the substrate W. The relative position is indicated by the rotation angle of the nozzle motor 303. The processing conditions also include fixed conditions that do not change over time. In this embodiment, the fixed conditions are the temperature of the etching solution, the concentration of the etching solution, the flow rate of the etching solution, and the rotation speed of the substrate W.

[0039] The learning device 200 trains a learning model with training data and generates an inference model that predicts the etching profile from the processing conditions. Hereinafter, the inference model generated by the learning device 200 will be referred to as the predictor.

[0040] The learning device 200 includes an experimental data acquisition unit 261, a first conversion unit 263, a predictor generation unit 265, and a predictor transmission unit 267. The functions of the learning device 200 are realized by the CPU 201 of the learning device 200, which executes a learning program stored in the RAM 202.

[0041] The experimental data acquisition unit 261 acquires experimental data from the substrate processing apparatus 300. The experimental data includes the processing conditions used when the substrate processing apparatus 300 actually processes the substrate W, and the film thickness characteristics of the film formed on the substrate W before and after processing.

[0042] The film thickness characteristics are represented by the film thickness at multiple different locations in the radial direction of the substrate W where the film is formed on the substrate W.

[0043] The variable conditions include the relative position of the nozzle 311 with respect to the substrate W, which changes over time. The substrate W rotates around the first rotation axis AX1, and the nozzle 311 rotates around the second rotation axis AX2. Therefore, the change in the relative position between the nozzle 311 and the substrate W is indicated by the change in the position of the nozzle 311. The position of the nozzle 311 is determined by the rotation angle of the nozzle motor 303. Furthermore, the range of the rotation angle of the nozzle motor 303 is limited to a predetermined range. In addition, the processing time is a predetermined period. In this embodiment, the processing time is 60 seconds.

[0044] Figure 5 illustrates the change in the relative position of the nozzle with respect to the substrate. Referring to Figure 5, the change in the relative position of the nozzle 311 with respect to the substrate W held in the spin chuck SC is shown. The nozzle 311 moves in the region above the substrate W held in the spin chuck SC. Since the nozzle rotates around the second rotation axis AX2, the trajectory of the movement of the nozzle 311 is an arc. The trajectory of the movement of the nozzle 311 passes through the substrate center OP, which is the center of the substrate. Therefore, the nozzle 311 moves radially across the entire periphery of the substrate W from the substrate center OP. Here, the trajectory of the movement of the nozzle 311 is shown with one end in the operating end EP1 inside the periphery of the substrate W, and the other end is shown with the operating end EP2 inside the periphery of the substrate W. Arrow a1 indicates the scanning of the nozzle 311 from the operating end EP1 to the substrate center OP, arrow a2 indicates the scanning of the nozzle 311 from the substrate center OP to the operating end EP2, arrow a3 indicates the scanning of the nozzle 311 from the operating end EP2 to the substrate center OP, and arrow a4 indicates the scanning of the nozzle 311 from the substrate center OP to the operating end EP1.

[0045] Figure 6 shows an example of a nozzle operation pattern. In Figure 6, the vertical axis shows the relative position of the nozzle 311 with respect to the substrate W, and the horizontal axis shows the elapsed time (seconds). In this embodiment, the nozzle operation, which moves the nozzle 311 relative to the substrate W, is shown from start to finish. The scanning period until the scan is performed is equal to the processing time. As mentioned above, the processing time is set to 60 seconds, so the nozzle's operating pattern shows the relative position during the period from 0 to 60 seconds. The relative position of the nozzle is defined with the substrate center OP as zero, the range from the substrate center OP to the operating end EP1 is shown as a negative value, and the range from the substrate center OP to the operating end EP2 is shown as a positive value. Since the substrate W has a diameter of 300 mm, the distance from the substrate center OP to the operating ends EP1 and EP2 is set to ±150 mm or less. Here, the distance from the substrate center OP to the operating end EP1 is set to -147 mm, and the distance from the substrate center OP to the operating end EP2 is set to +147 mm. In the nozzle operation pattern shown in Figure 6, the relative position of the nozzle 311 is indicated as 0 when the nozzle 311 is located at the center OP of the substrate, the relative position of the nozzle 311 is indicated as -147 mm when the nozzle 311 is located at the operating end EP1, and the relative position of the nozzle 311 is indicated as 147 mm when the nozzle 311 is located at the operating end EP2.

[0046] The nozzle movement pattern shown in Figure 6 is represented as a scan that reciprocates five times between the operating end EP1 and the operating end EP2. For the first reciprocating scan in the nozzle movement pattern, the relative positions corresponding to the scans indicated by arrows a1 to a4 in Figure 5 are indicated by the same reference numerals.

[0047] Figure 7 shows an example of film thickness characteristics. Referring to Figure 7, the horizontal axis shows the radial position of the substrate, and the vertical axis shows the film thickness. The origin of the horizontal axis indicates the center of the substrate. The film thickness formed on the substrate W before processing by the substrate processing apparatus 300 is shown by the solid line. The film thickness formed on the substrate W is adjusted by applying the etching solution according to the processing conditions performed by the substrate processing apparatus 300. The film thickness formed on the substrate W after processing by the substrate processing apparatus 300 is shown by the dotted line.

[0048] The difference between the film thickness formed on the substrate W before processing by the substrate processing apparatus 300 and the film thickness formed on the substrate W after processing by the substrate processing apparatus 300 is the processing amount (etching amount). The processing amount indicates the thickness of the film reduced by the process of applying the etching solution by the substrate processing apparatus 300. The radial distribution of the processing amount is called the etching profile. The etching profile includes the processing amount at each of several locations in the radial direction of the substrate W.

[0049] Furthermore, it is desirable that the film thickness formed by the substrate processing apparatus 300 be uniform across the entire surface of the substrate W. For this reason, a target film thickness is defined for the processing performed by the substrate processing apparatus 300. The target film thickness is indicated by a dashed line. The deviation characteristic is the difference between the film thickness formed on the substrate W after processing by the substrate processing apparatus 300 and the target film thickness. The deviation characteristic includes the difference at each of several locations in the radial direction of the substrate W.

[0050] Returning to Figure 4, the first conversion unit 263 converts the variable conditions included in the processing conditions of the experimental data input from the experimental data acquisition unit 261 into low-dimensional compressed data. Here, the variable conditions are the relative position of the nozzle 311 with respect to the substrate W, which changes over time. The first conversion unit 263 outputs the compressed data to the predictor generation unit 265.

[0051] The compressed data shows the amount of movement of the nozzle for each of the multiple movement intervals, which are obtained by dividing at least a portion of the movement range of the nozzle 311 during the scanning period from the start to the end of the nozzle movement relative to the substrate W into a number smaller than the number of data points for the variation conditions. The amount of movement is the time that the nozzle 311 is located in each of the multiple movement intervals. Now, the compressed data will be explained.

[0052] Figure 8 is a diagram illustrating the divided region. Referring to Figure 8, the upper surface of the substrate W is the substrate Fifteen divided regions b1 to b15 are shown, divided by multiple concentric circles centered on the central point OP. Divided region b15 is a circle, and divided regions b1 to b14 are annular. The radial length of the substrate W in each of the divided regions b1 to b14 is the same. The radial length of the substrate in each of the divided regions b1 to b14 is the difference between the radius of the outer circumference and the radius of the inner circumference. The radius of divided region b15 is the same as the radial length of the substrate W in each of the divided regions b1 to b14. Here, the radius of divided region b15 is 10 mm, and the difference between the radii of the outer circumference and the inner circumference of each of the divided regions b1 to b14 is 10 mm. The difference between the radii of the outer circumference and the inner circumference of each of the divided regions b1 to b14 and the radius of divided region b15 are greater than the inner diameter of the nozzle 311. Preferably, the radial length of the substrate in each of the divided regions b1 to b15 and the radius of divided region b15 are greater than or equal to the inner diameter of the nozzle 311.

[0053] Since the nozzle 311 rotates around the second rotation axis AX2, its center of rotation is different from the substrate center OP. The range of motion of the nozzle 311 is the trajectory it traces from the operating end EP1, through the substrate center OP, to the operating end EP2, and is an arc.

[0054] The range of movement of the nozzle 311 is the trajectory of the nozzle 311 during the processing period (scanning period) in which the nozzle 311 processes the substrate. The range of movement is divided into 30 movement sections d1 to d30 by the division regions b1 to b15. Movement sections d1 to d15 are sections of the trajectory in which the nozzle 311 moves between the operating end EP1 and the substrate center OP, crossing each of the division regions b1 to b15. For example, movement section d1 is the section in which the nozzle 311 moves between the operating end EP1 and the substrate center OP, crossing division region b1. Similarly, movement sections d16 to d30 are sections of the trajectory in which the nozzle 311 moves between the operating end EP2 and the substrate center OP, crossing each of the division regions b1 to b15. For example, movement section d30 is the section in which the nozzle 311 moves between the operating end EP2 and the substrate center OP, crossing division region b1. Note that the number of division areas b1 to b15 is not limited to 15, but can be set to any value. In this case, the number of divisions in the movement range, or in other words, the number of movement intervals, will differ.

[0055] Figure 9 shows an example of compressed data. In Figure 9, the horizontal axis represents the position on the substrate W. The position of the substrate center OP is indicated at 0 mm, one end of the substrate W in the radial direction is indicated at -150 mm, and the other end of the substrate W in the radial direction is indicated at 150 mm. Movement intervals d1 to d30 are assigned between -150 mm and +150 mm on the horizontal axis.

[0056] The vertical axis shows the dwell time of the nozzle 311 in each of the movement intervals d1 to d30. Here, the dwell time for each of the movement intervals d1 to d30 is shown when the nozzle 311 moves according to the operation pattern shown in Figure 6. The dwell time is the cumulative time that the nozzle 311 is located in each of the multiple movement intervals d1 to d30. For example, when the nozzle 311 moves according to the nozzle operation pattern shown in Figure 6, the nozzle 311 crosses movement interval d2 10 times. The dwell time in movement interval d2 is the cumulative time that the nozzle 311 crosses movement interval d2.

[0057] As described above, the movement range of the nozzle 311 is divided into multiple movement sections d1 to d30. Therefore, the residence time of the nozzle 311 in each of the multiple divided regions b1 to b15 is calculated for each of the multiple divided regions b1 to b15, including information on the radial position of the substrate W. Thus, the residence time in each of the multiple divided regions b1 to b15 includes information on the radial position of the substrate W. Furthermore, the radial length of the portion of the substrate W that the nozzle 311 crosses in each of the multiple divided regions b1 to b15 is the same. Therefore, the residence time of the nozzle 311 in each of the multiple divided regions b1 to b15 can be made to be a time without bias between different positions in the radial direction of the substrate W with respect to the change in the relative position of the nozzle 311 with respect to the substrate W.

[0058] Furthermore, in this embodiment, the upper surface of the substrate W is divided into 15 divided regions b1 to b15, so the number of compressed data is 30. The larger the radial length of each divided region b1 to b15 of the substrate, the smaller the number of compressed data. Since the radial length of each divided region b1 to b15 of the substrate is greater than or equal to the inner diameter of the nozzle 311, the maximum number of compressed data is determined by the inner diameter of the nozzle 311.

[0059] Returning to Figure 4, the predictor generation unit 265 receives compressed data with transformed variation conditions from the first transformation unit 263 and experimental data from the experimental data acquisition unit 261. The predictor generation unit 265 generates a predictor by having a neural network perform supervised training. Note that the neural network may be a convolutional neural network.

[0060] Specifically, the training data includes input data and ground truth data. The input data includes compressed data whose variable conditions have been transformed by the first transformation unit 263, and fixed conditions other than the variable conditions of the processing conditions included in the experimental data. The ground truth data includes an etching profile. The etching profile is the difference between the film thickness characteristics of the film before processing included in the experimental data and the film thickness characteristics of the film after processing included in the experimental data. This etching profile included in the ground truth data is an example of the first processing amount. The predictor generation unit 265 inputs the input data into the neural network and determines the parameters of the neural network so that the output of the neural network is equal to the ground truth data. The predictor generation unit 265 generates a neural network as a predictor by incorporating the parameters set in the trained neural network. The predictor is an inference program that incorporates the parameters set in the trained neural network. The predictor generation unit 265 transmits the predictor to the information processing device 100.

[0061] Figure 10 illustrates a predictor. Referring to Figure 10, the predictor includes an input layer, a hidden layer, and an output layer, with each layer containing multiple nodes indicated by circles. Although the figure shows one hidden layer, the number of hidden layers may be greater. Also, while the figure shows five nodes in the input layer, four in the hidden layer, and three in the output layer, the number of nodes is not limited to these. The outputs of higher-level nodes are connected to the inputs of lower-level nodes. Parameters include coefficients that weight the outputs of higher-level nodes. The number of hidden layers is one or more, and is not limited to that number.

[0062] When the predictor receives compressed data (where the variable conditions are converted into a low-dimensional dataset) and fixed conditions as input, an etching profile is output. The etching profile output by this predictor is an example of a second processing amount. The etching profile is represented by the difference in film thickness E[n] before and after processing at multiple radial positions P[n] (where n is an integer greater than or equal to 1) on the substrate W. Although the figure shows three output nodes for the predictor, the actual number of output nodes is n.

[0063] Returning to Figure 4, the information processing device 100 includes a processing condition determination unit 151, a predictor receiving unit 155, a second conversion unit 157, a prediction unit 159, an evaluation unit 161, and a processing condition transmission unit 163. The functions of the information processing device 100 are realized by the CPU 101 of the information processing device 100, which executes a processing condition determination program stored in the RAM 102.

[0064] The predictor receiver 155 receives the predictor transmitted from the learning device 200 and outputs the received predictor to the prediction unit 159.

[0065] The processing condition determination unit 151 determines the processing conditions for the substrate W to be processed by the substrate processing apparatus 300. The processing condition determination unit 151 outputs the variable conditions included in the processing conditions to the second conversion unit 157 and outputs the fixed conditions included in the processing conditions to the prediction unit 159. The fixed unit 151 selects one of several pre-prepared variable conditions using experimental design, pairwise method, or Bayesian estimation, and determines the processing conditions, which include the selected variable condition and the fixed condition, as the processing conditions for the prediction unit 159 to make an estimate. Preferably, the pre-prepared multiple variable conditions are those generated by the learning device 200 to generate the compressor.

[0066] The second conversion unit 157 has the same function as the first conversion unit 263 of the learning device 200 described above. The second conversion unit 157 converts the variable conditions input from the processing condition determination unit 151 into compressed data. The second conversion unit 157 outputs the converted compressed data to the prediction unit 159.

[0067] The prediction unit 159 uses a predictor to estimate the etching profile from the compressed data and fixed conditions. Specifically, the prediction unit 159 inputs the compressed data from the second conversion unit 157 and the fixed conditions from the processing condition determination unit 151 into the predictor, and outputs the etching profile output by the predictor to the evaluation unit 161.

[0068] The evaluation unit 161 evaluates the etching profile input from the prediction unit 159 and outputs the evaluation result to the processing condition determination unit 151. Specifically, the evaluation unit 161 acquires the film thickness characteristics of the substrate W that the substrate processing apparatus 300 is scheduled to process before processing. The evaluation unit 161 calculates the predicted film thickness characteristics after etching from the etching profile input from the prediction unit 159 and the film thickness characteristics of the substrate W before processing, and compares it with the target film thickness characteristics. If the comparison result satisfies the evaluation criteria, the processing conditions determined by the processing condition determination unit 151 are output to the processing condition transmission unit 163. For example, the evaluation unit 161 calculates the deviation characteristics and determines whether the deviation characteristics satisfy the evaluation criteria. The deviation characteristics are the difference between the film thickness characteristics of the substrate W after etching and the target film thickness characteristics. The evaluation criteria can be arbitrarily determined. For example, the evaluation criteria may be that the maximum difference in the deviation characteristics is less than or equal to a threshold, or that the average difference is less than or equal to a threshold.

[0069] The processing condition transmission unit 163 transmits the processing conditions determined by the processing condition determination unit 151 to the substrate processing apparatus 300. The substrate processing apparatus 300 processes the substrate W according to the processing conditions.

[0070] If the evaluation result does not meet the evaluation criteria, the evaluation unit 161 outputs the evaluation result to the processing condition determination unit 151. The evaluation result includes the film thickness characteristics predicted after the etching process, or the difference between the film thickness characteristics predicted after the etching process and the target film thickness characteristics.

[0071] The processing condition determination unit 151 determines new processing conditions for the prediction unit 159 to predict, in response to the evaluation results input from the evaluation unit 161. The processing condition determination unit 151 selects one of several pre-prepared variable conditions using experimental design, pairwise method, or Bayesian estimation, and determines the processing conditions, which include the selected variable condition and fixed conditions, as new processing conditions for the prediction unit 159 to predict.

[0072] The processing condition determination unit 151 may use Bayesian estimation to search for processing conditions. When the evaluation unit 161 outputs multiple evaluation results, there will be multiple pairs of processing conditions and evaluation results. From the trends of the etching profiles in each of the multiple pairs, the system searches for processing conditions that result in a uniform film thickness or processing conditions that minimize the difference between the film thickness characteristics predicted after etching and the target film thickness characteristics.

[0073] Specifically, the processing condition determination unit 151 searches for processing conditions that minimize the objective function. The objective function is a function that indicates the uniformity of the film thickness or a function that indicates the agreement between the film thickness characteristics and the target film thickness characteristics. For example, the objective function is a function in which the difference between the film thickness characteristics predicted after etching and the target film thickness characteristics is expressed by parameters. The parameters here are corresponding The variable conditions are the compressed data converted by the second conversion unit 157. The corresponding variable conditions are the variable conditions before the compressed data was converted, which the predictor used to estimate the etching profile. The processing condition determination unit 151 selects the variable conditions corresponding to the compressed data, which are parameters determined by search, from among a plurality of variable conditions, and determines new processing conditions including the selected variable conditions and fixed conditions.

[0074] Figure 11 is a flowchart showing an example of the predictor generation process. The predictor generation process is performed by the CPU 201 of the learning device 200, which executes the predictor generation program stored in the RAM 202. The predictor generation program is part of the learning program.

[0075] Referring to Figure 11, the CPU 201 of the learning device 200 acquires experimental data. The CPU 201 controls the input / output I / F 107 to acquire experimental data from the substrate processing device 300 (step S01). The experimental data may also be acquired by reading experimental data recorded on a recording medium such as a CD-ROM 209 with the storage device 104. Multiple experimental data sets are acquired here. The experimental data includes processing conditions and the film thickness characteristics of the film formed on the substrate W before and after processing. The film thickness characteristics are shown as the film thickness at multiple different positions in the radial direction of the substrate W.

[0076] In the next step, S02, the experimental data to be processed is selected, and the process proceeds to step S03. In step S03, the compressed data generation process is executed, and the process proceeds to step S04. The details of the compressed data generation process will be described later, but it is a process that converts the variable conditions included in the experimental data into compressed data.

[0077] In step S04, the compressed data, the fixed conditions included in the experimental data, and the etching profile are set as training data. The etching profile is the difference between the film thickness characteristics of the film before treatment included in the experimental data and the film thickness characteristics of the film after treatment included in the experimental data. The training data includes the input data and the ground truth data. In step S03, the compressed data converted and the fixed conditions included in the experimental data are set as input data. The etching profile is set as ground truth data.

[0078] In the next step, S05, the CPU 201 trains the predictor using machine learning and proceeds to step S06. The input data is fed into the predictor, which is a neural network, and the parameters are determined so that the predictor's output is equal to the correct data. This adjusts the predictor's parameters. The predictor is a neural network with parameters determined by machine learning using training data. The neural network may also be a convolutional neural network.

[0079] In step S06, it is determined whether the adjustment is complete. Training data to be used to evaluate the predictor is prepared in advance, and the performance of the predictor is evaluated using the evaluation training data. If the evaluation result meets the predetermined evaluation criteria, it is determined that the adjustment is complete. If the evaluation result does not meet the evaluation criteria (NO in step S06), the process returns to step S02, but if the evaluation result meets the evaluation criteria (YES in step S06), the process proceeds to step S07.

[0080] If the process returns to step S02, in step S02, experimental data that was not selected for processing from the experimental data acquired in step S01 is selected. In the loop from step S02 to step S06, the CPU 201 trains the predictor using multiple training data. This adjusts the parameters of the predictor, which is a neural network, to appropriate values. In step S08, the predictor is sent, The process is completed. The CPU 201 controls the input / output interface 107 and sends the predictor to the information processing device 100.

[0081] Figure 12 is a flowchart showing an example of the processing condition determination process. The processing condition determination process is a process executed by the CPU 101 of the information processing device 100 when the CPU 101 executes a processing condition determination program stored in the RAM 102.

[0082] Referring to Figure 12, the CPU 101 of the information processing device 100 selects one of several pre-prepared variable conditions (step S11) and proceeds to step S12. The multiple variable conditions are those generated by the learning device 200 to generate the compressor. One of the pre-prepared variable conditions is selected using experimental design, pairwise method, or Bayesian estimation, etc.

[0083] In step S12, the compressed data generation process is executed, and the process proceeds to step S13. Details of the compressed data generation process will be described later.

[0084] In step S13, the etching profile is estimated from the compressed data and fixed conditions using a predictor, and the process proceeds to step S14. The compressed data and fixed conditions generated in step S12 are input to the predictor, and the etching profile output by the predictor is obtained. In step S14, the film thickness characteristics after processing are compared with the target film thickness characteristics. The film thickness characteristics after processing the substrate W are calculated from the film thickness characteristics of the substrate W to be processed by the substrate processing apparatus 300 before processing and the etching profile estimated in step S13. Then, the film thickness characteristics after processing are compared with the target film thickness characteristics. Here, the difference between the film thickness characteristics after processing the substrate W and the target film thickness characteristics is calculated.

[0085] In step S15, it is determined whether the comparison result meets the evaluation criteria. If the comparison result meets the evaluation criteria (YES in step S15), the process proceeds to step S16; otherwise, the process returns to step S11. For example, the evaluation criteria are met if the maximum difference is less than or equal to the threshold. Also, the evaluation criteria are met if the average difference is less than or equal to the threshold.

[0086] In step S16, a processing condition including the variable condition selected immediately before in step S11 is set as a candidate for the processing condition to drive the substrate processing device 300, and the process proceeds to step S17. In step S17, it is determined whether or not a search termination instruction has been received. If a termination instruction is received by the user operating the information processing device 100, the process proceeds to step S18; otherwise, the process returns to step S11. Alternatively, instead of a termination instruction entered by the user, it may be determined whether or not a predetermined number of processing conditions have been set as candidates.

[0087] In step S18, one processing condition is selected from the one or more processing conditions set as candidates, and the process proceeds to step S19. Alternatively, one processing condition may be selected by the user operating the information processing device 100 from the one or more processing conditions set as candidates. This expands the range of selection for the user. Furthermore, the variation condition that results in the simplest nozzle operation may be automatically selected from among the variation conditions included in the multiple processing conditions. The variation condition that results in the simplest nozzle operation can be, for example, the variation condition with the fewest number of speed change points. This makes it possible to present multiple variation conditions for the processing results of complex nozzle operations that process the substrate W. By selecting a variation condition that makes nozzle control easy from among the multiple variation conditions, the control of the substrate processing device 300 becomes easier.

[0088] In step S19, a processing rule including the variable conditions determined in step S18 is used. The information is sent to the board processing unit 300, and the processing ends. The CPU 101 controls the input / output interface 107 to send processing conditions to the board processing unit 300. When the board processing unit 300 receives processing conditions from the information processing unit 100, it processes the board W according to those processing conditions.

[0089] Figure 13 is a flowchart showing an example of the compressed data generation process. The compressed data generation process is performed in step S03 in Figure 11 or step S12 in Figure 12. Yes. In step S21, time-series data showing the time-series operation of the nozzle 311 is acquired. In step S22, the number of divisions K (K is an integer of 2 or more) for setting multiple movement intervals is acquired from the time-series data. In this embodiment, the number of divisions K is set in advance. The number of divisions K may also be input by the user through the operation unit or the like. In the example in Figure 6, the number of divisions K is set to 30.

[0090] In step S23, the variable n is set to 1. In step S24, the dwell time of the nozzle 311 in the movement interval d(n) is calculated. The movement interval d(n) is the nth movement interval among movement intervals d1 to d30. Once the dwell time of the nozzle 311 in movement interval d(n) is calculated, in step S25, 1 is added to the variable n. At this time, in step S26, it is determined whether the variable n is greater than the number of divisions K. If the variable n is less than or equal to the number of divisions K, the process returns to step S24. If the variable n is greater than the number of divisions K, in step S27, the calculated dwell times of the nozzle 311 in movement intervals d(1) to d(K) are set in the compressed data. Steps S24 to S26 are repeated to calculate the dwell time of the nozzle 311 in each of the movement intervals d(1) to d(K).

[0091] 4. Specific Examples In this embodiment, the variable conditions are time-series data sampled with a nozzle operation processing time of 60 seconds and a sampling interval of 0.01 seconds. The variable conditions consist of 6001 values. Therefore, the variable conditions can represent complex nozzle operations. In particular, nozzle operations with a relatively large number of speed change points can be accurately represented by the variable conditions. On the other hand, because of the large number of variable conditions, overfitting may occur when machine learning is performed on the time-series data of the variable conditions.

[0092] In this embodiment, the first conversion unit 263 converts the variable conditions into compressed data. The compressed data consists of the residence time of the nozzle 311 in each of the multiple movement sections obtained by dividing the movement range of the nozzle 311 into 30 divisions. The inventors have experimentally discovered that even when converting variable conditions consisting of 6001 values ​​representing complex nozzle operation into compressed data, the desired result can be obtained as an etching profile predicted by the predictor.

[0093] Therefore, the amount of data input to the predictor can be reduced, simplifying the predictor's configuration and making it easier to train the neural network. Furthermore, the neural network's parameters can be adjusted to appropriate values, improving the predictor's accuracy.

[0094] Furthermore, since the variation conditions with 6001 dimensions are converted into compressed data with 30 dimensions, there may be multiple variation conditions that result in the same compressed data. In this case, the etching profiles predicted by the predictor from each of the multiple variation conditions with the same compressed data will be the same. In this embodiment, when the processing condition determination unit 151 searches for processing conditions, it searches for processing conditions that correspond to different etching profiles, so processing conditions corresponding to multiple different etching profiles are selected. For this reason, the processing condition determination unit 151 selects the target etching profile from among the multiple processing conditions. This allows for efficient searching of processing conditions under which a file is predicted to be generated.

[0095] Although an example using a sampling interval of 0.01 seconds was explained, the sampling interval is not limited to this. A longer or shorter sampling interval may be used. For example, the sampling interval may be 0.1 seconds or 0.005 seconds.

[0096] 5. Other Embodiments (1) In the embodiment described above, the learning device 200 generates a predictor based on the training data. The learning device 200 may also perform additional training on the predictor. After the predictor is generated, the learning device 200 obtains the film thickness characteristics and processing conditions of the substrate W processed by the substrate processing device 300 before and after processing. The learning device 200 then generates training data from the film thickness characteristics and processing conditions before and after processing, and performs machine learning on the predictor to perform additional training. The configuration of the neural network constituting the predictor is not changed by the additional training, but the parameters are adjusted.

[0097] The information obtained from the actual processing of the substrate W by the substrate processing device 300 is used to train the predictor through machine learning, thereby improving the accuracy of the predictor. Furthermore, the amount of training data used to generate the predictor can be minimized.

[0098] Figure 14 is a flowchart showing an example of the flow of the additional learning process. The additional learning process is a process executed by the CPU 201 of the learning device 200, which executes the additional learning program stored in the RAM 202. The additional learning program is part of the learning program.

[0099] Referring to Figure 14, the CPU 201 of the learning device 200 acquires production data (step S31) and proceeds to step S32. The production data includes the processing conditions when the substrate processing device 300 processes the substrate W after the predictor is generated, and the film thickness characteristics of the film before and after processing. The CPU 201 controls the input / output I / F 107 to acquire production data from the substrate processing device 300. The production data may also be acquired by reading experimental data recorded on a recording medium such as a CD-ROM 209 with the storage device 104.

[0100] In step S32, the compressed data generation process shown in Figure 13 is executed, and the process proceeds to step S33. The execution of the compressed data generation process converts the variable conditions into compressed data. In step S33, the compressed data, the fixed conditions included in the processing conditions of the production data, and the etching profile are set as training data. The etching profile is the difference between the film thickness characteristics of the film before processing and the film thickness characteristics of the film after processing, both included in the production data. The compressed data generated by the first conversion unit 263 and the fixed conditions included in the processing conditions are set as input data. The etching profile is set as the correct data.

[0101] In the next step, S34, the CPU 201 further trains the predictor and proceeds to step S35. The input data is fed into the predictor, which is a neural network, and the parameters are determined so that the predictor's output is equal to the correct data. This further adjusts the predictor's parameters.

[0102] In step S35, it is determined whether the adjustment is complete. The performance of the predictor is evaluated using the training data for evaluation. The adjustment is determined to be complete if the evaluation result meets the predetermined additional training evaluation criteria. The additional training evaluation criteria are higher than the evaluation criteria used when the predictor was generated. If the evaluation result does not meet the additional training evaluation criteria (NO in step S35), the process returns to step S31, but if the evaluation result meets the additional training evaluation criteria (YES in step S35), the process ends.

[0103] (2) The learning device 200 may generate a distillation model that has been trained on a new learning model using distillation data including processing conditions determined by the information processing device 100 and etching profiles predicted by a predictor from those processing conditions. This makes it easier to prepare data for training the new learning model.

[0104] (3) In this embodiment, the training data used to generate the predictor includes compressed data obtained by transforming the variable conditions of the input data and fixed conditions. The present invention is not limited thereto. The input data may include only compressed data obtained by transforming the variable conditions and may not include fixed conditions.

[0105] (4) In this embodiment, an example is described in which the first conversion unit 263 and the second conversion unit 157 convert time-series data relating to the movement of the nozzle 311 into compressed data indicating the dwell time of the nozzle 311 in each of a plurality of movement intervals, but the present invention is not limited thereto. For example, in the above embodiment, an example is shown in which the supply amount of processing liquid is constant, but the supply amount of processing liquid may fluctuate over time. In this case, the fluctuating condition includes the supply amount of processing liquid that fluctuates over time. In this case, the compressed data is the supply amount of processing liquid in each of the plurality of movement intervals.

[0106] Figure 15 shows an example of the processing liquid supply amount changing over time. The upper part of Figure 15 shows time-series data similar to the nozzle operation pattern shown in Figure 6. The lower part of Figure 15 shows an example of the change in the amount of processing liquid discharged from nozzle 311 (processing liquid discharge flow rate time history). In the graph at the bottom of Figure 15, the horizontal axis represents time, and the vertical axis represents the flow rate of the processing liquid discharged from nozzle 311. The amount of processing liquid supplied in each of the multiple movement sections d1 to d30 is calculated from the relative position of the nozzle with respect to the substrate, which changes over time, and the flow rate of the processing liquid discharged from nozzle 311, which also changes over time. Specifically, the amount of processing liquid supplied in each of the multiple movement sections is calculated from the time the nozzle stays in the movement section and the flow rate of the processing liquid supplied from nozzle 311.

[0107] Figure 16 shows another example of compressed data. In Figure 16, the horizontal axis indicates the position on the substrate W. The substrate center OP is indicated at 0 mm, one substrate edge in the radial direction is indicated at -150 mm, and the other substrate edge in the radial direction is indicated at 150 mm. Movement intervals d1 to d30 are assigned between -150 mm and +150 mm on the horizontal axis.

[0108] The vertical axis shows the amount of processing liquid supplied in each movement interval d1 to d30. Here, the amount of processing liquid supplied in each movement interval d1 to d30 is shown when the nozzle 311 moves according to the operation pattern shown in Figure 6. In each movement interval d1 to d30, the cumulative amount of processing liquid supplied from the nozzle 311 while the nozzle 311 is in that position is calculated as the supply amount. In this case, the time-series data showing the operation of the nozzle 311 is converted into compressed data that takes into account the amount of processing liquid supplied to the substrate W, making it possible to generate a more accurate predictor.

[0109] (5) Although the present invention has been described using the example of the information processing device 100 and the learning device 200 being separate from the substrate processing device 300, the present invention is not limited thereto. The information processing device 100 may be incorporated into the substrate processing device 300. Furthermore, the information processing device 100 and the learning device 200 may be incorporated into the substrate processing device 300. Also, although the information processing device 100 and the learning device 200 were described as separate devices, they may be configured as a single integrated device.

[0110] (6) In the above embodiment, each of the multiple movement sections d1 to d30 is set so that the radial lengths of the substrate are equal to each other, but each of the multiple movement sections d1 to d30 may be set to different lengths. For example, the movement range may be divided so that the trajectory of the movement of the nozzle 311 is equally divided. For example, if the angle between the operating end EP1 and the operating end EP2 with respect to the second rotation axis AX2 is 60 degrees, then the angle of each of the multiple movement sections d1 to d30 with respect to the second rotation axis AX2 is 2 degrees. In this way, the multiple movement sections d1 to d30 can be expressed in terms of the rotation angle of the nozzle motor 303.

[0111] Effects in the embodiment of 6. In this embodiment, the learning device 200 drives the substrate processing apparatus 300 with processing conditions including variable conditions to process a film formed on the substrate W. After processing, it obtains a processing amount indicating the difference in film thickness before and after processing. The first conversion unit 263 converts the variable conditions into compressed data, which is used as input data. This training data, which includes etching profiles corresponding to the processing conditions as ground truth data, is then used to train a neural network to generate a predictor, which is a learning model for estimating etching profiles. Since the training data includes compressed data converted so that the number of dimensions of the variable conditions that change over time is reduced, the number of dimensions of the training data can be reduced. Therefore, a learning device suitable for machine learning the conditions that change over time in order to process a film formed on the substrate W can be generated.

[0112] Furthermore, the learning device 200 compresses the time the nozzle 311 stays in each of the multiple movement sections obtained by dividing the movement range of the nozzle 311 of the substrate processing device 300, making it possible to easily convert from variable conditions to compressed data.

[0113] Furthermore, the processing conditions include variable conditions and fixed conditions that do not change over time. Therefore, it can handle processing with different fixed conditions, and there is no need to generate multiple learning models with different fixed conditions.

[0114] Furthermore, after generating a predictor, the learning device 200 acquires a processing amount indicating the difference in film thickness before and after processing the film formed on the substrate W processed by the substrate processing device 300 according to the processing conditions. The learning model is then trained using additional training data that includes the conversion result obtained by the compressor, where the fluctuating conditions have been transformed, and the acquired processing amount. As a result, the learning model is further trained, and the performance of the learning model can be improved.

[0115] Furthermore, the learning device 200 provides the learning model with the conversion result obtained by the compressor, which transforms the provisional fluctuation conditions. If the processing amount estimated by the learning model satisfies the acceptable conditions, it generates a new learning model using the distillation data, which includes the conversion result and the processing amount estimated by the learning model. This makes it easier to prepare data for training the new learning model.

[0116] Furthermore, the substrate processing apparatus 300 includes a nozzle 311 for supplying processing liquid to the substrate W, and a nozzle movement mechanism 301 for changing the relative position between the nozzle and the substrate W. The variable condition is the relative position between the nozzle 311 and the substrate W, which is changed by the nozzle movement mechanism 301. By changing the relative position between the nozzle 311 and the substrate W and supplying processing liquid from the nozzle 311 to the substrate W, a learning model is generated that estimates the amount of film to be processed. Therefore, a learning model can be generated that estimates the amount of processing in the etching process.

[0117] Furthermore, the information processing device 100 uses a compressor generated by the learning device 200 to process the temporary fluctuations. The compressed data with transformed conditions is fed to a learning model generated by the learning device 200. If the etching profile predicted by the learning model satisfies the acceptable conditions, the processing conditions, including the provisional variation conditions, are determined as the processing conditions for driving the substrate processing apparatus 300. Therefore, since the etching profile is predicted from the processing conditions, there is no need to determine, through experiments or other means, the influence of the complex operation of the nozzle on the processing result of the etching process. Furthermore, since multiple provisional variation conditions are determined for the processing amount that satisfies the acceptable conditions, multiple variation conditions corresponding to multiple etching profiles that satisfy the acceptable conditions can be determined. Thus, multiple variation conditions can be presented for the processing results of a complex process that processes substrates. By selecting processing conditions that make it easy to control the nozzle operation from among the multiple variation conditions, the control of the substrate processing apparatus 300 becomes easier.

[0118] Furthermore, since the information processing device 100 determines multiple processing conditions for a processing volume that satisfies the acceptable conditions, it can determine multiple processing conditions corresponding to multiple etching profiles that satisfy the acceptable conditions. The fixed conditions include the temperature of the etching solution. Therefore, it can present multiple etching solution temperatures for the processing results of a complex process that processes the substrate. In addition, it is possible to select an etching solution temperature that is easy to apply to the etching process from among the multiple etching solution temperatures. And because an easily applicable etching solution temperature can be selected, temperature control of the etching solution used in the etching process becomes easier.

[0119] 7. Correspondence between each component of the claim and each part of the embodiment Substrate W is an example of a substrate, etching solution is an example of a processing solution, substrate processing apparatus 300 is an example of a substrate processing apparatus, experimental data acquisition unit 261 is an example of an experimental data acquisition unit, first conversion unit 263 is an example of a conversion unit and first conversion unit, predictor is an example of a learning model, and predictor generation unit 265 is an example of a model generation unit. Furthermore, information processing apparatus 100 is an example of an information processing apparatus, second conversion unit 157 is an example of a second conversion unit, nozzle 311 is an example of a nozzle that supplies processing solution to the substrate, nozzle moving mechanism 301 is an example of a moving unit, and prediction unit 159, evaluation unit 161, and processing condition determination unit 151 are examples of processing condition determination units.

[0120] 8. Summary of Embodiments (1) An experimental data acquisition unit that, after processing the film formed on the substrate by moving a nozzle that supplies a processing liquid to a substrate on which a film has been formed and driving the substrate processing apparatus that supplies the processing liquid to the substrate under processing conditions that include a fluctuation condition indicating the relative position of the nozzle with respect to the substrate which fluctuates over time, acquires a first processing amount indicating the difference in film thickness before and after processing the film, A conversion unit converts the aforementioned variable conditions into compressed data representing the amount of movement of the nozzle for each of a plurality of movement intervals, which are obtained by dividing the movement range of the nozzle during the scanning period from when the substrate processing apparatus starts to when it finishes moving the nozzle relative to the substrate into a number smaller than the number of data points for the aforementioned variable conditions. A learning device comprising: a model generation unit that performs machine learning on learning data including the compressed data and the first processing amount corresponding to the processing conditions to generate a learning model that estimates a second processing amount indicating the difference in film thickness before and after processing of the film formed on the substrate before the film is processed by the substrate processing device.

[0121] The learning device described in paragraph 1 includes compressed data and processing data that have been transformed so as to reduce the number of dimensions of the fluctuation conditions indicating the relative position of the nozzle relative to the substrate that changes over time. Therefore, the number of dimensions of the learning data can be reduced. As a result, a learning device suitable for machine learning the conditions that change over time for processing a film formed on a substrate can be provided.

[0122] (Clause 2) The learning device according to Clause 1, wherein the amount of movement is the time the nozzle stays in each of the plurality of movement sections.

[0123] According to the learning device described in paragraph 2, since the amount of movement is the time the nozzle stays in each of the multiple movement sections, it becomes possible to easily convert from variable conditions to compressed data.

[0124] (Clause 3) The variable conditions further include the flow rate of the processing liquid discharged by the substrate processing apparatus to the substrate as time progresses, The learning device according to paragraph 2, wherein the amount of operation is the amount of processing liquid supplied, calculated from the time the nozzle stays in each of the plurality of movement sections and the flow rate of the processing liquid supplied from the nozzle.

[0125] According to the learning device described in Section 3, the amount of processing fluid supplied to each of the multiple movement sections is taken into account as an operational quantity, making it possible to convert the data into compressed data with fewer dimensions than the number of dimensions of the multiple types of variable conditions.

[0126] (Clause 4) The learning device according to any one of Clauses 1 to 3, wherein the multiple movement sections are of the same length.

[0127] According to the learning device described in Section 4, each of the multiple movement sections is set to the same length, so the compressed data shows the nozzle's movement within multiple movement sections set to the same length. Therefore, it becomes possible to convert the data into compressed data that reduces the bias in the amount of nozzle movement relative to the substrate between different positions on the substrate.

[0128] (Clause 5) The learning apparatus according to Clause 4, wherein the length of each of the plurality of moving sections is the radial length of the region of the upper surface of the substrate that the nozzle traverses while moving through the moving section.

[0129] According to the learning device described in Section 5, the length of each of the multiple movement sections is the radial length of the region that the nozzle crosses the substrate while moving through the movement section. Therefore, the amount of movement of the nozzle relative to the substrate can be converted into compressed data with reduced bias between different positions in the radial direction of the substrate.

[0130] (Clause 6) Information processing device for managing substrate processing device, The substrate processing apparatus processes the film formed on the substrate by supplying a processing liquid to the substrate on which the film has been formed, under processing conditions that include a fluctuation condition indicating the relative position of the nozzle with respect to the substrate which fluctuates over time. A conversion unit converts the aforementioned variable conditions into compressed data representing the amount of movement of the nozzle for each of a plurality of movement intervals, which are obtained by dividing the movement range of the nozzle during the scanning period from when the substrate processing apparatus starts to when it finishes moving the nozzle relative to the substrate into a number smaller than the number of data points for the aforementioned variable conditions. The system includes a processing condition determination unit that determines processing conditions for driving the substrate processing apparatus, using a learning model that estimates a second processing amount indicating the difference in film thickness before and after processing of the film formed on the substrate before the film is processed by the substrate processing apparatus, The learning model is an inference model that has been machine-trained using learning data which includes compressed data obtained by performing the same transformation as the transformation unit on the variable conditions included in the processing conditions for processing the film formed on the substrate by the substrate processing apparatus, and a first processing amount which indicates the difference in film thickness before and after processing the film formed on the substrate processed by the substrate processing apparatus. The processing condition determination unit provides the compressed data, from which the provisional variation conditions have been transformed by the transformation unit, to the learning model, and the second processing amount estimated by the learning model satisfies the acceptable conditions. An information processing device that determines the processing conditions, including the aforementioned provisional variable conditions, as the processing conditions for driving the substrate processing device.

[0131] According to the information processing device described in Section 6, compressed data obtained by transforming provisional fluctuation conditions that change over time is provided to a learning model, and if the processing amount estimated by the learning model satisfies the acceptable conditions, the processing conditions including the provisional fluctuation conditions are determined as the processing conditions for driving the substrate processing device. Therefore, multiple provisional fluctuation conditions can be determined for a processing amount that satisfies the acceptable conditions. As a result, it becomes possible to present multiple processing conditions for the processing results of a complex process that processes a film formed on a substrate.

[0132] (Item 7) A substrate processing apparatus equipped with the information processing apparatus described in Item 6.

[0133] According to the substrate processing apparatus described in Section 7, it becomes possible to present multiple processing conditions for the processing results of a complex process for processing a substrate.

[0134] (Clause 8) A substrate processing system for managing a substrate processing apparatus for processing substrates, Equipped with a learning device and an information processing device, The substrate processing apparatus processes the film formed on the substrate by supplying a processing liquid to the substrate on which the film has been formed, under processing conditions that include a fluctuation condition indicating the relative position of the nozzle with respect to the substrate which fluctuates over time. The learning device includes an experimental data acquisition unit that, after driving the substrate processing apparatus under the processing conditions to process the film formed on the substrate, acquires a first processing amount indicating the difference in film thickness before and after processing the film, A first conversion unit converts the aforementioned variable conditions into compressed data representing the amount of movement of the nozzle for each of a plurality of movement intervals, which are obtained by dividing the movement range of the nozzle during the scanning period from when the substrate processing apparatus starts to when it finishes moving the nozzle relative to the substrate into a number smaller than the number of data points for the aforementioned variable conditions. The system includes: a model generation unit that performs machine learning on training data including compressed data from which the variable conditions have been converted by the first conversion unit and the first processing amount corresponding to the processing conditions, to generate a learning model that estimates a second processing amount that indicates the difference in film thickness before and after processing of the film formed on a substrate before the film is processed by the substrate processing apparatus, The information processing device includes a second conversion unit, which is the same as the first conversion unit, The system includes a processing condition determination unit that determines processing conditions for driving the substrate processing device using the learning model generated by the learning device, A substrate processing system in which the processing condition determination unit provides the conversion result obtained by the second conversion unit from the provisional fluctuation conditions to the learning model, and determines the processing conditions including the provisional fluctuation conditions as processing conditions for driving the substrate processing apparatus when the second processing amount estimated by the learning model satisfies the acceptable conditions.

[0135] The substrate processing system described in Section 8 is suitable for machine learning to process conditions that change over time for processing films formed on a substrate, and it is possible to present multiple processing conditions for the processing results of a complex process for processing films formed on a substrate.

[0136] (Clause 9) A process to obtain a first processing amount indicating the difference in film thickness before and after processing the film formed on the substrate, by moving a nozzle that supplies a processing liquid to the substrate and driving the substrate processing apparatus that supplies the processing liquid to the substrate under processing conditions that include a fluctuation condition indicating the relative position of the nozzle with respect to the substrate which fluctuates over time, The variable conditions are defined as the range of movement of the nozzle during the scanning period from when the nozzle operation, in which the substrate processing apparatus moves the nozzle relative to the substrate, starts until it ends. A process of converting into compressed data that shows the amount of movement for the nozzle for each of the multiple movement segments that have been divided into a number smaller than the number of data points, A learning method that causes a computer to perform machine learning on learning data including the compressed data and the first processing amount corresponding to the processing conditions, to generate a learning model that estimates a second processing amount indicating the difference in film thickness before and after processing of the film formed on the substrate before the film is processed by the substrate processing apparatus.

[0137] The learning method described in Section 9 includes compressed data and processing data that have been transformed so that the number of dimensions of the variable conditions that change over time is reduced. Therefore, the number of dimensions of the learning data can be reduced. As a result, a learning method suitable for machine learning the conditions that change over time for processing films formed on a substrate can be provided.

[0138] (Clause 10) A method for determining processing conditions, which is performed by a computer that manages a substrate processing apparatus, The substrate processing apparatus processes the film formed on the substrate by supplying a processing liquid to the substrate on which the film has been formed, under processing conditions that include a fluctuation condition indicating the relative position of the nozzle with respect to the substrate which fluctuates over time. The process of converting the aforementioned variable conditions into compressed data representing the amount of movement of the nozzle for each of a plurality of movement intervals obtained by dividing the movement range of the nozzle during the scanning period from when the substrate processing apparatus starts to when it finishes moving the nozzle relative to the substrate into a number smaller than the number of data points for the aforementioned variable conditions, The process includes determining processing conditions for driving the substrate processing apparatus, using a learning model that estimates a second processing amount indicating the difference in film thickness before and after processing of the film formed on the substrate before processing the film by the substrate processing apparatus, The learning model is an inference model that uses machine learning to train learning data that includes compressed data obtained by performing the same transformation as the transformation process, and a first processing amount that indicates the difference in film thickness before and after processing of the film formed on the substrate by the substrate processing apparatus, which is included in the processing conditions for processing the film formed on the substrate by the substrate processing apparatus. A method for determining the processing conditions, wherein the processing for determining the processing conditions is to provide the compressed data, into which the provisional variation conditions have been transformed by the transformation process, to the learning model, and if the second processing amount estimated by the learning model satisfies the acceptable conditions, the processing conditions including the provisional variation conditions are determined as the processing conditions for driving the substrate processing apparatus.

[0139] The processing condition determination method described in Section 10 provides a processing condition determination method that can present multiple processing conditions for the processing results of a complex process for processing a film formed on a substrate. [Explanation of Symbols]

[0140] 1...Substrate processing system, 10...Control device, 30...Number of divisions, 100...Information processing device, 151...Processing condition determination unit, 155...Predictor receiving unit, 157...Second conversion unit, 159...Prediction unit, 161...Evaluation unit, 163...Processing condition transmission unit, 200...Learning device, 261...Experimental data acquisition unit, 263...First conversion unit, 265...Predictor generation unit, 267...Predictor transmission unit, 300...Substrate processing device, 301...Nozzle movement mechanism, 311...Nozzle, AX1...First rotation axis, AX2...Second rotation axis, EP1...Operating end, EP2...Operating end, OP...Substrate center, SC...Spin chuck, SM...Spin motor, W...Substrate, WU...Substrate processing unit, b1~b30...Division region, d1~d30...Movement section

Claims

1. An experimental data acquisition unit acquires a first processing amount that indicates the difference in film thickness before and after processing the film formed on the substrate, by moving a nozzle that supplies a processing liquid to the substrate and driving the substrate processing apparatus that supplies the processing liquid to the substrate under processing conditions that include a fluctuation condition indicating the relative position of the nozzle with respect to the substrate which fluctuates over time, and then acquiring a first processing amount indicating the difference in film thickness before and after processing the film. A conversion unit converts the aforementioned variable conditions into compressed data representing the amount of movement of the nozzle for each of a plurality of movement intervals, which are obtained by dividing the movement range of the nozzle during the scanning period from when the substrate processing apparatus starts to when it finishes moving the nozzle relative to the substrate into a number smaller than the number of data points for the aforementioned variable conditions. A learning device comprising: a model generation unit that performs machine learning on learning data including the compressed data and the first processing amount corresponding to the processing conditions to generate a learning model that estimates a second processing amount indicating the difference in film thickness before and after processing of the film formed on the substrate before the film is processed by the substrate processing device.

2. The learning device according to claim 1, wherein the amount of movement is the dwell time at which the nozzle is located in each of the plurality of movement sections.

3. The aforementioned variable conditions further include the flow rate of the processing liquid discharged by the substrate processing apparatus to the substrate over time, The learning device according to claim 2, wherein the amount of operation is the amount of processing liquid supplied, calculated from the time the nozzle stays in each of the plurality of movement sections and the flow rate of the processing liquid supplied from the nozzle.

4. The learning device according to any one of claims 1 to 3, wherein the plurality of movement sections are of the same length.

5. The learning device according to claim 4, wherein the length of each of the plurality of moving sections is the radial length of the region on the upper surface of the substrate that the nozzle traverses while moving through the moving section.

6. An information processing device for managing a substrate processing device, The substrate processing apparatus processes the film formed on the substrate by supplying a processing liquid to the substrate on which the film has been formed, under processing conditions that include a fluctuation condition indicating the relative position of the nozzle with respect to the substrate which fluctuates over time. A conversion unit converts the aforementioned variable conditions into compressed data representing the amount of movement of the nozzle for each of a plurality of movement intervals, which are obtained by dividing the movement range of the nozzle during the scanning period from when the substrate processing apparatus starts to when it finishes moving the nozzle relative to the substrate into a number smaller than the number of data points for the aforementioned variable conditions. The system includes a processing condition determination unit that determines processing conditions for driving the substrate processing apparatus, using a learning model that estimates a second processing amount indicating the difference in film thickness before and after processing of the film formed on the substrate before the film is processed by the substrate processing apparatus, The learning model is an inference model that has been machine-trained using learning data which includes compressed data obtained by performing the same transformation as the transformation unit on the variable conditions included in the processing conditions for processing the film formed on the substrate by the substrate processing apparatus, and a first processing amount which indicates the difference in film thickness before and after processing the film formed on the substrate processed by the substrate processing apparatus. The processing condition determination unit provides the compressed data, into which the provisional variation conditions have been converted by the conversion unit, to the learning model, and determines the processing conditions, including the provisional variation conditions, as processing conditions for driving the substrate processing device when the second processing amount estimated by the learning model satisfies the acceptable conditions.

7. A substrate processing apparatus comprising the information processing apparatus described in claim 6.

8. A substrate processing system for managing a substrate processing apparatus that processes substrates, Equipped with a learning device and an information processing device, The substrate processing apparatus processes the film formed on the substrate by supplying a processing liquid to the substrate on which the film has been formed, under processing conditions that include a fluctuation condition indicating the relative position of the nozzle with respect to the substrate which fluctuates over time. The learning device includes an experimental data acquisition unit that, after driving the substrate processing apparatus under the processing conditions to process the film formed on the substrate, acquires a first processing amount indicating the difference in film thickness before and after processing the film, A first conversion unit converts the aforementioned variable conditions into compressed data representing the amount of movement of the nozzle for each of a plurality of movement intervals, which are obtained by dividing the movement range of the nozzle during the scanning period from when the substrate processing apparatus starts to when it finishes moving the nozzle relative to the substrate into a number smaller than the number of data points for the aforementioned variable conditions. The system includes: a model generation unit that performs machine learning on training data including compressed data from which the variable conditions have been converted by the first conversion unit and the first processing amount corresponding to the processing conditions, to generate a learning model that estimates a second processing amount that indicates the difference in film thickness before and after processing of the film formed on a substrate before the film is processed by the substrate processing apparatus, The information processing device includes a second conversion unit, which is the same as the first conversion unit, The system includes a processing condition determination unit that determines processing conditions for driving the substrate processing device using the learning model generated by the learning device, A substrate processing system in which the processing condition determination unit provides the conversion result obtained by the second conversion unit from the provisional fluctuation conditions to the learning model, and determines the processing conditions including the provisional fluctuation conditions as processing conditions for driving the substrate processing apparatus when the second processing amount estimated by the learning model satisfies the acceptable conditions.

9. A process to obtain a first processing amount indicating the difference in film thickness before and after processing the film formed on the substrate, by moving a nozzle that supplies a processing liquid to the substrate and driving the substrate processing apparatus that supplies the processing liquid to the substrate under processing conditions that include a fluctuation condition indicating the relative position of the nozzle with respect to the substrate which fluctuates over time, and then moving a nozzle that supplies a processing liquid to the substrate on which the film has been formed, and driving the substrate processing apparatus that supplies the processing liquid to the substrate under processing conditions that include a fluctuation condition indicating the relative position of the nozzle with respect to the substrate which fluctuates over time, The process of converting the aforementioned variable conditions into compressed data representing the amount of movement of the nozzle for each of a plurality of movement intervals obtained by dividing the movement range of the nozzle during the scanning period from when the nozzle operation in which the substrate processing apparatus moves the nozzle relative to the substrate starts until it ends into a number smaller than the number of data points for the aforementioned variable conditions, A learning method that causes a computer to perform machine learning on learning data including the compressed data and the first processing amount corresponding to the processing conditions, to generate a learning model that estimates a second processing amount indicating the difference in film thickness before and after processing of the film formed on the substrate before the film is processed by the substrate processing apparatus.

10. A method for determining processing conditions, which is executed by a computer that manages a substrate processing apparatus, The substrate processing apparatus processes the film formed on the substrate by supplying a processing liquid to the substrate on which the film has been formed, under processing conditions that include a fluctuation condition indicating the relative position of the nozzle with respect to the substrate which fluctuates over time. The process of converting the aforementioned variable conditions into compressed data representing the amount of movement of the nozzle for each of a plurality of movement intervals obtained by dividing the movement range of the nozzle during the scanning period from when the substrate processing apparatus starts to when it finishes moving the nozzle relative to the substrate into a number smaller than the number of data points for the aforementioned variable conditions, The process includes determining processing conditions for driving the substrate processing apparatus, using a learning model that estimates a second processing amount indicating the difference in film thickness before and after processing of the film formed on the substrate before processing the film by the substrate processing apparatus, The learning model is an inference model that uses machine learning to train learning data that includes compressed data obtained by performing the same transformation as the transformation process, and a first processing amount that indicates the difference in film thickness before and after processing of the film formed on the substrate by the substrate processing apparatus, which is included in the processing conditions for processing the film formed on the substrate by the substrate processing apparatus. A method for determining the processing conditions, wherein the processing for determining the processing conditions is to provide the compressed data, into which the provisional variation conditions have been transformed by the transformation process, to the learning model, and if the second processing amount estimated by the learning model satisfies the acceptable conditions, the processing conditions including the provisional variation conditions are determined as the processing conditions for driving the substrate processing apparatus.

Images