Information processing method, computer program, and information processing device

Abstract

The invention provides an information processing method, a computer program, and an information processing device which are expected to correct a mechanical error with a reference device to control a target device. An information processing device acquires a sensor value of a target device, inputs the acquired sensor value of the target device to a sensor value conversion model, and acquires a sensor value of a reference device output by the sensor value conversion model. Inputting the acquired sensor value of the reference device together with a desired target value into a control input value determination model to acquire a control input value of the reference device output by the control input value determination model; the control input value of the target device, which is output by a control input value conversion model, is acquired by inputting the acquired control input value of the reference device to the control input value conversion model, and the target device is controlled on the basis of the acquired control input value of the target device.

Description

Technical Field

[0001] The present disclosure relates to an information processing method, a computer program, and an information processing device. Background Art

[0002] Patent document 1 proposes a substrate processing method, which uses an estimation model of sensor data to adjust the device parameters of each processing container so that the deviation of the sensor data from the ideal value of the sensor is within an allowable range, wherein the estimation model of the sensor data is generated based on the sensor data input and output to each processing container when a test substrate is processed under the same processing conditions in multiple processing containers included in a substrate processing device. In this substrate processing method, when a product substrate is transported to any processing container, the product substrate is processed while adjusting the sensor data input and output to the processing container to which the product substrate is transported based on the adjusted device parameters.

[0003] Patent Document 1: Japanese Patent Application Publication No. 2019-114695 Summary of the invention

[0004] The present disclosure provides an information processing method, a computer program, and an information processing device that can control a target device and the like while expecting to correct a mechanical error with a reference device.

[0005] In an information processing method of one embodiment, an information processing device executes: acquiring a sensor value of a target device, inputting the acquired sensor value of the target device into a sensor value conversion model to acquire a sensor value of a reference device output by the sensor value conversion model, wherein the sensor value conversion model is a model obtained by machine learning in a manner of receiving the sensor value of the target device as an input and outputting the sensor value of the reference device, inputting the acquired sensor value of the reference device together with a desired target value into a control input value determination model to acquire a control input value of the reference device output by the control input value determination model, wherein the control input value determination model is a model obtained by machine learning in a manner of receiving the target value and the sensor value of the reference device as input and outputting the control input value of the reference device, inputting the acquired control input value of the reference device into a control input value conversion model to acquire a control input value of the target device output by the control input value conversion model, wherein the control input value conversion model is a model obtained by machine learning in a manner of receiving the control input value of the reference device as an input and outputting the control input value of the target device, and controlling the target device based on the acquired control input value of the target device.

[0006] According to the present disclosure, it is expected that a mechanical error with a reference device can be corrected to control a target device or the like. BRIEF DESCRIPTION OF THE DRAWINGS

[0007] Figure 1 This is a schematic diagram for explaining an example of the information processing system according to the first embodiment.

[0008] Figure 2 This is a block diagram showing a configuration example of an information processing device according to this embodiment.

[0009] Figure 3 It is a schematic diagram showing a structural example of a characteristic value estimation model.

[0010] Figure 4 This is a schematic diagram showing an example of the structure of learning data.

[0011] Figure 5 This is a schematic diagram showing a structural example of a control input value determination model.

[0012] Figure 6 This is a schematic diagram showing a structural example of a sensor value control input value relationship model.

[0013] Figure 7 This is a schematic diagram showing a structural example of a sensor value conversion model.

[0014] Figure 8 This is a schematic diagram showing a structural example of a control input value conversion model.

[0015] Fig. 9 This is a schematic diagram for explaining monitoring of a substrate processing apparatus by an information processing apparatus.

[0016] Fig.10 This is a schematic diagram for explaining control of a substrate processing apparatus by an information processing apparatus.

[0017] Fig.11 This is a flowchart showing an example of the procedure of the learning model generation process performed by the information processing device of this embodiment.

[0018] Fig.12 This is a flowchart showing an example of the procedure of the learning model generation process performed by the information processing device of this embodiment.

[0019] Fig.13 This is a flowchart showing an example of a procedure of monitoring and controlling processing of a substrate processing apparatus performed by the information processing apparatus of the present embodiment.

[0020] Fig.14This is a flowchart showing an example of a procedure of monitoring and controlling processing of a substrate processing apparatus performed by the information processing apparatus of the present embodiment.

[0021] Fig.15 This is a schematic diagram showing a structural example of a control input value determination model according to the second implementation mode.

[0022] Fig.16 This is a schematic diagram for explaining control of a reference substrate processing apparatus by an information processing apparatus.

[0023] Fig.17 This is a schematic diagram for explaining control of a target substrate processing apparatus by an information processing apparatus. DETAILED DESCRIPTION

[0024] Hereinafter, a specific example of the information processing system according to the embodiment of the present disclosure will be described with reference to the drawings. In addition, the present disclosure is not limited to these examples, but is indicated by the claims, and is intended to include all changes within the meaning and scope equivalent to the claims.

[0025] <System Overview>

[0026] Figure 1 It is a schematic diagram for illustrating an example of an information processing system of Embodiment 1. The information processing system of this embodiment is configured to include a substrate processing device and an information processing device. The substrate processing device is, for example, a device that performs various processes for substrate processing such as CVD (Chemical Vapor Deposition), sputtering, or etching, and may be a semiconductor manufacturing device or a flat panel display (FPD) manufacturing device that manufactures display panels. The information processing device is a device that monitors and controls the operation of the substrate processing device. The information processing device, for example, obtains sensor values ​​obtained from a plurality of sensors provided in the substrate processing device, and determines control input values ​​for the substrate processing device based on the obtained sensor values. The information processing device causes the substrate processing device to perform substrate processing by inputting the determined control input values ​​into the substrate processing device.

[0027] exist Figure 1In the figure, two substrate processing devices, namely a reference substrate processing device (reference device) 101A and an object substrate processing device (object device) 101B, are shown as substrate processing devices, and two information processing devices 1A and 1B are shown as information processing devices. The information processing device 1A monitors and controls the reference substrate processing device 101A, and the information processing device 1B monitors and controls the object substrate processing device 101B. The reference substrate processing device 101A is, for example, a substrate processing device that is already in operation and operating normally. In contrast, the object substrate processing device 101B is basically a device having the same structure as the reference substrate processing device 101A, but is, for example, a device newly manufactured or purchased and newly added to a substrate processing factory. The reference substrate processing device 101A and the object substrate processing device 101B are basically devices having the same structure. It is expected that the information processing apparatuses 1A and 1B can obtain the same processing results by performing the same calculation processing based on the obtained sensor values ​​to determine the control input values ​​and inputting the determined control input values ​​to the reference substrate processing apparatus 101A and the target substrate processing apparatus 101B.

[0028] However, even in the case of devices with the same structure, there may be individual differences in, for example, the output sensor values ​​of each sensor or individual differences in the processing mechanism that performs substrate processing according to the control input value. Therefore, even if the same control input value is input for the same sensor value, the same processing result may not necessarily be obtained in the reference substrate processing device 101A and the target substrate processing device 101B. The information processing system of this embodiment is a system that assists in compensating for the mechanical errors of the reference substrate processing device 101A and the target substrate processing device 101B.

[0029] In addition, in this example, the reference substrate processing device 101A and the target substrate processing device 101B are set as different devices, but not limited to this. For example, by performing operations such as replacement of sensors, replacement of processing mechanisms, or maintenance of devices on the substrate processing device, there may be a situation where the actions of the substrate processing device change before and after these operations. In such a case, the substrate processing device before maintenance operations can be regarded as the reference substrate processing device 101A, and the substrate processing device after the operation can be regarded as the target substrate processing device 101B. In this case, the information processing devices 1A and 1B can be substantially the same device. In addition, even if the reference substrate processing device 101A and the target substrate processing device 101B are different devices, the information processing devices 1A and 1B can also be the same device when one information processing device monitors and controls multiple substrate processing devices.

[0030] The information processing apparatus 1A of this embodiment uses a learning model that has been machine-learned in advance to monitor and control the reference substrate processing apparatus 101A. Therefore, the information processing apparatus 1A includes a characteristic value estimation model 201 and a control input value determination model 202. The characteristic value estimation model 201 is a learning model that estimates the characteristics of the substrate processed by the reference substrate processing apparatus 101A based on the sensor values ​​obtained from the sensors of the reference substrate processing apparatus 101A and the control input values ​​input to the reference substrate processing apparatus 101A. The information processing apparatus 1A can use the characteristic value estimation model 201 to estimate the characteristic values ​​of the substrate processed by the reference substrate processing apparatus 101A, for example, to display the estimation results and provide information, or to stop the apparatus when an abnormality is detected based on the estimation results.

[0031] The control input value determination model 202 is a learning model that determines a control input value to be input to the reference substrate processing apparatus 101A based on a target characteristic value (target value) of a substrate processed by the reference substrate processing apparatus 101A and a sensor value obtained from a sensor of the reference substrate processing apparatus 101A. It is expected that the information processing apparatus 1A processes a substrate that satisfies the target characteristic value by inputting the control input value determined by the control input value determination model 202 to the reference substrate processing apparatus 101A.

[0032] In addition, the characteristic value is information obtained by measuring the substrate processed by the substrate processing device in the characteristic value measuring device 102. For example, when the substrate processing device performs etching, the measured value such as the depth of the hole formed by etching may become the characteristic value. The characteristic value may also be an arbitrary value. In addition, the target characteristic value is the characteristic value required for the substrate processed by the substrate processing device, and the characteristic value obtained by measuring the processed substrate in the characteristic value measuring device 102 is required to be the target characteristic value or a value close to the target characteristic value.

[0033] In order to generate the characteristic value estimation model 201 and the control input value determination model 202, the information processing device 1A causes the reference substrate processing device 101A to perform a predetermined substrate process. The information processing device 1A collects data that associates the sensor value obtained from the reference substrate processing device 101A, the control input value input to the reference substrate processing device 101A, and the characteristic value obtained by measuring the processed substrate in the characteristic value measuring device 102. The information processing device 1A performs machine learning processing using the data that associates the sensor value, the control input value, and the characteristic value, thereby generating the characteristic value estimation model 201 and the control input value determination model 202.

[0034] In addition, the information processing device 1A generates a sensor value control input value relationship model 203 when generating the characteristic value estimation model 201 and the control input value determination model 202. The sensor value control input value relationship model 203 is a learning model after learning the relationship between the multiple sensor values ​​obtained from the reference substrate processing device 101A and the multiple control input values ​​input to the reference substrate processing device 101A. That is, the sensor value control input value relationship model 203 is, for example, a learning model that estimates a value to supplement the missing value when any one of the multiple sensor values ​​and the control input value is missing. The sensor value control input value relationship model 203 is not a learning model used when the information processing device 1A monitors and controls the reference substrate processing device 101A, but is a learning model provided from the information processing device 1A to the information processing device 1B in order to compensate for the mechanical error between the reference substrate processing device 101A and the target substrate processing device 101B as described above. The sensor value-control input value relationship model 203 is generated by machine learning using data of sensor values ​​and control input values ​​included in the data used when generating the characteristic value estimation model 201 and the control input value determination model 202 .

[0035] In the information processing system of the present embodiment, the information processing device 1B that performs monitoring and control of the target substrate processing device 101B utilizes these learning models generated by the information processing device 1A that performs monitoring and control of the reference substrate processing device 101A. As described above, the characteristic value estimation model 201 and the control input value determination model 202 are generated based on the information obtained from the reference substrate processing device 101A. The characteristic value estimation model 201 is a learning model that estimates the characteristic value based on the sensor value and control input value of the reference substrate processing device 101A, and the control input value determination model 202 is a learning model that determines the control input value based on the sensor value of the reference substrate processing device 101A. Therefore, in the target substrate processing device 101B that has a mechanical error with the reference substrate processing device 101A, these learning models cannot be directly used for monitoring and control, or even if monitoring and control are performed, sufficient accuracy cannot be obtained.

[0036] Therefore, in the information processing system of the present embodiment, the information processing apparatus 1B generates and utilizes the sensor value conversion model 204 and the control input value conversion model 205, thereby compensating for the mechanical error between the target substrate processing apparatus 101B and the reference substrate processing apparatus 101A, and performing monitoring and control using the characteristic value estimation model 201 and the control input value determination model 202. The sensor value conversion model 204 is a learning model that converts the sensor value obtained from the target substrate processing apparatus 101B into the sensor value obtained from the reference substrate processing apparatus 101A. The control input value conversion model 205 is a learning model that converts the control input value input to the reference substrate processing apparatus 101A into the control input value input to the target substrate processing apparatus 101B.

[0037] In order to generate the sensor value conversion model 204 and the control input value conversion model 205, the information processing device 1B causes the target substrate processing device 101B to perform a predetermined substrate process. The information processing device 1B collects data that establishes a correspondence between the sensor value obtained from the target substrate processing device 101B and the control input value input to the target substrate processing device 101B. The information processing device 1B can generate the sensor value conversion model 204 and the control input value conversion model 205 by performing machine learning processing using the data that establishes a correspondence between the sensor value and the control input value and the sensor value control input value relationship model 203 given from the information processing device 1A.

[0038] In addition, in the present embodiment, the processing of generating these learning models, so-called machine learning processing, is performed by the information processing devices 1A and 1B, but the present invention is not limited thereto. The machine learning processing may also be performed by a device other than the information processing devices 1A and 1B, such as a server device with high computing processing capabilities. In this case, the information processing devices 1A and 1B collect information required for machine learning, send the collected information to the server device, etc., and obtain the learning model generated based on the information from the server device, etc.

[0039] <Device Structure>

[0040] Figure 21 is a block diagram showing a structural example of an information processing device of the present embodiment. In the information processing system of the present embodiment, each information processing device may be any one of an information processing device 1A that monitors and controls a reference substrate processing device 101A or an information processing device 1B that monitors and controls a target substrate processing device 101B. Hereinafter, a device that can perform both the processing of the information processing device 1A and the processing of the information processing device 1B is referred to as an information processing device 1, and the structure of the information processing device 1 is described. In addition, the reference substrate processing device 101A and the target substrate processing device 101B are devices of substantially the same structure, and when there is no need to distinguish them, they are simply referred to as substrate processing devices 101 for description.

[0041] The information processing device 1 of this embodiment is configured to include a processing unit 11, a storage unit (memory) 12, a communication unit 13, a display unit 14, an operation unit 15, etc. In addition, in this embodiment, the processing is performed by a single information processing device 1 for explanation, but the processing of the information processing device 1 may be performed in a distributed manner by a plurality of devices.

[0042] The processing unit 11 is configured using a CPU (Central Processing Unit), an MPU (Micro-Processing Unit), a GPU (Graphics Processing Unit), or a quantum processor, etc., a ROM (Read Only Memory), and a RAM (Random Access Memory). The processing unit 11 reads and executes a program 12a stored in the storage unit 12 to perform various processes such as monitoring and controlling the substrate processing apparatus 101 and generating a learning model required for these processes.

[0043] The storage unit 12 is configured to use a large-capacity storage device such as a hard disk. The storage unit 12 stores various programs executed by the processing unit 11 and various data required for the processing of the processing unit 11. In the present embodiment, the storage unit 12 stores a program 12a executed by the processing unit 11. In addition, the storage unit 12 is provided with a model information storage unit 12b storing information related to the above-mentioned multiple learning models, and a learning data storage unit 12c storing learning data used for machine learning to generate these learning models.

[0044] In the present embodiment, the program (computer program, program product) 12a is provided in a manner recorded on a recording medium 99 such as a memory card or an optical disk, and the information processing device 1 reads the program 12a from the recording medium 99 and stores it in the storage unit 12. However, the program 12a may be written to the storage unit 12, for example, during the manufacturing stage of the information processing device 1. In addition, for example, regarding the program 12a, the information processing device 1 may obtain a program distributed by a remote server device or the like by using communication. For example, regarding the program 12a, the writing device may read the program recorded on the recording medium 99 and write it to the storage unit 12 of the information processing device 1. The program 12a may be provided in a manner distributed via a network, or may be provided in a manner recorded on the recording medium 99.

[0045] The model information storage unit 12b of the storage unit 12 stores information related to the learning models such as the characteristic value estimation model 201, the control input value determination model 202, the sensor value control input value relationship model 203, the sensor value conversion model 204, and the control input value conversion model 205. The information related to the learning model can include, for example, structure information indicating how the learning model is structured, and information such as the values ​​of parameters inside the learning model. In the case of the information processing device 1A that monitors and controls the reference substrate processing device 101A, at least the information of the characteristic value estimation model 201, the control input value determination model 202, and the sensor value control input value relationship model 203 is stored in the model information storage unit 12b. In the case of the information processing device 1B that monitors and controls the target substrate processing device 101B, the information of the characteristic value estimation model 201, the control input value determination model 202, the sensor value control input value relationship model 203, the sensor value conversion model 204, and the control input value conversion model 205 is stored.

[0046] The learning data storage unit 12c of the storage unit 12 stores the learning data required for the machine learning process for generating the above-mentioned learning model. In the case of the information processing device 1A that monitors and controls the reference substrate processing device 101A, the sensor values ​​of the sensors of the reference substrate processing device 101A, the control input values ​​input to the reference substrate processing device 101A, and the characteristic values ​​of the substrate processed by the reference substrate processing device 101A measured by the characteristic value measuring device 102 are stored in the learning data storage unit 12c as learning data. In the case of the information processing device 1B that monitors and controls the target substrate processing device 101B, the sensor values ​​of the sensors of the target substrate processing device 101B and the control input values ​​input to the target substrate processing device 101B are stored in the learning data storage unit 12c as learning data.

[0047] The communication unit 13 communicates with various devices via a wired or wireless network N including a LAN (Local Area Network), the Internet, or a mobile phone communication network. The communication unit 13 can be configured as an IC using a transceiver, for example. In the present embodiment, the communication unit 13 communicates with the substrate processing device 101, the characteristic value measuring device 102, and other information processing devices 1. The communication unit 13 sends data given from the processing unit 11 to other devices, and gives data received from other devices to the processing unit 11.

[0048] The display unit 14 is configured to use a liquid crystal display or the like, and displays various images and texts based on the processing of the processing unit 11. The display unit 14 displays various information related to the operation of the substrate processing device 101, such as information related to the characteristic value estimated by the characteristic value estimation model 201. The operation unit 15 accepts the user's operation and notifies the processing unit 11 of the accepted operation. For example, the operation unit 15 accepts the user's operation through an input device such as a mechanical button or a touch panel provided on the surface of the display unit 14. In addition, for example, the operation unit 15 can be an input device such as a mouse and a keyboard, and these input devices can also be a structure that can be removed from the information processing device 1.

[0049] In addition, the storage unit 12 may be an external storage device connected to the information processing device 1. In addition, the information processing device 1 may be a multi-computer including a plurality of computers, or a virtual machine virtually constructed by software. In addition, the information processing device 1 is not limited to the above-mentioned structure, and for example, the display unit 14 and the operation unit 15 may not be provided.

[0050] In addition, in the information processing device 1 of the present embodiment, the information acquisition unit 11a, the model generation unit 11b, the characteristic value estimation unit 11c, the control processing unit 11d and the display processing unit 11e are implemented as functional units of the software by the processing unit 11 by reading out and executing the program 12a stored in the storage unit 12.

[0051] The information acquisition unit 11a communicates with the substrate processing apparatus 101 using the communication unit 13, thereby acquiring various sensor values ​​detected by multiple sensors provided in the substrate processing apparatus 101, such as values ​​of temperature or pressure. In addition, the information acquisition unit 11a acquires multiple control input values ​​input to the substrate processing apparatus 101 for the acquired sensor values, such as values ​​of the drive amount of the actuator or the applied voltage value. In addition, in the case of the information processing apparatus 1A that monitors and controls the reference substrate processing apparatus 101A, the information acquisition unit 11a communicates with the characteristic value measuring device 102 using the communication unit 13, thereby acquiring the characteristic value of the substrate measured by the characteristic value measuring device 102. The information acquisition unit 11a establishes a correspondence between the acquired information and stores it as learning data in the learning data storage unit 12c.

[0052] The model generation unit 11b performs the processing of generating each of the above-mentioned learning models by performing the processing of machine learning using the learning data stored in the learning data storage unit 12c. In the present embodiment, each learning model can adopt a learning model of various structures such as a neural network, SVM (Support Vector Machine) or a random forest. In addition, each learning model can process information of a time series, in which case a learning model of a structure such as RNN (Recurrent Neural Network) or LSTM (Long Short Term Memory) can also be adopted. In addition, the structure of these learning models and the generation method of learning models based on machine learning are prior arts, so detailed descriptions are omitted in the present embodiment. In addition, in the case of an information processing device 1A that monitors and controls the reference substrate processing device 101A, the model generation unit 11b generates a characteristic value estimation model 201, a control input value determination model 202 and a sensor value control input value relationship model 203. In addition, in the case of the information processing apparatus 1B that performs monitoring and control of the target substrate processing apparatus 101B, the model generating unit 11 b generates the sensor value conversion model 204 and the control input value conversion model 205 .

[0053] When the substrate processing apparatus 101 processes a substrate, the characteristic value estimation unit 11c uses the characteristic value estimation model 201 and the control input value determination model 202 stored in the model information storage unit 12b to estimate the characteristic value of the substrate processed by the substrate processing apparatus 101. The characteristic value estimation unit 11c inputs the sensor value and the target characteristic value obtained from the substrate processing apparatus 101 to the control input value determination model 202, obtains the control input value output by the control input value determination model 202, inputs the sensor value and the control input value to the characteristic value estimation model 201, and obtains the characteristic value output by the characteristic value estimation model 201. The characteristic value estimation unit 11c can, for example, compare the characteristic value obtained from the characteristic value estimation model 201 with a predetermined threshold value to determine whether the substrate processed by the substrate processing apparatus 101 satisfies the target characteristic value.

[0054] However, in the case of the information processing apparatus 1B that monitors and controls the target substrate processing apparatus 101B, the sensor value obtained from the target substrate processing apparatus 101B cannot be directly input into the characteristic value estimation model 201 and the control input value determination model 202. The characteristic value estimation unit 11c of the information processing apparatus 1B inputs the sensor value obtained from the target substrate processing apparatus 101B into the sensor value conversion model 204, obtains the sensor value of the reference substrate processing apparatus 101A output by the sensor value conversion model 204, and inputs the sensor value into the characteristic value estimation model 201 and the control input value determination model 202.

[0055] The control processing unit 11d determines the control input value based on the sensor value obtained from the substrate processing apparatus 101 using the control input value determination model 202 stored in the model information storage unit 12b, and inputs the determined control input value to the substrate processing apparatus 101, thereby controlling the substrate processing performed by the substrate processing apparatus 101. The control processing unit 11d inputs the sensor value obtained from the substrate processing apparatus 101 and the target characteristic value of the substrate processed by the substrate processing apparatus 101 into the control input value determination model 202, and obtains the control input value output by the control input value determination model 202. The control processing unit 11d inputs the obtained control input value to the substrate processing apparatus 101, so that the substrate processing apparatus 101 processes the substrate that satisfies the target characteristic value.

[0056] However, in the case of the information processing apparatus 1B that monitors and controls the target substrate processing apparatus 101B, the sensor value obtained from the target substrate processing apparatus 101B cannot be directly input into the control input value determination model 202. The control processing unit 11d of the information processing apparatus 1B inputs the sensor value obtained from the target substrate processing apparatus 101B into the sensor value conversion model 204, obtains the sensor value of the reference substrate processing apparatus 101A outputted by the sensor value conversion model 204, and inputs the sensor value into the control input value determination model 202. Similarly, in the case of the information processing apparatus 1B that monitors and controls the target substrate processing apparatus 101B, the control input value outputted by the control input value determination model 202 cannot be directly inputted into the target substrate processing apparatus 101B. The control processing unit 11d of the information processing apparatus 1B inputs the control input value obtained from the control input value determination model 202 into the control input value conversion model 205, obtains the control input value outputted by the control input value conversion model 205, and inputs the control input value into the target substrate processing apparatus 101B.

[0057] The display processing unit 11e performs processing to display various information on the display unit 14. The display processing unit 11e displays, for example, the estimation result of the characteristic value by the characteristic value estimation unit 11c. For example, when it is determined that the characteristic value estimated for the substrate processed by the substrate processing apparatus 101 does not meet the target characteristic value, the display processing unit 11e can display a warning message notifying the same on the display unit 14. In addition, the display processing unit 11e can display various information other than the estimation result of the characteristic value, such as the progress of the substrate processing performed by the substrate processing apparatus 101, or a graph indicating the change of the sensor value acquired from the substrate processing apparatus 101.

[0058] <Learning model structure and generation method>

[0059] Five learning models generated and used in the information system of this embodiment are described. In addition, in the example shown below, the sensor values ​​obtained from the substrate processing device 101 are set to five, the control input values ​​input to the substrate processing device 101 are set to three, and the characteristic value measured by the characteristic value measuring device 102 is set to one. This is for the purpose of simplifying the description, and the number of sensor values, control input values, and characteristic values ​​is not limited to the above number, and can be any number.

[0060] Figure 32 is a schematic diagram showing a configuration example of the characteristic value estimation model 201. The characteristic value estimation model 201 of the present embodiment receives five sensor values ​​1 to 5 related to the reference substrate processing apparatus 101A and three control input values ​​1 to 3 input to the reference substrate processing apparatus 101A as inputs, and outputs an estimation result of the characteristic value of the substrate processed by the reference substrate processing apparatus 101A. The information processing apparatus 1 can determine whether the characteristic value of the substrate processed by the substrate processing apparatus 101 satisfies the target characteristic value based on the characteristic value output by the characteristic value estimation model 201.

[0061] The characteristic value estimation model 201 is generated by the information processing device 1A that monitors and controls the reference substrate processing device 101A, etc. The information processing device 1A collects learning data in advance in order to perform machine learning processing to generate the characteristic value estimation model 201 . Figure 4 1 is a schematic diagram showing an example of a structure of learning data. The information processing device 1A performs substrate processing in the reference substrate processing device 101A, and at this time, obtains sensor values ​​1 to 5 from the sensor of the reference substrate processing device 101A, obtains control input values ​​1 to 3 input to the reference substrate processing device 101A based on the sensor values ​​1 to 5, and stores the obtained sensor values ​​1 to 5 and control input values ​​1 to 3 in a corresponding manner. In addition, the information processing device 1A can repeatedly obtain sensor values ​​1 to 5 and control input values ​​1 to 3 at a predetermined period, and can also store the time series information of the sensor values ​​1 to 5 and control input values ​​1 to 3 in the learning data storage unit 12c.

[0062] In addition, after the processing of the reference substrate processing apparatus 101A is completed, the information processing apparatus 1A obtains the characteristic value obtained by measuring the processed substrate by the characteristic value measuring apparatus 102, and stores the obtained characteristic value in correspondence with the sensor values ​​1 to 5 and the control input values ​​1 to 3 obtained when processing the base substrate. When the information processing apparatus 1A repeatedly obtains the sensor values ​​1 to 5 and the control input values ​​1 to 3, it is possible to store the common characteristic value in correspondence with the sensor values ​​1 to 5 and the control input values ​​1 to 3 of a plurality of groups.

[0063] For example, for a learning model with 8 inputs and 1 output, the information processing device 1A uses the sensor values ​​1 to 5 and the control input values ​​1 to 3 included in the learning data stored in the learning data storage unit 12c as input information (explanatory variables) and the characteristic value as output information (target variable, correct answer value) to perform so-called supervised machine learning. In this way, the information processing device 1A can determine the internal parameters of the learning model and generate the characteristic value estimation model 201.

[0064] Figure 52 is a schematic diagram showing a configuration example of the control input value determination model 202. The control input value determination model 202 of the present embodiment receives five sensor values ​​1 to 5 related to the reference substrate processing apparatus 101A and target characteristic values ​​related to the substrate processed by the reference substrate processing apparatus 101A as inputs, and outputs three control input values ​​1 to 3 to be input to the reference substrate processing apparatus 101A. The target characteristic values ​​are predetermined before the substrate processing apparatus 101 starts substrate processing, and are stored in the storage unit 12 of the information processing apparatus 1, etc.

[0065] The control input value determination model 202 is generated by the information processing device 1A that monitors and controls the reference substrate processing device 101A. The information processing device 1A can generate the control input value determination model 202 using the same data as the learning data used in the generation of the characteristic value estimation model 201. For example, for a learning model with a structure of 6 inputs and 3 outputs, the information processing device 1A uses the sensor values ​​1 to 5 and the characteristic values ​​contained in the learning data stored in the learning data storage unit 12c as input information (explanatory variables) and the control input values ​​1 to 3 as output information (target variables, correct answer values) to perform so-called supervised machine learning processing. In this way, the information processing device 1A can determine the internal parameters of the learning model and generate the control input value determination model 202.

[0066] Figure 6 2 is a schematic diagram showing a configuration example of the sensor value control input value relationship model 203. In the information processing system of this embodiment, the sensor value control input value relationship model 203 is generated for the total number of sensor values ​​and control input values ​​(5+3=8 in this example). Figure 6 2 shows configuration examples of two of the eight sensor value control input value relationship models 203 , and illustration of the remaining six is ​​omitted.

[0067] The sensor value-control input value relationship model 203 of the present embodiment is a learning model that estimates (complements) one value among the sensor values ​​1 to 5 and the control input values ​​1 to 3 based on the other seven values. Figure 6 The first sensor value control input value relationship model 203 shown in FIG. 2 receives sensor values ​​2 to 5 and control input values ​​1 to 3 related to the reference substrate processing apparatus 101A as inputs, and outputs a sensor value 1 related to the reference substrate processing apparatus 101A. In addition, Figure 6The second sensor value control input value relationship model 203 shown in FIG. 1 receives sensor values ​​1, 3 to 5 and control input values ​​1 to 3 related to the reference substrate processing apparatus 101A as inputs, and outputs sensor value 2 related to the reference substrate processing apparatus 101A. Similarly, there are sensor value control input value relationship models 203 that output sensor value 3, sensor value control input value relationship models 203 that output sensor value 4, ..., sensor value control input value relationship models 203 that output control input value 3.

[0068] The generation of each sensor value control input value relationship model 203 is performed by the information processing device 1A that monitors and controls the reference substrate processing device 101A. The information processing device 1A can generate the sensor value control input value relationship model 203 using the same data as the learning data used in the generation of the characteristic value estimation model 201. For example, for a learning model with a structure of 7 inputs and 1 output, the information processing device 1A uses any one of the sensor values ​​1 to 5 and the control input values ​​1 to 3 included in the learning data stored in the learning data storage unit 12c as output information (target variable, correct answer value), and uses the remaining seven as input information (explanatory variables) to perform so-called supervised machine learning processing. In this way, the information processing device 1A can determine the internal parameters of the learning model and generate the sensor value control input value relationship model 203. The information processing device 1A exchanges the correspondence between the input information and the output information and performs the same machine learning processing, thereby generating eight types of sensor value control input value relationship models 203.

[0069] Figure 7 2 is a schematic diagram showing a configuration example of the sensor value conversion model 204. The sensor value conversion model 204 of this embodiment receives sensor values ​​1 to 5 related to the target substrate processing apparatus 101B as input, and outputs sensor values ​​1 to 5 related to the reference substrate processing apparatus 101A. Figure 8 1 is a schematic diagram showing a configuration example of the control input value conversion model 205. The control input value conversion model 205 of this embodiment receives control input values ​​1 to 3 related to the reference substrate processing apparatus 101A as input, and outputs control input values ​​1 to 3 related to the target substrate processing apparatus 101B.

[0070] The sensor value conversion model 204 and the control input value conversion model 205 of the present embodiment are generated by the information processing device 1B that monitors and controls the target substrate processing apparatus 101B. The information processing device 1B collects learning data in advance in order to perform machine learning processing for generating the sensor value conversion model 204 and the control input value conversion model 205. The information processing device 1B performs a predetermined substrate processing, such as a test run that determines settings or steps for data collection, in the target substrate processing apparatus 101B. At this time, the information processing device 1B obtains sensor values ​​1 to 5 from the sensor of the target substrate processing apparatus 101B, and obtains control input values ​​1 to 3 input to the target substrate processing apparatus 101B based on the sensor values ​​1 to 5. The information processing device 1B stores the obtained sensor values ​​1 to 5 and the control input values ​​1 to 3 as learning data in a corresponding manner. In addition, the learning data used in the generation of the sensor value conversion model 204 and the control input value conversion model 205 may include the above-mentioned sensor values ​​1 to 5 and control input values ​​1 to 3, but may not include characteristic values. Therefore, it is not necessary to perform the measurement of characteristic values ​​using the characteristic value measurement device 102 for the substrate processed by the target substrate processing device 101B. The information processing device 1B generates the sensor value conversion model 204 and the control input value conversion model 205 using the learning data corresponding to the collected sensor values ​​1 to 5 and control input values ​​1 to 3 and the sensor value control input value relationship model 203 generated by the information processing device 1A.

[0071] The information processing apparatus 1A reads the sensor values ​​1 to 5 and the control input values ​​1 to 3 included in the learning data collected from the target substrate processing apparatus 101B. Figure 6 The sensor value control input value relationship model 203 of the structure shown in the upper section of the figure inputs sensor values ​​2 to 5 and control input values ​​1 to 3, and obtains the sensor value 1 output by the sensor value control input value relationship model 203. The information processing apparatus 1A sets the sensor value 1 output by the sensor value control input value relationship model 203 as the sensor value 1 of the reference substrate processing apparatus 101A corresponding to the sensor value 1 of the target substrate processing apparatus 101B. Similarly, the information processing apparatus 1B obtains the sensor values ​​2 to 5 and control input values ​​1 to 3 of the reference substrate processing apparatus 101A corresponding to the sensor values ​​2 to 5 and control input values ​​1 to 3 of the target substrate processing apparatus 101B from the sensor value control input value relationship model 203. Thus, the information processing apparatus 1A can obtain the sensor values ​​1 to 5 and control input values ​​1 to 3 of the reference substrate processing apparatus 101A corresponding to the sensor values ​​1 to 5 and control input values ​​1 to 3 of the target substrate processing apparatus 101B, respectively.

[0072] For example, for a learning model with a structure of 5 inputs and 5 outputs, the information processing device 1A uses the sensor values ​​1 to 5 of the target substrate processing device 101B included in the learning data as input information (explanatory variables), and the sensor values ​​1 to 5 of the reference substrate processing device 101A obtained from the sensor value control input value relationship model 203 as output information (target variables, correct answer values), and performs so-called supervised machine learning processing. Thus, the information processing device 1A determines the internal parameters of the learning model and generates the sensor value conversion model 204. In addition, for example, for a learning model with a structure of 3 inputs and 3 outputs, the information processing device 1A uses the control input values ​​1 to 3 of the target substrate processing device 101B included in the learning data as input information (explanatory variables), and the control input values ​​1 to 3 of the reference substrate processing device 101A obtained from the sensor value control input value relationship model 203 as output information (target variables, correct answer values), and performs so-called supervised machine learning processing. Thus, the information processing device 1A determines the internal parameters of the learning model and generates the control input value conversion model 205.

[0073] <Use of learning models>

[0074] The information processing apparatus 1 monitors and controls the substrate processing apparatus 101 using the characteristic value estimation model 201 , the control input value determination model 202 , the sensor value conversion model 204 , and the control input value conversion model 205 generated by the above-described method. Fig. 9 1 is a schematic diagram for explaining monitoring of the substrate processing apparatus 101 by the information processing apparatus 1. Fig. 9 The upper part of the figure shows that the information processing apparatus 1A monitors the reference substrate processing apparatus 101A. Fig. 9 The lower part of shows a situation where the information processing apparatus 1B monitors the target substrate processing apparatus 101B.

[0075] like Fig. 9 As shown in the upper section, the information processing apparatus 1A inputs the sensor values ​​obtained from the reference substrate processing apparatus 101A and the target characteristic values ​​of the processed substrate into the control input value determination model 202, and obtains the control input values ​​output by the control input value determination model 202. The information processing apparatus 1A inputs the sensor values ​​obtained from the reference substrate processing apparatus 101A and the control input values ​​obtained from the control input value determination model 202 into the characteristic value estimation model 201, and obtains the characteristic values ​​output by the characteristic value estimation model 201. For example, the information processing apparatus 1A determines whether the characteristic value estimated by the characteristic value estimation model 201 is within a prescribed range, and notifies the content of the abnormality when the characteristic value is outside the prescribed range.

[0076] like Fig. 9As shown in the lower part, the information processing apparatus 1B inputs the sensor value obtained from the target substrate processing apparatus 101B into the sensor value conversion model 204, obtains the sensor value output by the sensor value conversion model 204, that is, converts it into the sensor value of the reference substrate processing apparatus 101A. The information processing apparatus 1B inputs the sensor value obtained from the sensor value conversion model 204 and the target characteristic value of the processed substrate into the control input value determination model 202, and obtains the control input value output by the control input value determination model 202. The information processing apparatus 1B inputs the sensor value obtained from the sensor value conversion model 204 and the control input value obtained from the control input value determination model 202 into the characteristic value estimation model 201, and obtains the characteristic value output by the characteristic value estimation model 201. For example, the information processing apparatus 1B determines whether the characteristic value estimated by the characteristic value estimation model 201 is within a prescribed range, and notifies the content of the abnormality when the characteristic value is outside the prescribed range.

[0077] Fig.10 1 is a schematic diagram for explaining the control of the substrate processing apparatus 101 by the information processing apparatus 1. Fig.10 The upper part of the figure shows the information processing apparatus 1A controlling the reference substrate processing apparatus 101A. Fig.10 The lower part of shows a situation where the information processing apparatus 1B controls the target substrate processing apparatus 101B.

[0078] like Fig.10 As shown in the upper section, the information processing apparatus 1A inputs the sensor values ​​acquired from the reference substrate processing apparatus 101A and the target characteristic values ​​of the processed substrate into the control input value determination model 202, and acquires the control input values ​​output by the control input value determination model 202. The information processing apparatus 1A inputs the control input values ​​acquired from the control input value determination model 202 into the reference substrate processing apparatus 101A, thereby causing the reference substrate processing apparatus 101A to process the substrate corresponding to the target characteristic values.

[0079] like Fig.10As shown in the lower part, the information processing apparatus 1B inputs the sensor value obtained from the target substrate processing apparatus 101B into the sensor value conversion model 204, obtains the sensor value output by the sensor value conversion model 204, that is, the sensor value converted to the reference substrate processing apparatus 101A. The information processing apparatus 1B inputs the sensor value obtained from the sensor value conversion model 204 and the target characteristic value of the processed substrate into the control input value determination model 202, and obtains the control input value output by the control input value determination model 202. The information processing apparatus 1B inputs the control input value obtained from the control input value determination model 202 into the control input value conversion model 205, obtains the control input value output by the control input value conversion model 205, that is, the control input value converted to the target substrate processing apparatus 101B. By inputting the control input value obtained from the control input value conversion model 205 to the target substrate processing apparatus 101B, the information processing apparatus 1B can cause the target substrate processing apparatus 101B to process the substrate corresponding to the target characteristic value.

[0080] In this way, the information processing device 1B can monitor and control the target substrate processing device 101B by using the characteristic value estimation model 201 and the control input value determination model 202 generated for monitoring and controlling the reference substrate processing device 101A, by intervening the sensor value conversion model 204 and the control input value conversion model 205.

[0081] <Flowchart>

[0082] Fig.11 1 is a flowchart showing an example of the steps of the learning model generation process performed by the information processing device 1A of the present embodiment. The information processing device 1A of the present embodiment performs a predetermined substrate process, such as a trial run to determine settings or steps for data collection, in a reference substrate processing device 101A that has been confirmed to be operating normally, and performs data collection for machine learning. The information acquisition unit 11a of the processing unit 11 of the information processing device 1A communicates with the reference substrate processing device 101A using the communication unit 13 to acquire sensor values ​​detected by one or more sensors provided in the reference substrate processing device 101A (step S1). The information acquisition unit 11a acquires the control input value input to the reference substrate processing device 101A for the sensor value acquired in step S1 (step S2). In addition, the information acquisition unit 11a acquires the characteristic value obtained by the characteristic value measuring device 102 by communicating with the characteristic value measuring device 102 using the communication unit 13 (step S3).

[0083] The information acquisition unit 11a establishes a correspondence between the sensor value acquired in step S1, the control input value acquired in step S2, and the characteristic value acquired in step S3, and stores them in the learning data storage unit 12c as learning data (step S4). The information acquisition unit 11a determines whether the collection of learning data is completed based on, for example, whether sufficient data for implementing machine learning can be collected (step S5). If the collection of learning data is not completed (S5: No), the information acquisition unit 11a returns the process to step S1 and continues to collect learning data. If the collection of learning data is completed (S5: Yes), the information acquisition unit 11a enters the process into step S6.

[0084] The model generation unit 11b of the processing unit 11 reads the learning data stored in the learning data storage unit 12c (step S6). The model generation unit 11b performs so-called supervised machine learning processing by using the sensor values ​​and control input values ​​included in the learning data read in step S6 as input information (explanatory variables) and the corresponding characteristic values ​​as output information (target variables, correct answer values), thereby generating a characteristic value estimation model 201 (step S7). The model generation unit 11b performs so-called supervised machine learning processing by using the sensor values ​​and characteristic values ​​included in the learning data as input information (explanatory variables) and the corresponding control input values ​​as output information (target variables, correct answer values), thereby generating a control input value determination model 202 (step S8).

[0085] The model generation unit 11b uses any one of the multiple sensor values ​​and control input values ​​included in the learning data as output information (target variable, correct answer value) and uses the remaining sensor values ​​and control input values ​​as input information (explanatory variables) to perform so-called supervised machine learning. Thus, the model generation unit 11b generates a sensor value-control input value relationship model 203 for one sensor value or control input value as output information. The model generation unit 11b performs the same machine learning process by exchanging the correspondence between the input information and the output information, thereby generating a sensor value-control input value relationship model 203 for each value of the sensor value or the control input value (step S9).

[0086] The model generation unit 11b stores information related to the characteristic value estimation model 201 generated in step S7, the control input value determination model 202 generated in step S8, and the multiple sensor value control input value relationship model 203 generated in step S9, such as information related to the structure of the learning model and parameters determined by machine learning, in the model information storage unit 12b (step S10), and ends the processing.

[0087] Fig.121 is a flowchart showing an example of the steps of the learning model generation process performed by the information processing device 1B of the present embodiment. The information processing device 1B of the present embodiment performs a predetermined substrate process, such as a trial run to determine settings or steps for data collection, in a target substrate processing device 101B newly introduced into a substrate processing factory, and performs data collection for machine learning. The information acquisition unit 11a of the processing unit 11 of the information processing device 1B communicates with the target substrate processing device 101B using the communication unit 13, and acquires the sensor value detected by one or more sensors provided in the target substrate processing device 101B (step S21). The information acquisition unit 11a acquires the control input value input to the target substrate processing device 101B for the sensor value acquired in step S21 (step S22).

[0088] The information acquisition unit 11a establishes a correspondence between the sensor value acquired in step S21 and the control input value acquired in step S22 and stores them in the learning data storage unit 12c as learning data (step S23). The information acquisition unit 11a determines whether the collection of learning data is completed based on, for example, whether sufficient data for implementing machine learning can be collected (step S24). If the collection of learning data is not completed (S24: No), the information acquisition unit 11a returns the process to step S21 and continues to collect learning data. If the collection of learning data is completed (S24: Yes), the information acquisition unit 11a enters the process into step S25.

[0089] The model generation unit 11b of the processing unit 11 acquires information related to the characteristic value estimation model 201, the control input value determination model 202, and the sensor value control input value relationship model 203 generated by the information processing device 1A, for example, by communicating with the information processing device 1A using the communication unit 13, or by exchanging information via a recording medium (step S25), and stores the information in the model information storage unit 12b. The model generation unit 11b reads the sensor value control input value relationship model 203 stored in the model information storage unit 12b (step S26). The model generation unit 11b generates the sensor value and control input value of the reference substrate processing device 101A based on the sensor value and control input value of the target substrate processing device 101B included in the learning data stored in the learning data storage unit 12c and the sensor value control input value relationship model 203 read in step S26 (step S27).

[0090] The model generation unit 11b uses the sensor value of the target substrate processing device 101B contained in the learning data as input information (explanatory variable), and uses the sensor value of the reference substrate processing device 101A obtained from the sensor value control input value relationship model 203 in step S27 as output information (target variable, correct answer value), and performs so-called supervised machine learning processing. Thus, the model generation unit 11b generates a sensor value conversion model 204 (step S28). In addition, the model generation unit 11b uses the control input value of the target substrate processing device 101B contained in the learning data as input information (explanatory variable), and uses the control input value of the reference substrate processing device 101A obtained from the sensor value control input value relationship model 203 in step S27 as output information (target variable, correct answer value), and performs so-called supervised machine learning processing. Thus, the model generation unit 11b generates a control input value conversion model 205 (step S29).

[0091] The model generation unit 11b stores information related to the sensor value conversion model 204 generated in step S28 and the control input value conversion model 205 generated in step S29, such as information related to the structure of the learning model and parameters determined by machine learning, in the model information storage unit 12b (step S30), and ends the processing.

[0092] Fig.13 as well as Fig.14 1 is a flowchart showing an example of the steps of monitoring and controlling the substrate processing apparatus 101 by the information processing apparatus 1 of the present embodiment. The information acquisition unit 11a of the processing unit 11 of the information processing apparatus 1 of the present embodiment communicates with the substrate processing apparatus 101 using the communication unit 13, and acquires the sensor value detected by one or more sensors provided in the substrate processing apparatus 101 (step S41). The information acquisition unit 11a determines whether it is necessary to convert the sensor value acquired in step S41 from the sensor value of the target substrate processing apparatus 101B to the sensor value of the reference substrate processing apparatus 101A (step S42).

[0093] For example, in the information processing system of the present embodiment, setting information indicating whether the information processing apparatus 1 is the information processing apparatus 1A that monitors and controls the reference substrate processing apparatus 101A or the information processing apparatus 1B that monitors and controls the target substrate processing apparatus 101B is input in advance by a user or the like and stored in the storage unit 12 or the like. The information acquisition unit 11a reads the setting information and determines whether it is the information processing apparatus 1A or the information processing apparatus 1B, thereby being able to determine whether sensor value conversion is required. When the information acquisition unit 11a determines that it is the information processing apparatus 1B that monitors and controls the target substrate processing apparatus 101B and sensor value conversion is required (S42: Yes), the sensor value conversion model 204 stored in the model information storage unit 12b is used to convert the sensor value of the target substrate processing apparatus 101B acquired in step S41 into the sensor value of the reference substrate processing apparatus 101A (step S43), and the process proceeds to step S44. When the information acquisition unit 11 a determines that it is the information processing apparatus 1A that monitors and controls the reference substrate processing apparatus 101A and conversion of the sensor value is unnecessary ( S42 : No), the process proceeds to step S44 .

[0094] The control processing unit 11d of the processing unit 11 inputs the sensor value acquired in step S41 or the sensor value converted in step S43 and the target characteristic value of the substrate processed by the substrate processing apparatus 101 into the control input value determination model 202 stored in the model information storage unit 12b. Furthermore, the control processing unit 11d determines the control input value corresponding to the sensor value and the target characteristic value by acquiring the control input value output by the control input value determination model 202 (step S44). In addition, the target characteristic value is input in advance by a user or the like and stored in the storage unit 12 as setting information.

[0095] The characteristic value estimation unit 11c of the processing unit 11 inputs the sensor value acquired in step S41 or the sensor value converted in step S43 and the control input value determined in step S44 to the characteristic value estimation model 201 stored in the model information storage unit 12b. The characteristic value estimation unit 11c estimates the characteristic value of the substrate processed by the substrate processing apparatus 101 by acquiring the characteristic value output by the characteristic value estimation model 201 (step S45). The characteristic value estimation unit 11c determines whether there is an abnormality related to the substrate processing performed by the substrate processing apparatus 101 based on the characteristic value estimated in step S45, for example, by determining whether the characteristic value exceeds a threshold value (step S46). When it is determined that there is an abnormality (S46: Yes), the display processing unit 11e of the processing unit 11 notifies the user of the abnormality by displaying a message notifying the occurrence of the abnormality on the display unit 124 (step S47). The control processing unit 11d stops the substrate processing in which the abnormality has occurred (step S48), and ends the processing.

[0096] When it is determined that there is an abnormality based on the estimated characteristic value (S46: No), the control processing unit 11d determines whether it is necessary to convert the control input value of the reference substrate processing apparatus 101A to the control input value of the target substrate processing apparatus 101B for the control input value determined in step S44 (step S49). As described above, in the information processing system of the present embodiment, setting information indicating whether the information processing apparatus 1 is the information processing apparatus 1A that monitors and controls the reference substrate processing apparatus 101A or the information processing apparatus 1B that monitors and controls the target substrate processing apparatus 101B is stored in the storage unit 12 or the like. The control processing unit 11d determines whether it is the information processing apparatus 1A or the information processing apparatus 1B by reading the setting information, thereby being able to determine whether the control input value needs to be converted.

[0097] When the control processing unit 11d determines that it is the information processing unit 1B that monitors and controls the target substrate processing unit 101B and that the conversion of the control input value is necessary (S49: Yes), the control processing unit 11d uses the control input value conversion model 205 stored in the model information storage unit 12b to convert the control input value of the reference substrate processing unit 101A acquired in step S44 into the control input value of the target substrate processing unit 101B (step S50), and the process proceeds to step S51. When the control processing unit 11d determines that it is the information processing unit 1A that monitors and controls the reference substrate processing unit 101A and that the conversion of the control input value is not necessary (S49: No), the process proceeds to step S51.

[0098] The control processing unit 11d inputs the control input value determined in step S44 or the control input value converted in step S50 to the substrate processing apparatus 101 (step S51). Thus, the control processing unit 11d can control the substrate processing of the substrate processing apparatus 101. The control processing unit 11d determines whether the processing of the substrate by the substrate processing apparatus 101 is completed (step S52). In the case where the processing of the substrate is not completed (S52: No), the control processing unit 11d returns the processing to step S41 and repeats the above-mentioned processing. In the case where the processing of the substrate is completed (S52: Yes), the control processing unit 11d ends the monitoring and control of the substrate processing apparatus 101.

[0099] Summary

[0100] In the information processing system of the present embodiment having the above structure, the information processing device 1 obtains the sensor value of the target substrate processing device 101B. The information processing device 1 inputs the obtained sensor value of the target substrate processing device 101B into the sensor value conversion model 204, which is a model obtained by machine learning in a manner of receiving the sensor value of the target substrate processing device 101B as input and outputting the sensor value of the reference substrate processing device 101A. The information processing device 1 obtains the sensor value of the reference substrate processing device 101A output by the sensor value conversion model 204. The information processing device 1 inputs the obtained sensor value of the reference substrate processing device 101A together with the desired target characteristic value (target value) into the control input value determination model 202, which is a model obtained by machine learning in a manner of receiving the target characteristic value and the sensor value of the reference substrate processing device 101A as input and outputting the control input value of the reference substrate processing device 101A. The information processing device 1 obtains the control input value of the reference substrate processing device 101A output by the control input value determination model 202. The information processing device 1 inputs the obtained control input value of the reference substrate processing device 101A into the control input value conversion model 205, which is a model obtained by machine learning in a manner of receiving the control input value of the reference substrate processing device 101A as input and outputting the control input value of the target substrate processing device 101B. The information processing device 1 obtains the control input value of the target substrate processing device 101B output by the control input value conversion model 205. The information processing device 1 controls the target substrate processing device 101B based on the obtained control input value.

[0101] Thus, in the information processing system of the present embodiment, the information processing apparatus 1 that controls the target substrate processing apparatus 101B can control the target substrate processing apparatus 101B using the control input value determination model 202 generated for the reference substrate processing apparatus 101A. Therefore, it can be expected that the information processing system of the present embodiment can correct the mechanical error with the reference substrate processing apparatus 101A using the sensor value conversion model 204 and the control input value conversion model 205 and control the target substrate processing apparatus 101B.

[0102] In addition, in the information processing system of the present embodiment, the information processing device 1 acquires learning data that establishes a correspondence between the sensor value and the control input value of the target substrate processing device 101B. The information processing device 1 acquires the sensor value and the control input value of the reference substrate processing device 101A corresponding to the sensor value and the control input value of the target substrate processing device 101B based on the sensor value control input value relationship model 203 pre-generated for the reference substrate processing device 101A and the acquired learning data. The sensor value control input value relationship model 203 is a learning model obtained by machine learning in a manner of receiving a part of a plurality of sensor values ​​and control input values ​​as input and outputting the sensor value or control input value of the reference substrate processing device 101A not included in the part. The information processing device 1 generates a sensor value conversion model 204 by machine learning based on the sensor value of the target substrate processing device 101B and the sensor value of the reference substrate processing device 101A. In addition, the information processing device 1 generates a control input value conversion model 205 by machine learning based on the control input value of the target substrate processing device 101B and the control input value of the reference substrate processing device 101A.

[0103] In the information processing system of the present embodiment, the information processing device 1 that monitors and controls the reference substrate processing device 101A acquires learning data that associates the sensor value and control input value of the reference substrate processing device 101A. The information processing device 1 generates the sensor value control input value relationship model 203 by machine learning using the learning data.

[0104] Thus, the information processing system of this embodiment can use the sensor value control input value relationship model 203 related to the reference substrate processing apparatus 101A, and generate and utilize the sensor value conversion model 204 and the control input value conversion model 205 by the information processing apparatus 1 that monitors and controls the target substrate processing apparatus 101B.

[0105] In addition, in the information processing system of the present embodiment, the information processing device 1 acquires learning data that establishes correspondence between the sensor value, control input value, and characteristic value related to the reference substrate processing device 101A, and generates the control input value determination model 202 by machine learning using the learning data. In addition, the information processing device 1 uses the learning data to generate a characteristic value estimation model that receives the sensor value and control input value of the reference substrate processing device 101A as input and outputs the characteristic value of the reference substrate processing device 101A. By using these learning models, the information processing device 1 can monitor and control the reference substrate processing device 101A, etc. In addition, by combining these learning models with the above-mentioned sensor value conversion model 204 and control input value conversion model 205, the information processing device 1 can monitor and control the target substrate processing device 101B, etc.

[0106] In addition, in the information processing system of the present embodiment, the information processing device 1 acquires the sensor value of the target substrate processing device 101B, inputs the acquired sensor value to the sensor value conversion model 204, and acquires the sensor value of the reference substrate processing device 101A output by the sensor value conversion model 204. The information processing device 1 inputs the acquired sensor value of the reference substrate processing device 101A together with the desired target characteristic value to the control input value determination model 202, and acquires the control input value of the reference substrate processing device 101A output by the control input value determination model 202. The information processing device 1 inputs the sensor value and the control input value of the reference substrate processing device 101A to the characteristic value estimation model 201, and acquires the characteristic value of the reference substrate processing device 101A output by the characteristic value estimation model 201. The information processing device 1 outputs information related to the acquired characteristic value, such as the determination result of the presence or absence of abnormality based on the characteristic value.

[0107] Thus, in the information processing system of the present embodiment, the information processing apparatus 1 that controls the target substrate processing apparatus 101B can monitor the presence of abnormalities of the target substrate processing apparatus 101B using the characteristic value estimation model 201 generated for the reference substrate processing apparatus 101A. Therefore, it can be expected that the information processing system of the present embodiment can use the sensor value conversion model 204 and the control input value conversion model 205 to correct the mechanical error with the reference substrate processing apparatus 101A and monitor the target substrate processing apparatus 101B.

[0108] <Implementation method 2>

[0109] Fig.152 is a schematic diagram showing a configuration example of the control input value determination model 222 of Embodiment 2. The control input value determination model 202 is a configuration that receives sensor values ​​1 to 5 and target characteristic values ​​related to the reference substrate processing apparatus 101A as inputs and outputs control input values ​​1 to 3 to be input to the reference substrate processing apparatus 101A (see Figure 5 ). The target value accepted as input by the control input value determination model is not limited to the target characteristic value. The control input value determination model 222 of the second embodiment is a structure that accepts sensor values ​​1 to 5 related to the reference substrate processing apparatus 101A and the target values ​​of these sensor values ​​1 to 5, that is, target sensor values ​​1 to 5, as inputs, and outputs control input values ​​1 to 3 to be input to the reference substrate processing apparatus 101A.

[0110] The information processing device 1 of the second embodiment includes, instead of or in addition to the control input value determination model 202, Fig.15 The control input value determination model 222 of the structure shown. The information processing apparatus 1A of the second embodiment performs feedback control using the control input value determination model 222, thereby allowing the substrate processing to be performed so that the sensor value outputted from the reference substrate processing apparatus 101A becomes the target sensor value.

[0111] The generation of the control input value determination model 222 of the second embodiment is performed, for example, by the information processing device 1A that monitors and controls the reference substrate processing device 101A. The information processing device 1A performs substrate processing in the reference substrate processing device 101A, for example, and stores the corresponding learning data for the target sensor value at that time, the control input value input to the reference substrate processing device 101A, and the sensor value obtained from the sensor of the reference substrate processing device 101A and accumulates them in the learning data storage unit 12c. The information processing device 1A performs the so-called supervised machine learning process by using the sensor value and the target sensor value included in the learning data as input information (explanatory variables) and the control input value as output information (target variable, correct answer value), and can generate the control input value determination model 222.

[0112] Fig.16This is a schematic diagram for explaining the control of the reference substrate processing apparatus 101A by the information processing apparatus 1A. The information processing apparatus 1A inputs the sensor value acquired from the reference substrate processing apparatus 101A and the target sensor value which is the target value of the sensor into the control input value determination model 222, and acquires the control input value output by the control input value determination model 222. The information processing apparatus 1A inputs the control input value acquired from the control input value determination model 222 into the reference substrate processing apparatus 101A, thereby causing the reference substrate processing apparatus 101A to perform substrate processing corresponding to the target sensor value, and acquires the sensor value of the reference substrate processing apparatus 101A at this time.

[0113] The information processing device 1A feeds back the acquired sensor value and inputs it into the control input value determination model 222. At this time, the information processing device 1A inputs the same target sensor value as before into the control input value determination model 222. The information processing device 1A acquires the control input value output by the control input value determination model 222 and inputs it into the reference substrate processing device 101A, and acquires the sensor value output by the reference substrate processing device 101A. By repeatedly performing this processing cycle by the information processing device 1A, the sensor value output by the reference substrate processing device 101A can be made close to the target sensor value.

[0114] Fig.17 1 is a schematic diagram for explaining the control of the target substrate processing apparatus 101B by the information processing apparatus 1B. The information processing apparatus 1B inputs the sensor value acquired from the target substrate processing apparatus 101B to the sensor value conversion model 204, and acquires the sensor value of the reference substrate processing apparatus 101A output by the sensor value conversion model 204. The information processing apparatus 1B inputs the sensor value of the reference substrate processing apparatus 101A acquired from the sensor value conversion model 204 and the target sensor value which is the target value of the sensor to the control input value determination model 222, and acquires the control input value for the reference substrate processing apparatus 101A output by the control input value determination model 222. The information processing apparatus 1B inputs the acquired control input value for the reference substrate processing apparatus 101A to the control input value conversion model 205, and acquires the control input value for the target substrate processing apparatus 101B output by the control input value conversion model 205. The information processing apparatus 1B inputs the control input value acquired from the control input value conversion model 205 to the target substrate processing apparatus 101B, thereby causing the target substrate processing apparatus 101B to perform substrate processing corresponding to the target sensor value, and acquires the sensor value of the target substrate processing apparatus 101B at this time.

[0115] By repeatedly performing this processing cycle by the information processing apparatus 1B, the sensor value output by the target substrate processing apparatus 101B can be brought close to the target sensor value. In addition, by using the sensor value conversion model 204 and the control input value conversion model 205, the information processing apparatus 1B can control the target substrate processing apparatus 101B using the control input value determination model 222 generated for controlling the reference substrate processing apparatus 101A.

[0116] In addition, the other structures of the information processing system of Embodiment 2 are the same as those of the information processing system of Embodiment 1, and therefore the same reference numerals are given to the same parts, and detailed descriptions thereof are omitted.

[0117] The embodiments disclosed herein are illustrative in all aspects and should not be construed as restrictive. The scope of the present disclosure is indicated by the claims rather than the above meaning, and is intended to include all modifications within the meaning and scope equivalent to the claims.

[0118] The matters described in each embodiment can be combined with each other. In addition, the independent claims and dependent claims described in the claims can be combined with each other in all combinations regardless of the reference form. Moreover, the claims use the form of recording claims that reference two or more other claims (multiple claim form), but are not limited to this. It is also possible to record multiple claims that reference at least one multiple claim (multiple claims referencing multiple claims).

[0119] Description of Reference Numerals

[0120] 1, 1A, 1B…information processing device (computer); 11…processing unit; 11a…information acquisition unit; 11b…model generation unit; 11c…characteristic value estimation unit; 11d…control processing unit; 11e…display processing unit; 12…storage unit; 12a…program (computer program); 12b…model information storage unit; 12c…learning data storage unit; 13…communication unit; 14…display unit; 15…operation unit; 101…substrate processing device; 101A…reference substrate processing device (reference device); 101B…object substrate processing device (object device); 201…characteristic value estimation model; 202…control input value determination model; 203…sensor value control input value relationship model; 204…sensor value conversion model; 205…control input value conversion model.

Claims

1. An information processing method, wherein an information processing device executes: Get the sensor value of the target device, The sensor value of the target device is input into a sensor value conversion model to obtain the sensor value of the reference device output by the sensor value conversion model, wherein: The sensor value conversion model is a model obtained by machine learning in a manner of receiving the sensor value of the target device as input and outputting the sensor value of the reference device. The sensor value of the reference device obtained is input into a control input value determination model together with a desired target value to obtain a control input value of the reference device output by the control input value determination model, wherein the control input value determination model is a model obtained by machine learning in a manner of accepting the target value and the sensor value of the reference device as inputs and outputting the control input value of the reference device, The control input value of the reference device is input into a control input value conversion model to obtain the control input value of the object device output by the control input value conversion model, wherein the control input value conversion model is a model obtained by machine learning in a manner of accepting the control input value of the reference device as input and outputting the control input value of the object device. The target device is controlled based on the acquired control input value of the target device.

2. The information processing method according to claim 1, wherein: Acquiring learning data for establishing correspondence between sensor values ​​and control input values ​​for the target device, Based on the sensor value control input value relationship model and the acquired learning data, the sensor value and control input value of the reference device corresponding to the sensor value and control input value of the object device included in the learning data are acquired, wherein the sensor value control input value relationship model is a model obtained by machine learning in a manner of accepting a part of a plurality of sensor values ​​and control input values ​​as input and outputting the sensor value or control input value of the reference device not included in the part, The sensor value conversion model is generated by machine learning based on the sensor value included in the learning data and the acquired sensor value of the reference device. The control input value conversion model is generated by machine learning based on the control input values ​​included in the learning data and the acquired control input values ​​of the reference device.

3. The information processing method according to claim 2, wherein: Acquire learning data for establishing correspondence between sensor values ​​and control input values ​​for the reference device, The sensor value control input value relationship model is generated by machine learning using the acquired learning data.

4. The information processing method according to claim 1, wherein: Acquiring learning data for establishing correspondence between sensor values, control input values, and characteristic values ​​for the reference device, The control input value determination model is generated based on the acquired learning data.

5. The information processing method according to claim 4, wherein: A characteristic value estimation model is generated based on the acquired learning data, wherein the characteristic value estimation model receives a sensor value and a control input value of the reference device as input and outputs the characteristic value of the reference device.

6. The information processing method according to claim 5, wherein: Get the sensor value of the target device, The sensor value of the target device is input into the sensor value conversion model to obtain the sensor value of the reference device output by the sensor value conversion model. The sensor value of the reference device obtained is input into the control input value determination model together with the desired target value to obtain the control input value of the reference device output by the control input value determination model. The sensor value and control input value of the reference device are input into the characteristic value estimation model to obtain the characteristic value of the reference device output by the characteristic value estimation model. Output the information related to the above-obtained characteristic values.

7. The information processing method according to claim 6, wherein: Based on the above characteristic values ​​obtained, determine whether there is an abnormality. Outputs information related to the presence or absence of abnormality.

8. An information processing method, wherein an information processing device performs: Get the sensor value of the target device, The sensor value of the target device is input into a sensor value conversion model to obtain the sensor value of the reference device output by the sensor value conversion model, wherein: The sensor value conversion model is a model obtained by machine learning in a manner of receiving the sensor value of the target device as input and outputting the sensor value of the reference device. The sensor value of the reference device obtained is input into a control input value determination model together with a desired target value to obtain a control input value of the reference device output by the control input value determination model, wherein the control input value determination model is a model obtained by machine learning in a manner of accepting the target value and the sensor value of the reference device as inputs and outputting the control input value of the reference device, The sensor value and control input value of the reference device are input into a characteristic value estimation model to obtain the characteristic value of the reference device output by the characteristic value estimation model, wherein the characteristic value estimation model is a model obtained by machine learning in a manner of accepting the sensor value and control input value of the reference device as input and outputting the characteristic value of the reference device. Information related to the acquired characteristic value of the reference device is output.

9. A computer program that causes a computer to perform a process: Get the sensor value of the target device, The sensor value of the target device is input into a sensor value conversion model to obtain the sensor value of the reference device output by the sensor value conversion model, wherein: The sensor value conversion model is a model obtained by machine learning in a manner of receiving the sensor value of the target device as input and outputting the sensor value of the reference device. The sensor value of the reference device obtained is input into a control input value determination model together with a desired target value to obtain a control input value of the reference device output by the control input value determination model, wherein the control input value determination model is a model obtained by machine learning in a manner of accepting the target value and the sensor value of the reference device as inputs and outputting the control input value of the reference device, The control input value of the reference device is input into a control input value conversion model to obtain the control input value of the object device output by the control input value conversion model, wherein the control input value conversion model is a model obtained by machine learning in a manner of accepting the control input value of the reference device as input and outputting the control input value of the object device. The target device is controlled based on the acquired control input value of the target device.

10. A computer program that causes a computer to perform the process: Get the sensor value of the target device, The sensor value of the target device is input into a sensor value conversion model to obtain the sensor value of the reference device output by the sensor value conversion model, wherein: The sensor value conversion model is a model obtained by machine learning in a manner of receiving the sensor value of the target device as input and outputting the sensor value of the reference device. The sensor value of the reference device obtained is input into a control input value determination model together with a desired target value to obtain a control input value of the reference device output by the control input value determination model, wherein the control input value determination model is a model obtained by machine learning in a manner of accepting the target value and the sensor value of the reference device as inputs and outputting the control input value of the reference device, The sensor value and control input value of the reference device are input into a characteristic value estimation model to obtain the characteristic value of the reference device output by the characteristic value estimation model, wherein the characteristic value estimation model is a model obtained by machine learning in a manner of accepting the sensor value and control input value of the reference device as input and outputting the characteristic value of the reference device. Information related to the acquired characteristic value of the reference device is output.

11. An information processing device, comprising: A first acquisition unit acquires a sensor value of a target device; The second acquisition unit inputs the acquired sensor value of the target device into the sensor value conversion model to acquire the sensor value of the reference device output by the sensor value conversion model, wherein: The sensor value conversion model is a model obtained by machine learning in a manner of receiving the sensor value of the target device as input and outputting the sensor value of the reference device; a third acquisition unit, inputting the acquired sensor value of the reference device together with the desired target value into a control input value determination model to obtain the control input value of the reference device output by the control input value determination model, wherein the control input value determination model is a model obtained by machine learning in a manner of receiving the target value and the sensor value of the reference device as inputs and outputting the control input value of the reference device; a fourth acquisition unit, inputting the acquired control input value of the reference device into a control input value conversion model to acquire the control input value of the target device output by the control input value conversion model, wherein the control input value conversion model is a model obtained by machine learning in a manner of accepting the control input value of the reference device as input and outputting the control input value of the target device; and The control processing unit controls the target device based on the acquired control input value of the target device.

12. An information processing device comprising a processing unit, The processing unit has: A first acquisition unit acquires a sensor value of a target device; The second acquisition unit inputs the acquired sensor value of the target device into the sensor value conversion model to acquire the sensor value of the reference device output by the sensor value conversion model, wherein: The sensor value conversion model is a model obtained by machine learning in a manner of receiving the sensor value of the target device as input and outputting the sensor value of the reference device; a third acquisition unit, inputting the acquired sensor value of the reference device together with the desired target value into a control input value determination model to obtain the control input value of the reference device output by the control input value determination model, wherein the control input value determination model is a model obtained by machine learning in a manner of receiving the target value and the sensor value of the reference device as inputs and outputting the control input value of the reference device; a fourth acquisition unit, inputting the acquired sensor value and control input value of the reference device into a characteristic value estimation model to acquire the characteristic value of the reference device output by the characteristic value estimation model, wherein the characteristic value estimation model is a model obtained by machine learning in a manner of accepting the sensor value and control input value of the reference device as input and outputting the characteristic value of the reference device; and The output unit outputs information related to the acquired characteristic value of the reference device.

Images