Computer program, information processing method, and information processing device

Abstract

Provided are a computer program, an information processing method, and an information processing device capable of anticipating estimation of a substrate processing state on the basis of spectral data measured during substrate processing.　A computer program according to the present embodiment causes a computer to execute: processing for acquiring spectral data measured pertaining to substrate processing; processing for separating the acquired spectral data into line spectral data for a plurality of reactive species; and processing for predicting at least one of electron density, electron temperature, or electron energy distribution for each of the reactive species on the basis of the separated line spectral data.

Description

Computer program, information processing method, and information processing device

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

[0002] Patent Document 1 proposes a film thickness measurement method in which relationship information indicating the relationship between the absorbance spectrum of a film on a substrate and the film thickness is stored in a memory unit, the absorbance spectrum of the processed substrate is measured, and the film thickness of the film present on the surface of the processed substrate is derived from the measured absorbance spectrum based on the stored relationship information.

[0003] Japanese Patent Application Laid-Open No. 2023-169638

[0004] The present disclosure provides a computer program, an information processing method, and an information processing device that are expected to be able to estimate the state of substrate processing based on spectrum data measured during substrate processing.

[0005] A computer program according to one embodiment causes a computer to execute a process of acquiring spectral data measured in relation to substrate processing, separating the acquired spectral data into line spectral data for a plurality of reactive species, and predicting at least one of an electron density, an electron temperature, and an electron energy distribution for each reactive species based on the separated line spectral data.

[0006] According to the present disclosure, it is expected that the state of substrate processing can be estimated based on spectral data measured during substrate processing.

[0007] FIG. 1 is a schematic diagram for explaining an overview of an information processing system according to the present embodiment. FIG. 2 is a block diagram showing an example of a configuration of an information processing device according to the present embodiment. FIG. 3 is a schematic diagram for explaining an example of a configuration of a separation model used in spectrum separation processing. FIG. 4 is a schematic diagram for explaining an example of machine learning of the separation model. FIG. 5 is a schematic diagram showing an example of a table for determining a type of spectral width that affects electron temperature order prediction of reactive species. FIG. 6 is a schematic diagram showing an example of a table for determining an electron temperature order relative to a natural width and a Stark width. FIG. 7 is a schematic diagram for explaining examples of line spectrum data and Doppler width. FIG. 8 is a flowchart showing an example of the procedure of electron temperature order prediction processing performed by the information processing device according to the present embodiment. FIG. 9 is a schematic diagram for explaining an example of a configuration of a reactive species model. FIG. 10 is a flowchart showing an example of the procedure of electron density prediction processing performed by the information processing device according to the present embodiment. FIG. 11 is a schematic diagram showing an example of time series data.

[0008] Specific examples of information processing systems according to embodiments of the present disclosure will be described below with reference to the drawings. Note that the present disclosure is not limited to these examples, but is defined by the claims, and is intended to include all modifications within the meaning and scope of the claims.

[0009] <System Overview> FIG. 1 is a schematic diagram illustrating an overview of an information processing system according to this embodiment. The information processing system according to this embodiment is configured with an information processing apparatus 1 and a substrate processing apparatus 3. The substrate processing apparatus 3 is an apparatus that generates plasma in a chamber containing, for example, a semiconductor substrate (wafer) and performs various substrate processes, such as CVD (Chemical Vapor Deposition) to shape the substrate or etching. The substrate processing apparatus 3 is equipped with a measuring instrument in the chamber that measures the plasma emission spectrum, performs measurements repeatedly at predetermined intervals, and transmits the spectral data obtained by the measurements to the information processing apparatus 1. The spectral data is data related to light emitted from excited states of atoms or molecules in the plasma. The wavelength of the light emitted varies depending on the atomic species, molecular species, plasma state, etc., and this property can be utilized to evaluate the time variation of a specific process and medium information within the chamber. However, since the measuring instrument installed at a specific position in the chamber of the substrate processing apparatus 3 measures the spectrum for all light within its sensitivity range, the spectral data also includes data related to attenuation that is not the subject of evaluation.

[0010] The information processing device 1 acquires spectral data measured by a measuring instrument of the substrate processing device 3, analyzes and evaluates the state of substrate processing based on the acquired spectral data, and controls the operation of the substrate processing device 3 according to the results of the analysis and evaluation. The information processing device 1 may be an apparatus integrated with the substrate processing device 3, or may be a separate apparatus. Furthermore, there may be multiple substrate processing devices 3 for which the information processing device 1 evaluates and controls the substrate processing.

[0011] As described above, the spectral data obtained by measurement by the measuring instrument of the substrate processing apparatus 3 is data containing a mixture of multiple spectra due to multiple reactive species (atomic species, molecular species, etc.). Therefore, the information processing apparatus 1 according to this embodiment performs a spectral separation process to separate the spectral data obtained from the substrate processing apparatus 3 into spectral data for each reactive species (hereinafter referred to as line spectral data). In this embodiment, the information processing apparatus 1 uses a learning model generated in advance by machine learning to separate the spectral data obtained from the substrate processing apparatus 3 into line spectral data for each predetermined reactive species and spectral data other than the predetermined reactive species (hereinafter referred to as background spectral data). The learning model receives spectral data as input and is machine-learned in advance to separate the spectral data into multiple line spectral data and background spectral data.

[0012] Next, the information processing device 1 according to this embodiment performs a process of predicting the order (number of digits) of the electron temperature for each of the line spectrum data and the background spectrum data for each separated reactive species. The information processing device 1 predicts the order of the electron temperature based on the spectral width of the line spectrum data of the reactive species. The information processing device can calculate the spectral width of each reactive species by appropriately adopting, for example, Doppler broadening (Doppler width), natural broadening, or Stark broadening (Stark width) as the spectral width of each reactive species depending on the substrate processing conditions, etc. The information processing device 1 predicts the order of the electron temperature for each reactive species by performing a predetermined calculation based on the calculated spectral width or by referring to a predetermined table. The information processing device 1 also predicts the order of the electron temperature by performing fitting assuming that the background spectrum data follows, for example, a Boltzmann distribution.

[0013] The information processing device 1 uses the order of the predicted electron temperature to limit the search range when searching for an optimal value in the next stage of processing, that is, predicting the electron density. This enables the information processing device 1 to efficiently perform processing such as searching, and is expected to reduce the load. However, the information processing device 1 can also predict the next stage of electron density without predicting the order of the electron temperature.

[0014] Next, the information processing device 1 according to this embodiment performs a process of predicting the electron density of each reaction species based on the line spectrum data and background spectrum data of each separated reaction species and the predicted order of electron temperature. The information processing device 1 pre-stores a reaction species model that receives the electron temperature and electron density for each reaction species as input and outputs the emission intensity. The information processing device 1 can predict the electron density and electron temperature of each reaction species by searching for the input electron temperature and electron density so that the difference between the output of this reaction species model and the line spectrum data of each reaction species is smaller than a threshold value. Note that the information processing device 1 can limit the search range of the electron temperature by using the order of the electron temperature predicted in the previous process during this search.

[0015] The information processing device 1 stores the prediction results of the order of electron temperature, electron density, electron temperature, etc. obtained by these processes in a prediction result DB (database) 5. The information processing device 1 repeatedly acquires spectrum data from the substrate processing device 3 and performs the above prediction based on the acquired spectrum data at a predetermined cycle, and time-series data of the prediction results repeated at the predetermined cycle is stored and accumulated in the prediction result DB 5. The information processing device 1 predicts values ​​of the electron density, electron temperature, etc. at the next timing based on changes in past values ​​using the time-series data stored in the prediction result DB 5. The information processing device 1 can further limit the search range of the electron density, electron temperature, etc. by feeding back information such as the value predicted based on the time-series data or the range calculated based on this predicted value to the prediction process of the electron density, electron temperature, etc.

[0016] Based on the predicted electron density and electron temperature of each reactive species, the information processing apparatus 1 according to this embodiment can control the substrate processing by adjusting settings such as pressure, gas flow rate, or power in the substrate processing performed by the substrate processing apparatus 3. Furthermore, the information processing apparatus 1 can provide the user with information such as the predicted results of the electron density and electron temperature of each reactive species and time-series changes in the predicted results on a display or the like.

[0017] <Device Configuration> Fig. 2 is a block diagram showing an example configuration of an information processing device 1 according to this embodiment. The information processing device 1 according to this embodiment can be realized by installing a predetermined application program or the like in a general-purpose information processing device such as a personal computer or a server computer. The information processing device 1 according to this embodiment is configured to include a processing unit 11, a storage unit 12, a communication unit 13, a display unit 14, an operation unit 15, etc. Note that, in this embodiment, the processing will be described as being performed by a single information processing device 1, but the processing of the information processing device 1 may be distributed among multiple devices.

[0018] The processing unit 11 is configured using an arithmetic processing device such as a CPU (Central Processing Unit), an MPU (Micro-Processing Unit), a GPU (Graphics Processing Unit) or a quantum processor, a ROM (Read Only Memory), a RAM (Random Access Memory), etc. The processing unit 11 reads and executes a program 12a stored in the storage unit 12 to perform various processes, such as a process of acquiring spectral data from the substrate processing apparatus 3, a process of separating the spectral data into line spectral data for each reactive species, a process of predicting the electron temperature order for each reactive species, and a process of predicting the electron density and electron temperature for each reactive species.

[0019] The storage unit 12 is configured using a large-capacity storage device such as a hard disk or an SSD (Solid State Drive). 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 this embodiment, the storage unit 12 stores a program 12a executed by the processing unit 11. The storage unit 12 also includes a model information storage unit 12b that stores information about models used when performing processing such as separation processing into line spectrum data and prediction of electron density, and a prediction result DB 5 that stores and accumulates prediction results of electron density and electron temperature.

[0020] In this embodiment, the program (computer program, program product) 12a is provided in a form recorded on a recording medium 99 such as a memory card or an optical disc, 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 also be written to the storage unit 12, for example, during the manufacturing stage of the information processing device 1. Alternatively, the program 12a may be distributed by a remote server device or the like and acquired by the information processing device 1 via communication. For example, the program 12a may be read from the recording medium 99 by a writing device and written to the storage unit 12 of the information processing device 1. The program 12a may be provided in a form distributed via a network or in a form recorded on the recording medium 99.

[0021] The model information storage unit 12b stores information about various models, such as physical models representing the characteristics of reactive species and learning models generated by simulation and machine learning. The information about the models may include, for example, information indicating the configuration of the models and information such as values ​​of predetermined internal parameters. In this embodiment, the model information storage unit 12b stores, for example, information about a separation model that separates spectral data acquired from the substrate processing apparatus 3 into line spectral data of multiple reactive species and background spectral data. The model information storage unit 12b also stores information about a reactive species model that predicts the emission intensity of each reactive species from input electron temperature and electron density. The model information storage unit 12b also stores information about a prediction model that predicts values ​​at the next timing based on time-series data such as electron density and electron temperature stored in the prediction result DB5.

[0022] In the present embodiment, one or more models whose information is stored in the model information storage unit 12b are generated in advance by machine learning or the like in the information processing device 1, but this is not limited to this. Information about these models may be generated in a device different from the information processing device 1 and stored in the model information storage unit 12b. Information about the models may also be stored in a device different from the information processing device 1.

[0023] The prediction result DB 5 stores and accumulates information such as the electron density and electron temperature of each reactive species predicted based on the spectrum data acquired from the substrate processing apparatus 3. The prediction result DB 5 stores, in association with each other, information such as the date and time when the spectrum data was acquired from the substrate processing apparatus 3, identification information of the substrate to be processed, the acquired spectrum data, the separated line spectrum data and background spectrum data, and the predicted electron temperature order, electron density, and electron temperature.

[0024] The communication unit 13 is connected to the substrate processing apparatus 3 via, for example, a communication line, and exchanges data with the substrate processing apparatus 3. In this embodiment, the communication unit 13 receives spectrum data transmitted from the substrate processing apparatus 3 and provides the data to the processing unit 11. The communication unit 13 also transmits data such as control commands transmitted from the processing unit 11 to the substrate processing apparatus 3.

[0025] The display unit 14 is configured using a liquid crystal display or the like, and displays various images, characters, etc. based on the processing of the processing unit 11. The display unit 14 displays various information such as, for example, the spectrum data acquired from the substrate processing apparatus 3, the separated line spectrum data and background spectrum data, and the electron density and electron temperature for each reactive species.

[0026] The operation unit 15 accepts user operations and notifies the processing unit 11 of the accepted operations. For example, the operation unit 15 accepts user operations using input devices such as mechanical buttons or a touch panel provided on the surface of the display unit 14. Furthermore, for example, the operation unit 15 may be input devices such as a mouse and a keyboard, and these input devices may be configured to be detachable from the information processing device 1.

[0027] The storage unit 12 may be an external storage device connected to the information processing device 1. The information processing device 1 may be a multi-computer including multiple computers, or may be a virtual machine virtually constructed by software. The information processing device 1 is not limited to the above configuration, and may not include, for example, the display unit 14 and the operation unit 15.

[0028] In the information processing device 1 according to this embodiment, the processing unit 11 reads out and executes the program 12a stored in the storage unit 12, whereby a spectrum data acquiring unit 11a, a spectrum separating unit 11b, an electron temperature order predicting unit 11c, an electron density predicting unit 11d, a time-series data predicting unit 11e, a display processing unit 11f, a control processing unit 11g, etc. are realized as software functional units in the processing unit 11. Note that in the figure, functional units related to the process of predicting the electron density and electron temperature for each reactive species based on the spectrum data acquired from the substrate processing device 3 are shown as the functional units of the processing unit 11, and functional units related to other processes are not shown.

[0029] The spectral data acquiring unit 11a performs a process of acquiring spectral data measured by a measuring instrument, a sensor, or the like when the substrate processing apparatus 3 processes a substrate by communicating with the substrate processing apparatus 3 via the communication unit 13. In this embodiment, the spectral data is data indicating the correspondence between the wavelength and intensity of light measured in the chamber of the substrate processing apparatus 3, and is provided to the information processing apparatus 1 as, for example, one-dimensional array data. The spectral data acquiring unit 11a stores the spectral data acquired from the substrate processing apparatus 3 in the prediction result DB 5 in association with information such as date and time and substrate identification information.

[0030] The spectrum separation unit 11b separates the spectral data acquired by the spectrum data acquisition unit 11a into a plurality of line spectral data for each reactive species and background spectral data other than these reactive species. In this embodiment, the spectrum separation unit 11b separates the spectral data into a plurality of line spectral data and background spectral data using a separation model previously generated by machine learning. Information about the separation model is stored in the model information storage unit 12b. The spectrum separation unit 11b stores information about the line spectral data and background spectral data separated from the spectral data in the prediction result DB 5 in association with the original spectral data.

[0031] The electron temperature order prediction unit 11c performs processing to predict the order (digit) of the electron temperature for each reactive species based on the line spectrum data for each reactive species separated by the spectrum separation unit 11b. In this embodiment, the electron temperature order prediction unit 11c adopts, for example, any of the Doppler width, the natural width, or the Stark width as the spectral width of each reactive species, depending on the conditions of the substrate processing, etc. When the Doppler width is adopted, the electron temperature order prediction unit 11c calculates the width of the line spectrum data of the reactive species and sets this as the Doppler width, calculates the electron temperature of the reactive species using a predetermined arithmetic expression related to the Doppler width, and sets the number of digits as the predicted order of the electron temperature.

[0032] In this embodiment, the order of the electron temperature corresponding to the natural width or Stark width of the reactive species is calculated in advance, and is stored in advance in the information processing device 1 as a table associating the reactive species with the order of the electron temperature in the storage unit 12, for example. When the natural width is used as the spectral width, the electron temperature order prediction unit 11c reads out a table relating to the order of the electron temperature of the natural width from the storage unit 12 and obtains from the table the order of the electron temperature corresponding to the reactive species to be predicted, thereby predicting the order of the electron temperature corresponding to the natural width of the reactive species spectrum. Similarly, when the Stark width is used as the spectral width, the electron temperature order prediction unit 11c reads out a table relating to the order of the electron temperature of the Stark width from the storage unit 12 and obtains from the table the order of the electron temperature corresponding to the reactive species to be predicted, thereby predicting the order of the electron temperature corresponding to the Stark width of the reactive species spectrum.

[0033] The electron temperature order prediction unit 11c also predicts the order of electron temperature for background spectral data separated from the spectral data. The electron temperature order prediction unit 11c predicts the order of electron temperature by assuming that the background spectral data follows, for example, a Boltzmann distribution and fitting the separated background spectral data to the Boltzmann distribution. The electron temperature order prediction unit 11c stores information about the predicted order of electron temperature in the prediction result DB 5 in association with the original spectral data.

[0034] The electron density prediction unit 11d predicts the electron density and electron temperature of each reactive species using a reactive species model stored in advance for each reactive species. The reactive species model receives the electron density and electron temperature of the reactive species as input and outputs the emission intensity (spectrum) of light from the reactive species. In this embodiment, the reactive species model is given as a logical operation formula determined in advance based on a theoretical equation (rate equation) for determining the plasma composition. However, the reactive species model may be given as a learning model (surrogate model) generated by machine learning using simulation data, for example, or may be a model generated by other methods.

[0035] The electron density prediction unit 11d inputs appropriate electron densities and electron temperatures into the reactive species model and obtains the spectrum output by the reactive species model. The electron temperatures input to the reactive species model are values ​​that satisfy the order of the electron temperatures predicted for each reactive species. The electron density prediction unit 11d calculates the difference between the spectrum output by the reactive species model and the line spectrum data separated for that reactive species. If the calculated difference is greater than a threshold, the electron density prediction unit 11d appropriately corrects the electron densities and electron temperatures input to the reactive species model and searches for an optimal solution by repeatedly correcting the electron densities and electron temperatures until the difference between the spectrum output by the reactive species model and the line spectrum data of that reactive species becomes smaller than the threshold. If the difference is smaller than the threshold, the electron density prediction unit 11d considers the electron densities and electron temperatures at that time to be the optimal solution and outputs them as predicted values ​​of the electron density and electron temperature. The electron density prediction unit 11d also stores the predicted electron densities and electron temperatures in the prediction result DB 5 in association with the original spectrum data.

[0036] The time-series data prediction unit 11e treats the multiple electron density and electron temperature prediction results repeatedly predicted by the electron density prediction unit 11d and stored in the prediction result DB5 as time-series data, and performs a process of predicting the electron density and electron temperature for the next timing or further timing based on the past electron densities and electron temperatures. The time-series data prediction unit 11e uses a learning model that has been previously generated by machine learning, such as a recurrent neural network (RNN) or a long short-term memory (LSTM), for predicting time-series data. The time-series data prediction unit 11e sequentially inputs the time-series electron density or electron temperature data into the learning model and obtains the predicted electron density or electron temperature values ​​sequentially output by the learning model, thereby obtaining the predicted values ​​for the next timing. The time-series data prediction unit 11e provides the predicted electron density and electron temperature values ​​to the electron density prediction unit 11d, and the electron density prediction unit 11d can search for optimal electron density and electron temperature using the provided predicted values, for example, as initial values ​​for search.

[0037] The display processing unit 11f performs processing to display various characters, images, and the like on the display unit 14. In the present embodiment, the display processing unit 11f graphs, for example, spectrum data acquired from the substrate processing apparatus 3, line spectrum data separated from the spectrum data, or background spectrum data, and displays the graphs on the display unit 14. The display processing unit 11f also displays information on the electron density and electron temperature predicted by the electron density prediction unit 11d on the display unit 14. Note that the display processing unit 11f may display various information other than the above on the display unit 14.

[0038] The control processing unit 11g communicates with the substrate processing apparatus 3 via the communication unit 13 and controls the substrate processing performed by the substrate processing apparatus 3 by issuing various commands or instructions to the substrate processing apparatus 3. In the present embodiment, the control processing unit 11g adjusts settings such as the pressure, gas flow rate, or power of the substrate processing apparatus 3 based on information such as the electron density and electron temperature predicted by the electron density prediction unit 11d, thereby controlling the substrate processing. For example, the control processing unit 11g can determine whether the substrate processing is normal or abnormal based on the predicted electron density, and, if an abnormality is detected, perform control processing such as stopping the substrate processing. Furthermore, for example, when the electron density for a predetermined reactive species is higher or lower than the normal range, the control processing unit 11g adjusts the settings of the substrate processing apparatus 3 to decrease or increase the flow rate of the gas related to the reactive species. The control processing unit 11g may also perform control of various other substrate processing operations.

[0039] <Spectral Separation Processing> The information processing apparatus 1 according to this embodiment performs spectral separation processing on spectral data acquired from the substrate processing apparatus 3 using a separation model, which is a learning model previously generated by machine learning. FIG. 3 is a schematic diagram illustrating an example of the configuration of a separation model used in the spectral separation processing. The separation model 21 according to this embodiment is a learning model that has been previously machine-learned to accept spectral data acquired from the substrate processing apparatus 3 as input, separate the spectral data into line spectral data of multiple reactive species and background spectral data other than the reactive species, and output the separated spectral data. In the illustrated example, the separation model 21 separates line spectral data for N types of reactive species (N is a natural number) and one background spectral data from the original spectral data. The separation model 21 may be configured as a neural network, for example, but may also be a learning model with a different configuration.

[0040] In this embodiment, the spectral data input to the separation model 21 is data in which the wavelength and intensity of light are associated with each other, and is given, for example, as a one-dimensional array of data. The line spectral data and background spectral data for each reactive species output by the separation model 21 are parameters of a function obtained by approximating each post-separation spectral data with a predefined function. Various functions can be used as the function, such as a Gaussian function, a Lorentz function, a Voigt function, a Boltzmann function, or an exponential function.

[0041] For example, if one separated spectral data item is expressed by three parameters of a predetermined function, the separation model 21 outputs (N+1) × 3 values. In this case, the data output by the separation model 21 can be expressed as an (N+1) × 3 matrix. Note that a different function may be adopted for each reaction species, and in this case, the number of parameters may differ for each reaction species.

[0042] FIG. 4 is a schematic diagram illustrating an example of machine learning of the separation model 21. The information processing device 1 uses a spectral data reproducing unit 22 and an error calculating unit 23 in the machine learning process for generating the separation model 21. The spectral data reproducing unit 22 receives as input a plurality of line spectral data and background spectral data output by the separation model 21, reproduces the plurality of line spectral data and background spectral data, and outputs synthesized spectral data. That is, the spectral data reproducing unit 22 performs processing to restore the line spectral data and background spectral data separated by the separation model 21 to the original spectral data. The reproduced spectral data output by the spectral data reproducing unit 22 is data in the same format as the spectral data input to the separation model 21, such as one-dimensional array data. The spectral data reproducing unit 22 reproduces each line spectral data and background spectral data using a predefined function based on the input data, and can reproduce the original spectral data by combining the reproduced data.

[0043] The error calculation unit 23 calculates the error between the reproduced spectral data reproduced by the spectral data reproduction unit 22 and the original spectral data input to the separation model 21. The error calculation unit 23 calculates the error using a function known as a loss function or error function, and calculates an error such as a mean square error or a mean absolute error. The information processing device 1 can perform machine learning of the separation model 21 by updating the parameters of the separation model 21 using, for example, an error backpropagation method based on the error calculated by the error calculation unit 23.

[0044] The information processing apparatus 1 uses a sufficient amount of spectral data measured in advance by the substrate processing apparatus 3 as learning data to perform machine learning of the separation model 21 using the above-described method. This method eliminates the need to assign any correct answer labels to the spectral data obtained by measurement, and allows machine learning of the separation model 21 through so-called unsupervised learning. The information processing apparatus 1 stores information such as internal parameters of the separation model 21 obtained through machine learning in the model information storage unit 12b. When performing the spectral separation process, the information processing apparatus 1 reads information such as the internal parameters from the model information storage unit 12b to construct the separation model 21, inputs spectral data obtained from the substrate processing apparatus 3 to the separation model 21, and acquires data output by the separation model 21, thereby separating the spectral data into multiple line spectral data and background spectral data. Note that in this embodiment, the information processing apparatus 1 performs machine learning of the separation model 21. However, this is not limited thereto. The machine learning of the separation model 21 may be performed in a separate apparatus, and the information processing apparatus 1 may acquire information such as the internal parameters of the separation model 21 obtained through machine learning from the separate apparatus and store it in the model information storage unit 12b.

[0045] <Electron Temperature Order Prediction Process> The information processing device 1 according to this embodiment performs a process of predicting the order of the electron temperature of each reactive species based on the plurality of line spectrum data and background spectrum data separated by the spectrum separation process. In this embodiment, the electron temperature of a reactive species is significantly affected by one of three types of spectral widths, namely, the Doppler width, the natural width, and the Stark width, depending on the conditions of the substrate processing performed in the substrate processing device 3, and the information processing device 1 determines which spectral width should be used to predict the electron temperature order for each reactive species based on the conditions of the substrate processing.

[0046] 5 is a schematic diagram showing an example of a table for determining the type of spectral width that affects the prediction of the electron temperature order of a reactive species. The spectral width type determination table shown in FIG. 5 stores the types of spectral widths (Doppler width, natural width, Stark width) that contribute to the electron temperature order, in association with N types of reactive species 1 to N and substrate processing conditions A, B, C, etc. When acquiring spectral data from the substrate processing apparatus 3, the information processing apparatus 1 acquires information on the substrate processing conditions and, by referring to the illustrated table, determines which spectral width should be used to predict the electron temperature order for each reactive species.

[0047] In this embodiment, electron temperature orders are determined in advance for the natural width and Stark width of the three types of spectral widths. FIG. 6 is a schematic diagram showing an example of a table for determining the electron temperature orders for the natural width and Stark width. The electron temperature order determination table shown in FIG. 6 stores electron temperature orders in association with N types of reactive species 1 to N and the natural width and Stark width. When the information processing device 1 adopts the natural width or the Stark width as the spectral width based on the table shown in FIG. 5, it determines the electron temperature order corresponding to the reactive species and the natural width or the Stark width by referring to the table shown in FIG. 6.

[0048] 5 and 6 is determined in advance by a designer or administrator of the information processing system according to this embodiment through spectrum observation, simulation, etc., and is stored in advance in the storage unit 12 of the information processing device 1. In this example, the two tables shown in Fig. 5 and 6 are used, but the present invention is not limited to this, and the two tables may be combined into one table.

[0049] Furthermore, when the information processing device 1 employs the Doppler width as the spectral width based on the table shown in Fig. 5 , it predicts the electron temperature order based on the line spectral data separated from the spectral data acquired from the substrate processing device 3. Fig. 7 is a schematic diagram for explaining an example of line spectral data and the Doppler width, in which the line spectral data is graphed with the horizontal axis representing wavelength λ and the vertical axis representing spectral intensity. In the line spectral data shown in this figure, the wavelength at which the spectral intensity is maximum is designated as λ0. In this embodiment, the width of the range of wavelengths that includes this wavelength λ0 and where the spectral intensity is at least half the maximum value is designated as the Doppler width ΔλD. The information processing device 1 can calculate this Doppler width ΔλD for each separated line spectral data.

[0050] The following equation (1) holds between the Doppler width ΔλD of the reaction species and the electron temperature Tg. In equation (1), λ0 is the center wavelength of the spectrum, as shown in FIG. 7. In equation (1), c is the speed of light (299,792,458 m / s), mg is the mass of the reaction species, k is the Boltzmann constant, and ln2 is the natural logarithm of 2, and these values ​​are given in advance as constants.

[0051]

[0052] The information processing device 1 calculates the electron temperature Tg using the above formula (1) based on the Doppler width ΔλD calculated from the line spectrum data. However, in this embodiment, the information processing device 1 does not use the calculated electron temperature Tg itself, but rather obtains the number of digits of the calculated electron temperature Tg and uses this as a predicted value of the order of the electron temperature. The information processing device 1 predicts the order of the electron temperature based on the Doppler width ΔλD calculated from the line spectrum data and the above formula (1) for all reaction species for which the factor of the spectrum width is set as Doppler width in the table shown in FIG. 5 .

[0053] The information processing device 1 also predicts the order of electron temperature based on background spectrum data separated from spectrum data acquired from the substrate processing device 3. The background spectrum indicates an offset component obtained by removing a line spectrum signal at a specific wavelength from the input optical emission signal. In this embodiment, the information processing device 1 assumes that the background spectrum data follows a Boltzmann distribution, calculates a bremsstrahlung cross section from the amount of momentum transfer due to electron collisions with molecular / atomic species used in the process, and predicts the electron temperature or electron energy distribution that matches the offset signal of the background spectrum from the emissivity for each wavelength using the bremsstrahlung cross section.

[0054] The information processing device 1 calculates the electron temperature Te by fitting the background spectrum data to the above equation (2), obtains the number of digits of the calculated electron temperature Te, and sets it as a predicted value of the order of the electron temperature related to the background spectrum data.

[0055] 8 is a flowchart showing an example of the procedure of the electron temperature order prediction process performed by the information processing device 1 according to this embodiment. The electron temperature order prediction unit 11c of the processing unit 11 of the information processing device 1 according to this embodiment acquires line spectrum data for multiple reactive species separated by the spectrum separation process (step S1). The electron temperature order prediction unit 11c also acquires information about the conditions of the substrate processing that was being performed when the spectrum data was acquired from the substrate processing device 3 (step S2). The substrate processing conditions can be information indicating which process, such as an etching process or a film formation process, was being performed in the substrate processing.

[0056] The electron temperature order prediction unit 11c selects a target reaction species for which the electron temperature order is to be predicted from the plurality of reaction species obtained by separating the line spectrum data (step S3). The electron temperature order prediction unit 11c refers to the spectrum width type determination table shown in Fig. 5 based on the reaction species selected in step S3 and the substrate processing conditions acquired in step S2 (step S4). Based on the result of referring to the type determination table, the electron temperature order prediction unit 11c determines whether the spectrum width that has a large effect on the electron temperature of the target reaction species is the Doppler width (step S5).

[0057] If it is determined that the electron temperature order is a Doppler width (S5: YES), the electron temperature order prediction unit 11c calculates a Doppler width using the method shown in Fig. 7 based on the line spectrum data for the reaction species whose electron temperature order is to be predicted, among the line spectrum data acquired in step S1 (step S6). The electron temperature order prediction unit 11c calculates the electron temperature Tg using equation (1) based on the Doppler width ΔλD calculated in step S6, and calculates the electron temperature order for the reaction species of interest by obtaining the number of digits of the calculated electron temperature Tg (step S7), and then proceeds to step S10.

[0058] If it is determined that the spectral width is not the Doppler width (S5: NO), that is, if it is determined that the spectral width that has a large effect on the electron temperature of the target reactive species is the natural width or the Stark width, the electron temperature order prediction unit 11c refers to the electron temperature order determination table shown in FIG. 6 based on the reactive species selected in step S3 and the type of spectral width (natural width or Stark width) determined in the type determination table referred to in step S4 (step S8), obtains the electron temperature order corresponding to the type of reactive species and spectral width (step S9), and proceeds to step S10.

[0059] The electron temperature order prediction unit 11c determines whether or not the prediction of the electron temperature order has been completed for all reaction species of the plurality of line spectrum data acquired in step S1 (step S10). If the prediction has not been completed for all reaction species (S10: NO), the electron temperature order prediction unit 11c returns to step S3, selects another reaction species, and repeats the same process.

[0060] If predictions for all reaction species have been completed (S10: YES), the electron temperature order prediction unit 11c acquires background spectral data separated from the spectral data by the spectrum separation process (step S11). The electron temperature order prediction unit 11c calculates the electron temperature Te by fitting the background spectral data acquired in step S11 to the above equation (2), and calculates the electron temperature order for the background spectral data by acquiring the number of digits of the calculated electron temperature Te (step S12), thereby ending the process.

[0061] <Electron Density Prediction Processing> The information processing device 1 according to this embodiment performs processing to predict the electron density of each reaction species based on the multiple line spectrum data separated by the spectrum separation processing and the electron temperature order predicted by the electron temperature order prediction processing. In addition, in this embodiment, the information processing device 1 predicts the electron density of each reaction species as well as the electron temperature of each reaction species.

[0062] The information processing device 1 according to this embodiment predicts the electron density and electron temperature using a reactive species model generated in advance to reproduce the characteristics of each reactive species. FIG. 9 is a schematic diagram illustrating an example of the configuration of a reactive species model. The reactive species model 31 used by the information processing device 1 according to this embodiment for the electron density prediction process is a model that receives the electron temperature and electron density of the reactive species as input and outputs predicted values ​​of the line spectrum data of the reactive species. The reactive species model 31 may also receive information about the reactive species to be predicted (reactive species information) as input. For example, if reactive species models 31 are generated individually for multiple reactive species, input of reactive species information is not necessary. On the other hand, if one reactive species model 31 is configured to be able to perform predictions for multiple reactive species, information about the reactive species to be predicted is provided to the reactive species model 31 as reactive species information.

[0063] The reactive species model 31 may be provided as a physical model in which the physical properties of the reactive species are expressed by an equation or the like, and for example, a model based on a rate equation may be adopted. In this case, the reactive species model 31 is provided with information such as constants or coefficients set in the rate equation as reactive species information. The reactive species model 31 may also be provided as a learning model generated by machine learning such as a neural network. In this case, information corresponding to the input and output of the reactive species model 31 is collected in advance by experiments, simulations, or the like, and the reactive species model 31 is generated in advance by machine learning using the collected information.

[0064] The information processing device 1 appropriately sets and inputs the electron density and electron temperature to be input to the reactive species model 31, and accordingly acquires the line spectrum data output by the reactive species model 31. At this time, the information processing device 1 sets the electron temperature within the range of the electron temperature order predicted by the above-mentioned electron temperature order prediction process. The line spectrum data output by the reactive species model 31 may be, for example, a one-dimensional array of data having a plurality of intensity values ​​for the wavelength of light, or may be, for example, parameters of a function expressing the line spectrum data, similar to the line spectrum data output by the separation model 21.

[0065] Next, the information processing device 1 compares the line spectrum data acquired from the reactive species model 31 with the line spectrum data separated in the spectrum separation process, and calculates the difference (error) between the two line spectrum data. If the calculated error is greater than a predetermined threshold, the information processing device 1 adjusts the electron density and electron temperature input to the reactive species model 31 so as to reduce the error, and repeatedly acquires the line spectrum data output by the reactive species model 31 and calculates the error between the line spectrum data output by the reactive species model 31 and the line spectrum data obtained in the spectrum separation process, until the error becomes smaller than the threshold. This process is a so-called optimal solution search process, and an existing optimization method can be applied as a method for updating the values ​​of the electron density and electron temperature input to the reactive species model 31 so as to reduce the error.

[0066] If the calculated error is smaller than a predetermined threshold, the information processing device 1 sets the electron density and electron temperature input to the reactive species model 31 as the predicted results of the electron density and electron temperature for the target reactive species.

[0067] In this embodiment, the information processing device 1 predicts the electron density and electron temperature. However, this is not limited to this, and the information processing device 1 may be configured to predict the electron energy distribution instead of the electron temperature. The electron energy distribution may be expressed, for example, by an EEDF (Electron Energy Distribution Function). When predicting the electron energy distribution, the reactive species model 31 may be configured to accept the electron density and electron energy distribution as input and output line spectrum data. Furthermore, the information processing device 1 predicts the order of the electron energy distribution instead of predicting the order of the electron temperature. The electron temperature is synonymous with the variance of the electron energy distribution. For example, by a user specifying a function of the electron energy distribution in advance, a prediction of the order of the electron energy distribution can be obtained from a prediction of the order of the electron temperature. For example, a Maxwell distribution or a Druyvestcin distribution may be used as the function of the electron energy distribution. The order of the electron energy distribution is the order of the estimated coefficients of these distribution functions. As in the case where the electron temperature is used as described above, the information processing device 1 searches for the optimal electron density and electron energy distribution using the reaction species model 31 and the prediction results of the order of the electron energy distribution, and predicts the electron density and electron energy distribution for each reaction species.

[0068] Furthermore, in cases where the electron density is known experimentally or can be obtained by measurement, the information processing device 1 may not predict the electron density but may use the known electron density value to predict the electron temperature (or electron energy distribution) using the reactive species model 31.

[0069] 10 is a flowchart showing an example of the procedure of the electron density prediction process performed by the information processing apparatus 1 according to this embodiment. The electron density prediction unit 11d of the processing unit 11 of the information processing apparatus 1 according to this embodiment acquires line spectrum data separated from the spectrum data acquired from the substrate processing apparatus 3 for a reactive species whose electron density is to be predicted (step S31). The electron density prediction unit 11d also acquires reactive species information for the reactive species to be predicted (step S32). Note that, for example, when the reactive species model 31 is given by an arithmetic expression such as a rate equation, the reactive species information acquired in step S32 may include information such as constants or coefficients of this arithmetic expression. When a reactive species model 31 that does not require such information is used, the electron density prediction unit 11d does not need to acquire the reactive species information.

[0070] The electron density prediction unit 11d appropriately sets the electron density and electron temperature as initial values ​​to be input to the reaction species model 31 (step S33). At this time, the electron density prediction unit 11d sets the electron temperature within the range of the electron temperature order predicted by the electron temperature order prediction process. The electron density prediction unit 11d inputs the electron density and electron temperature set in step S33 to the reaction species model 31 and acquires line spectrum data output by the reaction species model 31 (step S34). The electron density prediction unit 11d calculates the error between the line spectrum data acquired in step S35 and the line spectrum data acquired in step S31 (step S35).

[0071] The electron density prediction unit 11d determines whether the error calculated in step S35 is smaller than a predetermined threshold (step S36). If the error is larger than the threshold (S36: NO), the electron density prediction unit 11d resets the electron density and electron temperature to be input to the reactive species model 31 so as to reduce the error (step S37), and returns to step S34. If the error is smaller than the threshold (S36: YES), the electron density prediction unit 11d optimizes the electron density and electron temperature input to the reactive species model 31 and stores the optimized electron density and electron temperature as prediction results in the prediction result DB 5 (step S38).

[0072] The electron density prediction unit 11d determines whether prediction of the electron density and electron temperature for all reaction species to be predicted has been completed (step S39). If prediction has not been completed for all reaction species (S39: NO), the electron density prediction unit 11d returns to step S31 and repeats the same process for another reaction species. If prediction has been completed for all reaction species (S39: YES), the display processing unit 11f of the processing unit 11 displays the predicted results of the electron density and electron temperature on the display unit 14 (step S40). The control processing unit 11g of the processing unit 11 controls the operation of the substrate processing apparatus 3 based on the predicted electron density and electron temperature (step S41), and then ends the electron density prediction process.

[0073] <Time Series Data Prediction Processing> The information processing apparatus 1 according to this embodiment associates information such as spectral data acquired from the substrate processing apparatus 3, line spectral data and background spectral data of each reactive species separated from this spectral data, electron temperature orders predicted based on the line spectral data and background spectral data of each reactive species, and electron densities and electron temperatures predicted for each reactive species, and stores these pieces of information in the prediction result DB 5. As the information processing apparatus 1 repeatedly stores this information, it is accumulated as time series data in the prediction result DB 5. The information processing apparatus 1 performs processing to predict future data based on this time series data stored in the prediction result DB 5.

[0074] 11 is a schematic diagram showing an example of time-series data, showing a graph with time t on the horizontal axis and electron density (predicted value) on the vertical axis. The graph in this example shows a tendency for electron density to increase over time during substrate processing performed by the substrate processing apparatus 3. The information processing apparatus 1 according to this embodiment predicts time-series data such as electron density and electron temperature for each reactive species using a learning model such as an RNN or LSTM that has been generated in advance by machine learning. The learning model, for example, outputs a predicted value for data at a next timing in response to input of data at a certain timing.

[0075] After predicting the electron density, electron temperature, etc., the information processing device 1 inputs the current values ​​of the electron density, electron temperature, etc., which are the prediction results, into a learning model that predicts time-series data, and obtains predicted values ​​of the electron density, electron temperature, etc. at the next time point. The information processing device 1 calculates a predetermined range (e.g., predicted value ±10%) that includes the obtained predicted values ​​of the electron density, electron temperature, etc., as the prediction range.

[0076] For example, the information processing device 1 feeds back the predicted values ​​and prediction ranges of the electron density and electron temperature to the above-mentioned electron density prediction process. As described above, the electron density prediction process searches for optimal electron density and electron temperature, but the information processing device 1 can use the electron density and electron temperature at the next timing predicted based on time-series data as initial values ​​for the search, or limit the search range of the electron density and electron temperature to the range predicted based on time-series data, etc.

[0077] <Information Provision and Control Processing> The information processing apparatus 1 according to this embodiment provides a user with information regarding substrate processing by displaying predicted results for the electron density and electron temperature for each reactive species on the display unit 14. The information processing apparatus 1 repeatedly acquires spectral data while substrate processing is being performed in the substrate processing apparatus 3 and repeatedly predicts the electron density and electron temperature for each reactive species based on the acquired spectral data. The information processing apparatus 1 can display, for example, temporal changes in the predicted electron density and electron temperature in real time as a graph. A user can monitor, in real time, changes in the electron density and electron temperature of important reactive species in a substrate processing process such as etching or film formation. Furthermore, based on information such as the predicted electron density or electron temperature for a specific reactive species, the user can estimate the wear level of components, for example, installed in a chamber of the substrate processing apparatus 3, and perform component replacement, for example.

[0078] The information processing apparatus 1 also controls the substrate processing apparatus 3 based on the predicted electron density, electron temperature, etc. The information processing apparatus 1 can, for example, determine whether the predicted electron density and electron temperature are within a normal range, and if they are not within the normal range, perform control to stop substrate processing in the substrate processing apparatus 3. Furthermore, for example, when the predicted electron density is higher / lower than the normal range, the information processing apparatus 1 adjusts the settings of the substrate processing apparatus 3 to decrease / increase the flow rate of gas related to this reactive species. Furthermore, for example, when the electron density or electron temperature of a predetermined reactive species reaches a predetermined target value, the information processing apparatus 1 can perform control such as proceeding with the substrate processing step to the next step.

[0079] The provision of information to the user and control of substrate processing based on the above predictions of electron density, electron temperature, etc. are just examples and are not limited to these, and the information processing device 1 can provide various information and perform control processing based on the prediction results.

[0080] <Summary> In the information processing system according to the present embodiment configured as described above, the information processing device 1 acquires spectral data measured in relation to substrate processing from the substrate processing device 3, separates the acquired spectral data into multiple line spectral data for multiple reactive species, and predicts at least one of the electron density, electron temperature, and electron energy distribution for each reactive species based on the separated line spectral data. This makes it possible for the information processing system according to the present embodiment to estimate the state of substrate processing based on the spectral data measured during substrate processing. The information processing system predicts at least one of the electron density, electron temperature, and electron energy distribution for each reactive species from the spectral data obtained by simultaneous measurements using measuring instruments provided in the substrate processing device 3, and is expected to realize processes such as providing detailed information related to substrate processing to a user or controlling the substrate processing in accordance with the status of each reactive species.

[0081] Furthermore, in the information processing system according to this embodiment, the information processing device 1 predicts the electron temperature or electron energy distribution as well as the electron density for each reactive species based on the line spectrum data separated from the spectrum data. This allows the information processing system according to this embodiment to predict more information related to substrate processing, and is expected to provide more information to users or realize control of substrate processing with high processing accuracy.

[0082] In the information processing system according to the present embodiment, the information processing apparatus 1 receives spectral data as input and separates the spectral data acquired from the substrate processing apparatus 3 into line spectral data and background spectral data for each reactive species using a separation model 21 that has been machine-learned in advance to output line spectral data for a predetermined reactive species included in the input spectral data and background spectral data for species other than the predetermined reactive species. The separation model 21 is machine-learned based on the error between the original spectral data input to the separation model 21 and the spectral data obtained by combining multiple line spectral data and background spectral data output by the separation model 21 in response to the input spectral data. As a result, the information processing system according to the present embodiment is expected to generate the separation model 21 by so-called unsupervised machine learning and accurately separate the spectral data into line spectral data and background spectral data for each reactive species using the generated separation model 21.

[0083] In the information processing system according to this embodiment, the information processing device 1 predicts the electron temperature order for each reactive species based on the separated line spectrum data, and predicts the electron density for each reactive species based on the separated line spectrum data and the predicted electron temperature order. The information processing device 1 also calculates a spectral width for the separated spectrum data and predicts the electron temperature order based on the calculated spectral width. Furthermore, when the spectral width that has a large effect on the electron temperature order is the Doppler width, the information processing device 1 calculates the spectral width and predicts the electron temperature order. When the spectral width is the natural width or the Stark width, the information processing device 1 predicts a predetermined electron temperature order. As a result, the information processing system according to this embodiment predicts the electron temperature order for each reactive species based on the separated line spectrum data, and uses this electron temperature order in subsequent prediction processing (electron density prediction processing), thereby improving the accuracy, processing speed, etc. of the subsequent prediction processing.

[0084] Furthermore, in the information processing system according to this embodiment, the information processing device 1 uses the reactive species model 31 that predicts line spectrum data in response to input of the electron density and electron temperature (or electron energy distribution) of the reactive species to search for the electron density and electron temperature so that the error between the line spectrum data separated from the spectrum data acquired from the substrate processing device 3 and the line spectrum data predicted by the reactive species model 31 is smaller than a threshold value, thereby predicting the electron density and electron temperature for each reactive species. Furthermore, at this time, the information processing device 1 may limit the search range of the electron temperature based on the order of the electron temperature predicted from the line spectrum data. As a result, the information processing system according to this embodiment can be expected to accurately predict the electron density and electron temperature for each reactive species by using the reactive species model 31 generated by unsupervised learning, which does not require teacher data.

[0085] In the information processing system according to this embodiment, the information processing device 1 repeatedly performs processes such as acquiring spectral data, separating line spectral data, and predicting electron density, predicts the range of electron density at a next time point based on the predicted electron density at one time point, and predicts the electron density at the next time point and thereafter based on the separated line spectral data and the predicted electron density range. As a result, the information processing system according to this embodiment is expected to predict electron density with higher accuracy.

[0086] Furthermore, in the information processing system according to this embodiment, the information processing device 1 controls the substrate processing by the substrate processing device 3 based on the predicted electron density for each reactive species. As a result, the information processing system according to this embodiment is expected to improve the accuracy of substrate processing.

[0087] The embodiments disclosed herein are to be considered as illustrative in all respects and not restrictive. The scope of the present disclosure is defined by the claims, not by the above meaning, and is intended to include all modifications within the meaning and scope of the claims.

[0088] The matters described in each embodiment can be combined with each other. Furthermore, the independent claims and dependent claims described in the claims can be combined with each other in any and all combinations, regardless of the reference format. Furthermore, the claims use a format in which a claim references two or more other claims (multiple claim format), but this is not limited to this. A multiple claim (multi-multi claim) that references at least one other multiple claim may also be used.

[0089] REFERENCE SIGNS LIST 1 Information processing device (computer) 3 Substrate processing device 5 Prediction result DB 11 Processing unit 11a Spectral data acquisition unit 11b Spectral separation unit 11c Electron temperature order prediction unit 11d Electron density prediction unit 11e Time series data prediction unit 11f Display processing unit 11g Control processing unit 12 Storage unit 12a Program (computer program) 12b Model information storage unit 13 Communication unit 14 Display unit 15 Operation unit 21 Separation model (learning model) 22 Spectral data reproduction unit 23 Error calculation unit 31 Reaction species model (model) 99 Recording medium

Claims

1. A computer program that causes a computer to execute the following process: acquire spectral data measured in relation to substrate processing; separate the acquired spectral data into line spectral data for multiple reactive species; and predict at least one of the electron density, electron temperature, and electron energy distribution for each reactive species based on the separated line spectral data.

2. The computer program of claim 1, which uses a learning model that has been machine-learned to accept spectral data as input and output line spectral data of a predetermined reactive species contained in the input spectral data and background spectral data other than the predetermined reactive species, inputs the acquired spectral data into the learning model, and obtains the line spectral data and background spectral data output by the learning model, thereby separating the spectral data into line spectral data for each reactive species.

3. The computer program according to claim 2, wherein the learning model is machine-learned based on the error between the input spectral data and the synthesized spectral data of line spectral data and background spectral data that the learning model outputs in response to input spectral data.

4. The computer program according to claim 1, which predicts the order of electron temperature or the order of electron energy distribution for each reactive species based on the separated line spectrum data, and predicts the electron density for each reactive species based on the separated line spectrum data and the predicted order of electron temperature or the predicted order of electron energy distribution.

5. The computer program according to claim 4, further comprising: calculating a spectral width for the separated line spectrum data; and predicting the order of electron temperature or the order of electron energy distribution based on the calculated spectral width.

6. The computer program of claim 5, wherein the spectral width is the Doppler width, the natural width, or the Stark width of the spectrum of the reactive species.

7. A computer program as claimed in claim 1, which predicts the electron density, electron temperature or electron energy distribution of each reactive species by using a model that predicts line spectrum data of the reactive species in response to input of the electron density, electron temperature or electron energy distribution of the reactive species, and searching for input values ​​of the electron density, electron temperature or electron energy distribution that make the error between the separated line spectrum data and the line spectrum data predicted by the model smaller than a threshold value.

8. The computer program according to claim 7, which predicts the order of electron temperature or the order of electron energy distribution for each reaction species based on the acquired spectrum data, and limits the search range of the electron temperature when searching for input values ​​of the electron temperature and the electron temperature or electron energy distribution using the model based on the predicted order of electron temperature or electron energy distribution.

9. The computer program of claim 1, which repeatedly acquires the spectral data, separates the line spectral data, and predicts at least one of the electron density, electron temperature, and electron energy distribution, predicts a range of at least one of the electron density, electron temperature, and electron energy distribution for a subsequent time point based on a prediction result of at least one of the electron density, electron temperature, and electron energy distribution at a certain time point, and predicts at least one of the electron density, electron temperature, and electron energy distribution for a subsequent time point based on the separated line spectral data and the predicted range.

10. The computer program according to claim 1, wherein the substrate processing is controlled based on at least one of electron density, electron temperature, and electron energy distribution corresponding to the predicted spectrum of each reactive species.

11. An information processing method, in which an information processing device acquires spectral data measured in relation to substrate processing, separates the acquired spectral data into line spectral data for a plurality of reactive species, and predicts at least one of the electron density, electron temperature, and electron energy distribution for each reactive species based on the separated line spectral data.

12. An information processing device comprising a processing unit, which acquires spectral data measured in relation to substrate processing, separates the acquired spectral data into line spectral data for a plurality of reactive species, and predicts at least one of electron density, electron temperature, and electron energy distribution for each reactive species based on the separated line spectral data.

Images