Program, information processing method, information processing device, and laser processing device

Abstract

This program causes a computer to execute a process for: acquiring operation state data relating to the operation state of a laser annealing device for irradiating a substrate with laser light; assessing, on the basis of the operation state data, whether surface unevenness has occurred in the substrate irradiated with the laser light from the laser annealing device or whether a decrease in luminance has occurred in the substrate; outputting handling information relating to a first parameter group required for handling surface unevenness in cases where it is assessed that surface unevenness has occurred in the substrate; and outputting handling information relating to a second parameter group required for handling decreases in luminance when it is assessed that a decrease in the luminance of the substrate has occurred.

Description

Program, information processing method, information processing device and laser processing device

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

[0002] A semiconductor film surface unevenness detection device, a laser annealing device, and a semiconductor film surface unevenness detection method are known that can detect surface unevenness of a semiconductor film that has been annealed by irradiating it with laser light (for example, Patent Document 1).

[0003] Japanese Patent Application Laid-Open No. 2016-129171

[0004] The present disclosure aims to provide a program or the like that can output, in response to the occurrence of surface unevenness or a decrease in brightness, response information related to a group of parameters required to respond to the occurrence.

[0005] The program according to this aspect causes a computer to acquire operating state data relating to the operating state of a laser annealing device that is irradiating a substrate with laser light, and based on the acquired operating state data, determine whether surface unevenness has occurred on the substrate irradiated with laser light from the laser annealing device or whether a decrease in brightness has occurred on the substrate.If it is determined that surface unevenness has occurred on the substrate, the program outputs corresponding information relating to a first group of parameters required to deal with the surface unevenness, and if it is determined that a decrease in brightness has occurred on the substrate, the program outputs corresponding information relating to a second group of parameters required to deal with the decrease in brightness.

[0006] The information processing method of this aspect causes a computer to execute a process of acquiring operating state data regarding the operating state of a laser annealing device that is irradiating a substrate with laser light, determining based on the acquired operating state data whether surface unevenness has occurred on the substrate irradiated with laser light from the laser annealing device or whether a decrease in brightness has occurred on the substrate, and outputting corresponding information regarding a first group of parameters required to deal with the surface unevenness if it is determined that surface unevenness has occurred on the substrate, and outputting corresponding information regarding a second group of parameters required to deal with the decrease in brightness if it is determined that a decrease in brightness has occurred on the substrate.

[0007] The information processing device according to this aspect is an information processing device that includes a control unit, and the control unit acquires operating state data regarding the operating state of a laser annealing device that is irradiating a substrate with laser light, and determines, based on the acquired operating state data, whether surface unevenness has occurred on the substrate irradiated with laser light from the laser annealing device or whether a decrease in brightness has occurred on the substrate.If it is determined that surface unevenness has occurred on the substrate, the control unit outputs corresponding information regarding a first group of parameters required to deal with the surface unevenness, and if it is determined that a decrease in brightness has occurred on the substrate, the control unit outputs corresponding information regarding a second group of parameters required to deal with the decrease in brightness.

[0008] The laser processing device according to this aspect is a laser processing device equipped with a laser light source that emits laser light, and has the function of acquiring operating state data relating to the operating state when the laser light from the laser light source is irradiated onto a substrate, determining based on the acquired operating state data whether surface unevenness has occurred on the substrate irradiated with the laser light from the laser light source or whether a decrease in brightness has occurred on the substrate, and outputting corresponding information relating to a first group of parameters required to deal with the surface unevenness if it is determined that surface unevenness has occurred on the substrate, and outputting corresponding information relating to a second group of parameters required to deal with the decrease in brightness if it is determined that a decrease in brightness has occurred on the substrate.

[0009] According to the present disclosure, it is possible to provide a program or the like that outputs, in response to the occurrence of surface unevenness or a decrease in brightness, response information related to a group of parameters required to respond to the occurrence.

[0010] 1 is a diagram illustrating an example of a system configuration of an operation management system including an information processing device and the like according to embodiment 1. FIG. 2 is a diagram illustrating an example of a configuration of a laser annealing device. FIG. 3 is a diagram illustrating an example of a configuration of an information processing device (control device) connected to the laser annealing device. FIG. 4 is an explanatory diagram relating to a generation process of a first learning model (unevenness prediction model). FIG. 5 is a flowchart illustrating an example of a processing procedure of a control unit of a model server (when learning an unevenness prediction model). FIG. 6 is an explanatory diagram relating to a generation process of a second learning model (brightness decrease prediction model). FIG. 7 is a flowchart illustrating an example of a processing procedure of a control unit of a model server (when learning a brightness decrease prediction model). FIG. 8 is a functional block diagram illustrating functional units included in a control unit of an information processing device. FIG. 9 is a flowchart illustrating an example of a processing procedure of a control unit of an information processing device. FIG. 10 is a diagram illustrating an example of a check parameter table. FIG. 11 is a diagram illustrating an example of an abnormality notification screen or the like that notifies of the occurrence of an abnormality in the laser annealing device.

[0011] (Embodiment 1) Hereinafter, an embodiment of the present invention will be described. Fig. 1 is a diagram showing an example of the system configuration of an operation management system S including an information processing device 9 according to embodiment 1. A laser annealing device 1 (laser processing device) is, for example, an excimer laser annealing (ELA) device that forms a low temperature polysilicon (LTPS) film.

[0012] The laser annealing apparatus 1 is installed in a manufacturing factory (base) that manufactures semiconductor substrates 8 (substrates 8), such as glass substrates 8 on which a polycrystalline silicon film is formed, and an information processing device 9 connected to the laser annealing apparatus 1 via an in-base network (LAN) is installed in the manufacturing factory (base). The information processing device 9 may function as a control device that controls the operation of the laser annealing apparatus 1, or may be included in the laser annealing apparatus 1. The information processing device 9 is connected to a model server SS so as to be able to communicate with it, for example, via an external network GN such as the Internet.

[0013] The model server SS may function as a remote monitoring device that acquires substrate images, operating parameters of the laser annealing apparatus 1, and various sensors transmitted from the information processing device 9, and monitors the operating status of the laser annealing apparatus 1 installed at each of multiple bases based on the acquired various data. Furthermore, the model server SS may generate or update various learning models using the substrate images, etc. transmitted from the information processing device 9. In this way, the operation management system S is configured by the laser annealing apparatus 1 installed at each of multiple bases, the information processing device 9 (control device) that controls the operation of the laser annealing apparatus 1, and the model server SS.

[0014] Fig. 2 is a diagram showing an example of the configuration of the laser annealing apparatus 1. Fig. 3 is a diagram showing an example of the configuration of an information processing device 9 (control device) connected to the laser annealing apparatus 1. The laser annealing apparatus 1 irradiates laser light onto a silicon film formed on a substrate 8. This makes it possible to convert an amorphous silicon film (amorphous silicon film: a-Si film) into a polycrystalline silicon film (polysilicon film: p-Si film). The substrate 8 is a semiconductor substrate 8.

[0015] As shown in the drawings in this embodiment, in an XYZ three-dimensional Cartesian coordinate system, the Z direction is the vertical direction, that is, the direction perpendicular to the substrate 8. The XY plane is a plane parallel to the surface of the substrate 8 on which the silicon film is formed. For example, the X direction is the longitudinal direction of the rectangular substrate 8, and the Y direction is the lateral direction of the substrate 8. When a θ-axis stage 71 that can rotate from 0° to 90° around the Z axis is used, the X direction can be the lateral direction of the substrate 8, and the Y direction can be the longitudinal direction of the substrate 8.

[0016] The laser annealing apparatus 1 includes an annealing optical system 11 and a laser irradiation chamber 7, and is connected to an information processing device 9 (control device). The laser irradiation chamber 7 houses a base 72 and a stage 71 arranged on the base 72. In the laser annealing apparatus 1, the silicon film is irradiated with laser light while the substrate 8 is transported in the +X direction by the stage 71. Furthermore, the apparatus includes a biplanar phototube 62, an OED sensor 63, a line camera 64, and a profiler camera 66 as detection units that detect information related to the emitted laser light.

[0017] The annealing optical system 11 is an optical system that generates laser light for crystallizing the amorphous silicon film formed on the substrate 8 and converting it into a polysilicon film, and irradiates the amorphous silicon film with the laser light. The annealing optical system 11 includes a laser light source 2, an attenuator 3, a polarization ratio control unit 4, a beam shaping optical system 5, an epi-mirror 61, and a projection lens 65, and emits a line-shaped laser light.

[0018] The laser light source 2 is a laser generating device that generates pulsed laser light as laser light to be irradiated onto the amorphous silicon film (object to be processed). The generated laser light is laser light for crystallizing the amorphous film on the substrate 8 to form a crystallized film, and is, for example, gas laser light such as excimer laser light with a center wavelength of 308 nm. Alternatively, the gas laser light is not limited to excimer laser light, and may be other gas lasers such as a Co2 laser.

[0019] The laser light source 2 has a chamber filled with gas such as xenon, and two resonator mirrors arranged facing each other with the gas in between. One resonator mirror is a total reflection mirror that reflects all light, and the other is a partial reflection mirror that transmits a portion of the light. Gas light excited by the gas is repeatedly reflected between the resonator mirrors, and the amplified light is emitted from the resonator mirror as laser light. The laser light source 2 repeatedly emits pulsed laser light at a frequency of, for example, 500 Hz to 600 Hz. The laser light source 2 emits the laser light toward the attenuator 3.

[0020] The attenuators 3 attenuate the incident laser light to adjust it to a predetermined energy density. These attenuators 3 have a transmittance characteristic that indicates the ratio of the emitted laser light to the incident laser light, and the transmittance is configured to be variable based on a signal from an information processing device 9 (control device). The attenuators 3 are provided in the optical path from the laser light source 2 to the beam shaping optical system 5. The attenuators 3 attenuate the laser light emitted by the laser light source 2 in accordance with the transmittance.

[0021] The energy density (E) emitted from the attenuator 3 is a value (E=E×T) obtained by multiplying the energy density (E) of the laser light emitted from the laser light source 2 by the transmittance (T) of the attenuator 3. The information processing device 9 (control device) may identify (derive) and change the transmittance of the attenuator 3 so that the energy density emitted from the attenuator 3 becomes an optimal energy density.

[0022] The polarization ratio control unit 4 is disposed on the output side of the attenuator 3. The polarization ratio control unit 4 is configured with, for example, a half-wave plate (λ / 2 plate) and a polarizing beam splitter, and changes the polarization ratio between P polarization and S polarization of the incident laser light. That is, the polarization ratio of the laser light output from the attenuator 3 is changed by the polarization ratio control unit 4. The polarization ratio control unit 4 is configured to change (variably change) the polarization ratio based on a control signal output from an information processing device 9 (control device).

[0023] When the transmittance of the attenuator 3 is changed, the polarization ratio of the laser light emitted from the attenuator 3 is changed in accordance with the change in transmittance. In response to this, the information processing device 9 (control device) may control the polarization ratio of the laser light emitted from the polarization ratio control unit 4 to be constant by changing the polarization ratio of the polarization ratio control unit 4 in accordance with the changed transmittance.

[0024] When changing the polarization ratio of the polarization ratio control unit 4, the information processing device 9 (control device) may refer to information (polarization ratio table) stored in a storage unit 92 of the information processing device 9 in table format, for example, and specify (derive) the polarization ratio according to the transmittance. The polarization ratio table defines the polarization ratios corresponding to each transmittance.

[0025] The laser light emitted from the polarization ratio control unit 4 is incident on the beam shaping optical system 5, which shapes the incident laser light to generate laser light having a beam shape suitable for irradiating a silicon film. The beam shaping optical system 5 generates a line beam that is linear along the Y direction.

[0026] The beam shaping optical system 5 splits one beam into multiple beams (multiple line beams aligned in the Z direction) using, for example, a homogenizer made up of a lens array. After splitting into multiple beams, the multiple beams can be combined using a condenser lens to form a line beam. The beam shaping optical system 5 emits the generated (shaped) linear laser light to the epi-illumination mirror 61.

[0027] The epi-mirror 61 is a rectangular reflecting mirror extending in the Y direction and reflects the laser light, which is a plurality of line beams generated by the beam shaping optical system 5. The epi-mirror 61 is, for example, a dichroic mirror, which is a partial reflecting mirror that transmits a portion of the light. The epi-mirror 61 reflects the line-shaped laser light to generate reflected light and transmits a portion of the line-shaped laser light to generate transmitted light. The epi-mirror 61 irradiates the reflected laser light onto the silicon film of the substrate 8 and emits the transmitted laser light to a pulse measuring device, for example, a biplanar phototube.

[0028] The projection lens 65 is disposed above the substrate 8. The projection lens 65 has a plurality of lenses for projecting the laser light onto the substrate 8, i.e., the silicon film. The projection lens 65 focuses the laser light onto the substrate 8. On the substrate 8, the laser light forms a linear irradiation area along the Y direction. That is, on the substrate 8, the laser light is a line beam with the Y direction as the longitudinal direction. Furthermore, while the substrate 8 is being transported in the +X direction, the laser light is irradiated onto the silicon film. This allows the laser light to be irradiated onto a band-shaped area whose width is the length of the irradiation area in the Y direction.

[0029] The line beam-shaped laser light irradiated onto the epi-illumination mirror 61 has a beam shape with a widened minor axis width, i.e., the minor axis width is somewhat widened and the shape is distorted after being emitted from the condenser lens. The laser light reflected by the epi-illumination mirror 61 passes through the projection lens 65 and is shaped into a line beam-shaped laser light with a minor axis width of about 1 / 5.

[0030] The biplanar phototube 62 is provided at the end of the annealing optical system 11, adjacent to the beam shaping optical system 5, and detects the pulse waveform of the laser light emitted from the laser light source 2 based on the transmitted light that has passed through the epi-illumination mirror 61. The biplanar phototube 62 outputs (transmits) the detected pulse waveform to the information processing device 9 (control device).

[0031] The OED sensor 63 includes a light sensor (light detection mechanism) and a light source for the OED sensor 63, and detects reflected light (light reflected by the substrate 8) of light emitted from the light source (light source for the OED sensor) to obtain information about the crystal surface on the substrate 8. The OED sensor 63 outputs (transmits as a signal) the brightness (detection value) of the detected reflected light to the information processing device 9 (control device). The line light 641 is provided above the base 72.

[0032] The line camera 64 captures an image of the region of interest on the substrate 8 irradiated with the laser light, and outputs the captured image of the substrate 8 (substrate image) to the information processing device 9. The line camera 64 also uses light emitted from a line-type illuminator 641 provided above the base 72 to capture an image of the surface of the substrate 8 irradiated with the light emitted from the line-type illuminator 641 (substrate image). Furthermore, the line camera 64 may function as an unevenness monitor that detects the average luminance of the region of interest included in the captured substrate image and acquires information about scattered light of the surface shape of the substrate 8. In addition, the line camera 64 functioning as an unevenness monitor may output (transmit as a signal) the detected average luminance (detection value) of the substrate 8 (region of interest) to the information processing device 9 (control device).

[0033] The profiler camera 66 is a sensor (line beam sensor) that detects information about the shape of the laser light shaped into a line beam by the projection lens 65, and is, for example, a beam profiler. The profiler camera 66 is provided, for example, on the side of the stage 71 and is aligned so that the top surface of the profiler camera 66 is at the same height as the substrate 8 placed on the stage 71. The laser light shaped into a line beam by the annealing optical system 11 is irradiated onto the top surface of the profiler camera 66. The profiler camera 66 includes an imaging unit, such as a CMOS camera, and captures the laser light shaped into a line beam with the imaging unit to obtain information (data) about the shape of the laser light, such as an image (captured image). The profiler camera 66 may detect, as information about the shape of the laser light shaped into a line beam, information about the axial widths of the minor and major axes of the rectangular line beam, distortion or depression of the axis, tilt when the line beam is viewed stereoscopically, and angle or curvature between adjacent surfaces. The profiler camera 66 may further detect information about the shape of the raw beam before being shaped into a line beam. In addition to the profiler camera 66 of this embodiment, a line beam sensor that acquires information about the shape of the laser beam may be provided, for example, near the biplanar phototube 62, with its Y-axis direction different from that of the biplanar phototube 62.

[0034] The information processing device 9 is a computer such as a personal computer or a server device that performs overall or integrated control or management of the laser annealing apparatus 1, and performs a process of deriving unevenness information regarding surface unevenness in a substrate image using various learning models. The information processing device 9 includes a control unit 91, a storage unit 92, a communication unit 93, and an input / output I / F 94, and is communicatively connected to control devices (other control devices) that control the laser light source 2 or each optical system in the annealing optical system 11 via the communication unit 93 or the input / output I / F 94. The information processing device 9 is communicatively connected to various measuring devices, such as a pulse measuring device and a photodetector, included in the laser annealing apparatus 1, and may perform various controls on the laser light source 2 or the annealing optical system 11 based on measurement data output from these various measuring devices.

[0035] The control unit 91 has an arithmetic processing device with a timing function, such as one or more CPUs (Central Processing Units), MPUs (Micro-Processing Units), GPUs (Graphics Processing Units), NPUs (Neural network Processing Units), etc., and performs various information processing and control processing for the laser light source 2 or each optical system included in the annealing optical system 11 by reading and executing a program P (program product) stored in the storage unit 92. Furthermore, by using various learning models stored in the storage unit 92, the control unit 91 performs processing to determine (estimate) whether or not surface unevenness or brightness reduction will occur at the present time and in the future.

[0036] The memory unit 92 includes a volatile memory area such as a static random access memory (SRAM), a dynamic random access memory (DRAM), or a flash memory, and a non-volatile memory area such as an EEPROM or a hard disk. The memory unit 92 pre-stores a program P (program product) and data referenced during processing. The program P stored in the memory unit 92 may be a program P (program product) read from a recording medium M readable by the control unit 91. Alternatively, the program P (program product) may be downloaded from an external computer (not shown) connected to a communication network (not shown) and stored in the memory unit 92. The memory unit 92 stores actual files of various learning models (a first learning model 901, a second learning model 902). The actual files of the various learning models may be configured as modules included in the program P (program product).

[0037] The communication unit 93 is, for example, a communication module or communication interface conforming to the Ethernet (registered trademark) standard, and an Ethernet cable is connected to the communication unit 93. The communication unit 93 is not limited to being a wired communication module such as an Ethernet cable, but may be a communication interface compatible with wireless communication, such as a short-range wireless communication module such as Wi-Fi (registered trademark) or Bluetooth (registered trademark), or a wide-area wireless communication module such as 4G or 5G. The information processing device 9 may communicate with, for example, a model server SS connected to an external network GN or an information terminal T connected to an in-base network (LAN) via the communication unit 93.

[0038] The input / output I / F 94 is a communication interface that complies with a communication standard such as RS232C or USB. An input device such as a keyboard or a display device 941 such as a liquid crystal display is connected to the input / output I / F 94. The information processing device 9 may acquire board images or various detection values ​​from a detection unit such as a biplanar phototube 62, an OED sensor 63, a line camera 64 (unevenness monitor), or a profiler camera 66 via the input / output I / F 94.

[0039] Furthermore, the input / output I / F 94 may be connected to various sensors that detect operating status data related to the operating status of the laser annealing apparatus 1, such as a temperature sensor 942, a flow rate sensor 943, a vibration sensor 944, a pressure sensor 945, and a gas sensor 946, which are provided at various locations in the laser annealing apparatus 1.

[0040] The temperature sensor 942 measures and outputs, for example, the temperatures of the vacuum pump, cold head, He compressor, and diaphragm pump provided in the laser annealing apparatus 1, or the surface temperature of the substrate 8. The flow rate sensor 943 measures and outputs, for example, the flow rate (volumetric flow rate per unit time) of nitrogen or oxygen in the laser irradiation chamber 7 (processing chamber). The vibration sensor 944 measures and outputs, for example, the vibration frequency of the stage 71, the base 72, or the substrate 8. The pressure sensor 945 measures and outputs, for example, the internal pressure of the laser irradiation chamber 7 (processing chamber), vacuum pump, He compressor, or diaphragm pump. The gas sensor 946 measures and outputs, for example, the concentration of each component of the gas in the laser irradiation chamber 7 (processing chamber). The control unit 91 periodically acquires, via the input / output I / F 94, detection values ​​(detected physical quantities, etc.) output from various sensors that detect operating state data related to the operating state of the laser annealing apparatus 1, such as the temperature sensor 942, flow rate sensor 943, vibration sensor 944, pressure sensor 945, and gas sensor 946.

[0041] The model server SS is, for example, a server device such as a cloud server, and includes a control unit, a storage unit, and a communication unit similar to the information processing device 9. The information terminal T is, for example, a smartphone, a tablet, or a PC, and includes a control unit, a storage unit, and a communication unit similar to the information processing device 9. The information terminal T and the model server SS may be communicably connected via an in-base network (LAN) and an external network GN (WAN) such as the Internet.

[0042] 4 is an explanatory diagram regarding the generation process of the first learning model 901 (unevenness prediction model). The model server SS or the control unit 91 of the information processing device 9 trains a neural network using training data, and generates the first learning model 901 (unevenness prediction model) that outputs information regarding the occurrence of surface unevenness in the future when operating state data is input.

[0043] The training data is composed of question data including operating state data for a predetermined period before the occurrence of surface unevenness and answer data including information regarding the occurrence of surface unevenness, and is stored in the model server SS or the storage unit 92 of the information processing device 9. The question data including the operating state data may include a first group of parameters that require checking when surface unevenness occurs, a second group of parameters that require checking when a decrease in brightness occurs, and a third group of parameters that require checking when other abnormal events occur. The original data for this training data can be generated, for example, by aggregating operating state data performed by multiple laser annealing apparatuses 1 and data regarding the occurrence of abnormal events.

[0044] The operating state data includes physical quantities such as temperature and pressure in each unit, module, component, or portion included in the laser annealing apparatus 1, the state of the laser light emitted by the laser annealing apparatus 1 (beam shape, spatial distribution, etc.), and data related to the state of the substrate 8 on which the laser light is irradiated. The operating state data is data detected by various sensors during a period in which the laser annealing apparatus 1 is operating normally (normal operation period), and corresponds to data before an abnormal event such as surface unevenness or brightness reduction occurs. Furthermore, the operating state data may also include data detected by various sensors during a period in which an abnormal event such as surface unevenness, brightness reduction, or oxygen concentration abnormality occurs during the operation of the laser annealing apparatus 1 (abnormal operation period). In this case, the abnormal event (type of surface unevenness, brightness reduction, oxygen concentration abnormality, etc.) that has occurred is labeled as answer data for the operating state data (problem data) during the abnormal operation period.

[0045] The driving state data included in the problem data is composed of a group of driving state data at multiple points in time (multiple consecutive measurement points) included in a predetermined period, i.e., time-series data. The predetermined period corresponds to a processing unit period when performing estimation using the first learning model 901, i.e., a period that defines a unit of input data when inputting to the first learning model 901, and defines a tensor (multidimensional array) that serves as input data to the first learning model 901.

[0046] The response data includes whether or not surface unevenness has occurred for the driving state data for a predetermined period, and if surface unevenness has occurred, the type of surface unevenness. Regarding the occurrence of surface unevenness, the response data may include not only the occurrence of surface unevenness in the future after the time of acquisition of the driving state data (time of measurement), but also the occurrence of surface unevenness at the present time of acquisition of the driving state data. The types of surface unevenness include, for example, streak unevenness, poor irradiation, film skipping, and flow unevenness.

[0047] Streak unevenness indicates linear streak-like surface unevenness in the vertical direction (scanning direction: scanning direction of the line beam) or horizontal direction (shot direction: laser beam direction) of the substrate 8. Irradiation defects indicate linear rectangular surface unevenness in the vertical direction (scanning direction: scanning direction of the line beam) or horizontal direction (shot direction: laser beam direction). Film skipping indicates wave-shaped surface unevenness in the vertical direction (scanning direction: scanning direction of the line beam). Flow unevenness indicates surface unevenness caused by irregular areas extending diagonally on the surface of the substrate 8.

[0048] The neural network (first learning model 901) trained using the training data is expected to be used as a program module that is part of artificial intelligence software. The first learning model 901 (mura prediction model) is used in the information processing device 9, and when executed in the model server SS or the information processing device 9 having such processing capabilities, a neural network system is configured.

[0049] The first learning model 901 (unevenness prediction model) is, for example, configured using a DNN (Deep Neural Network), and has an input layer that accepts input of driving condition data (time series data) for a predetermined period before the occurrence of surface unevenness, an intermediate layer that extracts features of the driving condition data, and an output layer that outputs information regarding the occurrence of surface unevenness.

[0050] The input layer has multiple neurons that receive a group of operating state data (time-series data) at multiple points in time within a predetermined period, and passes the input values ​​to the middle layer. The middle layer is defined using an activation function such as a ReLu function or a sigmoid function, and has multiple neurons that extract features of each input value, and passes the extracted features to the output layer. Parameters such as weighting coefficients and bias values ​​of the activation function are optimized using the backpropagation method. The output layer is composed of, for example, a fully connected layer, and outputs information about the occurrence of surface unevenness based on the features output from the middle layer.

[0051] In this embodiment, the first learning model 901 (mura prediction model) is a DNN, but is not limited to this and may be a learning model constructed using other learning algorithms, such as a neural network other than a DNN, a transformer, a recurrent neural network (RNN), a long-short term model (LSTM), a CNN, a support vector machine (SVM), a Bayesian network, linear regression, a regression tree, multiple regression, a random forest, or an ensemble.

[0052] 5 is a flowchart showing an example of a processing procedure (during learning of an unevenness prediction model) of the control unit 91 of the model server SS. The control unit 91 of the model server SS connected to each information processing device 9 installed at each base accepts an operation from an operator, for example, via a keyboard connected to an input / output, and performs the following processing based on the accepted operation. In this embodiment, the first learning model 901 (unevenness prediction model) is generated by the model server SS, but this is not limited to this and may be generated by each information processing device 9 installed at each base.

[0053] The control unit 91 of the model server SS acquires operating state data for a predetermined period before the occurrence of surface unevenness (S11). The control unit 91 of the model server SS acquires a group of operating state data (time-series data) at multiple points in time included in the predetermined period from each of the information processing devices 9 installed at each base. The control unit 91 of the model server SS acquires data related to the occurrence of surface unevenness (surface unevenness occurrence data) accompanying the operating state data. In acquiring the surface unevenness occurrence data, the control unit 91 of the model server SS may acquire not only data related to surface unevenness but also data related to the occurrence of abnormal events such as a decrease in brightness and an abnormal oxygen concentration (abnormal event occurrence data), and extract the surface unevenness occurrence data from the abnormal event occurrence data.

[0054] The control unit 91 of the model server SS generates training data using the acquired driving state data (S12). The control unit 91 of the model server SS generates training data using the acquired driving state data and data related to the occurrence of surface unevenness that accompanies the driving state data. That is, the control unit 91 of the model server SS generates training data by associating (setting a label) the presence or absence of surface unevenness and, if surface unevenness occurs, the type of surface unevenness with a group of driving state data (time-series data) at multiple points in time included in a predetermined period.

[0055] The control unit 91 of the model server SS uses the generated training data to train the first learning model 901 (unevenness prediction model) (S13). For example, the control unit 91 of the model server SS applies the learning data set (training data) to a neural network such as a DNN, and causes learning, thereby generating the first learning model 901 (unevenness prediction model) that outputs information regarding the occurrence of surface unevenness in the future when operating state data is input.

[0056] 6 is an explanatory diagram regarding the generation process of the second learning model 902 (brightness decrease prediction model). The model server SS or the control unit 91 of the information processing device 9 trains a neural network using training data, and generates the second learning model 902 (brightness decrease prediction model) that outputs information regarding the occurrence of future brightness decrease when driving state data is input.

[0057] The training data is composed of question data including operating state data for a predetermined period before the occurrence of the luminance decrease and answer data including information regarding the occurrence of the luminance decrease, and is stored in the model server SS or the storage unit 92 of the information processing device 9. The question data including the operating state data may include a first group of parameters that require checking when surface unevenness occurs, a second group of parameters that require checking when the luminance decrease occurs, and a third group of parameters that require checking when other abnormal events occur. The original data for this training data can be generated, for example, by aggregating operating state data performed by multiple laser annealing apparatuses 1 and data regarding the occurrence of abnormal events. The operating state data (question data) may be the same data as the operating state data (question data) used to generate the first learning model 901 (unevenness prediction model).

[0058] The response data includes whether or not a decrease in brightness has occurred with respect to the driving state data for a predetermined period. The occurrence of a decrease in brightness may include not only future occurrences of a decrease in brightness after the time point at which the driving state data is acquired (measurement time point), but also occurrences of a decrease in brightness at the present time point at which the driving state data is acquired. The decrease in brightness indicates an abnormal event in which the brightness of the substrate 8 has decreased, and the brightness of the substrate 8 is detected by the OED sensor 63, which includes a light sensor (light detection mechanism) and a light source. In other words, the brightness of the substrate 8 indicates the brightness of the reflected light (light reflected by the substrate 8) of light emitted from the light source (light source for the OED sensor) of the OED sensor 63.

[0059] The second learning model 902 (brightness reduction prediction model) is configured, for example, by a DNN (Deep Neural Network), and has an input layer that receives input of driving state data (time-series data) for a predetermined period before the occurrence of surface unevenness, an intermediate layer that extracts features of the driving state data, and an output layer that outputs information related to the occurrence of brightness reduction. The second learning model 902 (brightness reduction prediction model) may be configured by a DNN or the like, similar to the first learning model 901 (unevenness prediction model).

[0060] 7 is a flowchart showing an example of a processing procedure (during learning of a luminance decrease prediction model) of the control unit 91 of the model server SS. The control unit 91 of the model server SS connected to each of the information processing devices 9 installed at each base accepts an operation by an operator, for example, via a keyboard connected to an input / output, and performs the following processing based on the accepted operation. In this embodiment, the second learning model 902 (luminance decrease prediction model) is generated by the model server SS, but this is not limited to this, and may be generated by each of the information processing devices 9 installed at each base.

[0061] The control unit 91 of the model server SS acquires driving state data for a predetermined period before the occurrence of a luminance decrease (T11). The control unit 91 of the model server SS acquires a group of driving state data (time-series data) for multiple points in time included in the predetermined period from each of the information processing devices 9 installed at each base. The control unit 91 of the model server SS acquires data related to the occurrence of a luminance decrease (luminance decrease occurrence data) accompanying the driving state data. When acquiring the luminance decrease occurrence data, the control unit 91 of the model server SS may acquire not only data related to the luminance decrease but also data related to the occurrence of abnormal events such as surface unevenness and oxygen concentration abnormalities (abnormal event occurrence data), and extract the luminance decrease occurrence data from the abnormal event occurrence data.

[0062] The control unit 91 of the model server SS generates training data using the acquired driving state data (T12). The control unit 91 of the model server SS generates training data using the acquired driving state data and data related to the occurrence of luminance reduction associated with the driving state data. That is, the control unit 91 of the model server SS generates training data by associating (setting a label) the presence or absence of luminance reduction with a group of driving state data (time-series data) at multiple points in time included in a predetermined period.

[0063] The control unit 91 of the model server SS uses the generated training data to train the second learning model 902 (brightness decrease prediction model) (T13). For example, the control unit 91 of the model server SS applies the learning data set (training data) to a neural network such as a DNN, and causes learning, thereby generating the second learning model 902 (brightness decrease prediction model) that outputs information regarding the occurrence of future brightness decrease when driving state data is input.

[0064] 8 is a functional block diagram illustrating functional units included in the control unit 91 of the information processing device 9. The control unit 91 of the information processing device 9 executes a program P stored in the storage unit 92, thereby functioning as an acquisition unit 911, a time-series data analysis unit 912, a parameter identification unit 913, and a screen output unit 914. Furthermore, the control unit 91 of the information processing device 9 executes the program P stored in the storage unit 92, thereby functioning as a first learning model 901 (unevenness prediction model) and a second learning model 902 (brightness reduction prediction model).

[0065] The acquisition unit 911 acquires operating state data including time-series data periodically measured by various sensors. These sensors include, for example, the biplanar photoelectric tube 62, the OED sensor 63, the line camera 64, the profiler camera 66, the temperature sensor 942, the flow rate sensor 943, the vibration sensor 944, the pressure sensor 945, and the gas sensor 946. The operating state data detected by these various sensors includes not only physical quantities such as temperature and pressure in each unit, module, component, or part included in the laser annealing apparatus 1, but also data related to the state of the laser light emitted by the laser annealing apparatus 1 (beam shape, spatial distribution, etc.) and the state of the substrate 8 irradiated with the laser light. If the laser annealing apparatus 1 includes, for example, two laser light sources 2 (a first laser light source and a second laser light source), the data related to the state of the laser light (operating state data) may include data indicating the half-widths of the pulse widths of the two laser light sources and the synchronization state of the two laser light sources 2.

[0066] The acquisition unit 911 periodically acquires operating state data from various sensors, associates the acquired operating state data with the time of acquisition, and stores the acquired operating state data in a chronological order (manages it as chronological data) in the storage unit 92 of the information processing device 9. When the information processing device 9 is configured by, for example, a control device that controls the laser annealing device 1, the acquisition unit 911 may associate the operating state data periodically acquired from the various sensors with a device number that uniquely identifies the laser annealing device 1, and transmit the data to the model server SS via the external network GN.

[0067] During a period in which the laser annealing apparatus 1 is operating normally, the operating state data acquired by the acquisition unit 911 corresponds to data before an abnormal event such as surface unevenness or brightness reduction occurs. The acquisition unit 911 periodically acquires the operating state data before the abnormal event occurs. The acquisition unit 911 generates, from the group of operating state data acquired periodically at multiple time points, a group of operating state data acquired at multiple time points included in a predetermined period, as input data for the first learning model 901 (unevenness prediction model), the second learning model 902 (brightness reduction prediction model), and the time-series data analysis unit 912.

[0068] The acquisition unit 911 outputs the generated input data (a group of driving state data acquired at multiple time points included in a predetermined period) to the first learning model 901 (unevenness prediction model), the second learning model 902 (brightness decrease prediction model), and the time-series data analysis unit 912. The length of the predetermined period is stored in the memory unit 92 and corresponds to a processing unit period when performing abnormality determination using the first learning model 901, the second learning model 902, and the time-series data analysis unit 912. The acquisition unit 911 may convert each of the various data included in the periodically acquired driving state data into a format in which each data is listed for substantially the same measurement time point (acquisition time point). In this case, the format-converted driving state data may be data in a matrix format in which the horizontal direction represents data types such as a first parameter and a second parameter, and the vertical direction represents measurement time points. By using the driving state data converted into a matrix format having dimensions in both the vertical and horizontal directions, the first learning model 901 and the second learning model 902, which are configured as CNNs having convolutional layers, can be applied.

[0069] The first learning model 901 (unevenness prediction model) acquires input data (a group of operating state data acquired at multiple time points included in a predetermined period) from the acquisition unit 911, and outputs information regarding the future occurrence of surface unevenness based on the acquired input data. The information regarding the future occurrence of surface unevenness may include whether or not surface unevenness will occur in the future, the possibility of whether or not surface unevenness will occur, and, if the occurrence of surface unevenness is predicted, the type of surface unevenness. In this case, the future period corresponds to a predetermined elapsed period from the present time, and may be, for example, within 30 minutes or within 1 hour from the present time, which is pre-stored in the storage unit 92.

[0070] When outputting information regarding the occurrence of surface unevenness in the future, the first learning model 901 may include a determination result of whether or not surface unevenness has occurred at the present time. That is, the first learning model 901 outputs information regarding the occurrence of surface unevenness in the future, including the present time, (determination results regarding the presence or absence of surface unevenness, the type of surface unevenness, etc.) based on input data (a group of operating state data acquired at multiple points in time included in a predetermined period) from the acquisition unit 911. The first learning model 901 outputs the information regarding the occurrence of surface unevenness, which is the determination result, to the parameter identification unit 913.

[0071] The second learning model 902 (brightness decrease prediction model) acquires input data (a group of driving state data acquired at multiple time points within a predetermined period) from the acquisition unit 911 and outputs information regarding the occurrence of future brightness decrease based on the acquired input data. In this case, the future period corresponds to a predetermined elapsed period from the present time, and may be a period pre-stored in the storage unit 92, such as within 30 minutes or within 1 hour from the present time. When outputting the information regarding the occurrence of future brightness decrease, the second learning model 902 may include a determination result regarding whether or not brightness decrease has occurred at the present time. That is, the second learning model 902 outputs information regarding the occurrence of brightness decrease in the future, including the present time, based on the input data (a group of driving state data acquired at multiple time points within a predetermined period) from the acquisition unit 911. The second learning model 902 outputs the determination result, information regarding the occurrence of brightness decrease, to the parameter identification unit 913.

[0072] The time-series data analysis unit 912 acquires input data (a group of operating state data acquired at multiple time points included in a predetermined period) from the acquisition unit 911, and outputs information regarding the occurrence of an abnormal event in the future based on the acquired input data. The abnormal event includes, for example, at least some or all of an abnormal vibration frequency, a deterioration in the symmetry of the spatial distribution of the laser light, an increase in the half-width of the pulse waveform, and an increase in the oxygen concentration.

[0073] The time-series data analysis unit 912 analyzes the input data (a group of operating state data acquired at multiple time points within a predetermined period) using a determination rule that is predetermined for each abnormal event to be determined, based on time-series changes in each of the various data included in the input data, comparison results with predetermined thresholds, or differences between multiple correlated data. The time-series data analysis unit 912 outputs information regarding the occurrence of an abnormal event in the future, including the present, based on the analysis results using the determination rule. The information regarding the occurrence of an abnormal event output by the time-series data analysis unit 912 includes whether or not an abnormal event has occurred at the present time or in the future, and, if it is determined that an abnormal event has occurred, the type of abnormal event that is currently occurring or the type of abnormal event that is predicted to occur within a predetermined period. The time-series data analysis unit 912 outputs information regarding the occurrence of an abnormal event, which is the determination result, to the parameter identification unit 913.

[0074] In this manner, the first learning model 901, the second learning model 902, and the time-series data analysis unit 912 use the driving state data from the acquisition unit 911 to make judgments about different abnormal events. That is, by providing multiple judgment processing units corresponding to different types of abnormal events for the same driving state data, processing for each individual abnormal event can be performed in parallel or in a contemporaneous manner, thereby enabling efficient overall computation. In the present embodiment, the driving state data is used with judgment processing units (the first learning model 901, the second learning model 902, and the time-series data analysis unit 912) corresponding to each different abnormal event, respectively, but this is not limited thereto. The control unit 91 of the information processing device 9 may be configured to integrate these judgment processing units (the first learning model 901, the second learning model 902, and the time-series data analysis unit 912) and output (estimate) the type and presence or absence of an abnormal event based on the input driving state data using a single judgment processing unit (integrated model) corresponding to multiple types of abnormal events.

[0075] The parameter identification unit 913 derives correspondence information including a first group of parameters to be checked depending on the type of surface unevenness when surface unevenness occurs, based on the determination result (information related to the occurrence of surface unevenness) from the first learning model 901. The parameter identification unit 913 may derive correspondence information including the first group of parameters by referring to a check parameter table stored in the storage unit 92.

[0076] The parameter identification unit 913 derives correspondence information including a second group of parameters to be checked in response to a decrease in luminance when the decrease in luminance occurs, based on the determination result (information regarding the occurrence of a decrease in luminance) from the second learning model 902. The parameter identification unit 913 may derive correspondence information including the second group of parameters by referring to a check parameter table stored in the storage unit 92.

[0077] When an abnormal event occurs, the parameter specifying unit 913 derives correspondence information including a third group of parameters to be checked depending on the type of the abnormal event, based on the determination result (information related to the occurrence of the abnormal event) from the time-series data analyzing unit 912. The parameter specifying unit 913 may derive correspondence information including the third group of parameters by referring to a check parameter table stored in the storage unit 92. Details of the check parameter table will be described later.

[0078] When surface unevenness occurs based on the determination result of the first learning model 901, the parameter identification unit 913 outputs correspondence information including the derived first group of parameters to the screen output unit 914. When a decrease in brightness occurs based on the determination result of the second learning model 902, the parameter identification unit 913 outputs correspondence information including the derived second group of parameters to the screen output unit 914. When an abnormal event occurs based on the determination result of the time-series data analysis unit 912, the parameter identification unit 913 outputs correspondence information including the derived third group of parameters to the screen output unit 914.

[0079] The screen output unit 914 generates screen data in HTML format or the like constituting an abnormality notification screen using the correspondence information (correspondence information including the first parameter group, correspondence information including the second parameter group, and correspondence information including the third parameter group) acquired from the parameter identification unit 913, and outputs the generated screen data to, for example, the display device 941 or an information terminal T of the operator of the laser annealing apparatus 1. The screen output unit 914 may generate the abnormality notification screen (screen data) including the input data acquired from the acquisition unit 911 (a group of operating state data acquired at multiple time points included in a predetermined period). In this case, the screen output unit 914 may generate a graph using the operating state data consisting of multiple time points as time-series data, and generate the abnormality notification screen (screen data) including the graph.

[0080] The screen output unit 914 may generate different abnormality notification screens (screen data) according to the correspondence information including the first parameter group, the correspondence information including the second parameter group, and the correspondence information including the third parameter group acquired from the parameter identification unit 913, respectively, or may generate a single abnormality notification screen (screen data) by including these correspondence information. Details of the abnormality notification screen will be described later. The screen output unit 914 may output the generated abnormality notification screen (screen data) to the display device 941 or an information terminal T of an operator of the laser annealing apparatus 1, etc., to cause the abnormality notification screen to be popped up (displayed in a pop-up window) on the display device 941 or the information terminal T.

[0081] 9 is a flowchart showing an example of a processing procedure of the control unit 91 of the information processing device 9. The control unit 91 of the information processing device 9 connected to the laser annealing apparatus 1 accepts an operation from an operator using, for example, a keyboard connected to an input / output, and performs the following processing based on the accepted operation. The information processing device 9 may be a control device included in the laser annealing apparatus 1, and in this case, the laser annealing apparatus 1 including the control device may perform the following processing. Alternatively, a model server SS such as a cloud server connected to the control device (information processing device 9) of the laser annealing apparatus 1 via an external network GN such as the Internet may perform the following processing based on operating state data acquired from the information processing device 9. Alternatively, the control device (information processing device 9) of the laser annealing apparatus 1 and the model server SS may perform the following processing in cooperation or collaboration.

[0082] The control unit 91 of the information processing device 9 acquires operating state data relating to the operating state of the laser annealing device 1 irradiating the substrate 8 with laser light (S101). The control unit 91 of the information processing device 9 acquires operating state data relating to the operating state of the laser annealing device 1 for a predetermined period from various sensors. The operating state data may include a first group of parameters that require checking when surface unevenness occurs, a second group of parameters that require checking when brightness reduction occurs, and a third group of parameters relating to other abnormal events. The predetermined period may be a period during which the laser annealing device 1 is operating normally, i.e., a period during which surface unevenness or brightness reduction does not occur. The operating state data for the predetermined period is composed of time-series data including multiple time points (measurement time points) at which the operating state data was acquired.

[0083] The control unit 91 of the information processing device 9 inputs driving state data to the first learning model 901 (S102). The control unit 91 of the information processing device 9 acquires information regarding the occurrence of surface unevenness from the first learning model 901 (S103). The control unit 91 of the information processing device 9 inputs driving state data to the first learning model 901, thereby acquiring information regarding the occurrence of surface unevenness output by the first learning model 901. The information regarding the occurrence of surface unevenness output by the first learning model 901 includes whether or not surface unevenness has occurred at the present time or in the future, and, if surface unevenness has occurred, the type of surface unevenness. The control unit 91 of the information processing device 9 can acquire a determination result regarding the presence or absence of surface unevenness by using the first learning model 901.

[0084] The control unit 91 of the information processing device 9 outputs correspondence information regarding the first parameter group required to deal with surface unevenness (S104) in accordance with the information from the first learning model 901. Depending on the determination result, i.e., when it is determined that surface unevenness has occurred or that the occurrence of surface unevenness is predicted, the control unit 91 of the information processing device 9 outputs correspondence information regarding the first parameter group required to deal with surface unevenness, for example, by referring to a check parameter table stored in the storage unit 92.

[0085] 10 is a diagram illustrating an example of a check parameter table. The check parameter table is pre-stored in the storage unit 92 of the information processing device 9. The types of management items in the check parameter table include, for example, the type of abnormal event and response information (parameters that require a countermeasure or confirmation). The management items for the type of abnormal event include, for example, types of surface unevenness such as streak unevenness, poor irradiation, film skipping, and flow unevenness, as well as brightness reduction and other abnormal events such as brightness reduction, vibration frequency abnormality, deterioration of spatial distribution symmetry, increase in half-width of pulse waveform, and increase in oxygen concentration.

[0086] The management item for response information stores response information when the type of abnormal event stored in the same record occurs, i.e., parameters that require countermeasures or confirmation (first parameter group, second parameter group, third parameter group). If the abnormal event is surface unevenness, the first parameter group is stored. If the abnormal event is a decrease in brightness, the second parameter group is stored. If the abnormal event is another abnormal event, the third parameter group is stored.

[0087] If the type of abnormal event is streak unevenness (surface unevenness), the management items of the correspondence information may store the following: the countermeasure is to adjust the gain of the stage 71, and the parameters (first parameter group) that require confirmation are stage ripple, vibration, laser intensity fluctuation, and pulse waveform.If the type of abnormal event is poor irradiation (surface unevenness), the management items of the correspondence information may store the following: the countermeasure is to adjust the synchronization parameters, and the parameters (first parameter group) that require confirmation are energy density, synchronization deviation (Sync Dev), and beam shape.If the type of abnormal event is film flying (surface unevenness), the management items of the correspondence information may store the following: the countermeasure is to replace the gas and adjust the angle of the resonator mirror (epi-illumination mirror 61), and the parameters (first parameter group) that require confirmation are oxygen concentration, nitrogen concentration, exhaust volume, and floating amount of the substrate 8. When the type of abnormal event is flow unevenness (surface unevenness), the management items of the response information may store information indicating that the response measures are gas replacement and angle adjustment of the resonator mirror (epi-illumination mirror 61), and that the parameters to be checked (first parameter group) are oxygen concentration, nitrogen concentration, exhaust volume, and floating amount of the substrate 8. The control unit 91 of the information processing device 9 can efficiently derive response information related to the first parameter group required to respond to the surface unevenness according to the type of surface unevenness by referring to the check parameter table.

[0088] The control unit 91 of the information processing device 9 inputs the driving state data to the second learning model 902 (S105). The control unit 91 of the information processing device 9 acquires information regarding the occurrence of luminance reduction from the second learning model 902 (S106). The control unit 91 of the information processing device 9 inputs the driving state data to the second learning model 902, thereby acquiring information regarding the occurrence of luminance reduction output by the second learning model 902. The information regarding the occurrence of luminance reduction output by the second learning model 902 includes whether or not luminance reduction has occurred at the present time or in the future. The control unit 91 of the information processing device 9 can acquire a determination result regarding whether or not luminance reduction has occurred by using the second learning model 902.

[0089] The control unit 91 of the information processing device 9 outputs correspondence information regarding the second parameter group required to deal with the decrease in brightness in accordance with the information from the second learning model 902 (S107). Depending on the determination result, i.e., when it is determined that a decrease in brightness has occurred or that the occurrence of a decrease in brightness is predicted, the control unit 91 of the information processing device 9 outputs correspondence information regarding the second parameter group required to deal with the decrease in brightness, for example, by referring to a check parameter table stored in the storage unit 92.

[0090] In the check parameter table, when the type of abnormal event is a decrease in brightness, the management item of the response information may store information indicating that the response is to adjust synchronization parameters, and that the parameters to be checked (second parameter group) are energy density, synchronization deviation amount (Sync dev), and beam shape. The control unit 91 of the information processing device 9 can efficiently derive response information regarding the second parameter group required to respond to the decrease in brightness by referring to the check parameter table.

[0091] The control unit 91 of the information processing device 9 inputs the operating state data to the time-series data analysis unit 912 (S108). The control unit 91 of the information processing device 9 acquires information related to the occurrence of an abnormal event from the time-series data analysis unit 912 (S109). The control unit 91 of the information processing device 9 inputs the operating state data to the time-series data analysis unit 912, i.e., performs calculation processing using determination rules defined in routines or modules constituting the time-series data analysis unit 912, thereby outputting information related to the occurrence of an abnormal event in the future, including the present time. The information related to the occurrence of an abnormal event includes whether or not an abnormal event has occurred at the present time or in the future, and, if it is determined that an abnormal event has occurred, the type of abnormal event that has occurred at the present time or is predicted to occur within a predetermined period of time.

[0092] The control unit 91 of the information processing device 9 outputs correspondence information regarding the third parameter group required to respond to the abnormal event in accordance with the information from the time-series data analysis unit 912 (S110). Depending on the determination result, i.e., when it is determined that an abnormal event has occurred or that the occurrence of an abnormal event is predicted, the control unit 91 of the information processing device 9 outputs correspondence information regarding the third parameter group required to respond to the abnormal event, for example, by referring to the check parameter table stored in the storage unit 92.

[0093] In the check parameter table, when the type of abnormal event is a vibration frequency abnormality, the management item of the corresponding information may be adjustment of the gain of the stage 71 (a measure taken since oscillation of the stage 71 is suspected), and the parameter requiring confirmation (third parameter) may be the gain of the stage 71. When the type of abnormal event is deterioration of the symmetry of the spatial distribution, the management item of the corresponding information may be gas replacement or adjustment of the angle of the resonator mirror (a measure taken since deterioration of the gas for laser oscillation is suspected), and the parameters requiring confirmation (third parameter group) may be the gas components and the angle of the resonator mirror.

[0094] When the type of abnormal event is an increase in the half-width of the pulse waveform, the management item of the response information may be an adjustment of a synchronization parameter (a countermeasure taken due to a suspected loss of synchronization between lasers), and the parameters requiring confirmation (third parameter group) may be stored as synchronization parameters. When the type of abnormal event is an increase in oxygen concentration, the management item of the response information may be an increase in the nitrogen flow rate into the processing chamber (a countermeasure taken due to a suspected nitrogen leak), and the parameters requiring confirmation (third parameter group) may be the nitrogen concentration and the oxygen concentration. By referring to the check parameter table, the control unit 91 of the information processing device 9 can efficiently derive response information related to the third parameter group required to respond to the abnormal event depending on the type of abnormal event.

[0095] The control unit 91 of the information processing device 9 outputs an abnormality notification screen including various response information derived using the driving state data (S111). The control unit 91 of the information processing device 9 generates and outputs an abnormality notification screen (screen data) including the response information acquired from the first learning model 901, the second learning model 902, or the time-series data analysis unit 912 and the driving state data that is the source data for deriving the response information. The control unit 91 of the information processing device 9 may extract data (parameters) corresponding to an abnormal event determined to have occurred from various data included in the driving state data, and generate the abnormality notification screen (screen data) including a graph displaying the extracted data (parameters) in chronological order. In this case, the data (parameters) graphed in chronological order may be parameters (first parameter group, second parameter group, third parameter group) that should be checked when an abnormal event occurs.

[0096] 11 is a diagram illustrating an example of an abnormality notification screen or the like that notifies the occurrence of an abnormality in the laser annealing apparatus 1. The control unit 91 of the information processing device 9 outputs screen data in HTML format or the like that constitutes the abnormality notification screen to the display device 941 or the information terminal T of the operator of the laser annealing apparatus 1, whereby the abnormality notification screen is displayed as a pop-up on a display unit such as a display of the display device 941 or the information terminal T. At this time, the display device 941 or the information terminal T displays an operation status display screen that monitors the operation status of the laser annealing apparatus 1, and the operation status display screen may be used as a main screen, with the abnormality notification screen being displayed as a pop-up (displayed in a pop-up window) as a sub-screen. In other words, the display device 941 or the information terminal T may be triggered by receiving screen data from the information processing device 9 to display the abnormality notification screen as a pop-up (displayed in a pop-up window).

[0097] The pop-up abnormality notification screen may be a different abnormality notification screen (screen data) for each of the abnormalities, i.e., surface unevenness, brightness reduction, and other abnormal events, or a single abnormality notification screen may contain information corresponding to these. In this embodiment, a different abnormality notification screen is popped up for each of the abnormalities, i.e., surface unevenness, brightness reduction, and other abnormal events.

[0098] For example, if it is determined that an abnormal event other than surface unevenness or a decrease in brightness has occurred, the abnormality notification screen includes, for example, an abnormal event display area, a time-series data display area, and a response information display area. The abnormal event display area displays the type of abnormal event (in this embodiment, an increase in the oxygen concentration in the processing chamber). The time-series data display area displays, in a graph format, time-series data included in the operating state data, data (parameters) that serve as the basis for determining whether the abnormal event has occurred. The response information display area displays response information corresponding to the type of abnormal event, i.e., response information (parameters that require countermeasures or confirmation) defined for the type of abnormal event in the check parameter table.

[0099] Furthermore, the abnormality notification screen may include a character string (in this embodiment, "details") or an icon hyperlinked to a corresponding page in a manual that describes information corresponding to the type of abnormal event. By clicking on the character string, document data such as a manual that describes various response information related to the type of abnormal event can be accessed. Similarly, when surface unevenness or a decrease in brightness occurs, the abnormality notification screen pops up and displays information corresponding to the surface unevenness or decrease in brightness that has occurred in the abnormal event display area, the time-series data display area, and the response information display area.

[0100] According to this embodiment, the control unit 91 of the information processing device 9 acquires operating state data related to the operating state of the laser annealing device 1 from various sensors that detect operating state data related to the operating state of the laser annealing device 1, such as a temperature sensor 942, a flow rate sensor 943, a vibration sensor 944, a pressure sensor 945, and a gas sensor 946, which are provided at various locations in the laser annealing device 1 that is irradiating the substrate 8 with laser light. Furthermore, the control unit 91 of the information processing device 9 acquires operating state data related to the operating state of the laser annealing device 1 from various sensors that detect data related to the state of the laser light (beam shape) or the state of the substrate 8 that is irradiated with the laser light, such as the biplanar phototube 62, the OED sensor 63, the line camera 64, and the profiler camera 66. That is, the operating state data acquired by the information processing device 9 includes not only the physical quantities of each unit, module, component, or location included in the laser annealing device 1, but also data related to the state of the laser light (beam shape, spatial distribution, etc.) emitted by the laser annealing device 1 and the state of the substrate 8 that is irradiated with the laser light. For example, if the laser annealing apparatus 1 includes two laser light sources 2 (a first laser light source and a second laser light source), the data regarding the state of the laser light may include data indicating the half-width of the pulse widths of the two laser light sources 2 and the synchronization state of the two laser light sources 2. The control unit 91 of the information processing device 9 may periodically acquire operating state data from these various sensors, associate the acquired operating state data with the time of acquisition, and store the acquired operating state data in the storage unit 92 of the information processing device 9 to chronologically store the operating state data (manage as time-series data). Based on the acquired operating state data, the control unit 91 of the information processing device 9 determines whether surface unevenness has occurred on the substrate 8 or whether the luminance of the substrate 8 has decreased (luminance decrease has occurred). In making this determination, the control unit 91 of the information processing device 9 may determine that surface unevenness or luminance decrease has occurred not only when surface unevenness or luminance decrease has occurred at the present time, but also when surface unevenness or luminance decrease is predicted to occur in the future (within a predetermined elapsed period from the present time).Furthermore, the control unit 91 of the information processing device 9 may determine whether various events (abnormal events) that may cause surface unevenness or brightness reduction have occurred based on the acquired operating state data. Such abnormal events include, for example, the occurrence of a peak at a frequency (a frequency outside the steady-state range) not normally seen in vibration measurement, a deterioration in the symmetry of the spatial distribution of the laser light, or an increase in the half-width of the pulse waveform. If the control unit 91 of the information processing device 9 determines that surface unevenness has occurred, it outputs corresponding information regarding a first group of parameters required to address the surface unevenness. If the control unit 91 determines that brightness reduction has occurred, it outputs corresponding information regarding a second group of parameters required to address the brightness reduction to, for example, an information terminal T of an operator of the laser annealing device 1. In this case, parameter groups (first parameter group, second parameter group) corresponding to the type of abnormality, such as surface unevenness or brightness reduction, may be included in the operating state data. In other words, the type of operating state data used as the basis for the determination and the parameters (first parameter group or second parameter group) required to address the surface unevenness or brightness reduction may be the same type of data or different types of data. In this way, the control unit 91 of the information processing device 9 identifies the parameter group to be output (first parameter group, second parameter group) depending on the type of abnormality, and outputs corresponding information regarding the identified parameter group, thereby providing the operator of the laser annealing device 1 with useful information for operating or driving the laser annealing device 1.

[0101] According to this embodiment, the types of surface unevenness of the substrate 8 include streak unevenness and flow unevenness, and may further include unevenness due to poor irradiation or film skipping. If the type of surface unevenness is streak unevenness, the control unit 91 of the information processing device 9 includes at least one of stage ripple, vibration, laser intensity fluctuation, and pulse waveform in the first parameter group. If the type of surface unevenness is flow unevenness, the control unit 91 of the information processing device 9 includes at least one of oxygen concentration, nitrogen concentration, exhaust volume, and floating amount of the substrate 8 in the first parameter group. As such, since the types of surface unevenness of the substrate 8 include streak unevenness and flow unevenness, corresponding information corresponding to the type of surface unevenness can be generated using the first parameter group including appropriate parameters corresponding to the type, and can be provided to the operator of the laser annealing apparatus 1, etc.

[0102] According to this embodiment, when the control unit 91 of the information processing device 9 determines that a decrease in brightness has occurred on the substrate 8, it includes at least one of the energy density, the amount of synchronization deviation, and the beam shape in the second parameter group. When a decrease in brightness has occurred in this way, by using the second parameter group including at least one of the energy density, the amount of synchronization deviation, and the beam shape, it is possible to generate response information including parameters useful for dealing with the decrease in brightness and provide it to the operator of the laser annealing apparatus 1, etc.

[0103] According to this embodiment, the operating state data used to determine whether an abnormality such as surface unevenness or reduced brightness has occurred is time-series data periodically measured by various sensors. When outputting corresponding information regarding parameter groups (first parameter group, second parameter group) corresponding to the type of abnormality (surface unevenness, reduced brightness), the control unit 91 of the information processing device 9 includes, in the corresponding information, time-series data for a predetermined period that served as the basis for determining that an abnormality has occurred. In this case, the control unit 91 of the information processing device 9 may generate screen data including the time-series data for the predetermined period that served as the basis for the determination and the corresponding information regarding the first parameter group or the second parameter group, and output the screen data to an information terminal T of an operator of the laser annealing apparatus 1, etc. The information terminal T, which has acquired the screen data output from the information processing device 9, displays a display screen corresponding to the acquired screen data on a display unit, such as a display. The first parameter group or the second parameter group indicates one or more parameters that require confirmation, i.e., that should be checked, depending on the type of abnormality that has occurred (surface unevenness, brightness reduction). By generating screen data using correspondence information including the first parameter group or the second parameter group (parameter group to be checked), appropriate advice can be provided to the operator of the laser annealing apparatus 1. Furthermore, the screen data (display screen) includes time-series data (operating status data) for a predetermined period that served as the basis for determining that an abnormality has occurred, thereby ensuring or improving the operator's satisfaction in taking measures or performing operations in accordance with the correspondence information. When an abnormality such as surface unevenness or brightness reduction has occurred or is predicted to occur, the control unit 91 of the information processing device 9 generates and outputs screen data including the time-series data for a predetermined period that served as the basis for determining the correspondence information related to the parameter group corresponding to the type of abnormality. Therefore, the screen data (display screen) is generated and output when it is determined that an abnormality has occurred, and the display screen corresponds to an abnormality notification screen that notifies the operator of the abnormality.The information terminal T, which has acquired screen data notifying the occurrence of an abnormality from the information processing device 9, may be configured to pop up (display in a pop-up window) an abnormality notification screen in response to the acquisition of the screen data. That is, in the information terminal T used by an operator of the laser annealing apparatus 1, the abnormality notification screen notifying the occurrence of an abnormality such as surface unevenness or a decrease in brightness may be displayed as a separate screen (separate window) that pops up from the display screen that constantly displays the operating status of the laser annealing apparatus 1. By displaying the abnormality notification screen as a pop-up in this manner, it is possible to efficiently call the attention of the operator of the laser annealing apparatus 1 when an abnormality such as surface unevenness or a decrease in brightness occurs.

[0104] According to this embodiment, the control unit 91 of the information processing device 9 inputs driving state data acquired from various sensors into the first learning model 901, and acquires from the first learning model 901 a determination result as to whether or not surface unevenness has occurred. The first learning model 901 is trained to output information regarding the occurrence of surface unevenness when driving state data is input, and functions as an unevenness prediction model. The driving state data includes values ​​of each parameter, i.e., each data type, included in the first parameter group and the second parameter group, and the values ​​of each parameter group are stored and managed as time-series data detected at a predetermined cycle. The control unit 91 of the information processing device 9 may input driving state data for a predetermined period before the occurrence of surface unevenness, from the driving state data acquired as time-series data at a predetermined cycle, into the first learning model 901 (unevenness prediction model). The predetermined period corresponds to a processing unit period when performing estimation using the first learning model 901, i.e., a period defining a unit of input data when input to the first learning model 901, and therefore may define a tensor (multidimensional array) that serves as input data to the first learning model 901. When the input data uses a first parameter group measured periodically at multiple time points, the input data may be, for example, data in a matrix format with the horizontal direction representing the type of first parameter and the vertical direction representing the measurement time points. In the matrix-format input data, the period from the first to the last of the multiple measurement time points indicated vertically corresponds to the processing unit period. The first learning model 901 is trained to output, when operating state data for a predetermined period before the occurrence of surface unevenness is input, information regarding the occurrence of future surface unevenness, i.e., information including a determination result as to whether surface unevenness will occur within a predetermined elapsed period based on the last time point (current time point) of the predetermined period.In this way, the first learning model 901 outputs information regarding whether or not surface unevenness will occur in the future (within a predetermined period of time from the present) based on operating status data packaged as time-series data up to the present time, thereby providing operators of the laser annealing apparatus 1 with useful information for operating or running the laser annealing apparatus 1, and contributing to improving yield.

[0105] According to this embodiment, the control unit 91 of the information processing device 9 inputs driving state data acquired from various sensors into the second learning model 902, and acquires from the second learning model 902 a determination result as to whether or not a luminance decrease has occurred. The second learning model 902 is trained to output information regarding the occurrence of a luminance decrease when driving state data is input, and functions as a luminance decrease prediction model. The control unit 91 of the information processing device 9 may input driving state data for a predetermined period before the occurrence of a luminance decrease, from driving state data acquired as time-series data at a predetermined period, into the second learning model 902 (luminance decrease prediction model). The predetermined period corresponds to a processing unit period when performing estimation using the second learning model 902, i.e., a period defining a unit of input data when inputting data to the second learning model 902. Therefore, the predetermined period may define a tensor (multidimensional array) that serves as input data to the second learning model 902. When the input data uses a group of second parameters measured periodically at multiple time points, the input data may be, for example, data in a matrix format with the horizontal direction representing the type of second parameter and the vertical direction representing the measurement time point. The second learning model 902 is trained to output, when operating state data for a predetermined period before the occurrence of luminance degradation is input, information regarding the occurrence of future luminance degradation, i.e., information including a determination result as to whether or not luminance degradation will occur within a predetermined elapsed period based on the last point in time (the current point in time) in the predetermined period. In this way, the second learning model 902 outputs information regarding whether or not luminance degradation will occur in the future (within a predetermined elapsed period from the current point in time) based on operating state data packaged as time-series data up to the current point in time, thereby providing useful information to the operator of the laser annealing apparatus 1 when operating or driving the laser annealing apparatus 1, and contributing to improving yield.

[0106] The embodiments disclosed herein are to be considered as illustrative in all respects and not restrictive. The scope of the present invention 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.

[0107] Multiple claims in the claims may be combined with each other regardless of the form of reference. Multiple dependent claims are defined in the claims that depend on multiple dependent claims. Multiple dependent claims that depend on multiple dependent claims may not be defined in the claims, but multiple dependent claims that depend on multiple dependent claims may be defined.

[0108] S Operation management system GN External network SS Model server T Information terminal 1 Laser annealing device (laser processing device) 11 Annealing optical system 2 Laser light source 3 Attenuator 4 Polarization ratio control unit 5 Beam shaping optical system 61 Epi-illumination mirror 62 Biplanar phototube 63 OED sensor 64 Line camera (unevenness monitor) 641 Line-type lighting 65 Projection lens 66 Profiler camera (line beam sensor) 7 Laser irradiation chamber 71 Stage 72 Base 8 Board 9 Information processing device (control device) 91 Control unit 911 Acquisition unit 912 Time-series data analysis unit 913 Parameter identification unit 914 Screen output unit 92 Memory unit M Recording medium P Program (program product) 93 Communication unit 94 Input / output I / F 941 Display device 942 Temperature sensor 943 Flow rate sensor 944 Vibration sensor 945 Pressure sensor 946 Gas sensor 901 First learning model (unevenness prediction model) 902 Second learning model (brightness decrease prediction model)

Claims

1. A program that causes a computer to execute the following process: acquire operating state data relating to the operating state of a laser annealing device that is irradiating a substrate with laser light; determine, based on the acquired operating state data, whether or not surface unevenness has occurred on the substrate irradiated with laser light from the laser annealing device or whether or not a decrease in brightness has occurred on the substrate; if it is determined that surface unevenness has occurred on the substrate, output corresponding information relating to a first group of parameters required to deal with the surface unevenness; and if it is determined that a decrease in brightness has occurred on the substrate, output corresponding information relating to a second group of parameters required to deal with the decrease in brightness.

2. The program according to claim 1, wherein the types of surface unevenness of the substrate include streak unevenness and flow unevenness.

3. The program according to claim 2, wherein, when the type of surface unevenness determined to have occurred on the substrate is streak unevenness, the first parameter group includes at least one of stage ripple, vibration, laser intensity fluctuation, and pulse waveform related to the laser annealing device.

4. The program according to claim 2, wherein, when the type of surface unevenness determined to have occurred on the substrate is flow unevenness, the first parameter group includes at least one of oxygen concentration, nitrogen concentration, exhaust volume, and floating height of the substrate related to the laser annealing apparatus.

5. The program according to claim 1, wherein, when it is determined that a decrease in brightness has occurred on the substrate, the second group of parameters includes at least one of an energy density, a synchronization deviation amount, and a beam shape related to the laser annealing device.

6. The program according to claim 1, wherein the operating state data is time-series data measured periodically, and the correspondence information regarding the first parameter group and the second parameter group includes the time-series data for a predetermined period that was used as the basis for determining that surface unevenness or a decrease in brightness has occurred.

7. The program according to claim 6, which generates screen data including the time-series data for a predetermined period that served as the basis for the judgment and corresponding information regarding the first parameter group or the second parameter group, and outputs the generated screen data, thereby popping up a display screen corresponding to the screen data on an information terminal that is the output destination.

8. The program according to claim 1, which acquires the operating state data for a predetermined period before the occurrence of surface unevenness on the substrate, and acquires information regarding the occurrence of surface unevenness by inputting the acquired operating state data for the predetermined period into a first learning model that is trained to output information regarding the occurrence of surface unevenness in the future when operating state data is input.

9. The program described in claim 1, which acquires the operating state data for a predetermined period before the occurrence of a decrease in brightness on the substrate, and acquires information regarding the occurrence of a decrease in brightness by inputting the acquired operating state data for the predetermined period into a second learning model that is trained to output information regarding the occurrence of a decrease in brightness in the future when operating state data is input.

10. An information processing method that causes a computer to execute the following process: acquire operating state data relating to the operating state of a laser annealing device that is irradiating a substrate with laser light; determine based on the acquired operating state data whether surface unevenness has occurred on the substrate irradiated with laser light from the laser annealing device or whether a decrease in brightness has occurred on the substrate; if it is determined that surface unevenness has occurred on the substrate, output corresponding information relating to a first group of parameters required to deal with the surface unevenness; and if it is determined that a decrease in brightness has occurred on the substrate, output corresponding information relating to a second group of parameters required to deal with the decrease in brightness.

11. The information processing method according to claim 10, wherein the types of surface unevenness of the substrate include streak unevenness and flow unevenness.

12. The information processing method according to claim 10, wherein, when it is determined that a decrease in brightness has occurred on the substrate, the second group of parameters includes at least one of energy density, synchronization deviation, and beam shape related to the laser annealing device.

13. The information processing method according to claim 10, wherein the operating condition data is time-series data measured periodically, and the corresponding information regarding the first parameter group and the second parameter group includes the time-series data for a predetermined period that was used as the basis for determining that surface unevenness or a decrease in brightness has occurred.

14. An information processing device having a control unit, wherein the control unit acquires operating state data relating to the operating state of a laser annealing device that is irradiating a substrate with laser light, determines based on the acquired operating state data whether surface unevenness has occurred on the substrate irradiated with laser light from the laser annealing device or whether a decrease in brightness has occurred on the substrate, and if it is determined that surface unevenness has occurred on the substrate, outputs corresponding information relating to a first group of parameters required to deal with the surface unevenness, and if it is determined that a decrease in brightness has occurred on the substrate, outputs corresponding information relating to a second group of parameters required to deal with the decrease in brightness.

15. The information processing device according to claim 14, wherein the types of surface unevenness on the substrate include streak unevenness and flow unevenness.

16. The information processing device according to claim 14, wherein, when it is determined that a decrease in brightness has occurred on the substrate, the second group of parameters includes at least one of an energy density, a synchronization deviation amount, and a beam shape related to the laser annealing device.

17. The information processing device according to claim 14, wherein the operating state data is time series data measured periodically, and the corresponding information regarding the first parameter group and the second parameter group includes the time series data for a predetermined period that was used as the basis for determining that surface unevenness or a decrease in brightness has occurred.

18. A laser processing device equipped with a laser light source that emits laser light, the laser processing device having the functions of: acquiring operating state data relating to the operating state when a substrate is irradiated with laser light from the laser light source; determining whether or not surface unevenness or a decrease in brightness has occurred on the substrate irradiated with laser light from the laser light source based on the acquired operating state data; outputting corresponding information relating to a first group of parameters required to deal with the surface unevenness when it is determined that surface unevenness has occurred on the substrate; and outputting corresponding information relating to a second group of parameters required to deal with the decrease in brightness when it is determined that a decrease in brightness has occurred on the substrate.

19. The laser processing apparatus according to claim 18, wherein the types of surface unevenness of the substrate include streak unevenness and flow unevenness.

20. The laser processing device according to claim 18, wherein, when it is determined that a decrease in brightness has occurred on the substrate, the second group of parameters includes at least one of an energy density, a synchronization deviation amount, and a beam shape related to the laser processing device.

Images