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

Abstract

This program causes a computer to execute processing for: acquiring device information related to laser annealing devices at a plurality of bases; deriving state information related to the state of the laser annealing devices by using the acquired device information; and outputting the derived state information to acquisition sources of the device information, which is the source data of the state information.

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, etc. that can output status information derived using device information obtained from multiple locations to the source of the device information, which is the original data of the status information.

[0005] The program according to this aspect causes a computer to acquire device information relating to each of the laser annealing devices at multiple locations, use the acquired device information to derive status information relating to the status of the laser annealing device, and output the derived status information to the source from which the device information, which is the original data for the status information, was acquired.

[0006] The information processing method of this aspect has a computer acquire device information regarding laser annealing devices at multiple locations, use the acquired device information to derive status information regarding the status of the laser annealing devices, and output the derived status information to the source of the device information, which is the original data for the status information.

[0007] The information processing device of this aspect is an information processing device that has a control unit, and the control unit acquires device information regarding each of the laser annealing devices at multiple locations, uses the acquired device information to derive status information regarding the status of the laser annealing device, and outputs the derived status information to the source from which the device information, which is the original data of the status information, was acquired.

[0008] The laser processing device of this embodiment is a laser processing device equipped with a laser light source that emits laser light, and acquires device information regarding each of the laser annealing devices at multiple locations, uses the acquired device information to derive status information regarding the status of the laser annealing device, and outputs the derived status information to the source from which the device information, which is the original data of the status information, was acquired.

[0009] According to the present disclosure, it is possible to provide a program or the like that outputs status information derived using device information acquired from multiple locations to the source of the device information that is the original data of the status information.

[0010] FIG. 1 is a diagram showing 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 showing an example of a configuration of a laser annealing device. FIG. 3 is a diagram showing an example of a configuration of an information processing device (cloud server) that aggregates device information from multiple bases. FIG. 4 is an explanatory diagram illustrating a base master table. FIG. 5 is an explanatory diagram illustrating an device master table. FIG. 6 is an explanatory diagram illustrating a device information table. FIG. 7 is an explanatory diagram related to the generation process of a learning model (anomaly detection model). FIG. 8 is a flowchart showing an example of a processing procedure of a control unit of an information processing device according to embodiment 2 (development of a learning model). FIG. 9 is a flowchart showing an example of a processing procedure of a control unit of an information processing device according to embodiment 3 (determination of a learning model to be used). FIG. 10 is a flowchart showing an example of a processing procedure of a control unit of an information processing device according to embodiment 4 (application of an update program).

[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 the manufacturing factory (base) is equipped with an on-site computer K (edge ​​computer) that is connected to the laser annealing apparatus 1 via an on-site network (LAN). The on-site computer K (edge ​​computer) 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 on-site computer K (edge ​​computer) is communicably connected to an information processing device 9 (cloud server) via an external network GN, such as the Internet, for example.

[0013] The information processing device 9 (cloud server) may function as a remote monitoring device that acquires device information including substrate images, operating parameters of the laser annealing device 1, and various sensors transmitted from the on-site computer K (edge ​​computer), and monitors the operating status of the laser annealing device 1 installed at each of the multiple sites based on the acquired various data. Furthermore, the information processing device 9 may function as a model server that generates or updates various learning models 90, such as an unevenness detection model 901, a brightness reduction detection model 902, and an abnormality detection model 903, using substrate images, etc. transmitted from the on-site computer K. In this way, an operation management system S is configured by the laser annealing devices 1 installed at each of the multiple sites, the on-site computers K (control devices) that control the operation of the laser annealing devices 1, and the information processing device 9 (model server).

[0014] 2 is a diagram showing an example of the configuration of the laser annealing apparatus 1. The laser annealing apparatus 1 irradiates a silicon film formed on a substrate 8 with laser light. 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 on-site computer K (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 201 is irradiated with laser light while the substrate 8 is transported in the +X direction by the stage 71. Furthermore, the apparatus is equipped with 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 the in-site computer K (control device). The attenuators 3 are provided midway along 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 equal to the energy density (E) of the laser light emitted from the laser light source 2 multiplied by the transmittance (T) of the attenuator 3 (E=E×T). The on-site computer K (control device) may identify (derive) and change the transmittance of the attenuator 3 so that the energy density emitted from the attenuator 3 becomes the 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. In other words, 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 the in-site computer K (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 on-site computer K (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 on-site computer K (control device) may refer to information stored in a storage unit of the on-site computer K in the form of a table (a polarization ratio table) and specify (derive) the polarization ratio according to the transmittance. The polarization ratio table defines the polarization ratios corresponding to the respective transmittances.

[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 adjacent to the beam shaping optical system 5 at the end of the annealing optical system 11, 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 on-site computer K (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 in-site computer K (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 of the substrate 8 irradiated with the laser light and outputs the captured image of the substrate 8 (substrate image) to the on-site computer K. The line camera 64 also uses light emitted from a line light 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 light 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 on-site computer K (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 on-site computer K is an edge computer such as a personal computer or server device that performs overall or integrated control or management of the laser annealing apparatus 1. Like the information processing device 9 (cloud server) described below, the on-site computer K includes a control unit, a memory unit, a communication unit, and an input / output I / F, and is communicatively connected to a control device (another control device) that controls the laser light source 2 or each optical system in the annealing optical system 11 via the communication unit or the input / output I / F. The on-site computer K may acquire substrate images or various detection values ​​from a detection unit such as a biplanar photoelectric tube 62, an OED sensor 63, a line camera 64 (unevenness monitor), or a profiler camera 66 via the input / output I / F. The on-site computer K is communicatively connected to various measurement devices, such as a pulse counter 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 measurement devices.

[0035] 3 is a diagram showing an example of the configuration of an information processing device 9 (cloud server) that aggregates device information from multiple locations. The information processing device 9 is, for example, a server device such as a cloud server, and includes a control unit 91, a storage unit 92, a communication unit 93, and an input / output I / F 94. The information processing device 9 is operated, for example, by a maintenance company of the laser annealing device 1.

[0036] The control unit 91 has an arithmetic processing device with a timing function, such as one or more central processing units (CPUs), micro-processing units (MPUs), graphics processing units (GPUs), etc., and performs various information processing by reading and executing a program P (program product) stored in the storage unit 92. Furthermore, the control unit 91 uses various learning models 90, such as an unevenness detection model 901, a brightness reduction detection model 902, or an abnormality detection model 903, stored in the storage unit 92, to perform a process of deriving unevenness information regarding surface unevenness in a board image, and a process of determining whether an abnormal event has occurred.

[0037] The unevenness detection model 901 is trained to output unevenness information regarding multiple types of surface unevenness on the substrate 8 when a substrate image included in the apparatus information is input. The unevenness information regarding multiple types of surface unevenness on the substrate 8 output by the unevenness detection model 901 may include, for example, the presence or absence of surface unevenness on the surface of the substrate 8, and, if surface unevenness is present, the area and type of the surface unevenness. In this case, if it is estimated that multiple types of surface unevenness have occurred on the surface of the substrate 8, the unevenness detection model 901 may output unevenness information that also includes the probability for each type of surface unevenness. The types of surface unevenness include, for example, streak unevenness, poor irradiation, film skipping, and flow unevenness.

[0038] The luminance reduction detection model 902 is trained to output information regarding the occurrence of luminance reduction when the operating state data (time-series data) included in the device information is input. The information regarding the occurrence of luminance reduction may include a determination result regarding the presence or absence of surface unevenness or luminance reduction at the present time and in the future.

[0039] The anomaly detection model 903 detects abnormal events other than surface unevenness and brightness reduction by inputting the device information. Alternatively, the anomaly detection model 903 may include the functions of the unevenness detection model 901 and the brightness reduction detection model 902 and detect all abnormal events including surface unevenness and brightness reduction. The control unit of the information processing device 9 is described as using the learning model 90 such as the anomaly detection model 903, but is not limited to this and may also detect abnormal events using rule-based calculation processing.

[0040] The various learning models 90, such as the unevenness detection model 901, the brightness reduction detection model 902, and the anomaly detection model 903, may be learning models 90 constructed using other machine learning algorithms, such as R-CNN (Region Convolutional Neural Network), DNN (Deep Neural Network), Transformer, BERT, GPT, RNN (Recurrent Neural Network), LSTM (Long-Short Term Model), SVM (Support Vector Machine), Bayesian network, linear regression, regression tree, multiple regression, random forest, and ensemble. Alternatively, the learning model 90 may be constructed using a pre-trained language model (LLM) that has already undergone pre-training, such as ChatGPT. In this case, the LLM may be fine-tuned to efficiently output information on various abnormal events. Alternatively, a question generated using an external database such as a WebDB may be input, along with device information, to a prompt, which is the input interface of ChatGPT.

[0041] 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 90. The actual files of the learning models 90 may be configured as modules included in the program P (program product). Furthermore, the memory unit 92 stores a base master table, an equipment master table, and an equipment information table (described below).

[0042] 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, an in-site computer K or an information terminal T connected to an external network GN via the communication unit 93.

[0043] The input / output I / F 94 is a communication interface that complies with communication standards such as RS232C or USB, etc. To the input / output I / F 94, an input device such as a keyboard or a display device 941 such as a liquid crystal display is connected.

[0044] 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 information processing device 9 may be communicably connected via an in-base network (LAN) and an external network GN (WAN) such as the Internet.

[0045] 4 is an explanatory diagram illustrating an example of a base master table. The base master table is pre-stored in the storage unit 92 of the information processing device 9. Types of management items in the base master table include, for example, a base ID, a base name, a computer name within the base, and a customer name.

[0046] The base ID management item stores an identifier (base ID) that uniquely identifies the base where the laser annealing apparatus 1 is installed. The base name management item stores the name of the base (base name) indicated by the base ID stored in the same record. The base name management item stores the host name or IP address of the in-base computer K installed at the base indicated by the base ID stored in the same record. The customer name management item stores the name of the customer that owns the base indicated by the base ID stored in the same record.

[0047] 5 is an explanatory diagram illustrating an example of the device master table. The device master table is stored in advance in the storage unit 92 of the information processing device 9. Types of management items in the device master table include, for example, a device ID, a base ID, and a model.

[0048] The management item of the device ID stores an identifier (device ID) that uniquely identifies the laser annealing device 1. The management item of the base ID stores an identifier (base ID) of the base where the laser annealing device 1 indicated by the device ID stored in the same record is installed. The base ID sets an association (relation) between the device master table and the base master table, and normalization is performed. The management item of the model stores the model or model name of the laser annealing device 1 indicated by the device ID stored in the same record.

[0049] 6 is an explanatory diagram illustrating an example of an apparatus information table. The apparatus information table is stored in advance in the storage unit 92 of the information processing device 9. Types of management items in the apparatus information table include, for example, an apparatus ID, a substrate image, the number of voltage applications, the number of oscillations, an unevenness score, an operating rate, laser pulse energy, a standard deviation, a synchronization deviation amount, an applied voltage, a surface unevenness, a decrease in brightness, an oxygen concentration abnormality, a tube, and a cryopump.

[0050] The management item of the device ID stores an identifier (device ID) that uniquely identifies the laser annealing device 1. The device ID sets the association (relation) between the device information table and the device master table, and normalization is performed.

[0051] The management item for substrate image stores a substrate image of a substrate 8 irradiated with laser light from the laser annealing apparatus 1 indicated by the apparatus ID stored in the same record. The management item for number of voltage applications stores the number of times (TC) that voltage has been applied to the tube electrode provided in the laser annealing apparatus 1 indicated by the apparatus ID stored in the same record. The management item for number of oscillations stores the number of times (UC) that the laser has oscillated in the laser light source 2 provided in the laser annealing apparatus 1 indicated by the apparatus ID stored in the same record. The management item for unevenness score stores an unevenness score (a calculated numerical value indicating surface unevenness) derived based on the substrate image in the laser annealing apparatus 1 indicated by the apparatus ID stored in the same record. The management item for availability stores the availability of the laser annealing apparatus 1 indicated by the apparatus ID stored in the same record.

[0052] The management item of laser pulse energy stores the value of laser pulse energy from the laser light source provided in the laser annealing apparatus 1 indicated by the apparatus ID stored in the same record. The management item of standard deviation stores the standard deviation derived based on the value of laser pulse energy in the laser annealing apparatus 1 indicated by the apparatus ID stored in the same record. The management item of synchronization deviation amount stores the amount of synchronization deviation between the two laser light sources 2 provided in the laser annealing apparatus 1 indicated by the apparatus ID stored in the same record. The management item of applied voltage stores the voltage value applied to the tube electrodes provided in the laser annealing apparatus 1 indicated by the apparatus ID stored in the same record.

[0053] The management items related to abnormal events include, for example, surface unevenness, brightness reduction, and oxygen concentration abnormality. The management item of surface unevenness stores information about surface unevenness derived based on a substrate image in the laser annealing apparatus 1 indicated by the apparatus ID stored in the same record. The management item of brightness reduction stores information about brightness reduction derived based on the brightness of reflected light from the substrate 8 in the laser annealing apparatus 1 indicated by the apparatus ID stored in the same record. The management item of oxygen concentration abnormality stores information about oxygen concentration abnormality derived based on the amount of gas components in the laser irradiation chamber 7 (processing chamber) of the laser annealing apparatus 1 indicated by the apparatus ID stored in the same record.

[0054] The remaining service life management item includes, for example, a tube and a cryopump. The tube management item stores the remaining service life of a tube electrode provided in the laser annealing apparatus 1 indicated by the apparatus ID stored in the same record. The cryopump management item stores the remaining service life of a cryopump provided in the laser annealing apparatus 1 indicated by the apparatus ID stored in the same record.

[0055] These management items are merely examples, and the apparatus information table may include items corresponding to all parameters, such as detection values, acquired by various sensors when the laser annealing apparatus 1 is operated, and may further include items corresponding to various setting values ​​when the laser annealing apparatus 1 is operated. The control unit 91 of the information processing device 9 may store and manage the periodically acquired apparatus information (operating status data, etc.) as time-series data by appending the apparatus information (operating status data, etc.) periodically acquired from each of the in-site computers K in the apparatus information table. That is, the apparatus information table stores or registers various measurement information output from various measuring devices provided in the laser annealing apparatus 1, setting information when operating the laser annealing apparatus 1, and operation history information when operating the laser annealing apparatus 1, in association with the apparatus ID of the target laser annealing apparatus 1. In this way, the information processing device 9 may store all of the apparatus information acquired from each site in the apparatus information table, and may use the apparatus information table to store and manage all data (big data) generated by the operation of the laser annealing apparatus 1.

[0056] 7 is an explanatory diagram regarding the generation process of the learning model 90 (anomaly detection model 903). The information processing device 9 functions as a model server that generates or updates the learning model 90. A control unit 91 of the information processing device 9 trains a neural network using training data, and when device information targeted at the laser annealing device 1 is input, generates the learning model 90 that outputs status information regarding the status of the laser annealing device 1. The learning model 90 includes, for example, an unevenness detection model 901, a brightness decrease detection model 902, or an anomaly detection model 903.

[0057] The unevenness detection model 901 is trained to output unevenness information (status information) related to multiple types of surface unevenness on the substrate 8 when a substrate image included in the equipment information is input. The brightness reduction detection model 902 is trained to output information (status information) related to the occurrence of brightness reduction when operating state data (time-series data) included in the equipment information is input. The abnormality detection model 903 is trained to output information (status information) related to abnormal events other than surface unevenness and brightness reduction when the equipment information is input. Alternatively, the abnormality detection model 903 may include the functions of the unevenness detection model 901 and the brightness reduction detection model 902 and be trained to output information (status information) related to all abnormal events including surface unevenness and brightness reduction.

[0058] In this way, the learning model 90 may include multiple types of learning models 90 corresponding to the types of input and output data. Alternatively, the learning model 90 may be configured by a learning model 90 that performs integrated estimation processing corresponding to all types of abnormal events (anomaly detection model 903 that detects all abnormal events). In this embodiment, the learning model 90 will be described as an example of such a learning model 90 that detects all abnormal events (anomaly detection model 903). Like the anomaly detection model 903, the unevenness detection model 901 and the brightness decrease detection model 902 are also generated by learning using training data corresponding to the types of input and output data.

[0059] The training data for generating the anomaly detection model 903 is composed of question data including operating state data for a predetermined period of time in the target laser annealing apparatus 1, and answer data including state information that is information related to the occurrence of an abnormal event, and is stored in the storage unit 92 of the information processing apparatus 9. The operating state data for a predetermined period of time in the target laser annealing apparatus 1 is operating state data (measurement information, setting information, operating history information, etc.) extracted according to the apparatus ID of the laser annealing apparatus 1 in apparatus information periodically transmitted from the base where the laser annealing apparatus 1 is installed.

[0060] The response data includes information (status information) regarding the occurrence of an abnormal event relative to the operating status data for a predetermined period. The information (status information) regarding the occurrence of an abnormal event includes, for example, the type of abnormal event, such as surface unevenness, brightness reduction, or oxygen concentration abnormality, and whether or not the abnormal event occurred. The abnormal event of surface unevenness may include information regarding more specific types of surface unevenness, such as streak unevenness, poor irradiation, film skipping, and flow unevenness. Brightness reduction indicates an abnormal event in which the brightness of the substrate 8 is reduced, and the brightness of the substrate 8 is detected by the OED sensor 63, which includes a photosensor (light detection mechanism) and a light source. In other words, the brightness of the substrate 8 indicates the brightness of the reflected light (reflected light reflected by the substrate 8) of light emitted from the light source (light source for the OED sensor) of the OED sensor 63. The original data for these training data can be generated, for example, by aggregating operating status data and data regarding the occurrence of abnormal events performed by multiple laser annealing apparatuses 1.

[0061] The abnormality detection model 903 is configured, for example, by a DNN (Deep Neural Network), and has an input layer that accepts input of operating state data for a predetermined period of time in the target laser annealing apparatus 1, an intermediate layer that extracts features of the operating state data, and an output layer that outputs information regarding the occurrence of various abnormal events.

[0062] The input layer has multiple neurons that receive driving state data (driving state data groups) from 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 various abnormal events based on the features output from the middle layer.

[0063] The dataset of question data and answer data included in the training data for learning the anomaly detection model 903 (learning model 90) is synonymous with the dataset of input data and output data when using the anomaly detection model 903 (learning model 90), and if it is defined in one dataset, it naturally applies to the other dataset as well.

[0064] 8 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 (cloud server) that acquires, aggregates, and stores device information from multiple bases and is operated and managed by, for example, a maintenance company of the laser annealing device 1, accepts an operation by an operator using, for example, a keyboard connected to an input / output, and performs the following processing based on the accepted operation.

[0065] The control unit 91 of the information processing device 9 acquires device information on the laser annealing devices 1 at the plurality of bases (S101). The control unit 91 of the information processing device 9 acquires device information on the laser annealing devices 1 installed at each of the plurality of bases from each of the in-base computers K (edge ​​computers) installed at each of the plurality of bases via an external network GN such as the Internet.

[0066] The on-site computer K installed at each site is communicatively connected to each of the multiple laser annealing apparatuses 1 installed at the same site, or to various sensors installed in the laser annealing apparatuses 1, and periodically acquires operating status data or operating parameters, including substrate images and various sensor detection values ​​(measurement information), from these laser annealing apparatuses 1, etc. The measurement information includes, for example, information on the substrate image, unevenness score, substrate brightness, or laser intensity. The operating parameters are various setting information when operating the laser annealing apparatus 1, and may include, for example, control parameters such as the transmittance of the attenuator 3 determined by performing processing condition setting processing when processing the substrate 8 (production process).

[0067] When the on-site computer K functions as a control device included in the laser annealing apparatus 1, the on-site computer K may also periodically acquire, in the operating status data, operating history information (operating log data) when controlling the operation of the laser annealing apparatus 1. The on-site computer K may periodically acquire operating status data, etc., regarding multiple laser annealing apparatuses 1 installed at the same site as itself, and store the data in the storage unit 92 of the on-site computer K by associating the device ID of the laser annealing apparatus 1 that is the subject of the operating status data, etc., with the time of acquisition.

[0068] The on-site computer K generates apparatus information by adding a site ID indicating its own site to the operating status data stored in this manner, and transmits the apparatus information to an information processing device 9 (cloud server) operated and managed by a maintenance company of the laser annealing apparatus 1. Therefore, the apparatus information transmitted from the on-site computer K installed at each site includes the site ID indicating the source site and operating status data associated with the device ID of each laser annealing apparatus 1 installed at the site.

[0069] The control unit 91 of the information processing device 9 periodically acquires the operating state data (measurement information, setting information, operating history information, etc.) of each laser annealing device 1 installed at each of the bases by acquiring each of the device information transmitted from each of the in-site computers K. The control unit 91 of the information processing device 9 uses the base ID and the device ID in the device information thus acquired from each of the in-site computers K to extract the operating state data of each laser annealing device 1 indicated by each device ID, expands it into each data item, and stores it in the corresponding management item of the device information table together with the acquisition time (timestamp) of the device information.

[0070] The control unit 91 of the information processing device 9 may store the device information (operating state data, etc.) periodically acquired from each of the in-site computers K in the device information table in an appended manner, thereby saving the device information as time-series data. In this way, the control unit 91 of the information processing device 9 stores the device information (operating state data, etc.) periodically acquired from each of the in-site computers K in the device information table, and thereby can perform various types of arithmetic processing such as various statistical analyses, time-series analyses, comparison operations, deviation operations, and variance operations using the multiple pieces of device information (device information groups) stored in chronological order in the device information table.

[0071] The control unit 91 of the information processing device 9 may use a BI (Business Intelligence) tool to perform such various analytical processes. Application software related to the BI tool is stored in the storage unit 92 of the information processing device 9, and the control unit 91 of the information processing device 9 can execute various aggregation processes such as drill-down, slicing, or dicing by executing the application software (BI tool).

[0072] The control unit 91 of the information processing device 9 inputs the acquired device information into the learning model 90 (S102). Based on each device ID included in the device information acquired from each of the in-site computers K at each of the multiple sites, the control unit 91 of the information processing device 9 extracts operating state data (measurement information, setting information, operating history information, etc.) of the laser annealing device 1 identified by the device ID. The control unit 91 of the information processing device 9 inputs the extracted operating state data of the laser annealing device 1 into the learning model 90.

[0073] The learning model 90 includes, for example, an unevenness detection model 901, a brightness decrease detection model 902, and an abnormality detection model 903. The control unit 91 of the information processing device 9 may input each piece of input data extracted from the operating state data to the unevenness detection model 901, the brightness decrease detection model 902, and the abnormality detection model 903, respectively, according to the input / output characteristics (input / output data specifications) of the learning model 90. In this case, the control unit 91 of the information processing device 9 may input the substrate image extracted from the operating state data to the unevenness detection model 901, input the time-series data extracted from the operating state data to the brightness decrease detection model 902, and further input all data included in the operating state data to the abnormality detection model 903.

[0074] The control unit 91 of the information processing device 9 acquires the status information output by the learning model 90 (S103). The control unit 91 of the information processing device 9 acquires the status information from each of the learning models 90, which include, for example, the unevenness detection model 901, the brightness decrease detection model 902, and the abnormality detection model 903, and stores the status information in the storage unit 92 by storing the status information in a device information table.

[0075] The control unit 91 of the information processing device 9 receives comment information corresponding to the status information (S104). The control unit 91 of the information processing device 9 uses the device information and the status information acquired from the learning model 90 to generate, for example, screen data (detailed screen data) constituting a detailed screen showing detailed information about the target laser annealing device 1. The detailed screen (detailed screen data) may include information about time-series data, a substrate image, and a determination result (status information) by the learning model 90 for the target laser annealing device 1.

[0076] The control unit 91 of the information processing device 9 outputs the generated detailed screen data to an information terminal T used by a maintenance person who uses the learning model 90, thereby displaying a detailed screen on the information terminal T. The maintenance person may be someone who operates the information processing device 9 (cloud server). On the detailed screen displayed on the information terminal T used by the maintenance person, comment information on the status information output by the learning model 90 is input by the maintenance person's operation. The comment information input by the maintenance person is transmitted from the information terminal T to the information processing device 9. The information processing device 9 accepts the comment information from the information terminal T by receiving it, and stores the accepted comment information in a memory unit 92 of the information processing device 9 in association with status information corresponding to the original data of the comment information.

[0077] The control unit 91 of the information processing device 9 outputs status information including the received comment information (S105). The control unit 91 of the information processing device 9 may include the comment information received from the information terminal T of the maintenance staff in the status information output by the learning model 90 or add it to the status information, and then update or regenerate the details screen (details screen data). In this way, the control unit 91 of the information processing device 9 transmits a details screen (details screen data) displaying status information (estimated results by the learning model 90) including the comment information received from the information terminal T of the maintenance staff to the in-site computer K of the site where the target laser annealing device 1 is installed. Alternatively, the control unit 91 of the information processing device 9 may transmit the details screen (details screen data) to the information terminal T used by the operator of the target laser annealing device 1 at the site where the target laser annealing device 1 is installed. In this embodiment, the control unit 91 of the information processing device 9 transmits status information including comment information to the in-site computer K at the site where the target laser annealing device 1 is installed or to the information terminal T used by the operator of the laser annealing device 1, but this is not limited to this, and the control unit 91 may also transmit status information without including comment information.

[0078] The control unit 91 of the information processing device 9 may perform the processes from S102 to S105 for all laser annealing devices 1 managed or registered in the device master table. That is, the control unit 91 of the information processing device 9 may perform loop processing of the processes from S102 to S105 so as to execute the processes from S102 to S105 for all laser annealing devices 1. Alternatively, the control unit 91 of the information processing device 9 may perform a series of processes from S102 to S105 in parallel or in parallel by generating sub-processes according to the number of all laser annealing devices 1 registered in the device master table.

[0079] According to this embodiment, an information processing device 9 configured as a cloud server or the like is communicatively connected to each of the laser annealing apparatuses 1 installed at each of a plurality of bases, or to an on-site computer K, such as an edge computer connected to the laser annealing apparatus 1 at the base, via an external network GN such as the Internet. In this case, the information processing device 9 configured as a cloud server or the like may be operated, for example, by the manufacturer or maintenance company of the laser annealing apparatus 1. The base where the laser annealing apparatus 1 is installed may be a factory of a user of the laser annealing apparatus 1, i.e., a customer of the manufacturer of the laser annealing apparatus 1. A control device included in the laser annealing apparatus 1 may function or operate as the on-site computer K (edge ​​computer). The on-site computer K may be communicatively connected to multiple laser annealing apparatuses 1 installed at the same base, for example, via an on-site network (LAN), and may acquire and aggregate device information of the laser annealing apparatus 1 from each of the laser annealing apparatuses 1 at the same base, and store the information in a memory unit 92 of the on-site computer K. The apparatus information includes, for example, operating status data of the laser annealing apparatus 1 that is the subject of the apparatus information, various setting values ​​(setting information) when operating the laser annealing apparatus 1, and operating history information when the laser annealing apparatus 1 is operated. In this case, the operating status data includes parameters such as a substrate image of the substrate 8 irradiated with laser light and detection values ​​(measurement information) by various sensors (measuring devices) provided in the laser annealing apparatus 1, and may be associated with time information (timestamp) such as the time when the substrate image was captured or the time when it was detected (measurement time). The measurement information may include at least one of information regarding the unevenness score, substrate brightness, and laser intensity. In this way, the operating status data may be periodically acquired time-series data consisting of a group of data at multiple acquisition times (detection times, etc.).

[0080] The operation history information when the laser annealing apparatus 1 is operated includes a history of operation details based on various operations performed by the operator of the laser annealing apparatus 1 at the base where the laser annealing apparatus 1 is installed, and may include the start and end times of each operation detail, including, for example, operations related to processing condition setting processing. The on-site computer K assigns an identifier such as an apparatus ID that uniquely identifies the laser annealing apparatus 1 that is the subject of the apparatus information to each of the aggregated apparatus information, and transmits each of the apparatus information with the identifier assigned to the information processing device 9. At this time, when transmitting the apparatus information to the information processing device 9, the on-site computer K may assign an identifier such as a base ID that uniquely identifies its own base to the apparatus information. The information processing device 9 acquires and aggregates each of the apparatus information transmitted from each on-site computer K (edge ​​computer) at each of the multiple bases, associates it with the time of acquisition, and stores it in the memory unit 92 of the information processing device 9. The information processing device 9 uses the identification information (site ID, device ID) associated with the device information aggregated from the multiple sites to derive status information regarding the status of each laser annealing device 1 installed at each site (customer). The status information regarding the status of the laser annealing device 1 includes, for example, the presence or absence of surface unevenness on the substrate 8, the presence or absence of brightness reduction on the substrate 8, or the presence or absence of oxygen concentration abnormalities, as well as the presence or absence of various abnormal events and the type of abnormal event that has occurred. The information processing device 9 outputs the derived status information to the source of the device information, which is the original data of the status information, i.e., the on-site computer K that output the device information. The on-site computer K is assumed to be installed at the same site as the laser annealing device 1 that is the subject of the status information derived and transmitted by the information processing device 9. Therefore, the operator of the laser annealing device 1 can access the on-site computer K and use the on-site computer K to refer to and check the status information from the information processing device 9.Alternatively, the information processing device 9 may acquire the device information, which is the original data of the status information, from an information terminal T used by the operator of the laser annealing device 1, which is the target of the device information, and transmit the derived status information to the information terminal T. In this way, by outputting the status information derived by the information processing device 9 operated by the manufacturer or maintenance company of the laser annealing device 1 to the source of the device information, which is the original data of the status information, it is possible to provide feedback on the device information from the laser annealing device 1 that the operator of the laser annealing device 1, which corresponds to the source of the status information, to the operator of the laser annealing device 1 that he or she is operating, and it is possible to efficiently support the operation of the laser annealing device 1 by the operator.

[0081] According to this embodiment, the information processing device 9 is equipped with a learning model 90 that has been trained to output status information when device information is input. Therefore, the information processing device 9 functions as a model server that derives status information using the learning model 90. The learning model 90 includes, for example, an unevenness detection model 901, a brightness reduction detection model 902, or an abnormality detection model 903. The unevenness detection model 901 is trained to output unevenness information regarding multiple types of surface unevenness on the substrate 8 when a substrate image included in the device information is input. The brightness reduction detection model 902 is trained to output information regarding the occurrence of brightness reduction when operating status data (time-series data) included in the device information is input. The abnormality detection model 903 detects abnormal events other than surface unevenness and brightness reduction when device information is input. Alternatively, the abnormality detection model 903 may include the functions of the unevenness detection model 901 and the brightness reduction detection model 902 and detect all abnormal events, including surface unevenness and brightness reduction. In this way, by using various learning models 90 according to the type of abnormal event, or a learning model 90 that performs integrated estimation processing corresponding to all types of abnormal events (anomaly detection model 903 that detects all abnormal events), it is possible to efficiently derive anomaly detection monitoring results including whether or not an abnormal event has occurred and the type of abnormal event.

[0082] According to this embodiment, when the information processing device 9 derives status information based on device information using the learning model 90, it acquires comment information for the derived status information. The comment information may be input by a maintenance personnel to the learning model 90 or an information terminal T used by the maintenance personnel of the information processing device 9. That is, the status information derived by the learning model 90 is transmitted from the information processing device 9 to the information terminal T used by the maintenance personnel and referred to by the maintenance personnel. The comment information input by the maintenance personnel in accordance with the status information in the information terminal T used by the maintenance personnel is transmitted from the information terminal T to the information processing device 9. The information processing device 9 accepts the comment information by receiving it from the information terminal T, and stores the accepted comment information in a storage unit 92 of the information processing device 9 in association with status information corresponding to the original data of the comment information. The information processing device 9 includes the received comment information in the status information or assigns it to the status information, and then transmits the status information derived by the learning model 90 and the comment information accompanying the status information to the on-site computer K, which corresponds to the source of the device information that is the original data of the status information, or to the information terminal T used by the operator of the laser annealing device 1. In this way, by transmitting comment information from the manufacturer or maintenance company of the laser annealing device 1 in addition to the status information derived by the learning model 90 to the source of the device information that is the original data of the status information, it is possible to efficiently support the operation of the laser annealing device 1 by the operator.

[0083] According to this embodiment, the information processing device 9 generates training data based on device information acquired from each of a plurality of locations, and uses the generated training data to train the learning model 90. The learning model 90 may include, for example, an unevenness detection model 901, a brightness reduction detection model 902, or an anomaly detection model 903. The information processing device 9 may extract data corresponding to the type of each learning model 90 from the device information, and use the extracted data to generate training data suitable for each learning model 90. In this way, by using device information (big data) aggregated from a plurality of locations, the information processing device 9 can increase the number of cases consisting of question data and answer data, and efficiently generate a learning model 90 with relatively high estimation accuracy.

[0084] 9 is a flowchart showing an example of a processing procedure of a control unit 91 of an information processing device 9 according to embodiment 2 (development of a learning model 90). The control unit 91 of the information processing device 9 (cloud server) acquires, aggregates, and stores device information from multiple locations and is operated and managed by, for example, a maintenance company of the laser annealing device 1, accepts an operation by an operator using, for example, a keyboard connected to an input / output, and performs the following processing based on the accepted operation.

[0085] The control unit 91 of the information processing device 9 acquires the generated or updated learning model 90 (S201). The information processing device 9 functions as a model server that generates a learning model 90, such as an unevenness detection model 901, a brightness drop detection model 902, or an anomaly detection model 903, using device information acquired from each location, or that updates the generated learning model 90 by re-learning the learning model 90. The control unit 91 of the information processing device 9 stores an entity file of the generated or updated learning model 90 in the storage unit 92. Alternatively, the model server that generates or updates the learning model 90 may be configured as a device separate from the information processing device 9, and the information processing device 9 may transmit the device information acquired from each location to the model server and acquire the generated or updated learning model 90. In this way, the control unit 91 of the information processing device 9 acquires the generated or updated learning model 90.

[0086] The control unit 91 of the information processing device 9 outputs the acquired learning model 90 to the in-site computer K (S202). The control unit 91 of the information processing device 9 recognizes each in-site computer K installed at each site, for example, by referring to the site master table, and outputs the acquired learning model 90 (the entity file of the learning model 90) to each in-site computer K.

[0087] The control unit 91 of the information processing device 9 executes a process for applying the learning model 90 to the on-site computer K, which is the output destination of the learning model 90 (S203). After the output (transmission) of the learning model 90 to the on-site computer K is successfully completed, the control unit 91 of the information processing device 9 executes a process for applying the learning model 90 to the on-site computer K (the on-site computer K, which is the output destination of the learning model 90). The control unit 91 of the information processing device 9 may execute a process for applying the learning model 90, for example, by sending a signal (model application signal) or an RPC (Remote Procedure Call) to the on-site computer K instructing the application of the transmitted learning model 90. In this way, the generation or update of the learning model 90 is performed by the information processing device 9 (cloud server) that aggregates device information from each site, thereby enabling the learning model 90 to be efficiently generated or updated using training data including a large number of cases using so-called big data. Then, by sending and applying (deploying) the generated learning model 90 to the computer K at each base station, the estimation process using the learning model 90 can be decentralized and the processing response can be improved.

[0088] According to this embodiment, a base station where the laser annealing apparatus 1 is installed includes an on-site computer K connected to the laser annealing apparatus 1 via an on-site network (LAN). The on-site computer K functions, for example, as an edge computer at the base station where the laser annealing apparatus 1 is installed, and is communicatively connected to an information processing device 9 (e.g., a cloud server) that performs processing related to the generation or update of the learning model 90 via an external network GN (WAN) such as the Internet. The information processing device 9 (cloud server) functions as a model server that generates or updates the learning model 90 and outputs the generated learning model 90 to each on-site computer K (edge ​​computer) at each base station. The information processing device 9 then performs processing to apply or deploy the output learning model 90 to the on-site computer K. The information processing device 9 may transmit a signal instructing the on-site computer K to apply the learning model 90 when applying the learning model 90 to the on-site computer K. In this way, the information processing device 9 outputs and applies the learning model 90, which has been trained using device information aggregated from multiple locations where the laser annealing devices 1 are installed, to each of the on-site computers K at each location, thereby improving the usage environment for the learning model 90 at the on-site computers K. Furthermore, when the information processing device 9 updates the existing learning model 90 using the latest device information, that is, when the information processing device 9 also outputs and deploys the updated learning model 90 (updated learning model 90) to the on-site computers K, the learning model 90 of the on-site computers K can be updated efficiently.

[0089] 10 is a flowchart showing an example of a processing procedure of a control unit 91 of an information processing device 9 according to embodiment 3 (determining a learning model 90 to be used). The control unit 91 of the information processing device 9 (cloud server) acquires, aggregates, and stores device information from multiple locations and is operated and managed by, for example, a maintenance company for the laser annealing device 1, accepts an operation by an operator using, for example, a keyboard connected to an input / output, and performs the following processing based on the accepted operation.

[0090] The control unit 91 of the information processing device 9 acquires device information on the laser annealing devices 1 at multiple locations (S301). Similar to S101 of the first embodiment, the control unit 91 of the information processing device 9 periodically acquires device information on the laser annealing devices 1 from each location.

[0091] The control unit 91 of the information processing device 9 acquires information regarding the usage contract with the customer having the base that is the source of the device information (S302). The control unit 91 of the information processing device 9 acquires information regarding the usage contract with the customer having the base that is the source of the device information, i.e., the customer who is the user of the target laser annealing device 1. A usage contract for the use of an operation management system S that performs remote monitoring using the information processing device 9 is concluded between the customer (the user of the laser annealing device 1) and a maintenance management company (such as the manufacturer of the laser annealing device 1) that operates the information processing device 9 in which the learning model 90 is implemented. The content of the usage contract for each customer may be registered or stored, for example, in association with the management item for the customer name included in the base master table. The control unit 91 of the information processing device 9 acquires the content of the usage contract for the customer of the target laser annealing device 1 by referring to the base master table and the device master table.

[0092] The control unit 91 of the information processing device 9 determines the learning model 90 that the customer can use based on the acquired information about the usage contract (S303). For example, the usage contract for each customer managed in the base master table includes information about which learning model 90 each individual customer can use. The learning model 90 may include, for example, a shared model that is shared among multiple customers and a non-shared model that differs depending on the customer, i.e., a customer-specific model.

[0093] The shared model is a learning model 90 trained by training data generated using apparatus information on the laser annealing apparatuses 1 at multiple locations, without considering the identity of the customer or location. Because the shared model is trained by training data generated using apparatus information on the laser annealing apparatuses 1 at each of the locations owned by multiple customers, it is trained by training data based on a relatively large number of cases, and it is expected that highly versatile estimations or judgments will be made.

[0094] In contrast, the non-shared model takes into consideration the identity of the customer, i.e., it is a learning model 90 (customer-specific model) trained using training data generated using equipment information related to the laser annealing apparatuses 1 installed at one or more locations owned by the same customer. Therefore, the non-shared model is a learning model 90 trained using training data that differs depending on the customer, in other words, training data for each customer (each location owned by the customer), and an individual non-shared model may be generated for each customer. That is, the non-shared model for location A owned by customer A is trained using training data generated using equipment information from each laser annealing apparatus 1 installed at location A, and the trained non-shared model for location A is input with equipment information from each laser annealing apparatus 1 installed at location A. Since the non-shared model for each customer is trained using training data generated using equipment information related to the laser annealing apparatuses 1 at the customer's location, it is expected that estimation or judgment will be performed in accordance with the operating mode of the laser annealing apparatus 1 of the customer (customer's location).

[0095] The usage contract includes whether the learning model 90 will be used, a shared model or a non-shared model. The usage contract may include, for example, contract content such as use of only the shared model, use of only the non-shared model, or use of both the shared model and the non-shared model. Alternatively, if the learning model 90 includes multiple types of learning models 90 with different input and output data, such as an unevenness detection model 901, a brightness drop detection model 902, or an anomaly detection model 903, the usage contract may define which types of learning models 90 can be used. The control unit 91 of the information processing device 9 determines the learning model 90 that the customer, who is a user of the target laser annealing apparatus 1, can use, based on the content of the usage contract for the customer.

[0096] The control unit 91 of the information processing device 9 inputs the acquired device information into the determined learning model 90 (S304). The control unit 91 of the information processing device 9 inputs the device information of the laser annealing device 1 into one of the determined learning models 90 based on the content of the usage contract with the customer who is the user of the target laser annealing device 1, in the same way as S102 of the first embodiment.

[0097] The control unit 91 of the information processing device 9 acquires the state information output by the learning model 90 (S305). The control unit 91 of the information processing device 9 outputs the state information acquired from the learning model 90 (S306). The control unit 91 of the information processing device 9 executes the processes of S305 and S306 similarly to S103 and S105 of the first embodiment. At that time, the control unit 91 of the information processing device 9 may accept comment information corresponding to the state information and add the comment information to the state information similarly to S104 of the first embodiment.

[0098] According to this embodiment, the information processing device 9 is equipped with multiple learning models 90, and the multiple learning models 90 include a shared model shared among multiple customers and a non-shared model that differs depending on the customer. The customers have one or more bases and are users who use laser annealing apparatuses 1 installed at the customer's bases. The shared model is a learning model 90 trained using training data generated using apparatus information on laser annealing apparatuses 1 at multiple bases, without considering the identity of the customer or the base. In contrast, the non-shared model is a learning model 90 trained using training data generated using apparatus information on laser annealing apparatuses 1 installed at one or more bases owned by the same customer, taking into consideration the identity of the customer. A usage contract for the use of the learning model 90 is concluded between the customer, who is the user of the laser annealing apparatus 1, and the manufacturer or maintenance company of the laser annealing apparatus 1 that operates the information processing device 9 on which the learning model 90 is implemented, and the usage contract concluded with each customer is stored in the memory unit 92 of the information processing device 9. The usage contract includes, for example, whether to use a shared or non-shared learning model 90. By using different training data for learning models 90 with the same types of input data (device information) and output data (status information), it is possible to generate a non-shared model specialized for the operating mode of a customer (a base owned by the customer) and a shared model that reflects the operating modes of all customers (bases owned by the customer). Then, by determining whether to use the learning model 90, a shared or non-shared model, depending on the content of the usage contract with the customer, it is possible to provide the operator of the laser annealing apparatus 1 with status information from multiple perspectives (the judgment results of the learning model 90).

[0099] 11 is a flowchart showing an example of a processing procedure of a control unit 91 of an information processing device 9 according to a fourth embodiment (application of an update program). The control unit 91 of the information processing device 9 (cloud server) acquires, aggregates, and stores device information from a plurality of bases and is operated and managed by, for example, a maintenance company of the laser annealing device 1, accepts an operation by an operator using, for example, a keyboard connected to an input / output, and performs the following processing based on the accepted operation.

[0100] The control unit 91 of the information processing device 9 acquires an update program (S401). The update program is created, for example, by the manufacturer of the laser annealing device 1 that operates the information processing device 9, and is stored in the storage unit 92 of the information processing device 9. The control unit 91 of the information processing device 9 refers to the storage unit 92 to acquire an update program to be distributed to the laser annealing device 1 installed at each base.

[0101] The control unit 91 of the information processing device 9 acquires information about the control program currently applied to the laser annealing device 1 (S402). The device master table may include, in addition to management items such as the device ID, a management item (version number) that stores the version of the control program currently applied. The control unit 91 of the information processing device 9 acquires information about the control program currently applied to the target laser annealing device 1 by referring to the value (control program version) stored in the management item of the version number in the device master table.

[0102] The control unit 91 of the information processing device 9 determines whether or not application of an update program is necessary based on the acquired information about the control program (S403). Based on the acquired information about the control program, the control unit 91 of the information processing device 9 determines whether or not the version of the control program currently applied to the laser annealing device 1 is the latest version, or whether it is an older version than the update program (latest version of the control program) to be distributed. If the version of the control program currently applied to the laser annealing device 1 is not the latest version (it is an older version), the control unit 91 of the information processing device 9 determines that application of an update program is necessary.

[0103] If application of the update program is necessary (403: YES), the control unit 91 of the information processing device 9 outputs the update program to the laser annealing device 1 (S404). If the control unit 91 of the information processing device 9 determines that application of the update program is necessary, it outputs the update program to the laser annealing device 1. If each of the individual laser annealing devices 1 has a built-in control device, the control unit 91 of the information processing device 9 may output the update program to each of the control devices of the laser annealing device 1. Alternatively, when outputting the update program to the laser annealing device 1 installed at a base, the control unit 91 of the information processing device 9 may output the update program via the in-site computer K of the base. In other words, when outputting the update program to the laser annealing device 1, the control unit 91 of the information processing device 9 is not limited to directly communicating with the laser annealing device 1, but may also indirectly communicate with the laser annealing device 1 via, for example, a relay device or relay server such as the in-site computer K.

[0104] The control unit 91 of the information processing device 9 executes processing for applying the output update program to the laser annealing apparatus 1 (S405). After the output (transmission) of the update program to the on-site computer K or the like has been successfully completed, the control unit 91 of the information processing device 9 executes processing for applying the update program to the on-site computer K or the like (the on-site computer K or the like to which the update program has been output). The control unit 91 of the information processing device 9 may execute processing for applying the update program by, for example, transmitting a signal (program application signal) or an RPC (Remote Procedure Call) instructing the on-site computer K or a control device included in the laser annealing apparatus 1 to apply the output (transmitted) update program.

[0105] If application of the update program is not required (403: NO), or after executing the process of 405, the control unit 91 of the information processing device 9 ends the series of processes according to this flowchart. The control unit 91 of the information processing device 9 executes the series of processes according to this flowchart for each laser annealing device 1 installed at each individual base by, for example, referring to the base master table and the device master table. Alternatively, the control unit 91 of the information processing device 9 may execute the series of processes according to this flowchart simultaneously for all laser annealing devices 1 installed at all bases.

[0106] According to this embodiment, the laser annealing apparatus 1 installed at each of the multiple bases is equipped with a control program for controlling the laser annealing apparatus 1. The control program may be implemented in a control device that controls the operation of the laser annealing apparatus 1. If an on-site computer K functions as a control device included in the laser annealing apparatus 1, the control program may be implemented in the on-site computer K. The control program installed in the laser annealing apparatus 1 is manufactured by the manufacturer or maintenance company of the laser annealing apparatus 1, and an update (version upgrade), i.e., an update program (updated control program), is generated to add or improve functions to the laser annealing apparatus 1. The generated update program is stored in the storage unit 92 of the information processing device 9. The information processing device 9 acquires the update program by referring to the storage unit 92 and outputs the update program to each of the laser annealing apparatuses 1 installed at the multiple bases. If each laser annealing apparatus 1 has its own control device, the information processing device 9 may transmit the update program to each of the control devices. Alternatively, the information processing device 9 may transmit the update program to the on-site computer K, and the on-site computer K may transfer the update program to each of the laser annealing apparatuses 1. After transmitting the update program to the laser annealing apparatus 1, the information processing device 9 may perform processing on the laser annealing apparatus 1 to apply the update program. The information processing device 9 may cause the laser annealing apparatus 1 to apply the update program by transmitting a signal instructing the application of the update program to the control device of the laser annealing apparatus 1 or the on-site computer K. Alternatively, the information processing device 9 may transmit the update program to the laser annealing apparatus 1 as processing to apply the update program to the laser annealing apparatus 1, and then perform processing to display an operation screen for applying the update program on the control device of the laser annealing apparatus 1 or the on-site computer K.In this case, application of the update program in the laser annealing apparatus 1 may be started when an operation to start application of the update program is performed by an operator on an operation screen displayed on a control device of the laser annealing apparatus 1, a display device 941 such as a display connected to the in-site computer K, or an information terminal T used by the operator of the laser annealing apparatus 1. In this way, the information processing apparatus 9 can efficiently ensure that the control program used in the laser annealing apparatus 1 is kept up to date (the latest version) by transmitting and applying the update program to the laser annealing apparatus 1 installed at each of the multiple sites.

[0107] 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.

[0108] 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.

[0109] S Operation management system GN External network K In-site computer (edge ​​computer, control device) 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 (cloud server, model server) 91 Control unit 92 Storage unit M Recording medium P Program (program product) 93 Communication unit 94 Input / output I / F 941 Display device 90 Learning model 901 Unevenness detection model 902 Brightness decrease detection model 903 Abnormality detection model

Claims

1. A program that causes a computer to execute the following process: acquire equipment information on laser annealing equipment at multiple locations; use the acquired equipment information to derive status information on the status of the laser annealing equipment; and output the derived status information to the source of the equipment information, which is the original data of the status information.

2. The program according to claim 1, wherein the device information includes measurement information output from a measurement device installed in the laser annealing device, and the measurement information includes at least one of information regarding a substrate image, an unevenness score, substrate brightness, and laser intensity.

3. The program according to claim 1, wherein the device information includes setting information for operating the laser annealing device.

4. The program according to claim 1, wherein the device information includes operating history information when the laser annealing device is operated.

5. The program according to claim 1, wherein the status information includes information regarding the occurrence of an abnormal event in the laser annealing device.

6. The program according to claim 1, wherein the state information is derived by inputting the acquired device information into a learning model that has been trained to output the state information when device information is input.

7. The program according to claim 6, which receives comment information corresponding to the status information derived by the learning model from an information terminal of a maintenance staff member who uses the learning model, and outputs the status information including or adding the received comment information.

8. The program according to claim 6, further comprising: generating training data based on the acquired device information and the derived state information; and training the learning model using the generated training data.

9. The program according to claim 8, which outputs the learning model trained using the training data to a computer at the site where the laser annealing device is installed, and performs processing to apply the output learning model to the computer at the site to which it is output.

10. The program described in claim 6, wherein the learning model includes a shared model shared among multiple customers corresponding to each of the locations and a non-shared model that differs depending on the customer, and the program acquires a usage agreement with the customer regarding the use of the learning model, and determines whether the learning model to be used for the customer is the shared model or the non-shared model based on the acquired usage agreement.

11. The program according to claim 1, which acquires an update program to be applied to the laser annealing device, outputs the acquired update program to the laser annealing devices installed at multiple locations, and performs processing to apply the output update program to the laser annealing device to which it is output.

12. An information processing method that causes a computer to execute the following process: acquire equipment information related to laser annealing equipment at multiple locations; use the acquired equipment information to derive status information related to the status of the laser annealing equipment; and output the derived status information to the source of the equipment information, which is the original data of the status information.

13. The information processing method according to claim 12, wherein the apparatus information includes measurement information output from a measurement device provided in the laser annealing apparatus, and the measurement information includes at least one of information regarding a substrate image, an unevenness score, substrate brightness, and laser intensity.

14. The information processing method according to claim 12, wherein the device information includes setting information for operating the laser annealing device.

15. An information processing device having a control unit, wherein the control unit acquires device information relating to laser annealing devices at multiple locations, uses the acquired device information to derive status information relating to the status of the laser annealing devices, and outputs the derived status information to a source from which the device information, which is the original data of the status information, was acquired.

16. The information processing device according to claim 15, wherein the device information includes measurement information output from a measurement device provided in the laser annealing device, and the measurement information includes at least one of information regarding a substrate image, an unevenness score, a substrate brightness, and a laser intensity.

17. The information processing device according to claim 15, wherein the device information includes setting information for operating the laser annealing device.

18. A laser processing device equipped with a laser light source that emits laser light, which acquires device information on laser annealing devices at multiple locations, derives status information on the status of the laser annealing devices using the acquired device information, and outputs the derived status information to the source of the device information, which is the original data of the status information.

19. The laser processing apparatus according to claim 18, wherein the apparatus information includes measurement information output from a measurement device provided in the laser annealing apparatus, and the measurement information includes at least one of information regarding a substrate image, an unevenness score, a substrate brightness, and a laser intensity.

20. The laser processing apparatus according to claim 18, wherein the apparatus information includes setting information for operating the laser annealing apparatus.

Images