Laser processing apparatus and method

Abstract

A laser processing apparatus and method are disclosed. The laser processing method is a laser processing method performed by a processor of a laser processing apparatus, and may include the steps of acquiring a processing pattern image, generating processing command data using an artificial intelligence-based processing command generation model from the processing pattern image, and processing a target object by irradiating a laser based on the processing command data.

Description

Technology Field

[0001] The present invention relates to a laser processing apparatus and method that automatically generates processing command data using an artificial intelligence-based processing command generation model from a processing pattern image. Background Technology

[0002] Various methods for processing various patterns on an object using a laser have been disclosed in the past. For example, a method of processing a pattern by moving the laser irradiation unit along the XY axis using a CNC (Computer Numerical Control) machine can be used.

[0003] At this time, in order to process patterns using a CNC machine, processing command data (e.g., processing coding data) to control the laser irradiation unit must be generated individually for each pattern, which is cumbersome and time-consuming, resulting in reduced efficiency.

[0004] Therefore, there is a need for technology that can automatically generate processing command data according to a pattern and effectively process the pattern on an object based on the processing command data. The problem to be solved

[0005] The embodiment of the present invention aims to provide a laser processing apparatus and method capable of generating processing command data using an artificial intelligence-based processing command generation model from a processing pattern image, and irradiating a target object with a laser based on the processing command data, thereby easily acquiring processing command data and effectively processing a target object according to the processing pattern of the processing pattern image.

[0007] The problems that the present invention aims to solve are not limited to those mentioned above, and other problems and advantages of the present invention not mentioned can be understood from the following description and will be more clearly understood by the embodiments of the present invention. Furthermore, it will be understood that the problems and advantages that the present invention aims to solve can be realized by the means and combinations thereof set forth in the claims. means of solving the problem

[0008] A laser processing device according to an embodiment of the present invention is a processing device using a laser, comprising a processor and a memory that is operably connected to the processor and stores at least one code executed by the processor. When the memory is executed through the processor, the processor acquires a processing pattern image, generates processing command data using an artificial intelligence-based processing command generation model from the processing pattern image, and stores a code that causes a laser to be irradiated onto an object based on the processing command data to process the object.

[0009] A laser processing method according to an embodiment of the present invention is a laser processing method performed by a processor of a laser processing device, and may include the steps of acquiring a processing pattern image, generating processing command data using an artificial intelligence-based processing command generation model from the processing pattern image, and irradiating a laser onto an object based on the processing command data to process the object.

[0011] In addition to this, other methods for implementing the present invention, other systems, and computer-readable recording media storing a computer program for executing said methods may be further provided.

[0012] Other aspects, features, and advantages other than those described above will become clear from the following drawings, claims, and detailed description of the invention. Effects of the invention

[0013] According to the present invention, a laser processing apparatus and method can be provided that generate processing command data using an artificial intelligence-based processing command generation model from a processing pattern image, and irradiate a target object with a laser based on the processing command data, thereby easily acquiring processing command data and effectively processing the target object according to the processing pattern of the processing pattern image. Accordingly, the inconvenience of having to individually generate processing command data for each processing pattern, even when the processing patterns differ, can be eliminated, and the target object can be processed in real time based on the processing pattern.

[0015] The effects of the present invention are not limited to those mentioned above, and other unmentioned effects will be clearly understood by those skilled in the art from the description below. Brief explanation of the drawing

[0016] FIG. 1 is a drawing illustrating an example of the configuration of a laser processing device according to an embodiment of the present invention. FIG. 2 is a drawing for explaining an example of generating processing command data in a laser processing device according to an embodiment of the present invention. FIG. 3 is a drawing for explaining an example of processing in a laser processing device according to an embodiment of the present invention. FIG. 4 is a drawing for explaining another example of processing in a laser processing device according to an embodiment of the present invention. FIG. 5 is a flowchart illustrating a laser processing method according to an embodiment of the present invention. Specific details for implementing the invention

[0017] The advantages and features of the present invention, and the methods for achieving them, will become clear by referring to the embodiments described in detail together with the accompanying drawings. However, the present invention is not limited to the embodiments presented below, but can be implemented in various different forms and should be understood to include all modifications, equivalents, and substitutions that fall within the spirit and scope of the present invention. The embodiments presented below are provided to ensure that the disclosure of the present invention is complete and to fully inform those skilled in the art of the scope of the invention. In describing the present invention, detailed descriptions of related known technologies are omitted if it is determined that such detailed descriptions may obscure the essence of the present invention.

[0018] The terms used in this application are used merely to describe specific embodiments and are not intended to limit the invention. Singular expressions include plural expressions unless the context clearly indicates otherwise. In this application, terms such as “comprising” or “having” are intended to indicate the presence of the features, numbers, steps, actions, components, parts, or combinations thereof described in the specification, and should be understood as not precluding the existence or addition of one or more other features, numbers, steps, actions, components, parts, or combinations thereof. Terms such as “first,” “second,” etc., may be used to describe various components, but the components should not be limited by these terms. These terms are used solely for the purpose of distinguishing one component from another.

[0019] Additionally, in this application, "part" may be a hardware component, such as a processor or circuit, and / or a software component executed by a hardware component, such as a processor.

[0020] Hereinafter, embodiments according to the present invention will be described in detail with reference to the attached drawings. In describing with reference to the attached drawings, identical or corresponding components are given the same reference numerals, and redundant descriptions thereof will be omitted.

[0022] FIG. 1 is a drawing illustrating an example of the configuration of a laser processing device according to an embodiment of the present invention, and FIG. 2 is a drawing for explaining an example of generating processing command data in a laser processing device according to an embodiment of the present invention. In addition, FIG. 3 is a drawing for explaining an example of processing in a laser processing device according to an embodiment of the present invention.

[0023] Referring to FIG. 1, a laser processing device (100) according to an embodiment of the present invention is for vision-based autonomous laser processing and may include an interface (110), a camera module (120), a laser module (130), a processor (140), and a memory (150).

[0024] The interface (110) can receive a processed pattern image and provide it to the processor (140). In an embodiment, the interface (110) may receive a processed pattern image from an external device (e.g., an image processing device, a memory) or receive a processed pattern image from a user by linking with a network (not shown). The network may include wired networks such as LANs (local area networks), WANs (wide area networks), MANs (metropolitan area networks), and ISDNs (integrated service digital networks), or wireless networks such as wireless LANs, CDMA, Bluetooth, and satellite communication, but the scope of the present invention is not limited thereto. Additionally, the network may transmit and receive information using short-range communication and / or long-range communication. Here, short-range communication may include Bluetooth, RFID (radio frequency identification), infrared communication (IrDA, infrared data association), UWB (ultra-wideband), ZigBee, and Wi-Fi (Wireless fidelity) technologies, and long-range communication may include CDMA (code division multiple access), FDMA (frequency division multiple access), TDMA (time division multiple access), OFDMA (orthogonal frequency division multiple access), and SC-FDMA (single carrier frequency division multiple access) technologies.

[0025] In addition, the processing pattern image may be an image (2D or 3D image) on which a processing pattern is formed, or a video containing an image on which a processing pattern is formed.

[0026] The camera module (120) may be, for example, a CCD (Charge-Coupled Device) camera and may capture an object (for example, a substrate) located on a stand (not shown) to generate an image of the object.

[0027] The laser module (130) may include at least one of a laser light source, a beam regulator, an output regulator, a polarizer, a wavelength filter, a beam expander, and a scanner, and may irradiate a laser under the control of a processor (140).

[0028] The processor (140) can acquire a processing pattern image through the interface (110). At this time, the processor (140) can edit the processing pattern image based on set pattern conditions (e.g., image size, pattern size, curvature, etc.) or input modification requests (e.g., change in shape, change in size of the pattern, etc.). For example, if the processing pattern image (or pattern) is larger than the set size, the processor (140) can edit the processing pattern image so that it is reduced by the set value. If the curvature within the pattern of the processing pattern image is greater than the set value, the processor (140) can edit the processing pattern image so that the curvature within the pattern is reduced by the set value to make the curve smooth. Additionally, if the lines within the pattern of the processing pattern image are uneven or zigzag, the processor (140) can edit the processing pattern image so that the lines within the pattern are modified to be smooth.

[0029] In an embodiment, the processor (140) can edit the video based on the video conditions if the processed pattern image includes a video and the video does not satisfy the set video conditions. The video conditions may be, for example, conditions regarding the number of images (frames) forming the video, the size (or resolution) of the images, the frame rate, etc. At this time, the processor (140) can further edit each image within the video based on the set pattern conditions.

[0030] The processor (140) can generate processing command data from a processing pattern image using an artificial intelligence-based processing command generation model. For example, as shown in FIG. 2, the processor (140) can generate processing command data (230) from a processing pattern image (210) in which a first region and a second region separated by a diagonal line have different surfaces (or colors) using an artificial intelligence-based processing command generation model (220).

[0031] Here, the processing command generation model may be, but is not limited to, a generative AI (Artificial Intelligence) model trained to generate processing command data based on processing pattern images. For example, the processing command generation model may be a machine learning-based training model pre-trained to generate processing command data based on processing pattern images. In this case, the processing command generation model may be trained using a supervised learning method with training data that takes processing pattern images as input and processing command data as labels, but is not limited to this.

[0032] In the embodiment, the processing command data may be processing coding data (e.g., CNC (Computer Numerical Control) code) and may include at least one of the laser output intensity, wavelength type, focal length, beam diameter, position (coordinates) where the laser is irradiated, direction of movement at said position (e.g., x-axis, y-axis), distance of movement, and scan speed (or processing speed).

[0033] The processor (140) can automatically process an object according to the processing pattern of a processing pattern image by irradiating a laser onto the object based on processing command data through the laser module (130), thereby applying the processing pattern to the object. For example, as shown in FIG. 3, the processor (140) can automatically process an object (310) according to the processing pattern of a processing pattern image (210) in which the first region and the second region have different surfaces (or colors) by irradiating a laser onto the object (310) based on processing command data (230) through the laser module (130), thereby creating an object (320 in FIG. 3) with the processing pattern applied.

[0034] The processor (140) can process the object based on the scan result of the object through the laser module (130), but is not limited thereto, and can process the object based on the image of the object generated by the camera module (120).

[0035] In an embodiment, the processor (140) can irradiate a laser onto an object based on an image of the object generated by the camera module (120). Based on the image of the object, the processor (140) can identify information such as the position (or size) of the object, the application position of the processing pattern on the object, and the starting point (coordinates) of the laser irradiation, and based on the identified information, can irradiate a laser onto the object according to the processing command data. In an embodiment, the processor (140) compares the processing pattern image and the image of the object (e.g., image size or coordinate comparison), and based on the comparison result, can change at least one of the position (coordinates) for irradiating the laser within the processing command data, the direction of movement (e.g., x-axis, y-axis), and the distance of movement. For example, the processor (140) can change the laser irradiation coordinates (position for irradiating the laser) formed based on the first reference coordinate of the processing pattern image based on the difference between the first reference coordinate of the processing pattern image and the second reference coordinate of the image of the object. Here, the pixels of the processing pattern image and the pixels of the image of the object may be matched one-to-one or one-to-many (or many-to-one). Additionally, the first reference coordinate and the second reference coordinate may be pre-set in relation to any pixel of the processing pattern image and the image of the object, respectively, or may be set by the user through the interface (110).

[0036] In an embodiment, the processor (140) can recognize the state of an object (e.g., type (or material), thickness, etc.) through various methods, and can effectively apply a processing pattern to the object by changing processing command data based on the state of the object. At this time, the processor (140) can recognize the state of the object through, for example, an X-ray fluorescence scanner, a laser-induced spectroscopic scanner, an infrared scanner, etc., or receive the recognition result through an interface (110).

[0037] Additionally, when processing conditions are input through the interface (110), the processor (140) changes the processing command data based on the processing conditions, thereby enabling the user to obtain optimal processing command data. Here, the processing conditions may include, for example, change information for at least one of the laser output intensity, wavelength type, focal length, beam diameter, position where the laser is irradiated, direction of movement at said position, distance of movement, and scan speed (or processing speed).

[0038] In an embodiment, when the processor (140) receives a request to send (or share) processing command data to an external device (e.g., image processing device, memory) or another laser processing device through the interface (110), it can transmit a processing pattern image and processing command data corresponding to the processing pattern image to the external device or another laser processing device. By doing so, the processor (140) can provide an environment that allows the object to be easily processed even on a device that does not support the automatic generation of processing command data for the processing pattern image.

[0039] The processor (140) controls the overall operation of the laser processing device (100). For example, the processor (140) can control the interface (110), camera module (120), laser module (130), etc., by executing programs stored in memory (150), and thereby control the operation of the laser processing device (100).

[0040] The processor (140) may be implemented using at least one of ASICs (application specific integrated circuits), DSPs (digital signal processors), DSPDs (digital signal processing devices), PLDs (programmable logic devices), FPGAs (field programmable gate arrays), controllers, microcontrollers, microprocessors, and other electrical units for performing functions.

[0041] The memory (150) is hardware that stores various data processed within the laser processing device (100), is operably connected to the processor (140), and can store a program for processing and controlling the processor (140).

[0042] Additionally, the memory (150) can further store an artificial intelligence-based processing command generation model. Here, the processing command generation model may be generated by the processor (140) or received from an external server and stored.

[0043] The memory (150) may include RAM (random access memory), such as DRAM (dynamic random access memory) and SRAM (static random access memory), ROM (read-only memory), EEPROM (electrically erasable programmable read-only memory), CD-ROM, Blu-ray or other optical disc storage, HDD (hard disk drive), SSD (solid state drive), or flash memory.

[0044] In addition, embodiments according to the present invention may be implemented in the form of a computer program that can be executed through various components on a computer, and such a computer program may be recorded on a computer-readable medium. In this case, the medium may include a magnetic medium such as a hard disk, a floppy disk, and a magnetic tape, an optical recording medium such as a CD-ROM and a DVD, a magneto-optical medium such as a floptical disk, and a hardware device specifically configured to store and execute program instructions, such as a ROM, RAM, or flash memory.

[0045] Meanwhile, the above-mentioned computer program may be one specifically designed and configured for the present invention, or one known and available to those skilled in the art of computer software. Examples of computer programs may include machine code, such as that generated by a compiler, as well as high-level language code that can be executed by a computer using an interpreter, etc.

[0047] FIG. 4 is a drawing for explaining another example of processing in a laser processing device according to an embodiment of the present invention.

[0048] Referring to FIG. 4, a laser processing device (400) according to an embodiment of the present invention may acquire a processing pattern image (410) including, for example, a curve as a processing pattern. The laser processing device (400) may receive a processing pattern image from an external device (e.g., an image processing device, memory) or receive a processing pattern image from a user, but is not limited thereto. For example, the laser processing device (400) may acquire a processing pattern image by photographing, through a camera module (120), any one of a processing pattern paper placed on an object, an object on which a processing pattern sketch (e.g., a sketch using a marking pen, chalk, etc.) is drawn, and an object on which a processing pattern has already been applied. Here, the processing pattern paper or the object on which a processing pattern has already been applied may be placed temporarily (before irradiating with a laser) and may be removed after the processing pattern image is acquired. In addition, the processing pattern sketch may be temporarily drawn on the object, but is not limited to this; it may remain on the object and be used as a criterion for judging the precision of the processing pattern after the object is processed by a laser.

[0049] As the laser processing device (400) acquires a processing pattern image (410), it can generate processing command data (420) using an artificial intelligence-based processing command generation model from the processing pattern image (410). The laser processing device (400) can efficiently engrave a processing pattern including a curve on the object (430) by irradiating a laser onto the object (430) (the object to which the processing pattern is to be applied) based on the processing command data (420) and processing the object (430) in real time. In an embodiment, the object (430) may include, for example, a weld line in a butt weld of a complex shape. Here, the weld line may refer to seam tracking, and an environment can be provided that enables the welding (or processing) process to be performed automatically while observing with a vision system. The weld line may match the processing pattern of the processing pattern image (410), but is not limited thereto and may differ. If the weld line is different from the processing pattern of the processing pattern image (410), the laser processing device (400) can adjust the processing command data (420) based on the weld line when irradiating a laser onto an object (430) based on the processing command data (420).

[0051] FIG. 5 is a flowchart illustrating a laser processing method according to an embodiment of the present invention. Here, the laser processing method can be performed by a processor of a laser processing device.

[0052] Referring to FIG. 5, in step S510, the laser processing device can acquire a processing pattern image. At this time, the laser processing device may receive the processing pattern image from an external device (e.g., an image processing device) or receive the processing pattern image from a user. Here, the processing pattern image may be an image in which a processing pattern is formed or a video containing an image in which a processing pattern is formed.

[0053] In an embodiment, the laser processing device can edit a processing pattern image based on set pattern conditions (e.g., image size, pattern size, curvature, etc.) or input modification requests (e.g., change in pattern shape, change in size, etc.).

[0054] The laser processing device can edit the video based on the video conditions if the processing pattern image includes a video and the video does not satisfy the set video conditions.

[0055] In step S520, the laser processing device can generate processing command data from a processing pattern image using an artificial intelligence-based processing command generation model.

[0056] Here, the processing command generation model may be a generative AI (Artificial Intelligence) model trained to generate processing command data based on processing pattern images, or a machine learning-based learning model pre-trained to generate processing command data based on processing pattern images, but is not limited thereto.

[0057] In an embodiment, the processing command data may be processing coding data (e.g., CNC (Computer Numerical Control) code) and may include at least one of the laser output intensity, wavelength type, focal length, beam diameter, position where the laser is irradiated, direction of movement at the position, distance of movement, and scan speed.

[0058] In step S530, the laser processing device can process the object by irradiating a laser onto the object based on processing command data. By irradiating a laser onto the object based on processing command data, the laser processing device can automatically process the object according to the processing pattern of the processing pattern image and apply the processing pattern to the object.

[0059] In an embodiment, the laser processing device can recognize the state of an object (e.g., type (or material), thickness, etc.) through various methods, and by changing processing command data based on the state of the object, it can effectively apply a processing pattern to the object.

[0060] In addition, when processing conditions are input, the laser processing device modifies the processing command data based on the processing conditions, thereby enabling the user to obtain optimal processing command data. Here, the processing conditions may include, for example, information on changes to at least one of the laser output intensity, wavelength type, focal length, beam diameter, position where the laser is irradiated, direction of movement at the position, distance traveled, and scan speed.

[0062] A laser processing device according to an embodiment of the present invention generates processing command data using an artificial intelligence-based processing command generation model from a processing pattern image, and by irradiating a laser onto an object based on the processing command data, it can easily acquire processing command data and effectively process an object according to the processing pattern of the processing pattern image.

[0064] The embodiments according to the present invention described above may be implemented in the form of a computer program that can be executed through various components on a computer, and such a computer program may be recorded on a computer-readable medium. In this case, the medium may include a magnetic medium such as a hard disk, a floppy disk, and a magnetic tape, an optical recording medium such as a CD-ROM and a DVD, a magneto-optical medium such as a floptical disk, and a hardware device specifically configured to store and execute program instructions, such as a ROM, RAM, or flash memory.

[0065] Meanwhile, the above-mentioned computer program may be one specifically designed and configured for the present invention, or one known and available to those skilled in the art of computer software. Examples of computer programs may include machine code, such as that generated by a compiler, as well as high-level language code that can be executed by a computer using an interpreter, etc.

[0066] In the specification of the present invention (particularly in the claims), the use of the term "above" and similar descriptive terms may be in both singular and plural. Furthermore, where a range is described in the present invention, it is to include an invention to which individual values ​​belonging to said range are applied (unless otherwise stated), and this is equivalent to describing each individual value constituting said range in the detailed description of the invention.

[0067] Unless explicitly stated or contrary to the order of the steps constituting the method according to the present invention, said steps may be performed in a suitable order. The present invention is not necessarily limited by the order in which said steps are described. The use of all examples or exemplary terms (e.g., etc.) in the present invention is merely for the purpose of describing the present invention in detail, and the scope of the present invention is not limited by said examples or exemplary terms unless limited by the claims. Furthermore, those skilled in the art will understand that various modifications, combinations, and changes may be made according to design conditions and factors within the scope of the claims or equivalents to which they are added.

[0068] Accordingly, the scope of the present invention should not be limited to the embodiments described above, and all scopes equivalent to or equivalently modified from the claims set forth below, as well as the claims set forth below, shall be considered to fall within the scope of the concept of the present invention. Explanation of the symbols

[0069] 100: Laser processing device 110: Interface 120: Camera module 130: Laser Module 140: Processor 150: Memory

Claims

Claim 1 A laser processing method performed by a processor of a laser processing device, comprising: a step of acquiring a processing pattern image, which is an image in which a processing pattern to be processed on a target object is formed, or a video including said image; a step of generating processing command data using an artificial intelligence-based processing command generation model from said processing pattern image; and a step of applying a processing pattern of said processing pattern image to a target object by irradiating a laser on said target object based on said processing command data to process said target object, wherein the processing command generation model is a model trained to generate processing command data corresponding to a processing pattern of said processing pattern image using the processing pattern image as input, and said processing command data includes a position for irradiating the laser corresponding to said processing pattern, a direction of movement at said position, and a distance of movement. Claim 2 A laser processing method according to claim 1, wherein the processing command generation model is a generative AI (Artificial Intelligence) model trained to generate processing command data based on a processing pattern image. Claim 3 A laser processing method according to claim 1, wherein the processing command data comprises at least one of the output intensity, wavelength type, focal length, beam diameter, and scan speed of the laser. Claim 4 A laser processing method according to claim 1, wherein the step of generating processing command data includes the step of changing the processing command data based on the processing conditions when processing conditions are input. Claim 5 A laser processing method according to claim 1, further comprising a step of recognizing the state of the object, and a step of generating processing command data comprising a step of changing the processing command data based on the state of the object. Claim 6 A laser processing method according to claim 1, further comprising the step of editing the processing pattern image based on set pattern conditions or input modification requests. Claim 7 A laser processing method according to claim 1, wherein the processing pattern image includes a video, and if the video does not satisfy a set video condition, the method further includes the step of editing the video based on the video condition. Claim 8 A laser processing device comprising: a processor; and a memory operably connected to the processor and storing at least one code executed by the processor, wherein the memory stores a code that, when executed through the processor, causes the processor to obtain a processing pattern image, which is an image in which a processing pattern to be processed on a target object is formed or a video including said image, and generates processing command data from said processing pattern image using an artificial intelligence-based processing command generation model, and causes the processing pattern of said processing pattern image to be applied to said target object by irradiating a laser on said target object based on said processing command data to process said target object, and wherein the processing command generation model is a model trained to generate processing command data corresponding to the processing pattern of said processing pattern image using the processing pattern image as input, and said processing command data includes a position for irradiating the laser corresponding to said processing pattern, a direction of movement at said position, and a distance of movement. Claim 9 In claim 8, the above processing command generation model is a generative AI (Artificial Intelligence) model trained to generate processing command data based on a processing pattern image, a laser processing device. Claim 10 In claim 8, the laser processing device, wherein the processing command data comprises at least one of the output intensity, wavelength type, focal length, beam diameter, and scan speed of the laser. Claim 11 A laser processing device according to claim 8, wherein the memory stores a code that causes the processor to change the processing command data based on the processing conditions when processing conditions are input. Claim 12 A laser processing device according to claim 8, wherein the memory stores a code that causes the processor to recognize the state of the object and change the processing command data based on the state of the object. Claim 13 A laser processing device according to claim 8, wherein the memory further stores code that causes the processor to edit the processing pattern image based on set pattern conditions or input modification requests. Claim 14 A laser processing device according to claim 8, wherein the processing pattern image includes a video, and the memory further stores code that causes the processor to edit the video based on the video conditions when the video does not satisfy the set video conditions. Claim 15 A laser processing method according to claim 1, wherein the processing command data includes a CNC (Computer Numerical Control) code as processing coding data. Claim 16 A laser processing method according to claim 1, further comprising: a step of comparing the processing pattern image and the image of the object; and a step of changing at least one of the position for irradiating the laser, the direction of movement at the position, and the distance of movement within the processing command data based on the comparison result, wherein the change in the position for irradiating the laser is based on the difference between the first reference coordinate of the processing pattern image and the second reference coordinate of the image of the object. Claim 17 A laser processing method according to claim 1, wherein the processing command generation model is trained by supervised learning using training data in which a processing pattern image is input and processing command data is labeled. Claim 18 A laser processing device according to claim 8, wherein the processing command data includes a CNC (Computer Numerical Control) code as processing coding data. Claim 19 A laser processing device according to claim 8, wherein the memory further stores a code that causes the processor to compare the processing pattern image and the image of the object, and based on the comparison result, change at least one of the position for irradiating the laser, the direction of movement at the position, and the distance of movement within the processing command data, and the change in the position for irradiating the laser is based on the difference between the first reference coordinate of the processing pattern image and the second reference coordinate of the image of the object. Claim 20 In claim 8, the above processing command generation model is a laser processing device trained by supervised learning using training data in which a processing pattern image is input and processing command data is labeled.

Images