KR20240009314A - A printing device that learns artificial intelligence and collects learning data to optimize print quality - Google Patents

Abstract

According to an embodiment of the present invention, a printing device that optimizes printing quality by learning artificial intelligence and collecting learning data is disclosed. The device includes at least one processor; and a memory storing instructions that instruct the at least one processor to perform at least one operation. Additionally, the at least one operation may include receiving ink component information for each color; An operation of receiving design information including color and thickness matching each of a plurality of coordinates; An operation of determining ink component information matching the color that matches each of the coordinates using the ink component information for each color; An operation of generating printing information including the ink component information and the thickness matching each of the coordinates; An operation of generating optical output information including wavelength, output, exposure time, and curing time matching each of the coordinates using the printing information; and controlling an ink application module and an ink curing module included in the printing device using the design information and the optical output information. In addition, the operation of generating optical output information including wavelength, output, exposure time, and curing time matching each of the coordinates using the printing information includes the ink component information and the thickness matching each of the coordinates. An operation of generating a printing vector matching each of the coordinates using the coordinates; And inputting the printing vector as an input value to a pre-trained first artificial neural network, and obtaining the wavelength, the output, the exposure time, and the curing time corresponding to the printing vector from the first artificial neural network. do. In addition, the first artificial neural network is generated through machine learning using a learning data set containing learning data generated by labeling the learning printing vector with the learning wavelength, learning output, learning exposure time, and learning curing time. In addition, The at least one operation may include obtaining a cured image; An operation of dividing the image into a plurality of split images matching the coordinates; An operation of determining a score for each of the split images; An operation of selecting the segmented image whose score is greater than a preset reference score; Select the coordinates that match the selected split images, the ink component information that matches each of the selected coordinates, and the wavelength, the output, the exposure time, and the curing that match each of the coordinates selected for the thickness. An operation to generate learning data by labeling time; and providing the learning data to the server. In addition, the operation of determining the score of each of the segmented images includes inputting each of the segmented images as an input value to a pre-trained second artificial neural network, and calculating the score of each of the segmented images from the second artificial neural network. This is an operation to obtain, and the second artificial neural network is created through machine learning using a learning data set containing learning data generated by labeling learning segment images with learning scores.

Description

A printing device that learns artificial intelligence and collects learning data to optimize print quality {A PRINTING DEVICE THAT LEARNS ARTIFICIAL INTELLIGENCE AND COLLECTS LEARNING DATA TO OPTIMIZE PRINT QUALITY}

The present invention relates to a printing device that optimizes printing quality by learning artificial intelligence and collecting learning data.

Unless otherwise indicated herein, the material described in this section is not prior art to the claims of this application, and is not admitted to be prior art by inclusion in this section.

Printing using ink is a commonly used method. When you put paper in the printer and input the desired output type, the printer sprays ink on the paper according to the output type to complete the output.

However, with the development of ink that hardens when irradiated with ultraviolet rays, printing has become possible not only on paper but also on media such as wood, stone, and glass.

In particular, unlike existing inks that contain solvents or diluents and cause pollution, inks that harden when irradiated with ultraviolet rays do not contain solvents or diluents, so they do not cause pollution and are environmentally friendly.

Accordingly, the importance of printing technology related to ink that hardens when irradiated with ultraviolet rays is emerging.

The present invention is a printing device that uses eco-friendly UV curing ink to optimize print quality by learning artificial intelligence and collecting learning data that can provide output with improved print quality while not generating pollution during the printing process. The purpose is to provide.

One aspect of the present invention to achieve the above object provides a printing device that learns artificial intelligence and collects learning data to optimize printing quality.

Additionally, the device includes at least one processor; and a memory storing instructions that instruct the at least one processor to perform at least one operation.

Additionally, the at least one operation may include receiving ink component information for each color; An operation of receiving design information including color and thickness matching each of a plurality of coordinates; An operation of determining ink component information matching the color that matches each of the coordinates using the ink component information for each color; An operation of generating printing information including the ink component information and the thickness matching each of the coordinates; An operation of generating optical output information including wavelength, output, exposure time, and curing time matching each of the coordinates using the printing information; and controlling an ink application module and an ink curing module included in the printing device using the design information and the optical output information.

In addition, the operation of generating optical output information including wavelength, output, exposure time, and curing time matching each of the coordinates using the printing information includes the ink component information and the thickness matching each of the coordinates. An operation of generating a printing vector matching each of the coordinates using the coordinates; And inputting the printing vector as an input value to a pre-trained first artificial neural network, and obtaining the wavelength, the output, the exposure time, and the curing time corresponding to the printing vector from the first artificial neural network. do.

In addition, the first artificial neural network is generated through machine learning using a learning data set containing learning data generated by labeling a learning printing vector with a learning wavelength, learning output, learning exposure time, and learning curing time.

Additionally, the at least one operation may include obtaining an image in which curing has been completed; An operation of dividing the image into a plurality of split images matching the coordinates; An operation of determining a score for each of the split images; An operation of selecting the segmented image whose score is greater than a preset reference score; Select the coordinates that match the selected split images, the ink component information that matches each of the selected coordinates, and the wavelength, the output, the exposure time, and the curing that match each of the coordinates selected for the thickness. An operation to generate learning data by labeling time; and providing the learning data to the server.

In addition, the operation of determining the score of each of the segmented images includes inputting each of the segmented images as an input value to a pre-trained second artificial neural network, and calculating the score of each of the segmented images from the second artificial neural network. This is an operation to obtain, and the second artificial neural network is created through machine learning using a learning data set containing learning data generated by labeling learning segment images with learning scores.

According to one embodiment of the present invention, by using eco-friendly UV curing ink, pollution can be prevented during the printing process, and improved printing quality can be provided by irradiating ultraviolet rays with output suitable for the thickness of the ink and the printed material. .

Figure 1 is a schematic diagram of a system for providing a printing method using eco-friendly UV curing ink according to an embodiment of the present invention.
FIG. 2 is a diagram illustrating an example of the printing device according to FIG. 1.
Fig. 3 is a top view showing the printing assembly according to Fig. 2;
FIG. 4 is a diagram illustrating another embodiment of the printing device according to FIG. 1.
Fig. 5 is a top view showing the printing assembly according to Fig. 4;
FIG. 6 is a block diagram illustrating functional modules of the printing device according to FIG. 1 by way of example.
FIG. 7 is a diagram illustrating an exemplary hardware configuration of the printing device according to FIG. 1.
FIG. 8 is a flowchart showing a process in which the printing device according to FIG. 1 performs printing.
Figure 9 is a flowchart specifically showing step S15 of Figure 8.
FIG. 10 is a flowchart showing a process in which the printing device according to FIG. 1 generates learning data.

Since the present invention can make various changes and have various embodiments, specific embodiments will be illustrated in the drawings and described in detail in the detailed description. However, this is not intended to limit the present invention to specific embodiments, and should be understood to include all changes, equivalents, and substitutes included in the spirit and technical scope of the present invention. While describing each drawing, similar reference numerals are used for similar components.

Terms such as first, second, A, and B may be used to describe various components, but the components should not be limited by the terms. The above terms are used only for the purpose of distinguishing one component from another. For example, a first component may be named a second component, and similarly, the second component may also be named a first component without departing from the scope of the present invention. The term and/or includes any of a plurality of related stated items or a combination of a plurality of related stated items.

When a component is said to be "connected" or "connected" to another component, it is understood that it may be directly connected to or connected to the other component, but that other components may exist in between. It should be. On the other hand, when it is mentioned that a component is “directly connected” or “directly connected” to another component, it should be understood that there are no other components in between.

The terms used in this application are only used to describe specific embodiments and are not intended to limit the invention. Singular expressions include plural expressions unless the context clearly dictates otherwise. In this application, terms such as “comprise” or “have” are intended to designate the presence of features, numbers, steps, operations, components, parts, or combinations thereof described in the specification, but are not intended to indicate the presence of one or more other features. It should be understood that this does not exclude in advance the possibility of the existence or addition of elements, numbers, steps, operations, components, parts, or combinations thereof.

Unless otherwise defined, all terms used herein, including technical or scientific terms, have the same meaning as commonly understood by a person of ordinary skill in the technical field to which the present invention pertains. Terms defined in commonly used dictionaries should be interpreted as having a meaning consistent with the meaning in the context of the related technology, and unless explicitly defined in the present application, should not be interpreted in an ideal or excessively formal sense. No.

Hereinafter, preferred embodiments according to the present invention will be described in detail with reference to the attached drawings.

Figure 1 is a schematic diagram of a system for providing a printing method using eco-friendly UV (UltraViolet) curing ink according to an embodiment of the present invention.

In one embodiment, the eco-friendly UV curing ink may include oligomers, monomers, photopolymerization initiators, pigments, auxiliaries (viscosity improvers, antioxidants, wetting aids, dispersants), polymerization inhibitors, sensitizers, etc. You can.

In one embodiment, the eco-friendly UV curing ink may additionally include a phytoncide capsule and a photocatalyst TiO ₂ . In one embodiment, phytoncide capsules produced by a known method may be used.

As phytoncide capsules and photocatalyst TiO ₂ are used in UV curing ink, prints produced using UV curing ink can have the effect of decomposing organic substances and have an antibacterial effect.

Referring to FIG. 1, a system for providing a printing method using eco-friendly UV curing ink according to an embodiment of the present invention includes a server 1 and a printing device 10.

The server 1 may be communicatively connected to a plurality of printing devices 10 .

The server 1 may periodically provide a pre-trained first artificial neural network and a pre-trained second artificial neural network to the printing devices 10.

In one embodiment, the first artificial neural network is an artificial neural network that learns the correlation between the components of UV curing ink and printing thickness and wavelength, output, exposure time, and curing time to obtain good printing quality through machine learning. You can.

In one embodiment, the second artificial neural network may be an artificial neural network that establishes the correlation between printing images and printing quality through machine learning.

The printing device 10 may periodically provide learning data generated during the printing process to the server 1.

FIG. 2 is a diagram illustrating an embodiment of the printing device 10 according to FIG. 1 .

Referring to FIG. 2, the printing device 10 includes a housing 11 and a printing surface 12 disposed on one side of the housing 11. In one embodiment, the housing 11 may be formed in various known shapes.

The printing device 10 includes a printing assembly 20 connected to the housing 11 so as to be movable along the printing direction.

The printing assembly 20 includes a printing frame 21 that is moved along the printing direction. In one embodiment, a guide rail may be formed on the side of the housing 11 along the printing direction, and both sides of the printing frame 21 may be connected to the guide rail and moved in the printing direction along the guide rail.

The printing assembly 20 includes an ink curing module 24 attached to one side of the printing frame 21 along the printing direction.

FIG. 3 is a plan view showing the printing assembly 20 according to FIG. 2.

3 shows one side of the printing assembly 20 facing the printing surface 12.

The printing frame 21 includes an ink application module 23. The ink application module 23 is configured to apply a plurality of UV curing inks of different colors at designated coordinates. The ink application portion of the ink application module 23 is opened toward the printing surface 12, and as the printing frame 21 moves along the printing direction, the ink application module 23 also moves in the printing direction.

The ink curing module 24 includes a plurality of ultraviolet lamps 25. The ink curing module 24 is configured to adjust the wavelength, output, and output time of ultraviolet rays irradiated from the ultraviolet lamp 25. In one embodiment, the ultraviolet lamp 25 is disposed in the ink curing module 24 such that the portion irradiated with ultraviolet rays is directed toward the printing surface 12. In one embodiment, the ink curing module 24 may be configured to cover a filter that blocks ultraviolet rays from a portion of the ultraviolet lamp 25 that is irradiated with ultraviolet rays, or to remove the covered filter.

FIG. 4 is a diagram illustrating another embodiment of the printing device according to FIG. 1.

Referring to FIG. 4 , the printing device 10 includes a housing 11 and a printing surface 12 disposed on one side of the housing 11 . In one embodiment, the housing 11 may be formed in various known shapes.

The printing device 10 includes a printing assembly 20 connected to the housing 11 so as to be movable along the printing direction.

The printing assembly 20 includes a printing frame 21 that is moved along a direction intersecting the printing direction. In one embodiment, a guide rail may be formed on the side of the housing 11 along the printing direction, and both sides of the printing frame 21 are connected to the guide rail and can be moved along the guide rail in a direction intersecting the printing direction. You can. In the illustrated embodiment, the printing direction refers to the direction in which the printing frame 21 extends.

The printing assembly 20 includes a printing head 22 connected to the printing frame 21 so that it can move on the printing frame 21 along the printing direction.

An ink application module 23 is disposed on one side of the print head 22 in a direction intersecting the printing direction, and an ink curing module 24 is disposed on both sides of the ink application module 23 in the printing direction.

Fig. 5 is a top view showing the printing assembly according to Fig. 4;

The ink application module 23 is configured to apply a plurality of UV curing inks of different colors at designated coordinates.

The ink curing module 24 includes a plurality of ultraviolet lamps 25. The ink curing module 24 is configured to adjust the wavelength, output, and output time of ultraviolet rays emitted from the ultraviolet lamp 25. In one embodiment, the ultraviolet lamp 25 is disposed in the ink curing module 24 so that the portion irradiated with ultraviolet rays is directed toward the printing surface 12. In one embodiment, the ink curing module 24 may be configured to cover a filter that blocks ultraviolet rays on a portion of the ultraviolet lamp 25 that is irradiated with ultraviolet rays, or to remove the covered filter.

As the printing frame 21 moves along a direction intersecting the printing direction and the print head 22 moves along the printing direction, ink can be applied to all coordinates on the printing surface 12 and ultraviolet rays can be irradiated.

In one embodiment, the printing surface 12 may be divided into a plurality of coordinates in a grid.

FIG. 6 is a block diagram illustrating functional modules of the printing device 10 according to FIG. 1 by way of example.

Referring to FIG. 6, the printing device 10 includes an ink information receiving unit 101, a pattern receiving unit 102, a printing information generating unit 103, an optical output information generating unit 104, a printing assembly control unit 105, and It includes a learning data generation unit 106.

The ink information receiving unit 101 receives ink component information for each color of UV curing ink used for printing from the user. When multiple UV curing inks with different colored pigments are used, multiple ink component information is received for each color, and when a single color UV curing ink is used, ink component information for the UV curing ink used is received. do. In one embodiment, the ink information receiving unit 101 may receive ink component information through an input interface device. Additionally, the ink information receiving unit 101 may receive ink component information from the user's user terminal. In one embodiment, the ink component information includes oligomers, monomers, photopolymerization initiators, pigments, auxiliaries (viscosity improvers, antioxidants, wetting aids, dispersants), polymerization inhibitors, and sensitizers contained in UV curing ink. It may include information about the type of product, etc.

The design receiving unit 102 receives design information about a design to be used for printing from the user. In one embodiment, the design receiving unit 102 may receive design information through an input interface device. Additionally, the design receiving unit 102 may receive design information from the user's user terminal. In one embodiment, the design information may include a color and thickness that matches each of a plurality of preset coordinates.

The printing information generator 103 determines ink component information matching the color for each of the coordinates using ink component information for each color, and generates printing information including ink component information and thickness matching each of the coordinates. Create.

The optical output information generating unit 104 uses printing information to generate optical output information including wavelength, output, exposure time, and curing time matching each of the coordinates.

The print assembly control unit 105 controls the print assembly 20 using design information and optical output information.

The learning data generator 106 generates learning data using images taken of printed matter for which the printing process has been completed, and provides the generated learning data to the server 1.

FIG. 7 is a diagram illustrating the hardware configuration of the printing device 10 according to FIG. 1.

Referring to FIG. 7, the printing device 10 stores at least one processor 110 and instructions that instruct the at least one processor 110 to perform at least one operation. May include memory.

The at least one operation may include the components 101 to 106 of the above-described printing device 10 or other functions or operating methods.

Here, the at least one processor 110 may mean a central processing unit (CPU), a graphics processing unit (GPU), or a dedicated processor on which methods according to embodiments of the present invention are performed. there is. Each of the memory 120 and the storage device 160 may be comprised of at least one of a volatile storage medium and a non-volatile storage medium.

For example, the memory 120 may be one of read only memory (ROM) and random access memory (RAM), and the storage device 160 may be flash memory. , a hard disk drive (HDD), a solid state drive (SSD), or various memory cards (eg, micro SD card).

Additionally, the device 100 may include a transceiver 130 that performs communication through a wireless network. Additionally, the device 100 may further include an input interface device 140, an output interface device 150, a storage device 160, etc. Each component included in the device 100 is connected by a bus 170 and can communicate with each other.

FIG. 8 is a flowchart showing a process in which the printing device 10 according to FIG. 1 performs printing.

First, the ink information receiving unit 101 receives ink component information for each color (S11).

Additionally, the design receiving unit 102 receives design information including color and thickness matching each of a plurality of coordinates (S12).

Additionally, the printing information generator 103 determines ink component information matching each coordinate using ink component information for each color (S13).

The printing information generator 103 determines, for each of the coordinates, ink component information that matches the color of the coordinate. Through this, ink component information matching each of the coordinates can be determined.

Additionally, the printing information generating unit 103 generates printing information including ink component information and thickness matching each of the coordinates (S14).

The printing information generator 103 uses the thickness matching each of the coordinates included in the design information and the ink component information matching each of the coordinates determined in step S13 to generate the ink component information and thickness matching each of the coordinates. Generates print information including.

Additionally, the optical output information generating unit 104 uses the printing information to generate optical output information including the wavelength, output, and exposure time matching each of the coordinates (S15).

Figure 9 is a flowchart specifically showing step S15 of Figure 8.

Referring to FIG. 9, the optical output information generating unit 104 generates a printing vector matching each of the coordinates using ink component information and thickness matching each of the coordinates (S151).

In the database, preset numbers are stored in advance by matching each of the plurality of components that may be included in the ink component information, and the optical output information generation unit 104 selects numbers that match each of the plurality of components from the database. The optical output information generation unit 104 generates a printing vector, which is a multidimensional vector having the selected numbers and thickness as respective dimension values. In one embodiment, the number of dimensions of the multidimensional vector is set in advance, and if there is no component that matches the dimension in the ink component information, the dimension value of the corresponding dimension is determined to be 0.

The optical output information generation unit 104 inputs the printing vector as an input value to the first artificial neural network learned in advance, and obtains the wavelength, output, exposure time, and curing time corresponding to the printing vector from the first artificial neural network ( S152).

In one embodiment, the first artificial neural network may be generated through machine learning using a learning data set including learning data generated by labeling the learning printing vector with wavelength, output, exposure time, and curing time. In one embodiment, Random Forest, multiple regression analysis, Xgboost, etc. may be used for machine learning of the first artificial neural network. Through machine learning using learning data, the correlation between the ingredients of UV curing ink products and the application thickness of ink and the wavelength, output, exposure time, and curing time of ultraviolet rays to obtain relatively good printing quality can be learned. Through this, by inputting the ink vector obtained using the components and thickness of the UV curing ink to be used in the first artificial neural network, relatively excellent printing quality is achieved when the UV curing ink is applied with the thickness input from the first artificial neural network. You can obtain the wavelength, output, exposure time, and curing time of ultraviolet rays to obtain .

In one embodiment, the exposure time refers to the time the ink is exposed to the air without being irradiated with ultraviolet rays after being applied. In one embodiment, curing time refers to the time for irradiating ultraviolet rays to the applied ink. In one embodiment, the power represents the intensity of ultraviolet light, and the units of power are: It can be.

Referring again to FIG. 8, the print assembly control unit 105 controls the ink application module 23 and the ink curing module 24 using design information and optical output information (S16).

The print assembly control unit 105 controls the ink application module 23 to apply UV curing ink of a color matching each of the coordinates to each of the coordinates using a color that matches each of the coordinates included in the design information. .

The printing assembly control unit 105 uses the wavelength, output, exposure time, and curing time that match each of the coordinates included in the optical output information, and sets the ink curing module 24 to a wavelength that matches each of the coordinates. , control the output of ultraviolet rays by output and curing time.

In addition, the ink assembly control unit 105, after UV curing ink is applied to each of the coordinates by the ink application module 23, ink curing module 24 to each of the coordinates during an exposure time matching each of the coordinates. The ink curing module 24 is controlled so that ultraviolet rays are not irradiated. In one embodiment, the ink assembly control unit 105 may control the ink curing module 24 so that ultraviolet rays are not output from the ink curing module 24 during the exposure time. In one embodiment, the ink assembly control unit 105 may control the ink curing module 24 so that the filter covers the lamp irradiated with ultraviolet rays of the ink curing module 24 during the exposure time.

FIG. 10 is a flowchart showing a process in which the printing device 10 according to FIG. 1 generates learning data.

First, the learning data generator 106 acquires an image of a printed product that has been cured (S21).

In one embodiment, the printing device 10 may capture an image of a printed product that has been cured through a camera-type input interface device.

Additionally, the learning data generator 106 divides the image into a plurality of split images matching a plurality of coordinates (S22).

In one embodiment, each of the plurality of split images constituting the image may have a rectangular shape with a preset size.

Additionally, the learning data generator 106 determines the score of each segmented image (S23).

The learning data generator 106 inputs a segmented image as an input value to a pre-trained second artificial neural network and obtains a score corresponding to the segmented image from the second artificial neural network.

In one embodiment, the second artificial neural network may be created through machine learning using a learning data set including learning data generated by labeling scores on segmented images for learning. In one embodiment, CNN (Convolutional Neural Network), Random Forest, etc. may be used for machine learning of the second artificial neural network.

Additionally, the learning data generator 106 selects a segmented image whose score is greater than a preset standard score (S24).

In addition, the learning data generator 106 selects coordinates that match the selected split images, and ink component information and thickness that match each of the selected coordinates, as well as wavelength, output, exposure time, and Learning data is generated by labeling the curing time (S25).

Additionally, the learning data generator 106 provides the generated learning data to the server 1 (S26).

Through this, learning data generated using information corresponding to coordinates printed with a quality higher than a preset standard can be provided to the server 1 and used for learning of the first artificial neural network.

Through this, learning data for training the first artificial neural network can be collected periodically, and as the learning data gradually accumulates, the performance of the retrained first artificial neural network can be improved.

Methods according to the present invention may be implemented in the form of program instructions that can be executed through various computer means and recorded on a computer-readable medium. Computer-readable media may include program instructions, data files, data structures, etc., singly or in combination. Program instructions recorded on a computer-readable medium may be those specifically designed and configured for the present invention, or may be known and usable by those skilled in the art of computer software.

Examples of computer-readable media may include hardware devices specifically configured to store and execute program instructions, such as ROM, RAM, flash memory, etc. Examples of program instructions may include machine language code such as that created by a compiler, as well as high-level language code that can be executed by a computer using an interpreter, etc. The above-described hardware device may be configured to operate with at least one software module to perform the operations of the present invention, and vice versa.

Additionally, the above-described method or device may be implemented by combining all or part of its components or functions, or may be implemented separately.

Although the present invention has been described above with reference to preferred embodiments, those skilled in the art may make various modifications and changes to the present invention without departing from the spirit and scope of the present invention as set forth in the following patent claims. You will understand that you can do it.

Claims (1)

It is a printing device that optimizes printing quality by learning artificial intelligence and collecting learning data.
The device is,
at least one processor; and
Includes a memory that stores instructions that instruct the at least one processor to perform at least one operation,
The at least one operation is,
An operation of receiving ink component information for each color;
An operation of receiving design information including color and thickness matching each of a plurality of coordinates;
An operation of determining ink component information matching the color that matches each of the coordinates using the ink component information for each color;
An operation of generating printing information including the ink component information and the thickness matching each of the coordinates;
An operation of generating optical output information including wavelength, output, exposure time, and curing time matching each of the coordinates using the printing information; and
Comprising an operation of controlling an ink application module and an ink curing module included in the printing device using the design information and the optical output information,
The operation of using the printing information to generate optical output information including wavelength, output, exposure time, and curing time matching each of the coordinates,
An operation of generating a printing vector matching each of the coordinates using the ink component information and the thickness to which each of the coordinates matches; and
Inputting the printing vector as an input value into a pre-trained first artificial neural network, and obtaining the wavelength, the output, the exposure time, and the curing time corresponding to the printing vector from the first artificial neural network; ,
The first artificial neural network is,
Generated through machine learning using a learning data set containing learning data generated by labeling the learning printing vector with learning wavelength, learning output, learning exposure time, and learning curing time,
The at least one operation is,
An operation of acquiring an image of completed curing;
An operation of dividing the image into a plurality of split images matching the coordinates;
An operation of determining a score for each of the split images;
An operation of selecting the segmented image whose score is greater than a preset reference score;
Select the coordinates that match the selected split images, the ink component information that matches each of the selected coordinates, and the wavelength, the output, the exposure time, and the curing that match each of the coordinates selected for the thickness. An operation to generate learning data by labeling time; and
Including the operation of providing the learning data to the server,
The operation of determining the score of each of the split images is:
An operation of inputting each of the segmented images as an input value into a pre-trained second artificial neural network and obtaining the score of each of the segmented images from the second artificial neural network,
The second artificial neural network is,
Generated through machine learning using a learning data set containing learning data created by labeling learning segment images with learning scores,
Device.