KR102557870B1 - Method and apparatus for generating training data for and artificial intelligence model that predicts the performance verification results of automotive parts - Google Patents

Abstract

Disclosed is a method and apparatus for generating learning data of an artificial intelligence model that predicts performance analysis results of automobile parts by receiving skin data of automobile parts.
A method for generating learning data of an artificial intelligence model for predicting a performance verification result of an automobile part according to an embodiment includes the steps of collecting skin data obtained by 3D modeling an external shape of the automobile part as original data necessary for predicting the performance of the automobile part; converting the file format of the collected original data into a standard file format; and generating training data by labeling the collected original data with shape information recognized from the original data in the standard file format.

Description

Method and apparatus for generating training data for and artificial intelligence model that predicts the performance verification results of automotive parts}

A method and apparatus for generating learning data of an artificial intelligence model predicting performance verification results of automobile parts are disclosed.

Automotive parts are completed by repeating processes such as design, skin data generation, 3D data generation, and part performance analysis. Specifically, after completing the design of the exterior of the automobile part, skin data obtained by 3D modeling the exterior shape is created, and then, based on the skin data, design work is performed to add a fastening structure and a structure securing rigidity of the part to generate 3D data. Then, the performance of the parts is verified using these 3D data. If the performance verification result is unsatisfactory, the exterior design of the vehicle part is changed, and the skin data creation, 3D data creation, and part performance verification processes are repeated.

The steps as described above are repeatedly performed until the performance verification result reaches the target value. Therefore, there is a problem in that considerable time and cost are required to acquire the final design data of automobile parts.

Korean Registered Patent No. 10-2069553 (Title of Invention: Efficiency Prediction System and Method of Rotating Body Using Conversion of Learning Data, Publication Date: January 23, 2020)

Disclosed is a method and apparatus for generating learning data of an artificial intelligence model that predicts performance analysis results of automobile parts by receiving skin data of automobile parts.

In order to solve the above-described problems, a method for generating learning data of an artificial intelligence model for predicting performance verification results of automobile parts according to an embodiment is original data necessary for predicting the performance of automobile parts. Collecting skin data obtained by 3D modeling the exterior shape of the automobile parts; converting the file format of the collected original data into a standard file format; and generating training data by labeling the collected original data with shape information recognized from the original data in the standard file format.

In order to solve the above-described problems, an apparatus for generating learning data of an artificial intelligence model for predicting performance verification results of automobile parts according to an embodiment includes, as original data necessary for predicting performance of automobile parts, a data collection unit that collects skin data obtained by 3D modeling the exterior shape of the automobile parts; a conversion unit that converts the file format of the collected original data into a standard file format; and a learning data generation unit generating learning data by labeling the collected original data with shape information recognized from the original data in the standard file format.

Since the shape information is labeled on the skin data obtained by 3D modeling the exterior shape of the automobile part, the time and cost required for labeling can be reduced.

1 is a diagram showing the configuration of an apparatus for generating learning data of an artificial intelligence model predicting performance verification results of automobile parts according to an embodiment of the present invention.
2 is a diagram for explaining the structure of an IGES file format.
3 is a diagram illustrating the types and names of some entities among various types of shape entities supported in the IGES file format.
FIG. 4 is a diagram illustrating a directory entry section and a parameter data section of a Rational B-Spline Curve Entity corresponding to type 126 among the entities illustrated in FIG. 3 .
FIG. 5 is a diagram illustrating a directory entry section and a parameter data section of a rational B-Spline Surface Entity corresponding to type 128 among the entities illustrated in FIG. 3 .
FIG. 6 is a diagram illustrating a directory entry section and a parameter data section of a trimmed (parametric) surface entity corresponding to type 144 among the entities illustrated in FIG. 3 .
7 to 9 are diagrams illustrating screens generated by the screen configuration unit of FIG. 1 .
10 is a hardware configuration diagram of an exemplary computing device in which devices in accordance with some embodiments of the invention may be implemented.
11 is a flowchart illustrating a method of generating learning data of an artificial intelligence model predicting performance verification results of automobile parts according to an embodiment of the present invention.

Advantages and features of the present invention, and methods of achieving them, will become clear with reference to the detailed description of the following embodiments taken in conjunction with the accompanying drawings. However, the present invention is not limited to the embodiments disclosed below, but may be implemented in various different forms, and only the present embodiments are provided to complete the disclosure of the present invention and to fully inform those skilled in the art of the scope of the invention to which the present invention belongs, and the present invention is only defined by the scope of the claims.

Unless otherwise defined, all terms (including technical and scientific terms) used in this specification may be used in a meaning commonly understood by those of ordinary skill in the art to which the present invention belongs. In addition, terms defined in commonly used dictionaries are not interpreted ideally or excessively unless explicitly specifically defined.

Terminology used herein is for describing the embodiments and is not intended to limit the present invention. In this specification, the singular form also includes the plural form unless otherwise specified in the entry and exit phrase. As used herein, "comprises" and/or "comprising" does not exclude the presence or addition of one or more other elements other than the recited elements.

Hereinafter, embodiments of the present invention will be described with reference to the accompanying drawings. In the drawings, like reference numerals denote like elements.

1 is a diagram showing the configuration of an apparatus for generating learning data of an artificial intelligence model predicting a performance verification result of an automobile part according to an embodiment of the present invention (hereinafter, referred to as a 'learning data generating apparatus').

Referring to FIG. 1 , the learning data generation device 100 includes a data collection unit 110 , a conversion unit 120 and a learning data generation unit 130 .

The data collection unit 110 collects original data necessary for predicting the performance of automobile parts. Examples of the original data include skin data (envelope and vertex weights) of automotive parts created by various types of CAD (Computer-Aided Design)/CAM (Computer-Aided Manufacturing)/CAE (Computer Aided Engineering) software, that is, skin data before conversion to a standard file format and skin data converted to a standard file format. Among the collected skin data, skin data in a standard file format is provided to the learning data generator 130, and skin data in a non-standard file format is provided to a conversion unit 120 to be described later.

The conversion unit 120 converts the skin data provided from the data collection unit 110 into a standard file format. Examples of standard file formats include the STL file format and the IGES file format.

STL (STereoLithography) is a file format of stereo-lithography CAD software, and is a kind of polygon format that expresses the surface of a three-dimensional object, that is, a 3D model composed of countless triangular faces. Since the STL file format is composed of triangular tongues, it is difficult to express curved surfaces, but if you increase the number of divisions of triangles and draw them into more delicate triangles, you can obtain a shape almost similar to a curved surface. In addition to 'STereoLithography', the abbreviation STL is also used as 'Standard Transformation Language', 'Surface Tesselation Language', and 'Standard Triangulation Language'.

IGES (Initial Graphics Exchange Specification) is a standard established by the National Bureau of Standards (NBS) of the US Department of Commerce for the exchange of graphic information in 1980. Hereinafter, IGES will be described in more detail.

IGES aims to provide a neutral data format for digital representation and communication of product definition data. IGES is the most widely used among many neutral file formats developed in many countries around the world, so it can be said to be a de facto world standard. Since version 1.0 of IGES was released in 1980, version 6.0 including solid models was released in 1998.

The basic unit of data expressed in IGES is called an entity, and supported entities can be largely classified into three types: Geometry Entity, Annotation Entity, and Structure Entity.

Geometry entities represent curves, surfaces, and solids, and annotation entities represent annotation-related information such as leaders, dimensions, symbols, and cross-sections. In addition, the structure entity represents the size of a character, the thickness of a line, the definition of a color, a grouping relationship, a finite element model (FEM) element, and the like.

The IGES file format is largely classified into ASCII format and binary format.

ASCII format is divided into fixed line length format and compressed format. The fixed line length format is the most commonly used format, and data is recorded in units of lines consisting of 80 columns, but the file size is large. The compressed ASCII format has the advantage of being able to reduce the size of IGES files created in fixed line length format when the size is an issue. The reason is that the compressed ASCII format can eliminate redundant data by using a notation format that incorporates some paragraphs in the fixed line length format.

Binary format is ASCII format represented as a binary bit string. The binary format consists of a Byte-Oriented structure suitable for transmission of large files.

2 is a diagram showing the configuration of a fixed line length format.

Referring to FIG. 2, the fixed line length format consists of five sections: a Start section, a Global section, a Directory Entry section, a Parameter Data section, and a Terminate section. From column 1 to column 72, various types of information are recorded for each section, and in column 73, a character (one of S, G, D, P, or T) that distinguishes each section is located, and from column 74 to column 80, the sequential number of the section is listed.

The start section is a part that records arbitrary comments on the IGES file that can be read by the user. Arbitrary contents such as file name, data name, creator, creation date, etc. can be recorded.

The global section records information about the system environment in which the IGES file was created. For example, it consists of a total of 24 parameters such as IGES version number, preprocessor version number, file name, file creation date, author, number of integer expression bits, number of exponent digits and significant digits of real number type, measurement unit, maximum line width, etc.

The directory entry section is a part that provides an index for all shape/non-shape entities recorded in a file and records attribute information for these entities. Twenty fields of eight columns record entity type number, pointer to parameter data section, line font, line weight, and color. Since 10 fields make up one line, two lines make up one directory.

In the Parameter Data section, entity numbers, 3D coordinate values, and pointers referring to attributes of entities are recorded for entities recorded in the directory entry section. When several entities are logically combined with each other, a pointer referring to an entity representing an association or non-shape numerical information may be recorded.

The Terminate section consists of a single line and is divided into 10 fields of 8 columns. Section delimiters and line numbers are recorded for the four sections described above.

There are many types of shape entities supported by the IGES file format, and among them, the types and names of some entities are illustrated in FIG. 3 . Among the entities illustrated in FIG. 3, the main shape entities required to determine the area or volume include a Rational B-Spline Curve Entity corresponding to Type 126 and a Rational B-Spline Surface Entity corresponding to Type 128.

Fig. 4 shows the directory entry section and the parameter data section of the Rational B-Spline Curve Entity corresponding to type 126. 5 shows a directory entry section and a parameter data section of a free curved surface entity (Rational B-Spline Surface Entity) corresponding to type 128. Further, the directory entry section and the parameter data section of the trimmed (parametric) surface entity corresponding to type 144 are shown in FIG. 6 .

Referring back to FIG. 1 , the conversion unit 120 converts skin data into one of the standard file formats described above. The standard file format to convert the skin data to can be set by the user in advance, and the set value can be implemented to be changeable. In the following description, a case in which the conversion unit 120 converts skin data into an IGES file format will be described as an example.

The learning data generation unit 130 recognizes shape information from original data in a standard file format or original data converted to a standard file format, and labels the recognized shape information to the original data to generate training data. Labeling refers to the task of creating a correct answer (i.e., a label) for the data used for training of an artificial intelligence model. Since the performance of an AI model tends to improve as the amount of data used for training increases, a large amount of labeled data is required. However, manually labeling a large amount of data is time consuming and costly. In addition, when training with inaccurate labels, the performance of the artificial intelligence model deteriorates, so accurate labeling is important.

According to an embodiment, the learning data generating unit 130 may generate learning data by auto labeling or manual labeling. Alternatively, automatic labeling and manual labeling may be performed in parallel to generate training data. For example, automatic labeling may be performed on a large amount of data, and manual labeling may be performed on data for which labels are difficult to determine as a result of automatic labeling. Which method to use among automatic labeling and manual labeling may be set by a user in advance, and set information may be implemented to be changeable. As shown in FIG. 1 , the learning data generation unit 130 includes a recognizing unit 132 , a screen configuration unit 134 and a label assignment unit 136 .

The recognition unit 132 recognizes information by parsing original data in a standard file format according to a predetermined criterion. Specifically, as described in FIG. 2, the fixed line length format of the IGES file format records data in units of lines consisting of 80 columns. Therefore, if the original data in the standard file format is parsed line by line, information on five sections can be distinguished and recognized. In addition, if each line is parsed in column units, information included in each section, for example, shape information, can be recognized. More specifically, shape information recognition is described. Since the directory entry section includes an index for all shape/non-shape entities recorded in a file, shape information can be recognized from this index. For example, the number '126' (ie, code name) may be recognized as shape information of 'free-form curve', and the number '128' may be recognized as shape information of 'free-form curved surface'.

The screen configuration unit 134 configures a screen including information recognized by the recognition unit 132 . According to an embodiment, a screen may include a plurality of regions, and recognized information is displayed separately in each region. Here, with reference to FIGS. 7 to 9 , the screen configured by the screen configuration unit 134 will be described in more detail.

FIG. 7 is a diagram showing a first area 11, a second area 12, and a third area 13 among screens formed by the screen configuration unit 134. Referring to FIG. Referring to FIG. 7 , start section information is displayed in the first area 11 . The first area 11 may include a 'file name' item. Information of the global section is displayed in the second area 12 . The second area may include a 'field name' item and a 'result value' item. A pie chart related to the information of the parameter data section is displayed in the third area 13 . The pie graph represents the ratio of each entity to all entities, i.e., all entities included in the parameter data section, in the form of a sector. The information displayed on the third area 13 does not necessarily have to be displayed in a circular graph, but may be displayed in a graph of a different shape or expressed in numerical values rather than a graph.

FIG. 8 is a diagram showing a part of the fourth area 14 among the screens formed by the screen configuration unit 134 .

Referring to FIG. 8 , information of a directory entry section is displayed in the fourth area 14 . The fourth area 14 includes 'section_number' items, 'type_kr' items, 'entity_type' items, 'parameter_data' items, 'structure' items, 'line_font_pattern' items, 'level' items, 'view' items, 'transformat_matrix' items, 'label_display_associativity' items, 'line_weight_number' items, 'color_number' items, 'parameter_line_count_number' items, 'form_number' items, and 'ent ity_label', etc. In addition, the fourth region 14 may further include some items not shown in FIG. 8 , for example, a 'status_number' item, an 'entity_subscript' item, and a 'sequence_number' item. Information included in the directory entry section can be displayed separately for each item.

FIG. 9 is a diagram showing a part of the fifth region 15 among the screens formed by the screen configuration unit 134 .

Referring to FIG. 9 , the information of the parameter data section is displayed in the fifth area 15 . The fifth area 15 may include a 'type_kr' item, a 'section_number' item, and a 'data' item. Information included in the parameter data section can be displayed separately for each item.

The areas 11, 12, 13, 14, and 15 shown in FIGS. 7 to 9 may all be displayed on one screen or on different screens. In the latter case, when a user inputs a command while a screen including a specific area is being displayed, a screen including another area is displayed. Also, each of the regions 11, 12, 13, 14, and 15 may be arranged differently from those shown in FIGS. 7 to 9. At least one of the display method and arrangement method of each of the regions 11, 12, 13, 14, and 15 may be set in advance by a user, and the set value may be implemented to be changeable.

Referring back to FIG. 1 , the label assigning unit 136 assigns one or more pieces of shape information recognized by the recognizing unit 132 to the original data as a label. For example, when shape information such as a free curved line and a free curved surface is recognized by the recognizing unit 132, the recognized shape information is given as a label to the original data. In addition, the label assigning unit 136 assigns, as a label, information on a ratio occupied by one or more recognized shape information (ie, entities) of all entities included in the parameter data section to each original data. For example, for all entities included in the parameter data section, if the ratio occupied by the entity 'free-form curve' is 60% and the ratio occupied by the entity 'free-form curved surface' is 10%, this ratio information is given as a label to the original data along with shape information.

In addition, the label assigning unit 136 may assign information input by the user to the original data as a label. Specifically, when a screen including information recognized by the recognition unit 132 is configured by the screen configuration unit 134 and then displayed through a display unit (not shown), the user checks and/or analyzes the data displayed on the screen to determine information to be input (e.g., shape information). Then, by manipulating an input unit (not shown), the determined shape information is input into a specific region (eg, an input field where additional information can be input) of the displayed screen. Then, the labeling unit 136 additionally assigns the shape information input by the user as a label to the original data.

Original data labeled in the above manner may be used as training data for training a predictor (not shown). Here, the prediction unit may be an artificial intelligence model that receives skin data of a predetermined vehicle part and outputs a prediction value for a performance analysis result of the corresponding vehicle part.

Each component of the learning data generating apparatus 100 shown in FIG. 1 may mean software or hardware such as a Field Programmable Gate Array (FPGA) or an Application-Specific Integrated Circuit (ASIC). However, the components are not limited to software or hardware, and may be configured to be in an addressable storage medium or configured to execute one or more processors. Functions provided within the components may be implemented by more subdivided components, or may be implemented as a single component that performs a specific function by combining a plurality of components.

For reference, although the learning data generating device 100 is shown as one physical device in FIG. 1, this is only for convenience of understanding, and according to embodiments, the learning data generating device 100 may be implemented as a system composed of a plurality of computing devices. For example, one or more of the data collection unit 110, the conversion unit 120, and the learning data generation unit 130 may be implemented as an independent computing device. In this case, each computing device may communicate through a network.

In the above, the configuration and operation of the learning data generating apparatus 100 according to an embodiment of the present invention have been described with reference to FIGS. 1 to 9 . Hereinafter, referring to FIG. 10 , an exemplary computing device capable of implementing devices according to some embodiments of the present invention will be described.

10 is a hardware configuration diagram of an exemplary computing device in which devices in accordance with some embodiments of the invention may be implemented.

Referring to FIG. 10, a computing device 200 may include one or more processors 210, a storage 290 for storing a computer program 251, a memory 220 for loading a computer program 251 executed by the processor 210, a bus 230, and a network interface 240. However, only components related to the embodiment of the present invention are shown in FIG. 10 . Accordingly, those skilled in the art to which the present invention pertains can know that other general-purpose components may be further included in addition to the components shown in FIG. 10 .

The processor 210 controls the overall operation of each component of the computing device 200 . The processor 210 may include a central processing unit (CPU), a micro processor unit (MPU), a micro controller unit (MCU), a graphic processing unit (GPU), or any type of processor well known in the art. Also, the processor 210 may perform an operation for at least one application or program for executing a method according to embodiments of the present invention. Computing device 200 may include one or more processors.

The memory 220 stores one or more of various data, commands and information. The memory 220 may load one or more programs 251 from the storage 250 in order to execute the learning data generating method according to embodiments of the present invention. RAM is illustrated as an example of the memory 220 in FIG. 10 .

The bus 230 provides a communication function between components of the computing device 200 . The bus 230 may be implemented as various types of buses such as an address bus, a data bus, and a control bus.

The network interface 240 supports wired and wireless Internet communication of the computing device 200 . Also, the network interface 240 may support various communication methods other than internet communication. To this end, the network interface 240 may include a communication module well known in the art.

Storage 250 may non-temporarily store one or more computer programs 291 . The storage 250 may include a non-volatile memory such as read only memory (ROM), erasable programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), flash memory, etc., a hard disk, a removable disk, or any type of computer-readable recording medium well known in the art to which the present invention pertains.

11 is a flowchart illustrating a method of generating learning data of an artificial intelligence model predicting performance verification results of automobile parts according to an embodiment of the present invention.

First, the learning data generating device 100 collects original data for automobile parts (S710). An example of original data for automobile parts is skin data obtained by 3D modeling of the exterior shape of automobile parts. The skin data includes both skin data converted to a standard file format and skin data before conversion to a standard file format.

Then, the learning data generating device 100 converts the file format of the collected original data into a standard file format. Examples of standard file formats include the STL file format and the IGES file format. Which standard file format to use among the exemplified standard file formats may be set in advance. In addition, the set standard file format can be implemented to be changeable by the user.

Thereafter, the learning data generating device 100 configures and displays a screen including information recognized from the original data in a standard file format (S720). Step 720 includes parsing the original data according to a predetermined criterion and recognizing information about each section, and configuring and displaying a screen displaying the information of each recognized section. Examples of types of recognized information include start section information, global section information, directory entry section information, parameter data section information (entity information included in the parameter data section), and ratio information of each entity to all entities included in the parameter data section.

Thereafter, the learning data generating apparatus 100 assigns the shape information as a label to the original data among the information recognized in step S720 to generate learning data (S730). At this time, in addition to shape information, ratio information of each shape information may be given as a label. In addition, if there is information input from the user in step S720, the input information may also be assigned as a label.

Original data labeled according to the above method, that is, training data, may be used to learn the prediction unit. The prediction unit may be an artificial intelligence model that receives skin data of a predetermined vehicle part and outputs a predicted value for a performance analysis result of the corresponding vehicle part.

In the above, the embodiments of the present invention have been described. In addition to the above-described embodiments, embodiments of the present invention may be implemented through a medium including computer readable codes/instructions for controlling at least one processing element of the above-described embodiments, for example, a computer readable medium. The medium may correspond to a medium/media enabling storage and/or transmission of the computer readable code.

The computer readable code may not only be recorded on a medium, but may also be transmitted through the Internet. The medium may include, for example, a recording medium such as a magnetic storage medium (e.g., ROM, floppy disk, hard disk, etc.) and an optical recording medium (e.g., CD-ROM, Blu-Ray, DVD), and a transmission medium such as a carrier wave. Since the medium may be a distributed network, computer readable code may be stored/transmitted and executed in a distributed manner. Still further, by way of example only, a processing element may include a processor or a computer processor, and the processing element may be distributed and/or included within a device.

Although the embodiments of the present invention have been described with reference to the illustrated drawings as described above, those skilled in the art to which the present invention pertains may understand that the present invention may be embodied in other specific forms without changing the technical spirit or essential features. Therefore, the embodiments described above are illustrative in all respects, and should be understood as non-limiting.

100: learning data generating device
110: data collection unit
120: conversion unit
130: learning data generation unit
200: computing device

Claims (8)

Collecting, by a data collection unit, skin data obtained by 3D modeling an external shape of the automobile part as original data necessary for predicting the performance of the automobile part;
Converting the file format of the collected original data into a standard file format by a conversion unit;
Recognizing information included in the original data of the standard file format by a recognition unit for each of a plurality of sections, recognizing all shape entities and non-shape entities included in the parameter data section among the plurality of recognized sections, Recognizing shape entities among the recognized entities as shape information;
configuring, by a screen composition unit, a screen including at least one area among a plurality of areas in which the information of the plurality of sections is divided and displayed; and
Generating learning data by labeling the recognized shape information to the collected original data;
Wherein the plurality of areas includes at least one of a first area displaying start section information, a second area displaying global section information, a third area displaying ratio information of each entity with respect to all entities included in the parameter data section, a fourth area displaying directory entry section information, and a fifth area displaying parameter data section information. According to claim 1,
The standard file format is
A method of generating training data of an artificial intelligence model that predicts performance verification results of automotive parts, including at least one of a STereoLithography (STL) file format and an Initial Graphics Exchange Specification (IGES) file format. According to claim 1,
The step of generating the learning data is
A method of generating training data of an artificial intelligence model that predicts a performance verification result of an automobile part, comprising assigning at least one of the recognized shape information and ratio information occupied by the shape entity with respect to all entities as a label to the original data. According to claim 1,
At least one of the display method and the arrangement method of the plurality of regions is changeable by a user, a method for generating learning data of an artificial intelligence model predicting a performance verification result of an automobile part. According to claim 1,
If there is information input from the operator through the screen, further comprising assigning the input information as a label to the original data. According to claim 1,
The learning data is
A method of generating learning data of an artificial intelligence model for predicting a performance verification result of an automobile part, which is used to learn a prediction unit that receives the skin data of the automobile part and predicts a performance analysis result of the automobile part. a data collection unit that collects skin data obtained by 3D modeling an external shape of the automobile part as original data necessary for predicting performance of the automobile part;
a conversion unit that converts the file format of the collected original data into a standard file format;
a recognizing unit that classifies and recognizes information included in the original data in the standard file format by a plurality of sections, recognizes all shape entities and non-shape entities included in the parameter data section among the plurality of recognized sections, and recognizes shape entities among the recognized entities as shape information;
a screen configuration unit configuring a screen including at least one area among a plurality of areas in which the information of the plurality of sections is divided and displayed; and
A learning data generation unit configured to generate learning data by labeling the collected original data with the recognized shape information;
The plurality of areas includes at least one of a first area displaying information of a start section, a second area displaying information of a global section, a third area displaying ratio information of each entity with respect to all entities included in the parameter data section, a fourth area displaying information of a directory entry section, and a fifth area displaying information of a parameter data section. Combined with a computing device,
Collecting skin data obtained by 3D modeling an external shape of the automobile part as original data necessary for predicting the performance of the automobile part;
converting the file format of the collected original data into a standard file format;
Recognizing information included in the original data in the standard file format by dividing into a plurality of sections, recognizing all shape entities and non-shape entities included in the parameter data section among the plurality of recognized sections, and recognizing shape entities among the recognized entities as shape information - the plurality of areas include a first area displaying information of a start section among the plurality of sections, a second area displaying information of a global section, and a third area displaying ratio information of each entity with respect to all entities included in the parameter data section, and a directory entry. includes at least one of a fourth area in which section information is displayed, and a fifth area in which parameter data section information is displayed;
configuring, by a screen composition unit, a screen including at least one area among a plurality of areas in which the information of the plurality of sections is divided and displayed; and
A computer program implemented to perform the step of generating learning data by labeling the collected original data with the recognized shape information, and stored in a computer-readable recording medium.