MEHTOD FOR GENERATING A 3d DESIGN MODEL BASED ON LAGACY DRAWINGS AND AN ELECTRONIC DEVICE FOR PERFORMING THEREOF

Abstract

A method for generating a 3D design model based on a legacy drawing according to one embodiment of the present application is characterized by comprising the steps of receiving a legacy drawing, extracting text data included in the legacy drawing, determining location information and image information of text corresponding to the extracted text data, storing the determined location information and image information as metadata of the text data, classifying the text data into part specification data or design data, and mapping the part specification data or design data to the legacy drawing and storing it in a legacy drawing database.

Description

Technology Field

[0001] The present application relates to a method for generating a 3D design model based on legacy drawings and an electronic device for performing the same. Background Technology

[0003] In industrial fields such as plants, power generation facilities, and shipbuilding and offshore structures, two-dimensional (2D) drawing-based design methods have been used for a long time, and these drawings are stored in the form of PDF or CAD files and include both Bill of Materials (BoM) and Design Data.

[0004] However, the vast amount of legacy drawings accumulated within a company differs in format and notation, and the structures of text, dimensions, and symbols are inconsistent, making automatic conversion into 3D design models difficult. Consequently, when designing new projects, inefficiencies arise as existing drawings must be repeatedly referenced or 3D models must be recreated manually.

[0005] Existing 3D CAD systems or PLM solutions focus on 3D shape editing and management functions, and do not provide functions to automatically generate 3D models by extracting text, coordinate, and image information from 2D drawings.

[0006] Therefore, there is a need for technology capable of automatically recognizing meaningful data from existing legacy drawings, structuring it, and converting it into a 3D design model. In particular, there is a growing need for automation technology that can reuse existing drawing assets and improve design efficiency by referencing multiple legacy drawings and interpolating optimal shape parameters according to design conditions. Prior art literature

[0008] KR10-1952518B1 The problem to be solved

[0009] The problem that the present invention aims to solve is to provide a technology that can automatically extract text and design information from legacy 2D drawings, structure them into part specification data and design data, and automatically generate a 3D design model.

[0010] The problems that the present invention aims to solve are not limited to those described above, and problems not mentioned will be clearly understood by those skilled in the art from this specification and the attached drawings. means of solving the problem

[0012] A method for generating a 3D design model based on a legacy drawing according to an embodiment of the present invention may include the steps of receiving a legacy drawing, extracting text data included in the legacy drawing, determining location information and image information of text corresponding to the extracted text data, storing the determined location information and image information as metadata of the text data, classifying the text data into part specification data or design data, and mapping the part specification data or design data to the legacy drawing and storing it in a legacy drawing database.

[0013] An electronic device for generating a 3D design model based on a legacy drawing according to an embodiment of the present invention comprises a communication unit, an input unit, a memory for storing at least one instruction, and a processor for executing said at least one instruction. The at least one instruction may cause the processor to receive a legacy drawing, extract text data included in the legacy drawing, determine location information and image information of the text corresponding to the extracted text data, store said determined location information and image information as metadata for said text data, classify said text data into part specification data or design data, and map said part specification data or design data to said legacy drawing and store it in a legacy drawing database.

[0014] The means for solving the problem of the present invention are not limited to the means for solving the problem described above, and unmentioned means for solving the problem will be clearly understood by those skilled in the art from this specification and the attached drawings. Effects of the invention

[0016] According to one embodiment of the present invention, text, coordinate, and image information from past 2D legacy drawings can be automatically recognized to structure part specification data and design data, thereby enabling the efficient digitization of unstructured drawings.

[0017] In addition, according to one embodiment of the present invention, a three-dimensional design model can be automatically generated based on a constructed legacy drawing database and user design conditions, thereby enabling the reuse of existing drawing assets and improving the efficiency and consistency of design work.

[0018] In addition, according to one embodiment of the present invention, a 3D model optimized for design conditions can be rapidly produced by interpolating shape parameters from a plurality of legacy drawings, thereby ensuring both the accuracy and quality of the new design. Brief explanation of the drawing

[0020] FIG. 1 is a block diagram briefly illustrating the configuration of an electronic device for generating a 3D design model according to one embodiment of the present application. FIG. 2 is a block diagram briefly illustrating the configuration of a processor according to one embodiment of the present application. FIG. 3 is a flowchart illustrating a method for generating a 3D design model based on legacy drawings according to one embodiment of the present application. FIG. 4 is a diagram illustrating the structure of data stored in a legacy drawing database according to one embodiment of the present application. FIG. 5 is a flowchart illustrating a method for generating a 3D design model based on legacy drawings according to one embodiment of the present application. FIG. 6 is a drawing illustrating a screen for receiving design conditions according to one embodiment of the present application. FIG. 7 is a diagram illustrating a parameter table for generating a 3D model according to one embodiment of the present application. FIG. 8 is a drawing illustrating a 3D design drawing according to one embodiment of the present application. Specific details for implementing the invention

[0021] The aforementioned objectives, features, and advantages of the present application will become more apparent from the following detailed description in conjunction with the accompanying drawings. However, as the present application is subject to various modifications and may have various embodiments, specific embodiments are illustrated in the drawings and described in detail below.

[0022] Throughout the specification, identical reference numbers generally represent identical components. Additionally, components with identical functions within the same scope of concept appearing in the drawings of each embodiment are described using the same reference numeral, and redundant descriptions thereof are omitted.

[0023] If it is determined that a detailed description of known functions or configurations related to this application could unnecessarily obscure the essence of this application, such detailed description is omitted. Furthermore, numbers used in the description of this specification (e.g., First, Second, etc.) are merely identifiers to distinguish one component from another.

[0024] Furthermore, the suffixes "module" and "part" for components used in the following embodiments are assigned or used interchangeably solely for the ease of drafting the specification, and do not inherently possess distinct meanings or roles.

[0025] In the following examples, singular expressions include plural expressions unless the context clearly indicates otherwise.

[0026] In the following embodiments, terms such as "include" or "have" mean that the features or components described in the specification are present, and do not preclude the possibility that one or more other features or components may be added.

[0027] In the drawings, the size of components may be exaggerated or reduced for convenience of explanation. For example, the size and thickness of each component shown in the drawings are arbitrarily depicted for convenience of explanation, and the present invention is not necessarily limited to what is illustrated.

[0028] Where an embodiment can be implemented differently, the order of a particular process may be performed differently from the order described. For example, two processes described consecutively may be performed substantially simultaneously or proceed in the reverse order of the description.

[0029] In the following embodiments, when components are described as being connected, the case includes not only instances where the components are directly connected but also instances where components are indirectly connected by interposing them in between.

[0030] For example, when it is stated in this specification that components, etc. are electrically connected, it includes not only cases where the components, etc. are directly electrically connected, but also cases where components, etc. are interposed in between and are indirectly electrically connected.

[0032] Hereinafter, with reference to FIGS. 1 to 8, a method for generating a 3D design model based on the legacy drawings of the present application and an apparatus for performing the same will be described.

[0034] FIG. 1 is a simplified block diagram illustrating the configuration of an electronic device for generating a 3D design model according to one embodiment of the present application. Referring to FIG. 1, the electronic device (100) may include a communication unit (110), an input unit (120), a processor (130), and a memory (140).

[0036] The communication unit (110) can support the establishment of a direct communication channel or a wireless communication channel between the device (100) and an external electronic device, and the performance of communication through the established communication channel. The communication unit (110) may include one or more communication processors that operate independently of the processor (130) and support direct communication or wireless communication.

[0038] The input unit (120) can receive commands or data to be used for a component of the electronic device (100) from outside the electronic device (100) (e.g., a user). The input unit (120) may include, for example, a microphone, a mouse, a keyboard, a key (e.g., a button), or a digital pen (e.g., a stylus pen).

[0040] The processor (130) can execute software to control at least one other component (e.g., a hardware or software component) of the device (100) connected to the processor (120) and can perform various data processing or operations. According to one embodiment, as at least part of the data processing or operations, the processor (120) can store commands or data received from another component (e.g., a communication unit (110)) in volatile memory, process the commands or data stored in volatile memory, and store the resulting data in non-volatile memory. According to one embodiment, the processor (120) may include a main processor (e.g., a central processing unit or an application processor) or an auxiliary processor (e.g., a neural processing unit (NPU), an image signal processor, a sensor hub processor, or a communication processor) that can operate independently or together with it.

[0041] According to one embodiment, an auxiliary processor (e.g., a neural network processing unit) may include a hardware structure specialized for processing an artificial intelligence model. The artificial intelligence model may be generated through machine learning. Such learning may be performed, for example, on the electronic device itself where the artificial intelligence is performed, or through a separate server (e.g., a server (108)). The learning algorithm may include, for example, supervised learning, unsupervised learning, semi-supervised learning, or reinforcement learning, but is not limited to the examples described above. The artificial intelligence model may include a plurality of artificial neural network layers. An artificial neural network may be a deep neural network (DNN), a convolutional neural network (CNN), a recurrent neural network (RNN), a restricted Boltzmann machine (RBM), a deep belief network (DBN), a bidirectional recurrent deep neural network (BRDNN), deep Q-networks, a transformer neural network, or a combination of two or more of the above, but is not limited to the examples described above. In addition to the hardware structure, the artificial intelligence model may include a software structure, either additionally or substantially.

[0043] The processor (130) may receive legacy drawings. For example, legacy drawings may mean 2D or 3D drawing image files (e.g., PDF) or 2D or 3D drawing files of a specific format (e.g., CAD).

[0045] The processor (130) can extract text data contained in the legacy drawing. For example, if the legacy drawing is an image file, the processor (130) can extract text data using optical character recognition (OCR) technology. Additionally, if the legacy drawing is a drawing file, the processor (130) can extract text data using an application program (e.g., LISP) interface (API) corresponding to a specific drawing file.

[0047] The processor (130) can determine location information and image information of the text corresponding to the extracted text data. Here, the location information of the text includes coordinate values ​​of the text data, and the image information of the text may include a preset surrounding area image of the data where the texts exist, as well as top-left and bottom-right coordinate values.

[0049] The processor (130) can store the determined location information and image information as metadata for the text data. Specifically, the processor (130) can store the location information where the text data is placed within the drawing and the image of the area surrounding the text data together with the text data.

[0051] The processor (130) can classify text data into part specification data or design data. Specifically, the processor (130) can determine whether the text corresponds to a part name, quantity, material, specification, or dimension based on the location information of the text and the header information of an adjacent table. For example, if the text corresponds to one of the part name, quantity, material, or specification items, the processor (130) can classify the text as part specification data. Alternatively, if the text corresponds to a dimension item, the processor (130) can classify the text as design data.

[0053] The processor (130) can map part specification data or design data to legacy drawings and store them in a legacy drawing database. In this case, the legacy drawing database may be a non-relational database structured in a specific format (e.g., JSON).

[0055] The processor (130) can receive design conditions from the user. Specifically, the processor (130) can receive at least some of the dimensions, material, temperature, pressure, or weight information of a part for creating a 3D design model from the user.

[0057] The processor (130) can search for legacy drawings corresponding to design conditions entered by the user in the legacy drawing database. Specifically, the processor (130) can search for multiple legacy drawings corresponding to design conditions entered by the user in the legacy drawing database. Then, the processor (130) can determine the legacy drawing with the highest similarity among the multiple legacy drawings found as the reference legacy drawing.

[0059] The processor (130) can generate a 3D design model based on part specification data and design data mapped to the retrieved legacy drawings. Specifically, the processor (130) can identify part specification data and design data mapped to the reference legacy drawings. Additionally, the processor (130) can generate a 3D design model based on the part specification data and design data mapped to the reference legacy drawings. Furthermore, the processor (130) can correct the 3D design model based on the design data mapped to the retrieved multiple legacy drawings.

[0061] The memory (140) can store various data used by at least one component of the electronic device (100). The data may include, for example, input data or output data for software and related commands. The memory (140) may include volatile memory or non-volatile memory.

[0063] FIG. 2 is a block diagram briefly illustrating the configuration of a processor according to one embodiment of the present application. Referring to FIG. 2, the processor (130) may include a legacy drawing data extraction unit (131), a legacy drawing database construction unit (133), and a 3D design model generation unit (135).

[0065] The legacy drawing data extraction unit (131) can extract text data included in the legacy drawing from the legacy drawing, determine location information and image information of the text data, and store the determined location information and image information of the text data as metadata for the text data. If the legacy drawing is an image file (e.g., a PDF file) that has been scanned from the drawing, the legacy drawing data extraction unit (131) can recognize characters, numbers, symbols, and table division lines included in the legacy drawing using Optical Character Recognition (OCR) technology. If the legacy drawing is a drawing file in a digital format (e.g., a CAD file), the legacy drawing data extraction unit (131) can call an application program interface (e.g., LISP) corresponding to the drawing file to extract attribute data of the drawing object, text objects, coordinates, linear information, and layer information. Accordingly, the legacy drawing data extraction unit (131) can extract the same data structure regardless of whether the legacy drawing is paper-based or digital-based.

[0066] The legacy drawing data extraction unit (131) can determine location information of text data. Specifically, when text data is extracted using an OCR method, the legacy drawing data extraction unit (131) can determine the boundary area of ​​the text data by determining the coordinate values ​​that the text occupies within the drawing based on absolute coordinates in the image pixel unit. Additionally, when text data is extracted using a CAD method, the legacy drawing data extraction unit (131) can determine the boundary area of ​​the text data by determining the coordinate values ​​that the text occupies within the drawing using the insertion point of the drawing object and the height and width of the text. Here, the location information can be utilized in a subsequent step for analyzing row and column relationships between texts or for analyzing semantic connections with table headers.

[0067] The legacy drawing data extraction unit (131) can determine image information of text data. Specifically, the legacy drawing data extraction unit (131) can determine an image of the surrounding area of ​​the text data.

[0068] The legacy drawing data extraction unit (131) can generate metadata for the text data based on location information and image data of the text data. Specifically, the legacy drawing data extraction unit (131) can generate metadata by collecting location information and image information containing images of surrounding drawing areas containing the text together with the extracted text data. For example, the legacy drawing data extraction unit (131) can store the text string, coordinate information, and image arrangement (Base64 encoded image data) on the drawing together for the extracted texts. The stored metadata can be used in subsequent steps to determine not only what the text data is simply a string, but also what design meaning it has based on the surrounding table structure or geometric composition. That is, the legacy drawing data extraction unit (131) can reconstruct unstructured legacy drawing data into structured input data that an artificial intelligence model can learn by extracting text data, location information, and image information from the input legacy drawing.

[0070] The legacy drawing database construction unit (133) classifies text data into part specification data and design data based on text data extracted from the legacy drawing data extraction unit (131) and corresponding metadata, and can construct a legacy drawing database by mapping the classified part specification data and design data to the corresponding legacy drawings. Specifically, the legacy drawing database construction unit (133) can determine the relative arrangement relationship of text data based on location information and image information of each text data. At this time, the legacy drawing database construction unit (133) can determine that text data located in the same row constitutes data that makes up the same part unit, and that text data located in the same column corresponds to data that corresponds to the same item (e.g., part name, material, quantity, etc.). The legacy drawing database construction unit (133) can determine the table structure within the drawing based on the relative arrangement relationship of the text data and determine the semantic correspondence relationship of the texts contained in each cell of the table.

[0071] The legacy drawing database construction unit (133) can determine whether each piece of text data corresponds to part specification data or design data. Specifically, the legacy drawing database construction unit (133) can determine whether the text data corresponds to part specification data or design data based on the structural pattern of the drawing (e.g., the position of the table header, column spacing, text alignment direction, etc.). For example, if a “quantity” header exists around the string “100,” the legacy drawing database construction unit (133) can determine the string 100 as part quantity and determine it as part specification data. Alternatively, if “length” or “pipe diameter” is adjacent to the string “100,” the legacy drawing database construction unit (133) can determine the string 100 as pipe dimension and determine it as design data.

[0072] The legacy drawing database construction unit (133) can perform mapping between text data classified into part specification data and design data and legacy drawings. For example, the legacy drawing database construction unit (133) can perform mapping by connecting an image area containing the corresponding text data to the coordinate system of the legacy drawing based on the location information of the text data. After performing mapping, the legacy drawing database construction unit (133) can assign a unique identifier to each legacy drawing and convert the part specification data and design data of each legacy drawing into a structured data format based on a specific format (e.g., JSON) and store it in the legacy drawing database. In addition, the legacy drawing database construction unit (133) can also store attribute information such as the filename, creation date, format (PDF or CAD), and drawing type (piping drawing, assembly drawing, etc.) of the legacy drawing to facilitate searching or management in subsequent steps.

[0073] The legacy drawing database construction unit (133) may determine the similarity between legacy drawings of the same format and cluster legacy drawings having similar structures. For example, the legacy drawing database construction unit (133) may manage legacy drawings of the same equipment group or the same part series as one group.

[0074] The legacy drawing database construction unit (133) can detect and correct cases where text data is stored redundantly or coordinate values ​​conflict with each other, and can improve accuracy through an artificial intelligence-based correction logic in cases where OCR recognition errors or incorrect location information are included. Accordingly, the legacy drawing database construction unit (133) can convert unstructured legacy drawings into structured data that can be utilized by an artificial intelligence model, and can provide basic data for creating a 3D design model in the 3D design model unit (135).

[0076] The 3D design model generation unit (135) can generate a 3D design model corresponding to design conditions input by a user based on part specification data and design data stored in a legacy drawing database. Specifically, the 3D design model generation unit (135) can receive design conditions from a user through a graphical user interface (GUI). Here, the design conditions may include design parameters such as pipe diameter, length, pressure, temperature, material, valve type, flange specifications, etc., and an importance (weight) may be set for each design parameter.

[0077] The 3D design model generation unit (135) can search for legacy drawings corresponding to design conditions entered by the user in the legacy drawing database. Specifically, the 3D design model generation unit (135) can search for multiple legacy drawings corresponding to design conditions in the legacy drawing database based on similarity with the design conditions. For example, the 3D design model generation unit (135) can determine the similarity between the design conditions and the legacy drawings based on multidimensional feature vectors such as similarity of part configuration, drawing type, and design purpose. The 3D design drawing generation unit (135) can calculate weights among the multiple legacy drawings according to the entered design conditions and determine the drawing with the highest weight as the reference legacy drawing.

[0078] The 3D design model generation unit (135) can generate a 3D design model based on part specification data and design data mapped to a determined reference legacy drawing. Specifically, the 3D design model generation unit (135) can determine the type, material, specifications, quantity, etc. of each part constituting the 3D design model from the part specification data mapped to the reference legacy drawing, and can determine shape parameters such as the position, distance, angle, and height of each part from the design data. The 3D design model generation unit (135) can obtain the basic shape of each part from a library using the determined data, and can construct a basic 3D shape (basic skeleton model) by placing the corresponding part based on the design data.

[0079] The 3D design model generation unit (135) can generate a 3D design model by interpolating the parameters of a basic 3D shape by referring to the searched multiple legacy drawings and mapped design data. For example, if the numerical values ​​of the same part, such as length, angle, and radius of curvature, differ in the searched multiple legacy drawings, the 3D design model generation unit (135) can calculate each parameter value using a weighted average or curve interpolation method based on the input design conditions and the similarity weights of each legacy drawing. In addition, for categorical data such as valve type or flange grade, the 3D design model generation unit (135) can calculate the optimal value of the parameter using a probabilistic selection method.

[0080] The 3D design model generation unit (135) can determine the final shape of each part based on the optimal value of the calculated parameters and verify whether there is interference between shapes or violation of constraints. For example, if the 3D design model generation unit (135) does not satisfy standard constraints such as the minimum bending radius of the pipe, the flange connection spacing, and the valve installation direction, the shape can be modified by adjusting it to a value within the allowable range.

[0081] Once verification is complete, the 3D design model generation unit (135) can generate a 3D design model by integrating the parameters of all parts. The 3D design model generation unit (135) can display the generated 3D design model in the form of a drawing and can output it in a file format that can be used in various 3D design software.

[0082] Additionally, the 3D design model generation unit (135) stores the generated 3D design model in a legacy drawing database so that it can be used as additional training data when generating a 3D design model with the same or similar conditions in the future. Accordingly, the 3D design model unit (135) can automatically generate a 3D design model corresponding to the user's input conditions based on the legacy drawing database.

[0084] FIG. 3 is a flowchart illustrating a method for generating a 3D design model based on legacy drawings according to an embodiment of the present application. The operations in FIG. 3 are not limited in order, and additional operations may be performed between two adjacent operations. Furthermore, at least some of the operations in FIG. 3 may be omitted. In the present invention, the expression that an electronic device (100) performs a specific operation may mean that a processor (130) of the electronic device (100) performs a specific operation, or that the processor (130) controls other hardware to perform a specific operation.

[0085] FIG. 3 will be explained in more detail with reference to FIG. 4. FIG. 4 is a diagram for explaining the structure of data stored in a legacy drawing database according to one embodiment of the present application.

[0087] Referring to FIG. 3, the electronic device (100) can receive a legacy drawing (S1000). For example, the legacy drawing may be an image file scanned from a paper drawing or a digital drawing in CAD format.

[0089] The electronic device (100) can extract text data included in the legacy drawing (S2000). If the input legacy drawing is an image file, the electronic device (100) can recognize characters, numbers, symbols, etc. by applying Optical Character Recognition (OCR) technology. During the OCR process, the electronic device (100) can divide the recognition area of ​​the legacy drawing into blocks and then separate text and non-text areas using line segments, shape boundaries, etc., relative to the background of each block. If the input legacy drawing is a digital drawing, the electronic device (100) can directly obtain attribute data of the legacy drawing object using an Application Programming Interface (API) (e.g., AutoCAD LISP). The electronic device (100) can obtain not only text objects (TEXT, NTEXT) but also additional information such as layer information to which the object belongs, color, font size, and rotation angle from the attribute data.

[0091] The electronic device (100) can determine location information and image information of the text corresponding to the extracted text data (S3000). Specifically, the electronic device (100) can determine location information by calculating coordinate values ​​for each of the recognized text data. Additionally, the electronic device (100) can determine image information including a surrounding area containing the text. Specifically, the electronic device (100) can capture the image portion of the corresponding area based on the text's coordinate values ​​and recognize the table structure or line, symbol information to which the text belongs.

[0092] The electronic device (100) can filter out duplicate characters, noise, and data with low recognition reliability, and perform preprocessing to primarily distinguish between the part specification data area and the design data area by referring to the drawing location where the text is placed and keywords.

[0094] The electronic device (100) can store determined location information and image information as metadata for text data (S4000). For example, the metadata may include text strings, coordinate values, image areas, font information, recognition reliability, etc., and may indicate which visual and spatial context the text data belongs to within a legacy drawing.

[0096] The electronic device (100) can classify text data into part specification data or design data (S5000). Specifically, the electronic device (100) can classify whether the text data is part specification data or design data by determining the meaning of the text based on the text data and metadata. The electronic device (100) can classify text data placed in a table in which columns such as part name, quantity, and material are detected as part specification data based on the structure of the table in the drawing, the relative distance between the header and the corresponding text data, and the alignment direction of the text data, and classify text data placed in a table containing columns such as dimensions, pressure, temperature, and coordinates as design data.

[0098] The electronic device (100) can map part specification data or design data to legacy drawings and store them in a legacy drawing database (S6000). At this time, specific areas of legacy drawing images and part or design information can be linked based on location information of text data. The legacy drawing database may be a non-relational database structured in a specific format. For example, as shown in FIG. 4, each legacy drawing has a unique identifier, and part specification data, design data, location of each text, image information, etc. corresponding to the legacy drawing can be stored in a JSON-based structure. Through this data structure, the electronic device (100) can easily perform search, classification, and similarity analysis at the drawing level.

[0100] FIG. 5 is a flowchart illustrating a method for generating a 3D design model based on legacy drawings according to one embodiment of the present application. The operations in FIG. 5 are not limited in order, and additional operations may be performed between two adjacent operations. Furthermore, at least some of the operations in FIG. 5 may be omitted.

[0101] FIG. 5 will be explained in more detail with reference to FIGS. 6 to 8. FIG. 6 is a drawing illustrating a screen for receiving design conditions according to one embodiment of the present application. FIG. 7 is a drawing illustrating a parameter table for generating a 3D model according to one embodiment of the present application. FIG. 8 is a drawing illustrating a 3D design drawing according to one embodiment of the present application.

[0103] Referring to FIG. 5, the electronic device (100) can receive design conditions from the user (S7000). The design conditions may include pipe diameter, length, radius of curvature, material, pressure rating, temperature, valve type, flange rating, support options, placement constraints (minimum spacing, no-interference zone), and weights for each item. For example, as shown in FIG. 6, project-specific design conditions can be received through an electronic GUI.

[0105] The electronic device (100) can search for legacy drawings corresponding to design conditions entered in the legacy drawing database (S8000). For example, the electronic device (100) can search the legacy drawing database by converting design conditions entered by the user into a standardized condition vector. Specifically, the electronic device (100) can exclude unsuitable legacy drawings by applying a filter to items that conflict with the design conditions (e.g., DN, material group, pressure class, etc.). Then, the electronic device (100) can calculate a similarity score for the remaining legacy drawings by calculating the difference between the condition vector, drawing specification data, and design data as a normalized distance and reflecting user weights. Then, the electronic device (100) can determine the top K drawings with the highest similarity as reference legacy drawings.

[0107] The electronic device (100) can generate a 3D design model based on part specification data and design data mapped to retrieved legacy drawings (S9000). Specifically, the electronic device (100) can generate a 3D design model by constructing a basic 3D model, performing parameter interpolation and correction based on a plurality of retrieved legacy drawings, and finalizing a parameter table.

[0108] The electronic device (100) can set the drawing with the highest similarity weight as the base legacy drawing and construct a base 3D design model (skeleton model) based on the part specification data and design data of the base legacy drawing. The electronic device (100) can determine the type, material, specifications, and quantity of parts based on the part specification data and determine shape parameters such as the position, angle, distance, and height between parts based on the design data. The electronic device (100) can obtain part templates (e.g., pipes, valve shapes, flanges, etc. by DN) from a part library.

[0109] The electronic device (100) can calculate a final candidate value by similarity-weighted interpolating the corresponding values ​​of multiple legacy drawings retrieved for continuous parameters (length, angle, radius of curvature, thickness, etc.) of a basic 3D design model. The electronic device (100) can determine categorical parameters (valve type, flange grade, joint method, material group, etc.) by similarity-weighted majority voting or probabilistic selection.

[0110] The electronic device (100) can determine a parameter table based on the interpolated and corrected results. For example, the parameters can have various values ​​as shown in FIG. 7. The electronic device (100) can generate a parametric 3D design model based on the determined parameter table.

[0111] The electronic device (1000) can visualize the generated 3D design model or output it in a CAD exchange format. For example, FIG. 8 illustrates an example of a 3D design drawing.

[0113] The features, structures, effects, etc. described in the embodiments above are included in at least one embodiment of the present invention and are not necessarily limited to only one embodiment. Furthermore, the features, structures, effects, etc. exemplified in each embodiment may be combined or modified and implemented in other embodiments by a person skilled in the art to which the embodiments belong. Accordingly, details regarding such combinations and modifications should be interpreted as being included within the scope of the present invention.

[0114] Furthermore, although the embodiments have been described above, this is merely illustrative and does not limit the invention. Those skilled in the art will understand that various modifications and applications not exemplified above are possible within the scope of the essential characteristics of the embodiments. In other words, each component specifically shown in the embodiments may be modified and implemented. Differences related to such modifications and applications should be interpreted as being included within the scope of the invention as defined in the appended claims. Explanation of the symbols

[0116] 100: Electronic device 110: Communications Department 120: Input section 130: Processor 140: Memory

Claims

Claim 1 A method for generating a 3D design model based on legacy drawings, comprising: receiving a legacy drawing; extracting text data included in the legacy drawing; determining location information and image information of text corresponding to the extracted text data; storing the determined location information and image information as metadata of the text data; classifying the text data into part specification data or design data; mapping the part specification data or design data to the legacy drawing and storing it in a legacy drawing database; receiving design conditions from a user; searching for a plurality of legacy drawings corresponding to the input design conditions in the legacy drawing database; generating a 3D design model based on part specification data and design data mapped to the legacy drawing with the highest similarity to the design conditions among the plurality of legacy drawings; and correcting the 3D design model based on the design data mapped to the plurality of legacy drawings. Claim 2 delete Claim 3 A method for generating a 3D design model according to claim 1, wherein the position information of the text includes the coordinate values ​​of the text data, and the image information of the text includes a preset surrounding area image of the data where the texts exist, and the top-left coordinate values ​​and bottom-right coordinate values. Claim 4 A method for generating a 3D design model according to claim 1, wherein the step of classifying into part specification data or design data comprises the step of determining which item among part name, quantity, material, specification, or dimension the text corresponds to based on location information of the text and header information of an adjacent table. Claim 5 A method for generating a 3D design model according to claim 4, comprising: a step of classifying the text as part specification data if the text corresponds to one of the items of part name, quantity, material, or specification; and a step of classifying the text as design data if the text corresponds to a dimension item. Claim 6 A method for generating a 3D design model, wherein the legacy drawing database is a non-relational database structured in JSON format in claim 1. Claim 7 A method for generating a 3D design model according to claim 1, wherein the design conditions include design parameters including the dimensions of the part, the material of the part, the pressure rating of the part, and the flange rating of the part, and weights of the design parameters. Claim 8 delete Claim 9 delete Claim 10 An electronic device for generating a 3D design model based on a legacy drawing, comprising: a communication unit; an input unit; and a memory for storing at least one instruction; An electronic device comprising: a processor that executes at least one instruction; wherein the at least one instruction comprises the processor receiving a legacy drawing, extracting text data included in the legacy drawing, determining location information and image information of the text corresponding to the extracted text data, storing the determined location information and image information as metadata of the text data, classifying the text data into part specification data or design data, mapping the part specification data or design data to the legacy drawing and storing it in a legacy drawing database, receiving design conditions from a user, searching for a plurality of legacy drawings corresponding to the input design conditions in the legacy drawing database, generating a 3D design model based on the part specification data and design data mapped to the legacy drawing with the highest similarity to the design conditions among the plurality of legacy drawings, and correcting the 3D design model based on the design data mapped to the plurality of legacy drawings.

Images