Method and Apparatus for Providing a Cloud-Based Drawing Management User Interface Using Generative AI

Abstract

The present invention provides a method for providing a cloud-based drawing management user interface using generative artificial intelligence, performed by a service server, comprising: a step of extracting attribute values ​​for a drawing uploaded to the service server using generative artificial intelligence; a step of providing the extracted automatic attribute values ​​to a user together with the drawing; a step of displaying the extracted automatic attribute values ​​in a first expression format different from user input attribute values ​​entered by the user; and a step of changing the extracted attribute values ​​to a second expression format when the extracted automatic attribute values ​​are modified or confirmed by the user.

Description

Technology Field

[0001] The present invention relates to a cloud-based drawing management system, and more specifically, to a method for providing a cloud-based drawing management user interface that supports efficient user review, modification, and verification tasks by using generative artificial intelligence to automatically extract attribute values ​​included in a drawing and visually distinguishing and providing the status of the extracted attribute values ​​through a user interface, and a program for executing the same. Background Technology

[0003] Conventional drawing management systems faced problems where identifying incorrect information or user verification procedures were cumbersome and inefficient, as attribute information such as text, dimensions, and symbols contained within drawings was extracted manually or simple OCR-based extraction results were provided to users in bulk. Furthermore, since automatically extracted information and information entered or modified by users were displayed in the same manner, it was difficult to distinguish the source and reliability of the two types of information.

[0004] As a result, there were various limitations regarding the accuracy and speed of drawing attribute reviews, particularly in data quality management in collaborative environments. Specifically, even when the accuracy of automatically extracted information is low, no user guidance or visual emphasis is provided; furthermore, during the review process of large volumes of drawings, there is a lack of features such as selective filtering of attribute information, batch verification, and accuracy-based classification, which makes it unsuitable for practical application. Prior art literature

[0006] Korean Registered Patent No. 10-1995046 (June 25, 2019) The problem to be solved

[0007] The present invention aims to provide a user interface that can enhance the reliability and management efficiency of drawing attribute information by solving the above problems through the use of generative artificial intelligence to automatically extract attribute values ​​of a drawing, visualize them in different representation formats according to the state and accuracy of the attributes, and dynamically switch the state based on whether the user inputs, confirms, or modifies the information.

[0008] The purpose of the present invention is not limited to the above matters and may include various technical problems identified by the embodiments of this specification. means of solving the problem

[0010] A method for providing a cloud-based drawing management user interface using generative artificial intelligence according to one embodiment of the present specification may be performed by a service server, and the method comprises: a step of extracting attribute values ​​for a drawing uploaded to the service server using generative artificial intelligence; a step of providing the extracted automatic attribute values ​​to a user together with the drawing; a step of displaying the extracted automatic attribute values ​​in a first expression format different from user input attribute values ​​entered by the user; and a step of changing the extracted attribute values ​​to a second expression format when the extracted automatic attribute values ​​are modified or confirmed by the user.

[0011] In one embodiment, the user input attribute value refers to an attribute value directly entered by the user and is displayed in a second expression format different from the first expression format, and the automatic attribute value may have a modifiable text attribute.

[0012] In one embodiment, the automatic attribute value has two or more expression formats based on accuracy, and the accuracy is determined based on drawing-related information calculated by the generative artificial intelligence, wherein the drawing-related information may include one or more of a drawing image, metadata of a drawing file, and communication information related to the drawing.

[0013] In one embodiment, a plurality of automatic attribute values ​​are provided to the user, and automatic attribute values ​​included within a two-dimensional area set by the user can be automatically processed as confirmed by the user.

[0014] In one embodiment, the two or more expression forms include a first expression form and a third expression form, and the third expression form may have an automatic attribute value included in an accuracy range lower than that of the first expression form.

[0015] In one embodiment, the automatic attribute value having the third expression format may be changed to a user input attribute value only after being verified or modified by multiple users.

[0016] In one embodiment, the method may further include the step of connecting a drawing uploaded to the service server with a file other than the drawing; and the step of specifying one or more relationships among an assembly / part, an attachment file, and a site image based on the cross-reference characteristics of the drawing and the other file in the connection step.

[0017] In one embodiment, the method may further include the step of visually displaying the connection status between the drawing and the other file on a user interface according to the specified relationship; and the step of filtering and providing a file list based on the specified relationship.

[0018] A computer program according to one embodiment of the present specification is combined with hardware and stored on a computer-readable recording medium and may include instructions for executing the method described above. Effects of the invention

[0020] According to the present invention, attribute values ​​automatically extracted from a drawing through generative artificial intelligence are displayed together on a drawing interface, and the attribute values ​​can be provided in different visual representation formats depending on whether they are automatically extracted values, user input values, or user confirmation values. Through this, the user can clearly recognize the source or status of the attributes and intuitively identify items that require editing or review.

[0021] In addition, the automatically extracted values ​​can be subdivided into multiple expression formats (e.g., first expression format, third expression format) according to the level of accuracy, and the accuracy can be calculated by analyzing drawing images, file metadata, related communication information, etc. Based on this, the system may include a structure that highlights items with low accuracy to the user or requires confirmation from multiple users.

[0022] In addition to checking attribute values ​​individually, users can specify a specific 2D area of ​​the drawing to collectively check attributes within that area, thereby simplifying the iterative review process.

[0023] Furthermore, the present invention provides an integrated process for visualizing, editing, and reviewing drawing attribute information, and since this function can be implemented in the form of a program stored on a computer-readable recording medium, it can be easily utilized in various client environments.

[0024] It should be understood that the effects of this specification are not limited to the matters described above and can be extended to various contents that can be derived from the detailed description of the embodiments of the invention below. Brief explanation of the drawing

[0026] FIG. 1 is a drawing illustrating an example of an operating environment of a system according to one embodiment of the present invention. FIG. 2 is a block diagram for explaining the internal configuration of a computing device (200) according to one embodiment of the present invention. FIG. 4 is an example of a web-based drawing management service according to an embodiment of the present specification. FIG. 5 shows a user's personal storage drawing file storage (50) according to one embodiment of the present specification. Figure 6 shows an example of providing various versions for a single drawing. FIG. 7 illustrates an example of changing a plurality of attribute information into a user verification state according to one embodiment of the present specification. FIG. 8 is a diagram illustrating a method of sharing drawings at least partially according to one embodiment of the present specification. FIG. 9 is a drawing for explaining a drawing comparison function according to an embodiment of the present invention. FIG. 10 is a drawing illustrating a function to provide a user with a comparison result between two drawings in the form of attributes of a component, according to an embodiment of the present invention. FIGS. 11 and FIGS. 12 are flowcharts of a web-based drawing management method using generative artificial intelligence according to different embodiments of the present specification. FIG. 13 is a conceptual diagram illustrating a method of visualizing a plurality of drawings by hierarchically linking them according to one embodiment of the present specification. FIG. 14 shows a hierarchical management user interface of the drawing according to one embodiment of the present specification. FIG. 15 is a figure showing the relationship between a figure and other elements according to one embodiment of the present specification. FIG. 16 is a figure for explaining the attribute preview function of a drawing according to one embodiment of the present specification. Specific details for implementing the invention

[0027] In describing the embodiments of this specification, if it is determined that a detailed description of known configurations or functions could obscure the essence of the embodiments of this specification, such detailed description is omitted. Additionally, parts of the drawings unrelated to the description of the embodiments of this specification have been omitted, and similar parts are denoted by similar reference numerals.

[0028] In the embodiments of this specification, when a component is described as being "connected," "combined," or "joined" with another component, this may include not only a direct connection but also an indirect connection in which another component exists in between. Furthermore, when a component is described as "comprising" or "having" another component, this means that, unless specifically stated otherwise, it does not exclude the other component but may include additional components.

[0029] In the embodiments of this specification, terms such as first, second, etc. are used solely for the purpose of distinguishing one component from another component and do not limit the order or importance of the components unless specifically stated otherwise. Accordingly, within the scope of the embodiments of this specification, the first component in an embodiment may be referred to as the second component in another embodiment, and likewise, the second component in an embodiment may be referred to as the first component in another embodiment.

[0030] In the embodiments of this specification, distinct components are intended to clearly explain their respective features and do not imply that the components are necessarily separated. That is, multiple components may be integrated to form a single hardware or software unit, or a single component may be distributed to form multiple hardware or software units. Therefore, such integrated or distributed embodiments are included within the scope of the embodiments of this specification, even if not otherwise mentioned.

[0031] In this specification, the term "network" may encompass both wired and wireless networks. In this context, the network may refer to a communication network where data exchange between devices, systems, and devices can be performed, and is not limited to a specific network.

[0032] The embodiments described herein may have aspects that are entirely hardware, partially hardware and partially software, or entirely software. In this specification, terms such as “unit,” “device,” or “system” refer to computer-related entities, such as hardware, a combination of hardware and software, or software. For example, in this specification, a unit, module, device, or system, etc., may be, but are not limited to, a running process, processor, object, executable, thread of execution, program, and / or computer. For example, both an application running on a computer and the computer may correspond to a unit, module, device, or system, etc., in this specification.

[0033] Furthermore, in this specification, the term "device" may refer not only to mobile devices such as smartphones, tablet PCs, wearable devices, and Head Mounted Displays (HMDs), but also to fixed devices such as PCs or home appliances equipped with display functions. Additionally, as an example, the term "device" may refer to an in-vehicle cluster or an IoT (Internet of Things) device. In other words, in this specification, the term "device" may refer to any device capable of running an application and is not limited to a specific type. For convenience of explanation, the term "device" is used below to refer to a device on which an application runs.

[0034] In this specification, the communication method of the network is not limited, and connections between each component may not be connected using the same network method. The network may include not only communication methods utilizing communication networks (e.g., mobile communication networks, wired internet, wireless internet, broadcasting networks, satellite networks, etc.) but also short-range wireless communication between devices. For example, the network may include any communication method that allows objects to network with each other and is not limited to wired communication, wireless communication, 3G, 4G, 5G, or any other method. For example, wired and / or networks include Local Area Network (LAN), Metropolitan Area Network (MAN), Global System for Mobile Network (GSM), Enhanced Data GSM Environment (EDGE), High Speed ​​Downlink Packet Access (HSDPA), Wideband Code Division Multiple Access (W-CDMA), Code Division Multiple Access (CDMA), Time Division Multiple Access (TDMA), Bluetooth, Zigbee, Wi-Fi, VoIP (Voice over Internet Protocol), LTE Advanced, IEEE802.16m, WirelessMAN-Advanced, HSPA+, 3GPP Long Term Evolution (LTE), Mobile WiMAX (IEEE 802.16e), UMB (formerly EV-DO Rev. C), Flash-OFDM, iBurst and MBWA (IEEE 802.20) A communication network may be referred to by one or more communication methods selected from the group consisting of systems, HIPERMAN, Beam-Division Multiple Access (BDMA), Wi-MAX (World Interoperability for Microwave Access) and ultrasonic communication, but is not limited thereto.

[0035] The components described in the various embodiments do not necessarily mean essential components, and some may be optional components. Accordingly, embodiments consisting of a subset of the components described in the embodiments are also included within the scope of the embodiments of this specification. Furthermore, embodiments including other components in addition to the components described in the various embodiments are also included within the scope of the embodiments of this specification.

[0036] Hereinafter, embodiments of the present specification will be examined in detail with reference to the drawings.

[0037] FIG. 1 is a diagram illustrating an example of an operating environment of a system according to an embodiment of the present invention. Referring to FIG. 1, a user device (110) and one or more servers (120, 130, 140) are connected through a network (1). FIG. 1 is an example for explaining the invention, and the number of user devices or servers is not limited to that shown in FIG. 1.

[0038] The user device (110) may be a fixed terminal or a mobile terminal implemented as a computer system. The user device (110) may be, for example, a smartphone, a mobile phone, a navigation system, a computer, a laptop, a digital broadcasting terminal, a PDA (Personal Digital Assistants), a PMP (Portable Multimedia Player), a tablet PC, a game console, a wearable device, an IoT (Internet of Things) device, a VR (Virtual Reality) device, an AR (Augmented Reality) device, etc. For example, in the embodiments, the user device (110) may refer to one of various physical computer systems capable of communicating with other servers (120-140) via a network (1) using substantially wireless or wired communication methods.

[0039] Each server may be implemented as a computer device or a plurality of computer devices that communicate with a user device (110) via a network (1) to provide commands, code, files, content, services, etc. For example, the server may be a system that provides each service to a user device (110) connected via the network (1). As a more specific example, the server may provide the service intended by the application (e.g., providing information) to the user device (110) through an application that is a computer program installed and running on the user device (110). As another example, the server may distribute a file for the installation and operation of the above-mentioned application to the user device (110) and receive user input information to provide a corresponding service.

[0040] FIG. 2 is a block diagram for explaining the internal configuration of a computing device (200) according to an embodiment of the present invention. This computing device (200) can be applied to the user device (110) or server (120-140) described above with reference to FIG. 1, and each device and server may have the same or similar internal configuration by adding or excluding some components.

[0041] Referring to FIG. 2, the computing device (200) may include memory (210), a processor (220), a communication module (230), and a transceiver (240). The memory (210) is a non-transient computer-readable recording medium and may include a permanent mass storage device such as RAM (random access memory), ROM (read only memory), a disk drive, an SSD (solid state drive), or a flash memory. Here, a permanent mass storage device such as a ROM, SSD, flash memory, or a disk drive may be included in the aforementioned device or server as a separate permanent storage device distinct from the memory (210). Additionally, the memory (210) may store an operating system and at least one program code (e.g., code for a browser installed and running on a user device (110), or code for an application installed on a user device (110), etc., to provide a specific service). These software components may be loaded from a computer-readable recording medium separate from memory (210). This separate computer-readable recording medium may include computer-readable recording media such as a floppy drive, disk, tape, DVD / CD-ROM drive, memory card, etc.

[0042] In another embodiment, software components may be loaded into memory (210) via a communication module (230) rather than a computer-readable recording medium. For example, at least one program may be loaded into memory (210) based on a computer program (e.g., the application described above) that is installed by files provided through a network (1) by developers or a file distribution system (e.g., the server described above) that distributes installation files for the application.

[0043] The processor (220) may be configured to process instructions of a computer program by performing basic arithmetic, logic, and input / output operations. Instructions may be provided to the processor (220) by memory (210) or a communication module (230). For example, the processor (220) may be configured to execute instructions received according to program code stored in a recording device such as memory (210).

[0044] The communication module (230) can provide a function for the user device (110) and the server (120-140) to communicate with each other through the network (1), and each of the device (110) and / or the server (120-140) can provide a function for communicating with other electronic devices.

[0045] The transmitting and receiving unit (240) may be a means for interfacing with an external input / output device (not shown). For example, the external input device may include devices such as a keyboard, mouse, microphone, camera, etc., and the external output device may include devices such as a display, speaker, haptic feedback device, etc.

[0046] As another example, the transmitting and receiving unit (240) may be a means for interfacing with a device in which the functions for input and output are integrated into one, such as a touchscreen.

[0047] Additionally, in other embodiments, the computing device (200) may include more components than those of FIG. 2 depending on the nature of the device to which it is applied. For example, when the computing device (200) is applied to a user device (110), it may be implemented to include at least some of the input / output devices described above, or it may include additional components such as a transceiver, a GPS (Global Positioning System) module, a camera, various sensors, a database, etc. As a more specific example, when the user device is a smartphone, it may be implemented to include additional components such as an accelerometer or gyroscope sensor, a camera module, various physical buttons, buttons using a touch panel, input / output ports, and a vibrator for vibration, which are generally included in smartphones.

[0048] FIG. 3 illustrates a system environment for performing a web-based drawing management method using generative artificial intelligence according to an embodiment of the present invention. Referring to FIG. 3, a service server (31) can be communicated with a user terminal (32) and / or a manufacturer terminal (33) to exchange information with each other. The service server (31) can provide a work environment to the user terminal or manufacturer terminal based on the web or an application for uploading drawings such as CAD, modifying drawings, creating drawings, sharing drawings, and managing drawings. That is, the service server may be a cloud-based drawing management platform in the form of SaaS.

[0049] In one embodiment, the user terminal (32) may be a producer who creates drawings such as CAD, or a consumer who requests drawings. Additionally, the manufacturer may be an entity that produces actual products based on the drawing file. That is, the user terminal and the manufacturer terminal may be displayed as different blocks but may include the same entity. Furthermore, the user terminal or the manufacturer terminal may include multiple entities. A drawing uploaded by the first manufacturer terminal can be shared or modified by the first user terminal, and subsequently, the second user terminal or the manufacturer terminal may share or further modify it. Conventionally, there was inconvenience in transmitting CAD files using email or a separate storage device and managing modification history locally, but according to the present invention, there is an advantage that drawings can be created and managed by multiple entities on a single platform.

[0050] Service Overview

[0051] FIG. 4 is an example of a web-based drawing management service according to an embodiment of the present specification. The web-based drawing management service may be performed by the service server described above. Referring to FIG. 4, a user may log in as a user by subscribing to the platform service (40). The user may use the service with one of several subscription plans with various functions applied differentially. Functions and data storage capacity may vary depending on the subscription plan. The user may check the contents of drawing attributes for all or part of the uploaded drawing. Referring to FIG. 4, the platform service may include a drawing attribute analysis area (400). The drawing attribute analysis area (400) may provide information related to the corresponding attributes for all or part of the drawing for each of the various drawing attributes.

[0052] In one example, the attributes of a drawing may include various information such as post-processing, material, color, thickness, shape type, dimensional information, texture, machining method, joining method, part identifier, surface roughness, surface treatment method, and material strength. These attributes can be extracted based on metadata, drawing symbols, annotations, layer information, or text areas contained within the CAD file or drawing image. For instance, "Anodized Aluminum" indicated on a drawing can represent both material and post-processing attributes, while notations such as "M10x30" can simultaneously indicate screw shape and dimensional attributes. Generative AI extracts this information through various machine learning-based technologies, such as Optical Character Recognition (OCR), Natural Language Processing (NLP), and geometry analysis, and each extracted attribute can be stored in conjunction with specific location information within the drawing. Furthermore, some of the attributes may contain high-level meanings that suggest the overall design purpose or use of the drawing; in such cases, Generative AI can automatically classify or tag the drawing by identifying relationships between attributes and inferring them as attributes of a higher category.

[0053] In one example, to extract attributes of a drawing, the drawing file may be input into a generative AI module (not shown), and the attribute values ​​may be output and utilized. The aforementioned drawing file may be of various file formats, such as CAD files, image files, and PDF files. The generative AI recognizes the visually displayed image of the file to primarily extract attributes within the drawing, and can further extract attributes by utilizing the file's metadata. Generally, since relevant information is presented at the bottom right of the file execution screen for CAD files, the AI ​​can retrieve information from this area. In the case of image files, the metadata of the corresponding image file may also be utilized. Furthermore, in another example, email files exchanged with the drawing file may be included in the drawing file. Attribute information regarding the drawing may be estimated based on the email history.

[0054] Referring further to FIG. 4, regarding post-processing (410) among the attributes of a drawing, the type and ratio of post-processing can be distinguished and displayed for all or part of the drawing, and various users can write comments for each drawing, and the rate of change of the number of post-processing mentioned in these comments can be checked. Information can also be provided for materials in a similar manner to post-processing.

[0055] FIG. 5 illustrates a personal storage drawing file repository (50) of a user (meaning a logged-in user, such as a user terminal or a manufacturer terminal) according to an embodiment of the present specification. Referring to FIG. 5, drawing files can be stored and managed using folders, etc., and files stored in the parent folder can be displayed as the file itself as Figure 501 of FIG. 5. When a drawing file is uploaded to a platform service, attributes of the drawing may be automatically extracted through a generative AI, or attributes may be extracted through a generative AI at the request of the user. For example, the user may command the extraction of attributes of the selected drawings by selecting one or more drawings and executing the attribute extraction tab (51).

[0056] Meanwhile, the format of drawings uploaded to this platform service may include not only CAD but also various file formats such as PDF and images.

[0057] Referring further to Fig. 5, the number of comments (501-1) for each drawing may be displayed. By referring to these number of comments, the user can check whether recent modifications have been made to a drawing or whether there is a lot of discussion about it.

[0058] In addition, in one example, the attribute extraction command of a drawing file can be executed not only in the form of a tab (51) but also through an additional information window (52) provided when a specific drawing is selected.

[0059] FIG. 6 illustrates an example of providing various versions for a single drawing. Referring to FIG. 6, the service server (31) can provide these versions in a hierarchical manner when modifications to an initially uploaded file are made by various users through various branches. Here, the difference in versions may be branched into a new version when the difference between the original drawing and the modified drawing exceeds a predetermined ratio. That is, if the content modified in Version 1 (difference in similarity before and after modification) is within a predetermined ratio (e.g., 30% similarity), the modified file is displayed as Version 1.1 or 1.3, etc., but if the difference in similarity before and after modification exceeds 30%, the version integer may be set to change to Version 2 or 3. In addition, the content of such modifications may be displayed hierarchically as in FIG. 6. Furthermore, if the result of a second user's modification of a single file (e.g., Version 3.1) is closer to Version 2.1 than Version 3.1, the service server may define the version of the second user's modification result as 2.2 rather than 3.2. Of course, in other examples, version 3.2 may be generated.

[0060] In addition, in one example, the similarity may be determined based solely on the difference between the drawing images before and after modification, while in another embodiment, it may be determined based on the importance of the modified part. For instance, in the case of a product divided into a main part and a dependent part, if the main part is modified, the similarity may be evaluated as lower.

[0061] In addition, in other examples, comments can be automatically generated for the modified parts. For instance, if the gap between Part 1 and Part 2 is modified to be increased from 2 to 3, the service server can automatically generate a tag such as “Adjustment of gap between Part 1 and 2 (3)” on the modified result through generative AI.

[0062] Referring further to FIG. 6, the version comparison tab (60) is executed so that any two or more drawings selected by the user can be displayed for comparison. The two drawings may be arranged side by side or displayed overlapping. In another example, the differences between the two drawings may be generated and provided as text.

[0063] Drawing Control User Interface

[0064] A web-based drawing management service according to one embodiment of the present specification displays drawing attributes extracted based on generative artificial intelligence. Meanwhile, since attribute information extracted using generative artificial intelligence may contain errors, users need to visually distinguish between automatically extracted parts and non-extracted parts, and to further verify the automatically extracted parts.

[0065] To this end, in one embodiment, attribute information for a drawing may be provided in multiple forms. For example, automatically extracted attribute information may have a first color, and attribute information entered by a user may have a second color. Additionally, among the automatically extracted attribute information, attribute information verified by a user may have a third color. Accordingly, the user and other users have the advantage of being able to visually and quickly distinguish whether the attribute values ​​provided for each drawing are reliable.

[0066] FIG. 7 illustrates an example of changing a plurality of attribute information into a user-confirmed state according to an embodiment of the present specification. The attribute information automatically extracted through generative AI may, for example, have a first color and may be text that can be modified by the user. If the attribute information is incorrect, the user can modify the content. Meanwhile, if the attribute information is confirmed to be accurate, it is necessary to indicate that it has been confirmed. In one example, the user can confirm the attribute information by clicking or touching (on a touch screen). In another example, as shown in FIG. 7, the user may select a predetermined area (70) and input that the attribute information within that predetermined area has been confirmed. For example, the user may create a predetermined area (70) after right-clicking the mouse, or select the confirmed attribute information at once by changing the position and size of the created rectangle after pressing the area setting tab (not shown) on the touch screen.

[0067] In addition, attribute information may be displayed in different colors depending on the probability that the attribute information extracted in one example is accurate. Due to resolution issues within the drawing or conflicting information, any one of the extracted values ​​may be uncertain based on the judgment of the generative AI. If this uncertainty is quantified and falls below a certain threshold (e.g., the probability that the extracted attribute value is incorrect is 50% or higher), that attribute value may be displayed in a different color from other extracted attribute values. For instance, if the automatically extracted attribute value is blue and the attribute value entered by the user is black, the automatically extracted but uncertain attribute value may be displayed as a combination of blue and red, or simply in red.

[0069] Drawing sharing algorithm

[0070] According to one embodiment of the present specification, a user who owns the first drawing may share the first drawing with another second or third user. The shared drawing may be shared with the second or third user through the present platform (40). When sharing, the first user may set permissions for viewing, using, and editing the shared drawing. Depending on the set permissions, the user who receives the shared drawing may use the drawing. Meanwhile, the second user may be a user who is registered with the present service platform or a user who is not registered. A unique link (801) is assigned to each drawing, and the second or third user may use the shared drawing through the link.

[0071] FIG. 8 is a diagram illustrating a method of sharing a drawing at least partially according to an embodiment of the present specification. Referring to FIG. 8, a first user may share a drawing (81) that he or she possesses or has the right to share with another second user. At this time, the first user may share only a part of the drawing. More specifically, the user may share only a part (811) of the entire components (811-813) of the drawing with another user. By selecting the part (811) to be shared and setting the sharing of only this part to be selected, and selecting the person to receive the sharing, the service server may generate a drawing for sharing (81-1) based on the drawing. The drawing for sharing (81-1) may have a different URL from the original drawing (81) but may be set as a sub-address of the original drawing's URL. Additionally, parts of the drawing for sharing (81-1) that are not set for sharing may be deleted or blurred (812-1, 813-1) as shown in FIG. 8. That is, a new image with the parts not set for sharing blurred may be generated with a new URL and shared.

[0072] Additionally, according to one embodiment, a first user may insert annotations, attribute information, or comments on a portion of a drawing prior to sharing the drawing. The annotations and information may be configured to be included in the drawing for sharing (81-1), and a second user may view the annotations or add comments according to the configured permissions. The annotations may include, for example, processing methods, surface treatment instructions, review requests, etc. The first user may separately specify the scope of the annotations included in the drawing for sharing.

[0073] According to another embodiment, the first user may select and share only a portion of multiple drawing components, rather than the entire drawing. The user may specify the elements to be shared using a polygonal area tool, a layer filter, a filter based on specific objects, etc. Additionally, multiple drawings may be grouped together and shared collectively, in which case individual settings can be configured for each drawing. The first user may generate a unique link for each drawing or drawing group, and this link may be sent along with the requester's email, name, company name, etc. According to yet another embodiment, the first user may set access restriction conditions for each user to whom the content is shared. For example, the number of viewings, viewing validity period, printability, and downloadability may be specified, and these settings may be stored on the server along with the sharing link. Even if the second user is a non-member, temporary access rights may be granted through email verification, etc. Furthermore, the first user may expire the sharing link, and the expired link may be automatically discarded by the server or switched to an access-restricted state. In addition, the first user may configure the system to receive feedback from the second user regarding the shared drawings. A second user may enter comments or create revision suggestions within the drawing, and a first user may decide whether to accept such feedback. The feedback may be stored in a form linked to a specific location in the drawing, and the feedback history may be integrated into and stored in a drawing history management system.

[0074] Additionally, the first user can configure sharing for specific versions among multiple versions of a drawing. For example, intermediate versions of work that have not been finally approved can be excluded from sharing, and external sharing can be restricted to only approved drawings. Each drawing is managed along with version information, and sharing links can be issued linked to this version information. If a drawing is modified, you can configure whether to automatically update the drawings accessible via the existing sharing link.

[0076] Drawing comparison function

[0077] FIG. 9 is a diagram illustrating a drawing comparison function according to an embodiment of the present invention. Referring to FIG. 9, the first drawing (901) and the second drawing (902) selected by the user may be drawings saved at different points in time or different versions, or they may be similar drawings created at the same point in time. The comparison function according to the present invention can be activated simply by selecting two drawings, regardless of the nature of the drawings to be compared. The drawings to be compared can be selected by the user on a web-based CAD drawing management platform, and the selected drawings are designated as subjects for comparison processing by the system. According to the present embodiment, drawing comparison can be performed through a generative artificial intelligence module. The artificial intelligence module can preprocess input drawing data and decompose geometric objects, text elements, annotation information, drawing title block information, layer and line attributes, etc. included in each drawing, and convert them into an internal data structure. In this process, information can be extracted from CAD format files or raster images, and multiple preprocessing techniques can be applied in combination. For example, shape recognition algorithms, optical character recognition (OCR) technology, and line type and color analysis can be applied in parallel.

[0078] Subsequently, the artificial intelligence module can represent the components extracted for each drawing in a vector form and determine whether a match exists by analyzing the similarity between each object. Objects that are not matched may be classified into 'add', 'delete', or 'modify' categories, and these categories may be visually provided to the user as comparison results. For example, objects that exist only in drawing (902) may be highlighted with a blue border, and objects that exist in drawing (901) but not in drawing (902) may be represented with a red dotted border. For modified objects, the changed attribute items are highlighted, and when the user clicks on the object or hovers the mouse over it, a detailed history of attribute changes may be provided as a popup. Additionally, according to an embodiment of the present invention, the comparison results may be organized in the form of a separate comparison table (906) and placed within the drawing. The comparison table may list the name of the changed element, location coordinates, and values ​​before and after the change (e.g., length, angle, text, etc.), and each item may be hyperlinked or have a synchronization function added to link with the corresponding part of the drawing. This allows the user to intuitively recognize not only visual differences but also numerical and structural differences. According to another embodiment, the user can pre-set criteria for the comparison method. For example, one or more of geometric shape-centered comparison, attribute value-centered comparison, text information-centered comparison, or annotation-centered comparison can be selected, and the AI ​​comparison algorithm can be selectively applied according to the set criteria. Additionally, the user can mask specific areas within the drawing to exclude them from the comparison, or set only the areas of interest as the comparison targets. This can be usefully applied when analyzing complex drawings only partially.

[0079] Additionally, the comparison results can be output not only in the form of images but also as summary reports or voice guidance. For example, natural language-based descriptions such as “The square shape at the bottom left has been deleted” or “The diameter of the central circular part has been changed from 60mm to 45mm” can be provided in text or voice. This feature enhances the understanding of the comparison results and helps even non-expert users easily recognize the changes. Meanwhile, the comparison results are stored on a web platform and can be linked with a timeline interface that manages the history of changes to the drawings. Users can view each comparison result in chronological order and repeatedly view comparison records with previous drawings. Furthermore, the comparison results can be generated as a unique link in the form of a URL and shared with external users, and access permissions, editing rights, and download rights can be set upon sharing. As such, the drawing comparison function according to the present invention can provide various comparison methods, intuitive visualizations, and flexible sharing and expansion functions based on generative artificial intelligence.

[0080] FIG. 10 is a diagram illustrating a function to provide a user with a comparison result between two drawings in the form of a component attribute unit, according to an embodiment of the present invention. In one embodiment, the user can select a first drawing and a second drawing as comparison targets through a web-based drawing management platform, and the selected drawings are registered as comparison analysis targets by the system. Based on the components extracted from each drawing, the system can compare the attribute values ​​included in the corresponding components and display the results in a list form on a user interface. The comparison list can be implemented, for example, as a drawing comparison list window (911), and the list can be composed of multiple columns such as 'object name', 'item classification', 'value of Drawing A', 'value of Drawing B', and 'remarks'. 'Object name' includes the name or location information of a component on the drawing that serves as the basis for comparison, and 'item classification' is defined as an item for identifying the item of the attribute being compared (e.g., length, angle, material, etc.). 'Value of Drawing A' and 'Value of Drawing B' represent the attribute values ​​of the corresponding items extracted from the first and second drawings, respectively. If the two values ​​are identical, they may be provided in a standard font; if they differ, they may be visually distinguished through background color or highlighting. The 'Remarks' item may include information regarding user confirmation of the automatically extracted value, manual editing, or other memo details. Each item may be sorted or filtered based on the point of comparison. To aid user understanding, the above list may be linked with a function that highlights the location of the corresponding object on the drawing upon mouse hover.

[0081] Meanwhile, according to one embodiment of the present invention, the comparison list may simultaneously display attribute values ​​automatically extracted by generative artificial intelligence and verification values ​​reviewed or directly entered by the user. The automatically extracted values ​​are values ​​extracted by artificial intelligence from components within a drawing through a learning-based analysis model, such as results generated through object recognition, text recognition, or pattern analysis. If the user verifies and manually modifies these values, the system may save the corresponding values ​​as user-verified values ​​and visually distinguish and display the differences from the automatically extracted values. For example, the automatically extracted values ​​may be displayed on a gray background or in an italic font, while the user-verified values ​​may be displayed in a standard font, allowing for intuitive identification of the differences between the two values. Additionally, if the automatically extracted values ​​and the user-verified values ​​do not match, the system may add an accent color or an icon (e.g., a warning sign) to draw the user's attention, and clicking on the item may provide a popup allowing the user to view detailed change history or the reason for the modification. These comparison items can be selectively displayed on the list through conditional searches such as 'show only mismatched items' or 'filter user-checked values,' and bulk comparison results for multiple drawings can also be provided in an integrated list format. This feature enables efficient verification even when drawings have structural complexity and a large number of components, and can be particularly useful for identifying large-scale design change histories managed on a project basis. Users can click on items in the list to directly check the location of corresponding objects on the drawing images, and the system can provide real-time synchronization between the drawing viewing area and the comparison list. Accordingly, users can intuitively identify the location on the drawing, whether changes have been made, and the values ​​before and after the change solely from the list.

[0082] The drawing comparison list is provided via a web-based UI and can be combined with various interaction functions. Users can enter comments for each item, and these comments can be saved along with the drawing attribute history. When multiple users participate in the comparison process in parallel, the system can store comment history separately for each user and display them so that they can be identified by user color or initials. Additionally, the status of each item can be set to 'Needs Review,' 'Review Completed,' or 'Pending,' and these status values ​​can also be utilized to visualize the overall review rate or remaining review items. Through a filter function based on drawing change history, only recently changed items can be extracted, or changes that occurred only in specific versions can be selectively displayed. The list can be downloaded in formats such as PDF, CSV, and XLS, and can be delivered to external users as a shared link upon user request. The generated link can include various access permissions, such as read-only, editable, or comments only, and settings can be configured to share the list either together with the drawing body or independently. The drawing comparison list can ultimately be converted into a change history report, review log, or approval record and linked to the design change approval process. Through this, the comparison list function of the present invention integrates an automatic analysis function utilizing generative AI with a user interaction-based collaborative review function, thereby enabling efficient and accurate management of drawing changes.

[0084] First embodiment

[0085] FIG. 11 is a flowchart of a web-based drawing management method using generative artificial intelligence according to an embodiment of the present specification. Referring to FIG. 11, the present method may include the steps of receiving a drawing from a user (S100), extracting attribute values ​​for the received drawing using generative artificial intelligence (S200), associating the extracted attribute values ​​with the drawing at least partially (S300), and providing a thumbnail image of the drawing from which the attribute values ​​were extracted (S400).

[0086] In one embodiment, drawings uploaded by a user may be received by the system through a web browser-based interface, a CAD integration plugin, or API integration with an external system, and the drawing format may support various industrial or standard formats such as DWG, DXF, PDF, SVG, IFC, and STEP. Along with the drawing file, metadata such as the author, version information, project name, upload time, and reference relationships may be automatically extracted or entered directly by the user. In the case of a complex structure containing multiple sheets, the data may be stored separately on a sheet-by-sheet basis, or a representative sheet may be automatically identified and registered. Images, 3D data, title block information, etc. included in the drawing may be stored separately on an individual layer or object basis, and if a predefined template structure is detected, metadata may be automatically mapped to match that structure. If an uploaded drawing has the same hash value as an existing drawing, duplicate registration is prevented, and association information between files may be automatically linked according to the project-specific directory structure. Users may grant access permissions, sharing settings, tags, etc., upon upload, which can be used as filtering criteria for search, comparison, and sharing functions in the future.

[0087] Upon receipt of a drawing, generative AI recognizes elements such as shapes, text, dimensions, symbols, and annotations included in the drawing, and extracts semantic-based attribute values ​​assigned to each object. For example, in the notation “Ø50 SUS304 Post-processing: Sandblasting,” multiple attributes such as ‘diameter,’ ‘material,’ and ‘post-processing’ can be identified simultaneously; these can then be broken down into individual items and normalized into attribute-value pairs. The AI ​​infers the matching relationship between components and attributes by comprehensively performing OCR (Optical Character Recognition), object detection, interpretation of dimension lines, and correlation judgment based on annotation distances. If the same object appears repeatedly across multiple sheets or drawings, batch attribute application is possible through pattern recognition and clustering functions. If multiple languages ​​are mixed within the drawing, attribute names can be standardized through automatic language detection and translation functions, and a domain-specific dictionary can be applied to interpret the meaning of special symbols and unit notations. During attribute extraction, a reliability-based score is assigned to automatically classify subjects for user review, and accuracy can be continuously improved through past user feedback.

[0088] Attribute values ​​can be linked and stored with individual objects within the drawing immediately upon extraction, and the system can automatically determine the attribute's connection targets based on the object's coordinates, vector properties, and connection line structure. For example, based on the relative position between a rectangular shape in the drawing and an adjacent annotation, as well as dimension line connections, the attribute value of that annotation can be attributed to the corresponding shape object; users can selectively modify the linkage or directly specify the connection point. If the same attribute applies to multiple objects, it can be managed as a group attribute or linked collectively via inheritance; conversely, if multiple attributes are assigned to a single object, they can be represented as a hierarchical structure or an attribute tree. These object-attribute connections are integrated with the interface on the drawing view, allowing the corresponding relationship to be visualized bidirectionally when a user clicks an object or an attribute. Each attribute item stores information such as whether it was manually edited, the last modifier, and history data, enabling integration with change tracking or approval workflows.

[0090] Thumbnail images for drawings are generated based on the representative geometry of the drawing file or key components identified by artificial intelligence, and can be composed of standard square or sheet ratio-based images. These thumbnails can be configured to display key attribute values ​​of the drawing (e.g., Material: AL6061, Machining: CNC, Dimensions: 120x60), and this attribute information can appear as text overlays, tooltips, or tags. Users can perform functions such as filtering by attribute (e.g., viewing only SUS material drawings), sorting (by most recent, by size, etc.), and multi-selection from the thumbnail list; clicking a thumbnail opens the entire drawing and attribute view in an integrated manner. If multiple sheets are included, sheet-specific thumbnails may be generated, or summary thumbnails may be configured based on the representative sheet; for 3D model drawings, projected images captured from a specified angle may be used as thumbnails. Thumbnails are automatically generated based on resolution and aspect ratio to ensure compatibility with various devices, and the system is configured to output them quickly through pre-rendering and caching within the server.

[0091] When a user selects a provided thumbnail, the selected drawing is loaded in full screen or a designated viewer, along with the attribute values ​​associated with that drawing. These attribute values ​​can be displayed as fixed panels on the left or right side of the drawing, or implemented as interactive pop-ups that appear when an object is clicked, allowing the user to edit each attribute or add annotations. Modified attributes are displayed in parallel with the existing automatically generated values ​​and are clearly distinguished by visually distinct formatting (e.g., bold text, color coding, underlining, etc.). For instance, automatically generated values ​​are displayed in gray italics, while user-modified values ​​are highlighted in black standard font. The modification history of attribute values ​​is recorded chronologically, enabling log-based management to verify who changed which item and when. The attribute panel may provide sorting, filtering, and original-modification comparison functions, and may also include a feature to visually check the relationships between attributes on the drawing.

[0092] Drawings are automatically assigned a unique link and can be accessed via a URL, which users can copy and share with external users. The recipients of the shared content may include not only registered users but also non-members; in such cases, the system may allow viewing through email verification or temporary access permissions. Access permissions can be set for the link, and granular permission levels can be specified, such as viewing only, allowing comments, allowing editing, or allowing attribute viewing only. Users may set specific areas or attribute values ​​as targets for sharing, rather than the entire drawing; in this case, non-shared areas are converted by the system into blurred images or grayscaled forms before being shared. A shared drawing has a URL different from the original drawing but is structured as a sub-path of the original drawing link, maintaining a hierarchical structure between drawings. The shared drawing is rendered as a separate image on the server and may be displayed differently depending on the recipient's permission settings; similarly, the visibility of attribute values ​​may be restricted. Sharing history is recorded in the system log, which may include access statistics or access restriction period settings.

[0094] 2nd embodiment

[0095] FIG. 12 is a flowchart of a method for providing a cloud-based drawing management user interface using generative artificial intelligence according to another embodiment of the present specification. Referring to FIG. 12, the method for providing a cloud-based drawing management user interface using generative artificial intelligence may include: a step of extracting attribute values ​​for a drawing uploaded to a service server using generative artificial intelligence (S1100); a step of providing the extracted automatic attribute values ​​to a user along with the drawing (S1200); a step of displaying the extracted automatic attribute values ​​in a first expression format different from the user input attribute values ​​entered by the user (S1300); and a step of changing the extracted attribute values ​​to a second expression format when the extracted automatic attribute values ​​are modified or confirmed by the user (S1400).

[0097] When a drawing is uploaded, the service server analyzes the symbols, annotations, text, dimension lines, etc., to automatically extract attribute values ​​and provides them to the user along with the drawing visualization screen. The automatically extracted attribute values ​​are displayed as text input fields that allow users to modify them directly; users can change, delete, or enter new values ​​from the automatically provided values. At this time, the automatically extracted attribute values ​​are classified into distinct attribute types within the system, and their display format on the drawing is specified differently from user-input attribute values. For example, automatically extracted values ​​may be displayed with a gray background or border, while attribute values ​​directly entered by the user may be displayed in black or blue.

[0098] When a user checks or modifies a provided attribute value, the system changes the state of the corresponding attribute and switches the display format to a second representation format. This representation format is configured to be distinct from the original automatic extraction state and can be displayed separately in the attribute value list, attribute list view, and object overlay within the drawing. The modified attribute value is stored in parallel with the original value, and the original extracted value may be provided together in a separate area or as a tooltip. Attribute values ​​reflecting user input are treated as user-confirmed attributes for future searching, comparison, and sharing, and the modification history can be maintained as a separate record for each attribute value.

[0100] Generative AI can calculate accuracy for each extracted item when extracting attributes. Accuracy can be determined by combining the resolution of the drawing image, the presence of adjacent text, the clarity of dimension symbols, or the metadata of the drawing file and communication information related to the drawing (e.g., title, filename, email wording, etc.). The system can be configured to distinguish automatic attribute values ​​in different display formats based on this accuracy score; for instance, attributes with high accuracy can be displayed in plain gray, while attributes with low accuracy can be displayed with red or dotted borders. Users can select attributes for review based on this distinction or configure the system to view attributes with lower accuracy first through a priority sorting function.

[0101] When multiple automatic attribute values ​​are displayed in a drawing, the user can specify a 2D area via mouse drag or a touch-based interface to collectively check the attribute values ​​contained within it. For example, regarding automatic attribute values ​​located within an area designated in the form of a rectangle or free curve, the system may consider them to have been checked by the user and automatically change the display format of these attributes to a second representation format. The user may also select a function to individually select and modify attribute values ​​that have been switched to a checked state, or to reset multiple selected items at once. This function can be utilized when the user needs to repeatedly check attribute values ​​contained within a large drawing area.

[0102] For attribute values ​​classified as having low accuracy, the system can be configured to convert them to user-input values ​​only after verification or modification by multiple users is completed. The system tracks the review status for each user and changes the status of the corresponding attribute value if the same verification or modification occurs by more than a specified number of reviewers. For example, if two users enter the same value for the same attribute, or if the verification process confirming the validity of the existing value is repeated, the attribute is converted to a second representation format. This function can determine whether to process an attribute based on the review history of each user, and attributes currently under review may be assigned a separate status indicator (e.g., “Pending,” “Under Review”).

[0104] Hierarchical drawing management

[0105] FIG. 13 is a conceptual diagram illustrating a method of visualizing a plurality of drawings by hierarchically linking them according to an embodiment of the present specification. Referring to FIG. 13, the process of hierarchically linking drawings and entering and exiting a drawing hierarchy view is described.

[0106] As illustrated in Fig. 13, a user can start working on a specific drawing, for example, 'Drawing B'. This 'Drawing B' may be a higher-level drawing, and the user can enter 'Hierarchy View Mode' from this drawing. Upon entering 'Hierarchy View Mode', the state 'Drawings within Drawing B are displayed', which means that 'Drawing A', 'Drawing E', and 'Drawing G', which are lower-level drawings directly linked to 'Drawing B', are all displayed. In this way, the user can grasp the relationship between the upper and lower drawings at a glance. As described at the bottom of the drawing, all linked drawings are displayed in 'Hierarchy View', and this does not move to the detail view of the corresponding drawing. Additionally, the user can select a specific drawing among 'Drawing A', 'Drawing E', and 'Drawing G' displayed in Hierarchy View Mode. For example, if 'Drawing A' is selected, the user exits 'Hierarchy View Mode' and the actual folder and project information where 'Drawing A' is located is displayed. Similarly, selecting 'Drawing E' displays the folder / project where 'Drawing E' is located, and selecting 'Drawing G' displays the folder / project where 'Drawing G' is located. This allows users to navigate hierarchical drawing relationships, ultimately verify the actual save location or affiliated project of a drawing of interest, and perform detailed operations on that drawing. Additionally, the 'Exit Hierarchy View Mode' path allows users to return to the starting point at any time to explore other drawings or exit the hierarchy view.

[0107] FIG. 14 illustrates a hierarchical management user interface for drawings according to an embodiment of the present specification. Referring to FIG. 14, the user can set up association relationships between drawings such that they become lower in hierarchy as they move to the right.

[0108] As shown in FIG. 14, drawings are represented by individual boxes such as C1, C2, C3, C4, and C5, with connection points on the left and right sides of each box indicating connections. These connection points are displayed with the symbols '+' (meaning 'add') and '-' (meaning 'exclude'), allowing the user to intuitively set and control the relationships between drawings. For example, drawings C2 and C3, which start from drawing C1 and connect to the right, visually indicate that they are a sub-level of drawing C1. Here, the right connection point of drawing C1 and the left connection point of drawings C2 and C3 are connected to each other to form a hierarchical relationship.

[0109] Furthermore, Drawing C2 is connected to the right, serving as the upper layer for Drawings C4 and C5. In other words, the right connection point of Drawing C2 is linked to the left connection point of Drawings C4 and C5, establishing the association between Drawings C2 and C4, and C2 and C5. This user interface allows users to directly set and visually verify hierarchical relationships between drawings, facilitating an intuitive understanding of the overall project or product structure. The '+' and '-' symbols in each drawing box indicate that users can add new drawings to the lower layer of a specific drawing or exclude existing connected drawings from the hierarchical relationship. This enables users to flexibly manage complex reference relationships between drawings.

[0110] Referring further to FIGS. 13 and 14, in a drawing management user interface where the hierarchical association is established, the user can perform individual management and operation functions for each connected drawing file. According to one embodiment of the present specification, a context menu or operation button may be provided in each hierarchically linked drawing file box (e.g., C1, C2, etc. in FIG. 14) or in the thumbnail view of the corresponding drawing. These operation functions may include, for example, an unlink function and a download function in various file formats. When the unlink function is executed, the hierarchical reference information between the drawings is released or deactivated from the system's database. At this time, the unlink operation may be configured to apply only to the user who executed the drawing unlink (individual view) so as not to affect the hierarchical views of other users, or it may be configured to apply collectively to all users participating in the project to change the hierarchical relationships of all users. The system may request the user to select the scope of application (individual / all) when unlinking.

[0112] Specifying relationships between files and managing hierarchical connections

[0113] FIG. 15 is a diagram illustrating the relationship between a drawing and other elements according to an embodiment of the present specification. A web-based drawing management service associates multiple files uploaded to a platform, such as drawing files, attachment files (PDF, images), and Bill of Materials (BOM) files, with one another, and provides a function to explicitly specify the nature, or relationship, when creating a connection between these files. This goes beyond simply setting links; it enables the system to recognize and visually clearly provide the role in which files are cross-referenced within the project structure.

[0114] The aforementioned relationships are established based on the purpose of the files, categorized into assembly / part relationships, attachment file relationships, and physical image relationships (e.g., site images). For instance, assembly / part relationships are used to clarify the hierarchical structure of a product when a parent drawing, such as Drawing A, references other part drawings, while attachment file relationships are used to link related documents, such as quality reports (e.g., BOM). Users can configure these relationships by selecting Drawing A as the reference file, specifying the target files to be linked, and selecting one of the aforementioned defined relationship types. Files with assigned relationships are visualized in a hierarchical or network format within the user interface, facilitating the understanding and management of complex design structures and file reference relationships at a glance. Additionally, users can filter or search for files based on the specified relationships. Here, filtering refers to selectively extracting only the associated files corresponding to the relationship types explicitly designated for a specific drawing selected by the user.

[0115] According to one embodiment of the present specification, a user interface may be provided with a relation filter function to effectively manage the relationship between a drawing and other files. The relation filter function refers to a function that classifies files associated with a drawing by predefined relationship types, such as parts, attachments, physical images, related documents, and included drawings, and searches, displays, or manages a file list based on these classifications.

[0116] Users can define new relationship types or add associated files corresponding to existing relationship types through the aforementioned relationship filter interface. File addition can be performed via a new file upload method or by linking to existing files already present in the cloud system. Multiple files can be grouped and managed for each relationship type, which enhances the efficiency of project management centered around a single drawing.

[0117] In particular, the present invention utilizes generative artificial intelligence to determine the appropriateness between a relationship type and the content of an uploaded file. For example, when a user makes an upload request to add a file to the 'Real Image' item, the generative artificial intelligence analyzes the file and, if it determines that the file format or content is inappropriate for a real image—such as a CAD drawing file (DWG, DXF, etc.) or a text document (DOCX, etc.)—provides a message to the user requesting confirmation of the content discrepancy. This confirmation request message can be displayed in a visual form, such as a popup, a warning icon, or a tooltip, and contributes to improving data quality by reconfirming the user's intent and increasing the accuracy of file classification. Additionally, by checking (selecting) or deselecting (unselecting) a relationship filter, the user can selectively view and access only the associated files corresponding to a specific relationship type for the drawing currently being viewed.

[0119] FIG. 16 is a diagram illustrating a drawing attribute preview function according to an embodiment of the present specification. Referring to FIG. 16, one or more drawings (1600) provided as a gallery, list, or Excel type may have some of the drawing attribute information (1601) displayed together with a drawing preview (1600). Some of the attribute information displayed in this way may be recently updated or entered values, or may be determined as attribute information of high importance in the corresponding drawing, and may be changed according to the view by user settings. That is, if the user determines the preview attribute values ​​in the current view, the determined attribute values ​​may be displayed as a preview.

[0121] Industrial applicability

[0122] According to one embodiment of the present specification, a user can directly view drawings in a web or mobile environment without installing a separate CAD program or plugin. The system utilizes an open API-based viewer to render CAD drawing files on a browser and can apply unique UI / UX tuning considering user convenience. For example, when a user uploads a drawing file, the system can be implemented to allow immediate viewing of the drawing without a login procedure, and key drawing areas can be automatically recognized and enlarged, or multiple drawings can be viewed in parallel in a tab format. In particular, touch-based zooming, panning, and rotation functions are optimized for mobile devices, and CAD drawing files can be provided in a lightweight format to enable smooth viewing even in low-spec environments. Additionally, users can select only specific parts of a drawing, rather than the entire drawing, to share with external partners, and sharing permissions can be subdivided based on whether viewing, annotation, or editing is possible. Shared drawings can be configured to be partially blurred or allow only limited interaction depending on the specified permissions, and the system can automatically apply the optimal interface according to the user's approach.

[0123] According to another embodiment of the present specification, attribute information extracted from an uploaded drawing can be automatically transferred and stored in a cloud-based database. Generative AI can automatically structure information within a drawing into attribute items such as 'material name', 'specification', 'quantity', 'unit', and 'part code' based on text recognition, symbol interpretation, and classification of dimensions and structural objects. This data is automatically mapped to each field within the cloud according to a predefined classification system. For example, simply by uploading a drawing, a series of processes including “attribute recognition → classification → field mapping → BOM generation” can be automatically performed without manual effort, and the system enables the real-time generation and utilization of a drawing-based Bill of Materials (BOM). This process is based on open AI technologies such as GPT API or Vision API, but is executed through a unique algorithm that incorporates a prompt system and post-processing logic specialized for the Korean manufacturing environment. Therefore, by simply providing a drawing file, users can automate the complex attribute extraction and data transfer processes in bulk without separate editing, and the generated attribute data can be utilized in various business scenarios in conjunction with subsequent comparison, tagging, and search functions.

[0124] The embodiments described above may be implemented at least partially as computer programs and recorded on computer-readable recording media. Computer-readable recording media on which programs for implementing the embodiments are recorded include all types of recording devices in which data readable by a computer is stored. Examples of computer-readable recording media include ROM, RAM, CD-ROM, magnetic tape, optical data storage devices, etc. Additionally, computer-readable recording media may be distributed across networked computer systems, so that computer-readable code is stored and executed in a distributed manner. Furthermore, functional programs, codes, and code segments for implementing the embodiments will be readily understood by a person skilled in the art to which the embodiments pertain.

[0125] Although the present specification described above has been explained with reference to the embodiments illustrated in the drawings, this is merely illustrative and those skilled in the art will understand that various modifications and variations of the embodiments are possible therefrom. However, such modifications should be considered to be within the technical scope of protection of the present specification. Accordingly, the true technical scope of protection of the present specification should be determined to include other implementations, other embodiments, and equivalents to the claims based on the technical spirit of the appended claims.

Claims

Claim 1 A method for providing a cloud-based drawing management user interface using generative artificial intelligence, performed by a service server, comprising: a step of extracting attribute values ​​for a drawing uploaded to a service server using generative artificial intelligence; a step of providing the extracted automatic attribute values ​​to a user along with the drawing; a step of displaying the extracted automatic attribute values ​​in a first expression format different from user input attribute values ​​entered by the user; and a step of changing the extracted attribute values ​​to a second expression format when the extracted automatic attribute values ​​are modified or confirmed by the user, wherein the user input attribute values ​​refer to attribute values ​​directly entered by the user and are displayed in a second expression format different from the first expression format, and the automatic attribute values ​​have modifiable text attributes. Claim 2 delete Claim 3 A method for providing a cloud-based drawing management user interface using generative artificial intelligence, wherein, in claim 1, the automatic attribute value has two or more expression formats based on accuracy, and the accuracy is determined based on drawing-related information calculated by the generative artificial intelligence, wherein the drawing-related information includes one or more of drawing images, metadata of drawing files, and communication information related to drawings. Claim 4 A method for providing a cloud-based drawing management user interface using generative artificial intelligence, characterized in that, in claim 1, a plurality of automatic attribute values ​​are provided to the user, and automatic attribute values ​​included within a two-dimensional area set by the user are automatically processed as confirmed by the user. Claim 5 A method for providing a cloud-based drawing management user interface using generative artificial intelligence, characterized in that, in paragraph 3, the two or more expression forms include a first expression form and a third expression form, and the third expression form has an automatic attribute value included in an accuracy range lower than that of the first expression form. Claim 6 A method for providing a cloud-based drawing management user interface using generative artificial intelligence, characterized in that, in claim 5, the automatic attribute value having the third expression format can be changed into a user input attribute value only after being verified or modified by multiple users. Claim 7 A method for providing a cloud-based drawing management user interface using generative artificial intelligence, characterized in that, in claim 1, it further comprises the step of connecting a drawing uploaded to the service server with a file other than the drawing; and the step of specifying one or more relationships among assembly / part, attachment file, and site image based on the cross-reference characteristics of the drawing and the other file in the connection step. Claim 8 A method for providing a cloud-based drawing management user interface using generative artificial intelligence, characterized in that, in claim 7, it further comprises the steps of: visually displaying the connection status between the drawing and the other file on the user interface according to the specified relationship; and filtering and providing a file list based on the specified relationship.

Images