KR102399248B1 - Apparatus, method and computer-readable storage medium for generating digital twin space based on architectural drawing - Google Patents

Abstract

According to one embodiment of the present invention, an apparatus for generating a digital twin space may perform: an operation of generating a digital twin space including a plurality of buildings of which exterior is implemented in three dimensions; an operation of obtaining a plan view, a cross-sectional view, and an elevation view corresponding to a first building among the plurality of buildings; an operation of generating 3D space model corresponding to the first building based on the plan view, cross-sectional view, and elevation view; and an operation of substituting the generated 3D space model to a location of the first building.

Description

Apparatus, method, and computer-readable recording medium for creating a digital twin space based on building blueprints

An embodiment of this document relates to a technology for constructing a digital twin space modeled in three dimensions based on a building blueprint and providing an application service related thereto.

With the development of GPS technology and the release of map data between countries, it has become possible to experience various places in the world in 2D or 3D through map services such as Google Maps and Google Earth.

Furthermore, the current map service provides a 360-degree first-person view of the actual shooting of a specific place by interworking with the 360-degree front camera sensing technology.

However, the map service of the existing technology implements only the appearance of the object that can be observed through GPS on the map service, and the subject of the map service is It is difficult to implement it automatically unless you design the space yourself.

Meanwhile, the use of services such as Naver Real Estate, which links map service and real estate information, has recently been increasing, but for the reasons described above, there is a limit to only being able to observe the interior space of a real estate with limited photos, and furthermore, due to the emergence of Corona Due to this, there are restrictions on movement and offline meeting, and new technologies and services that can overcome these limitations and restrictions are required.

Korean Patent Publication No. 10-0952393: Space movement method for virtual reality service Korean Patent Publication No. 10-2199940: 3D map construction method of mobile 3D digital twin through 3D engine

Embodiments of this document intend to provide a technology for constructing a digital twin space modeled in three dimensions on the basis of a building blueprint in order to solve the above-described problems.

However, the problem to be solved by the present invention is not limited as mentioned above, and although not mentioned, it includes a purpose that can be clearly understood by those of ordinary skill in the art to which the present invention belongs from the description below. can do.

An apparatus for generating a digital twin space according to an embodiment includes one or more memories storing instructions for performing a predetermined operation; and one or more processors configured to be operatively connected to the one or more memories and to execute the instructions, wherein the operation of the processor includes: generating a digital twin space including a plurality of buildings having exteriors implemented in 3D; obtaining a plan view, a cross-sectional view, and an elevation view corresponding to a first building among the plurality of buildings; generating a three-dimensional space model corresponding to the first building based on the plan view, cross-sectional view, and elevation view; and substituting the generated 3D spatial model of the first building at the location of the first building.

Also, the operation of generating the VR space may include the operation of generating the digital twin space by capturing open source 3D spatial data generated based on an actual map.

In addition, the operation of generating the digital twin space may include generating an exterior texture of each building based on 3D spatial data generated based on an actual map and mapping the actual address information to each of the buildings.

The operation of acquiring the floor plan, cross-sectional view, and elevation is an image of the floor plan, cross-section, and elevation of the building from the owner or occupant based on the authentication of the real building owner or occupant corresponding to the real address information of the building implemented in the digital twin space may include the operation of obtaining

In addition, the operation of generating the three-dimensional space model may include: generating a space model for each floor based on a plan view corresponding to each floor; According to the height information of each floor described in the cross-sectional view, a virtual height corresponding to the height information of each floor is formed in the space model for each floor, and the virtual height of each floor is formed in the space model for each floor according to the order of each floor described in the cross-sectional view An operation of creating a connected interior space model by spaced enough; and generating an external space model for each side described in the elevation view, and connecting the external space model to the internal space model so that the height information of each floor described in the elevation view and the height information of each floor described in the cross-sectional view correspond to the above 3 It may include the operation of generating a dimensional space model.

In addition, the operation of generating a space model for each floor based on the floor plan may include: specifying line segments and symbols described in the floor plan; generating a three-dimensional model of an object corresponding to a line segment specified in the plan view; and generating a three-dimensional model of an object corresponding to a symbol specified in the plan view.

In addition, the operation of specifying the line segment and the symbol is an operation of specifying the line segment and the symbol included in the plan view by inputting the plan view to a neural network model learned based on the learning floor plan in which the classes for the line information and the symbol information are labeled. may include

In addition, the operation of generating the 3D space model further includes the operation of providing a custom interface for a user to select an object to be placed in the 3D space model, and for the user to custom select a material and color of the object can do.

In addition, the object is mapped with a URL link to information of an actual product corresponding to the object, and when the object is selected by a user in the digital twin space, the URL link may be provided to the user.

In addition, the operation of the processor may include: providing a camera interface for moving the inside of the 3D spatial model of the first building in a first-person view; and when the first-person view is located in a portion corresponding to the 3D model object corresponding to the stairs in the location of the spatial model for each floor, the position of the space model for each floor is moved upward or downward based on the moving direction of the first-person view. The method may further include outputting a subsequent spatial model for each floor in the first-person view.

In addition, the camera interface may be provided to a user account for which permission is approved from a user account of an actual building owner or lessee corresponding to the first building.

Also, the camera interface may be set to output the digital twin space as a first-person view in a portion corresponding to the window of the 3D space model.

In addition, the operation of the processor may include: providing a camera interface for moving the inside of the 3D spatial model of the first building in a first-person view; and when different users simultaneously use the camera interface in the first building, displaying the positions of the first-person viewpoints of different users and providing a dialogue interface for performing voice or chat conversations between the different users may further include.

Also, the operation of substituting the 3D spatial model may include an operation of setting and substituting the size of the 3D spatial model to correspond to the size of the 3D exterior in which the first building is expressed in the digital twin space.

In addition, the operation of substituting the three-dimensional space model is performed so that the difference between the volume of the 3D exterior in which the first building is expressed in the digital twin space and the volume of the outermost texture of the three-dimensional space model is within a preset range. It may include the operation of setting and substituting the size of the dimensional space model.

In addition, the operation of the processor may include: changing a direction in which a light source is irradiated in the digital twin space according to the passage of time; and generating a shadow on the opposite side of the object in contact with the direction in which the light source is irradiated.

According to an embodiment, the method for generating a digital twin space based on a building plan performed by the apparatus for generating a digital twin space based on a building plan according to an embodiment includes: generating a digital twin space including a plurality of buildings having exteriors implemented in 3D; obtaining a plan view, a cross-sectional view, and an elevation view corresponding to a first building among the plurality of buildings; generating a three-dimensional space model corresponding to the first building based on the plan view, cross-sectional view, and elevation view; and substituting the generated 3D spatial model of the first building at the location of the first building.

According to the embodiment of this document, by building a digital twin space where the inside and outside of the building are modeled in three dimensions based on the building blueprint, object customization, space view, authentication-based space visit, user-to-user conversation/chat/game in the digital twin space , it is possible to provide various linkage services such as linking product information to 3D objects and accessing metaverse through WebGL-based URLs.

The effects obtainable in the present invention are not limited to the above-mentioned effects, and other effects not mentioned may be clearly understood by those of ordinary skill in the art to which the present disclosure belongs from the description below. will be.

1 is a functional block diagram of an apparatus for generating a digital twin space according to an embodiment.
2 is an exemplary diagram of an operation of generating a digital twin space by capturing open source 3D spatial data according to an embodiment.
3 is a flowchart of an operation performed by an apparatus for generating a digital twin space according to an embodiment.
4 is an exemplary diagram of a digital twin space including a plurality of buildings whose exteriors are implemented in 3D according to an embodiment.
5 to 7 are exemplary views of an operation of generating a spatial model for each floor based on a plan view according to an exemplary embodiment.
8 and 9 are exemplary views of an operation of generating an internal space model in which a spatial model for each floor is connected based on a cross-sectional view according to an embodiment.
10 and 11 are exemplary views of an operation of generating an external space model for each side of a building based on an elevation view according to an embodiment.
12 is an exemplary diagram of an operation of substituting a 3D spatial model into a digital twin space according to an embodiment.

Hereinafter, various embodiments of the present invention will be described with reference to the accompanying drawings. However, it is not intended to limit the present invention to specific embodiments, and it should be understood that various modifications, equivalents, and/or alternatives of the embodiments of the present invention are included.

The digital twin space generating apparatus 100 according to the embodiment of this document may include a server that builds a digital twin space modeled in three dimensions and provides an application service platform that can be linked in the digital twin space.

1 is a functional block diagram of an apparatus 100 for generating a digital twin space based on a building plan (hereinafter, referred to as "a device for generating a digital twin space 100") according to an embodiment.

Referring to FIG. 1 , an apparatus 100 for generating a digital twin space according to an embodiment may include a memory 110 , a processor 120 , an input/output interface 130 , and a communication interface 140 .

The memory 110 may include a map information DB 111 , a drawing information DB 112 , a neural network DB 113 , and a command DB 114 .

The map information DB 111 may store 3D spatial data. For example, 3D spatial data may include spatial information that can be implemented in virtual reality (VR) and augmented reality (AR) by three-dimensionalizing 2D spatial information. The 3D spatial data may include open 3D spatial data provided by the Ministry of Land, Infrastructure and Transport, the National Geographic Information Service, and Google. In the 3D spatial data, information obtained by 3D modeling a real space and a real address specifying a location of the real space may be mapped and stored.

The drawing information DB 112 may store a building plan, object information related to the building plan, and a three-dimensional model in which the object information is implemented in three dimensions. Building blueprints include images of floor plans, sections, and elevations of buildings in which objects (ex. walls, doors, rooms, windows, wardrobes, washbasins, etc.) that make up the inside and outside of the building are expressed as information such as lines, symbols, and scales. can The drawing information DB 112 may map and store the relationship between the image included in the building design and the object specified by the image. For example, in the drawing information DB 112 , the type of object (eg, door, chair, staircase, window, etc.) that a specific symbol means and the type of object that a specific line segment means (eg, inner wall, outer wall, room, etc.) information can be stored. The drawing information DB 112 may store a three-dimensional model in which an appearance corresponding to each object is implemented in three dimensions.

The neural network DB 113 may store the learned neural network model. For example, the neural network DB 113 stores a neural network model learned based on a building design for learning (eg, plan, cross-section, elevation, etc.) in which classes for line information, symbol information, orientation information, and scale information are labeled. can

The command DB 114 may store commands capable of performing an operation of the processor 120 . For example, the command DB 114 may store computer code for performing operations corresponding to operations of the processor 120 to be described later.

The processor 120 may control the overall operation of the apparatus 100 for generating a digital twin space. The processor 120 may implement the modeling module 121 , the neural network module 122 , the control module 123 , and the interface module 124 . The processor 120 may execute the instructions stored in the memory 110 to drive the modeling module 121 , the neural network module 122 , the control module 123 , and the interface module 124 .

The modeling module 121 may implement a digital twin space (eg VR space) based on 3D spatial data stored in the map information DB 111 .

2 is an exemplary diagram of an operation of generating a digital twin space by capturing open source 3D spatial data according to an embodiment. Figure 2 (a) is a view of the Griffith Observatory on Google Maps, (b) is a view of changing the camera viewpoint of the Griffith Observatory on Google Maps, (c) is a Google map through a 3D texture capture program (ex. Blender, RenderDoc) of 3D spatial data captured, (d) is a re-realization of the digital twin space by applying a texture to the captured 3D spatial data.

Referring to FIG. 2 , the modeling module 121 captures open source 3D spatial data generated based on an actual map and creates a digital twin space that matches the open source 3D spatial data through a 3D modeling program (ex. Blender) can do.

The neural network module 122 may recognize image information included in the building blueprint and match it with object information meant by the image. The neural network DB 113 may recognize the types of lines and symbols included in the building blueprint, and learn and control a neural network model for specifying an orientation and a scale.

As an example, the neural network module 122 is a neural network model using an image identification algorithm based on a building design for learning (eg, plan, cross-section, elevation) in which classes for line information, symbol information, orientation information, and scale information are labeled. can be learned When the training of the neural network model is completed, when an image of any one of a floor plan, a cross-sectional view, and an elevation view is input to the neural network model, the feature values of the image are extracted through a convolution operation, and based on the extracted feature values, the It is possible to recognize the type of line or symbol included in the image and the position of the line or symbol, and specify the orientation and scale. The neural network module 124 may search the drawing information DB 112 for information on an object indicated by the recognized line or symbol, and map object information corresponding to each specified line or symbol.

The modeling module 121 may generate a three-dimensional space model by forming a three-dimensional model mapped to the object information of the drawing information DB 112 in a virtual space by the neural network module 122 according to specific object information in the building design. there is. For example, when the modeling module 121 recognizes a line segment specifying a wall among objects included in the building design, a 3D model corresponding to the wall may be formed in the virtual space. For example, when the modeling module 121 recognizes a chair symbol (eg, specifying a chair) among objects included in the building design, a 3D model corresponding to the chair may be formed in the virtual space. The modeling module 121 may generate a 3D space model by arranging 3D models corresponding to the corresponding object in the virtual space based on the location and type corresponding to the object included in the building blueprint.

The control module 123 may control elements related to the digital twin space. For example, the control module 123 may reflect the 3D space model generated by the modeling module 121 at a specific location in the digital twin space. The control module 123 may reflect actual information (eg, address, custom information, etc.) provided by the user of the service in the digital twin space. The control module 123 may change the direction in which the light source is irradiated in the digital twin space according to the passage of time, and may generate a shadow on the opposite side of the object in contact with the direction in which the light source is irradiated.

The interface module 124 may provide an interface that allows the user of the service to utilize a predetermined function in the digital twin space. For example, the interface module 124 provides a custom interface that allows the user to select an object (wall materials, flooring, furniture, home appliances, etc.) to be placed in the digital twin space, and allows the user to customize and select the material and color of the object. can do. For example, the interface module 124 may provide the user of the service with a camera interface that moves the digital twin space in the first person and outputs the viewing point in the first person. The interface module 124 may provide a light source interface that allows the irradiation direction of the light source to be adjusted by the user in the digital twin space. The interface module 124 may allow the user to access the digital twin space with only a URL through gamification of a building based on WebGL.

Operations performed by the modeling module 121 , the neural network module 122 , the control module 123 , and the interface module 124 described above may be understood as operations performed by the processor 120 .

The input/output interface 130 may include a hardware interface or a software interface that allows a server manager who controls the digital twin space generating apparatus 100 to input specific information or outputs specific information to the server manager.

The communication interface 140 enables the digital twin space generating device 100 to transmit and receive information to and from an external device (eg, a user terminal) through a communication network. To this end, the communication interface 140 may include a wireless communication module or a wired communication module.

The apparatus 100 for generating a digital twin space may be implemented as various types of devices capable of performing calculations through the processor 120 and transmitting/receiving information through a network. For example, it may include a portable communication device, a smart phone, a computer device, a portable multimedia device, a notebook computer, a tablet PC, and the like.

Hereinafter, an embodiment of the operation performed by the apparatus 100 for generating a digital twin space through the above-described configuration will be described with reference to FIG. 3 .

3 is a flowchart of an operation performed by the apparatus 100 for generating a digital twin space according to an embodiment.

First, the modeling module 121 may create a digital twin space including a plurality of buildings in which exteriors are implemented in 3D (S1010).

4 is an exemplary diagram of a digital twin space including a plurality of buildings whose exteriors are implemented in 3D according to an embodiment.

Referring to FIG. 4 , the modeling module 121 may generate a digital twin space including a plurality of buildings in which the exterior of the building is implemented as a 3D texture based on 3D spatial data captured based on an actual map. The modeling module 121 may specify the location of each building in the digital twin space by mapping the address information of the actual map to the building in the digital twin space.

Next, the modeling module 121 may acquire a plan view, a cross-sectional view, and an elevation view corresponding to at least one of a plurality of buildings included in the digital twin space ( S1020 ). For example, the modeling module 121 is based on the real address information mapped to the building implemented in the digital twin space and the real building owner or occupant's authentication (eg, comparison authentication between real estate registration image and service user information). It is possible to receive images of floor plans, sections, and elevations of the building from the owner.

Next, the modeling module 121 may generate a 3D spatial model of the building corresponding to the acquired building design based on the acquired floor plan, cross-sectional view, and elevation ( S1030 ). As an example, the modeling module 121 may generate a 3D space model by performing the operations of FIGS. 5 to 11 below.

5 to 7 are exemplary views of an operation of generating a spatial model for each floor based on a plan view according to an exemplary embodiment.

5 to 7, the modeling module 121 generates a spatial model of the first floor plan corresponding to FIG. 5 based on the plan view, and by generating a spatial model of the second floor plan corresponding to FIG. 6, respectively, You can create a spatial model for each floor.

To this end, the neural network module 122 may specify line segments and symbols described in the floor plan for each floor, and determine object information that the specified line segments and symbols mean from the drawing information DB 112 . For example, the neural network module 122 inputs a plan view obtained to a neural network model learned based on a floor plan for learning in which classes for line information and symbol information used in the design are labeled, and the line segments and symbols included in the plan view Location and type can be specified.

The modeling module 121 loads a 3D model of an object (eg, an inner wall and an outer wall, etc.) corresponding to the type of line segment included in the obtained plan view from the drawing information DB 112, and loads a virtual model corresponding to the position of the line segment in the plan view. can be created in space. The modeling module 121 loads a three-dimensional model of an object (eg, a sink, a chair, etc.) corresponding to the type of symbol included in the obtained floor plan from the drawing information DB 112, and loads a virtual model corresponding to the symbol position of the floor plan. can be created in space.

In this way, the modeling module 121 loads the three-dimensional model of the object corresponding to the lines and symbols included in the obtained floor plan for each floor into the virtual space, and generates a three-dimensional space model for each floor corresponding to each floor plan as shown in FIG. 7 . can do. The modeling module 121 may map a URL link for information on an actual product corresponding to the corresponding object to the 3D model object included in the spatial model for each floor. Accordingly, when a 3D model object is selected by the user in the digital twin space, the modeling module 121 may provide the user with a URL link for information of the corresponding object.

8 and 9 are exemplary views of an operation of generating an internal space model in which a spatial model for each floor is connected based on a cross-sectional view according to an embodiment.

8 and 9 , the modeling module 121 applies the virtual height corresponding to the height information of each floor described in the cross-sectional view of FIG. 8 to the previously generated space model for each floor to the space model for each floor, and described in the cross-sectional view. According to the order of each floor, an internal space model in which the space models for each floor are spaced apart by the virtual height and connected may be generated.

To this end, the modeling module 121 specifies the line segments and symbols described in the cross-sectional view of FIG. 8 through the neural network module 122, and can determine object information that the specified line segments and symbols mean from the drawing information DB 112. . For example, the neural network module 122 enters the obtained cross-section into the neural network model trained based on the cross-section for learning in which classes for line, symbol, scale, and orientation information used in the design are labeled, and is included in the cross-section. It is possible to specify the position and type of lines and symbols, and to determine scale and orientation information.

The modeling module 121 applies the virtual height of the object (eg, the height of the wall) corresponding to the type of line segment included in the cross-sectional view to the space model for each floor, and the space model for each floor based on the scale and orientation recognized in the cross-sectional view. Among the plurality of surfaces it has, the surface corresponding to the surface described in the cross-sectional view is determined, the arrangement surface of the space model for each floor is arranged based on the surface described in the cross-sectional view, and the space model for each floor is drawn according to the order of each floor described in the cross-sectional view. An interior space model can be created as shown in FIG. 9 by connecting the layers at a distance as much as the virtual height of the floor.

10 and 11 are exemplary views of an operation of generating an external space model for each side of a building based on an elevation view according to an embodiment.

10 and 11 , the modeling module 121 may generate an external space model of each side (eg, east side, west side, south side, north side) constituting the exterior of the building based on the elevation view. there is.

To this end, the modeling module 121 specifies the line segments and symbols described in the elevation view of FIG. 10 through the neural network module 122, and can determine object information that the specified line segments and symbols mean from the drawing information DB 112. . For example, the neural network module 122 inputs the obtained elevation to the neural network model learned based on the elevation for learning in which classes for lines, symbols, scales, and orientation information used in the design are labeled. It is possible to specify the position and type of lines and symbols, and to determine scale and orientation information.

The modeling module 121 creates a three-dimensional model of an object (ex. exterior wall, window, handrail) corresponding to the type of line and symbol included in the elevation view in a virtual space, and each side (ex. east side) constituting the exterior of the building face, west face, south face, north face) and create an external space model connecting each face according to azimuth and scale. Thereafter, the modeling module 121 is based on the orientation and scale information of the building design, the height information of each floor included in the external space model generated by the elevation view, and the internal space model generated by the floor plan and the cross-sectional view. By connecting the height information of each floor to correspond to each other, it is possible to create a three-dimensional space model in which both the inside and outside of the building are realized.

12 is an exemplary diagram of an operation of substituting a 3D spatial model into a digital twin space according to an embodiment.

Referring to FIG. 12 , the control module 123 is located in a location of a building corresponding to information of a building blueprint obtained from among a plurality of buildings (eg, buildings in the state of FIG. 4 ) in which a 3D appearance is implemented in a digital twin space in a three-dimensional space. A model may be substituted (S1040). The control module 123 compares the address information mapped to the building in which the 3D exterior of the digital twin space is implemented with the address information mapped to the obtained building blueprint, and the three-dimensional space generated according to the process of FIGS. 5 to 11 . model can be substituted.

On the other hand, if the 3D space model generated by the S1030 operation is generated in a virtual environment (project) different from the digital twin space created by the S1010 operation, a heterogeneous size difference may occur when substituting the 3D spatial model into the digital twin space. can To solve this, the control module 123 may reset the size of the 3D space model to be substituted so that it corresponds to the size of the 3D exterior implemented in the digital twin space. For example, the control module 123 controls the outermost part of the three-dimensional space model so that the difference between the volume of the building having the 3D exterior in the digital twin space and the volume of the outermost texture of the three-dimensional space model is within a preset range. By adjusting the volume, it can be substituted into the digital twin space.

The interface module 124 may provide a digital twin space-based application service in which the three-dimensional space model is reflected (S1050)

As an example, the interface module 124 may provide a camera interface that moves the interior of a building reflecting a 3D space model in a digital twin space from a first-person view. When the first-person view is located in a portion corresponding to the 3D model object corresponding to the stairs of the building design, the interface module 124 provides a space model for each floor of the current location based on the movement direction of the first-person view manipulated by the user. It is possible to output a space model for each floor from the location to the upper or lower part in a first-person view.

For example, the interface module 124 may control the movement of the first-person view to be permitted only to a user account that has received permission from a user account corresponding to an actual building owner or a tenant of the building corresponding to the building.

As an example, the interface module 124 may output the external digital twin space of the 3D space model to the window portion as a first-person view when the first-person view views the object corresponding to the window in the 3D space model. .

For example, when different users use the camera interface in the 3D space model of the same building at the same time, the interface module 124 displays the positions of the first-person viewpoints of different users, and voice conversation or chatting between different users. A conversation interface for conducting a conversation may be provided.

For example, when different users use the camera interface in the 3D space model of the same building at the same time, the interface module 124 may be configured to display a predetermined 3D space at a certain point inside the 3D space model. By creating a model object, it is possible to provide a game interface for treasure hunting.

According to the above-described embodiment, by constructing a digital twin space where the inside and outside of the building is modeled in three dimensions based on the building blueprint, object customization, space view, authentication-based space visit, user-to-user conversation/chat/game, It is possible to provide various linkage services such as linkage of product information to 3D objects and metaverse access through WebGL-based URL.

The various embodiments of this document and terms used therein are not intended to limit the technical features described in this document to specific embodiments, but it should be understood to include various modifications, equivalents, or substitutions of the embodiments. In connection with the description of the drawings, like reference numerals may be used for similar or related components. The singular form of the noun corresponding to the item may include one or more items, unless the relevant context clearly dictates otherwise.

As used herein, “A or B”, “at least one of A and B”, “at least one of A or B,” “A, B or C,” “at least one of A, B and C,” and “A , B, or C" each may include all possible combinations of items listed together in the corresponding one of the phrases. Terms such as "first", "second", or "first" or "second" may simply be used to distinguish an element from other such elements, and may refer elements to other aspects (e.g., importance or order). ) is not limited to that one (eg first) component is “coupled” or “connected” to another (eg, second) component with or without the terms “functionally” or “communicatively” When referenced, it means that one component can be coupled to another component directly (eg, by wire), wirelessly, or through a third component.

As used herein, the term “module” may include a unit implemented in hardware, software, or firmware, and may be used interchangeably with terms such as, for example, logic, logic block, component, or circuit. A module may be an integrally formed part or a minimum unit of a part or a part thereof that performs one or more functions. For example, according to an embodiment, the module may be implemented in the form of an application-specific integrated circuit (ASIC).

Various embodiments of the present document may be implemented as software (eg, a program) including one or more instructions stored in a storage medium (eg, memory) readable by a device (eg, an electronic device). The storage medium may include random access memory (RAM), memory buffers, hard drives, databases, erasable programmable read-only memory (EPROM), electrically erasable read-only memory (EEPROM), read-only memory (ROM) and/or the like. may include

In addition, the processor of the embodiments of the present document may call at least one of the one or more instructions stored from the storage medium and execute it. This enables the device to be operated to perform at least one function according to at least one command called. One or more of these instructions may include code generated by a compiler or code executable by an interpreter. The processor may be a general-purpose processor, a Field Programmable Gate Array (FPGA), an Application Specific Integrated Circuit (ASIC), a Digital Signal Processor (DSP), and/or the like.

The device-readable storage medium may be provided in the form of a non-transitory storage medium. Here, 'non-transitory' only means that the storage medium is a tangible device and does not include a signal (eg, electromagnetic wave), and this term refers to cases where data is semi-permanently stored in a storage medium and temporarily stored. It does not distinguish between cases where

Methods according to various embodiments disclosed in this document may be provided by being included in a computer program product. Computer program products may be traded between sellers and buyers as commodities. The computer program product is distributed in the form of a machine-readable storage medium (eg compact disc read only memory (CD-ROM)), or through an application store (eg Play Store) or on two user devices (eg, compact disc read only memory (CD-ROM)). : can be distributed (eg, downloaded or uploaded) online, directly between smartphones). In the case of online distribution, at least a part of the computer program product may be temporarily stored or temporarily created in a machine-readable storage medium such as a memory of a server of a manufacturer, a server of an application store, or a relay server.

According to various embodiments, each component (eg, a module or a program) of the described components may include a singular or a plurality of entities. According to various embodiments, one or more components or operations among the above-described corresponding components may be omitted, or one or more other components or operations may be added. Alternatively or additionally, a plurality of components (eg, a module or a program) may be integrated into one component. In this case, the integrated component may perform one or more functions of each component of the plurality of components identically or similarly to those performed by the corresponding component among the plurality of components prior to integration. According to various embodiments, operations performed by a module, program, or other component are executed sequentially, in parallel, iteratively, or heuristically, or one or more of the operations are executed in a different order, omitted, or , or one or more other operations may be added.

Claims (12)

one or more memories storing instructions for performing predetermined operations; and one or more processors operatively coupled to the one or more memories and configured to execute the instructions;
The operation of the processor is
An operation of creating a digital twin space including a plurality of buildings whose exterior is implemented in 3D in a first virtual environment;
obtaining a plan view, a cross-sectional view, and an elevation view for realizing the inside and outside of a first building among the plurality of buildings;
generating a three-dimensional space model in which the interior and exterior of the first building are implemented using a neural network model in a second virtual environment different from the first virtual environment based on the plan view, cross-sectional view, and elevation view; and
and substituting a three-dimensional spatial model of the second virtual environment at the location of the first building in the first virtual environment,
The substituting operation is
In order to make the sizes of the first building and the 3D space model implemented in different virtual environments correspond to each other in the same virtual environment, the volume of the outermost texture of the 3D space model loaded into the first virtual environment and the and controlling and substituting the size of the 3D spatial model of the first virtual environment so that the difference in volume of the 3D exterior of the first building previously implemented in the first virtual environment is within a preset range.
A device for creating a digital twin space based on a building blueprint.
According to claim 1,
The operation of creating the digital twin space is
Generating the exterior texture of each building based on the 3D spatial data generated based on the actual map and mapping the actual address information to each building,
The operation of obtaining the plan view, sectional view and elevation view is,
Comprising the operation of acquiring images of the floor plan, sectional view, and elevation of the building from the owner or resident based on the authentication of the real building owner or resident corresponding to the real address information of the building implemented in the digital twin space,
A device for creating a digital twin space based on a building blueprint.
According to claim 1,
The operation of generating the three-dimensional space model is,
generating a spatial model for each floor based on a floor plan corresponding to each floor;
According to the height information of each floor described in the cross-sectional view, a virtual height corresponding to the height information of each floor is formed in the space model for each floor, and the virtual height of each floor is formed in the space model for each floor according to the order of each floor described in the cross-sectional view An operation of creating a connected interior space model by spaced enough; and
Create an external space model for each side described in the elevation view, and connect the external space model to the internal space model so that the height information of each floor described in the elevation view and the height information of each floor described in the cross-sectional view correspond to the three-dimensional comprising the operation of generating a spatial model;
A device for creating a digital twin space based on a building blueprint.
4. The method of claim 3,
The operation of creating a spatial model for each floor based on the floor plan is,
specifying the line segments and symbols described in the plan view;
generating a three-dimensional model of an object corresponding to a line segment specified in the plan view; and
Including the operation of generating a three-dimensional model of the object corresponding to the symbol specified in the plan view,
A device for creating a digital twin space based on a building blueprint.
5. The method of claim 4,
The operation of specifying the line segment and symbol is,
Including the operation of specifying the line segments and symbols included in the plan view by inputting the plan view into a neural network model learned based on the learning floor plan in which classes for line information and symbol information are labeled,
A device for creating a digital twin space based on a building blueprint.
4. The method of claim 3,
The operation of generating the three-dimensional space model is,
Further comprising the operation of providing a custom interface for a user to select an object to be placed in the three-dimensional space model, and to allow the user to custom select a material and color of the object,
A device for creating a digital twin space based on a building blueprint.
7. The method of claim 6,
The object is
A URL link to information of an actual product corresponding to the object is mapped, and when the object is selected by a user in the digital twin space, the URL link is provided to the user,
A device for creating a digital twin space based on a building blueprint.
4. The method of claim 3,
The operation of the processor is
providing a camera interface for moving the inside of the 3D spatial model of the first building to a first-person view; and
When the first-person view is located in a portion corresponding to the 3D model object corresponding to the stairs in the location of the spatial model for each floor, the location of the space model for each floor leads to the upper or lower part based on the movement direction of the first-person view Further comprising the operation of outputting the spatial model for each floor in the first-person view,
A device for creating a digital twin space based on a building blueprint.
4. The method of claim 3,
The operation of the processor is
providing a camera interface for moving the inside of the 3D spatial model of the first building to a first-person view; and
When different users use the camera interface in the first building at the same time, the operation of displaying the positions of the first-person viewpoints of different users and providing a dialog interface for performing voice or chatting conversations between the different users more containing,
A device for creating a digital twin space based on a building blueprint.
delete According to claim 1,
changing the direction in which the light source is irradiated in the digital twin space according to the passage of time; and
Further comprising the operation of generating a shadow on the opposite side of the object in contact with the direction in which the light source is irradiated,
A device for creating a digital twin space based on a building blueprint.
In the building design-based digital twin space creation method performed by the building design-based digital twin space creation device,
Creating a digital twin space including a plurality of buildings in which the exterior is implemented in 3D in a first virtual environment;
obtaining a plan view, a cross-sectional view, and an elevation view for the implementation of the inside and outside of a first building among the plurality of buildings;
generating a three-dimensional spatial model embodied inside and outside the first building using a neural network model in a second virtual environment different from the first virtual environment based on the plan view, cross-sectional view, and elevation view; and
substituting a three-dimensional spatial model of the second virtual environment at the location of the first building in the first virtual environment;
The substituting step is
In order to make the sizes of the first building and the 3D space model implemented in different virtual environments correspond to each other in the same virtual environment, the volume of the outermost texture of the 3D space model loaded into the first virtual environment and the Controlling and substituting the size of the 3D spatial model of the first virtual environment so that the difference in volume of the 3D exterior of the first building previously implemented in the first virtual environment is within a preset range,
A method of creating a digital twin space based on a building blueprint.

Images