Digital modular decoration method and system based on building information

Abstract

The invention belongs to the field of digital decoration, and provides a digital modular decoration method and system based on building information, and the method comprises the steps: constructing a digital model of a to-be-decorated building based on a building information model technology; a self-encoder is used for automatically generating a modular decoration design scheme meeting the building structure and user requirements, and the modular decoration design scheme comprises functional region division, module size, shape and material information; according to the modular decoration design scheme, needed prefabricated decoration modules are determined, the installation position and sequence of the prefabricated decoration modules are generated in combination with the digital model, and the prefabricated decoration modules are uniquely coded based on the installation position and sequence; and displaying the digital model and the installation position of the prefabricated decoration module on an information terminal, and marking the number of the corresponding prefabricated decoration module.

Description

Technical Field

[0001] The present invention belongs to the field of digital decoration, and in particular relates to a digital modular decoration method and system based on building information. Background Art

[0002] Modular decoration is a new type of decoration method with standardization and prefabrication as its core concept. It decomposes the decoration process into multiple independent functional modules, and uses factory prefabrication and on-site assembly to achieve efficient, high-quality and low-cost decoration solutions. Modular decoration has been widely used in residential, commercial, office and public facilities. Its core goal is to improve decoration efficiency, save costs, reduce resource waste and meet users' needs for personalization and functional diversification through refined design and manufacturing.

[0003] Although modular decoration has the advantages of high efficiency, standardization and sustainability, in practical applications, there are still the following major technical problems: modular decoration needs to be designed according to different building structures and user needs, and the current design process still relies on manual design or traditional rule-based methods; the spatial layout between modules does not fully consider the spatial topological constraints such as the adjacency between functional areas (such as the kitchen and the dining room should be adjacent) and pipeline connectivity (such as the bathroom and the water supply and drainage system), resulting in unreasonable logic of the generated scheme. During the construction stage, the size, connection or physical installation constraints between modules are not fully considered, and the generated scheme may encounter actual construction difficulties or mismatches. Summary of the invention

[0004] In order to solve the problems in the prior art, the present invention provides a digital modular decoration method based on building information, the method comprising the following steps:

[0005] Constructing a digital model of the building to be renovated based on building information modeling technology, wherein the model includes building structure information, spatial layout information, and functional requirement information;

[0006] Using an autoencoder to automatically generate a modular decoration design plan that meets the building structure and user needs, the modular decoration design plan includes functional area division, module size, shape and material information;

[0007] Determine the required prefabricated decoration modules according to the modular decoration design scheme, generate the installation positions and sequence of the prefabricated decoration modules in combination with the digital model, and uniquely encode the prefabricated decoration modules based on the installation positions and sequence;

[0008] The digital model and the installation position of the prefabricated decoration module are displayed on the information terminal, and the corresponding prefabricated decoration module number is marked.

[0009] Furthermore, the method of using an autoencoder to automatically generate a modular decoration design scheme that meets the building structure and user needs includes:

[0010] Input data includes building structure information, user needs, and spatial topological relationships;

[0011] The building structure information is extracted from the building information model data and represented as a multi-dimensional tensor, including: geometric features, functional features, and connection features;

[0012] The user requirements are expressed as condition vectors, including: decoration style, budget constraints, and functional requirements;

[0013] The spatial topological relationship is represented as a graph, including nodes: representing the characteristics of each functional area module, and edges: representing the relationship between modules;

[0014] The encoder maps architectural structure information and user needs into a latent space:

[0015] Building information processing: geometric features are input into the convolutional network to extract spatial features, and functional features are input into the fully connected layer to generate functional embedding;

[0016] Spatial relationship modeling: Use graph convolutional networks to embed topological graphs and output module relationship features;

[0017] User demand processing: User demand input is embedded in the layer to generate demand features;

[0018] Output latent distribution: The encoder outputs the mean and variance of the latent variable, which is used to sample the latent variable;

[0019] The decoder generates decoration design solutions from latent variables and user needs:

[0020] Functional area division: Use the conditional embedding layer to generate the distribution matrix of functional areas based on the latent variables;

[0021] Module size: output the length, width and height of each module;

[0022] Module shape: Output the geometric shape parameters of the module;

[0023] Material information: Output the material of the module.

[0024] Furthermore, the autoencoder includes the following constraints:

[0025] Adjacency constraints ensure the rationality of functional areas between modules;

[0026] Connection constraints ensure that pipelines between modules are correctly connected;

[0027] The spatial distribution between modules should not overlap.

[0028] Furthermore, the unique numbering of the prefabricated decoration modules based on the installation position and order includes: extracting the function and position data of each module from the BIM model, connecting the function and position, and automatically generating the unique code by increasing the module quantity.

[0029] Further, the displaying of the digital model and the installation position of the prefabricated decoration module on the information terminal and marking the corresponding prefabricated decoration module number includes:

[0030] Export 3D digital models from BIM systems;

[0031] Loading the three-dimensional model on the information terminal;

[0032] The user clicks on a module in the model to view detailed module information;

[0033] After selecting a module, the system will highlight the corresponding module in the model and automatically locate it to the specific installation location;

[0034] The digital model and the installation location of the prefabricated decoration modules are displayed through the information terminal, and the corresponding numbers are marked.

[0035] Another aspect of the present invention is to provide a digital modular decoration system based on building information, the system comprising the following modules:

[0036] A three-dimensional module is used to construct a digital model of the building to be renovated based on building information modeling technology, wherein the model includes building structure information, spatial layout information and functional requirement information;

[0037] A generation module, for automatically generating a modular decoration design scheme that meets the building structure and user needs using an autoencoder, wherein the modular decoration design scheme includes functional area division, module size, shape and material information;

[0038] A coding module, used to determine the required prefabricated decoration modules according to the modular decoration design scheme, generate the installation position and sequence of the prefabricated decoration modules in combination with the digital model, and uniquely encode the prefabricated decoration modules based on the installation position and sequence;

[0039] The display module is used to display the digital model and the installation position of the prefabricated decoration module on the information terminal, and mark the corresponding prefabricated decoration module number.

[0040] Furthermore, the method of using an autoencoder to automatically generate a modular decoration design scheme that meets the building structure and user needs includes:

[0041] Input data includes building structure information, user needs, and spatial topological relationships;

[0042] The building structure information is extracted from the building information model data and represented as a multi-dimensional tensor, including: geometric features, functional features, and connection features;

[0043] The user requirements are expressed as condition vectors, including: decoration style, budget constraints, and functional requirements;

[0044] The spatial topological relationship is represented as a graph, including nodes: representing the characteristics of each functional area module, and edges: representing the relationship between modules;

[0045] The encoder maps architectural structure information and user needs into a latent space:

[0046] Building information processing: geometric features are input into the convolutional network to extract spatial features, and functional features are input into the fully connected layer to generate functional embedding;

[0047] Spatial relationship modeling: Use graph convolutional networks to embed topological graphs and output module relationship features;

[0048] User demand processing: User demand input is embedded in the layer to generate demand features;

[0049] Output latent distribution: The encoder outputs the mean and variance of the latent variable, which is used to sample the latent variable;

[0050] The decoder generates decoration design solutions from latent variables and user needs:

[0051] Functional area division: Use the conditional embedding layer to generate the distribution matrix of functional areas based on the latent variables;

[0052] Module size: output the length, width and height of each module;

[0053] Module shape: Output the geometric shape parameters of the module;

[0054] Material information: Output the material of the module.

[0055] Furthermore, the autoencoder includes the following constraints:

[0056] Adjacency constraints ensure the rationality of functional areas between modules;

[0057] Connection constraints ensure that pipelines between modules are correctly connected;

[0058] The spatial distribution between modules should not overlap.

[0059] Furthermore, the unique numbering of the prefabricated decoration modules based on the installation position and order includes: extracting the function and position data of each module from the BIM model, connecting the function and position, and automatically generating the unique code by increasing the module quantity.

[0060] Further, the displaying of the digital model and the installation position of the prefabricated decoration module on the information terminal and marking the corresponding prefabricated decoration module number includes:

[0061] Export 3D digital models from BIM systems;

[0062] Loading the three-dimensional model on the information terminal;

[0063] The user clicks on a module in the model to view detailed module information;

[0064] After selecting a module, the system will highlight the corresponding module in the model and automatically locate it to the specific installation location;

[0065] The digital model and the installation location of the prefabricated decoration modules are displayed through the information terminal, and the corresponding numbers are marked.

[0066] The modular decoration design method of the present invention automatically generates a decoration design scheme that meets the building structure and user needs through an autoencoder, which significantly improves the design efficiency and scheme quality, and solves the core technical problems in traditional modular decoration. Specifically, it has the following beneficial effects:

[0067] Based on the conditional generation method, it supports users to adjust their needs (such as style, budget, and functional zoning) in real time and quickly generate high-quality customized solutions. The adjacency and connectivity between modules are modeled through graph neural networks to ensure the logic of the generated solution in terms of spatial layout and functional zoning. During the solution generation process, the size conflicts, pipeline connections, and space overlaps between modules are automatically detected and optimized to ensure that the solution meets the feasibility and consistency of actual construction. Based on multi-objective optimization constraints, it ensures that the layout of functional zoning (such as kitchen and dining room, bedroom and bathroom) is reasonable and meets actual usage requirements. In the design stage, the pipeline connection paths (such as water, electricity, and gas) between modules are clarified to avoid additional adjustments caused by design defects in later construction. Automatically detect and eliminate size and position conflicts between modules to ensure that the generated solution can be directly used for construction and improve actual execution efficiency.

[0068] Through innovative generation models and optimization methods, the present invention effectively solves the technical problems in current modular decoration, such as low design efficiency, unstable solution quality, lack of personalization and diversity support, and poor construction feasibility, and provides an intelligent, efficient and high-quality technical solution for modular decoration. BRIEF DESCRIPTION OF THE DRAWINGS

[0069] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0070] Figure 1 is a flow chart of the method of the present invention. DETAILED DESCRIPTION

[0071] Below, the invention is preferably described in conjunction with the accompanying drawings and specific implementation methods.

[0072] This embodiment solves the above problem through the following steps:

[0073] In one embodiment, reference Figure 1 The present invention provides a digital modular decoration method based on building information, which combines Building Information Modeling (BIM) technology with modular decoration design technology to digitally construct an information model in the building decoration process, and modularly decompose and optimize the decoration plan based on the information model, thereby realizing efficient coordination and full-process digital management of decoration design, module production, on-site construction and subsequent operation and maintenance. Specifically, it includes the following steps:

[0074] Step S10, constructing a digital model of the building to be renovated based on building information modeling technology, wherein the model includes building structure information, space layout information and functional requirement information.

[0075] In this step, the physical structure data of the building to be renovated is obtained through laser scanning, drone mapping or existing design drawings, including the geometric shape and size information of the building's walls, floor slabs, columns and beams, and the layout information of the building's functional zoning, ventilation ducts, electrical wiring, and water supply and drainage ducts;

[0076] Using Building Information Modeling (BIM) technology, the collected building physical information is integrated with the decoration requirements to establish a three-dimensional digital model, which includes not only the geometric form of the building structure, but also its attribute information, such as component material type, strength, durability parameters, etc.

[0077] Define and embed functional area division information based on the user's decoration requirements, including the use of the building space (such as living room, bedroom, kitchen, etc.), functional layout requirements (such as furniture arrangement, equipment installation location), and decoration style preferences (such as modern, simple, retro, etc.);

[0078] Verify and refine the initially established digital model to ensure the geometric accuracy, functional requirements description and completeness and accuracy of the attribute information of the model;

[0079] The constructed digital model is stored as a format file that supports multi-dimensional information. The file can support the analysis and automatic generation of subsequent modular decoration designs, ensuring that all steps in the decoration process are coordinated based on the digital model.

[0080] Step S20, using an autoencoder to automatically generate a modular decoration design plan that meets the building structure and user needs, wherein the modular decoration design plan includes functional area division, module size, shape and material information.

[0081] In this step, the building information model (BIM) data and user demand input are combined to generate a modular decoration design plan including functional area division, module size, module shape and material information. The specific process is as follows:

[0082] Input data includes building structure information, user needs, and spatial topological relationships.

[0083] Building structure information is extracted from BIM data and represented as a multi-dimensional tensor, including the following:

[0084] Geometric features: three-dimensional spatial features (such as the geometric shape and size of walls, floors, columns and beams).

[0085] Functional features: initial partition information of functional areas, such as living room, kitchen, bedroom, etc.

[0086] Connection characteristics: information about internal building wiring connections, such as electrical circuits, water pipes, ventilation systems, etc.

[0087] User requirements are expressed as a condition vector, including:

[0088] Decoration style: such as modern, simple, retro.

[0089] Budget constraint: The total budget acceptable to the user.

[0090] Functional requirements: functional requirements for module division (such as the bedroom must be close to the bathroom).

[0091] The spatial relationship between modules is represented as a graph:

[0092] Node: represents the characteristics of each functional area module, such as the center point of each module.

[0093] Edge: represents the relationship between modules, such as the adjacency between module i and module j.

[0094] The model structure consists of an encoder and a decoder.

[0095] The encoder maps architectural structure information and user needs into a latent space:

[0096] Building Information Processing:

[0097] The geometric features are input into the convolutional network to extract spatial features.

[0098] The functional features are input into the fully connected layer to generate functional embedding.

[0099] Spatial relationship modeling:

[0100] The topological graph is embedded using a graph convolutional network (GCN) and the module relationship features are output.

[0101] User demand processing:

[0102] User requirements are input into the embedding layer to generate requirement features.

[0103] Output potential distribution:

[0104] The encoder outputs the mean and variance of the latent variable, which is used to sample the latent variable.

[0105] The decoder generates decoration design solutions from latent variables and user needs:

[0106] Functional area division:

[0107] Using the conditional embedding layer, a distribution matrix of functional areas is generated according to the latent variables.

[0108] Such as the center point of the living room, kitchen, and bedroom.

[0109] Module size:

[0110] Output the length, width and height of each module.

[0111] Such as the dimensions of the bedroom module.

[0112] Module shape:

[0113] Output the geometric parameters of the module, such as wall thickness, window size, etc.

[0114] Material Information:

[0115] Output the material of the module, such as the surface material of a wall.

[0116] In order to obtain the correct solution, the following constraints are required during the encoding process:

[0117] Adjacency constraints ensure the rationality of functional areas between modules:

[0118]

[0119] Among them, L adjacency Indicates the adjacency constraint value, which is not greater than the preset threshold; d ij represents the distance between module i and module j, E represents the module set; d max Indicates the maximum allowed distance between adjacent modules.

[0120] Connection constraints ensure that the pipelines between modules are connected correctly:

[0121]

[0122] Among them, L connectivity Represents the connection constraint value, C i represents the connection point of pipeline i, C j represents the connection point of pipeline j, and || ||2 represents the L2 normal form.

[0123] The spatial distribution between modules should not overlap:

[0124]

[0125] Among them, L overlap It represents the amount of spatial superposition, and OverlapArea(i,j) represents the overlapping area of ​​modules i and j.

[0126] The generated modular decoration design plan includes the following information:

[0127] Functional area division: location, coordinates of the center point of the functional area; distribution, coordinates of the boundary of the functional area.

[0128] Module size: length, width and height, physical dimensions of each module, module shape:

[0129] Geometric parameters: e.g. the curvature of a curved wall.

[0130] Material information: such as the material used for the wall.

[0131] In this step, the encoder processes the input data, learns the distribution characteristics of building information and user needs, and establishes associations in the latent space. This learning mechanism ensures that the functional division and spatial layout of the modules are based on the building structure; the generated latent space captures a variety of potential design possibilities.

[0132] The decoder combines user requirements (e.g., style, budget) to perform conditional generation in the latent space, ensuring that the output solution meets the constraints specified by the user.

[0133] Graph neural networks model the adjacency and connectivity properties of modules so that the generated solutions satisfy the physical constraints between functional areas and modules.

[0134] The key information of the building structure is captured through the geometric features, functional area features and spatial relationship modeling of BIM data.

[0135] The user demand vector is input as a conditional variable to ensure the personalization and controllability of the generated solution.

[0136] The sampling mechanism of the latent space is able to generate diverse solutions while the decoder ensures that these solutions conform to practical constraints.

[0137] Step S30, according to the modular decoration design scheme, determine the required prefabricated decoration modules, generate the installation positions and sequence of the prefabricated decoration modules in combination with the digital model, and uniquely number the prefabricated decoration modules based on the installation positions and sequence.

[0138] Extracting module information from modular decoration design scheme

[0139] For example, the modular decoration design plan shows that the living room area requires the following modules:

[0140] Wall module:

[0141] Size: 2.5 meters long, 0.2 meters wide, 3 meters high;

[0142] Materials: concrete + white paint;

[0143] Function: Partition wall with hidden wiring trough.

[0144] Floor module:

[0145] Size: 0.6m x 0.6m;

[0146] Material: Ceramic tile (grey non-slip).

[0147] Ceiling modules:

[0148] Size: 2m x 2m per piece;

[0149] Material: Lightweight aluminum alloy with integrated LED lights.

[0150] Modules are classified according to function and area:

[0151] Wall module:

[0152] 2 standard partition walls to separate the living room and dining room;

[0153] 1 wall with wire routing trough, used for TV background wall.

[0154] Floor module:

[0155] 30 non-slip tile floor modules are required for the living room (total area 18 m2).

[0156] Ceiling modules:

[0157] The integrated lighting module requires 4 pieces (covering 8 square meters).

[0158] Check whether each module meets the prefabrication requirements:

[0159] The wall modules are divided into standard-sized units, each 2.5 meters long and 3 meters high;

[0160] Floor and ceiling modules do not require adjustment and are available in standard sizes.

[0161] Get the specific installation location and area of ​​the module from the BIM model:

[0162] Wall module:

[0163] The partition wall module is located in the straight area from the entrance of the living room to the left side of the dining room;

[0164] The installation start and end points of each wall module are marked directly on the BIM model, for example:

[0165] Block 1: start point (0,0,0), end point (2.5,0,3).

[0166] Floor module:

[0167] The floor modules start on the left side of the living room and are arranged in a grid;

[0168] The installation order is from left to right and from front to back, and the coordinates of each floor module are clearly marked in the BIM model.

[0169] Ceiling modules:

[0170] A ceiling module with integrated LED lights is installed in the center of the living room, ensuring even distribution.

[0171] Determine the reasonable installation sequence according to the area and function of the modules:

[0172] Wall modules are preferred:

[0173] The wall needs to be installed first to ensure that the space division is completed before subsequent operations;

[0174] The installation sequence is divided by area, first install the partition wall, then install the background wall.

[0175] The floor module is followed by:

[0176] Lay in a grid order to avoid damage to the floor caused by subsequent construction.

[0177] Ceiling module final:

[0178] After the wall and floor modules are installed, the ceiling and lighting fixtures can be arranged.

[0179] Modules are uniquely numbered using a combination of module function, area, and sequence:

[0180] Numbering format: [Function code]-[Area code]-[Sequence number].

[0181] Example:

[0182] Wall module number: WT-01-001

[0183] Function code: WT (wall module);

[0184] Area code: 01 (living room);

[0185] Sequence number: 001 (Partition wall No. 1).

[0186] Floor module number: FL-01-015

[0187] Function code: FL (floor module);

[0188] Area code: 01 (living room);

[0189] Sequence number: 015 (15th tile).

[0190] Ceiling Module No.: CL-01-003

[0191] Function code: CL (ceiling module);

[0192] Area code: 01 (living room);

[0193] Sequence number: 003 (the 3rd ceiling).

[0194] The system extracts the function and location data of each module from the BIM model and automatically generates a number.

[0195] The example generates the numbered results:

[0196] Wall module:

[0197] Block 1: WT-01-001

[0198] Block 2: WT-01-002

[0199] Floor module:

[0200] Block 1: FL-01-001

[0201] Block 30: FL-01-030

[0202] Ceiling modules:

[0203] Block 1: CL-01-001

[0204] Block 4: CL-01-004

[0205] The factory produces corresponding modules according to the numbers and marks the numbers on the surface of the modules for easy transportation and installation.

[0206] For example, the wall module WT-01-001 is marked with this number after production, along with the installation area and location.

[0207] Modules are packaged and transported according to numbers and arranged in the order of installation during storage to reduce on-site search time.

[0208] Workers install according to the numbered list and the installation location of the BIM model to ensure quick matching:

[0209] For example, looking at the number WT-01-001, the corresponding location in the BIM model is the wall installation at the entrance of the living room.

[0210] Step S40, displaying the digital model and the installation position of the prefabricated decoration module on the information terminal, and marking the corresponding prefabricated decoration module number.

[0211] The digital model and the installation location of the prefabricated decoration modules are displayed through the information terminal, and the corresponding prefabricated decoration module numbers are clearly marked to ensure that the construction personnel can accurately locate and quickly match the modules during the installation process. The following is a detailed description of the specific implementation method:

[0212] Export the three-dimensional digital model from the BIM system, including building structure information, module division, functional areas, etc.

[0213] Load the 3D model on an information terminal (such as a tablet, smartphone, or AR / VR device);

[0214] Provides multi-viewing functions, including top view, cross-section view, local magnification, etc.

[0215] For example, a complete building model is displayed on the information terminal, in which the living room area is marked with wall, floor and ceiling modules.

[0216] Users can click on a module in the model to view detailed module information, including size, material, functional purpose and number.

[0217] After selecting a module, the system will highlight the corresponding module in the model and automatically locate it to the specific installation location.

[0218] For example, after clicking on the wall module, the wall's dimensions (2.5m×3m), material (concrete) and number (WT-01-001) pop up on the side of the screen.

[0219] By displaying the digital model and the installation location of the prefabricated decoration modules on the information terminal and marking the corresponding numbers, construction workers can quickly locate the modules and understand the installation steps, which can significantly improve construction efficiency and reduce installation errors.

[0220] On the other hand, the present invention also provides a digital modular decoration system based on building information, comprising:

[0221] A three-dimensional module is used to construct a digital model of the building to be renovated based on building information modeling technology, wherein the model includes building structure information, spatial layout information and functional requirement information;

[0222] A generation module, for automatically generating a modular decoration design scheme that meets the building structure and user needs using an autoencoder, wherein the modular decoration design scheme includes functional area division, module size, shape and material information;

[0223] A coding module, used to determine the required prefabricated decoration modules according to the modular decoration design scheme, generate the installation position and sequence of the prefabricated decoration modules in combination with the digital model, and uniquely encode the prefabricated decoration modules based on the installation position and sequence;

[0224] The display module is used to display the digital model and the installation position of the prefabricated decoration module on the information terminal, and mark the corresponding prefabricated decoration module number.

[0225] The prior art mentioned in the above background technology section and specific embodiment section of the present invention can be used as part of the present invention to understand the meaning of some technical features or parameters.

Claims

1. A digital modular decoration method based on building information, characterized in that: The method comprises the following steps: Constructing a digital model of the building to be renovated based on building information modeling technology, wherein the model includes building structure information, spatial layout information, and functional requirement information; Using an autoencoder to automatically generate a modular decoration design plan that meets the building structure and user needs, the modular decoration design plan includes functional area division, module size, shape and material information; Determine the required prefabricated decoration modules according to the modular decoration design scheme, generate the installation positions and sequence of the prefabricated decoration modules in combination with the digital model, and uniquely encode the prefabricated decoration modules based on the installation positions and sequence; The digital model and the installation position of the prefabricated decoration module are displayed on the information terminal, and the corresponding prefabricated decoration module number is marked.

2. The digital modular decoration method based on building information according to claim 1 is characterized in that: The method of using an autoencoder to automatically generate a modular decoration design scheme that meets the building structure and user needs includes: Input data includes building structure information, user needs, and spatial topological relationships; The building structure information is extracted from the building information model data and represented as a multi-dimensional tensor, including: geometric features, functional features, and connection features; The user requirements are expressed as condition vectors, including: decoration style, budget constraints, and functional requirements; The spatial topological relationship is represented as a graph, including nodes: representing the characteristics of each functional area module, and edges: representing the relationship between modules; The encoder maps architectural structure information and user needs into a latent space: Building information processing: geometric features are input into the convolutional network to extract spatial features, and functional features are input into the fully connected layer to generate functional embedding; Spatial relationship modeling: Use graph convolutional networks to embed topological graphs and output module relationship features; User demand processing: User demand input is embedded in the layer to generate demand features; Output latent distribution: The encoder outputs the mean and variance of the latent variable, which is used to sample the latent variable; The decoder generates decoration design solutions from latent variables and user needs: Functional area division: Use the conditional embedding layer to generate the distribution matrix of functional areas based on the latent variables; Module size: output the length, width and height of each module; Module shape: Output the geometric shape parameters of the module; Material information: Output the material of the module.

3. The digital modular decoration method based on building information according to claim 2 is characterized in that: The autoencoder includes the following constraints: Adjacency constraints ensure the rationality of functional areas between modules; Connection constraints ensure that pipelines between modules are correctly connected; The spatial distribution between modules should not overlap.

4. The digital modular decoration method based on building information according to claim 1 is characterized in that: The unique numbering of the prefabricated decoration modules based on the installation position and order includes: extracting the function and position data of each module from the BIM model, connecting the function and position, and automatically generating the unique code by increasing the module quantity.

5. The digital modular decoration method based on building information according to claim 1 is characterized in that: The display of the digital model and the installation position of the prefabricated decoration module on the information terminal and marking the corresponding prefabricated decoration module number includes: Export 3D digital models from BIM systems; Loading the three-dimensional model on the information terminal; The user clicks on a module in the model to view detailed module information; After selecting a module, the system will highlight the corresponding module in the model and automatically locate it to the specific installation location; The digital model and the installation location of the prefabricated decoration modules are displayed through the information terminal, and the corresponding numbers are marked.

6. A digital modular decoration system based on building information, characterized in that: The system includes the following modules: A three-dimensional module is used to construct a digital model of the building to be renovated based on building information modeling technology, wherein the model includes building structure information, spatial layout information and functional requirement information; A generation module, for automatically generating a modular decoration design scheme that meets the building structure and user needs using an autoencoder, wherein the modular decoration design scheme includes functional area division, module size, shape and material information; A coding module, used to determine the required prefabricated decoration modules according to the modular decoration design scheme, generate the installation position and sequence of the prefabricated decoration modules in combination with the digital model, and uniquely encode the prefabricated decoration modules based on the installation position and sequence; The display module is used to display the digital model and the installation position of the prefabricated decoration module on the information terminal, and mark the corresponding prefabricated decoration module number.

7. The digital modular decoration system based on building information according to claim 6 is characterized in that: The method of using an autoencoder to automatically generate a modular decoration design scheme that meets the building structure and user needs includes: Input data includes building structure information, user needs, and spatial topological relationships; The building structure information is extracted from the building information model data and represented as a multi-dimensional tensor, including: geometric features, functional features, and connection features; The user requirements are expressed as condition vectors, including: decoration style, budget constraints, and functional requirements; The spatial topological relationship is represented as a graph, including nodes: representing the characteristics of each functional area module, and edges: representing the relationship between modules; The encoder maps architectural structure information and user needs into a latent space: Building information processing: geometric features are input into the convolutional network to extract spatial features, and functional features are input into the fully connected layer to generate functional embedding; Spatial relationship modeling: Use graph convolutional networks to embed topological graphs and output module relationship features; User demand processing: User demand input is embedded in the layer to generate demand features; Output latent distribution: The encoder outputs the mean and variance of the latent variable, which is used to sample the latent variable; The decoder generates decoration design solutions from latent variables and user needs: Functional area division: Use the conditional embedding layer to generate the distribution matrix of functional areas based on the latent variables; Module size: output the length, width and height of each module; Module shape: Output the geometric shape parameters of the module; Material information: Output the material of the module.

8. The digital modular decoration system based on building information according to claim 7 is characterized in that: The autoencoder includes the following constraints: Adjacency constraints ensure the rationality of functional areas between modules; Connection constraints ensure that pipelines between modules are correctly connected; The spatial distribution between modules should not overlap.

9. The digital modular decoration system based on building information according to claim 6 is characterized in that: The unique numbering of the prefabricated decoration modules based on the installation position and order includes: extracting the function and position data of each module from the BIM model, connecting the function and position, and automatically generating the unique code by increasing the module quantity.

10. The digital modular decoration system based on building information according to claim 6 is characterized in that: The display of the digital model and the installation position of the prefabricated decoration module on the information terminal and marking the corresponding prefabricated decoration module number includes: Export 3D digital models from BIM systems; Loading the three-dimensional model on the information terminal; The user clicks on a module in the model to view detailed module information; After selecting a module, the system will highlight the corresponding module in the model and automatically locate it to the specific installation location; The digital model and the installation location of the prefabricated decoration modules are displayed through the information terminal, and the corresponding numbers are marked.

Images