47 results about "Building modeling" patented technology

The invention discloses a three-dimensional point cloud building automatic modeling system based on deep learning. The system comprises a point cloud acquisition and input module, a point cloud preprocessing module, a depth feature extraction module, a semantic segmentation and component identification module, a structure parameter analysis module and a parameterized model generation module. According to the invention, through deep fusion of the point cloud deep learning network and the parametric modeling engine, full-process automation of building three-dimensional modeling is realized; the depth feature extraction module is used, so that the recognition accuracy of structures such as doors, windows and roof edges can be effectively improved, the precision of a building model is ensured, and the depth feature extraction module can continuously improve the recognition accuracy along with continuous use of the system; and by using the semantic segmentation and component identification module, the irregularity of the building point cloud, the complexity of the structure and the shielding noise can be identified and distinguished, and the problem that semantic annotation and topological repair need to be manually performed in the prior art is solved.

The invention provides an existing building BEM modeling method, system and device based on an infrared thermal image of an unmanned aerial vehicle and a medium, and belongs to the technical field of building modeling. Generating a three-dimensional geometric model of the building main body; screening out an external window candidate area by analyzing RGB value characteristics of the visible light point cloud, generating a window opening three-dimensional boundary, and determining an internal surface temperature and an indoor air temperature through internal surface infrared temperature measurement and area weighted integration; and based on the temperature data and the building envelope construction parameters, inverting heat transfer coefficients of the outer wall, the roof and the outer window, and finally constructing a building energy consumption model in combination with the weighted average K value. According to the method, precise operation from building geometric model construction to thermal parameter acquisition and then building energy consumption model construction is realized. The efficiency and precision of BEM modeling of the existing building are improved, and a scientific basis is provided for building energy-saving transformation, energy consumption evaluation and the like.

The invention provides a building three-dimensional automatic modeling method based on oblique photogrammetry data, and belongs to the technical field of three-dimensional modeling. The method comprises the following steps: converting measurement data into three-dimensional point clouds, and obtaining non-ground point clouds in the three-dimensional point clouds by adopting a CSF algorithm; non-ground point clouds are clustered on the XY plane by adopting a DBSCAN algorithm to obtain independent point cloud clusters corresponding to the building, and two-dimensional vector contours of the independent point cloud clusters are obtained by adopting an Alpha Shape algorithm. The independent point cloud clusters are horizontally sliced along the Z axis, a plurality of cross section point sets are extracted in the Z-axis direction, two-dimensional convex hulls of the cross section point sets are calculated, the intersection-to-union ratio of the two-dimensional convex hulls and preset convex hulls is calculated, and when the intersection-to-union ratio exceeds a threshold value for the first time and is kept stable, the boundary height of the building is obtained. And stretching the two-dimensional vector contour along the Z axis according to the boundary height to obtain a first three-dimensional model of the building. According to the invention, manual intervention can be reduced, and the building modeling efficiency is improved.

The invention provides a three-dimensional image modeling method and device based on plane data, and the method comprises the steps: carrying out the full-color / multispectral band fusion, bit depth adjustment, thin cloud removal, image enhancement, stripe removal and light and color uniformity of a satellite surveying and mapping image, and achieving the real color recovery of the image; performing splicing preprocessing on the plurality of small orthographic satellite surveying and mapping images after real color recovery, performing image registration on the to-be-registered image and a reference image, performing image geometric correction on the registered image, and performing image mosaic processing on the plurality of images after image geometric correction to obtain a single large-scene image; and three-dimensional image matching, building mask extraction, three-dimensional building modeling and three-dimensional building post-processing are carried out on a single large scene image to obtain a three-dimensional digital surface model, and ground three-dimensional real image modeling is completed. By applying the technical scheme of the invention, the technical problem that the existing two-dimensional surveying and mapping data is difficult to meet the increasing application requirements of three-dimensional scenes is solved.

An ancient building cornice parameterized modeling method based on Revit secondary development belongs to the technical field of building information models, solves the technical problems of tedious steps, poor accuracy, low efficiency and the like of traditional ancient building modeling, and comprises the following steps: S1, parameterized design of cornice; s2, creating a DGWindow class which is used for calling a GUI (Graphical User Interface) window in the plug-in; s3, assembling the model; and S4, designing a graphic GUI (Graphical User Interface) to complete the assembly of the cornice model. According to the method, through deep fusion of the C # language and the RevitAPl, an innovative solution integrating parameterized interactive input, intelligent rule verification and complex component automatic generation is constructed. According to the scheme, building French material division is taken as core design logic, modulus rules, component proportions and drawing standards of a traditional cornice are converted into quantifiable parameter driving models, and full-process automation from design parameter input to national standard BIM model output is achieved.

The invention discloses a modeling file generation method, electronic equipment and a computer readable storage medium, and relates to the technical field of digital models.The modeling file generation method comprises the steps that target objects in an original building graph are extracted, and the target objects at least comprise wall objects; determining a central axis of each wall object, and extending each central axis to perform closing processing on the adjacent wall objects to generate closed space data; determining each basic primitive of each wall object, extracting attribute quantification information of each basic primitive, and associating the attribute quantification information, each basic primitive and each wall object according to the affiliation relationship to obtain structured data of each wall object; and based on the closed space data and the structured data, generating a target modeling file of the original building corresponding to the original building graph. According to the method, each target object is directly extracted from the original building graph to generate the target modeling file, so that the precision and convenience of building modeling are ensured.

The invention discloses an ancient building digital modeling method and a display platform, and relates to the technical field of building modeling, and the method comprises the steps: obtaining the three-dimensional point cloud data of the surface of a target ancient building, defining a plurality of potential defect regions, dividing the potential defect regions into a plurality of independent sub-regions, and combining the curvature deviation, normal vector deviation and residual error of each sub-region, thereby obtaining the three-dimensional point cloud data of the surface of the target ancient building. And calculating a corresponding comprehensive damage index to reflect the damage degree of the sub-region. According to the method, through the obtained three-dimensional point cloud data of the surface of the target historic building, through comprehensive analysis of the point cloud density, the normal vector deviation and the curvature value, the potential defect area is rapidly and accurately identified and refined to the sub-areas, the damage type and degree are comprehensively evaluated, and the efficiency and quality of historic building digital protection are improved. By means of three-dimensional point cloud rendering and diversified marking modes of a display platform, a user can visually know distribution and depth evaluation results of building surface defects, and meanwhile, damage priority ranking and repair simulation functions are achieved.

The invention discloses a BIM model number inputting and auditing method based on GH and Revit. A two-dimensional drawing is cleaned and number data is extracted through Rhino, the centroid of a BIM model component is extracted by utilizing Grasshopper and is projected to generate a point cloud, the number of the two-dimensional drawing and the BIM model component are matched based on a nearest neighbor algorithm, and batch inputting and dynamic synchronous updating of the number are realized. And reading an instance parameter value of the BIM model component through Grasshopper, and automatically comparing the instance parameter value with the two-dimensional drawing number data set to generate an Excel auditing report containing a consistency mark. The invention relates to the technical field of building modeling, and can solve the technical problems in the prior art.

The application discloses a kind of building fine modeling method and device fusing knowledge graph, belong to landscape modeling and surveying technology field.The method is first obtained target building image and generates point cloud, obtains the mapping relationship between point cloud and image;According to building modeling content determines building modeling knowledge graph architecture, builds knowledge graph by knowledge representation, knowledge storage and knowledge fusion;Under the guidance of knowledge graph, utilize point cloud to build building main structure surface model;Obtain the positioning information of opening component, construct opening component model and modify main structure surface model;Determine the non-main component information outside main structure and opening component, and construct non-main component model by the guidance of knowledge graph;Combine all models, obtain target building model.The application avoids the problems such as model complexity and texture distortion, component monomer reconstruction difficulty of traditional method, and realizes hierarchical, component, fine building modeling.

The invention belongs to the technical field of graphic processing and three-dimensional modeling, and discloses a fluid impact building damage simulation method and system, and the method comprises solid-liquid mixed virtual simulation, building breaking virtual simulation and impact judgment virtual simulation. The solid-liquid mixing virtual simulation comprises solid modeling, liquid virtual simulation, particle mixing and buoyancy setting, the building crushing virtual simulation comprises building modeling, building pre-crushing and crushing threshold setting, and the impact judgment virtual simulation comprises polyhedron partition division and force field judgment. The fluid impact building damage virtual simulation effect is good, the calculation cost is reduced, the frame rate during virtual simulation is improved, and the universality is high. According to the virtual simulation method considering the mixing condition of the solid phase and the water phase, virtual simulation of a mechanism that the solid phase is carried by the water phase is achieved, pressure brought by collision point detection of liquid and the solid on models such as buildings is reduced, and the method can be used for virtual simulation of disasters such as flood and debris flow.

The invention discloses an open-web truss structure design method based on a single-layer cable net deformation form, and relates to the field of building design. The open-web truss structure design method based on the single-layer cable net deformation form comprises the following steps that a building space curved surface is projected to an xoy plane, and a projection line of a building outer contour line on the xoy plane is obtained; designing an initial cable net structure model based on the projection line of the outer contour line of the building in combination with building modeling requirements; finite element software is adopted to simulate the deformation form and deformation data of the initial cable net structure model under real load and real boundary conditions; extracting a displacement result of nodes of the initial cable net structure model, and performing scaling processing by combining the displacement result with the actual size of the building to obtain an optimal cable net structure matched with the actual shape of the building; and modifying the optimal cable net structure into an open-web truss structure. The open-web truss structure design method based on the deformation form of the single-layer cable net solves the problem of shear design of vertical rods in open-web truss design, and has the advantages of clear mechanics concept, simplicity in operation, low design difficulty and time and cost saving.

The application relates to the technical field of building modeling, in particular to a rapid construction method of a high-reduction building white model, which comprises the following steps: obtaining point cloud data of a target city; obtaining each closed edge contour at each height in the height direction of the building in the point cloud data, and taking the closed edge contour at the height of the position of the road surface as a ground contour; obtaining each profile surface in the target city and out-of-profile point cloud data of each profile surface; obtaining point cloud distribution characteristic values of each profile surface; obtaining each similar profile surface of each profile surface; obtaining the building feature similarity of each profile surface by the spatial distance between the ground contours and the similarity degree between the closed edge contours at each height for each profile surface and each similar profile surface thereof; obtaining the retainable degree of each profile surface, screening building point clouds and constructing a building white model. The application aims to improve the accuracy of the screened building point clouds and then improve the reduction degree of the subsequently constructed building white model.

The application provides an ancient building repair modeling reconstruction method based on digital technology, and belongs to the field of artificial intelligence and building repair technology. The method comprises the following steps: obtaining three-dimensional structure information and plane structure information of a target ancient building to be repaired; generating a three-dimensional structure diagram and a target plane structure diagram of the target ancient building to be repaired; performing matching search in a preset plane structure diagram database based on the target plane structure diagram to obtain at least one matching plane structure diagram; performing semantic analysis on the matching plane structure diagram to obtain a plurality of three-dimensional reconstruction prompt words; inputting the three-dimensional reconstruction prompt words and the three-dimensional structure diagram of the target ancient building to be repaired into a graph generation artificial intelligence engine to output a plurality of three-dimensional structure repair effect candidate diagrams; and evaluating to obtain a three-dimensional structure repair scheme diagram of the target ancient building to be repaired. The application realizes ancient building modeling reconstruction based on digital technology, and assists the artificial intelligence engine to obtain a plurality of candidate schemes and then evaluates to obtain an optimal repair scheme.

The embodiment of the application discloses a building modeling method, the method comprises the following steps: acquiring point cloud data collected for a target building, the point cloud data containing first point cloud data of multiple wall surfaces of the target building; acquiring topological information according to the first point cloud data, the topological information including position information of a projection line segment of each wall surface and position information of at least one ground area formed by the multiple projection line segments; wherein the multiple projection line segments are formed by the intersection of straight lines where the projection lines of the multiple wall surfaces on a horizontal plane are located; determining whether each projection line segment or the ground area is retained through a target neural network according to the topological information, wherein the retained projection line segment and the ground area are used to construct a building information model (BIM) of the target building. The application can still obtain a building model with high precision when the data collected for the building is not comprehensive.

The invention discloses a method, a system and a medium for establishing a pile type pier in midas software, and relates to the technical field of building modeling, and the method comprises the following steps: determining section information and component node information of each component of the pile type pier based on basic parameters of the pile type pier; based on the basic parameters of the soil spring, carrying out adaptive soil spring calculation to obtain a deformation-internal force function; according to the method, the component node information and the deformation-internal force function are subjected to format conversion, and then the pile type pier model and the soil spring model are created, so that convenient and efficient modeling and soil spring calculation can be carried out, the repeated labor of designers is reduced, the accuracy of pile type pier modeling and soil spring calculation is improved, the requirements of bridge construction in the frozen earth region are met, and the construction period is shortened. And support can be provided for increasing bridge construction requirements in frozen earth areas.

The high-adaptability glass curtain wall cleaning robot in the low-altitude engineering comprises a sweeping mechanism, a water gun mechanism, a moving mechanism and a self-adaption mechanism, the sweeping mechanism is an inner hole circle supporting mechanism, and a roller at the sweeping end conducts reciprocating cycle compound sweeping; the water gun mechanism is linked with the cleaning mechanism, and liquid is sprayed out synchronously during cleaning; the moving mechanism is used for driving the whole cleaning robot to linearly move and turn; the self-adaptive mechanism adsorbs / separates the glass curtain wall, and the self-adaptive mechanism is combined with driving of the moving mechanism to achieve overall movement of the cleaning robot. The glass cleaning area can be automatically adjusted in the cleaning process, dynamic adjustment is carried out, and the glass cleaning robot can be qualified for glass cleaning tasks under various high-rise buildings. According to the invention, 360-degree omni-directional movement can be carried out by virtue of the cooperation of the screw rod and the worm gear and worm, and the flexibility is extremely high. The building glass curtain wall cleaning device can meet the requirement for cleaning building glass curtain walls in a low-altitude range and is suitable for existing building modeling and building height.

The invention discloses an implicit parameterized CAD modeling method based on autoregressive point cloud deconstruction, which is suitable for a task of generating a structured modeling instruction by a three-dimensional point cloud and can realize reconstruction and interpretable modeling of a target CAD structure. Extracting global geometric features by using a point cloud encoder, and gradually generating a plurality of potential component representations through an autoregression mechanism; on the basis of each part representation, two sets of independent Transform decoders are guided to generate sketch parameters and stretching parameters respectively, and continuous modeling parameters are quantized and coded into a unified discrete modeling instruction space; an introduced judgment module is used for judging the modeling effectiveness of each latent variable, and modeling steps are screened out to form a final instruction sequence; the generated parametric modeling program can be directly used for reconstruction execution in a CAD environment; the method achieves end-to-end program generation and structure recovery, has the advantages of being clear in modeling logic, high in editability, high in geometric adaptability and the like, and is widely suitable for industrial design, intelligent manufacturing, building modeling, education assistance and other scenes.

The invention discloses a horizontal member labeling and placing method and device and a medium, belongs to the technical field of building modeling views, and aims to solve the problems that in an existing Revit model, labeling of horizontal members is generally manually operated, time and labor are consumed, manual errors are large, and the labeling efficiency is high. The technical problem that more reasonable annotation content cannot be well expressed at a proper position is solved. The method comprises the steps that line marking processing is conducted on a non-axis beam in a total building view of the horizontal component, and a plurality of marking lines and reference lines are obtained; performing transverse grouping processing under related axis projection on the total building view of the horizontal component; calculating and adjusting the labeled placement position to obtain transverse labeled position information; performing longitudinal group labeling processing on the longitudinal collinear; performing dimension alignment processing on the transverse continuous labeling group and the longitudinal collinear labeling group to obtain a dimension alignment result; and carrying out corresponding placement processing on the horizontal component labeling information to obtain final labeling result information.

The present application belongs to the technical field of curtain wall facilities, and particularly relates to a horizontal-through vertical-cut curtain wall system, which comprises a fixed plate, the side surface of the fixed plate is provided with a bracket, the side surface of the bracket is provided with an insertion block, the bottom of the insertion block protrudes from the bottom side edge of the bracket, the fixed plate is provided with an insertion slot corresponding to the insertion block, the fixed plate and the bracket are connected through the insertion of the insertion block and the insertion slot, the fixed plate and the bracket form a basic adapter, a horizontal beam is fixed on the platform of the bracket and the platform of the adapter, an insertion core is arranged on the top of the horizontal beam, the insertion core is fixed on the horizontal beam through a pin, a vertical column is arranged on the top of the horizontal beam, the vertical column is sleeved on the outside of the insertion core, a long shaft bolt is fixed on the side surface of the fixed plate, a notch is arranged on the bottom side of the insertion block, and the slot type of the insertion slot is matched with the insertion block. The present application can reduce the positioning time of the overall building modeling, greatly save the corresponding labor, simplify the positioning process, improve the construction speed, and shorten the construction period.

The invention discloses a building modeling method and device, electronic equipment, a storage medium and a computer program product, and the method comprises the steps: outputting first information; the first information is used for guiding a user to move a first terminal to a first area; the first area represents an area where the first terminal is located under the condition that an image sensor of the first terminal can perform complete imaging on the first building; determining a first height of the first building based on second information; the second information represents sensing parameters of one or more sensors in the first terminal when the first terminal is located in the first area; and rendering a model of the first building based on the first height of the first building.

The application discloses a method and device for inverse form-finding of cable elements, and a storage medium, which projects a building space curved surface to an xoy plane to obtain a building outer contour projection line; an initial net shell structure model is designed according to the building outer contour projection line and combined with building modeling needs; real boundary conditions are set for the net shell structure model, real loads are applied, all beam elements in the net shell structure model are replaced by cable elements, initial stiffness is set, and an initial cable structure model is obtained; a finite element analysis software is used to obtain deformation forms and deformation data of the cable structure model under real loads and real boundary conditions; the obtained deformation data is scaled and inverted in combination with actual building sizes to obtain an optimal structure form matched with an actual building form. The form-finding calculation process of the application does not need multiple iterative calculations, effectively saves time cost, greatly improves structure form-finding efficiency, is simple to operate, low in design difficulty and high in design efficiency.

The application discloses a building model generation system, method, device and medium, and relates to the field of building modeling.The system comprises a vector data import module, a building contour generation module, a height calculation module, an extrusion modeling module and a user interaction module.The vector data import module supports importing vector data and can complete multi-component polygon disassembly and ring direction standardization processing.The contour generation module converts the coordinate data after standardization processing into a polygon building base suitable for a three-dimensional software and completes the adaptation through a coordinate scaling factor.The height calculation module provides multiple height generation modes and realizes dynamic and diversified generation of building heights.The extrusion modeling module encapsulates a three-dimensional software bottom polygon extrusion command, completes conversion from a plane base to a three-dimensional block, and generates a three-dimensional building block with a top surface.The user interaction module integrates all the functions in a visual interface and supports intuitive parameter adjustment.

The application discloses a kind of parameterized modeling methods of amusement park outer packaging steel structure based on Grasshopper, one, the process of modeling is simplified into the form of cluster group in grasshopper;Two, in Rhino platform, specify the reference point at building modeling place, rotate and translate building modeling to coordinate origin, and modeling surface at original point is as input end building control surface;Three, according to building modeling;Five, select the bottom node on the outline of civil engineering roof, offset node according to the set column pier height, then generate column base node;Six, the generated entity rod piece result is reselected and translated back to the original building packaging modeling place, whether the steel structure arrangement generated automatically meets the design requirement is quickly reviewed through collision checking or entity visual effect.The application can directly capture the packaging modeling surface of building, according to building packaging modeling, input controllable parameters such as size, spacing, to directly generate the model wireframe diagram required by structure design, and quickly generate three-dimensional model for subsequent deepening structure design.

The invention discloses a building three-dimensional modeling method based on a single recent satellite image, and belongs to the field of three-dimensional modeling and remote sensing information processing. On the basis of a historical three-dimensional model or a self-adaptive parameterized building monomer initialization model, the height of a building monomer change area is estimated according to a single recent satellite image, deviation injection is carried out based on the estimated height of the change area, iteration is carried out by fusing semantic driving and geometric constraint through a space-time diffusion technology, deviation remodeling is completed, and a new satellite image is obtained. Contour surface extraction is carried out on the Gaussian element set after deviation remodeling, and building monomer modeling is completed. According to the method, modeling can be completed only by combining a single recent satellite image with the historical three-dimensional model, geometric, semantic and time sequence information of the satellite image can be effectively integrated, the data acquisition cost is greatly reduced, the modeling precision is remarkably improved, and the modeling efficiency is improved. The problems that in the prior art, when building modeling is conducted through satellite images, precision is low, efficiency is low, and multivariate information is difficult to fuse are solved.

The invention discloses a monocular remote sensing image three-dimensional building modeling method based on multi-task learning, which relates to the technical field of three-dimensional modeling, and comprises the following steps: constructing an instance-level multi-task learning model, and optimizing the positioning of an overall bounding box of a building instance by using a cascade detection module; by adopting a roof frame extraction branch, a roof mask extraction branch, a house bottom mask extraction module based on geometrical relationship reasoning and a height predictor based on a binning mechanism, the problem of house bottom information loss caused by facade shielding and the problem of high height estimation difficulty caused by large height difference of various buildings can be effectively relieved; using a multi-task joint loss function to train an instance-level multi-task learning model; and inputting a monocular image into the trained instance-level multi-task learning model to obtain a house bottom mask and a height value, and further constructing an LOD 1 (Level of Detail 1) building three-dimensional model. According to the invention, robust three-dimensional building modeling can be carried out on a monocular image in a city scene under a non-orthographic condition.

The application relates to the field of cultural heritage digitization. The application discloses a classical building three-dimensional modeling and image redrawing method, system, terminal and medium, which can model and redraw images of fictitious classical buildings or classical buildings that existed in history but have disappeared today, and improve the accuracy of classical building modeling and the cultural expression of classical buildings. The method comprises obtaining text description information and building feature images corresponding to a classical building, and extracting building feature information from the text description information; inputting the text description information and the building feature information into a Dall-E 3 model to generate an intention map; constructing a three-dimensional model of the classical building based on the building feature information and the building feature images and referring to the intention map; selecting a two-dimensional image of the three-dimensional model at a preset angle, redrawing the classical building based on the building feature information and the two-dimensional image to generate a redrawing image.

The invention provides a building modeling method based on a building engineering file, and belongs to the technical field of modeling simulation, and the method comprises the steps: carrying out the line cutting of each building region in a building design drawing through a minimum two-dimensional building unit according to a structural design description, and obtaining a two-dimensional cutting map of each building region; initial three-dimensional line structures are obtained according to the three-dimensional parameters, spatial position alignment is carried out on each installation device and the corresponding initial three-dimensional line structure according to a device installation drawing, and a fused three-dimensional line structure is obtained; extracting a surface attribute set of each entity space surface constructed by depending on the sub-lines, and constructing an entity sub-structure; and performing spatial arrangement on all the initial model components to obtain an overall building model, and verifying and positioning an abnormal space for correction. And a high-precision model support is provided for digital application of the full life cycle of constructional engineering.

The invention relates to the technical field of building modeling, in particular to a rapid construction method of a high-reduction-degree building white pattern, and the method comprises the steps: obtaining the point cloud data of a target city; obtaining each closed edge contour at each height in the height direction of the building in the point cloud data, and recording the closed edge contour at the height of the position where the road surface is located as a ground contour; obtaining each contour surface in the target city and out-of-contour point cloud data of each contour surface; obtaining a point cloud distribution characteristic value of each contour surface; obtaining similar contour surfaces of the contour surfaces; for each contour surface and each similar contour thereof, obtaining the building feature similarity of each contour surface through the spatial distance between the ground contours and the similarity between the closed edge contours at each height; and obtaining the retention degree of each contour surface, screening building point clouds, and constructing a building white mold. According to the method, the precision of the building point cloud obtained through screening is improved, and then the reduction degree of the building white pattern obtained through subsequent construction is improved.

The utility model relates to the field of building modeling provides a three -dimensional scanner mounting base for building modeling, this base includes: support rod, fixed cylinder, fixedly covers in the outer surface of support rod, and the inner wall department of fixed cylinder all movably set up a plurality of support rods, the application is in use, through a plurality of connecting rods drive a plurality of sliding blocks in a plurality of groove boards inner wall department upwards sliding, further make a plurality of support rods angle bigger, further reduce the height of scanner body, when the slide cylinder slides down, through a plurality of connecting rods drive a plurality of sliding blocks in a plurality of groove boards inner wall department downwards sliding, further make a plurality of support rods angle smaller, further increase the height of scanner body, after height adjustment is good, through the fixed rod is inserted to the inside of slide cylinder and one of positioning hole, make the slide cylinder fixed on the outer surface of support rod, thereby when using the base, the base height of scanner can be adjusted, improve the practicality of base.

The application belongs to the technical field of building modeling, and is a building engineering design semantic structured description and compliance review method and system, which comprises the following steps: formulating a unified data format, storing various building design objects and their attribute fields in the data format, integrating model information of various types layer by layer to form an information model; performing knowledge extraction on the Chinese natural language text in the digitalized articles, combining the knowledge into a multi-dimensional unified description knowledge set, and storing the knowledge set in a database in a structured form to form a knowledge base; using the knowledge base to encapsulate the building design objects and their attribute fields stored in the data format, providing a description structure of the building engineering design compliance semantics, formulating a descriptive rule language with object orientation as the core, and performing compliance review of the building engineering design; and solving the problems of repeated redundancy, difficult maintenance and upgrade, and invisible logic caused by the hard coding mode of the prior art.