46 results about "Building code" patented technology

The invention relates to a building specification compliance verification method based on dynamic prompt and map dual drive. The method comprises the steps of obtaining a to-be-examined construction organization design scheme text; preprocessing is carried out, and a core construction object set is identified; generating a high-confidence structured design element set; matching the structured design element set with specification terms in the building specification knowledge graph; performing logic comparison on parameter values in the structured design elements and compliance requirements in the matched standard terms, judging a compliance state and generating deviation information; and generating a compliance verification report according to a comparison result. The method has the beneficial effects that through a dynamic multi-round prompt chain technology, the large language model is guided to carry out iterative extraction, conflict verification and context completion on the construction scheme text, and the defects that omission, ambiguity and logic contradictions are easy to occur in a complex and lengthy document in single extraction are overcome.

The invention discloses a knowledge graph-based old building reconstruction scheme automatic recommendation method. The method comprises the following steps of S1, obtaining and preprocessing old building house data; s2, extracting a semantic entity and attribute relationship from a transformation case library, a building specification library and a construction scheme library, and constructing a knowledge graph; s3, mapping the house data to knowledge graph entity nodes, and executing graph embedding to generate building semantic representation; s4, constructing a graph neural network, calculating node semantic relevancy, and generating a building state vector; s5, inputting the building state vector into the reinforcement learning decision network, and optimizing the strategy to obtain an optimal transformation action; s6, screening reconstruction measures from the knowledge graph according to the optimal reconstruction action, and performing scoring to form candidate schemes; and S7, sorting the candidate schemes, selecting the scheme with the highest score, and recommending and updating the knowledge graph. According to the method, intelligent generation and self-optimization recommendation of the old building reconstruction scheme are realized, and the reconstruction efficiency of the scheme is remarkably improved.

The invention discloses a Langchain-based building specification graphical representation multi-modal question answering method and equipment, belongs to the technical field of artificial intelligence and building industry crossing, and is used for solving the problems of difficulty in processing multi-modal information, low query efficiency and the like in building industry specification graphical representation question answering. The method comprises the following steps: constructing a building specification multi-modal database, and carrying out storage management on building specification multi-modal data; based on a user query instruction, retrieving the multi-modal database from different dimensions; generating a structured answer corresponding to the user query instruction according to the retrieval result; and performing image-text consistency verification on the structured answer, and after the verification is passed, outputting the answer corresponding to the user query instruction. According to the method, a complete building specification question answering system is constructed, efficient and accurate building specification multi-mode question answering is achieved, and the building specification query efficiency is improved.

Disclosed embodiments perform automated design for buildings or portions of buildings and machine-generate architectural design and floor plans. Computer-implemented systems and methods of designing multi-unit buildings and portions of buildings include a set of one or more input requirements, a relationships module, an options placement system, a layout predictor system, and a design plan generator. The input requirements include one or more pre-defined footprints and may include local regulatory requirements such as building code, zoning, accessibility, among others. The design plan generator generates an architectural design plan for the building or portion of a building that can be built on the one or more pre-defined footprints. Disclosed systems and methods substantially reduce the design time and cost while increasing the profitability, sustainability and efficiency of construction projects.

The invention relates to a building space layout optimization design method and device, equipment and a medium. The method comprises the following steps: analyzing a building base contour, a room type library and a building specification text to generate structured data; based on the geometric boundary, the hard constraint rule set and the spatial topological relation graph, an optimized sampling scheme set is obtained through Latin hypercube sampling, reinforcement learning strategy and supplementary sampling processing, and based on the spatial topological relation graph, the attribute matrix and the soft constraint target set, multi-target calculation and agent model training processing are conducted on the optimized sampling scheme set, so that the optimal sampling scheme set is obtained. Obtaining a full-scheme evaluation set; and based on the hard constraint rule set and the soft constraint target set, performing Pareto screening, hard constraint repair and soft constraint optimization processing on the whole scheme evaluation set to generate a final optimization layout scheme. According to the method, by means of building design information structured analysis, multi-strategy sampling, multi-target evaluation and the like, the design efficiency, scheme compliance and multi-target performance global optimality of building space layout are improved.

The invention discloses a model compliance checking method and device based on a building information model, and belongs to the technical field of BIM, and the method comprises the following steps: collecting and sorting related building specifications and standards, and converting the specifications into formats which can be read and processed by BIM software; preparing a BIM model to be checked; defining a series of inspection rules according to building specifications and standards; the rules cover all aspects from structure safety to energy efficiency; automatically comparing the BIM model with a pre-defined rule through an algorithm of BIM software; detecting whether each element in the model meets the rule requirement, and analyzing and reporting results: summarizing the detection results, analyzing non-compliant parts in the model, and providing a detailed report; the report not only points out specific positions and reasons of non-compliance, but also provides modification suggestions or possible solutions; and modifying and optimizing the BIM model according to an inspection result, and performing compliance inspection again until the model completely conforms to all specified standards and specifications.

The application discloses a kind of fusion BIM and AI's construction method, system, equipment and storage medium, it is related to intelligent construction and building digitization technical field, including importing building data into BIM modeling software, obtain BIM building data;Call AI design model, based on BIM building data and the design requirement of user, generate building layout scheme and space arrangement result, and automatically update to BIM model;AI drawing optimization is carried out to the BIM model after updating, load building specification library and user-defined rule, identify cross-professional conflict point in combination with collision detection algorithm;In construction stage, call the BIM model after drawing optimization, carry out risk prediction and decision deduction to real-time construction and operation data by AI.The method described in the application realizes automatic design and model dynamic updating, can improve compliance and cross-professional consistency in design stage, can realize dynamic monitoring and intelligent decision support in whole construction process.

The system according to the embodiment aims to efficiently create architectural design patterns from photographs and drawings. [Solution] A system according to an embodiment includes a reception unit, an analysis unit, and a generation unit. The reception unit inputs photographs and drawings. The analysis unit analyzes the information input by the reception unit. The generation unit creates a pattern of building guidelines based on the information analyzed by the analysis unit.

Self-supporting concrete slabs can eliminate the need for temporary backshoring, streamlining the building process and enhancing productivity. These slabs are engineered to support their own weight and additional loads without relying on external supports, reducing labor and material costs while accelerating construction schedules. The process incorporates advanced reinforcement techniques, including post-tensioning and code-compliant splicing methods, to ensure structural integrity, continuity, and compliance with building codes. By simplifying forming processes and enabling early access for other trades, self-supporting slabs offer significant economic and operational advantages, making them a superior alternative to traditional slab designs.

The disclosure is directed at a method and system for generating dynamic building inspection checklists. The system and method compares tasks for a construction project with building code requirements and then generates a building inspection checklist based on the comparison. The system and method may then determine which tasks within the inspection checklist may result in a more negative impact if the task does not pass inspection and updates the checklist accordingly.

The present invention relates to a system and method for automatically generating a complete and precise bill of materials by learning the structural and logical relationships between design components using a graph neural network (GNN) from heterogeneous design data sources such as 2D CAD drawings, 3D BIM models, and specifications, and by predicting and interpolating the actual quantities to be input at the time of final completion from incomplete initial design data using a generative adversarial interpolation neural network (GAIN). The effects according to the present invention are as follows. First, the present invention precisely interpolates missing attributes using a Generative Adversarial Interpolation Network (GAIN) even in incomplete situations where input data, such as drawings, BIM, and specifications, is heterogeneous and some information (thickness, material, specifications, etc.) is missing. Through this, the reliability and integrity of input data, which forms the basis of quantity calculation, can be dramatically improved even in the initial design stage where data quality is low. Second, active risk management and design quality improvement through learning design change trajectories. Unlike existing methods that simply sum dimensions on drawings or predict only the final result, this invention predicts future change risks in advance by learning the trajectory of design changes through LSTM-based time-series historical analysis. By providing real-time feedback to the designer regarding warnings and alternatives for potential change-inducing factors, it fundamentally prevents unnecessary design changes, maximizes the accuracy of completion predictions, and minimizes the risk of increased construction costs and project delays. Third, it structurally learns the physical support, connectivity, inclusion, and spatial adjacency relationships of a building through a Graph Neural Network (GNN). This enables the automatic generation of a consistent bill of materials that aligns with the structural hierarchy and engineering correlations of the entire building (e.g., the relationship between column load and foundation reinforcement quantity), rather than merely calculating the fragmentary quantities of individual objects. Fourth, by utilizing a Large Language Model (LLM), the generated bill of materials items are double-checked to ensure they logically align with text-based specifications and building codes. By comprehensively evaluating semantic similarity and logical validity, legal and technical risks are minimized by preventing errors in advance where the quantity is correct but the specifications are incorrect (e.g., standard gypsum board vs. fire-resistant gypsum board). Fifth, by applying X-ray Influence Analysis (XAI) technology to the results generated by AI, it explains, using 3D heatmaps and causal text, which object (node) on the drawing is the origin of a specific volume increase. This resolves the 'black box' problem of AI and provides a reliable environment where users can clearly trace the basis of calculations. Sixth, regarding scalability, it enables risk-based estimation by providing multiple scenarios in the form of 'average value + range of variation (confidence interval)' rather than a single predicted value. Furthermore, by linking the calculated quantity data with cost and schedule data, it provides full-cycle project management efficiency that allows for the immediate simulation of the impact of design changes on total construction costs (5D) and construction duration (4D).

The application provides a building space segmentation method and system based on a maximum inscribed rectangle, comprising: acquiring a building space image to be segmented, reading the number of marked text points in the building space image to be segmented; solving the maximum inscribed rectangle of the building space image to be segmented based on the marked text points, obtaining the maximum inscribed rectangle of the marked text points; for the building space image to be segmented with different numbers of marked text points, different processing is performed on the maximum inscribed rectangle of each marked text point to obtain a space segmentation result, and a building space segmentation image is output; the method performs multi-space division based on the maximum inscribed rectangle, turns the abstract space division problem into an actual image processing problem, and accurately divides the building space in various marked text point situations in accordance with the building specification.

The invention provides an integrated structure intelligent design system and method oriented to the field of building industry, and the system comprises a structure performance prediction module which generates corresponding input features based on the design parameters of a target component, and predicts the structure performance indexes of the target component; the parameter optimization module is used for executing two-stage optimization in a preset design variable space by taking a structural performance index and material cost as multi-objective optimization objectives: firstly, performing global search by adopting an improved genetic algorithm to generate a Pareto leading edge candidate scheme set; then, the performance of the candidate schemes is optimized in combination with a gradient descent method, and the optimized candidate schemes are obtained; and the scheme generation module is used for inputting the optimized candidate scheme into a pre-constructed building specification knowledge graph, automatically matching related design terms, executing compliance verification, and generating a structure calculation book and a component list after the verification is passed. By means of a full-process architecture generated by data driving, intelligent analysis and scheme, technical independence can be achieved, and the design efficiency is improved.

The invention discloses an intelligent examination method and system for a building construction drawing, and belongs to the technical field of building construction. The technical problems that a traditional manual review mode is low in efficiency and prone to making mistakes, and an existing automatic system is difficult to process heterogeneous drawing data and understand complex building specifications are solved. According to the technical scheme, the method comprises the steps of receiving original drawing files generated by different drawing software through a data interface and analyzing the original drawing files into standardized structured data objects; fusing two-dimensional geometric and text information based on the data object, and reconstructing a lightweight three-dimensional building information model with semantic attributes; converting the building standard provisions into structured computational logic rule nodes through natural language processing to form a standard knowledge graph; and finally, carrying out dynamic matching reasoning on the three-dimensional model and the knowledge graph, automatically identifying violation through parameterization calculation and logic judgment, and generating a visual review report. The system is mainly used for realizing automatic, intelligent and precise examination of the building construction drawing.

The application relates to the field of building engineering digitization and computer vision technology, in particular to a BIM model generation method based on AI image recognition, which comprises the following steps: collecting a building scene image sequence, using a convolutional neural network based on a feature pyramid network to extract multi-scale visual features and generate a visual semantic density map; generating a binary mask based on the semantic density map, extracting a component instance aggregated feature vector; generating initial parameters through a parameterized inference function and combining the initial parameters into an initial BIM component parameter set; finally, constructing a total optimization objective function containing topological consistency loss and building specification compliance evaluation, optimizing the initial parameter set to output a final BIM model parameter set, the application constitutes a full-automatic and high-fidelity generation path from an original image to a compliant BIM model, ensures that the output final BIM model is not only geometrically accurate, but also logically self-consistent and compliant with engineering specifications, and significantly improves the intelligent level of building engineering digitization.

This application discloses a BIM model compliance review method and system based on deep learning, belonging to the field of building structural defect detection technology. The method involves: processing the BIM model to obtain a 3D point cloud space and region labels; partitioning and resampling the 3D point cloud space according to the connection relationships of various building components to obtain 3D point cloud models of multiple regions to be detected; using preset component keywords and fused region labels, matching building codes and regulations to the regions to be detected based on the fusion results; detecting the component dimensions and relative distances in the regions to be detected to obtain the structural deviation distribution of each region, thereby identifying design defects in the BIM model. Therefore, by implementing this application, the problem of low review efficiency and insufficient accuracy of building design defect review caused by the difficulty of quickly and accurately matching appropriate and complete building codes and regulations to building components of BIM models in existing technologies can be solved.

The present disclosure describes system and methods for determination of building code performance. One such method comprises transforming a building code regulation into a computable record that defines a building design and / or engineering rule for the building code regulation; performing design model validation, wherein design model validation comprises entering building permit application file information and checking the building permit application file information against relevant codes and regulations, using a taxonomy or neural natural language processing techniques or artificial Intelligence; performing exchange model code checking; performing code conformance checking, wherein the code conformance checking comprises receiving a request from the exchange models and passing the building permit application file information to code checking modules; performing verification reporting based on input provided from the code checking modules; and performing results reporting based on findings of the verification reporting.

The invention discloses a building model family parameter generation method and system based on AI driving. The method comprises the steps that a building design gene pool driving platform is called to extract and screen building model family calibration parameters; inputting the calibration parameters into a building boundary to represent a structured potential geometric tree diffusion model to generate a geometric feature parameter subset; generating a verification hybrid algorithm verification parameter through a building specification embedded parameter, and marking a parameter which does not accord with the rule; the mark parameters are adjusted and corrected in combination with historical data; integrating the parameters, and performing secondary diffusion through a diffusion model to generate an intermediate parameter set; and mapping the intermediate parameter as a building model family target parameter. The system comprises six units which are sequentially connected and cooperatively work. According to the method and the system, historical design data can be fully utilized, deep fusion of specification and parameter generation is realized, the geometric relevance of parameters is enhanced, the problems of low efficiency and lagging of specification verification in the prior art are solved, and the efficiency and the accuracy of parameter generation are improved.

Self-supporting concrete slabs can eliminate the need for temporary backshoring, streamlining the building process and enhancing productivity. These slabs are engineered to support their own weight and additional loads without relying on external supports, reducing labor and material costs while accelerating construction schedules. The process incorporates advanced reinforcement techniques, including post-tensioning and code-compliant splicing methods, to ensure structural integrity, continuity, and compliance with building codes. By simplifying forming processes and enabling early access for other trades, self-supporting slabs offer significant economic and operational advantages, making them a superior alternative to traditional slab designs.

The invention discloses an integrated light building filling external wall panel (WQ-JKGN panel) capable of replacing an existing filling block wall. The integrated light building filling external wall panel comprises a fireproof thermal insulation material layer, a reinforcing mesh and a silicic acid fiber calcium board layer which are sequentially arranged from the middle to the two sides. Wherein the reinforcing mesh is fixedly connected to the two sides of the fireproof thermal insulation material layer through reinforcing steel bar inclined connecting rods, and lightweight aggregate concrete is poured on the inner side and the outer side of the reinforcing mesh; silicic acid fiber calcium boards are arranged on the inner side and the outer side of the outermost layer of the silicic acid fiber calcium board layer finger board, and a sound insulation felt is arranged between the silicic acid fiber calcium board on the outer side and the lightweight aggregate concrete. According to the integrated light building filling external wall panel, the requirements of national building design specifications for various rigid indexes such as energy conservation, compression resistance, fire resistance and sound insulation of building external walls in current residences and public buildings are met at a time, and design adjustment can be carried out according to different requirements of different national and regional building specifications; the building assembly rate is improved, the construction time is saved, and the building quality is improved.

The invention discloses a BIM model-oriented building specification review method and device and a medium, and relates to the technical field of building design software, the method comprises the following steps: according to a review configuration selection instruction, reading attribute data of a target BIM model; performing format conversion on the natural language articles, and constructing an examination rule; performing logic judgment on the attribute data according to an examination rule to obtain a violation component; according to the illegal component, generating a structured review report, and bidirectionally associating the structured review report with the building component of the BIM model to modify the illegal component; and according to a received re-review instruction, reviewing the modified violation component so as to update the structured review report. According to the method, the attribute data and the component ID of the component in the BIM model are extracted and matched with the building specification rule for examination, so that the effect of quickly completing full-provision examination is achieved, the problems that in the prior art, high-level experts are relied on, and the examination period is long are solved, and the examination efficiency is greatly improved.

This invention relates to a structured rule description method and system for querying building code indicators. The method includes: acquiring multiple building BIM models of the project to be queried and their corresponding SNL rules; extracting entity data from the multiple building BIM models and determining the corresponding entity relationships to construct a multiple building semantic model of the project to be queried; parsing and acquiring the syntax structure of the SNL rules corresponding to the multiple building BIM models of the project to be queried, obtaining the SNL for querying building indicators, and determining the SPARQL query statement for building indicators; performing a query in the multiple building semantic model using the SPARQL query statement for building indicators to obtain the building code indicators of the multiple building BIM models of the project to be queried; parsing the conclusion clause of the SNL for querying building indicators, determining whether the conclusion clause contains calculations, and outputting the corresponding building code indicator as the target building code indicator based on the determination result. This invention can be widely applied in the field of automatic detection.

Self-supporting concrete slabs can eliminate the need for temporary backshoring, streamlining the building process and enhancing productivity. These slabs are engineered to support their own weight and additional loads without relying on external supports, reducing labor and material costs while accelerating construction schedules. The process incorporates advanced reinforcement techniques, including post-tensioning and code-compliant splicing methods, to ensure structural integrity, continuity, and compliance with building codes. By simplifying forming processes and enabling early access for other trades, self-supporting slabs offer significant economic and operational advantages, making them a superior alternative to traditional slab designs.

The application discloses a kind of parameterized bricklaying methods of arc wall based on GH plug-in, the radius of the outer arc line of arc wall is obtained;Cutting angle is plane right trapezoidal brick for laying for plane rectangular brick, the local cutting angle of the block with marked size is 581mm masonry for laying, so as to ensure that the mortar joint between inner and outer arc masonry is 3-4mm, and only cutting is carried out once for the block, battery pack is written by grasshopper, different radius arc wall is analyzed, the short side value and arrangement scheme of right trapezoidal block are obtained, and are developed into plane bricklaying drawing paper.The application solves the problem that the mortar joint width cannot meet the requirements of building specifications when using conventional size block for laying of circular arc secondary infill wall.

The invention discloses a self-adaptive building layout method and system based on a dynamic weight and constraint softening genetic algorithm, and the method achieves the self-adaptive building layout through a dynamic weight adjustment mechanism, a constraint softening strategy and self-adaptive iteration control under the condition of meeting the building specification constraint conditions (building spacing, sunlight requirement, plot ratio upper limit, building density limitation and the like). The method automatically and efficiently generates and optimizes an optimization scheme of the building layout in the plot, can respond to dynamic adjustment of planning parameters in real time, and is suitable for high-frequency design change and narrow feasible region scenes under planning. The method can respond to high-frequency parameter change in real time, and after parameters such as plot ratio / plot shape are changed through a dynamic parameter response mechanism (reserving compliant individuals, locally repairing and supplementing new individuals), the optimization process does not need to be completely restarted; the response time is shortened to 1 / 5 of that of a traditional method (minute-level scheme adjustment is supported); the problem that the prior art cannot adapt to high-frequency design change is thoroughly solved.

The invention discloses a building specification document layout component relation intelligent extraction method and device and a medium, and relates to the technical field of data processing. The method comprises the following steps of: uniformly coding visual and textual features of a segmented layout component by utilizing CLIP to ensure semantic alignment; secondly, explicitly extracting layout auxiliary features such as relative positions, distances and alignment among the segmented layout components, and quantifying a specific typesetting rule of the building document; and in the relation extraction network, the semantic similarity and the spatial rationality are dynamically fused through an attention mechanism. And finally, in combination with domain rule verification and knowledge graph multi-hop reasoning, precise relation identification under semantic and structural double constraints is realized, the problem that the structural hierarchy and the logical relation of the layout component in the building document are difficult to accurately capture in a traditional method is effectively solved, and the manual annotation and later proofreading cost is greatly reduced.

The application discloses an industrial Internet of Things-based equipment position management method, system, device and medium, relates to the technical field of equipment management, and collects position information of equipment through a positioning device, analyzes data of the position information to obtain GIS coordinates and building code information, and realizes multi-aspect positioning management of the equipment. Since different equipment requires different positioning accuracy, after the GIS coordinates are converted by a spatial database, more accurate spatial coordinates are obtained, the building code is decoded, the structured code is restored, the GIS coordinates and the building code system are fused, macro spatial analysis requirements can be met, accurate positioning in a building can be realized, a more complete spatial data basis is provided for equipment management, and the calling of the data basis finally realizes diversified task requirement application of equipment positioning data.

The invention discloses a building method, system and device fusing BIM and AI and a storage medium, and relates to the technical field of intelligent building and building digitization, and the method comprises the steps: importing building data into BIM modeling software, and obtaining BIM building data; calling an AI design model, generating a building layout scheme and a spatial arrangement result based on the BIM building data and the design requirements of the user, and automatically updating the building layout scheme and the spatial arrangement result to the BIM model; performing AI drawing auditing optimization on the updated BIM model, loading a building specification library and a user-defined rule, and recognizing cross-professional conflict points in combination with a collision detection algorithm; and in the construction stage, calling the BIM model after drawing examination optimization, and carrying out risk prediction and decision deduction on real-time construction and operation and maintenance data through AI. According to the method, automatic design and model dynamic updating are achieved, the compliance and cross-professional consistency of the design stage can be improved, and dynamic monitoring and intelligent decision support of the whole construction process can be achieved.

The invention relates to a multi-modal data-driven AI house type customization scheme generation method and system, and the method comprises the steps: obtaining multi-modal data, carrying out the feature extraction, and obtaining a design target feature set; matching is performed through the building specification knowledge base, and a preliminary constraint condition set is generated; matching a plurality of optimization strategies, and generating an enhanced constraint condition set through the first agent; a space planning scheme set is generated through the second agent, and a stylized layout scheme set is generated through the third agent; generating a parameterized building information model set through a fourth agent; in conclusion, the multi-modal data is acquired, feature extraction is performed, constraint matching is performed through a building specification knowledge base, reinforcement constraint conditions are generated in combination with intelligent agent optimization, then a space planning scheme, a stylization scheme and a parameterized building information model are generated, and multi-modal data driving and intelligent agent optimization are performed, so that the construction efficiency is improved. The problem that the prior art lacks flexibility, controllability and engineering compliance is solved.

The invention provides a constructional engineering AI system which comprises a construction system, a supervision system, a safety system and a construction system, and a user can flexibly select and start the corresponding system according to engineering requirements. In each system, an intelligent recognition module collects user voice, pictures or various documents, performs intelligent recognition and classification, and automatically generates a construction engineering file based on an embedded standard template. The AI inspection module analyzes field picture content through image recognition, recognizes quality defects or potential safety hazards fed back by the picture content, automatically calls related building standard provisions according to the quality defects or the potential safety hazards and generates quality inspection records or safety inspection records. And the achievement display module is used for uniformly classifying and managing all the generated files and supporting the user to conveniently download or view file contents. Through automatic file generation and intelligent inspection, human errors and omissions are greatly reduced, and timeliness and accuracy of building engineering ledger entry and efficiency and reliability of engineering management are improved.