A method and system for rapid disassembly of a BIM model

Abstract

The application relates to the technical field of building information modeling, in particular to a BIM model rapid splitting method and system, which comprises the following steps: based on building element types and function requirements, integrated decision tree classification algorithms and K-means clustering are adopted to perform hierarchical processing on BIM model data, and type, function and project stage classification is performed to generate hierarchical data structures; in the application, the integrated decision tree classification algorithms and K-means clustering are applied, the efficiency of processing large and complex structure BIM models is improved, the challenge of large data volume can be effectively coped with, the whole model processing flow is optimized through efficient data hierarchical processing and classification, in the aspect of multi-specialty integrated processing, such as buildings, structures, electricity, pipelines and the like, deeper data correlation and analysis are realized, the fluency and efficiency of cross-specialty cooperation are improved, meanwhile, data optimization algorithms and logic splitting technologies accelerate the identification and classification of different components in the model.

Description

TECHNICAL FIELD

[0001] The application relates to the technical field of building information modeling, and in particular to a BIM model rapid splitting method and system. BACKGROUND

[0002] Building information modeling is a digital technology-based solution for the construction industry, which uses three-dimensional modeling software and other related technologies to create and manage digital representations of the physical and functional characteristics of construction projects. BIM technology involves the entire process of design, construction and operation of construction projects, including the integration of multiple disciplines such as architecture, structure, electricity, piping, etc. It supports decision-making processes, improves design efficiency, optimizes construction and operation processes, and enhances collaboration and communication among project stakeholders.

[0003] The purpose of the BIM model rapid splitting method is to improve the processing efficiency and accuracy of complex BIM models. By quickly splitting large and complex BIM models into smaller, easily managed and analyzed parts, it makes the architectural design and construction process more efficient and accurate. This method can reduce the need for manual operations, reduce errors, and improve the overall efficiency of project management. Typically, this BIM model rapid splitting method is achieved by using advanced computer vision technology and deep learning algorithms. For example, it uses convolutional neural networks to analyze and process BIM models, achieving accurate identification and classification of different components in the model. In addition, the method combines object detection and semantic segmentation techniques to accurately distinguish architectural elements such as walls, floors, pipes, etc. The application of this technology not only improves the speed of model processing, but also improves the accuracy and efficiency of the splitting process.

[0004] Traditional BIM model processing methods are difficult to efficiently process large and complex BIM models, especially when the amount of data increases significantly. The data processing capacity is limited, resulting in low efficiency in collaboration and communication during the entire process of design, construction and operation. In the multi-disciplinary integration of fields such as architecture, structure, electricity, piping, etc., the correlation and analysis of data are not fully realized, which to some extent limits the smoothness of cross-disciplinary cooperation. At the same time, it is difficult to quickly identify and classify different components in the model. Although existing technologies provide a solid foundation for BIM model processing, there is still room for improvement in processing efficiency, data fusion depth and automation level. SUMMARY

[0005] The purpose of the present application is to solve the shortcomings in the prior art and provide a BIM model rapid splitting method and system.

[0006] In order to achieve the above-mentioned purpose, the application adopts the following technical scheme: a BIM model rapid splitting method, comprising the following steps:

[0007] S1: based on the building element type and functional requirements, using an integrated decision tree classification algorithm and K-means clustering, hierarchical processing of BIM model data is performed, and type, function and project stage classification is performed to generate a hierarchical data structure;

[0008] S2: based on the hierarchical data structure, using a heuristic rule-based data optimization algorithm, differential processing is performed on the main and secondary areas, and the splitting process is optimized to generate an optimized splitting plan;

[0009] S3: based on the optimized splitting plan, using a predicate logic-based splitting engine, logical reasoning is performed and a splitting path is selected to generate a logical splitting path;

[0010] S4: based on the logical splitting path, using an incremental change detection algorithm, the changed part of the model is updated to generate updated splitting data;

[0011] S5: based on the updated splitting data, using a data compression and optimization algorithm, data streamlining processing is performed to generate streamlined splitting data;

[0012] S6: based on the streamlined splitting data, using data integrity verification technology, data quality is optimized to generate quality verification data;

[0013] S7: based on the quality verification data, using network topology analysis technology, the mutual dependence between components is identified to generate a component correlation analysis report;

[0014] S8: based on the component correlation analysis report, using data fusion and integration algorithm, the results of hierarchical data structure, optimized splitting plan, logical splitting path, updated splitting data, streamlined splitting data and quality verification data are integrated to complete BIM model splitting to generate split BIM model.

[0015] The hierarchical data structure includes data hierarchy of structure, electrical, piping and other functions, the logical splitting path specifically refers to the path of splitting method and sequence based on logical formula derivation, the updated splitting data specifically refers to modification and update information of the changed part of the model, the streamlined splitting data specifically refers to an optimized data set, the quality verification data specifically refers to a verified data set, and the component correlation analysis report specifically refers to a report showing the dependency relationship and network connection strength between components.

[0016] As a further scheme of the present application, the step of generating a hierarchical data structure based on the building element type and functional requirements, using an integrated decision tree classification algorithm and K-means clustering, hierarchical processing of BIM model data is performed, and type, function and project stage classification is performed, specifically comprises:

[0017] S101: Based on the building element type and functional requirements, a decision tree classification algorithm is used to preliminarily classify the BIM model data, and preliminary classification data is generated;

[0018] S102: Based on the preliminary classification data, a K-means clustering method is used to functionally divide the data, and function classification data is generated;

[0019] S103: Based on the function classification data, a correlation rule learning algorithm is used to analyze the relationship between the data and the project stage, and project stage correlation data is generated;

[0020] S104: Based on the project stage correlation data, a data merging technique is used for data integration, and a hierarchical data structure is generated.

[0021] As a further scheme of the present application, based on the hierarchical data structure, a data optimization algorithm based on heuristic rules is used to implement differential processing on the main area and the secondary area, and the splitting process is optimized, and the steps of generating the optimized splitting plan are as follows:

[0022] S201: Based on the hierarchical data structure, a heuristic rule analysis algorithm is used to analyze the main area data, and a main area processing plan is generated;

[0023] S202: Based on the main area processing plan, a simplified processing algorithm is used to analyze the secondary area, and a secondary area processing plan is generated;

[0024] S203: Based on the main area processing plan and the secondary area processing plan, a data fusion technique is used to balance the processing strategy, and a comprehensive data processing scheme is generated;

[0025] S204: Based on the comprehensive data processing scheme, a multi-objective optimization technique is used for differential data processing, and an optimized splitting plan is generated.

[0026] As a further scheme of the present application, based on the optimized splitting plan, a splitting engine based on predicate logic is used for logical reasoning and selection of splitting path, and the steps of generating the logical splitting path are as follows:

[0027] S301: Based on the optimized splitting plan, a predicate logic algorithm is used for preliminary logical reasoning, and a preliminary logical reasoning result is generated;

[0028] S302: Based on the preliminary logical reasoning result, a logical optimization technique is used to further optimize the logical structure of the splitting path, and a logical optimization path result is generated;

[0029] S303: based on the logical optimization path result, using a weighted ranking algorithm, ranking the path options, generating a weighted ranking split result;

[0030] S304: based on the weighted ranking split result, using a path decision analysis method, selecting a suitable split path, and optimizing the logical reasoning efficiency, generating a logical split path.

[0031] As a further scheme of the application, based on the logical split path, using an incremental change detection algorithm, updating the changed part in the model, generating updated split data, the steps are as follows:

[0032] S401: based on the logical split path, using incremental change detection technology, identifying and updating the changed part in the model, generating preliminary update data;

[0033] S402: based on the preliminary update data, using a data synchronization protocol, maintaining the consistency of the data, generating synchronization update data;

[0034] S403: based on the synchronization update data, using the difference query technology in the database, processing the data difference, generating differential update data;

[0035] S404: based on the differential update data, using data merging algorithm, data integration, generating updated split data.

[0036] As a further scheme of the application, based on the updated split data, using data compression and optimization algorithm, data streamlining processing, generating streamlining split data, the steps are as follows:

[0037] S501: based on the updated split data, using compression encoding technology, reducing the data volume, generating preliminary compressed data;

[0038] S502: based on the preliminary compressed data, using data reorganization technology, optimizing the data structure, generating optimization processing data;

[0039] S503: based on the optimization processing data, using data reconstruction algorithm, reconstructing the data format, generating reconstructed data;

[0040] S504: based on the reconstructed data, using data stream processing framework for stream processing, generating streamlining split data.

[0041] As a further scheme of the application, based on the streamlining split data, using data integrity verification technology, optimizing data quality, generating quality verification data, the steps are as follows:

[0042] S601: Based on the streamlined split data, a data integrity detection algorithm is used to perform a preliminary quality check, and preliminary quality inspection data is generated;

[0043] S602: Based on the preliminary quality inspection data, a data cleaning algorithm is used to eliminate inconsistent and erroneous data, and cleaned data is generated;

[0044] S603: Based on the cleaned data, integrity reinforcement technology is used to optimize data accuracy, and integrity evaluation data is generated;

[0045] S604: Based on the integrity evaluation data, a comprehensive data quality evaluation framework is used to optimize data quality, and quality verification data is generated.

[0046] As a further scheme of the present application, based on the quality verification data, a network topology analysis technique is used to identify the mutual dependence between components, and the steps of generating a component correlation analysis report are as follows:

[0047] S701: Based on the quality verification data, a graph theory algorithm is used to analyze the connectivity between components, and a preliminary component relationship graph is generated;

[0048] S702: Based on the preliminary component relationship graph, a network flow analysis technique is used to identify components and dependent paths, and a component dependency graph is generated;

[0049] S703: Based on the component dependency graph, a cluster analysis algorithm is used to distinguish the groups of multiple types of components, and a component group analysis result is generated;

[0050] S704: Based on the component group analysis result, a network topology optimization technique is used to further analyze the dependence and interaction relationship between components by considering multiple types of network parameters, and a component correlation analysis report is generated.

[0051] As a further scheme of the present application, based on the component correlation analysis report, a data fusion and integration algorithm is used to integrate the results of hierarchical data structure, optimize the split plan, logical split path, updated split data, streamlined split data and quality verification data, complete the BIM model split, and the steps of generating the split BIM model are as follows:

[0052] S801: Based on the component correlation analysis report, an associated data integration technique is used to preliminarily integrate the data results of multiple stages, and preliminary integrated data is generated;

[0053] S802: Based on the preliminary integrated data, a dimension analysis method is used to integrate multiple aspects of data and create a comprehensive multi-dimensional data view, and a multi-dimensional fusion data set is generated;

[0054] S803: Based on the multi-dimensional fusion data set, data optimization and simplification are performed using data processing technology to generate a refined data set;

[0055] S804: Based on the refined data set, a comprehensive data management strategy is adopted to perform final fusion and integration of data, and information consistency and integrity are checked to generate a split BIM model.

[0056] A BIM model rapid splitting system for performing the above-mentioned BIM model rapid splitting method, the system comprising a preliminary classification module, a functional division module, a project phase association module, a data level construction module, a main area processing module, a secondary area processing module, a comprehensive data processing module, a multi-objective optimization module, a logical splitting path module, a data fusion and integration module;

[0057] The preliminary classification module uses a decision tree classification algorithm to preliminarily classify BIM model data based on building element types and functional requirements, generating preliminary classification data;

[0058] The functional division module uses a K-means clustering algorithm to functionally divide data based on preliminary classification data, generating functional classification data;

[0059] The project phase association module uses an association rule learning algorithm to analyze the relationship between data and project phases based on functional classification data, generating project phase association data;

[0060] The data level construction module uses data merging technology to integrate data based on project phase association data, generating hierarchical data structures;

[0061] The main area processing module uses heuristic rule analysis algorithm to analyze main area data based on hierarchical data structures, generating main area processing plans;

[0062] The secondary area processing module uses a simplified processing algorithm to analyze secondary areas based on main area processing plans, generating secondary area processing plans;

[0063] The comprehensive data processing module uses data fusion technology to balance processing strategies based on main area processing plans and secondary area processing plans, generating comprehensive data processing schemes;

[0064] The multi-objective optimization module uses multi-objective optimization technology to perform differentiated data processing based on comprehensive data processing schemes, generating optimized splitting plans;

[0065] The logical splitting path module uses a predicate logic splitting engine to perform logical reasoning based on optimized splitting plans, generating logical splitting paths;

[0066] The data fusion integration module integrates the results of the preliminary classification module, the functional division module, the project phase association module, the data level construction module, the main area processing module, the secondary area processing module, the comprehensive data processing module, the multi-objective optimization module, and the logical split path module based on the logical split path, completes the BIM model splitting, and generates the split BIM model.

[0067] Compared with the prior art, the application has the advantages and positive effects that:

[0068] In the application, the efficiency of processing large and complex BIM models is improved by applying the integrated decision tree classification algorithm and K-means clustering, which can effectively cope with large data challenges, optimize the entire model processing flow through efficient data layering and classification, realize deeper data association and analysis in multi-specialty integrated processing such as architecture, structure, electricity, and pipeline, thereby improving the smoothness and efficiency of cross-specialty cooperation, and also including data optimization algorithm and logical splitting technology, which not only speeds up the identification and classification of different components in the model, but also improves the automation degree, and the scheme realizes significant improvement in processing efficiency, data fusion depth, and automation degree, effectively overcoming the limitations of the prior art, and providing a more advanced and comprehensive solution for BIM model processing. BRIEF DESCRIPTION OF DRAWINGS

[0069] Figure 1 It is a workflow diagram of the application;

[0070] Figure 2 It is a S1 refinement flowchart of the application;

[0071] Figure 3 It is a S2 refinement flowchart of the application;

[0072] Figure 4 It is a S3 refinement flowchart of the application;

[0073] Figure 5 It is a S4 refinement flowchart of the application;

[0074] Figure 6 It is a S5 refinement flowchart of the application;

[0075] Figure 7 It is a S6 refinement flowchart of the application;

[0076] Figure 8 It is a S7 refinement flowchart of the application;

[0077] Figure 9 It is a S8 refinement flowchart of the application;

[0078] Figure 10 System flowchart of the present application. DETAILED DESCRIPTION

[0079] In order to make the purpose, technical solutions and advantages of the present application clearer, the present application will be further described in detail below in combination with the drawings and examples. It should be understood that the specific examples described herein are only used to explain the present application and do not limit the present application.

[0080] In the description of the present application, it should be understood that the terms "length", "width", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer" and the like indicate the orientation or positional relationship shown in the drawings, which are only for the convenience of describing the present application and simplifying the description, and do not indicate or imply that the device or element referred to must have a particular orientation, be constructed and operated in a particular orientation, and therefore cannot be understood as a limitation of the present application. In addition, in the description of the present application, the meaning of "a plurality of" is two or more, unless otherwise explicitly and specifically limited.

[0081] Example one

[0082] Please refer to Figure 1 The present application provides a technical solution: a BIM model rapid splitting method, comprising the following steps:

[0083] S1: Based on the building element type and functional requirements, using an integrated decision tree classification algorithm and K-means clustering, the BIM model data is processed in layers, and the type, function and project stage are classified to generate a hierarchical data structure;

[0084] S2: Based on the hierarchical data structure, using a data optimization algorithm based on heuristic rules, differential processing is performed on the main area and the secondary area, and the splitting process is optimized to generate an optimized splitting plan;

[0085] S3: Based on the optimized splitting plan, using a splitting engine based on predicate logic, logical reasoning is performed and the splitting path is selected to generate a logical splitting path;

[0086] S4: Based on the logical splitting path, using an incremental change detection algorithm, the changed part in the model is updated to generate updated splitting data;

[0087] S5: Based on the updated splitting data, using a data compression and optimization algorithm, data streamlining processing is performed to generate streamlined splitting data;

[0088] S6: Based on the streamlined splitting data, using data integrity verification technology, the data quality is optimized to generate quality verification data;

[0089] S7: Based on the quality verification data, use network topology analysis techniques to identify the interdependence between components, and generate a component correlation analysis report;

[0090] S8: Based on the component correlation analysis report, use data fusion and integration algorithms to integrate the hierarchical data structure, optimize the splitting plan, logical splitting path, updated splitting data, streamlined splitting data, and the results of quality verification data, complete the BIM model splitting, and generate the split BIM model.

[0091] The hierarchical data structure includes data layers of structure, electrical, and piping functions, the logical splitting path specifically refers to the path based on the splitting method and sequence derived from logical formulas, the updated splitting data specifically refers to the modification and update information for the changed parts of the model, the streamlined splitting data specifically refers to the optimized data set, the quality verification data specifically refers to the verified data set, and the component correlation analysis report specifically refers to the report showing the dependency relationship and network connection strength between components.

[0092] Through the integrated decision tree classification algorithm, K-means clustering, and heuristic rule data optimization algorithm, BIM model data can be quickly and accurately layered and optimized, thus saving time. In addition, the flexibility and customizability of the method make it suitable for various projects and scenarios, and the splitting rules can be customized according to specific needs, increasing the applicability. The method ensures the consistency and accuracy of the splitting results through logical reasoning and data integrity verification techniques, improves the quality of model data, and reduces the volume of data after splitting through data compression and optimization algorithms and data streamlining processing, improving the efficiency of subsequent analysis and application. Through quality verification data and component correlation analysis report, potential design and construction problems can be found, increasing the project team's understanding and mastery of the model. The automated process helps to reduce the splitting and maintenance costs of the project.

[0093] Please refer to Figure 2 , based on the type of building elements and functional requirements, use integrated decision tree classification algorithm and K-means clustering to layer the BIM model data, and perform type, function and project stage classification. The steps of generating hierarchical data structure are as follows:

[0094] S101: Based on the type of building elements and functional requirements, use the decision tree classification algorithm to preliminarily classify the BIM model data, and generate preliminary classification data;

[0095] S102: Based on the preliminary classification data, use the K-means clustering method to functionally divide the data, and generate function classification data;

[0096] S103: Based on the functional classification data, use the association rule learning algorithm to analyze the relationship between the data and the project phase, and generate project phase association data;

[0097] S104: Based on the project phase association data, use data merging technology to integrate data and generate hierarchical data structure.

[0098] In step S101, the decision tree classification algorithm is used to classify the BIM model data according to the building element type and functional requirements, forming preliminary classification data. This step helps to divide model elements into different categories according to their types. In step S102, the K-means clustering method is used to functionally divide the data based on the preliminary classification data, generating functional classification data, which helps to aggregate similar functional elements together and better understand the functional layout in the model. In step S103, the association rule learning algorithm is used to analyze the relationship between the functional classification data and the project phase, generating project phase association data. This step helps to determine the evolution and relevance of different functional elements in different project phases. In step S104, the data merging technology is used to integrate the preliminary classification data, functional classification data and project phase association data, generating a complete hierarchical data structure. This hierarchical data structure contains detailed information about building element types, functional classification and project phases, providing a basis for subsequent splitting and analysis.

[0099] Please refer to Figure 3 , based on the hierarchical data structure, using heuristic rule-based data optimization algorithm to implement differential treatment for main area and secondary area, and optimize the splitting process, the steps of generating optimized splitting plan are as follows:

[0100] S201: Based on the hierarchical data structure, use heuristic rule analysis algorithm to analyze the main area data, and generate main area processing plan;

[0101] S202: Based on the main area processing plan, use simplified processing algorithm to analyze the secondary area, and generate secondary area processing plan;

[0102] S203: Based on the main area processing plan and the secondary area processing plan, use data fusion technology to balance the processing strategy, and generate comprehensive data processing scheme;

[0103] S204: Based on the comprehensive data processing scheme, use multi-objective optimization technology to perform differential data processing, and generate optimized splitting plan.

[0104] In step S201, a heuristic rule analysis algorithm is used to analyze the main area data in detail based on the hierarchical data structure. This step aims to determine the characteristics and requirements of the main area and generate a processing plan for the main area to ensure that the data in these areas meets specific optimization requirements. In step S202, based on the processing plan for the main area, a simplified processing algorithm is used to analyze the secondary area. The secondary area may require different processing strategies, so a processing plan for the secondary area is generated to ensure that the data in the secondary area can also be properly optimized. In step S203, based on the main area processing plan and the secondary area processing plan, a data fusion technique is used to balance the processing strategies and generate a comprehensive data processing scheme. This scheme takes into account the requirements of the main and secondary areas to ensure that the data of the entire model is properly optimized and processed during the splitting process. In step S204, a multi-objective optimization technique is used to consider differentiated data processing requirements and generate a final optimization splitting plan. This plan optimizes various aspects of the comprehensive data processing scheme to meet multiple optimization objectives, such as reducing data redundancy and improving data quality.

[0105] Please refer to Figure 4 Based on the optimization splitting plan, a predicate logic-based splitting engine is used to perform logical reasoning and select a splitting path. The steps for generating a logical splitting path are as follows:

[0106] S301: Based on the optimization splitting plan, a predicate logic algorithm is used to perform preliminary logical reasoning and generate a preliminary logical reasoning result.

[0107] S302: Based on the preliminary logical reasoning result, a logical optimization technique is used to further optimize the logical structure of the splitting path and generate a logical optimization path result.

[0108] S303: Based on the logical optimization path result, a weighted sorting algorithm is used to sort the path options and generate a weighted sorting splitting result.

[0109] S304: Based on the weighted sorting splitting result, a path decision analysis method is used to select an appropriate splitting path and optimize the efficiency of logical reasoning, generating a logical splitting path.

[0110] In step S301, a predicate logic algorithm is used to perform preliminary logical reasoning based on the optimized split plan. This step aims to extract logical relationships and conditions from the optimized split plan and generate preliminary logical reasoning results, such as determining which elements need to be split in what order. In step S302, based on the preliminary logical reasoning results, a logical optimization technique is used to further optimize the logical structure of the split path. This includes rearranging and organizing logical relationships to ensure the rationality and efficiency of the split path, and generating logical optimization path results. In step S303, based on the logical optimization path results, a weighted ranking algorithm is used to rank different path options. This step will consider various factors, such as the complexity of the split path, data relevance, etc., to generate a weighted ranking of split results list. In step S304, based on the weighted ranking of split results, a path decision analysis method is used to select the most suitable split path and further optimize the efficiency of logical reasoning. This step will ensure that the selected split path is optimal to meet specific split goals and requirements.

[0111] Please refer to Figure 5 Based on the logical split path, an incremental change detection algorithm is used to update the changed parts of the model to generate updated split data. The steps are as follows:

[0112] S401: Based on the logical split path, an incremental change detection technique is used to identify and update the changed parts of the model to generate preliminary updated data;

[0113] S402: Based on the preliminary updated data, a data synchronization protocol is used to maintain data consistency to generate synchronized updated data;

[0114] S403: Based on the synchronized updated data, a differential query technique in the database is used to handle data differences to generate differential updated data;

[0115] S404: Based on the differential updated data, a data merging algorithm is used to integrate data to generate updated split data.

[0116] In step S401, based on the logical split path, the incremental change detection technology is used to identify and update the changed part in the BIM model. This step aims to determine the model changes that need to be made under the guidance of the split path and generate preliminary update data. In step S402, based on the preliminary update data, the data synchronization protocol is used to ensure data consistency. This can include synchronizing the updated data with the original model data to ensure that the updated data remains consistent with other parts of the model. In step S403, based on the synchronized update data, the difference query technology in the database is used to process the data differences. This step helps to determine the data changes in the model and generates differentiated update data that reflects the changes caused by the split path. In step S404, based on the differentiated update data, the data merging algorithm is used for data integration. This step integrates the new update data with the original model data to generate the final updated split data.

[0117] Please refer to Figure 6 Based on the updated split data, the data streamlining processing is performed using the data compression and optimization algorithm to generate streamlined split data. The steps are as follows:

[0118] S501: Based on the updated split data, the compression encoding technology is used to reduce the data volume to generate preliminary compressed data.

[0119] S502: Based on the preliminary compressed data, the data reorganization technology is used to optimize the data structure to generate optimized processing data.

[0120] S503: Based on the optimized processing data, the data reconstruction algorithm is used to reconstruct the data format to generate reconstructed data.

[0121] S504: Based on the reconstructed data, the data stream processing framework is used for stream processing to generate streamlined split data.

[0122] In step S501, based on the updated split data, compression encoding technology is used to reduce data volume. This step aims to compress data to a smaller size through compression algorithms, generating preliminary compressed data, which helps reduce data transmission and storage costs. In step S502, based on the preliminary compressed data, data reorganization technology is used to optimize data structure. This includes reorganizing data to improve data access efficiency and readability, and generating optimized processing data. In step S503, based on the optimized processing data, data reconstruction algorithms are used to reconstruct data format. This step helps restore data to its original format to ensure data integrity and correctness, and generates reconstructed data. In step S504, based on the reconstructed data, data stream processing framework is used for stream processing. This step processes data in a streaming manner to ensure data continuity and real-time performance in the process, ultimately generating streamlined split data.

[0123] Please refer to Figure 7 Based on the streamlined split data, data integrity verification technology is used to optimize data quality, generating quality verification data. The steps are as follows:

[0124] S601: Based on the streamlined split data, data integrity detection algorithm is used to perform preliminary quality check, generating preliminary quality inspection data;

[0125] S602: Based on the preliminary quality inspection data, data cleaning algorithm is used to remove inconsistent and incorrect data, generating cleaned data;

[0126] S603: Based on the cleaned data, integrity enhancement technology is used to optimize data accuracy, generating integrity evaluation data;

[0127] S604: Based on the integrity evaluation data, comprehensive data quality evaluation framework is used to optimize data quality, generating quality verification data.

[0128] In step S601, based on the streamlined split data, a data integrity detection algorithm is used to perform a preliminary quality check, which aims to identify potential problems and inconsistencies in the data, generating preliminary quality inspection data that includes possible problems or errors. In step S602, based on the preliminary quality inspection data, a data cleaning algorithm is used to remove inconsistent and erroneous data, which helps to ensure data consistency and accuracy, and generates cleaned data that has excluded detected problems. In step S603, based on the cleaned data, integrity reinforcement techniques are used to further optimize data accuracy, which may include filling in missing data, correcting erroneous data, and generating integrity evaluation data to ensure data integrity and accuracy. In step S604, based on the integrity evaluation data, a comprehensive data quality evaluation framework is used to consider various data quality factors to further optimize data quality, which helps to ensure that the data meets quality standards in all aspects, and finally generates quality verification data to prove the high quality and reliability of the data.

[0129] Please refer to Figure 8 , based on the quality verification data, network topology analysis techniques are used to identify the interdependence between components, and the steps for generating the component correlation analysis report are as follows:

[0130] S701: Based on the quality verification data, graph theory algorithms are used to analyze the connectivity between components, and a preliminary component relationship graph is generated.

[0131] S702: Based on the preliminary component relationship graph, network flow analysis techniques are used to identify components and dependency paths, and a component dependency graph is generated.

[0132] S703: Based on the component dependency graph, cluster analysis algorithms are used to distinguish groups of multiple types of components, and component group analysis results are generated.

[0133] S704: Based on the component group analysis results, network topology optimization techniques are used to consider multiple types of network parameters to further analyze the dependency and interaction between components, and generate a component correlation analysis report.

[0134] In step S701, based on the quality verification data, the connectivity between components is analyzed using graph theory algorithms. This step aims to generate a preliminary component relationship graph that contains basic connection relationships between components to identify potential relationships between components. In step S702, based on the preliminary component relationship graph, network flow analysis techniques are used to identify components and dependency paths, which helps determine the dependency relationships between components and generate a component dependency graph that contains information about dependency paths. In step S703, based on the component dependency graph, clustering analysis algorithms are used to distinguish multiple types of component groups. This step helps to divide components into different categories or groups and generates component group analysis results to better understand the relationships between components. In step S704, based on the component group analysis results, network topology optimization techniques are used to further analyze the dependency and interaction relationships between components while considering multiple types of network parameters. This step helps to gain a deeper understanding of the relationships between different component groups and generates a component association analysis report that provides detailed dependency and interaction information.

[0135] Please refer to Figure 9 Based on the component association analysis report, data fusion and integration algorithms are used to integrate the results of hierarchical data structures, optimized splitting plans, logical splitting paths, updated splitting data, streamlined splitting data, and quality verification data to complete BIM model splitting and generate a split BIM model. The specific steps are as follows:

[0136] S801: Based on the component association analysis report, use association data integration techniques to preliminarily integrate data results from multiple stages to generate preliminary integrated data.

[0137] S802: Based on the preliminary integrated data, use dimensional analysis to integrate data from multiple aspects and create a comprehensive multi-dimensional data view to generate a multi-dimensional fusion data set.

[0138] S803: Based on the multi-dimensional fusion data set, use data processing techniques to optimize and simplify data to generate a refined data set.

[0139] S804: Based on the refined data set, use comprehensive data management strategies to perform final data fusion and integration, and perform information consistency and completeness checks to generate a split BIM model.

[0140] In step S801, based on the component association analysis report, the association data integration technology is used to preliminarily integrate the data results of multiple stages. This step aims to integrate data from different stages together to generate preliminary integrated data, which contains information from multiple data sources. In step S802, based on the preliminary integrated data, the dimension analysis method is used to integrate multi-aspect data and create a comprehensive multi-dimensional data view. This helps to integrate information from different data dimensions and angles to generate a multi-dimensional fusion data set, providing a more comprehensive data view. In step S803, based on the multi-dimensional fusion data set, data processing techniques are used for data optimization and refinement. This step may include data cleaning, deduplication, filtering, etc. to generate a refined data set, ensuring data quality and accuracy. In step S804, based on the refined data set, comprehensive data management strategies are used for the final fusion and integration of data. This may involve the fusion of different data types, information consistency and completeness correction to generate the final split BIM model, which contains data results from all stages.

[0141] Please refer to Figure 10 A BIM model rapid splitting system for implementing the above BIM model rapid splitting method, the system includes a preliminary classification module, a functional division module, a project stage association module, a data hierarchy construction module, a main area processing module, a secondary area processing module, a comprehensive data processing module, a multi-objective optimization module, a logical splitting path module, and a data fusion integration module.

[0142] The preliminary classification module uses a decision tree classification algorithm to preliminarily classify BIM model data based on building element types and functional requirements, generating preliminary classification data.

[0143] The functional division module uses a K-means clustering algorithm to functionally divide data based on preliminary classification data, generating functional classification data.

[0144] The project stage association module uses an association rule learning algorithm to analyze the relationship between data and project stages based on functional classification data, generating project stage association data.

[0145] The data hierarchy construction module uses data merging techniques to integrate data based on project stage association data, generating a hierarchical data structure.

[0146] The main area processing module uses heuristic rule analysis algorithms to analyze main area data based on the hierarchical data structure, generating a main area processing plan.

[0147] The secondary area processing module uses a simplified processing algorithm to analyze secondary areas based on the main area processing plan, generating a secondary area processing plan.

[0148] The comprehensive data processing module generates a comprehensive data processing scheme based on the primary area processing plan and the secondary area processing plan using data fusion technology and balancing processing strategies;

[0149] The multi-objective optimization module generates an optimized splitting plan by performing differentiated data processing using multi-objective optimization technology based on the comprehensive data processing scheme;

[0150] The logical splitting path module generates a logical splitting path by performing logical reasoning using a predicate logic splitting engine based on the optimized splitting plan;

[0151] The data fusion integration module completes BIM model splitting and generates a split BIM model by integrating the results of the preliminary classification module, the functional division module, the project phase association module, the data level construction module, the primary area processing module, the secondary area processing module, the comprehensive data processing module, the multi-objective optimization module, and the logical splitting path module using data fusion and integration algorithms based on the logical splitting path.

[0152] The system improves data quality, reduces errors and issues in projects, and reduces subsequent repair costs through quality verification and data cleaning algorithms. The system can handle data of various sources and formats, providing users with a comprehensive data view, allowing better understanding and analysis of BIM model data. The multi-objective optimization module and the logical splitting path module provide intelligent decision support, helping users generate optimal splitting plans and paths, improving project planning and management. The data fusion integration module ensures consistency and completeness between data results from various modules, avoiding data dispersion and inconsistency, and improving the credibility of BIM model data. In summary, the BIM model rapid splitting system provides comprehensive support for building and engineering projects, improves work efficiency, data quality, and decision-making levels, providing a solid foundation for successful project implementation and management, and is of great significance for improving productivity and quality in the construction and engineering fields.

[0153] The above is only a preferred embodiment of the present application, and does not limit the form of the present application. Any skilled person in the art can modify or change the above disclosed technical content to apply equivalent embodiments to other fields, but any simple modification, equivalent change, and modification of the above embodiments without departing from the technical solution content of the present application, according to the technical essence of the present application, still belongs to the protection scope of the technical solution of the present application.

Claims

1. A method for rapid disassembly of a BIM model, characterized by, The method comprises the following steps: Based on the type of building elements and functional requirements, the integrated decision tree classification algorithm and K-means clustering are used to perform hierarchical processing on the BIM model data, and type, function and project stage classification is performed to generate a hierarchical data structure; Based on the hierarchical data structure, a data optimization algorithm based on heuristic rules is used to implement differential processing on the main and secondary areas, and to optimize the splitting process to generate an optimized splitting plan; Based on the optimized splitting plan, a splitting engine based on predicate logic is used to perform logical reasoning and select a splitting path to generate a logical splitting path; Based on the logical splitting path, an incremental change detection algorithm is used to update the changed part of the model to generate updated splitting data; Based on the updated splitting data, a data compression and optimization algorithm is used to perform data streamlining processing to generate streamlined splitting data; Based on the streamlined splitting data, a data integrity verification technology is used to optimize data quality to generate quality verification data; Based on the quality verification data, a network topology analysis technology is used to identify the mutual dependence between components to generate a component correlation analysis report; Based on the component correlation analysis report, a data fusion and integration algorithm is used to integrate the results of the hierarchical data structure, the optimized splitting plan, the logical splitting path, the updated splitting data, the streamlined splitting data and the quality verification data to complete the BIM model splitting and generate a split BIM model; The hierarchical data structure includes data layers of structure, electrical, and piping functions, the logical splitting path specifically refers to the path of the splitting method and sequence based on logical formula derivation, the updated splitting data specifically refers to modification and update information of the changed part of the model, the streamlined splitting data specifically refers to an optimized data set, the quality verification data specifically refers to a verified data set, and the component correlation analysis report specifically refers to a report showing the dependency relationship and network connection strength between components; The step of generating a hierarchical data structure based on the type of building elements and functional requirements, using an integrated decision tree classification algorithm and K-means clustering to perform hierarchical processing on BIM model data, and performing type, function and project stage classification, specifically comprises: Based on the type of building elements and functional requirements, a decision tree classification algorithm is used to perform preliminary classification on BIM model data to generate preliminary classification data; Based on the preliminary classification data, a K-means clustering method is used to perform functional division on the data to generate functional classification data; Based on the functional classification data, an association rule learning algorithm is used to analyze the relationship between the data and the project stage to generate project stage association data; Based on the project stage association data, a data merging technology is used to integrate the data to generate a hierarchical data structure; The step of generating a logical splitting path based on the optimized splitting plan, using a splitting engine based on predicate logic to perform logical reasoning and select a splitting path, specifically comprises: Based on the optimized splitting plan, a predicate logic algorithm is used to perform preliminary logical reasoning to generate preliminary logical reasoning results; Based on the preliminary logical reasoning result, a logical optimization technique is used to further optimize the logical structure of the split path, and a logical optimization path result is generated; Based on the logical optimization path result, a weighted sorting algorithm is used to sort the path options, and a weighted sorting split result is generated; Based on the weighted sorting split result, a path decision analysis method is used to select the appropriate split path and optimize the logical reasoning efficiency, and a logical split path is generated.

2. The method of claim 1, wherein, Based on the hierarchical data structure, a data optimization algorithm based on heuristic rules is used to implement differential processing on the main area and the secondary area, and to optimize the split process, and the steps to generate the optimized split plan are as follows: Based on the hierarchical data structure, a heuristic rule analysis algorithm is used to analyze the main area data and generate a main area processing plan; Based on the main area processing plan, a simplified processing algorithm is used to analyze the secondary area and generate a secondary area processing plan; Based on the main area processing plan and the secondary area processing plan, a data fusion technology is used to balance the processing strategy and generate a comprehensive data processing scheme; Based on the comprehensive data processing scheme, a multi-objective optimization technique is used for differential data processing to generate an optimized split plan.

3. The method of claim 2, wherein, Based on the logical split path, an incremental change detection algorithm is used to update the changed part of the model, and the steps to generate the updated split data are as follows: Based on the logical split path, an incremental change detection technology is used to identify and update the changed part of the model, and preliminary update data is generated; Based on the preliminary update data, a data synchronization protocol is used to maintain data consistency, and synchronization update data is generated; Based on the synchronization update data, a differential query technology in the database is used to process data differences, and differential update data is generated; Based on the differential update data, a data merging algorithm is used for data integration to generate updated split data.

4. The method of claim 3, wherein, Based on the updated split data, a data compression and optimization algorithm is used for data streamlining processing to generate streamlining split data, and the steps are as follows: Based on the updated split data, a compression encoding technology is used to reduce data volume, and preliminary compressed data is generated; Based on the preliminary compressed data, a data reorganization technology is used to optimize data structure, and optimized processing data is generated; Based on the optimized processing data, a data reconstruction algorithm is used to reconstruct the data format, and the reconstructed data is generated; Based on the reconstructed data, a data stream processing framework is used for stream processing to generate streamlining split data.

5. The method of claim 4, wherein, Based on the streamlining split data, a data integrity verification technology is used to optimize data quality, and quality verification data is generated, and the steps are as follows: Based on the streamlining split data, a data integrity detection algorithm is used to perform preliminary quality inspection, and preliminary quality inspection data is generated; Based on the preliminary quality inspection data, a data cleaning algorithm is used to remove inconsistent and incorrect data, and cleaned data is generated; Based on the cleaned data, an integrity enhancement technology is used to optimize data accuracy, and integrity evaluation data is generated; Based on the integrity evaluation data, a comprehensive data quality evaluation framework is used to optimize data quality and generate quality verification data.

6. The method of claim 5, wherein, Based on the quality verification data, a network topology analysis technique is used to identify the interdependence between components and generate a component correlation analysis report. The steps are as follows: Based on the quality verification data, a graph theory algorithm is used to analyze the connectivity between components and generate a preliminary component relationship graph. Based on the preliminary component relationship graph, a network flow analysis technique is used to identify components and dependent paths, and a component dependency graph is generated. Based on the component dependency graph, a cluster analysis algorithm is used to distinguish groups of components of multiple types, and a component group analysis result is generated. Based on the component group analysis result, a network topology optimization technique is used to further analyze the dependence and interaction between components, considering multiple types of network parameters, and a component correlation analysis report is generated.

7. The method of claim 6, wherein, Based on the component correlation analysis report, a data fusion and integration algorithm is used to integrate the results of hierarchical data structure, optimized splitting plan, logical splitting path, updated splitting data, streamlined splitting data, and quality verification data, complete BIM model splitting, and generate a split BIM model. The steps are as follows: Based on the component correlation analysis report, an associated data integration technique is used to preliminarily integrate the data results of multiple stages to generate preliminary integrated data. Based on the preliminary integrated data, a dimension analysis method is used to integrate multiple aspects of data and create a comprehensive multi-dimensional data view to generate a multi-dimensional fusion data set. Based on the multi-dimensional fusion data set, a data processing technique is used for data optimization and simplification to generate a refined data set. Based on the refined data set, a comprehensive data management strategy is used for the final fusion and integration of data, and information consistency and integrity are checked to generate a split BIM model.

8. A BIM model quick-splitting system, characterized in that, The BIM model rapid splitting method according to any one of claims 1-7, wherein the system comprises a preliminary classification module, a functional division module, a project stage association module, a data hierarchical construction module, a main area processing module, a secondary area processing module, a comprehensive data processing module, a multi-objective optimization module, a logical splitting path module, and a data fusion and integration module. The preliminary classification module uses a decision tree classification algorithm to preliminarily classify BIM model data based on building element types and functional requirements, and generates preliminary classification data. The functional division module uses a K-means clustering algorithm to functionally divide data based on preliminary classification data, and generates functional classification data. The project stage association module uses an association rule learning algorithm to analyze the relationship between data and project stages based on functional classification data, and generates project stage association data. The data hierarchical construction module uses data merging techniques to integrate data based on project stage association data, and generates hierarchical data structure. The main area processing module uses heuristic rule analysis algorithm to analyze main area data based on hierarchical data structure, and generates main area processing plan. The secondary area processing module uses a simplified processing algorithm to analyze secondary areas based on the main area processing plan, and generates a secondary area processing plan. The comprehensive data processing module generates a comprehensive data processing scheme based on the primary area processing plan and the secondary area processing plan, using a data fusion technology and a balanced processing strategy; The multi-objective optimization module generates an optimized splitting plan by performing differentiated data processing based on the comprehensive data processing scheme, using a multi-objective optimization technology; The logical splitting path module generates a logical splitting path by performing logical reasoning based on the optimized splitting plan, using a predicate logic splitting engine; The data fusion integration module completes BIM model splitting and generates a split BIM model by integrating the results of the preliminary classification module, the functional division module, the project phase association module, the data level construction module, the primary area processing module, the secondary area processing module, the comprehensive data processing module, the multi-objective optimization module, and the logical splitting path module, based on the logical splitting path, using a data fusion and integration algorithm.

Images