Model quality evaluation method and device, electronic equipment, product and storage medium

Abstract

The embodiment of the application discloses a model quality evaluation method, device, electronic equipment, product and storage medium, the method comprises the following steps: obtaining the source file of the building information model and the engineering construction specification information corresponding to the building information model; at least one specification entity and the association relationship between the specification entities are extracted from the engineering construction specification information to construct a target knowledge graph; information associated with at least one building component in the building information model is extracted from the source file to obtain building component association information; the building component association information is converted into knowledge structured data matching the data format of the target knowledge graph; the quality of the building information model is evaluated according to the knowledge structured data and the target knowledge graph, and an evaluation result is obtained. The scheme in the application can improve the efficiency and accuracy of the building information model quality evaluation result.

Description

Technical Field

[0001] This application relates to the field of data processing technology, specifically to a model quality evaluation method, apparatus, electronic device, product, and storage medium. Background Technology

[0002] BIM (Building Information Model) is a digital carrier that integrates multi-dimensional information such as geometry, material properties, construction techniques, cost, and schedule throughout the entire lifecycle of a building project. It enables interdisciplinary collaboration, visual simulation, and data sharing. BIM model quality evaluation aims to ensure its application value, focusing on the model's accuracy, consistency, completeness, and standardization. Problems are identified through professional software verification, manual review, and collaborative auditing to ensure the model reliably supports subsequent construction guidance, cost accounting, and operation and maintenance management, avoiding actual project risks caused by model defects.

[0003] However, existing BIM model quality assessment methods mostly rely on pre-stored knowledge bases to search for model collision quality issues. The knowledge base for automatic BIM model quality assessment has limited rule coverage, requiring the acquisition of evaluation problem requirements information first, and then translating the evaluation problem requirements information into a language that microcomputers can recognize. This leads to a decrease in the efficiency and accuracy of model quality assessment results.

[0004] Therefore, improving the efficiency and accuracy of BIM quality assessment results is an urgent problem to be solved. Summary of the Invention

[0005] This application provides a model quality evaluation method, apparatus, electronic device, product, and storage medium, which can improve the efficiency and accuracy of BIM quality evaluation results.

[0006] This application provides a model quality evaluation method, including:

[0007] Obtain the source files of the building information model and the engineering construction specifications information corresponding to the building information model;

[0008] Extract at least one specification entity and the association between the specification entities from the engineering construction specification information to construct a target knowledge graph;

[0009] Extract information associated with at least one building component in the building information model from the source file to obtain building component association information;

[0010] The building component association information is converted into structured knowledge data that matches the data format of the target knowledge graph;

[0011] The quality of the building information model is evaluated based on the structured knowledge data and the target knowledge graph, and the evaluation results are obtained.

[0012] In some embodiments, before extracting information associated with at least one building component in the building information model from the source file, the method further includes:

[0013] For files of different source formats in the source files, different data cleaning processes are performed to remove invalid and redundant data and repair broken data chains, resulting in first pre-processed data, which includes RVT data, DWG data, and 3DM data.

[0014] The parametric attributes of the RVT data are preserved, the mapping relationship between the two-dimensional annotations and the three-dimensional model in the DWG data is strengthened, and the conversion algorithm of the surface data in the 3DM data is optimized to obtain the second preprocessed data.

[0015] The second preprocessed data is converted into a preset data format using a format conversion tool to obtain the third preprocessed data.

[0016] After comparing the source file with the third preprocessed data and confirming that the number of components, key attributes, and spatial topology relationships in the third preprocessed data have not been lost or tampered with, the third preprocessed data is used as the converted data, wherein the converted data is used to obtain the association information of the building components.

[0017] In some implementations, the step of extracting information associated with at least one building component in the building information model from the source file to obtain building component association information includes:

[0018] Extract the component information of the building information model from the source file, wherein the component information includes component attributes, component spatial relationships, component material information, and component connection relationships;

[0019] Extract multi-dimensional association information corresponding to the component information from the source file. The multi-dimensional association information includes the industry standard clause serial number corresponding to the component, the design stage version number, the construction process requirements, the material supplier qualification information, and the quality inspection records of similar components in previous projects.

[0020] The component information is integrated with the multi-dimensional association information to obtain the building component association information.

[0021] In some implementations, converting the building component association information into structured knowledge data that matches the data format of the target knowledge graph includes:

[0022] A unique identifier code is added to each data node in the building component association information, and a mapping relationship is established between the component information, the multi-dimensional association information and the unique identifier code to obtain initial knowledge structured data.

[0023] The initial knowledge structured data is transformed into a resource description framework or web ontology language format to obtain knowledge structured data that matches the data format of the target knowledge graph.

[0024] In some implementations, extracting at least one specification entity and the association between the specification entities from the engineering construction specification information to construct a target knowledge graph includes:

[0025] Obtain specification documents from the engineering construction specification information, wherein the specification documents include structured data, semi-structured data, and unstructured data;

[0026] Knowledge extraction and annotation are performed on the standard documents to identify standard terms, standard definitions and standard relationships, and the standard terms, standard definitions and standard relationships are transformed into structured standard text;

[0027] Extract component types, component attributes, and relationships between components from the specification text, and associate the component types, component attributes, and relationships between components with the corresponding definitions and attributes to obtain specification entities and the association relationships between the specification entities;

[0028] The target knowledge graph is obtained by using the standardized entities as nodes and the relationships between the standardized entities as edges.

[0029] In some implementations, after constructing the target knowledge graph, the following steps are also included:

[0030] Based on the normative attributes, determine the mandatory level corresponding to the normative entities in the target knowledge graph;

[0031] Based on the engineering phase, determine the degree of engineering criticality corresponding to the standardized entities in the target knowledge graph;

[0032] Based on the mandatory level and the criticality of the project, the execution priority of each of the specification entities is determined;

[0033] Based on the execution priority, an index table corresponding to the target knowledge graph is established so that the standard entity can be located and invoked through the index table when evaluating the quality of the building information model.

[0034] In some implementations, evaluating the quality of the building information model based on the knowledge structured data and the target knowledge graph includes:

[0035] Based on the structured knowledge data and the target knowledge graph, check for missing components and omissions of related data in the building information model;

[0036] Based on the structured knowledge data and the target knowledge graph, check the compliance of the building information model with the relevant standards.

[0037] Based on the structured knowledge data and the target knowledge graph, check the missing component attributes and the accuracy of parameters in the building information model;

[0038] Based on the missing components, the omissions of the associated data, the compliance with the specifications, the missing component attributes, and the accuracy of the parameters, the quality evaluation result of the building information model is obtained.

[0039] In some embodiments, after evaluating the quality of the building information model, the method further includes:

[0040] Based on the spatial topology and data association network of the target knowledge graph, information on non-compliant components is determined, wherein the information on non-compliant components includes the three-dimensional coordinates, professional zone, and associated component group of the non-compliant component in the building information model;

[0041] By tracing the relationships between data nodes in the structured knowledge data, the root cause of data errors can be located;

[0042] A model detection report is generated based on the information of the non-compliant components and the root cause of the data errors.

[0043] In some implementations, after generating the model detection report, the method further includes:

[0044] Based on the correct cases, industry best practice data, and associated construction process requirements in the target knowledge graph, determine the modification scheme corresponding to each non-compliant component in the building information model;

[0045] By combining the priority of the norms in the target knowledge graph and the influence range of components that do not conform to the norms, the modification schemes are sorted to obtain modification priorities, so that the modification schemes can be executed based on the modification priorities.

[0046] This application embodiment also provides a model quality evaluation device, including:

[0047] The information acquisition unit is used to acquire the source file of the building information model and the engineering construction specification information corresponding to the building information model;

[0048] A knowledge graph construction unit is used to extract at least one specification entity and the association between the specification entities from the engineering construction specification information in order to construct a target knowledge graph.

[0049] The building component association information acquisition unit is used to extract information associated with at least one building component in the building information model from the source file to obtain building component association information.

[0050] The information conversion unit is used to convert the building component association information into knowledge structured data that matches the data format of the target knowledge graph;

[0051] The quality evaluation unit is used to evaluate the quality of the building information model based on the knowledge structured data and the target knowledge graph, and obtain the evaluation result.

[0052] This application also provides an electronic device, including a processor and a memory, wherein the memory stores a plurality of instructions; the processor loads instructions from the memory to execute steps in any of the model quality evaluation methods provided in this application.

[0053] This application also provides a computer program product, including a computer program / instructions, which, when executed by a processor, implement the steps in any of the model quality evaluation methods provided in this application.

[0054] This application also provides a computer-readable storage medium storing a plurality of instructions adapted for loading by a processor to execute steps in any of the model quality evaluation methods provided in this application.

[0055] In this embodiment, the following steps are taken: First, the source file of the Building Information Model (BIM) and the corresponding engineering construction standard information are obtained. Then, at least one standard entity and the relationship between the standard entities are extracted from the engineering construction standard information to construct a target knowledge graph. Next, information associated with at least one building component in the BIM is extracted from the source file to obtain building component association information. Then, the building component association information is converted into knowledge structured data that matches the data format of the target knowledge graph. Finally, the quality of the BIM is evaluated based on the knowledge structured data and the target knowledge graph to obtain an evaluation result.

[0056] In this application, source files of the Building Information Model (BIM) and engineering construction standard information are obtained to provide basic data for subsequent evaluation work. The association information of building components in the source files is extracted and transformed into structured knowledge data that matches the data format of the knowledge graph. Furthermore, standard entities and their relationships are extracted from the standard information to establish a target knowledge graph, ensuring that both building information and standard information are presented in a structured and easily associative form. Finally, the quality of the BIM is evaluated based on these two factors, enabling a more accurate comparison between the model and standard requirements, and a comprehensive and precise identification of model quality issues, thereby improving the efficiency and accuracy of BIM quality evaluation results. Attached Figure Description

[0057] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0058] Figure 1 This is a schematic diagram of a scenario for the model quality evaluation method provided in the embodiments of this application;

[0059] Figure 2 This is a flowchart illustrating the model quality evaluation method provided in the embodiments of this application;

[0060] Figure 3 This is a schematic diagram of the structure of the model quality evaluation device provided in the embodiments of this application;

[0061] Figure 4 This is a schematic diagram of the structure of the electronic device provided in the embodiments of this application. Detailed Implementation

[0062] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0063] This application provides a model quality evaluation method, apparatus, electronic device, product, and storage medium.

[0064] Specifically, the model quality evaluation device can be integrated into an electronic device, such as a terminal or server. The terminal can be a mobile phone, tablet, smart Bluetooth device, laptop, or personal computer (PC); the server can be a single server or a server cluster consisting of multiple servers.

[0065] In some embodiments, the model quality evaluation device can also be integrated into multiple electronic devices, such as multiple servers, with multiple servers implementing the model quality evaluation method of this application.

[0066] In some embodiments, the terminal can also be used as a server to implement some or all of the functions of a server.

[0067] For example, refer to Figure 1 , Figure 1 This is a schematic diagram of a scenario for the model quality evaluation method provided in the embodiments of this application.

[0068] like Figure 1 As shown, this application scenario may include a terminal device 100 and a building information model 200, wherein the terminal device 100 can acquire multiple building information models 200. In practical applications, the user issues instructions to the terminal device 100 to acquire the source files of the building information models 200 and the corresponding engineering construction specifications information; the terminal device 100 extracts at least one specification entity and the association relationships between the specification entities from the engineering construction specifications information to construct a target knowledge graph; the terminal device 100 extracts information associated with at least one building component in the building information model from the source files to obtain building component association information; the terminal device 100 converts the building component association information into knowledge structured data that matches the data format of the target knowledge graph; the terminal device 100 evaluates the quality of the building information model based on the knowledge structured data and the target knowledge graph to obtain an evaluation result.

[0069] in, Figure 1 The scenario shown includes a terminal device 100. In other possible implementation environments, when more users evaluate the model quality through terminal devices 100, there may be more terminal devices 100. This application does not impose any limitations on this.

[0070] The server can be a standalone physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, CDN (Content Delivery Network), and big data and artificial intelligence platforms. Terminals and servers can be connected directly or indirectly via wired or wireless communication; this application does not impose any restrictions on this.

[0071] The following sections provide detailed descriptions of each example. It should be noted that the sequence numbers of the following embodiments are not intended to limit the preferred order of the embodiments.

[0072] This embodiment provides a model quality evaluation method. (Reference) Figure 2 , Figure 2 This is a flowchart illustrating the model quality evaluation method provided in an embodiment of this application. For example... Figure 2 As shown, the specific process of this model quality evaluation method can be as follows:

[0073] 210. Obtain the source files of the building information model and the engineering construction specifications information corresponding to the building information model.

[0074] Among them, model quality evaluation refers to the evaluation process of building information models in terms of compliance with relevant specifications and completeness, which is used to determine whether the model meets the requirements of engineering construction. This evaluation is carried out based on knowledge structured data and target knowledge graph to determine the quality status of the model.

[0075] Among them, the source files of the building information model refer to the initial files containing information related to the building project, such as RVT (Revit File, a proprietary file format used by Autodesk Revit software), DWG (Drawing, a standard two-dimensional and three-dimensional design data format used by AutoCAD software), 3DM (a file format used by Rhino software that supports complex three-dimensional modeling tasks), and other format files. These files record various aspects of the building project's design, construction, and other information.

[0076] Among them, engineering construction standard information refers to the normative content such as laws and standards followed in the engineering construction process, which covers the normative requirements such as component types, attributes, and relationship calculations. Key content is extracted from this information to establish a target knowledge graph, which serves as the standard basis for evaluating the quality of the model.

[0077] 220. Extract at least one specification entity and the association between the specification entities from the engineering construction specification information to construct a target knowledge graph.

[0078] Among them, the normative entities are the specific entity content such as key concepts, terms, component types, and attributes extracted from engineering construction standard information. These normative entities serve as nodes in the target knowledge graph, constructing a normative knowledge system.

[0079] Among them, the relationship between normative entities refers to the mutual connection between normative entities, such as the complex relationship between components. These relationships serve as edges of the target knowledge graph, connecting various normative entities to form a complete target knowledge graph.

[0080] Among them, the target knowledge graph is a knowledge system that is represented in the form of a graph database by extracting the standard entities and standard relationships from the engineering construction standard information. Nodes represent entities and edges represent the relationships between entities. It serves as an important basis for evaluating model quality and is combined with structured knowledge data to judge model quality.

[0081] 230. Extract information associated with at least one building component in the building information model from the source file to obtain building component association information.

[0082] Among them, building component association information refers to various types of information related to building components, including component attributes, spatial relationships, material information, and connection relationships between components, as well as corresponding multi-dimensional association information, such as industry standard clause IDs and design phase version numbers. This information is extracted from the transformed data for subsequent conversion into knowledge structured data.

[0083] 240. Convert the building component association information into knowledge structured data that matches the data format of the target knowledge graph.

[0084] Among them, the knowledge structured data that matches the data format of the target knowledge graph refers to the data after the association information of building components has been structured in a way that the knowledge graph can recognize and process, such as converting it into the Resource Description Framework (RDF) or Web Ontology Language (OWL) format, and adding a unique identifier code to each data node. These data formats are convenient for combining with the target knowledge graph to evaluate the model quality.

[0085] 250. Evaluate the quality of the building information model based on the structured knowledge data and the target knowledge graph, and obtain the evaluation results.

[0086] For example, consider a residential building project whose Building Information Model (BIM) source files include architectural design documents in RVT format and drawing files in DWG format. The engineering construction specifications are relevant national standards and specifications for residential building construction. Component attributes such as dimensions and materials of beams and slabs, their spatial relationships (e.g., coordinates), and corresponding industry standard clause IDs (serial numbers) are extracted from the source files as building component association information. This information is then converted into RDF format, a knowledge-structured data format matching the knowledge graph's data format. Standard entities such as beam load-bearing capacity requirements and the relationships between these entities (e.g., the connection relationships between beams and slabs) are extracted from the engineering construction specifications to establish a target knowledge graph. Finally, based on the knowledge-structured data and the target knowledge graph, the quality of the residential building BIM is evaluated, determining whether beam dimensions conform to specifications, etc., to obtain the evaluation results.

[0087] As can be seen from the above, this embodiment of the application provides basic data for subsequent evaluation work by acquiring the source files of the building information model and engineering construction specification information; extracting the building component association information from the source files and converting it into knowledge structured data that matches the data format of the knowledge graph; and extracting specification entities and the association relationships between specification entities from the specification information to establish a target knowledge graph, so that both building information and specification information are presented in a structured and easily associative form; finally, the quality of the building information model is evaluated based on these two, which can more accurately compare the model with the specification requirements, comprehensively and accurately discover model quality problems, thereby improving the efficiency and accuracy of BIM quality evaluation results.

[0088] In some embodiments, before extracting information associated with at least one building component in the building information model from the source file, the method further includes:

[0089] For files of different source formats in the source files, different data cleaning processes are performed to remove invalid and redundant data and repair broken data chains, resulting in first pre-processed data, which includes RVT data, DWG data, and 3DM data.

[0090] The parametric attributes of the RVT data are preserved, the mapping relationship between the two-dimensional annotations and the three-dimensional model in the DWG data is strengthened, and the conversion algorithm of the surface data in the 3DM data is optimized to obtain the second preprocessed data.

[0091] The second preprocessed data is converted into a preset data format using a format conversion tool to obtain the third preprocessed data.

[0092] After comparing the source file with the third preprocessed data and confirming that the number of components, key attributes, and spatial topology relationships in the third preprocessed data have not been lost or tampered with, the third preprocessed data is used as the converted data, wherein the converted data is used to obtain the association information of the building components.

[0093] Among them, different source format files refer to the fact that the source files of Building Information Modeling (BIM) exist in multiple formats, such as the common RVT, DWG, 3DM, etc. Each format has different data structures and characteristics, and is suitable for different design and modeling scenarios. These different format files need to be processed separately to achieve unified data format conversion.

[0094] The data cleaning process involves specific operations performed on files of different source formats. Its purpose is to clean and repair file data, improve data quality, and develop customized data cleaning processes based on the characteristics of different file formats to remove invalid data and repair damaged data.

[0095] Removing invalid and redundant data is a key step in the data cleaning process. It involves removing data from files that is useless and redundant for evaluating model quality, such as temporary annotations and discarded component sketches. By performing this step, the data base is kept clean, the amount of data to be processed in subsequent steps is reduced, and processing efficiency is improved.

[0096] Repairing damaged data chains is also an important part of the data cleaning process. This involves fixing data connection problems in the files, such as broken component relationships, to ensure the integrity and consistency of the data. This operation enables the data to accurately reflect the actual structure and relationships of the building model, providing accurate data for subsequent processing.

[0097] Among them, parametric attributes are a characteristic of RVT data. Through parametric settings, the size, material and other attributes of building components can be automatically adjusted according to parameter changes. Preserving the parametric attributes of RVT data helps to analyze and judge based on parameters in subsequent model quality evaluation.

[0098] Among them, the mapping and association between two-dimensional annotations and three-dimensional models refers to establishing an accurate correspondence between the annotation information on the two-dimensional drawings and the corresponding components and features in the three-dimensional model in the DWG data. Strengthening this mapping and association can enable the information of the two-dimensional drawings to better serve the quality evaluation of the three-dimensional model.

[0099] Among them, the surface data conversion algorithm is a calculation method used to convert surface data in 3DM data into a preset data format. Optimizing the algorithm can improve the conversion accuracy and efficiency of surface data in the format conversion process of 3DM data.

[0100] The preset data format is a pre-defined data format, such as IFC (Industry Foundation Classes, an international standard organization's building information modeling data format). Its purpose is to unify the source files of building information models from different source formats into a format that is easy to process and analyze.

[0101] Format conversion refers to the process of transforming the source files of a Building Information Model (BIM) from their original format to a preset data format. This process is accomplished by using an IFC conversion tool, which performs dedicated data cleaning and format compatibility adaptation steps, and then verifies the conversion results.

[0102] For example, in a commercial building project, the source files of the Building Information Modeling (BIM) include RVT format building structure design files, DWG format building floor plans, and 3DM format building exterior design files. For these different source formats, a data cleaning process is performed on the RVT files to remove invalid and redundant data such as temporary decorative elements, and to repair potentially broken data chains, such as broken connections between some walls and beams, resulting in the first pre-processed data. For the RVT data, parametric attributes such as column dimensions are retained; for the DWG data, the mapping between 2D annotations such as doors and windows in the building floor plans and corresponding components in the 3D model is strengthened, for example, accurately mapping the dimensions of doors and windows to the door and window components in the 3D model; for the 3DM data, the conversion algorithm for its building exterior surface design data is optimized. Then, the second preprocessed data is converted into the preset IFC format using a format conversion tool to obtain the third preprocessed data. This third preprocessed data is then compared with the original RVT, DWG, and 3DM source files to confirm that the number of components, key attributes (such as column material, beam length, etc.), and spatial topology (such as the connection relationship between walls and floor slabs) have not been lost or tampered with, and then used as the converted data.

[0103] In this embodiment, different data cleaning processes are performed on files of different source formats to remove invalid and redundant data and repair broken data chains, effectively improving data quality and providing a reliable foundation for subsequent processing. Targeted processing is applied to RVT, DWG, and 3DM data respectively, preserving the parametric attributes of RVT data, strengthening the mapping relationship between 2D annotations and 3D models in DWG data, and optimizing the conversion algorithm for surface data in 3DM data, fully utilizing the advantages of different data formats. Data conversion is performed using format conversion tools and comparison verification, ensuring the integrity and accuracy of the converted data. This improves the efficiency and quality of source file format conversion for Building Information Modeling (BIM), thereby enhancing the accuracy and reliability of BIM model quality evaluation based on the converted data.

[0104] In some implementations, the step of extracting information associated with at least one building component in the building information model from the source file to obtain building component association information includes:

[0105] Extract the component information of the building information model from the source file, wherein the component information includes component attributes, component spatial relationships, component material information, and component connection relationships;

[0106] Extract multi-dimensional association information corresponding to the component information from the source file. The multi-dimensional association information includes the industry standard clause serial number corresponding to the component, the design stage version number, the construction process requirements, the material supplier qualification information, and the quality inspection records of similar components in previous projects.

[0107] The component information is integrated with the multi-dimensional association information to obtain the building component association information.

[0108] Component information refers to the basic information about various components in the Building Information Model (BIM), including: component attributes such as dimensions, material, and strength grade, which describe the characteristics of the component itself; spatial relationships such as location coordinates, adjacency relationships, and containment relationships, reflecting the layout and interrelationships of components in space; component material information, including model, specifications, and environmental protection level, specifying the relevant parameters of the materials used in the component; and component connection relationships, such as connection methods and fastener parameters, explaining how the components are connected together. This information is extracted from the converted data and serves as the foundation for analyzing and evaluating the quality of building components.

[0109] The multi-dimensional related information consists of a series of extended information corresponding to the component information, including the industry standard clause serial number corresponding to the component, which clarifies the specific standards the component should follow; the design stage version number, reflecting the status of the component at different design stages; construction process requirements, guiding the operation of the component during construction; material supplier qualification information, ensuring the reliability of the source of the materials used; and quality inspection records of similar components in previous projects, which can be used as a reference to assess the quality of the current component. This multi-dimensional information enriches the description of the component and provides more basis for a comprehensive evaluation of the component.

[0110] In this process, when integrating component information with multi-dimensional association information to obtain building component association information, the component information extracted from the transformed data and the multi-dimensional association information can be merged to form a more comprehensive and integrated information set. This integrated building component association information provides a complete data foundation for subsequent conversion into knowledge structured data that matches the data format of the knowledge graph, and for building information model quality evaluation based on this.

[0111] For example, in a high-rise office building construction project, the source file extracts the component information of the steel beam in the office building from the converted data. This includes component attributes such as the steel beam's dimensions (length is 10 meters, cross-sectional dimensions are 500mm×300mm) and material (Q345 steel), the steel beam's position coordinates in the floor (located on the 5th floor, X coordinate is 10-20 meters, Y coordinate is 15-25 meters), the component's spatial relationship with adjacent columns, the component material information such as the steel type (Q345) and specifications (thickness 10mm) of the steel used in the steel beam, and the component connection relationship such as the connection method (e.g., welding) and welding parameters between the steel beam and the column. Simultaneously, multi-dimensional correlation information is extracted, such as the industry standard clause serial number corresponding to the steel beam (the clause on steel beam strength calculation in GB50017-2017), the design stage version number (V2.0), construction process requirements (temperature, speed, and other conditions that welding must meet), material supplier qualification information (possessing the corresponding steel production qualifications), and quality inspection records of similar components in previous projects (flaw detection results of steel beams in a similar project). Finally, this component information is integrated with the multi-dimensional correlation information to obtain the building component correlation information of the steel beam.

[0112] In this embodiment, by extracting and integrating component information and multi-dimensional correlation information from the source files, comprehensive and detailed data on building components are obtained. Component information provides the basic characteristics and interrelationships of the components themselves, while multi-dimensional correlation information enriches the understanding of the components from multiple perspectives such as specifications, design, and construction. The integrated building component correlation information provides detailed and comprehensive data support for subsequent quality evaluation of building information models based on knowledge graphs. This enables the quality evaluation to more accurately and deeply consider the components in various aspects, thereby improving the accuracy and reliability of BIM quality evaluation results and better ensuring the quality of building projects.

[0113] In some implementations, converting the building component association information into structured knowledge data that matches the data format of the target knowledge graph includes:

[0114] A unique identifier code is added to each data node in the building component association information, and a mapping relationship is established between the component information, the multi-dimensional association information and the unique identifier code to obtain initial knowledge structured data.

[0115] The initial knowledge structured data is transformed into a resource description framework or web ontology language format to obtain knowledge structured data that matches the data format of the target knowledge graph.

[0116] The unique identifier code is a unique identification code assigned to each data node in the building component association information. It is like an ID card for each data point, used to accurately locate and distinguish different data in subsequent data processing and analysis. By adding a unique identifier code to each data node, it is convenient to manage and trace component information and multi-dimensional association information.

[0117] Establishing a mapping relationship between component information, multi-dimensional association information, and unique identifier codes refers to constructing a corresponding connection between these three elements. This allows for the rapid retrieval of corresponding component information and multi-dimensional association information using the unique identifier code, and vice versa. This mapping relationship is a crucial step in constructing initial structured knowledge data, contributing to the formation of a structured and traceable data network.

[0118] Among them, the Resource Description Framework (RDF) is a language used to describe resources on the World Wide Web. It expresses information in the form of triples (subject, predicate, object), which enables data to be represented and exchanged in a universal and easy-to-understand way. Transforming initial knowledge structured data into RDF format is beneficial for knowledge graphs to identify and process data, and facilitates data sharing between different systems and platforms.

[0119] Among them, the Web Ontology Language Format (OWL) is a language used to represent ontology in the Semantic Web. Based on descriptive logic, it can accurately describe concepts, attributes, and relationships, enhancing the semantic expressive power of data. Transforming initial knowledge structured data into OWL format can better adapt to the semantic information processing needs of knowledge graphs, enabling knowledge graphs to understand and utilize this data more intelligently.

[0120] For example, in a large shopping mall construction project, the structural information associated with a concrete column includes component information such as dimensions (diameter 800mm, height 5 meters), material (C30 concrete), and multi-dimensional associated information such as the corresponding industry standard clause sequence number (the clause on concrete column design in GB50010-2010), construction process requirements (vibration method and time for concrete pouring), etc. First, a unique identifier code is added to each data node. For example, the data node for diameter 800mm is assigned the code C001-001, and the data node for the clause on concrete column design in GB50010-2010 is assigned the code C001-002, etc., establishing a mapping relationship between component information, multi-dimensional associated information, and these unique identifier codes, thus obtaining initial structured knowledge data. Then, these initial knowledge structured data are transformed into a resource description framework format, such as represented by triples (concrete column, with dimensions, 800mm), etc.; or transformed into a web ontology language format to accurately describe the concept, attributes, and relationship of the concrete column with other components or specification clauses, thereby obtaining knowledge structured data that matches the data format of the knowledge graph.

[0121] In this embodiment, a unique identifier is added to each data node of the building component association information, and a mapping relationship is established. This makes the connections between data clearer and more orderly, facilitating the management and querying of large amounts of complex data, and improving the efficiency and accuracy of data processing. The initial knowledge-structured data is transformed into a resource description framework or web ontology language format, enhancing the data's universality and semantic expressiveness, enabling better matching with knowledge graphs. These operations allow the building component association information to be presented in a way that is easily understood and processed by a knowledge graph, laying a solid data foundation for subsequent accurate and efficient quality evaluation of the building information model based on the knowledge graph, thereby improving the reliability and effectiveness of BIM quality evaluation results.

[0122] In some implementations, extracting at least one specification entity and the association between the specification entities from the engineering construction specification information to construct a target knowledge graph includes:

[0123] Obtain specification documents from the engineering construction specification information, wherein the specification documents include structured data, semi-structured data, and unstructured data;

[0124] Knowledge extraction and annotation are performed on the standard documents to identify standard terms, standard definitions and standard relationships, and the standard terms, standard definitions and standard relationships are transformed into structured standard text;

[0125] Extract component types, component attributes, and relationships between components from the specification text, and associate the component types, component attributes, and relationships between components with the corresponding definitions and attributes to obtain specification entities and the association relationships between the specification entities;

[0126] The target knowledge graph is obtained by using the standardized entities as nodes and the relationships between the standardized entities as edges.

[0127] Standard documents refer to documents containing engineering construction standards information. These documents come from a wide range of sources and have diverse data formats, including: structured data, such as standard parameters explicitly presented in tabular form; semi-structured data, such as explanatory text with a certain format but not fully structured; and unstructured data, such as standard requirements described in plain text. Standard documents are the original source of information for extracting standard entities and relationships, and thus building the target knowledge graph.

[0128] The standard text is a structured document that transforms standard terminology, definitions, and relationships into standard content after knowledge extraction and annotation of the standard document. It organizes the originally complex and diverse data into a more orderly and easier-to-process structure, highlighting the key information in the standard and the relationships between them. It makes it easier to extract component types, component attributes, and other content from the standard text, laying the foundation for building the target knowledge graph.

[0129] For example, in a bridge construction project, the engineering construction specifications information comes from relevant national and industry standards and regulations, which constitute the specification documents. These may include structured data tables on bridge structural design, specifying the load-bearing capacity parameters for different types of bridges; semi-structured textual descriptions of the general process of a certain stage in bridge construction; and unstructured plain text explaining the general principles of bridge seismic design. Knowledge extraction and annotation are performed on these specification documents to identify specification terms such as bridge span seismic resistance grade, specification definitions such as bridge span (referring to the horizontal distance between adjacent piers), and specification relationships such as the relationship between bridge span and load-bearing capacity, and these are transformed into structured specification text. Next, component attributes such as box girder types, concrete strength grades of box girders, and relationships between box girders and piers are extracted from this specification text. Box girders are treated as specification entities, and the connection relationships between box girders and piers are treated as associations between specification entities. Finally, specification entities such as box girders are used as nodes in the target knowledge graph, and the association relationships between specification entities such as the connection relationships between box girders and piers are used as edges, thus establishing the target knowledge graph for this bridge construction project.

[0130] In this embodiment, by acquiring standard documents containing various data formats from engineering construction standard information, the original information required to build the target knowledge graph is comprehensively collected. Knowledge extraction and annotation of the standard documents are performed to transform them into standard text, effectively streamlining the complex standard information and making it more structured, facilitating subsequent in-depth mining of key content. Standard entities and their relationships are extracted from the standard text, and the target knowledge graph is constructed based on this, presenting the engineering construction standards in an intuitive, orderly, and easily computer-processable graphical manner. This provides accurate and clear standard criteria for quality evaluation of Building Information Models (BIM) based on knowledge graphs, enabling more precise judgment of whether the model meets the standard requirements, significantly improving the accuracy and reliability of BIM quality evaluation results, and effectively ensuring the compliant construction of building engineering projects.

[0131] In some implementations, after constructing the target knowledge graph, the following steps are also included:

[0132] Based on the normative attributes, determine the mandatory level corresponding to the normative entities in the target knowledge graph;

[0133] Based on the engineering phase, determine the degree of engineering criticality corresponding to the standardized entities in the target knowledge graph;

[0134] Based on the mandatory level and the criticality of the project, the execution priority of each of the specification entities is determined;

[0135] Based on the execution priority, an index table corresponding to the target knowledge graph is established so that the standard entity can be located and invoked through the index table when evaluating the quality of the building information model.

[0136] Among them, the normative attribute refers to the inherent characteristics of the engineering construction standard, such as whether the standard is mandatory or recommended. Different normative attributes determine the enforcement strength and requirements of the standard in actual engineering projects, and the mandatory level corresponding to the standard entity is determined based on the normative attribute.

[0137] The mandatory level refers to the degree of enforcement of a standard entity based on its attributes. It is generally divided into different levels, such as strong, medium, and weak. Standard entities with a high mandatory level must be strictly followed in engineering construction; failure to comply may lead to serious consequences. Clarifying the mandatory level of a standard entity through its attributes provides a basis for determining subsequent enforcement priorities.

[0138] Among them, the engineering phases refer to the different processes that a construction project goes through from start to finish, commonly including the design phase, construction preparation phase, construction implementation phase, and final acceptance phase. The requirements and emphases of the specifications differ at each phase, and the criticality of the specification entity at each phase is determined based on the engineering phase.

[0139] Among them, the engineering criticality refers to the importance of a specification entity in a specific engineering phase. Some specification entities may play a crucial role in the smooth progress and quality assurance of the project at a certain engineering phase, while their importance may be relatively low at other phases. Assessing the engineering criticality of specification entities in conjunction with the engineering phase is one of the important factors in determining the execution priority.

[0140] The execution priority of a specification entity is determined by considering both its mandatory level and the criticality of the project, thus establishing the order in which they are executed during the quality evaluation process. Specification entities with higher execution priority will be considered and applied first in the quality evaluation of the Building Information Model (BIM). By determining the execution priority, the order in which specification entities are used during the quality evaluation process can be rationally arranged.

[0141] The index table is a data structure built according to the execution priority of the specification entities, similar to a directory. It can quickly locate and call the specification entities in the target knowledge graph. The index table facilitates the rapid acquisition and application of the corresponding specification entities during the quality evaluation of building information models, thereby improving the evaluation efficiency.

[0142] For example, in a residential construction project, a target knowledge graph has been established. For the entity representing the fire separation distance standard for buildings, its regulatory attribute is mandatory, so its mandatory level is determined to be high. In terms of engineering phases, fire separation distances must be strictly considered from the design stage, and are equally important during the construction implementation stage; its engineering criticality is high at each stage. Considering both the mandatory level and engineering criticality, the execution priority of this regulatory entity is determined to be high. An index table is created for the entire target knowledge graph, in which the fire separation distance standard for buildings is ranked first based on its high execution priority. When evaluating the quality of the residential building information model, the index table allows for quick location and retrieval of the building's fire separation distance standard to check whether the fire separation distances in the model meet the requirements.

[0143] In this embodiment, the mandatory level is determined based on the specification attributes, the criticality of the project is determined based on the project stage, and then the execution priority of the specification entities is determined. This comprehensive approach can fully and reasonably assess the importance and execution order of specification entities in the construction project. Furthermore, establishing an index table based on execution priority provides an effective way to quickly locate and call specification entities during the quality evaluation of the Building Information Model (BIM). On the one hand, it ensures the priority application of important specification entities during the quality evaluation process, helping to more accurately identify potential key issues in the model and improve the accuracy of the evaluation results. On the other hand, quickly calling specification entities through the index table greatly improves the efficiency of the quality evaluation, saves time and resources, and makes the entire knowledge graph-based BIM model quality evaluation process more scientific and efficient.

[0144] In some implementations, evaluating the quality of the building information model based on the knowledge structured data and the target knowledge graph includes:

[0145] Based on the structured knowledge data and the target knowledge graph, check for missing components and omissions of related data in the building information model;

[0146] Based on the structured knowledge data and the target knowledge graph, check the compliance of the building information model with the relevant standards.

[0147] Based on the structured knowledge data and the target knowledge graph, check the missing component attributes and the accuracy of parameters in the building information model;

[0148] Based on the missing components, the omissions of the associated data, the compliance with the specifications, the missing component attributes, and the accuracy of the parameters, the quality evaluation result of the building information model is obtained.

[0149] For example, consider a building information model (BIM) for a hospital building. First, the structured knowledge data contains various information extracted and processed from the model's transformed data, such as the component attributes of wards and their spatial relationships with other areas. The target knowledge graph constructs various standards and regulations for hospital buildings, such as minimum ward area requirements and fire escape route specifications. During the evaluation process, the structured knowledge data and target knowledge graph are used to check for missing components, such as whether any ward bathroom components in the design plan are missing; and to check for missing related data, such as whether related data like the opening method of ward windows is missing. Next, compliance with regulations is checked, such as whether the ward area meets the minimum area requirements specified in the target knowledge graph, and whether the staircase width meets fire evacuation regulations. Simultaneously, missing component attributes are checked, such as whether the material attributes of ward doors are missing, and the accuracy of parameters, such as whether the cooling parameters of the ward air conditioning system are accurate. Finally, by comprehensively considering the missing components, missing related data, compliance with regulations, missing component attributes, and parameter accuracy, a quality evaluation result for the hospital's BIM model is obtained, such as determining whether the model is qualified and which parts need improvement.

[0150] In this embodiment, by relying on structured knowledge data and target knowledge graphs, a comprehensive inspection of the Building Information Model (BIM) is conducted from multiple dimensions, including missing components, missing related data, compliance with standards, missing component attributes, and parameter accuracy. This allows for the systematic and detailed identification of various quality issues within the model. This comprehensive quality evaluation method avoids the limitations of single-dimensional evaluation, resulting in more accurate and objective evaluation results. It provides a reliable quality reference for construction projects, helps to promptly identify and correct deficiencies in the model, ensures the smooth progress of construction projects in accordance with standards, and ultimately improves the overall quality and reliability of the construction project.

[0151] In some embodiments, after evaluating the quality of the building information model, the method further includes:

[0152] Based on the spatial topology and data association network of the target knowledge graph, information on non-compliant components is determined, wherein the information on non-compliant components includes the three-dimensional coordinates, professional zone, and associated component group of the non-compliant component in the building information model;

[0153] By tracing the relationships between data nodes in the structured knowledge data, the root cause of data errors can be located;

[0154] A model detection report is generated based on the information of the non-compliant components and the root cause of the data error.

[0155] Among them, spatial topology describes the position, connection and mutual relationship of each component in the building information model in space. It does not consider the specific size and shape of the components, but only focuses on the logical connection and spatial layout relationship between them. By using the spatial topology in the target knowledge graph, the position information of non-compliant components in the whole model space can be determined.

[0156] Among them, the data association network refers to the network structure formed between the data nodes in the knowledge structured data. Each data node has some kind of relationship with other related nodes. Through this network, the source and flow of data can be traced, and the data association network can be used to trace and locate the data association clues that lead to the violation of the component.

[0157] Among them, the root cause of data errors refers to the fundamental reason why components in the building information model do not meet the specifications. This may involve deviations in the data extraction process, anomalies during model format conversion, and parameter input errors in the design phase. The root cause of data errors can be found by tracing the relationship between data nodes in the knowledge structured data in order to accurately solve the problem.

[0158] The process of generating a model inspection report based on the information of the non-compliant components and the root causes of the data errors involves organizing and summarizing the specific information of the identified non-compliant components in the model and the root causes of the data errors to form a detailed report. This model inspection report provides clear and specific guidance for subsequent targeted modifications to the building information model.

[0159] For example, after evaluating the quality of the Building Information Model (BIM) of a school building, it was found that the evacuation door in a stairwell on a certain floor did not meet the code requirements. The spatial topology in the target knowledge graph can clearly define the three-dimensional coordinates of this evacuation door in the building model. For instance, it is located on the second floor, with an X-coordinate of 10-15 meters, a Y-coordinate of 20-25 meters, and a Z-coordinate of 3-4 meters. It belongs to the building's fire compartment, and the associated component groups include stairs, walls, etc. By tracing the data association network of the knowledge-structured data, it was found that the root cause of the data error was an incorrect evacuation door width parameter input during the design phase. Based on this information on non-compliant components and the root cause of the data error, a model inspection report is generated, which records in detail the non-compliance of the evacuation door and the reason for the error.

[0160] In this embodiment, by utilizing the spatial topology and data association network of the target knowledge graph to determine the information of non-compliant components and locate the root cause of data errors, accurate localization and detailed cause analysis of model quality issues can be provided. The model inspection report generated based on this provides crucial evidence for the optimization and improvement of the Building Information Model (BIM). Clear information on non-compliant components allows relevant personnel to quickly identify problems in the model, improving error correction efficiency; clearly defined root causes of data errors help to fundamentally solve problems and prevent similar errors from recurring. This ultimately improves the overall quality of the BIM, ensures that building projects meet regulatory requirements, reduces changes and risks during later construction processes, and enhances the overall quality and efficiency of building engineering.

[0161] In some implementations, after generating the model detection report, the method further includes:

[0162] Based on the correct cases, industry best practice data, and associated construction process requirements in the target knowledge graph, determine the modification scheme corresponding to each non-compliant component in the building information model;

[0163] By combining the priority of the norms in the target knowledge graph and the influence range of components that do not conform to the norms, the modification schemes are sorted to obtain modification priorities, so that the modification schemes can be executed based on the modification priorities.

[0164] Among them, correct cases refer to examples in the target knowledge graph that conform to engineering construction specifications. These cases demonstrate the correct practices and standards for components in design, construction, etc. They provide a reference for rectification of components that do not conform to the specifications and help determine the modification plan.

[0165] Among these, industry best practice data, accumulated over a long period of practice in the construction industry, is widely recognized as the most effective practices, processes, parameters, and other data. This data reflects advanced technologies and experience within the industry and is used to assist in developing optimization measures for non-compliant components, making modification plans more scientific and reasonable.

[0166] The modification plan addresses non-compliant components in the Building Information Model (BIM) and outlines specific improvement measures based on correct examples from the target knowledge graph, industry best practice data, and related construction process requirements. The plan clarifies how to adjust non-compliant components to meet relevant regulatory requirements.

[0167] For example, in the building information model of a commercial complex, an inspection revealed that the width of a fire escape route on a certain floor did not meet the standards. Correct examples in the target knowledge graph indicate that fire escape routes in similar commercial complexes should meet certain width standards and require appropriate evacuation signage. Industry best practice data suggests that while ensuring the width of the escape route, the layout within the route should also be optimized to avoid obstacles affecting evacuation. Based on these findings, the proposed modification for this non-compliant component is: widening the fire escape route to the required width, replanning the placement of equipment within the route, and installing evacuation signage on the route walls at standard intervals. Furthermore, considering the high priority of fire safety regulations in the target knowledge graph and the significant impact of this non-compliant fire escape route on evacuation, this modification plan is given a higher priority for implementation.

[0168] In this embodiment, modification schemes are determined based on correct cases in the target knowledge graph, industry best practice data, and associated construction process requirements. This provides scientific, reasonable, and targeted improvement measures for non-compliant components, making the modified components more compliant with specifications and ensuring the safety and compliance of the construction project. Prioritizing modification schemes by combining specification priority and the scope of component impact helps to rationally arrange the order of modification work, prioritizing issues with significant impact on the project and strict specification requirements, improving the efficiency and effectiveness of modification work, avoiding blind rectification, and thus more effectively improving the quality of the building information model and ensuring the smooth progress of the construction project.

[0169] To better implement the above methods, this application also provides a model quality evaluation device, which can be integrated into an electronic device, such as a terminal or server. The terminal can be a mobile phone, tablet computer, smart Bluetooth device, laptop computer, or personal computer; the server can be a single server or a server cluster composed of multiple servers.

[0170] For example, in this embodiment, the method of this application embodiment will be described in detail by taking the model quality evaluation device as a specific integrated terminal device.

[0171] For example, refer to Figure 3 , Figure 3 This is a schematic diagram of the model quality evaluation device provided in the embodiments of this application. Figure 3 As shown, the model quality evaluation device may include an information acquisition unit 301, a knowledge graph construction unit 302, a building component association information acquisition unit 303, an information conversion unit 304, and a quality evaluation unit 305, as follows:

[0172] The information acquisition unit 301 is used to acquire the source file of the building information model and the engineering construction specification information corresponding to the building information model;

[0173] The knowledge graph construction unit 302 is used to extract at least one specification entity and the association relationship between the specification entities from the engineering construction specification information in order to construct a target knowledge graph.

[0174] Building component association information acquisition unit 303 is used to extract information associated with at least one building component in the building information model from the source file to obtain building component association information.

[0175] Information conversion unit 304 is used to convert the building component association information into knowledge structured data that matches the data format of the target knowledge graph;

[0176] The quality evaluation unit 305 is used to evaluate the quality of the building information model based on the knowledge structured data and the target knowledge graph, and obtain the evaluation result.

[0177] In practice, each of the above units can be implemented as an independent entity or can be arbitrarily combined to be implemented as the same or several entities. For the specific implementation of each of the above units, please refer to the previous method embodiments, which will not be repeated here.

[0178] In the embodiments of this application, the term "module" or "unit" refers to a computer program or part of a computer program that has a predetermined function and works with other related parts to achieve a predetermined goal, and can be implemented wholly or partially using software, hardware (such as processing circuitry or memory), or a combination thereof. Similarly, a processor (or multiple processors or memory) can be used to implement one or more modules or units. Furthermore, each module or unit can be part of an overall module or unit that includes the functionality of that module or unit.

[0179] As can be seen from the above, the model quality evaluation device in this embodiment provides basic data for subsequent evaluation work by acquiring the source files of the building information model and engineering construction specification information; it extracts the building component association information from the source files and transforms it into knowledge structured data that matches the data format of the knowledge graph; and it extracts specification entities and the association relationships between specification entities from the specification information to establish a target knowledge graph, so that both building information and specification information are presented in a structured and easily associative form; finally, it evaluates the quality of the building information model based on these two factors, which can more accurately compare the model with the specification requirements, comprehensively and accurately discover model quality problems, thereby improving the efficiency and accuracy of BIM quality evaluation results.

[0180] This application also provides an electronic device, which can be a terminal, a server, or other similar device. The terminal can be a mobile phone, tablet computer, smart Bluetooth device, laptop computer, personal computer, etc.; the server can be a single server or a server cluster composed of multiple servers, etc.

[0181] In some embodiments, the model quality evaluation device can also be integrated into multiple electronic devices, such as multiple servers, with multiple servers implementing the model quality evaluation method of this application.

[0182] In this embodiment, the electronic device will be described in detail as a terminal, for example, such as... Figure 4 As shown, it illustrates a structural schematic diagram of the electronic device involved in the embodiments of this application, specifically:

[0183] The electronic device may include components such as a processor 401 with one or more processing cores, a memory 402 with one or more computer-readable storage media, a power supply 403, an input module 404, and a communication module 405. Those skilled in the art will understand that... Figure 4 The electronic device structure shown does not constitute a limitation on the electronic device and may include more or fewer components than shown, or combine certain components, or have different component arrangements. Wherein:

[0184] The processor 401 is the control center of the electronic device. It connects various parts of the electronic device via various interfaces and lines. By running or executing software programs and / or modules stored in the memory 402, and by calling data stored in the memory 402, it performs various functions and processes data, thereby performing overall detection of the electronic device. In some embodiments, the processor 401 may include one or more processing cores; in some embodiments, the processor 401 may integrate an application processor and a modem processor, wherein the application processor mainly handles the operating system, user interface, and applications, and the modem processor mainly handles wireless communication. It is understood that the modem processor may also not be integrated into the processor 401.

[0185] The memory 402 can be used to store software programs and modules. The processor 401 executes various functional applications and model quality evaluations by running the software programs and modules stored in the memory 402. The memory 402 may mainly include a program storage area and a data storage area. The program storage area may store the operating system, application programs required for at least one function (such as sound playback function, image playback function, etc.), etc.; the data storage area may store data created according to the use of the electronic device, etc. In addition, the memory 402 may include high-speed random access memory, and may also include non-volatile memory, such as at least one disk storage device, flash memory device, or other volatile solid-state storage device. Accordingly, the memory 402 may also include a memory controller to provide the processor 401 with access to the memory 402.

[0186] The electronic device also includes a power supply 403 that supplies power to the various components. In some embodiments, the power supply 403 can be logically connected to the processor 401 through a power management system, thereby enabling functions such as charging, discharging, and power consumption management through the power management system. The power supply 403 may also include one or more DC or AC power supplies, recharging systems, power fault detection circuits, power converters or inverters, power status indicators, and other arbitrary components.

[0187] The electronic device may also include an input module 404, which can be used to receive input digital or character information and generate keyboard, mouse, joystick, optical or trackball signal inputs related to user settings and function control.

[0188] The electronic device may also include a communication module 405. In some embodiments, the communication module 405 may include a wireless module, through which the electronic device can perform short-range wireless transmission, thereby providing users with wireless broadband internet access. For example, the communication module 405 can be used to help users send and receive emails, browse web pages, and access streaming media.

[0189] Although not shown, the electronic device may also include a display unit, etc., which will not be described in detail here. Specifically, in this embodiment, the processor 401 in the electronic device loads the executable files corresponding to the processes of one or more applications into the memory 402 according to the following instructions, and the processor 401 runs the applications stored in the memory 402 to realize various functions, as follows:

[0190] Obtain the source files of the building information model and the engineering construction specifications information corresponding to the building information model;

[0191] Extract at least one specification entity and the association between the specification entities from the engineering construction specification information to construct a target knowledge graph;

[0192] Extract information associated with at least one building component in the building information model from the source file to obtain building component association information;

[0193] The information associated with the building components is converted into structured knowledge data that matches the data format of the target knowledge graph.

[0194] The quality of the building information model is evaluated based on the structured knowledge data and the target knowledge graph, and the evaluation results are obtained.

[0195] For details on the implementation of each of the above operations, please refer to the previous examples, which will not be repeated here.

[0196] As can be seen from the above, the embodiments of this application can improve the efficiency and accuracy of BIM quality evaluation results.

[0197] Those skilled in the art will understand that all or part of the steps in the various methods of the above embodiments can be performed by instructions, or by instructions controlling related hardware. These instructions can be stored in a computer-readable storage medium and loaded and executed by a processor.

[0198] Therefore, embodiments of this application provide a computer-readable storage medium storing a plurality of instructions that can be loaded by a processor to execute steps in any of the model quality evaluation methods provided in embodiments of this application. For example, the instructions can execute the following steps:

[0199] Obtain the source files of the building information model and the engineering construction specifications information corresponding to the building information model;

[0200] Extract at least one specification entity and the association between the specification entities from the engineering construction specification information to construct a target knowledge graph;

[0201] Extract information associated with at least one building component in the building information model from the source file to obtain building component association information;

[0202] The information associated with the building components is converted into structured knowledge data that matches the data format of the target knowledge graph.

[0203] The quality of the building information model is evaluated based on the structured knowledge data and the target knowledge graph, and the evaluation results are obtained.

[0204] The storage medium may include: read-only memory (ROM), random access memory (RAM), disk or optical disk, etc.

[0205] According to one aspect of this application, a computer program product is provided, comprising a computer program / instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer program / instructions from the computer-readable storage medium and executes the computer program / instructions, causing the computer device to perform the methods provided in the above embodiments.

[0206] Since the program / instructions stored in the storage medium can execute the steps in any of the model quality evaluation methods provided in the embodiments of this application, the beneficial effects that any of the model quality evaluation methods provided in the embodiments of this application can achieve can be realized. For details, please refer to the previous embodiments, which will not be repeated here.

[0207] The foregoing has provided a detailed description of a model quality evaluation method, apparatus, electronic device, product, and storage medium provided in the embodiments of this application. Specific examples have been used to illustrate the principles and implementation methods of this application. The descriptions of the above embodiments are only for the purpose of helping to understand the method and core ideas of this application. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of this application. Therefore, the content of this specification should not be construed as a limitation of this application.

Claims

1. A method for evaluating model quality, characterized in that, The methods include: Obtain the source files of the building information model and the engineering construction specifications information corresponding to the building information model; Extract at least one specification entity and the association between the specification entities from the engineering construction specification information to construct a target knowledge graph; Extract information associated with at least one building component in the building information model from the source file to obtain building component association information; The information associated with the building components is converted into structured knowledge data that matches the data format of the target knowledge graph. The quality of the building information model is evaluated based on the structured knowledge data and the target knowledge graph, and the evaluation results are obtained. Before extracting information associated with at least one building component in the building information model from the source file, the method further includes: For files of different source formats in the source files, different data cleaning processes are performed to remove invalid and redundant data and repair broken data chains, resulting in first pre-processed data, which includes RVT data, DWG data, and 3DM data. The parametric attributes of the RVT data are preserved, the mapping relationship between the two-dimensional annotations and the three-dimensional model in the DWG data is strengthened, and the conversion algorithm of the surface data in the 3DM data is optimized to obtain the second preprocessed data. The second preprocessed data is converted into a preset data format using a format conversion tool to obtain the third preprocessed data. After comparing the source file with the third preprocessed data and confirming that the number of components, key attributes, and spatial topology relationships in the third preprocessed data have not been lost or tampered with, the third preprocessed data is used as the converted data, wherein the converted data is used to obtain the association information of the building components.

2. The model quality evaluation method as described in claim 1, characterized in that, The step of extracting information associated with at least one building component in the building information model from the source file to obtain building component association information includes: Extract the component information of the building information model from the source file, wherein the component information includes component attributes, component spatial relationships, component material information, and component connection relationships; Extract multi-dimensional association information corresponding to the component information from the source file. The multi-dimensional association information includes the industry standard clause serial number corresponding to the component, the design stage version number, the construction process requirements, the material supplier qualification information, and the quality inspection records of similar components in previous projects. The component information is integrated with the multi-dimensional association information to obtain the building component association information.

3. The model quality evaluation method as described in claim 2, characterized in that, The step of converting the building component association information into knowledge structured data that matches the data format of the target knowledge graph includes: A unique identifier code is added to each data node in the building component association information, and a mapping relationship is established between the component information, the multi-dimensional association information and the unique identifier code to obtain initial knowledge structured data. The initial knowledge structured data is transformed into a resource description framework or web ontology language format to obtain knowledge structured data that matches the data format of the target knowledge graph.

4. The model quality evaluation method as described in claim 1, characterized in that, The step of extracting at least one specification entity and the association relationships between the specification entities from the engineering construction specification information to construct a target knowledge graph includes: Obtain specification documents from the engineering construction specification information, wherein the specification documents include structured data, semi-structured data, and unstructured data; Knowledge extraction and annotation are performed on the standard documents to identify standard terms, standard definitions and standard relationships, and the standard terms, standard definitions and standard relationships are transformed into structured standard text; Extract component types, component attributes, and relationships between components from the specification text, and associate the component types, component attributes, and relationships between components with the corresponding definitions and attributes to obtain specification entities and the association relationships between the specification entities; The target knowledge graph is obtained by using the standardized entities as nodes and the relationships between the standardized entities as edges.

5. The model quality evaluation method as described in claim 1, characterized in that, After constructing the target knowledge graph, the following is also included: Based on the normative attributes, determine the mandatory level corresponding to the normative entities in the target knowledge graph; Based on the engineering phase, determine the degree of engineering criticality corresponding to the standardized entities in the target knowledge graph; Based on the mandatory level and the criticality of the project, the execution priority of each of the specification entities is determined; Based on the execution priority, an index table corresponding to the target knowledge graph is established so that the standard entity can be located and invoked through the index table when evaluating the quality of the building information model.

6. The model quality evaluation method as described in claim 1, characterized in that, The evaluation of the quality of the building information model based on the structured knowledge data and the target knowledge graph includes: Based on the structured knowledge data and the target knowledge graph, check for missing components and omissions of related data in the building information model; Based on the structured knowledge data and the target knowledge graph, check the compliance of the building information model with the relevant standards. Based on the structured knowledge data and the target knowledge graph, check the missing component attributes and the accuracy of parameters in the building information model; Based on the missing components, the omissions of the associated data, the compliance with the specifications, the missing component attributes, and the accuracy of the parameters, the quality evaluation result of the building information model is obtained.

7. The model quality evaluation method as described in claim 1, characterized in that, After evaluating the quality of the building information model, the process also includes: Based on the spatial topology and data association network of the target knowledge graph, information on non-compliant components is determined, wherein the information on non-compliant components includes the three-dimensional coordinates, professional zone, and associated component group of the non-compliant component in the building information model; By tracing the relationships between data nodes in the structured knowledge data, the root cause of data errors can be located; A model detection report is generated based on the information of the non-compliant components and the root cause of the data error.

8. The model quality evaluation method as described in claim 7, characterized in that, Following the generated model detection report, the following is also included: Based on the correct cases, industry best practice data, and associated construction process requirements in the target knowledge graph, determine the modification scheme corresponding to each non-compliant component in the building information model; By combining the priority of the norms in the target knowledge graph and the influence range of components that do not conform to the norms, the modification schemes are sorted to obtain modification priorities, so that the modification schemes can be executed based on the modification priorities.

9. A model quality evaluation device, characterized in that, The device includes: The information acquisition unit is used to acquire the source file of the building information model and the engineering construction specification information corresponding to the building information model; A knowledge graph construction unit is used to extract at least one specification entity and the association between the specification entities from the engineering construction specification information in order to construct a target knowledge graph. The building component association information acquisition unit is used to extract information associated with at least one building component in the building information model from the source file to obtain building component association information. The information conversion unit is used to convert the building component association information into knowledge structured data that matches the data format of the target knowledge graph; The quality evaluation unit is used to evaluate the quality of the building information model based on the knowledge structured data and the target knowledge graph, and obtain the evaluation result. Before extracting information associated with at least one building component in the building information model from the source file, the method further includes: For files of different source formats in the source files, different data cleaning processes are performed to remove invalid and redundant data and repair broken data chains, resulting in first pre-processed data, which includes RVT data, DWG data, and 3DM data. The parametric attributes of the RVT data are preserved, the mapping relationship between the two-dimensional annotations and the three-dimensional model in the DWG data is strengthened, and the conversion algorithm of the surface data in the 3DM data is optimized to obtain the second preprocessed data. The second preprocessed data is converted into a preset data format using a format conversion tool to obtain the third preprocessed data. After comparing the source file with the third preprocessed data and confirming that the number of components, key attributes, and spatial topology relationships in the third preprocessed data have not been lost or tampered with, the third preprocessed data is used as the converted data, wherein the converted data is used to obtain the association information of the building components.

10. An electronic device, characterized in that, It includes a processor and a memory, the memory storing multiple instructions; the processor loads instructions from the memory to perform the steps in the model quality evaluation method as described in any one of claims 1 to 8.

11. A computer program product, comprising a computer program / instructions, characterized in that, When the computer program / instruction is executed by the processor, it implements the steps in the model quality evaluation method according to any one of claims 1 to 8.

12. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a plurality of instructions adapted for loading by a processor to perform the steps of the model quality evaluation method according to any one of claims 1 to 8.

Images