BIM model review method and device based on knowledge graph and image matching

Abstract

The present application discloses a BIM model review method and device based on knowledge graph and image matching, which relates to building information model engineering. The method includes: constructing a standard specification knowledge graph based on review standard specification documents; parsing the engineering documents based on an off-platform development strategy to obtain a target BIM model, and extracting the attribute information and geometric information of the target BIM model; comparing and reviewing the attribute information of the target BIM model based on the standard specification knowledge graph to obtain an attribute review result; projecting the geometric information onto a two-dimensional plane to obtain two-dimensional plane drawing information, and comparing and reviewing the geometric information based on the feature information in the two-dimensional plane drawing information to obtain a geometric review result; generating a review report file for the target BIM model based on the attribute review result and the geometric review result. Through the above method, model parsing, model review and review report output can be automatically realized, thereby improving review efficiency.

Description

Technical Field

[0001] The present application relates to building information modeling (BIM) engineering, and in particular to a BIM model review method and device based on knowledge graph and image matching. Background Art

[0002] At present, the main method used is commercial software + manual review to check and review the attributes and geometric information of BIM (Building Information Modeling) models. Through the secondary development interface provided by commercial software, the attributes and geometric information in the BIM model are parsed and checked with the information in the standard specification documents, and the review results are organized and output into the review report.

[0003] For large-scale BIM model data, manual review will consume a long time and human resources. For BIM model data in different formats, it is necessary to rely on the secondary development interface provided by different commercial software to load and parse, which has strong technical dependence, limited interface extensibility, and high development costs. In the model review process, the method of polling and traversing the specification information is adopted to compare and review the model attribute information and geometric information. Not only is the review efficiency low, but it is also easy to have the problem of inconsistent matching between the model geometric features and the standard drawings, resulting in errors.

[0004] The above content is only used to assist in understanding the technical solution of the present invention and does not constitute an admission that the above content is prior art. Summary of the Invention

[0005] The main purpose of this application is to provide a BIM model review method and device based on knowledge graph and image matching, aiming to solve the technical problem of low efficiency of BIM model review methods in the existing technology.

[0006] To achieve the above objectives, this application provides a BIM model review method based on knowledge graph and image matching, the method comprising:

[0007] Build a knowledge graph of standards and specifications based on the review of standard and specification documents;

[0008] Based on the off-platform development strategy, the BIM project file is parsed to obtain the target BIM model, and the attribute information and geometric information of the target BIM model are extracted;

[0009] Based on the standard specification knowledge graph, the attribute information of the target BIM model is compared and reviewed to obtain an attribute review result;

[0010] Projecting the geometric information of the target BIM model onto a two-dimensional plane to obtain two-dimensional plane drawing information;

[0011] Based on the feature information in the two-dimensional plane drawing information, the geometric information is compared and reviewed to obtain a geometric review result;

[0012] Based on the attribute review result and the geometry review result, a review report file of the target BIM model is generated.

[0013] In one embodiment, the step of constructing a standard specification knowledge graph based on the review standard specification document includes:

[0014] Analyze and review standard and specification documents to determine standard and specification clause information;

[0015] Extracting the standard specification information into structured data, wherein the structured data includes at least entity data, relationship data, and attribute data;

[0016] Perform knowledge fusion on the structured data to construct a standard knowledge graph.

[0017] In one embodiment, the step of parsing the BIM project file based on the off-platform development strategy to obtain the target BIM model includes:

[0018] Acquire a BIM project file, where the BIM project file has multiple formats;

[0019] Based on the off-platform development strategy, BIM project files in multiple formats are parsed to obtain multiple BIM models of the target project, and the multiple BIM models are used as the target BIM model.

[0020] In one embodiment, the step of comparing and reviewing the attribute information of the target BIM model based on the standard specification knowledge graph to obtain the attribute review result includes:

[0021] Based on the attribute information of the target BIM model, corresponding specification attribute information is retrieved in the standard specification knowledge graph, where the attribute information includes at least category, layer information, and material information;

[0022] Based on the specification attribute information, the attribute information of the target BIM model is compared and reviewed to generate an attribute review result.

[0023] In one embodiment, the step of comparing and reviewing the attribute information of the target BIM model based on the specification attribute information to generate an attribute review result includes:

[0024] When the attribute information of the target BIM model meets the specification attribute information, determining that the attribute review result is qualified;

[0025] When the attribute information of the target BIM model does not conform to the standard attribute information, the attribute review result is determined to be unqualified.

[0026] In one embodiment, the step of projecting the geometric information of the target BIM model onto a two-dimensional plane to obtain two-dimensional plane drawing information includes:

[0027] Based on the geometric information of the target BIM model, extracting the kernel basic data structure in the geometric information;

[0028] Performing three-dimensional hiding on the kernel basic data structure to determine occlusion relationships in the kernel basic data structure, the occlusion relationships at least including occlusion relationships between edges, occlusion relationships between edges and faces, and occlusion relationships between faces;

[0029] Based on the occlusion relationship, the kernel basic data structure is projected onto a two-dimensional plane to obtain the two-dimensional plane drawing information.

[0030] In one embodiment, the step of comparing and reviewing the geometric information based on the feature information in the two-dimensional planar drawing information to obtain a geometric review result includes:

[0031] Extracting features from the two-dimensional drawing information based on a pre-trained feature model to obtain feature information;

[0032] Extract features from standard drawing files based on pre-trained feature models to obtain standard feature information;

[0033] Matching the standard feature information with the feature information based on a pre-trained matching model to determine a matching score;

[0034] Based on the matching score, the geometric review result is determined.

[0035] In one embodiment, the step of determining the geometric review result based on the matching score includes:

[0036] When the matching score is greater than or equal to a preset score, determining that the geometric review result is qualified;

[0037] When the matching score is less than the preset score, the geometric review result is determined to be unqualified.

[0038] In one embodiment, the step of generating a review report file of the target BIM model based on the attribute review result and the geometry review result includes:

[0039] Recording the attribute review result and the geometry review result, and determining whether the target BIM model is traversed;

[0040] When the traversal is completed, an audit report file corresponding to the attribute audit result and the geometric audit result is generated based on the audit report template file.

[0041] In addition, to achieve the above objectives, the present application also proposes a BIM model review device based on knowledge graph and image matching, wherein the BIM model review device based on knowledge graph and image matching comprises:

[0042] A graph construction module is used to construct a standard specification knowledge graph based on the review of standard specification documents;

[0043] A model parsing module is used to parse the BIM project file based on the off-platform development strategy to obtain the target BIM model and extract the attribute information and geometric information of the target BIM model;

[0044] A model review module is used to compare and review the attribute information of the target BIM model based on the standard specification knowledge graph to obtain an attribute review result;

[0045] The model review module is further configured to project the geometric information of the target BIM model onto a two-dimensional plane to obtain two-dimensional plane drawing information;

[0046] The model review module is further configured to compare and review the geometric information based on the feature information in the two-dimensional planar drawing information to obtain a geometric review result;

[0047] The model review module is further used to generate a review report file of the target BIM model based on the attribute review result and the geometry review result.

[0048] In addition, to achieve the above-mentioned purpose, the present application also proposes a BIM model review device based on knowledge graph and image matching, and the BIM model review device based on knowledge graph and image matching includes: a memory, a processor, and a computer program stored on the memory and executable on the processor, and the computer program is configured to implement the steps of the BIM model review method based on knowledge graph and image matching as described above.

[0049] In addition, to achieve the above-mentioned purpose, the present invention also proposes a storage medium, which is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by the processor, the steps of the BIM model review method based on knowledge graph and image matching as described above are implemented.

[0050] In addition, to achieve the above-mentioned purpose, the present application also provides a computer program product, which includes a computer program, and when the computer program is executed by a processor, it implements the steps of the BIM model review method based on knowledge graph and image matching as described above.

[0051] This application provides a BIM model review method based on knowledge graph and image matching, which constructs a standard specification knowledge graph based on the review standard specification file; parses the BIM project file based on the off-platform development strategy to obtain the target BIM model, and extracts the attribute information and geometric information of the target BIM model; compares and verifies the attribute information of the target BIM model based on the standard specification knowledge graph to obtain the attribute review result; projects the geometric information of the target BIM model onto a two-dimensional plane to obtain two-dimensional plane drawing information, and compares and verifies the geometric information based on the feature information in the two-dimensional plane drawing information to obtain the geometric review result; generates a review report file for the target BIM model based on the attribute review result and the geometric review result. This application adopts a platform-free development concept, which can automatically realize model parsing, model review and review report output, improve review efficiency, build a standard specification knowledge graph based on the review specification documents, use the standard specification knowledge graph for search, and realize efficient and accurate retrieval and review of BIM model attribute information, ensuring review efficiency and accuracy. It also adopts image feature extraction and matching algorithms, combined with the review specification drawing documents, to review the geometric features of the BIM model, accurately verify the consistency of the drawing and model, reduce errors, ensure the accuracy of the review, and solve the technical problem of low efficiency of the BIM model review method. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0053] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0054] Figure 1 This is a flowchart of the first embodiment of the BIM model review method based on knowledge graph and image matching of this application;

[0055] Figure 2 A schematic diagram of a standard specification knowledge graph for a BIM model review method based on knowledge graph and image matching provided in Example 1 of the present application;

[0056] Figure 3 A BIM parsing diagram of the BIM model review method based on knowledge graph and image matching provided in Example 1 of the present application;

[0057] Figure 4 A schematic diagram of a knowledge graph retrieval query for a BIM model review method based on knowledge graph and image matching provided in Example 1 of the present application;

[0058] Figure 5 A schematic diagram of the Brep structure of the BIM model review method based on knowledge graph and image matching provided in Example 1 of the present application;

[0059] Figure 6 A schematic diagram of two-dimensional information generation for the BIM model review method based on knowledge graph and image matching provided in Example 1 of the present application;

[0060] Figure 7 A schematic diagram of feature extraction of a BIM model review method based on knowledge graph and image matching provided in Example 1 of the present application;

[0061] Figure 8 A schematic diagram of feature matching of a BIM model review method based on knowledge graph and image matching provided in Example 1 of the present application;

[0062] Figure 9 A schematic diagram of a simplified process of the BIM model review method based on knowledge graph and image matching provided in Example 1 of the present application;

[0063] Figure 10 This is a schematic diagram of the module structure of a BIM model review device based on knowledge graph and image matching in an embodiment of the present application;

[0064] Figure 11 This is a schematic diagram of the device structure of the hardware operating environment involved in the BIM model review method based on knowledge graph and image matching in the embodiment of the present application.

[0065] The realization of the objectives, functional features and advantages of this application will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0066] It should be understood that the specific embodiments described herein are merely used to explain the technical solutions of the present application and are not intended to limit the present application.

[0067] In order to better understand the technical solution of the present application, a detailed description will be given below in conjunction with the accompanying drawings and specific implementation methods.

[0068] The main solutions of the embodiments of the present application are: based on the review of standard specification documents, a standard specification knowledge graph is constructed; based on the off-platform development strategy, the BIM project files are parsed to obtain the target BIM model, and the attribute information and geometric information of the target BIM model are extracted; based on the standard specification knowledge graph, the attribute information of the target BIM model is compared and reviewed to obtain the attribute review result; the geometric information of the target BIM model is projected onto a two-dimensional plane to obtain two-dimensional plane drawing information, and based on the feature information in the two-dimensional plane drawing information, the geometric information is compared and reviewed to obtain the geometric review result; based on the attribute review result and the geometric review result, a review report file of the target BIM model is generated.

[0069] Currently, the main method for verifying and reviewing the attributes and geometric information of BIM models is commercial software combined with manual review. Using the secondary development interface provided by commercial software, the attributes and geometric information in the BIM model are parsed and compared with the information in standard specification documents. The review results are then compiled and output into a review report. For large-scale BIM model data, manual review consumes a considerable amount of time and human resources.

[0070] This application provides a solution that adopts a platform-free development concept, which can automatically realize model parsing, model review and review report output, improve review efficiency, build a standard specification knowledge graph based on the review specification standard documents, use the standard specification knowledge graph for search, and realize efficient and accurate retrieval and review of BIM model attribute information, ensuring review efficiency and accuracy. It also adopts image feature extraction and matching algorithms, combined with the review specification drawing documents, to review the geometric features of the BIM model, accurately verify the consistency of the drawing and model, reduce errors, ensure the accuracy of the review, and solve the technical problem of low efficiency of the BIM model review method.

[0071] It should be noted that the execution subject of this embodiment can be a computing service device with data processing, network communication, and program execution functions, such as a tablet computer, personal computer, mobile phone, etc., or an electronic device capable of performing the above functions, a BIM model review device based on knowledge graph and image matching, etc., and this embodiment does not specifically limit this. The following uses the BIM model review device based on knowledge graph and image matching as an example to illustrate this embodiment and the following embodiments.

[0072] The present application embodiment provides a BIM model review method based on knowledge graph and image matching, referring to Figure 1 , Figure 1 This is a flow chart of the first embodiment of the BIM model review method based on knowledge graph and image matching in this application.

[0073] In this embodiment, the BIM model review method based on knowledge graph and image matching includes steps S10 to S60:

[0074] Step S10: constructing a standard specification knowledge graph based on the review standard specification document;

[0075] It should be noted that the review standard specification document is the specification document that needs to be referenced during the review process, and the standard specification knowledge graph is the knowledge graph formed by the content in the review standard specification document.

[0076] In a feasible implementation, step S10 may include steps S101 to S103:

[0077] Step S101: Analyze the review standard specification document to determine the standard specification clause information;

[0078] It should be noted that the standard specification article information refers to the specification content of each article in the review standard specification document.

[0079] Step S102: extracting the standard specification information into structured data, wherein the structured data at least includes entity data, relationship data, and attribute data;

[0080] It should be noted that the construction of knowledge graphs requires the use of structured data. Structured data includes at least entity data, relationship data, and attribute data, namely entities, relationships, and attributes. Entities can be the professions and categories to which BIM models belong, relationships can be (contains, points to), and attributes can be the IFD codes and layer information of BIM models.

[0081] Step S103: perform knowledge fusion on the structured data to construct a standard specification knowledge graph.

[0082] It is understandable that, based on the extracted structured data, the flattened entity nodes are fused by knowledge fusion to construct a standard knowledge graph, such as Figure 2 shown.

[0083] In the specific implementation, based on the review of standard specification documents, the specification clause information is extracted as structured data, and the standard specification knowledge graph is constructed based on the extracted structured data.

[0084] Step S20: parsing the BIM project file based on the off-platform development strategy to obtain a target BIM model, and extracting attribute information and geometric information of the target BIM model;

[0085] It should be noted that the off-platform development strategy refers to off-platform development technology, and the framework and tools used in off-platform development are not specifically limited in this embodiment. BIM project files refer to relevant project files, and the target BIM model refers to the BIM model that needs to be reviewed, which is generally all BIM models in the project files. Attribute information and geometric information are the information that needs to be compared and verified when reviewing the BIM model.

[0086] In a feasible implementation, based on the off-platform development strategy, the step of parsing the BIM project file to obtain the target BIM model may include steps S201 to S202:

[0087] Step S201: Acquire a BIM project file, where the BIM project file has multiple formats;

[0088] It should be noted that different BIM project files may have different formats, such as dgn, rvt, etc., which is not specifically limited in this embodiment.

[0089] In step S202 , based on the off-platform development strategy, BIM project files in multiple formats are parsed to obtain multiple BIM models of the target project, and the multiple BIM models are used as the target BIM model.

[0090] Understandably, the reference Figure 3 For BIM project files in different formats, the off-platform development component ODA (Open Data Alliance) is used to load and parse them, and traverse and collect all BIM models in the BIM project.

[0091] In the specific implementation, the off-platform development technology is adopted to parse the BIM project files, collect all the BIM models in the project, and then extract the attribute information and geometric information in the BIM models.

[0092] Step S30: Based on the standard specification knowledge graph, compare and review the attribute information of the target BIM model to obtain an attribute review result;

[0093] It should be noted that the attribute review result is the result obtained after reviewing the attribute information of the BIM model.

[0094] In a feasible implementation, step S30 may include steps S301 to S302:

[0095] Step S301: Based on the attribute information of the target BIM model, corresponding specification attribute information is retrieved from the standard specification knowledge graph, where the attribute information includes at least category, layer information, and material information;

[0096] It should be noted that the attribute information in this embodiment includes at least category, layer information, and material information. Specification attribute information refers to the attribute information in the specification stored in the standard specification knowledge graph.

[0097] Understandably, the reference Figure 4 ,Based on the extracted attribute information of the target BIM model, the ,knowledge graph relationship search algorithm is adopted to quickly query the ,corresponding attribute information in the specification.

[0098] Step S302: Based on the specification attribute information, the attribute information of the target BIM model is compared and reviewed to generate an attribute review result.

[0099] It is understandable that the attribute information in the target BIM model should be compared and reviewed to see whether it is consistent with the attribute information in the specification.

[0100] In a feasible implementation manner, when the attribute information of the target BIM model conforms to the specification attribute information, the attribute review result is determined to be qualified; when the attribute information of the target BIM model does not conform to the specification attribute information, the attribute review result is determined to be unqualified.

[0101] It should be noted that the target BIM model's attribute information conforming to the specification attribute information means that the target BIM model's attribute information is consistent with the specification attribute information. In this case, the attribute information review is usually considered qualified / passed. The target BIM model's attribute information not conforming to the specification attribute information means that the target BIM model's attribute information is inconsistent with the specification attribute information. In this case, the attribute information review is usually considered unqualified / failed.

[0102] In the specific implementation, the attribute information in the BIM model is traversed, and the knowledge graph relationship search algorithm is used to quickly query the standard attribute information for comparison and review.

[0103] It should be understood that the traditional review method usually requires polling and traversing all specification information to compare the model's attribute information, which has low review efficiency. This embodiment is based on reviewing specification standard documents, constructing a standard specification knowledge graph, and using the standard specification knowledge graph for search to achieve efficient and accurate retrieval and review of BIM model attribute information, thereby ensuring review efficiency and accuracy.

[0104] Step S40: Projecting the geometric information of the target BIM model onto a two-dimensional plane to obtain two-dimensional plane drawing information;

[0105] In a feasible implementation, step S40 may include steps S401 to S403:

[0106] Step S401: extracting a kernel basic data structure from the geometric information of the target BIM model based on the geometric information of the target BIM model;

[0107] It should be noted that the reference Figure 5 , the kernel basic data structure is the Brep structure in the geometric information.

[0108] Step S402, performing three-dimensional hidden removal on the kernel basic data structure to determine the occlusion relationship in the kernel basic data structure;

[0109] It should be noted that the reference Figure 6 This embodiment uses a 3D hidden ZBuffer algorithm to obtain corresponding occlusion relationships. The occlusion relationships include at least edge-to-edge occlusion relationships, edge-to-face occlusion relationships, and face-to-face occlusion relationships.

[0110] It can be understood that the three-dimensional hidden ZBuffer algorithm is used to calculate the occlusion relationship between edges, edges and faces, and faces in the Brep structure.

[0111] Step S403: projecting the kernel basic data structure onto a two-dimensional plane based on the occlusion relationship to obtain the two-dimensional plane drawing information;

[0112] It can be understood that based on the calculated occlusion relationship between the Brep structures, a perspective projection algorithm is used to project the Brep structures onto a two-dimensional plane.

[0113] In the specific implementation, based on the extracted geometric information of the target BIM model, the three-dimensional geometric information is projected onto a two-dimensional plane using three-dimensional hidden layer removal and perspective projection algorithms.

[0114] Step S50: Based on the feature information in the two-dimensional plane drawing information, the geometric information is compared and reviewed to obtain a geometric review result.

[0115] It should be noted that the geometric review result is the result obtained after reviewing the attribute information of the BIM model.

[0116] In a feasible implementation, step S50 may include steps S501 to S503:

[0117] Step S501, extracting features from the two-dimensional drawing information based on a pre-trained feature model to obtain feature information;

[0118] It should be noted that the feature model is a model used for feature extraction and has been pre-trained. The feature information refers to the features extracted from the two-dimensional planar drawing information. The feature model in this embodiment uses a MatchNet trained feature network.

[0119] Understandably, the reference Figure 7 Based on the two-dimensional plane drawing information obtained by projection, MatchNet is used to train the feature network and calculate the feature information.

[0120] Step S502: extracting features from the standard drawing file based on the pre-trained feature model to obtain standard feature information;

[0121] It should be noted that standard feature information refers to features extracted from standard drawing files. Standard drawing files and 2D planar drawing information use the same feature model for feature extraction.

[0122] It can be understood that based on the standard drawing file, MatchNet is used to train the feature network and calculate the feature information.

[0123] Step S503: Based on the pre-trained matching model, the standard feature information is matched with the feature information to determine a matching score, and based on the matching score, the geometric review result is determined.

[0124] It should be noted that the matching model is a model used for feature matching and has been pre-trained. The matching score is a numerical value output by the matching model to measure the degree of matching, i.e., the matching score value. The matching model in this embodiment uses the MatchNet training measurement network.

[0125] Understandably, the reference Figure 8 , based on the calculated feature information and the standard feature information, a feature pair is created, and the MatchNet measurement network is trained to perform pairwise matching. According to the matching score value, the matching degree between the geometric information of the target BIM model and the standard drawing file is judged.

[0126] In a feasible implementation, when the matching score is greater than or equal to a preset score, the geometric review result is determined to be qualified; when the matching score is less than the preset score, the geometric review result is determined to be unqualified.

[0127] It should be noted that the degree of matching between the geometric information and the standard drawing file can be determined by setting a threshold. The preset score is the threshold of the matching score set in this embodiment. The specific value can be set according to actual needs and is not specifically limited to this.

[0128] It can be understood that if the matching score is greater than or equal to the preset score, it means that the geometric information matches the standard drawing file to a high degree, and the geometric information review can be considered qualified / passed. If the matching score is less than the preset score, it means that the geometric information matches the standard drawing file to a low degree, and the geometric information review can be considered unqualified / failed.

[0129] In the specific implementation, based on the two-dimensional plane drawing information obtained by projection and combined with the standard drawing file, the MatchNet algorithm is used to intelligently extract feature information, perform image matching and review, and obtain the geometric review results.

[0130] It should be understood that the traditional review method usually requires polling and traversing all standard drawings to compare the geometric information of the model, which has low review efficiency. This embodiment adopts image feature extraction and matching algorithms, combined with the review of standard drawing files, to review the geometric features of the BIM model, accurately verify the consistency of the drawings and models, reduce errors, and ensure the accuracy of the review.

[0131] Step S60: generating a review report file of the target BIM model based on the attribute review result and the geometry review result.

[0132] In a feasible implementation, step S60 may include steps S601 to S602:

[0133] Step S601, recording the attribute review result and the geometry review result, and determining whether the target BIM model is traversed;

[0134] Step S602: When the traversal is completed, an audit report file corresponding to the attribute audit result and the geometry audit result is generated based on the audit report template file.

[0135] It should be noted that the review report template file is a template used for reference when generating the review report file.

[0136] It can be understood that the attribute review results and geometric review results of the target BIM model are collected and recorded, and it is determined whether the target BIM model collected from the BIM project has been traversed. If it has not been traversed, the attribute information and geometric information are extracted and the execution of step S30 is returned. If it has been traversed, step 602 is continued, and the attribute review results and geometric review results of all collected BIM models are output to the review report file with reference to the review report template file.

[0137] This embodiment provides a BIM model review method based on knowledge graph and image matching. Based on the review of standard specification documents, a standard specification knowledge graph is constructed; based on the off-platform development strategy, the BIM project file is parsed to obtain the target BIM model, and the attribute information and geometric information of the target BIM model are extracted; based on the standard specification knowledge graph, the attribute information of the target BIM model is compared and reviewed to obtain the attribute review result; the geometric information of the target BIM model is projected onto a two-dimensional plane to obtain two-dimensional plane drawing information, and based on the feature information in the two-dimensional plane drawing information, the geometric information is compared and reviewed to obtain the geometric review result; based on the attribute review result and the geometric review result, a review report file of the target BIM model is generated. By adopting a platform-free development concept, model parsing, model review, and review report output can be automatically realized, thereby improving review efficiency. Based on the review of standard specifications and documents, a standard specification knowledge graph is constructed, and the standard specification knowledge graph is used for search to achieve efficient and accurate retrieval and review of BIM model attribute information, ensuring review efficiency and accuracy. In addition, image feature extraction and matching algorithms are used, combined with the review of standard drawing documents, to review the geometric features of the BIM model, accurately verify the consistency of the drawings and models, reduce errors, and ensure the accuracy of the review.

[0138] For example, in order to help understand the implementation process of the BIM model review method based on knowledge graph and image matching obtained by combining this embodiment with the above embodiment 1, please refer to Figure 9 , Figure 9 This paper provides a brief flowchart of the BIM model review method based on knowledge graph and image matching. Specifically:

[0139] Based on the review of standard specification documents, the specification clause information is extracted as structured data, and a standard specification knowledge graph is constructed based on the extracted structured data; off-platform development technology is used to parse BIM project files and collect all BIM models in the project; based on the BIM model data collected in the previous step, the attribute information and geometric information in the BIM model are extracted; the attribute information in the BIM model is traversed, and the knowledge graph relationship search algorithm is used to quickly query the specification attribute information for comparison and review; based on the extracted BIM model geometric information, the 3D geometric feature information is projected onto a 2D plane using a 3D hidden layer removal and perspective projection algorithm; based on the projected 2D plane drawing information, combined with the standard drawing file, the MatchNet algorithm is used to intelligently extract feature information and perform image matching review; the results of the BIM model attribute information review and geometric information review are collected and recorded; it is determined whether the BIM model collected from the BIM project has been traversed. If not, the review is continued. If it has been traversed, the review results of all collected BIM model attributes and geometric information are output to the review report file with reference to the review report template file.

[0140] It should be noted that the above examples are only used to understand this application and do not constitute a limitation on the BIM model review method based on knowledge graph and image matching in this application. More forms of simple transformations based on this technical concept are all within the scope of protection of this application.

[0141] This application also provides a BIM model review device based on knowledge graph and image matching, please refer to Figure 10 , the BIM model review device based on knowledge graph and image matching includes:

[0142] The graph construction module 10 is used to construct a standard specification knowledge graph based on the review standard specification documents.

[0143] The model parsing module 20 is used to parse the BIM project file based on the off-platform development strategy, obtain the target BIM model, and extract the attribute information and geometric information of the target BIM model.

[0144] The model review module 30 is used to compare and review the attribute information of the target BIM model based on the standard specification knowledge graph to obtain an attribute review result.

[0145] The model review module 30 is further configured to project the geometric information of the target BIM model onto a two-dimensional plane to obtain two-dimensional plane drawing information.

[0146] The model review module 30 is further used to compare and review the geometric information based on the feature information in the two-dimensional plane drawing information to obtain a geometric review result.

[0147] The model review module 30 is further configured to generate a review report file of the target BIM model based on the attribute review result and the geometry review result.

[0148] In a feasible implementation, the graph construction module 10 is further used to analyze the review standard specification document to determine the standard specification clause information;

[0149] Extracting the standard specification information into structured data, wherein the structured data includes at least entity data, relationship data, and attribute data;

[0150] Perform knowledge fusion on the structured data to construct a standard knowledge graph.

[0151] In a feasible implementation, the model parsing module 20 is further configured to obtain a BIM project file, wherein the BIM project file has multiple formats;

[0152] Based on the off-platform development strategy, BIM project files in multiple formats are parsed to obtain multiple BIM models of the target project, and the multiple BIM models are used as the target BIM model.

[0153] In a feasible embodiment, the model review module 30 is further configured to retrieve corresponding specification attribute information in the standard specification knowledge graph based on the attribute information of the target BIM model, wherein the attribute information includes at least category, layer information, and material information;

[0154] Based on the specification attribute information, the attribute information of the target BIM model is compared and reviewed to generate an attribute review result.

[0155] In a feasible implementation manner, the model review module 30 is further configured to determine that the attribute review result is qualified when the attribute information of the target BIM model meets the specification attribute information;

[0156] When the attribute information of the target BIM model does not conform to the standard attribute information, the attribute review result is determined to be unqualified.

[0157] In a feasible implementation manner, the model review module 30 is further configured to extract a kernel basic data structure from the geometric information based on the geometric information of the target BIM model;

[0158] Performing three-dimensional hiding on the kernel basic data structure to determine occlusion relationships in the kernel basic data structure, the occlusion relationships at least including occlusion relationships between edges, occlusion relationships between edges and faces, and occlusion relationships between faces;

[0159] Based on the occlusion relationship, the kernel basic data structure is projected onto a two-dimensional plane to obtain the two-dimensional plane drawing information.

[0160] In a feasible implementation manner, the model review module 30 is further configured to extract features from the two-dimensional plan drawing information based on a pre-trained feature model to obtain feature information;

[0161] Extract features from standard drawing files based on pre-trained feature models to obtain standard feature information;

[0162] Matching the standard feature information with the feature information based on a pre-trained matching model to determine a matching score;

[0163] Based on the matching score, the geometric review result is determined.

[0164] In a feasible implementation manner, the model review module 30 is further configured to determine that the geometric review result is qualified when the matching score is greater than or equal to a preset score;

[0165] When the matching score is less than the preset score, the geometric review result is determined to be unqualified.

[0166] In a feasible implementation manner, the model review module 30 is further configured to record the attribute review result and the geometry review result, and determine whether the target BIM model is traversed completely;

[0167] When the traversal is completed, an audit report file corresponding to the attribute audit result and the geometric audit result is generated based on the audit report template file.

[0168] The BIM model review device based on knowledge graph and image matching provided by this application adopts the BIM model review method based on knowledge graph and image matching in the above-mentioned embodiment, which can solve the technical problem of low efficiency of the BIM model review method. Compared with the existing technology, the beneficial effects of the BIM model review device based on knowledge graph and image matching provided by this application are the same as the beneficial effects of the BIM model review method based on knowledge graph and image matching provided by the above-mentioned embodiment, and the other technical features of the BIM model review device based on knowledge graph and image matching are the same as the features disclosed in the above-mentioned embodiment method, which will not be repeated here.

[0169] The present application provides a BIM model review device based on knowledge graph and image matching. The BIM model review device based on knowledge graph and image matching includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the BIM model review method based on knowledge graph and image matching in the above-mentioned embodiment one.

[0170] Reference below Figure 11, which shows a schematic diagram of the structure of a BIM model review device based on knowledge graph and image matching suitable for implementing the embodiments of the present application. The BIM model review device based on knowledge graph and image matching in the embodiments of the present application may include, but is not limited to, mobile terminals such as mobile phones, laptops, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Descriptions), PMPs (Portable Media Players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., as well as fixed terminals such as digital TVs, desktop computers, etc. Figure 11 The BIM model review device based on knowledge graph and image matching shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0171] like Figure 11 As shown, the BIM model review device based on knowledge graph and image matching may include a processing device 1001 (such as a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes according to the program stored in the read-only memory (ROM: Read Only Memory) 1002 or the program loaded from the storage device 1003 to the random access memory (RAM: Random Access Memory) 1004. Various programs and data required for the operation of the BIM model review device based on knowledge graph and image matching are also stored in RAM1004. The processing device 1001, ROM1002 and RAM1004 are connected to each other via a bus 1005. The input / output (I / O) interface 1006 is also connected to the bus. Typically, the following systems can be connected to the I / O interface 1006: input devices 1007 including, for example, a touch screen, a touchpad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.; output devices 1008 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; storage devices 1003 including, for example, a magnetic tape, a hard disk, etc.; and communication devices 1009. The communication device 1009 can allow the BIM model review device based on the knowledge graph and image matching to communicate with other devices wirelessly or by wire to exchange data. Although the figure shows a BIM model review device based on the knowledge graph and image matching with various systems, it should be understood that it is not required to implement or have all the systems shown. More or fewer systems may be implemented or have instead.

[0172] In particular, according to the embodiments disclosed in the present application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, the embodiments disclosed in the present application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program comprising program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network via a communication device, or installed from a storage device 1003, or installed from a ROM 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the method of the embodiment disclosed in the present application are executed.

[0173] The BIM model review device based on knowledge graph and image matching provided by this application adopts the BIM model review method based on knowledge graph and image matching in the above-mentioned embodiment, which can solve the technical problem of low efficiency of the BIM model review method. Compared with the existing technology, the beneficial effects of the BIM model review device based on knowledge graph and image matching provided by this application are the same as the beneficial effects of the BIM model review method based on knowledge graph and image matching provided by the above-mentioned embodiment, and the other technical features of the BIM model review device based on knowledge graph and image matching are the same as the features disclosed in the method of the previous embodiment, which will not be repeated here.

[0174] It should be understood that the various parts disclosed in this application can be implemented using hardware, software, firmware, or a combination thereof. In the description of the above embodiments, specific features, structures, materials, or characteristics can be combined in any one or more embodiments or examples in a suitable manner.

[0175] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.

[0176] The present application provides a computer-readable storage medium having computer-readable program instructions (i.e., a computer program) stored thereon, and the computer-readable program instructions are used to execute the BIM model review method based on knowledge graph and image matching in the above-mentioned embodiment.

[0177] The computer-readable storage medium provided in this application may be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, systems or devices, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In this embodiment, the computer-readable storage medium may be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, system or device. The program code contained on the computer-readable storage medium may be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination thereof.

[0178] The above-mentioned computer-readable storage medium may be included in the BIM model review device based on knowledge graph and image matching; or it may exist independently without being assembled into the BIM model review device based on knowledge graph and image matching.

[0179] The above-mentioned computer-readable storage medium carries one or more programs. When the above-mentioned one or more programs are executed by the BIM model review device based on the knowledge graph and image matching, the BIM model review device based on the knowledge graph and image matching: constructs a standard specification knowledge graph based on the review standard specification file; parses the BIM project file based on the off-platform development strategy to obtain the target BIM model, and extracts the attribute information and geometric information of the target BIM model; compares and verifies the attribute information of the target BIM model based on the standard specification knowledge graph to obtain the attribute review result; projects the geometric information of the target BIM model onto a two-dimensional plane to obtain two-dimensional plane drawing information, and compares and verifies the geometric information based on the feature information in the two-dimensional plane drawing information to obtain the geometric review result; generates a review report file of the target BIM model based on the attribute review result and the geometric review result.

[0180] Computer program code for performing the operations of the present application may be written in one or more programming languages, or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a stand-alone software package, partially on the user's computer and partially on a remote computer, or entirely on the remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., through the Internet using an Internet service provider).

[0181] The flow charts and block diagrams in the accompanying drawings illustrate the possible architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present application. In this regard, each box in the flow chart or block diagram can represent a module, program segment or a part of code, and the module, program segment or a part of code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order than that marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flow chart, and the combination of the boxes in the block diagram and / or flow chart can be implemented by a dedicated hardware-based system that performs the specified function or operation, or can be implemented by a combination of dedicated hardware and computer instructions.

[0182] The modules described in the embodiments of the present application may be implemented in software or hardware, wherein the name of a module does not necessarily limit the unit itself.

[0183] The readable storage medium provided in this application is a computer-readable storage medium, which stores computer-readable program instructions (i.e., a computer program) for executing the above-mentioned BIM model review method based on knowledge graph and image matching, and can solve the technical problem of low efficiency in BIM model review methods. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided in this application are the same as the beneficial effects of the BIM model review method based on knowledge graph and image matching provided in the above-mentioned embodiment, and will not be repeated here.

[0184] The present application also provides a computer program product, including a computer program, which, when executed by a processor, implements the steps of the BIM model review method based on knowledge graph and image matching as described above.

[0185] The computer program product provided in this application can address the technical issue of inefficient BIM model review methods. Compared to the prior art, the beneficial effects of the computer program product provided in this application are the same as those of the BIM model review method based on knowledge graphs and image matching provided in the aforementioned embodiments, and are not further elaborated here.

[0186] The above description is only part of the embodiments of the present application and does not limit the patent scope of the present application. All equivalent structural transformations made by using the contents of the present application specification and drawings under the technical concept of the present application, or direct / indirect application in other related technical fields are included in the patent protection scope of the present application.

Claims

1. A BIM model review method based on knowledge graph and image matching, characterized in that: The method comprises: Build a knowledge graph of standards and specifications based on the review of standard and specification documents; Based on the off-platform development strategy, the BIM project file is parsed to obtain the target BIM model, and the attribute information and geometric information of the target BIM model are extracted; Based on the standard specification knowledge graph, the attribute information of the target BIM model is compared and reviewed to obtain an attribute review result; Projecting the geometric information of the target BIM model onto a two-dimensional plane to obtain two-dimensional plane drawing information; Based on the feature information in the two-dimensional plan drawing information, the geometric information is compared and reviewed to obtain a geometric review result; Based on the attribute review result and the geometry review result, a review report file of the target BIM model is generated.

2. The method according to claim 1, wherein The steps of constructing a standard specification knowledge graph based on reviewing standard specification documents include: Analyze and review standard and specification documents to determine standard and specification clause information; Extracting the standard specification information into structured data, wherein the structured data includes at least entity data, relationship data, and attribute data; Perform knowledge fusion on the structured data to construct a standard knowledge graph.

3. The method according to claim 1, wherein The steps of parsing the BIM project file based on the off-platform development strategy to obtain the target BIM model include: Acquire a BIM project file, where the BIM project file has multiple formats; Based on the off-platform development strategy, BIM project files in multiple formats are parsed to obtain multiple BIM models of the target project, and the multiple BIM models are used as the target BIM model.

4. The method according to claim 1, wherein The step of comparing and reviewing the attribute information of the target BIM model based on the standard specification knowledge graph to obtain the attribute review result includes: Based on the attribute information of the target BIM model, corresponding specification attribute information is retrieved in the standard specification knowledge graph, where the attribute information includes at least category, layer information, and material information; Based on the specification attribute information, the attribute information of the target BIM model is compared and reviewed to generate an attribute review result.

5. The method according to claim 4, wherein The step of comparing and reviewing the attribute information of the target BIM model based on the specification attribute information to generate an attribute review result includes: When the attribute information of the target BIM model meets the specification attribute information, determining that the attribute review result is qualified; When the attribute information of the target BIM model does not conform to the standard attribute information, the attribute review result is determined to be unqualified.

6. The method according to claim 1, wherein The step of projecting the geometric information of the target BIM model onto a two-dimensional plane to obtain two-dimensional plane drawing information includes: Based on the geometric information of the target BIM model, extracting the kernel basic data structure in the geometric information; Performing three-dimensional hiding on the kernel basic data structure to determine occlusion relationships in the kernel basic data structure, the occlusion relationships at least including occlusion relationships between edges, occlusion relationships between edges and faces, and occlusion relationships between faces; Based on the occlusion relationship, the kernel basic data structure is projected onto a two-dimensional plane to obtain the two-dimensional plane drawing information.

7. The method according to claim 1, wherein The step of comparing and reviewing the geometric information based on the feature information in the two-dimensional plan drawing information to obtain a geometric review result includes: Extracting features from the two-dimensional drawing information based on a pre-trained feature model to obtain feature information; Extract features from standard drawing files based on pre-trained feature models to obtain standard feature information; Matching the standard feature information with the feature information based on a pre-trained matching model to determine a matching score; Based on the matching score, the geometric review result is determined.

8. The method according to claim 7, wherein The step of determining the geometric review result based on the matching score includes: When the matching score is greater than or equal to a preset score, determining that the geometric review result is qualified; When the matching score is less than the preset score, the geometric review result is determined to be unqualified.

9. The method according to any one of claims 1 to 8, characterized in that The step of generating a review report file of the target BIM model based on the attribute review result and the geometry review result includes: Recording the attribute review result and the geometry review result, and determining whether the target BIM model is traversed; When the traversal is completed, an audit report file corresponding to the attribute audit result and the geometric audit result is generated based on the audit report template file.

10. A BIM model review device based on knowledge graph and image matching, characterized in that: The device comprises: A graph construction module is used to construct a standard specification knowledge graph based on the review of standard specification documents; A model parsing module is used to parse the BIM project file based on the off-platform development strategy to obtain the target BIM model and extract the attribute information and geometric information of the target BIM model; A model review module is used to compare and review the attribute information of the target BIM model based on the standard specification knowledge graph to obtain an attribute review result; The model review module is further configured to project the geometric information of the target BIM model onto a two-dimensional plane to obtain two-dimensional plane drawing information; The model review module is further configured to compare and review the geometric information based on the feature information in the two-dimensional planar drawing information to obtain a geometric review result; The model review module is further used to generate a review report file of the target BIM model based on the attribute review result and the geometry review result.

Images