Building element spatial topology semantic relation ontology construction method based on IFC data

Abstract

The invention provides a building element spatial topology semantic relation ontology construction method based on IFC data, and the method comprises the steps: extracting a basic spatial relation between building entity elements based on the native relation information in the IFC data; based on the coordinate parameters of the entities, extracting a topological space relationship between the entities; performing operational analysis on the entities based on a geometric calculation function, and extracting a specific spatial relationship between the entities; and mapping and converting the various extracted spatial relationships into attributes conforming to BOT ontology specifications to form a spatial topology semantic relationship ontology. According to the method, building IFC data is taken as a research object, triad clear semantic information in an ontology is abstracted, extracted and concrete from original IFC file data by researching a spatial relationship between semantics in a specification and the BOT ontology, so that conversion from an original IFC file to concrete ontology semantic information is realized. The obtained ontology comprises an entity, a relation attribute and an invisible relation, so that spatial topological relation data contained in the IFC can be directly used by AI or employees.

Description

TECHNICAL FIELD

[0001] The application relates to the field of building information modeling and artificial intelligence technology, and particularly relates to a construction method of a building element space topological semantic relationship ontology based on IFC data. BACKGROUND

[0002] With the continuous development of information technology, artificial intelligence gradually appears in the whole cycle of building information. The application of artificial intelligence in the life cycle of building information is changing the design, construction, operation and maintenance and updating mode of buildings. Through automation of simple tasks, assistance to professional personnel in decision-making, improvement of decision-making quality and optimization of resource allocation, the industry is finally driven to a more efficient and intelligent information age. In this process, IFC (Industry Foundation Class) data, as a standard paradigm of building information modeling, plays an irreplaceable role in information storage and transmission.

[0003] However, in the application of artificial intelligence and the work of practitioners, various spatial relationships in IFC data are often hidden in massive data and cannot be directly utilized. In particular, in the scenario of dense equipment and complex structure in large building models, the previous processing method faces the challenges of insufficient computational efficiency and insufficient semantic expression. Traditional methods have significant redundancy problems when processing the above IFC scenarios. The spatial relationship information extraction process is often time-consuming, incomplete and not thorough, and it is difficult to meet the actual needs in engineering practice. At the same time, in terms of semantic expression, existing schemes can usually only provide simple geometric relationship description, and lack accurate topological relationship description between building components, which is difficult to support more complex and specific artificial intelligence applications. SUMMARY

[0004] In view of the defects in the prior art, the purpose of the present application is to provide an ontology of spatial topological semantic relationships between building entity elements based on IFC data and a construction method.

[0005] In a first aspect, the application provides a construction method of a building element space topological semantic relationship ontology based on IFC data, comprising: extracting the basic spatial relationship between the building entity elements based on the original relationship information in the IFC data; extracting the topological spatial relationship between the entities based on the coordinate parameters of the entities; performing operation analysis on the entities based on geometric calculation functions to extract the specific spatial relationship between the entities; mapping and converting the various spatial relationships extracted above into attributes conforming to the BOT ontology specification to form the spatial topological semantic relationship ontology.

[0006] Optionally, the spatial topological semantic relationship ontology comprises: Instance: the instance is a specific entity corresponding to an electrical equipment class, a physical element class and a space element class extracted from an IFC file; Relationship attribute: the relationship attribute is an attribute type for describing the association characteristics between instances determined by analysis and sorting based on relevant specification requirements; Implicit relationship: the implicit relationship is a specific relationship reflecting the actual association between instances obtained by mining entity attribute data from the IFC file.

[0007] Optionally, the basic spatial relationship between building entity elements is extracted based on the native relationship information in the IFC data, including: By analyzing six types of predefined relationship entities and two types of binding entities, the inherent topological relationship between entity elements is directly extracted as the basic spatial relationship; By analyzing six types of predefined relationship entities and two types of binding entities, the inherent topological relationship between entity elements is directly extracted as the basic spatial relationship; Among them, the six types of predefined relationship entities include: space boundary relationship IfcRelSpaceBoundary, space structure contained relationship IfcRelContainedInSpatialStructure, aggregation relationship IfcRelAggregates, element void relationship IfcRelVoidsElemen, element connection relationship IfcRelConnectsElements\element path connection relationship IfcRelConnectsPathElements, port connection relationship IfcRelConnectsPorts; Among them, the two types of binding entities include: element filling relationship IfcRelFillsElement, port and element connection relationship IfcRelConnectsPortToElement.

[0008] Optionally, the topological spatial relationship between entities is extracted based on the coordinate parameters of the entities, including: Obtain the corner point coordinates of the axis bounding box or the aligned bounding box of the entity, and determine the orientation relationship by comparing the corner point coordinates, including up-down orientation, front-back orientation, left-right orientation, adjacent and direct up-down relationship.

[0009] Optionally, the specific spatial relationship between entities is extracted based on the operation analysis of the entity by using a geometric calculation function, including: The nine intersection model algorithm is used to analyze the intersection state between the interiors, boundaries and exteriors of two entities; Combine the minimum distance calculation to determine the spatial distance characteristics between entities, and detect and identify whether there is a coplanar or collinear boundary association between entities through shared boundary detection; According to the detection recognition result based on the intersection state and the boundary association, combined with the space relationship judgment rule in the building field, the specific space relationship of the two entities is finally determined, including containing, crossing, adjacent and attaching.

[0010] Optionally, the mapping and conversion of the extracted various space relationships into attributes conforming to the BOT ontology specification form a structured space topology semantic relationship ontology, including: The conventional relationship in the space relationship directly generates a <entity-relation-entity> triple; The distance type relationship in the space relationship creates a Distance entity and associates numerical attributes and type attributes, realizing the structured semantic storage and query of the space relationship.

[0011] Optionally, in the process of constructing the ontology, a hierarchical caching mechanism and R-Tree space indexing optimization are adopted.

[0012] The second aspect of the application provides a building element space topology semantic relationship ontology construction system based on IFC data, including: A first extraction module: based on the native relationship information in the IFC data, extracting the basic space relationship between the building entity elements; A second extraction module: based on the coordinate parameters of the entities, extracting the topology space relationship between the entities; A third extraction module: based on geometric calculation functions, performing operation analysis on the entities to extract the specific space relationship between the entities; A conversion module: mapping and converting the extracted various space relationships into attributes conforming to the BOT ontology specification to form a structured space topology semantic relationship ontology.

[0013] The third aspect of the application provides a building element space topology semantic relationship ontology construction system based on IFC data, including: An original module: based on the native relationship information in the IFC data, extracting the basic space relationship between the building entity elements; A coordinate module: based on the coordinate parameters of the entities, extracting the topology space relationship between the entities; A function module: based on geometric calculation functions, performing operation analysis on the entities to extract the specific space relationship between the entities; A conversion module: mapping and converting the extracted various space relationships into attributes conforming to the BOT ontology specification to form a structured space topology semantic relationship ontology.

[0014] The fourth aspect of the application provides a terminal, including a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to execute the method or run the system.

[0015] In a fifth aspect, the present application provides a computer readable storage medium, having stored thereon a computer program, which, when executed by a processor, is operable to perform the method or run the system.

[0016] The ontology construction method of the spatial topological semantic relationship between the building entity elements based on IFC data of the present application takes the building IFC data as the research object, abstracts, extracts and materializes the explicit semantic information of triples in the ontology from the original IFC file data by researching the semantics in the specification and the spatial relationship of the BOT ontology, so as to realize the conversion from the original IFC file to the materialized ontology semantic information. The obtained ontology of the spatial topological semantic relationship between the building elements based on IFC data includes entities, relationship attributes and invisible relationships, so that the spatial topological relationship data contained in IFC can be directly used by AI or practitioners.

[0017] Other technical effects brought by the additional features will be further described in the corresponding embodiments. BRIEF DESCRIPTION OF DRAWINGS

[0018] Other features, objects and advantages of the present application will become more apparent from the following detailed description of non-limiting embodiments with reference to the attached drawings: Figure 1 A flow chart of the construction method of the ontology of the spatial topological semantic relationship between the building elements based on IFC data according to an exemplary embodiment is shown; Figure 2 An IFC ontology class structure according to an exemplary embodiment is shown; Figure 3 A complex spatial relationship judgment logic flow chart according to an exemplary embodiment is shown; Figure 4 A structure diagram of the construction system of the ontology of the spatial topological semantic relationship between the building elements based on IFC data according to an exemplary embodiment is shown; Figure 5 A class relationship diagram according to an exemplary embodiment is shown; Figure 6 An IFC data native relationship visualization diagram according to an exemplary embodiment is shown; Figure 7 A coordinate parameter-based relationship judgment visualization diagram according to an exemplary embodiment is shown; Figure 8 A spatial relationship visualization diagram based on a geometric calculation function according to an exemplary embodiment is shown. DETAILED DESCRIPTION

[0019] The application will be described in detail below with specific embodiments. The following examples will help those skilled in the art to further understand the application, but do not limit the application in any form. It should be noted that those skilled in the art can make several modifications and improvements without departing from the concept of the application, and these all belong to the protection scope of the application. The parts not described in detail in the following examples can be realized by using existing technologies.

[0020] Glossary: IFC is the abbreviation of Industry Foundation Classes, which is a general data standard in the field of Building Information Modeling (BIM), used to standardize the storage and transmission of entity (such as beam, column, equipment) and attribute, relationship data in the whole life cycle of building, and realize data intercommunication between different software and teams.

[0021] BOT is the abbreviation of Building Topology Ontology, which is a special semantic framework in the field of building, used to standardize the definition of building entities, spatial topology relationships between entities and attributes, so that the semantics of building data (such as IFC data) is more unified, and machine understanding and cross-scene reuse are supported.

[0022] The various spatial relationships in IFC data are often hidden in a large amount of data and are difficult to use directly. Based on the above problems, the embodiment of the application provides an ontology of spatial topology semantic relationship between building entity elements based on IFC data to solve the above problems.

[0023] Referring to Figure 1 In an embodiment of the application, a method for constructing an ontology of spatial topology semantic relationship between building entity elements based on IFC data can adopt the following steps: S100, based on the original relationship information in the IFC data, extracting the basic spatial relationship between the building entity elements; S200, based on the coordinate parameters of the entity, extracting the topological spatial relationship between the entities; S300, based on the geometric calculation function, performing operation analysis on the entity, and extracting the specific spatial relationship between the entities; S400, mapping and converting the various spatial relationships extracted above into attributes conforming to the BOT ontology specification, forming a structured spatial topology semantic relationship ontology.

[0024] The above embodiment of the application takes building IFC data as the research object, abstracts, extracts and materializes the semantic information of triples in the ontology from the original IFC file data by studying the semantics in the specification and the spatial relationship of the BOT ontology, so as to realize the conversion from the original IFC file to the materialized ontology semantic information.

[0025] It is worth noting that the execution order of S100, S200, and S300 is not solely limited to the above order; in other embodiments, the execution order of the three can be arbitrarily arranged, and any parallel execution method can also be adopted. In one specific embodiment, the following is used: Figure 3 The execution order is shown.

[0026] like Figure 2 As shown, the ontology representing the spatial topological semantic relationships between building entity elements based on IFC data, obtained using the method described in the above embodiments, includes: Example: An instance is a concrete entity corresponding to the electrical equipment class, physical element class, and spatial element class extracted from the IFC file; Specifically, instances are concrete building objects extracted from the IFC file, corresponding to the three main categories (Electrical Equipment, IfcElement, and Spatial Element), and have explicit attributes (such as location and model). The Physical Element category is further categorized as: Industrial Foundation Building Element (IfcBuildingElement); Industrial Foundation Civil Engineering Element (IfcCivilElement); Industrial Foundation Distribution Element (IfcDistributionElement); Industrial Foundation Assembly Element (IfcElementAssembly); Industrial Foundation Element Component; Industrial Foundation Feature Element (IfcFeatureElement); Industrial Foundation Furnishing Element (IfcFurnishingElement); Industrial Foundation Geographic Element (IfcGeographicElement); Industrial Foundation Transportation Element (IfcTransportElement); and Industrial Foundation Virtual Element (IfcVirtualElement). The Spatial Element category is further categorized as: Industrial Foundation External Spatial Structure Element (IfcExternalSpatialStructureElement); Industrial Foundation Spatial Structure Element (IfcSpatialStructureElement); and Industrial Foundation Spatial Zone (IfcSpatialZone). Example: The electrical distribution box (model: XX-100) in the 3rd floor conference room in the IFC document is an example.

[0027] Relationship attributes: Relationship attributes are attribute types used to describe the relationship characteristics between instances, determined through analysis and sorting based on relevant specification requirements; Specifically, relational attributes are definitions that describe the types of relationships between instances, compiled according to building codes, and constitute a general relational framework.

[0028] Example: Power supply dependency based on the Low Voltage Power Distribution Specification (describe the association type between the distribution box and the electrical equipment).

[0029] Implicit relationships: Implicit relationships are specific relationships that are mined from the entity attribute data of the IFC file and reflect the actual association between instances.

[0030] Specifically, entity attribute data includes coordinates, ID, identifier, etc.

[0031] Example: From the IFC file: Power supply ID of the distribution box matches the air conditioner, and it is found that: the power supply box of the 3rd floor conference room supplies power to the air conditioner in this room.

[0032] The entities, relational attributes, and implicit relationships included in the above embodiments of this application enable the spatial topology relational data contained in the IFC to be directly used by AI or practitioners.

[0033] To better obtain the basic spatial relationships, in some specific embodiments of this application, S100, based on the native relationship information in the IFC data, the basic spatial relationships between building entity elements can be extracted using the following steps: S101, based on the native relationships of IFC data, directly extracts the inherent topological relationships of the construct instance by parsing six types of predefined relational entities and two types of bound entities.

[0034] Specifically, the six predefined relational entities are: IfcRelSpaceBoundary, IfcRelContainedInSpatialStructure, IfcRelAggregates, IfcRelVoidsElemen, IfcRelConnectsElements, IfcRelConnectsPathElements, and IfcRelConnectsPorts.

[0035] Specifically, the two types of bound entities are IfcRelFillsElement and IfcRelConnectsPortToElement.

[0036] Specifically, inherent topological relationships include: component enclosure, spatial enclosure, etc.

[0037] For example, IfcRelSpaceBoundary explicitly stores "the boundary of a room is formed by a certain wall", and the "boundary relationship between the room and the wall" can be obtained directly without calculation.

[0038] The embodiments described above directly extract inherent topological relationships, eliminating complex calculations, quickly obtaining basic spatial relationships, and reducing data processing costs. Based on the native IFC relationships, the extracted relationships conform to the standard and have high accuracy, laying a reliable foundation for subsequent semantic processing.

[0039] To better obtain the spatial topological relationships between entities, in some specific embodiments of this application, S200, the topological spatial relationships between entities are extracted based on the coordinate parameters of the entities, which can be achieved by the following steps: S201, obtain the coordinates of the corner points of the axis bounding box or the alignment bounding box of the entity; Specifically, axial bounding boxes and aligned bounding boxes are two types of bounding boxes. An axial bounding box is a cube that can completely enclose a solid shape. An axial bounding box has its three directions as axes. An aligned bounding box is the bounding box whose direction minimizes its volume. The bounding box corresponds to the solid shape. The corner points of the bounding box are the corner points of the cube, totaling eight.

[0040] S202 determines the orientation relationship by comparing the corner coordinates, including the top and bottom orientation (isAbove / isBelow), front and back orientation (isInFrontOf / isBehind), and left and right orientation (isOnTheLeftOf / isOnTheRightOf), as well as some other orientation relationships, such as adjacent and direct top and bottom relationships.

[0041] The embodiments described above utilize axis and alignment bounding box coordinate comparison to quickly determine the positional relationships between entities, such as vertical, front-back, and left-right, thereby improving the efficiency of spatial relationship extraction. They can also provide accurate data support for the automatic verification of building code provisions (such as checking the compliance of equipment installation orientation), reducing the cost of manual intervention.

[0042] To further obtain the specific spatial relationships between entities, in some specific embodiments of this application, S300, the entities are analyzed based on geometric calculation functions to extract the specific spatial relationships between entities, which can be achieved by the following steps: S301 uses the nine-intersection model algorithm to analyze the intersection state between the interior, boundary, and exterior of two entities; Specifically, the nine-intersection model refers to an internationally recognized framework for analyzing topological relationships. This framework decomposes the geometry of each entity into three parts: "interior (the space occupied by the entity itself), boundary (the edge of the entity, such as the surface of a wall or the side of a column), and exterior (the space outside the entity)." By calculating the "intersection states" (intersecting or non-intersecting) of two entities in nine combinations such as "interior-interior, interior-boundary, interior-exterior, boundary-interior, etc.", a "nine-bit feature code" is generated, which is then used to determine the most basic type of topological relationship.

[0043] S302 combines minimum distance calculation to clarify the spatial distance characteristics between entities, and identifies whether there are coplanar or collinear boundary associations between entities through shared boundary detection.

[0044] The nine-intersection model can be used to determine whether two entities intersect. However, it cannot answer detailed questions such as the distance when they do not intersect or how their boundaries relate when they do intersect. Therefore, two additional dimensions are needed: first, minimum distance calculation, to quantify the closest distance between two entities (or their boundaries); and second, shared boundary detection, to determine whether two entities are coplanar or collinear. Coplanarity includes cases such as a ceiling and the top of a wall sharing a plane. Collinearity includes cases such as the bases of two columns sharing an axis.

[0045] S303, based on S301 and S302, adapts to the spatial relationship determination rules specific to the architectural field, and ultimately determines the specific spatial relationship between two entities, including inclusion, crossing, adjacency, and dependence.

[0046] Specifically, the first two steps yield pure geometric features, but spatial relationships in the architectural field have their own specializations and need to be translated into professional terminology in accordance with industry rules. For example: Geometrically, two entities with a distance of ≤0.5 meters and no shared boundary may be defined as adjacent in architecture; however, the same distance may not be considered adjacent in the mechanical field.

[0047] The embodiments described above in this application combine the nine-intersection model, distance calculation, and boundary detection to accurately analyze the geometric relationships of entities from multiple dimensions, thereby improving the accuracy of spatial relationship determination. They are adapted to architectural rules and can clearly identify specific relationships such as inclusion and crossing, providing accurate relationship data support for subsequent semantic conversion and standard verification.

[0048] In some specific embodiments of this application, in S400, the extracted spatial relationships are converted into BOT ontology attributes, which can be achieved by the following steps: S401, regular relations directly generate <entity-relationship-entity> triples; Specifically, conventional relationships refer to relationships that can be directly expressed by triples, such as the adjacency relationship or dependency relationship between two entities, which can be directly represented as <entity1, adjacent, entity2> or <entity1, dependent on, entity2>.

[0049] S402, distance-based relationships create a Distance entity and associate it with numerical and type attributes to achieve structured semantic storage and querying of spatial relationships.

[0050] Specifically, distance-related relationships refer to distance concepts that include specific numerical values, such as minimum distance, horizontal distance, and elevation difference.

[0051] In the embodiments described above, the specification-driven BOT ontology mapping framework constructed at the semantic layer transforms geometric relationships into machine-readable RDF triple structures, thereby realizing the explicit semantic expression of building code clauses.

[0052] When processing the geometric relationships of building entities (such as calculating the distance between two components or determining whether they contain each other), two typical problems exist: redundant calculation: the geometric data (such as coordinates and bounding boxes) of the same batch of entities may be calculated repeatedly; inefficient query: when the number of entities is large, determining "which entities are near a certain entity" may require comparing them one by one, which is extremely time-consuming. Therefore, in some specific embodiments of this application, at the calculation level, a hierarchical caching mechanism and R-Tree spatial index optimization are used to reduce the overhead of geometric redundant calculations.

[0053] Specifically, caching temporarily stores frequently accessed data in faster storage media to avoid recalculation or reading from slower storage devices (such as hard drives) on each access.

[0054] Hierarchical storage refers to employing a multi-tiered storage strategy based on data access frequency and computational cost. High-level cache (such as in-memory cache): used to store the most frequently accessed and computationally expensive data (such as the coordinates of the corner points of the axis-aligned bounding box of a complex component, which is time-consuming to calculate but needs to be accessed frequently). Low-level cache (such as a regular cache in memory): used to store data with moderate access frequency (such as simplified geometric parameters of a component); No caching: Data with extremely low access frequency or minimal computational cost (such as temporarily generated intermediate results) is not cached.

[0055] Specifically, R-Tree spatial index optimization refers to: by constructing a hierarchical directory based on the spatial location of building entities, it enables rapid location of entities within a specific spatial range, avoiding the inefficiency of comparing one by one.

[0056] For example: the entire spatial extent of the building is considered as a root node; the root node is divided into multiple child nodes, each corresponding to a sub-region; each child node is further subdivided into smaller regions, until it ultimately points to a specific entity. This R-Tree index reduces the time required to locate the target entity.

[0057] In the embodiments described above, the hierarchical caching mechanism and dynamic spatial index established at the computing layer reduce redundant computing overhead and achieve efficient processing of industrial building models.

[0058] Based on the same technical concept, other embodiments of this application also provide an ontology construction system 100 for spatial topological semantic relationships between building entity elements based on IFC data, such as... Figure 4 As shown, it includes: First extraction module 110: Based on the native relationship information in the IFC data, extract the basic spatial relationships between building entity elements; Second extraction module 120: Extracts the topological spatial relationships between entities based on their coordinate parameters; Third extraction module 130: Performs calculation and analysis on entities based on geometric calculation functions to extract specific spatial relationships between entities; Transformation module 140: Converts the various spatial relationships extracted above into attributes that conform to the BOT ontology specification, forming a structured spatial topological semantic relation ontology.

[0059] The preferred features in the above embodiments can be used individually in any embodiment, or in any combination thereof, provided they do not conflict with each other. Furthermore, parts not described in detail in the embodiments can be implemented using existing technologies.

[0060] The following examples and comparative examples will be used to further illustrate this application in order to better understand the above-mentioned technical solutions. It should be understood that the following are only some examples and are not intended to limit this application.

[0061] Application Example 1 An IFC model of a typical industrial building—a 110kV substation—was selected as the experimental subject. This model fully reflects the unique complexity of industrial buildings: dense equipment layout, rich spatial structure hierarchy, and strict functional area division. By implementing the ontology construction method based on the spatial topological semantic relationships between building entity elements according to the above embodiments of this application, a complete building information semantic network was successfully constructed, realizing an effective conversion from geometric model to semantic ontology. During the experiment, the multi-level optimized architecture demonstrated significant structural advantages, especially in handling the unique electrical equipment layout and building structural relationships of substations, showing good adaptability.

[0062] (1) Class instance writing In the IFC model of the substation experimental object, instances of various categories from the predefined knowledge graph are written into it. That is, all entities in the IFC file that meet the class name requirements are written into the ontology as instances, while maintaining the original structure of the ontology. Figure 5 And it is prepared to be written into the relation attribute as a component of the triple.

[0063] (2) Relationship Realization and Visual Verification To verify the effectiveness of the method, the relational attributes of all entities in the substation's IFC model were extracted. Following the ontology construction method described in the above embodiment, the relational implementation was divided into three main parts: native relations based on IFC data, relations based on coordinate parameter judgment, and spatial relations based on geometric calculation functions. Each relation was implemented and visualized separately. Since full visualization would display too many entities, making it not only complex and difficult to understand but also potentially misleading, only the visualization of the first group or special group of building instances was considered.

[0064] Based on the native relationships of IFC data, it implements relationship attributes between instances such as bounds, partially contains, partially attach, composedof, and partially connect. The first group or a specific combination extracted from these attributes is then visualized, such as... Figure 6 As shown.

[0065] Based on coordinate parameters, it implements relationship attributes between instances such as above (up / down), directly-above (directly up / down), behind (behind / back), and left (left / right). For example... Figure 7 As shown.

[0066] Based on geometric calculation functions, relational properties between instances such as `crosses`, `dooroveragainststairflight`, `adjacentto`, `separatedby`, `contains`, and `attached` are implemented. Figure 8 As shown.

[0067] Based on the above examples, it is clear that in the application process, the implementation of various entity instances and the relationship attributes between instances is well completed, and the entity instance relationship attributes in the IFC model can be extracted completely and accurately.

[0068] This example provides an ontology construction method aimed at achieving efficient and accurate spatial topological semantic relationships between building entity elements based on IFC data. Based on the original IFC data format and the semantic expression of relationships between building entities using knowledge graphs, this method extracts implicit relationships between entities in building information models with complex and chaotic entity relationships, such as complex large buildings, and finally semantically maps them to form a semantically clear knowledge graph (ontology).

[0069] The method in this application adopts a "computation-spatial relationship-semantic" architecture: at the computation layer, a caching mechanism is established to reduce redundant computation, and spatial indexing is used to accelerate neighborhood search; at the spatial relationship layer, a judgment algorithm based on bounding box filtering, the nine-intersection model, and inclusion relationships is developed to accurately identify topological relationships such as inclusion and adjacency; at the semantic mapping layer, an RDF triple generation process oriented towards BOT ontology is used to achieve semantic conversion from geometric relationships to ontology attributes. This provides a structured semantic foundation for intelligent building applications, improves the completeness and effectiveness of spatial relationship extraction, and particularly supports the deep application of AI in scenarios such as security review and operation and maintenance decision-making.

[0070] Optionally, the memory is used to store programs; the memory may include volatile memory, such as random-access memory (RAM), such as static random-access memory (SRAM), double data rate synchronous dynamic random-access memory (DDR SDRAM), etc.; the memory may also include non-volatile memory, such as flash memory. The memory is used to store computer programs (such as application programs and functional modules that implement the above methods), computer instructions, etc., and the aforementioned computer programs and computer instructions can be partitioned and stored in one or more memories. Furthermore, the aforementioned computer programs, computer instructions, data, etc., can be accessed by the processor.

[0071] The aforementioned computer programs, computer instructions, etc., can be stored in partitions within one or more memory locations. Furthermore, the aforementioned computer programs, computer instructions, data, etc., can be accessed by a processor.

[0072] A processor is used to execute a computer program stored in memory to implement the various steps of the methods involved in the above embodiments. For details, please refer to the relevant descriptions in the preceding method embodiments.

[0073] The processor and memory can be separate structures or integrated structures. When the processor and memory are separate structures, they can be coupled together via a bus.

[0074] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0075] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0076] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0077] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0078] The foregoing has described some specific embodiments of this application. It should be understood that this application is not limited to the specific embodiments described above, and those skilled in the art can make various modifications or variations within the scope of the claims, which do not affect the substantive content of this application. The above-described preferred features can be used in any combination without conflict.

Claims

1. A method for constructing a building element space topology semantic relationship ontology based on IFC data, characterized in that, The method comprises the following steps: Based on the native relationship information in the IFC data, the basic spatial relationship between the building entity elements is extracted; Based on the coordinate parameters of the entities, the topological spatial relationship between the entities is extracted; Based on the geometric calculation function, the entities are analyzed and calculated, and the specific spatial relationship between the entities is extracted; The above-mentioned various types of spatial relationship mapping are converted into attributes conforming to the BOT ontology specification, and a structured spatial topological semantic relationship ontology is formed.

2. The method of claim 1, wherein the method further comprises: determining a spatial relationship between the first IFC data and the second IFC data; and determining a spatial relationship between the first IFC data and the third IFC data. The spatial topological semantic relationship ontology comprises: Instance: the instance is a specific entity corresponding to an electrical equipment class, a physical element class and a space element class extracted from an IFC file; Relationship attribute: the relationship attribute is an attribute type used to describe the correlation characteristics between instances determined by analysis and sorting based on relevant specification requirements; Implicit relationship: the implicit relationship is a specific relationship reflecting the actual correlation between instances mined from the entity attribute data of the IFC file.

3. The method of claim 1, wherein the method further comprises: determining a spatial relationship between the first building element and the second building element based on the IFC data; and determining a spatial relationship between the first building element and the third building element based on the IFC data. The basic spatial relationship between the building entity elements is extracted based on the native relationship information in the IFC data, comprising: By analyzing six types of predefined relationship entities and two types of binding entities, the inherent topological relationship between the entity elements is directly extracted as the basic spatial relationship; The six types of predefined relationship entities comprise: a space boundary relationship IfcRelSpaceBoundary, a space structure contained relationship IfcRelContainedInSpatialStructure, an aggregation relationship IfcRelAggregates, an element opening relationship IfcRelVoidsElement, an element connection relationship IfcRelConnectsElements, an element path connection relationship IfcRelConnectsPathElements and a port connection relationship IfcRelConnectsPorts; The two types of binding entities comprise: an element filling relationship IfcRelFillsElement and a port and element connection relationship IfcRelConnectsPortToElement.

4. The method of claim 1, wherein the method further comprises: The topological spatial relationship between the entities is extracted based on the coordinate parameters of the entities, comprising: The corner point coordinates of the axis bounding box or the aligned bounding box of the entity are obtained, and the orientation relationship is determined by comparing the corner point coordinates, including up-down orientation, front-back orientation, left-right orientation, adjacent and direct up-down relationship.

5. The method of claim 1, wherein the method further comprises: determining a spatial relationship between the first building element and the second building element based on the IFC data; and determining a spatial relationship between the first building element and the third building element based on the IFC data. The specific spatial relationship between the entities is extracted by performing operation analysis on the entities based on the geometric calculation function, comprising: The intersection state between the interiors, boundaries and exteriors of two entities is analyzed by using a nine intersection model algorithm; The spatial distance characteristics between the entities are determined by combining minimum distance calculation, and whether there is a coplanar or collinear boundary association between the entities is detected and identified by shared boundary detection; According to the detection and identification results based on the intersection state and the boundary association, and combining the spatial relationship determination rules in the field of architecture, the specific spatial relationship between the two entities is finally determined, including containing, penetrating, adjacent and adhering.

6. The method of claim 1, wherein the method further comprises: The above-mentioned various types of spatial relationship mapping are converted into attributes conforming to the BOT ontology specification, and a structured spatial topological semantic relationship ontology is formed, comprising: The conventional relationship in the spatial relationship directly generates an <entity-relation-entity> triple; The distance type relationship in the spatial relationship creates a Distance entity and associates a numerical attribute and a type attribute, achieving structured semantic storage and query of the spatial relationship.

7. The method of claim 1, wherein the method further comprises: determining a spatial relationship between the first IFC data and the second IFC data; and determining a spatial relationship between the first IFC data and the third IFC data. In the process of constructing the ontology, a hierarchical cache mechanism and an R-Tree spatial index are adopted for optimization.

8. A system for constructing an ontology of spatial topological semantic relationships of building elements based on IFC data, characterized in that, The method comprises the following steps: A first extraction module: based on the native relationship information in the IFC data, extracting the basic spatial relationship between the building entity elements; A second extraction module: based on the coordinate parameters of the entities, extracting the topological spatial relationship between the entities; A third extraction module: based on geometric calculation functions, performing operation analysis on the entities, and extracting the specific spatial relationship between the entities; A conversion module: mapping and converting the various types of spatial relationships extracted above into attributes conforming to the BOT ontology specification, and forming a structured spatial topological semantic relationship ontology.

9. A terminal comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that, The processor executes the program and can be used to execute the method in any one of claims 1-7, or run the system in claim 8.

10. A computer-readable storage medium having stored thereon a computer program, characterized in that, The program is executed by the processor and can be used to execute the method in any one of claims 1-7, or run the system in claim 8.

Images