Modeling file generation method, electronic equipment and computer readable storage medium

Abstract

The invention discloses a modeling file generation method, electronic equipment and a computer readable storage medium, and relates to the technical field of digital models.The modeling file generation method comprises the steps that target objects in an original building graph are extracted, and the target objects at least comprise wall objects; determining a central axis of each wall object, and extending each central axis to perform closing processing on the adjacent wall objects to generate closed space data; determining each basic primitive of each wall object, extracting attribute quantification information of each basic primitive, and associating the attribute quantification information, each basic primitive and each wall object according to the affiliation relationship to obtain structured data of each wall object; and based on the closed space data and the structured data, generating a target modeling file of the original building corresponding to the original building graph. According to the method, each target object is directly extracted from the original building graph to generate the target modeling file, so that the precision and convenience of building modeling are ensured.

Description

Technical Field

[0001] This application relates to the field of digital modeling technology, and in particular to a method for generating modeling files, an electronic device, and a computer-readable storage medium. Background Technology

[0002] In fields such as Building Information Modeling (BIM) and building energy consumption simulation, rapidly extracting the geometric and attribute information of building components (such as walls, doors, and windows) is crucial for achieving automated modeling. However, existing technologies primarily rely on raster graphics-based plan recognition methods. These methods typically convert CAD (Computer-Aided Design) plans into raster images or scanned documents, which may result in the loss of a significant amount of original building vector information, failing to meet the needs of building modeling.

[0003] The above content is only used to help understand the technical solution of this application and does not represent an admission that the above content is prior art. Summary of the Invention

[0004] The main purpose of this application is to provide a method for generating modeling files, an electronic device, and a computer-readable storage medium, which aims to solve the technical problem that traditional modeling methods are prone to losing the original building vector information and cannot meet the needs of building modeling.

[0005] To achieve the above objectives, this application proposes a method for generating modeling files, the method comprising: Extract each target object from the original building drawing, wherein each target object includes at least a wall object; Determine the centerline of each wall object, and extend each centerline to enclose adjacent wall objects to generate closed space data; The basic graphic elements of each wall object are determined, the attribute quantification information of each basic graphic element is extracted, and the attribute quantification information, each basic graphic element and each wall object are associated according to the attribution relationship to obtain the structured data of each wall object. Based on the enclosed space data and the structured data, a target modeling file corresponding to the original building drawing is generated.

[0006] Optionally, the step of determining the centerline of each wall object and extending each centerline to enclose adjacent wall objects and generate enclosed space data includes: The central axis of each wall object is determined based on the thickness of the walls on both sides of each wall object; Extend each central axis to obtain extended connection elements; The target intersection point is obtained by performing a preset optimization process on the extended connection element; Based on the relationship between the target intersection point and the wall object, the closed space formed by adjacent wall objects is identified, and the closed space data is generated.

[0007] Optionally, the step of extending each central axis includes: For any one of the central axes, determine the angle between the central axis and the adjacent central axes: Based on a preset trigonometric function relationship and the included angle, the wall thickness of the wall object related to the central axis is converted into an extended length, wherein the preset trigonometric function relationship is determined based on the wall type of the wall object to which the central axis belongs; The central axis is extended based on the stated extension length.

[0008] Optionally, the step of performing preset optimization processing on the extended connection element to obtain the target intersection point includes: When the extended connecting element is an extension of an overlapping line segment, the midpoint of the overlapping portion of the extension of the overlapping line segment is taken as the target intersection point. When the extended connecting element is a non-overlapping line segment extension, the endpoint of the non-overlapping line segment extension is taken as the target intersection point; When the extended connection element is the original intersection point, determine whether there are other original intersection points within a preset range around the original intersection point. If so, merge the original intersection points within the preset range around the original intersection point to obtain the target intersection point.

[0009] Optionally, after the step of identifying the enclosed space formed by adjacent wall objects based on the association between the target intersection point and the wall object, the method further includes: From the wall objects, select a first type of wall object and a second type of wall object, wherein the first type of wall object is a wall object that is adjacent to two or more enclosed spaces, and the second type of wall object is an arc-shaped wall object; Determine the first wall break point of the first type of wall object, wherein the first wall break point is the common intersection of the enclosed spaces adjacent to the first type of wall object; Determine the second wall break point of the second type of wall object, wherein the second wall break point is the division point of the polygonization of the second type of wall object; Configure the first wall breakpoint and the second wall breakpoint for the wall objects in the structured data based on the hierarchical relationship.

[0010] Optionally, each target object may also include door and window objects; The step of generating the target modeling file of the original building corresponding to the original building drawing based on the enclosed space data and the structured data includes: Construct the hierarchical framework of the original building corresponding to the original building graphic; Based on the closed space data, each closed space element is generated, and the relationship between each spatial element and the floor-level nodes in the hierarchical framework is established to obtain an intermediate modeling file. The structured data is converted to obtain intermediate structured data; Receive the vertical height parameters of each target object in the original building, and expand the intermediate structured data into each wall geometry based on the height parameters; Add door and window openings to each wall geometry to obtain the target geometric wall, and / or construct the target geometric wall according to the affiliation relationship between the door and window objects and each wall geometry; Associate the spatial elements in the intermediate modeling file with the corresponding target geometric walls, and configure the ground and roof surfaces for the spatial elements in the intermediate modeling file to obtain the target modeling file.

[0011] Optionally, the target modeling file corresponds to a modeling data table, which is obtained by converting the target modeling file; After the step of generating the target modeling file of the original building corresponding to the original building drawing based on the enclosed space data and the structured data, the method further includes: Receive the model adjustment request for the building corresponding to the original building drawing; Based on the model adjustment requirements and the preset first prompt word template, a first target prompt word is generated; The modeling data table is adjusted by the preset large language model guided by the first target prompt word to obtain a new modeling data table; The new modeling data table is converted into a new target modeling file.

[0012] Optionally, the target modeling file is configured with a building simulation operation parameter file, which is used to control the simulation operation of the building model corresponding to the target modeling file; After the step of generating the target modeling file of the original building corresponding to the original building drawing based on the enclosed space data and the structured data, the method further includes: Receive the operational status adjustment request of the building model; Based on the operational status adjustment requirements and the preset second prompt word template, a second target prompt word is generated; Guided by the second target prompt word, the preset large language model is used to adjust the running data text corresponding to the building simulation running parameter file, resulting in new running data text; The new operational data text is converted into a new building simulation operational parameter file.

[0013] In addition, to achieve the above objectives, this application also proposes an electronic device, the device comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, the computer program being configured to implement the steps of the modeling file generation method as described above.

[0014] In addition, to achieve the above objectives, this application also proposes a storage medium, which is a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, it implements the steps of the modeling file generation method described above.

[0015] In addition, to achieve the above objectives, this application also provides a computer program product, which includes a computer program that, when executed by a processor, implements the steps of the modeling file generation method described above.

[0016] One or more technical solutions proposed in this application have at least the following technical effects: In this embodiment, target objects are extracted from the original architectural drawings, including at least wall objects. The central axis of each wall object is determined, and this axis is extended to enclose adjacent wall objects, generating enclosed space data. Basic geometric elements of each wall object are determined, and their attribute quantification information is extracted. The attribute quantification information, basic geometric elements, and wall objects are associated according to their affiliation to obtain structured data for each wall object. Based on the enclosed space data and the structured data, a target modeling file for the original building corresponding to the original architectural drawings is generated. It is understood that compared to traditional modeling methods that convert CAD floor plans into raster images or scanned documents for information recognition, this application directly extracts target objects from the original architectural drawings, determines enclosed space data based on the wall objects within the target objects, and extracts the attribute quantification information of the basic geometric elements of the wall objects to generate the target modeling file for the original building. This avoids the problem of losing original architectural information caused by graphic conversion, ensuring the accuracy and convenience of architectural modeling. Attached Figure Description

[0017] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0018] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0019] Figure 1 This is a flowchart illustrating the first embodiment of the modeling file generation method in this application; Figure 2 A schematic diagram of the scene in which the target object is extracted using the modeling file generation method of this application; Figure 3 This is a schematic diagram of the centerline adjustment in the modeling file generation method of this application; Figure 4 This is a schematic diagram of the first optimized scenario in the modeling file generation method of this application; Figure 5 This is a schematic diagram of the second optimized scenario in the modeling file generation method of this application; Figure 6 This is a schematic diagram of the third optimized scenario in the modeling file generation method of this application; Figure 7 A flowchart illustrating the data supplementation process in the method for generating modeling documents for this application; Figure 8 This is a schematic diagram of the device structure of the hardware operating environment involved in the modeling file generation method in this application embodiment.

[0020] The purpose, features, and advantages of this application will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0021] It should be understood that the specific embodiments described herein are merely illustrative of the technical solutions of this application and are not intended to limit this application.

[0022] To better understand the technical solution of this application, a detailed description will be provided below in conjunction with the accompanying drawings and specific implementation methods.

[0023] In fields such as Building Information Modeling (BIM) and building energy consumption simulation, rapidly extracting the geometric and attribute information of building components (such as walls, doors, and windows) is crucial for achieving automated modeling. However, existing technologies primarily rely on raster graphics-based plan recognition methods. These methods typically convert CAD (Computer-Aided Design) plans into raster images or scanned documents, which may result in the loss of a significant amount of original building vector information, failing to meet the needs of building modeling.

[0024] The main solution of this application embodiment is as follows: extract each target object from the original building drawing, wherein each target object includes at least a wall object; determine the central axis of each wall object, extend each central axis to enclose adjacent wall objects to generate enclosed space data; determine each basic graphic element of each wall object, extract the attribute quantification information of each basic graphic element, and associate the attribute quantification information, each basic graphic element, and each wall object according to the attribution relationship to obtain the structured data of each wall object; and generate the target modeling file of the original building corresponding to the original building drawing based on the enclosed space data and the structured data.

[0025] Compared to traditional modeling methods that convert CAD floor plans into raster images or scanned documents for information recognition, this application directly extracts target objects from the original architectural drawings. Based on wall objects within these target objects, it determines enclosed space data and extracts the attribute quantification information of the basic graphic elements of the wall objects to generate the original building's target modeling file. This avoids the loss of original architectural information caused by graphic conversion, ensuring both accuracy and convenience in architectural modeling.

[0026] It should be noted that the execution subject of this embodiment can be a computing service device with data processing, network communication and program running functions, such as a cloud platform, computer, mobile phone, etc., or an electronic device capable of realizing the above functions.

[0027] Based on the above description, this application provides a method for generating modeling files, referring to... Figure 1 This is a flowchart illustrating the first embodiment of the modeling file generation method of this application.

[0028] In this embodiment, the modeling file generation method includes steps S10 to S40: Step S10: Extract each target object from the original building drawing, wherein each target object includes at least a wall object; It should be noted that the above-described method for generating modeling files can be applied to cloud platforms, computers, and mobile smart terminals. The original architectural drawings mentioned above can be original architectural design drawings, such as common CAD floor plans.

[0029] For example, target objects can be extracted from the original architectural drawings. These target objects may include wall objects, door and window objects, etc. It is understood that if the original architectural drawings are CAD floor plans, target objects can be extracted using the name characteristics of the layers within the drawings. For instance, based on layer name characteristics, key layers requiring protection can be automatically identified and locked. Layers containing features such as "WALL" or "WIN" can be locked as key images. Visible objects on the remaining unlocked layers in the original architectural drawings can be batch-cleaned, and finally, all layers can be unlocked, thus achieving the extraction of each target object. This selective protection mechanism ensures that target objects are unaffected while effectively removing interfering elements from irrelevant layers, creating a clean data environment for subsequent modeling file generation. For example, refer to... Figure 2 Extract a schematic diagram for the target object. Figure 2 After extracting (filtering) the original architectural graphic on the left, a layer containing only the target object is obtained (i.e., the image on the right).

[0030] Step S20: Determine the centerline of each wall object, extend each centerline to enclose adjacent wall objects and generate closed space data; For example, the original architectural image may implicitly contain the central axes of each wall object. Optionally, in this state, the central axes can be directly determined based on the original architectural image, and the central axes can represent the position and orientation of the wall objects. It should be noted that, under normal circumstances, buildings are mostly composed of enclosed rooms (not considering openings such as doors and windows). However, the central axes of the walls determined in the above steps may not necessarily form a complete enclosed space. Therefore, the determined central axes are extended to enclose adjacent wall objects, generating enclosed space data. For example, after extending the central axes, adjacent central axes can intersect to create intersection points. Based on the intersection points, it can be determined which adjacent wall objects can form enclosed spaces, thus obtaining enclosed space data, such as which wall objects can form an enclosed room (or space).

[0031] Step S30: Determine the basic graphic elements of each wall object, extract the attribute quantification information of each basic graphic element, and associate the attribute quantification information, each basic graphic element, and each wall object according to the attribution relationship to obtain the structured data of each wall object. For example, the basic graphic elements of each wall object are determined. These basic graphic elements refer to the basic lines that make up the wall object. It should be noted that wall objects can include two types: block walls and linear walls. Block walls typically refer to complete walls defined and encapsulated in design software, such as Tianzheng walls. Linear walls, on the other hand, are walls composed of basic lines that are not encapsulated or defined; therefore, the basic graphic elements of linear walls can be directly identified. However, block walls, being complete walls defined and encapsulated, may not be directly recognized by the original CAD design software. In this case, the wall object needs to be decomposed. Optionally, the EXPLODE command can be executed on each selected block wall to decompose it from a complex, custom strong object into basic graphic elements native to CAD (such as lines and arcs). Optionally, to ensure the purity of the data source, after decomposition, all newly generated basic graphic elements of type "line" and "arc" are traversed and filtered to remove other irrelevant elements, ensuring the purity of the data source.

[0032] Furthermore, multi-dimensional data extraction is performed on each basic graphic element. For each basic graphic element, its attribute quantification information can be extracted, which can include geometric and non-geometric attributes. Regarding geometric attributes, if the basic graphic element is a straight line, the coordinates of its start point, end point, and midpoint can be extracted; if the basic graphic element is an arc, the start point, end point, center, radius, and the start and end angles converted to angle values ​​can be extracted. For non-geometric attributes, the layer where the basic graphic element resides, its color index, and a unique entity handle (which serves as the identifier for the basic graphic element) can be obtained.

[0033] Furthermore, based on attribution relationships, data association and structured storage are completed. Optionally, a unique number can be assigned to each wall object. For any given wall object, it can be associated with all its decomposed basic elements. Then, the geometric and non-geometric attributes of each basic element are assembled into a structured record, i.e., the structured data of each wall object. Through the above steps, block-type walls that are difficult to access directly can be transformed into complete structured data containing counts, types, layers, colors, entity handles, start coordinates, end coordinates, center / circle center coordinates, radius, start angle, and end angle.

[0034] Step S40: Based on the closed space data and structured data, generate the target modeling file of the original building corresponding to the original building drawing.

[0035] For example, enclosed space data and structured data are integrated to generate a target modeling file corresponding to the original building drawings. This target modeling file can be used to generate a digital building model of the original building, such as by inputting the target modeling file into BIM modeling software to render and generate a digital building model. Regarding the process of integrating enclosed space data and structured data, it can be understood that the original building can consist of multiple enclosed spaces, and a single enclosed space can consist of multiple wall objects. The structured data includes quantified data for each wall object. Accordingly, the target modeling file can be constructed according to the hierarchical framework of building—enclosed space—wall object—attribute quantification information. Furthermore, it should be noted that CAD design drawings (i.e., the original building drawings) are usually two-dimensional drawings. Therefore, information about the building's vertical direction cannot be obtained from the original building drawings. This information (including the height of walls, doors, and windows) can be supplemented by relevant personnel, and then added to the attribute quantification information.

[0036] In this embodiment, target objects are extracted from the original architectural drawings, each target object including at least wall objects; the central axis of each wall object is determined, and each central axis is extended to enclose adjacent wall objects, generating enclosed space data; the basic graphic elements of each wall object are determined, the attribute quantification information of each basic graphic element is extracted, and the attribute quantification information, each basic graphic element, and each wall object are associated according to their affiliation to obtain the structured data of each wall object; based on the enclosed space data and the structured data, a target modeling file of the original building corresponding to the original architectural drawings is generated. It is understood that, compared to traditional modeling schemes that convert CAD floor plans into raster images or scanned documents for information recognition, this application directly extracts target objects from the original architectural drawings, determines enclosed space data based on the wall objects within the target objects, and extracts the attribute quantification information of the basic graphic elements of the wall objects to generate the target modeling file of the original building. This avoids the problem of loss of original architectural information caused by graphic conversion, ensuring the accuracy and convenience of architectural modeling.

[0037] In one feasible implementation, the steps of determining the centerline of each wall object and extending each centerline to enclose adjacent wall objects and generate enclosed space data include steps S21 to S24: Step S21: Determine the centerline of each wall object based on the thickness of the walls on both sides of each wall object; Step S22: Extend each centerline to obtain extended connection elements; Step S23: Perform preset optimization processing on the extended connection elements to obtain the target intersection point; Step S24: Based on the relationship between the target intersection point and the wall object, identify the enclosed space formed by adjacent wall objects and generate enclosed space data.

[0038] It should be noted that in practical applications, the central axis of the wall objects included in the original architectural drawing may not be standardized. For example, the wall thicknesses on both sides of the central axis of a wall object may be different, meaning the central axis is not located in the middle of the wall object. Therefore, judging the position of the wall object based on the central axis in this case is inaccurate.

[0039] For example, the central axis of each wall object can be determined based on the wall thickness on both sides. For instance, the wall thickness attributes on both sides of the wall object can be identified from the original architectural drawings, and the average of the wall thicknesses on both sides can be calculated to obtain the half-wall thickness. The central axis located in the middle of the wall object can then be determined based on this half-wall thickness. For example, refer to... Figure 3 This is a schematic diagram for adjusting the centerline. For wall objects whose centerline is deviated, the centerline can be adjusted from the deviated position to the center position by summing and averaging the thickness of half the wall.

[0040] Furthermore, each central axis is extended. These extended central axes can intersect or overlap to obtain the aforementioned extended connecting elements. That is, the extended connecting elements can be intersections or overlapping line segments formed by the extension of the central axes. The extended connecting elements are then subjected to preset optimization processing to obtain target intersections. For example, target intersections can be configured for overlapping line segments, and multiple intersections that are close in distance can be merged into a single target intersection. Based on the association between the target intersections and wall objects, adjacent wall objects forming closed spaces are identified, thereby generating closed space data. This closed space data can record which wall objects constitute each closed space. For example, the smallest loop formed by the target intersections and central axes can be extracted. The adjacent wall objects corresponding to the central axes forming the smallest loop are considered as potentially forming closed spaces. For instance, in a typical architectural plan, a room consists of four walls; correspondingly, the central axes of the four walls and the target intersections formed by connecting them can constitute a loop. Optionally, an association mapping table between target intersections and wall objects can be established, and the endpoint coordinates can be updated using a farthest point matching algorithm to achieve intelligent wall closure.

[0041] In one feasible implementation, the step of extending each central axis includes steps S221 to S223: Step S221: For any one of the central axes, determine the angle between the central axis and its adjacent central axes. Step S222: Based on the preset trigonometric function relationship and the included angle, the wall thickness of the wall object related to the central axis is converted into the extended length. The preset trigonometric function relationship is determined based on the wall type of the wall object to which the central axis belongs. Step S223: Extend the central axis based on the extension length.

[0042] It should be noted that since the processing methods for each central axis are similar, this embodiment will use one of the central axes as an example for explanation.

[0043] For example, for any one of the central axes, the angle between that central axis and its adjacent central axes can be extracted from the original building drawing. Then, based on a preset trigonometric function relationship and this angle, the wall thickness of the wall object related to that central axis is converted into an extended length. For example, the related wall object can be the wall object belonging to that central axis or an adjacent wall object. Optionally, the preset trigonometric function relationship can be a tangent function, a cosine function, etc. Specifically, the preset trigonometric function relationship is determined according to the wall type of the wall object belonging to that central axis. For example, wall types include block walls and linear walls. Correspondingly, for linear walls, the preset trigonometric function relationship can be a tangent function, and for block walls, it can be a cosine function. The calculation method for the extended length is as follows: For cases where the wall type is linear: ; In the formula, The wall thickness of the relevant wall object (e.g., the wall thickness of the wall object belonging to the central axis). To extend the length, It is the angle between the central axis and the adjacent central axis.

[0044] For cases where the wall type is block wall: ; In the formula, The wall thickness of the relevant wall object (e.g., the wall thickness of the wall object adjacent to the center axis). To extend the length, It is the angle between the central axis and the adjacent central axis.

[0045] Accordingly, once the extension length is determined, the central axis can be extended accordingly.

[0046] In one feasible implementation, the step of performing a preset optimization process on the extended connection element to obtain the target intersection point includes steps S231 to S233: Step S231: When the extended connecting element is an extension of an overlapping line segment, the midpoint of the overlapping part of the extension of the overlapping line segment is taken as the target intersection point. Step S232: When the extended connecting element is a non-overlapping line segment extension, the endpoint of the non-overlapping line segment extension is taken as the target intersection point. Step S233: When the extended connection element is the original intersection point, determine whether there are other original intersection points within a preset range around the original intersection point. If so, merge the original intersection points within the preset range around the original intersection point to obtain the target intersection point.

[0047] For example, when the central axes of two or more wall objects extend to form overlapping line segments, the system first detects the overlapping area of ​​these line segments. By calculating the coordinates of the start and end points of the overlapping portion, its geometric midpoint is determined. For instance, in CAD vector graphics, overlapping line segments may partially coincide due to differences in wall thickness or angle. The system uses geometric algorithms (such as line segment intersection detection and midpoint calculation) to automatically identify the overlapping area and set the midpoint coordinates as the target intersection point. (See reference...) Figure 4 In the diagram, line segments B and C overlap. After optimization, the midpoint of the overlapping portion of the two line segments (such as point X) can be used as the target intersection point. This process requires no manual intervention, ensuring the objectivity of the intersection point location.

[0048] Understandably, overlapping line segments may be caused by minor deviations at wall connections, design irregularities, or excessive line extension, leading to non-unique or offset intersection points in traditional methods, thus affecting the accuracy of enclosed space identification. This step eliminates the ambiguity caused by overlap by taking the midpoint as the intersection point, avoiding errors in space closure due to improper intersection point selection.

[0049] For example, when the extended connection element is a non-overlapping line segment extension, the system directly extracts the endpoint coordinates of the line segments in the extended connection element as the target intersection point. For instance, if only the endpoints of the extended central axis of a wall object meet (such as a T-shaped or L-shaped connection), the system identifies the connection points through an endpoint coordinate matching algorithm and sets the endpoints as the intersection points. As shown in Figure 5, line segment A is the extended portion of the central axis (i.e., the extended connection element), while a1 and a2 are the endpoints of the extended lines, which can be used as target intersection points. This process is based on the geometric properties of vector data, ensuring the uniqueness and accuracy of endpoint selection.

[0050] For example, when the extended connecting element itself is an original intersection point (such as an intersection point formed before or during the extension of the central axis), the system first sets a preset range (e.g., a tolerance band based on pixel distance or actual size, such as a 5mm radius) centered on this intersection point. A spatial query algorithm (such as range search or cluster analysis) is used to detect whether other original intersection points exist within this range. If they exist, the system merges these intersection points, for example, by calculating their geometric center or weighted average position as the new target intersection point. The merging process may employ a clustering algorithm (such as K-means) or a simple averaging method to ensure that the merged intersection point represents the overall position of multiple close points. For example, refer to... Figure 6 , Figure 6 Before the intersection point is merged, there are three adjacent original intersection points. Accordingly, these three adjacent original intersection points are merged into a single target intersection point.

[0051] Understandably, in complex architectural drawings, original intersection points may be densely distributed due to design details, measurement errors, or repetitive data processing, leading to intersection point redundancy and model clutter. For example, multiple close intersection points may represent the same connection point. Therefore, this step, through merging, can eliminate data redundancy and noise.

[0052] The steps S231 to S233 described above together constitute an optimization processing chain for extending the connection elements. By distinguishing between overlapping, non-overlapping, and original intersection point cases, geometric calculations and spatial analysis methods are used to accurately generate the target intersection points. These steps solve the technical problems of inaccurate intersection point positioning, data redundancy, and inconsistent connections in architectural vector graphics processing, achieving the technical effects of improving the accuracy of modeling files, optimizing computational efficiency, and enhancing model robustness. This implementation method reflects the innovation of this application in the field of digital modeling technology, ensuring high-fidelity conversion from original architectural drawings to target modeling files.

[0053] In one feasible implementation, after identifying the enclosed space formed by adjacent wall objects based on the association between the target intersection point and the wall object, the method further includes steps S251 to S254: Step S251: Select the first type of wall object and the second type of wall object from the wall objects. The first type of wall object is a wall object that is adjacent to two or more enclosed spaces, and the second type of wall object is an arc-shaped wall object. Step S252: Determine the first wall break point of the first type of wall object, wherein the first wall break point is the common intersection of the enclosed spaces adjacent to the first type of wall object; Step S253: Determine the second wall break point of the second type of wall object, wherein the second wall break point is the division point of the polygonization of the second type of wall object; Step S254: Configure the first wall breakpoint and the second wall breakpoint for the wall objects in the structured data based on the hierarchical relationship.

[0054] It should be noted that the target modeling file generated in this embodiment can be used to construct a 3D model of the building. This 3D model is then used for building energy simulation, and the relevant simulation software has certain requirements for the model. Therefore, this embodiment will break the walls of the building model to meet the data requirements of the simulation software.

[0055] For example, based on the adjacency relationships between wall objects and spaces in enclosed space data, as well as the geometric attributes of the wall objects, automatic classification and filtering are performed. In this scenario, the classification mainly includes two categories: Category 1 wall objects and Category 2 wall objects. For Category 1 wall objects, spatial topology analysis can be used to identify walls adjacent to two or more enclosed spaces. For instance, by traversing each wall object and checking the number of its associated enclosed spaces, if the number is greater than 2 (or greater than or equal to 3), it is marked as a Category 1 wall object. For Category 2 wall objects, the system uses geometric feature recognition to detect whether the basic primitives of the wall object contain arc elements; if so, it is marked as a Category 2 wall object. This process uses an automated algorithm, requiring no manual intervention, ensuring the objectivity and efficiency of the classification.

[0056] For example, after filtering the two types of walls, for each first-type wall object, the common intersection points between all adjacent enclosed spaces can be extracted. Through spatial geometric calculations, the intersection points of these enclosed spaces on the wall object are identified. For example, at the junction of T-shaped or cross-shaped walls, this is identified as the first wall break point. Specifically, a line segment intersection detection algorithm can be used, combined with the geometric data of the wall object, to automatically calculate the precise coordinates of the break point. The first-type wall object serves as a shared boundary for multiple spaces; without segmentation, it may lead to data conflicts or attribute confusion during model adjustments or spatial analysis. This step achieves logical segmentation of the wall by accurately locating the break point. It is understandable that the first-type break point ensures the independence and operability of shared walls across multiple spaces. For example, in a residential unit, a common wall is divided into different segments at the break point, allowing each space to independently configure attributes, improving the model's flexibility and accuracy, and providing a reliable foundation for subsequent spatial management and simulation analysis.

[0057] For example, for the second type of wall object, polygonization can be used to convert the curved wall into a series of straight line segments, and the dividing points can be determined as the break points of the second wall. Specifically, by calculating the chord length of the arc and a preset precision threshold (such as a dividing point every 10 degrees), the dividing points are set uniformly or adaptively along the arc. For example, for a 90-degree curved wall with a radius of 5 meters, the system may set the dividing points at 5-degree intervals, generating 18 straight line segments and their corresponding break points.

[0058] For example, after identifying wall breakpoints, the first and second wall breakpoints can be integrated into structured data based on the dependency relationship between the wall objects and the breakpoints. Specifically, a unique identifier is assigned to each breakpoint, and an association is established with the corresponding wall object. For instance, a data mapping table records the coordinates, type (first or second type), and ID of the wall object to which the breakpoint belongs. This process ensures seamless integration of breakpoint data with the geometric and attribute information of the wall objects.

[0059] Understandably, steps S251 to S254 together constitute a refined processing chain for special wall objects. Through classification and identification, breakpoint determination, and data configuration, the challenges of handling shared walls and curved walls in building models are solved. These steps achieve structural optimization and geometric accuracy of the modeling data, improving the applicability and maintainability of the BIM model in complex scenarios. This implementation reflects the innovation of this application in the field of digital modeling technology, ensuring high-quality conversion from original building drawings to target modeling files.

[0060] In one feasible implementation, each target object also includes door and window objects; The steps for generating the target modeling file of the original building corresponding to the original building drawing based on closed space data and structured data include steps S41 to S46: Step S41: Construct the hierarchical framework of the original building corresponding to the original building graphic; Step S42: Generate spatial elements based on the closed spaces included in the closed space data, and establish the association between each spatial element and the floor-level nodes in the hierarchical framework to obtain the intermediate modeling file. Step S43: Perform unit conversion on the structured data to obtain intermediate structured data; Step S44: Receive the vertical height parameters of each target object in the original building, and expand the intermediate structured data into the geometry of each wall based on the height parameters; Step S45: Add door and window openings to each wall geometry to obtain the target geometric wall, and / or construct the target geometric wall according to the ownership relationship between the door and window objects and each wall geometry; Step S46: Associate the spatial elements in the intermediate modeling file with the corresponding target geometric walls, and configure the ground and roof surfaces for the spatial elements in the intermediate modeling file to obtain the target modeling file.

[0061] For example, a hierarchical building information framework can be automatically constructed based on the overall structure of the original building drawings. Optionally, a root element of the hierarchical framework can be created first, which is used to measure the building model, such as temperature units (e.g., degrees Celsius), length units (e.g., meters), etc. Then, standard hierarchical nodes of the hierarchical framework are built according to the structure of "Campus→Building→BuildingStorey". For example, in a gbXML (Green Building XML) document, under the root element gbXML, the following nodes are created sequentially... <campus> 、 <building>and <buildingstorey>Nodes at different levels.

[0062] For example, iterate through each enclosed space in the enclosed space data and convert it into an independent space element (such as in gbXML). <space>(Elements). Assign a unique ID to each spatial element and establish associations based on the spatial location and the containment relationship with floor nodes. For example, by matching the spatial polygon boundary with the floor plan, spatial elements are assigned to the corresponding floor nodes, generating intermediate modeling files (such as preliminary gbXML documents).

[0063] For example, the geometric units of structured data (such as millimeters in the original CAD) can be identified and converted into standard units in the target modeling file (such as meters in the root element of gbXML). For instance, the coordinates of the start and end points of a wall line can be converted from millimeters to meters using a batch unit conversion algorithm. Simultaneously, non-geometric attributes (such as layer information) are standardized to generate intermediate structured data.

[0064] Additionally, it should be noted that since original architectural drawings are typically two-dimensional CAD designs, it is difficult to extract vertical information (such as the height of parts of the building or information along the z-axis) from two-dimensional drawings in practical applications. Therefore, this information is usually input from external sources, such as by the user.

[0065] For example, the system receives vertical parameters input by the user, such as floor height and wall height. Based on these parameters, the two-dimensional wall line data is expanded into a three-dimensional wall geometry. For instance, the coordinates of the wall line's start and end points are expanded from two-dimensional (X,Y) to three-dimensional (X,Y,Z). By assigning Z-coordinate values ​​(e.g., Z=0 to Z=floor height), a three-dimensional geometry of the four points on the wall is generated. Simultaneously, normal vector calculations can be used to ensure the correct surface orientation. In essence, this three-dimensional expansion achieves the three-dimensional geometric reconstruction of the wall. For example, in a residential model, two-dimensional wall lines are expanded into three-dimensional walls, ensuring the model's realistic representation in three-dimensional space and laying the foundation for subsequent opening processing and simulation analysis.

[0066] It should be noted that the target objects extracted from the original building image may also include door and window objects, and the extraction method is similar to that of wall objects, so it will not be described in detail here.

[0067] For example, openings are precisely added to the wall geometry based on the relationship between door / window objects and walls. First, precise positioning is achieved using the wall ID to which the door / window belongs. Then, opening areas are generated on the wall geometry using planar projection and boundary distance calculations (such as windowsill height and door / window dimensions). For wall objects that are curtain walls, window openings with boundary distances can be added directly to obtain the target geometric wall. For independent doors and windows, such as identified wall objects, Containment verification can be used to ensure that the door / window openings are completely embedded within the wall boundary to obtain the target geometric wall. At the same time, geometric consistency can be ensured by unifying the normal vector directions of wall objects and door / window objects.

[0068] Furthermore, spatial elements are associated with their corresponding target geometric walls via IDs to ensure the integrity of the spatial envelope. Subsequently, ground and roof surfaces are generated for each spatial element: based on the boundary points of the spatial polygons, a floor surface with Z=0 and a roof surface with Z=story height are created after simplification using the Douglas-Peucker algorithm. Finally, all elements are integrated to output a complete target modeling file (e.g., a file conforming to the gbXML7.03 standard).

[0069] Reference Figure 7 This is a schematic diagram illustrating the data supplementation process in this embodiment. For example, Figure 7 As shown, the 3D data supplemented by the user can include wall height, windowsill height, window height, and door height. Correspondingly, door, window, and wall data are reconstructed based on this height data, forming the basic data for 3D reconstruction. Then, the basic data for 3D reconstruction is analyzed and output as a gbXML file in gbXML format. This gbXML file can generate a 3D building model or be converted into a modeling data table, which is used for subsequent model adjustments.

[0070] Understandably, steps S41 to S46 together constitute a complete conversion chain from two-dimensional graphics to three-dimensional modeling files. Through hierarchical construction, spatial association, unit conversion, geometric expansion, opening addition, and enclosure closure, they solve problems such as structural deficiencies, geometric incompleteness, and standard incompatibility in three-dimensional modeling of two-dimensional data. These steps achieve high-precision generation and standardized output of modeling files, improving the reliability and efficiency of BIM models in advanced applications such as energy simulation.

[0071] In summary, this embodiment establishes a complete technical chain from 2D CAD drawings to 3D energy models. Through key technologies such as wall (Tianzheng wall) analysis, spatial topology reconstruction, and component association mapping, it achieves accurate extraction and automated reconstruction of core building elements. Compared with traditional manual modeling, this method improves 3D reconstruction efficiency by several orders of magnitude while ensuring a 99.77% recognition accuracy for walls, 99.44% for openings, and 100% for spaces, providing reliable technical support for building digitization.

[0072] In one feasible implementation, the target modeling file corresponds to a modeling data table, which is obtained by converting the target modeling file; After generating the target modeling file of the original building corresponding to the original building drawing based on the closed space data and structured data, the method also includes steps S51 to S54: Step S51: Receive the model adjustment request for the building corresponding to the original building drawing; Step S52: Generate the first target prompt word based on the model adjustment requirements and the preset first prompt word template; Step S53: The preset large language model is guided by the first target prompt word to adjust the modeling data table and obtain a new modeling data table; Step S54: Convert the new modeling data table into a new target modeling file.

[0073] It should be noted that, to further lower the barrier to modeling and improve its convenience, this implementation proposes a method for adjusting the model using natural language. Additionally, it should be noted that the aforementioned target modeling file also corresponds to a modeling data table, which is derived from the target modeling file. For example, the modeling data table can be imported from relevant software (such as simulation software). For example, a pre-set human-computer interaction interface can receive model adjustment requests described by users in natural language. For instance, a user could input "move the east wall of the conference room on the third floor 500 mm eastward" or "convert the conference room into an open-plan office area." Optionally, a natural language processing module can perform intent recognition and key parameter extraction on the input statement, converting it into structured adjustment instructions. This process does not require users to have professional modeling software operation knowledge. Understandably, the natural language interface lowers the technical barrier to model adjustment and enables efficient input of requirements.

[0074] For example, the aforementioned first prompt word template can be a pre-built structured text framework specifically designed to guide a large language model in performing architectural model editing tasks. Optionally, the user-input natural language text, or the structured adjustment instructions parsed in step S51, can be concatenated with the preset template to generate the final first target prompt word. For example, the content of the first prompt word template is as follows: You are a Building Energy Model (BEM) expert assistant. Your task is to convert user-expressed modification instructions in natural language into a strictly formatted JSON format.

[0075] Important information: The highest floor in this building is the {max floor} floor.

[0076] Object of operation: 1. This building.

[0077] 2. Second floor (the second floor of the building) 3. Space (space 31).

[0078] Operation types: 1. Create window / window size; 2. Create shadow; 3. Remove outer window; 4. Remove shadow effect; 5. Change the ratio of window to wall; 6. Modify construction.

[0079] Output requirements: The output should be presented in plain JSON format and must not contain any other text.

[0080] Make sure all values ​​have the correct units (e.g., meters, watts, etc.).

[0081] The parameter names will be output strictly according to the following example.

[0082] Multi-story buildings employ a layout format with multiple spaces.

[0083] For multiple operations, each operation is output as a separate JSON object on a new line.

[0084] Multi-story buildings or multiple spaces can be handled separately as multiple individual floors or multiple individual spaces.

[0085] When breaking down a multi-story building or space into multiple operations, it is prohibited to include phrases such as "Space 31", "Space 32", "Building Floor 1", or "Building Floor 2" in the "Operation Object".

[0086] Surface type: Exterior wall; Roof (the ceiling surface of all floors); Interior walls; Non-active door; Fixed windows; Underground slab (floor surface of non-ground floors); Homogeneous panel (bottom surface); Example: {"Operation Type":"Create Window","Parameters":{"Operation Object":"Building","Window Height in meters":1.2","Window Sill Height in meters":0.9","Window Width in meters":1.2}}; {"Operation Type":"Create Shading Device","Parameters":{"Operation Object":"Second Floor of Building","Shading Device Width in Meters": 0.5}}; {"Operation Type":"Delete External Window", "Parameters":{"Operation Target":"Building Fifth Floor"}}; {"Operation Type":"Delete Shading Device", "Parameters":{"Operation Target":"Tenth Floor of Building"}}; {"Operation Type":"Change the ratio of windows to walls","Parameters": {{"Operation Object":"Second Floor of Building","Ratio of Windows to Walls": 0.4}}; {"Operation Type":"Change Structure"Parameters":{"Operation Object":"Space 30","Surface Type":{"Exterior Wall","Roof"},"Structure ID":"Structure 1","Structure Name":"Structure 1""Layer":[{"Layer ID":"Layer 1","Layer Name":"Layer 1","Material":{"Material ID":"Material 1","Material Name":"Material 1","Thickness in meters":0.04,"Thermal Conductivity in Watts / meter Kelvin":0.7,"Density in kg_m3":1858,"Specific Heat in J_kgK":837,"Roughness":"Smooth","External Infrared Reflectance":0.1"Internal Infrared Reflectance":0.1","External Solar Reflectance":0.2","Internal Solar Reflectance":0.1" .2, "External visible light reflectance":0.15, "Internal visible light reflectance":0.15}}, {Layer ID":"Layer 2", "Layer Name":"Layer 2", "Material":{"Material ID":"Material 2", "Material Name", "Material 2", "Thickness_m":0.06, "Thermal conductivity_w_mk:0.035,"Density_kg_m3:35, "Specific heat_j_kgk":1400,"Roughness":"Medium roughness", "Infrared reflectance":0.2,"Internal infrared reflectance":0.2,"External solar reflectance":0.3,"Internal solar reflectance":0.3,"External visible light reflectance":0.25,"Internal visible light reflectance":0.25}}]} User Tip: (user imput)

[0087] Please confirm the target object multiple times.

[0088] Please follow the instructions above to generate formatted JSON output, with each operation on a separate line.

[0089] In practical applications, those skilled in the art can also refer to the above examples to set up templates, so the specific template content is not limited here.

[0090] Understandably, this step, through a pre-set professional template, constrains user requirements within an executable and structured framework, ensuring the accuracy and operability of the instructions.

[0091] Furthermore, the first target prompt is input into the preset large language model. Guided by the prompt, the large language model understands the specific operations required on the modeling data table (such as a structured JSON or Excel spreadsheet). Accordingly, the large model performs the corresponding operations to adjust the modeling data table, and then outputs a compliant JSON object describing the adjustments. For example, the large model can modify the size parameters or position coordinates of a target object in the modeling data table according to the adjustment requirements, thereby obtaining a new modeling data table.

[0092] Furthermore, after obtaining the new modeling data table output in step S53 (i.e., the updated structured data, such as JSON or Excel), a standardized data converter is invoked to re-convert and encapsulate the data table into the target modeling file format (such as gbXML, IFC, etc.).

[0093] Understandably, steps S51 to S54 collectively construct an intelligent architectural model editing system based on natural language interaction and a large-scale language model. This system, through a closed-loop process of "requirement reception → prompt word generation → guiding LLM modification of modeling data tables → target model file regeneration," solves the technical challenges of traditional model editing methods, which are highly specialized, inefficient, and prone to errors. This method lowers the barrier to model modification operations through a large language model while ensuring high accuracy and topological consistency in model modifications, significantly improving the intelligence level and iteration speed of the architectural design and simulation analysis process.

[0094] In one feasible implementation, the target modeling file is configured with a building simulation operation parameter file, which is used to control the simulation operation of the building model corresponding to the target modeling file; After generating the target modeling file of the original building corresponding to the original building drawing based on the closed space data and structured data, the method also includes steps S61 to S64: Step S61: Receive the request for adjusting the running status of the building model; Step S62: Generate a second target prompt word based on the operational status adjustment requirements and the preset second prompt word template; Step S63: Guide the preset large language model with the second target prompt word to adjust the running data text corresponding to the building simulation running parameter file to obtain new running data text; Step S64: Convert the new running data text into a new building simulation running parameter file.

[0095] It should be noted that, in this embodiment, in addition to modifying the building model using natural language, the operating parameters of the building model during the simulation process can also be adjusted using natural language. Correspondingly, the target modeling file is configured with a building simulation operating parameter file, such as an OSM (OpenStreetMap) file. The building simulation operating parameter file can control the simulation operation of the building model corresponding to the target modeling file, such as the operation of the air conditioning in the building model.

[0096] For example, the system can also receive user adjustment requests for the simulated operation of a building model, described in natural language, through a human-computer interaction interface. These requests typically involve modifying input parameters for building energy consumption simulations (such as those using EnergyPlus software). For instance, a user might input "adjust the air conditioning setpoint temperature in the office area from 24℃ to 26℃" or "change the building's staff work schedule from 'standard office' to '24-hour operation'." The system parses the input using a natural language processing module, identifying the core intent (e.g., "modify setpoint temperature") and key parameters (e.g., "26℃," "office area"), and converts them into structured adjustment instructions. A preset second prompt template is invoked, which guides the large language model in understanding and modifying the simulation parameters. This template integrates the user's adjustment requests, knowledge of the target simulation software's data structure, and strict output format requirements. For example: "You are a building energy consumption simulation expert. Please modify the provided operational data text according to the user's adjustment requests. Your output must be a standard txt text object, precisely describing the object type, object identifier, field names, and new values ​​to be modified." The user's input of the running status adjustment requirements and the preset second prompt word template are combined to form the final second target prompt word, which is then input into the large language model.

[0097] Furthermore, the generated second target prompt is input into a preset large language model. Under the strict constraints of the prompt, the large language model understands the semantics of the adjustment instruction and accurately locates the specific paragraphs, objects, and fields in the runtime data text (such as txt text content) that need to be modified. Subsequently, the large language model outputs a structured new runtime data text that conforms to the preset template requirements. Similarly, the new runtime data text is then converted into a new building simulation runtime parameter file, and the new building simulation runtime parameter file is re-imported into the corresponding simulation software, thereby realizing the adjustment of the building's operating status.

[0098] Understandably, steps S61 to S64 above collectively construct an intelligent adjustment system for building simulation operation parameters based on natural language. This system, through a closed-loop process of "requirement reception → prompt word generation → LLM-guided precise text modification → parameter file regeneration," solves the core technical challenges of traditional parameter adjustment methods, which are characterized by high professional requirements, cumbersome operation, and susceptibility to errors. This method combines the natural language understanding capabilities of large language models with domain expertise and the reliability of deterministic procedures, significantly improving operational efficiency while ensuring the accuracy of parameter modifications and the validity of simulation files, thus significantly advancing the intelligentization of building energy consumption simulation.

[0099] In summary, this application implements a natural language-based geometric parameter editing function. It supports semantic operations for common renovation scenarios, transforming the highly specialized and complex BEM geometric editing into intuitive natural language interaction. This allows even non-professionals to perform precise model adjustments, significantly improving the design efficiency and technical accessibility of building renovation schemes. Addressing the complexity of BEM operational parameter settings, this application employs a three-layer processing mechanism: time decomposition reconstruction, spatial topology association, and natural language conversion. By intelligently associating operational data editing with the geometric topology, it achieves precise mapping and dynamic adjustment of the building's operational status, solving the technical problem of the disconnect between geometric models and operational parameters in traditional methods, and providing a complete solution for refined simulation of building energy consumption.

[0100] The following is for reference. Figure 8 The diagram illustrates a structural schematic suitable for implementing the electronic device in the embodiments of this application. The electronic device in the embodiments of this application may include, but is not limited to, mobile terminals such as computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Description), PMPs (Portable Media Players), in-vehicle terminals (e.g., in-vehicle navigation terminals), and fixed terminals such as computers. Figure 8 The electronic device shown is merely an example and should not impose any limitation on the functionality and scope of use of the embodiments of this application.

[0101] like Figure 8 As shown, the electronic device may include a processing unit 1001 (e.g., a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 1002 or a program loaded from a storage device 1003 into a random access memory (RAM) 1004. The RAM 1004 also stores various programs and data required for the operation of the electronic device. The processing unit 1001, ROM 1002, and RAM 1004 are interconnected via a bus 1005. An 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 touchscreen, touchpad, keyboard, mouse, image sensor, microphone, accelerometer, gyroscope, etc.; output devices 1008 including, for example, a liquid crystal display (LCD), speaker, vibrator, etc.; storage devices 1003 including, for example, magnetic tape, hard disk, etc.; and communication devices 1009. Communication device 1009 allows electronic devices to communicate wirelessly or wiredly with other devices to exchange data. Although electronic devices with various systems are shown in the figures, it should be understood that implementation or possession of all the systems shown is not required. More or fewer systems may be implemented alternatively.

[0102] Specifically, according to the embodiments disclosed in this application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments disclosed in this application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device, or installed from storage device 1003, or installed from ROM 1002. When the computer program is executed by processing device 1001, it performs the functions defined in the methods of the embodiments disclosed in this application.

[0103] The electronic device provided in this application, employing the modeling file generation method described in the above embodiments, can solve the technical problem that traditional modeling methods easily lose original building vector information and cannot meet the needs of building modeling. Compared with the prior art, the beneficial effects of the electronic device provided in this application are the same as those of the modeling file generation method provided in the above embodiments, and other technical features of this electronic device are the same as those disclosed in the method of the previous embodiment, and will not be repeated here.

[0104] 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 suitable manner in one or more embodiments or examples.

[0105] The above are merely specific embodiments of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

[0106] This application provides a computer-readable storage medium having computer-readable program instructions (i.e., a computer program) stored thereon, the computer-readable program instructions being used to execute the modeling file generation method in the above embodiments.

[0107] 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, devices, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to: electrical connections having one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing 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 suitable medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination thereof.

[0108] The aforementioned computer-readable storage medium may be included in an electronic device or may exist independently without being assembled into an electronic device.

[0109] The aforementioned computer-readable storage medium carries one or more programs, which, when executed by an electronic device, cause the electronic device to: Extract each target object from the original building drawing, wherein each target object includes at least a wall object; Determine the centerline of each wall object, and extend each centerline to enclose adjacent wall objects to generate closed space data; The basic graphic elements of each wall object are determined, the attribute quantification information of each basic graphic element is extracted, and the attribute quantification information, each basic graphic element and each wall object are associated according to the belonging relationship to obtain the structured data of each wall object. Based on closed space data and structured data, a target modeling file corresponding to the original building drawing is generated.

[0110] Computer program code for performing the operations of this application can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, and C++, as well as conventional procedural programming languages ​​such as "C" or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0111] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0112] The modules described in the embodiments of this application can be implemented in software or hardware. The names of the modules do not necessarily limit the functionality of the unit itself.

[0113] The readable storage medium provided in this application is a computer-readable storage medium that stores computer-readable program instructions (i.e., a computer program) for executing the above-described modeling file generation method. This solves the technical problem that traditional modeling methods easily lose original building vector information and cannot meet the needs of building modeling. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided in this application are the same as those of the modeling file generation method provided in the above embodiments, and will not be repeated here.

[0114] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the steps of the modeling file generation method described above.

[0115] The computer program product provided in this application can solve the technical problem that traditional large language models are difficult to effectively assist in professional process-oriented design work. Compared with the prior art, the beneficial effects of the computer program product provided in this application are the same as those of the modeling file generation method provided in the above embodiments, and will not be repeated here.

[0116] The above are only some embodiments of this application and do not limit the patent scope of this application. All equivalent structural transformations made under the technical concept of this application and using the contents of the specification and drawings of this application, or direct / indirect applications in other related technical fields, are included in the patent protection scope of this application.< / space> < / buildingstorey> < / building> < / campus>

Claims

1. A method for generating modeling files, characterized in that, The method for generating the modeling file includes: Extract each target object from the original building drawing, wherein each target object includes at least a wall object; Determine the centerline of each wall object, and extend each centerline to enclose adjacent wall objects to generate closed space data; The basic graphic elements of each wall object are determined, the attribute quantification information of each basic graphic element is extracted, and the attribute quantification information, each basic graphic element and each wall object are associated according to the attribution relationship to obtain the structured data of each wall object. Based on the enclosed space data and the structured data, a target modeling file corresponding to the original building drawing is generated.

2. The modeling file generation method as described in claim 1, characterized in that, The step of determining the centerline of each wall object and extending each centerline to enclose adjacent wall objects and generate closed space data includes: The central axis of each wall object is determined based on the thickness of the walls on both sides of each wall object; Extend each central axis to obtain extended connection elements; The target intersection point is obtained by performing a preset optimization process on the extended connection element; Based on the relationship between the target intersection point and the wall object, the closed space formed by adjacent wall objects is identified, and the closed space data is generated.

3. The modeling file generation method as described in claim 2, characterized in that, The step of extending each central axis includes: For any one of the central axes, determine the angle between the central axis and the adjacent central axes: Based on a preset trigonometric function relationship and the included angle, the wall thickness of the wall object related to the central axis is converted into an extended length, wherein the preset trigonometric function relationship is determined based on the wall type of the wall object to which the central axis belongs; The central axis is extended based on the stated extension length.

4. The modeling file generation method as described in claim 2, characterized in that, The step of performing preset optimization processing on the extended connection element to obtain the target intersection point includes: When the extended connecting element is an extension of an overlapping line segment, the midpoint of the overlapping portion of the extension of the overlapping line segment is taken as the target intersection point. When the extended connecting element is a non-overlapping line segment extension, the endpoint of the non-overlapping line segment extension is taken as the target intersection point; When the extended connection element is the original intersection point, determine whether there are other original intersection points within a preset range around the original intersection point. If so, merge the original intersection points within the preset range around the original intersection point to obtain the target intersection point.

5. The modeling file generation method as described in claim 2, characterized in that, After the step of identifying the enclosed space formed by adjacent wall objects based on the association between the target intersection point and the wall object, the method further includes: From the wall objects, select a first type of wall object and a second type of wall object, wherein the first type of wall object is a wall object that is adjacent to two or more enclosed spaces, and the second type of wall object is an arc-shaped wall object; Determine the first wall break point of the first type of wall object, wherein the first wall break point is the common intersection of the enclosed spaces adjacent to the first type of wall object; Determine the second wall break point of the second type of wall object, wherein the second wall break point is the division point of the polygonization of the second type of wall object; Configure the first wall breakpoint and the second wall breakpoint for the wall objects in the structured data based on the hierarchical relationship.

6. The modeling file generation method as described in claim 1, characterized in that, The target objects also include door and window objects; The step of generating the target modeling file of the original building corresponding to the original building drawing based on the enclosed space data and the structured data includes: Construct the hierarchical framework of the original building corresponding to the original building graphic; Based on the closed space data, each closed space element is generated, and the relationship between each spatial element and the floor-level nodes in the hierarchical framework is established to obtain an intermediate modeling file. The structured data is converted to obtain intermediate structured data; Receive the vertical height parameters of each target object in the original building, and expand the intermediate structured data into each wall geometry based on the height parameters; Add door and window openings to each wall geometry to obtain the target geometric wall, and / or construct the target geometric wall according to the affiliation relationship between the door and window objects and each wall geometry; Associate the spatial elements in the intermediate modeling file with the corresponding target geometric walls, and configure the ground and roof surfaces for the spatial elements in the intermediate modeling file to obtain the target modeling file.

7. The modeling file generation method as described in claim 1, characterized in that, The target modeling file corresponds to a modeling data table, which is obtained by converting the target modeling file. After the step of generating the target modeling file of the original building corresponding to the original building drawing based on the enclosed space data and the structured data, the method further includes: Receive the model adjustment request for the building corresponding to the original building drawing; Based on the model adjustment requirements and the preset first prompt word template, a first target prompt word is generated; The modeling data table is adjusted by the preset large language model guided by the first target prompt word to obtain a new modeling data table; The new modeling data table is converted into a new target modeling file.

8. The modeling file generation method as described in claim 1, characterized in that, The target modeling file is configured with a building simulation operation parameter file, which is used to control the simulation operation of the building model corresponding to the target modeling file; After the step of generating the target modeling file of the original building corresponding to the original building drawing based on the enclosed space data and the structured data, the method further includes: Receive the operational status adjustment request of the building model; Based on the operational status adjustment requirements and the preset second prompt word template, a second target prompt word is generated; Guided by the second target prompt word, the preset large language model is used to adjust the running data text corresponding to the building simulation running parameter file, resulting in new running data text; The new operational data text is converted into a new building simulation operational parameter file.

9. An electronic device, characterized in that, The electronic device includes: a processor, a memory, and a modeling file generation program stored in the memory and executable on the processor, wherein the modeling file generation program, when executed, implements the steps of the modeling file generation method as described in any one of claims 1-8.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a modeling file generation program, which, when executed, implements the steps of the modeling file generation method as described in any one of claims 1-8.

Images