Lintel model generation method and device and program product

Abstract

The invention relates to the technical field of constructional engineering, and discloses a lintel model generation method and device and a program product. The method comprises the steps that an architectural drawing is acquired, and lintel information in the architectural drawing is recognized; based on the expression type of the lintel information, parameter information corresponding to the lintel component is determined, and the parameter information comprises text information, table information and detailed drawing information; the text information, the table information and the detailed drawing information are fused, and structural parameters of the lintel component are generated; and generating a lintel model corresponding to the lintel component according to the structured parameters. By implementing the technical scheme, the lintel information can be automatically extracted and fused from the architectural drawing, the corresponding lintel model is generated, and the architectural design efficiency and precision are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of construction engineering, and in particular to a lintel model generation method, device and program product. Background Art

[0002] In the field of construction cost modeling, digital modeling of secondary structural components (such as lintels and structural columns) is a key step in engineering quantity calculation. However, because the design phase typically only expresses information about these components through non-modeled methods such as text descriptions, tables, and detailed drawings, cost estimators must expend considerable effort manually extracting and integrating multi-source heterogeneous data from architectural drawings to complete the modeling. This process severely limits the efficiency and accuracy of lintel modeling. Summary of the Invention

[0003] In view of this, the present invention provides a lintel model generation method, device and program product to solve the problem of low efficiency and poor accuracy of lintel modeling caused by traditional reliance on manual extraction and integration of multi-source heterogeneous data from architectural drawings.

[0004] In a first aspect, the present invention provides a method for generating a lintel model, comprising: obtaining architectural drawings and identifying lintel information in the architectural drawings; determining parameter information corresponding to the lintel component based on the expression type of the lintel information, the parameter information including text information, table information and detailed drawing information; fusing the text information, table information and detailed drawing information to generate structural parameters of the lintel component; and generating a lintel model corresponding to the lintel component according to the structural parameters.

[0005] The lintel model generation method provided in an embodiment of the present invention automatically identifies text, tables and detailed drawing information in architectural drawings, integrates multi-source data to generate structural parameters of lintel components, and automatically generates a lintel model based on this, significantly reducing the steps of manual information extraction and integration, improving modeling efficiency and parameter accuracy, and avoiding errors caused by information dispersion or omission in traditional methods.

[0006] In an optional embodiment, based on the expression type of the lintel information, the text information corresponding to the lintel component is determined, including: obtaining the description keywords corresponding to the lintel component; extracting the lintel arrangement conditions, table names and detailed drawing names from the architectural drawings according to the description keywords; wherein the text information includes the lintel arrangement conditions, table names and detailed drawing names.

[0007] The lintel model generation method provided in an embodiment of the present invention automatically extracts lintel arrangement conditions, table names and detail drawing names from architectural drawings by pre-setting descriptive keywords, systematically locates key information sources, effectively reduces the tedious process of manual item-by-item retrieval and judgment, improves the standardization and accuracy of information extraction, and ensures the integrity and consistency of lintel component parameters.

[0008] In an optional implementation, the lintel arrangement conditions are converted into generation rules corresponding to the lintel components; the generation rules, table names, and detailed drawing names are associated to obtain an association result.

[0009] The lintel model generation method provided by the embodiment of the present invention realizes the precise mapping of business logic and data source by converting the lintel arrangement conditions into specific generation rules and structurally associating them with table names and detailed drawing names, thereby avoiding the deviation of manual rule conversion and ensuring the consistency and integrity of parameter calls, thereby significantly improving the standardization and execution efficiency of lintel model generation.

[0010] In an optional embodiment, based on the expression type of the lintel information, the table information corresponding to the lintel component is determined, including: locating a target table that matches the table name in the architectural drawing according to the table name; identifying the table wireframe information in the target table, and determining the target cell corresponding to the table wireframe information; and extracting the table information from the target cell.

[0011] The lintel model generation method provided by the embodiment of the present invention accurately locates the target table through the table name, and quickly identifies and extracts the target cell data in combination with the table wireframe information, effectively avoiding the tediousness and errors of traditional manual search and positioning, improving the automation and reliability of table information extraction, and at the same time ensuring the accuracy of the parameter source and the integrity of the data structure, providing efficient and consistent basic data support for lintel model generation.

[0012] In an optional embodiment, the first row of data and the first column of data of the target table are read; the first row of data and the first column of data are input into a pre-trained first classification model, so that the first classification model predicts whether the target table is a lintel information table.

[0013] The lintel model generation method provided by the embodiment of the present invention quickly identifies the table features through the first row and first column data, and uses a pre-trained classification model to automatically determine whether the target table is a lintel information table, which significantly reduces the time and subjective deviation of manual verification of table types, improves the accuracy and efficiency of table screening, and provides a reliable data source verification basis for subsequent parameter extraction.

[0014] In an optional embodiment, based on the expression type of the lintel information, determining the detailed drawing information corresponding to the lintel component includes: locating a target detailed drawing that matches the detailed drawing name in the architectural drawing according to the detailed drawing name; identifying detailed drawing wireframe information in the target detailed drawing, and determining a target image area intercepted by the detailed drawing wireframe information; and extracting the detailed drawing information from the target image area.

[0015] The lintel model generation method provided by the embodiment of the present invention accurately locates the target detailed drawing through the detailed drawing name, automatically intercepts and extracts the detailed drawing content of the target area in combination with the wireframe information, effectively avoiding the tediousness and errors of manual search and manual screenshots, improving the automation level and accuracy of detailed drawing information extraction, and ensuring the strict correspondence between component parameters and drawing details, providing reliable and structured detailed drawing data support for lintel model generation.

[0016] In an optional embodiment, extracting detailed image information from a target image area includes: inputting the target image area into a pre-trained second classification model so that the second classification model predicts the image type of the target detailed image; and extracting detailed image information corresponding to the image type from the image area.

[0017] The lintel model generation method provided by the embodiment of the present invention automatically identifies the image type of the target detailed drawing through a pre-trained second classification model, and extracts the corresponding detailed drawing information according to the type, avoiding the errors of manual classification and general analysis, significantly improving the accuracy and adaptability of detailed drawing information extraction, and ensuring the strict match between parameter analysis and the actual business scenario of the drawing.

[0018] In an optional embodiment, the text information, tabular information and detailed drawing information are integrated to generate the structural parameters of the lintel component, including: performing coordinate analysis on the text information, tabular information and detailed drawing information to determine the first coordinate information of the text information, the second coordinate information of the tabular information and the third coordinate information of the detailed drawing information; aligning the first coordinate information, the second coordinate information and the third coordinate information to establish a spatial association relationship among the text information, the tabular information and the detailed drawing information; matching the text information, the tabular information and the detailed drawing information according to the spatial association relationship to obtain the structural parameters of the lintel component.

[0019] The lintel model generation method provided in an embodiment of the present invention uses coordinate analysis and spatial alignment technology to accurately associate the spatial positions of text, tables and detailed drawing information in architectural drawings, eliminate the positional fragmentation of multi-source data, ensure the physical and logical consistency of parameter matching, and automatically construct an overall relationship network of cross-modal data, significantly improving the integrity and business adaptability of structured parameter generation, and avoiding the misalignment or omission problems that may be caused by manual splicing.

[0020] In an optional embodiment, text information, tabular information and detailed drawing information are matched according to spatial association relationships to obtain structural parameters of the lintel component, including: using spatial association relationships to compare tabular information and detailed drawing information to generate parameter comparison results; if the parameter comparison results indicate that there are missing parameters in the tabular information, the missing parameters are supplemented based on the detailed drawing information to obtain supplemented tabular information; and based on the text information and the supplemented tabular information, the structural parameters of the lintel component are generated.

[0021] The lintel model generation method provided in an embodiment of the present invention automatically compares table and detailed drawing information through spatial association relationships, identifies and supplements missing parameters in the table, and generates structured parameters in combination with text information, effectively reducing the workload of manual omission detection and filling, ensuring multi-source complementarity and logical consistency of parameter sources, and improving the integrity and accuracy of the overall data.

[0022] In an optional embodiment, generating a lintel model corresponding to the lintel component according to the structural parameters includes: obtaining a target position of the lintel to be generated in the architectural drawing; and generating the lintel model at the target position according to the structural parameters.

[0023] The lintel model generation method provided by the embodiment of the present invention directly drives the lintel model to be automatically generated at the target position in the architectural drawing through structured parameters, accurately matching the design requirements, avoiding the tedious operations of manual positioning and repeated parameter input, significantly improving modeling efficiency, and at the same time ensuring strict correspondence between the model and the drawing space position and business parameters, thereby reducing human errors.

[0024] In a second aspect, the present invention provides a lintel model generation device, comprising: an acquisition module for acquiring architectural drawings and identifying lintel information in the architectural drawings; a determination module for determining parameter information corresponding to the lintel component based on the expression type of the lintel information, the parameter information including text information, table information and detailed drawing information; a fusion module for fusing the text information, table information and detailed drawing information to generate structural parameters of the lintel component; and a generation module for generating a lintel model corresponding to the lintel component according to the structural parameters.

[0025] In a third aspect, the present invention provides a computer device comprising: a memory and a processor, the memory and the processor being communicatively connected to each other, the memory storing computer instructions, and the processor executing the lintel model generation method of the first aspect or any corresponding embodiment thereof by executing the computer instructions.

[0026] In a fourth aspect, the present invention provides a computer-readable storage medium having computer instructions stored thereon, the computer instructions being used to enable a computer to execute the lintel model generation method of the first aspect or any corresponding embodiment thereof.

[0027] In a fifth aspect, the present invention provides a computer program product comprising computer instructions for causing a computer to execute the lintel model generation method of the first aspect or any corresponding embodiment thereof. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] In order to more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the specific embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0029] Figure 1 is a schematic flow chart of a method for generating a lintel model according to an embodiment of the present invention;

[0030] Figure 2 is a schematic flow chart of another lintel model generation method according to an embodiment of the present invention;

[0031] Figure 3 is a flow chart of another method for generating a lintel model according to an embodiment of the present invention;

[0032] Figure 4 is a schematic diagram of fusing table information and detailed diagram information according to an embodiment of the present invention;

[0033] Figure 5 is a schematic diagram of arrangement conditions corresponding to lintel arrangement positions according to an embodiment of the present invention;

[0034] Figure 6 is a structural block diagram of a lintel model generating device according to an embodiment of the present invention;

[0035] Figure 7 Schematic diagram of the hardware structure of a computer device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0036] To make the purpose, technical solutions, and advantages of the embodiments of the present invention more clear, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without making creative efforts shall fall within the scope of protection of the present invention.

[0037] During the Computer Aided Design (CAD) drawing process, the general design description usually explains some business that does not require modeling, and uses text descriptions, tables, drawings, etc. to express it in detail. Cost engineers perform cost modeling based on the descriptions on the CAD drawings. For the main structures such as columns, beams, wall panels, etc., there are usually detailed design models, which can be easily re-molded. However, for the lintels, ring beams, structural columns, etc. in the secondary structure, designers usually do not draw the corresponding models. Cost engineers need to extract information based on the general descriptions, tables, and detailed drawings in the CAD drawings to perform cost modeling.

[0038] The current civil engineering quantity calculation software provides the ability to batch model according to business instructions. Cost estimators can extract parameters from CAD drawings and use the table picking and modeling functions of the civil engineering quantity calculation software to generate a three-dimensional model of the lintel for quantity calculation. However, the relevant technical solutions have some problems in information extraction and table picking. First, cost estimators need to manually extract and merge information from the general instructions, tables and drawings in the CAD drawings, which is cumbersome and error-prone. Secondly, the current table extraction function only supports the extraction of table formats and cannot effectively parse business information, so cost estimators need to manually adjust and check. Finally, the detailed drawing information in CAD is not included, and cost estimators must supplement it in the civil engineering quantity calculation software model based on their own understanding, which increases the workload and the risk of errors.

[0039] In light of this, the present invention's technical solution obtains architectural drawings, identifies lintel information, and fuses this data with parameter information from text, tables, and detailed drawings to generate structural parameters for the lintel component. Based on these structural parameters, a corresponding lintel model can be automatically generated, improving modeling efficiency and accuracy.

[0040] According to an embodiment of the present invention, an embodiment of a method for generating a lintel model is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0041] In this embodiment, a lintel model generation method is provided, which can be used in computer equipment, such as desktop computers, laptop computers, etc. Figure 1 is a flow chart of a method for generating a lintel model according to an embodiment of the present invention. Figure 1 As shown, the process includes the following steps:

[0042] Step S101: Obtain architectural drawings and identify lintel information in the architectural drawings.

[0043] Architectural drawings are those created using CAD technology and contain detailed information such as the building structure, component location, and dimensioning, used to guide construction and cost modeling. Lintel information refers to the design data related to lintels in architectural drawings. Specifically, CAD architectural drawings are imported into civil engineering quantity calculation software, and image recognition technology (such as OCR text recognition and line segment detection algorithms) or deep learning-based semantic segmentation models are used to automatically identify lintel information such as lintel location, annotation text (such as dimensions and materials), tables, and detailed drawings in the architectural drawings.

[0044] Step S102: determining parameter information corresponding to the lintel component based on the expression type of the lintel information, where the parameter information includes text information, table information, and detailed drawing information.

[0045] The expression type of lintel information refers to the different ways in which lintel information is presented in architectural drawings. A lintel component refers to a beam structure used to bear loads above door and window openings in a building and is a secondary structure. Parameter information refers to the specific lintel attribute data extracted from different expression types. Specifically, the expression types of lintel information include text (such as the text description in the general description), table (such as the lintel specification table), and detailed drawing (such as the cross-section view, front view, and other graphical details of the lintel). For different expression forms, corresponding processing methods need to be adopted. For example, natural language processing (NLP) technology is used to extract parameters from the text, parse the row and column data in the table, and combine computer vision technology to analyze the geometric features in the detailed drawing. Finally, the extracted data is classified by type and the parameters are standardized.

[0046] Step S103: Fusing the text information, table information, and detailed drawing information to generate structural parameters of the lintel component.

[0047] Structured parameters refer to the integration of lintel information scattered across text, tables, and detailed drawings into a unified data format through multimodal data fusion technology. Specifically, by integrating and matching text, table, and detailed drawing information, this information is converted into structured lintel parameters for the lintel component, ensuring parameter integrity and consistency.

[0048] Step S104: generating a lintel model corresponding to the lintel component according to the structural parameters.

[0049] A lintel model refers to a 3D geometric model of a lintel automatically generated based on structural parameters in civil engineering quantity calculation software. Specifically, the lintel's 3D geometric model is automatically generated based on structural parameters in civil engineering quantity calculation software. Based on the extracted and integrated structural parameters, the civil engineering quantity calculation software constructs the lintel's 3D form and, in conjunction with specific design requirements, generates an accurate lintel model.

[0050] The lintel model generation method provided in an embodiment of the present invention automatically identifies text, tables and detailed drawing information in architectural drawings, integrates multi-source data to generate structural parameters of lintel components, and automatically generates a lintel model based on this, significantly reducing the steps of manual information extraction and integration, improving modeling efficiency and parameter accuracy, and avoiding errors caused by information dispersion or omission in traditional methods.

[0051] In this embodiment, a lintel model generation method is provided, which can be used in computer equipment, such as desktop computers, laptop computers, etc. Figure 2 is a flow chart of a method for generating a lintel model according to an embodiment of the present invention. Figure 2 As shown, the process includes the following steps:

[0052] Step S201: Obtain architectural drawings and identify lintel information in the architectural drawings. Figure 1 Step S101 of the illustrated embodiment will not be described in detail here.

[0053] Step S202: determining parameter information corresponding to the lintel component based on the expression type of the lintel information, where the parameter information includes text information, table information, and detailed drawing information.

[0054] Specifically, the above step S202 includes:

[0055] Step S2021: Determine the text information corresponding to the lintel component based on the expression type of the lintel information.

[0056] Text information refers to the textual descriptions of lintel components extracted from architectural drawings. Specifically, an algorithm matches keywords from the general description of the CAD architectural drawings to extract textual descriptions, referenced drawing names, or table names related to the lintel components. This information is then analyzed for generation conditions and, combined with textual coordinate information, associated content is located to form structured text parameters.

[0057] In some optional implementations, the above step S2021 includes:

[0058] Step a1: Obtain description keywords corresponding to the lintel component.

[0059] Descriptive keywords are predefined keywords used to identify lintel components, such as "lintel," "underhang plate," "table," and "detail drawing." Specifically, a text matching algorithm is used to scan and extract relevant text information from the general description of CAD architectural drawings using predefined lintel business keywords.

[0060] Step a2: extracting lintel arrangement conditions, table names, and detail drawing names from architectural drawings according to description keywords.

[0061] The text information includes lintel arrangement conditions, table name and detail drawing name.

[0062] Lintel arrangement conditions refer to the installation rules or constraints of lintels in buildings (such as "a lintel must be installed when the opening width is ≥1.5m"). Table names refer to the names of specific tables used to store lintel parameters in architectural drawings (such as "Table 7.2"). Detailed drawing names refer to the identification names of lintel details in architectural drawings (such as "Figure 10.1a"). Specifically, based on descriptive keywords, coordinate matching and text analysis technology are used to extract lintel arrangement conditions, table names, and detailed drawing names from the general description of CAD architectural drawings. If the name is missing, a supplementary match is performed based on general lintel business rules (such as the default table name or drawing name format).

[0063] In the above embodiment, lintel arrangement conditions, table names and detailed drawing names are automatically extracted from architectural drawings by pre-setting descriptive keywords, and key information sources are systematically located, which effectively reduces the tedious process of manual item-by-item retrieval and judgment, improves the standardization and accuracy of information extraction, and ensures the integrity and consistency of lintel component parameters.

[0064] Step a3: converting the lintel arrangement conditions into generation rules corresponding to the lintel components.

[0065] Generation rules convert lintel placement conditions into computer-interpretable logical rules. Specifically, the logical relationships within the lintel placement conditions are parsed into structured rules. For example, "Generate a slat if the height is less than 200mm, otherwise generate a lintel" is converted into a conditional statement (e.g., if (height < 200mm) {generate a slat} else {generate a lintel}). These rules are then associated with parameters such as size thresholds and component types to form executable generation rules.

[0066] Step a4: associate the generation rule, table name, and detailed drawing name to obtain an association result.

[0067] The association result is the data structure that associates the generation rules, table names, and detailed drawing names. This data is used for subsequent parameter fusion and model generation. Specifically, the generation rules are bound to the corresponding table names and detailed drawing names to ensure that the information in the table and detailed drawing matches the generation rules.

[0068] In the above implementation, by converting the lintel arrangement conditions into specific generation rules and making structured associations with the table names and detailed drawing names, accurate mapping of business logic and data sources is achieved, avoiding deviations in manual rule conversion, and ensuring the consistency and integrity of parameter calls, thereby significantly improving the standardization and execution efficiency of lintel model generation.

[0069] Step S2022: Determine the table information corresponding to the lintel component based on the expression type of the lintel information.

[0070] Tabular information refers to structured data such as lintel specifications, dimensions, and materials, listed in a table. Specifically, tables in CAD architectural drawings are located based on table name matching or common lintel table names. Wireframe recognition technology is used to extract table content (such as dimensions and reinforcement information). A lightweight model (such as a deep learning model) is used to determine whether it is a lintel table. The business relevance of the table data is verified, and finally, the table parameter information is extracted and stored.

[0071] In some optional implementations, the above step S2022 includes:

[0072] Step b1: locate the target table that matches the table name in the architectural drawing according to the table name.

[0073] The target table refers to the specific table located by table name in the architectural drawing. Specifically, a text matching algorithm is used to search for text tags in the CAD architectural drawing that are exactly the same as the table name extracted above (such as "Table 7.2") to locate the location of the target table. If the name is missing, a fuzzy match is performed based on the general naming rules for lintel tables (such as preset keywords such as "lintel table" and "beam table"), combined with the layout characteristics of the table in the drawing (such as its location near the general instructions or detailed drawings), to ultimately determine the coordinate range of the target table.

[0074] Step b2: identifying table wireframe information in the target table and determining the target cell corresponding to the table wireframe information.

[0075] Table wireframe information refers to the border line information of the table (such as horizontal and vertical line coordinates), which is used to identify the table structure and cell position. The target cell refers to the cell in the table that stores a specific parameter value, such as the numerical cell corresponding to the "section height". Specifically, the wireframe parsing technology of the CAD drawing is used to identify the intersections and closed areas of the horizontal and vertical lines of the target table and construct the geometric boundaries of the cell. By analyzing the density, spacing and arrangement rules of the wireframe, the table header, data row and other areas are divided, and the position of each cell is determined based on the coordinate information to form a structured table grid model.

[0076] Step b3: extract table information from the target cell.

[0077] Using optical character recognition (OCR) or native CAD text parsing, text content is extracted cell by cell. For merged cells, data ranges are parsed using cross-cell wireframe merging rules to ensure that key parameters such as length, width, height, and reinforcement information are fully extracted.

[0078] The cost engineer verifies the extracted table information.

[0079] In the above implementation, the target table is accurately located by the table name, and the target cell data is quickly identified and extracted in combination with the table wireframe information, which effectively avoids the tediousness and errors of traditional manual search and positioning, improves the automation and reliability of table information extraction, and ensures the accuracy of the parameter source and the integrity of the data structure, providing efficient and consistent basic data support for the generation of the lintel model.

[0080] Step b4: Read the first row and column of data in the target table.

[0081] The first row of data refers to the title information of the first row of the table, such as "Span", "Lintill Height", etc. The first column of data refers to the classification information of the first column of the table, such as different lintel numbers. Specifically, the first row of data locates the wireframe area at the top of the table and extracts the text content of all cells in the row. The first column of data identifies the wireframe column on the far left of the table and extracts the text content of the cells in the column (such as the lintel numbers "GL-01" and "GL-02") as the index identifier of the data row.

[0082] Step b5: input the first row of data and the first column of data into a pre-trained first classification model, so that the first classification model predicts whether the target table is a lintel information table.

[0083] The first classification model refers to a pre-trained machine learning model, which is used to determine whether a table is a lintel information table based on the first row and first column data. The lintel information table refers to a table that specifically stores lintel design parameters (such as lintel height, reinforcement information, etc.). Specifically, after the first row and first column of data are vectorized, they are input into a lightweight classification model trained based on textCNN, namely the first classification model. The first classification model analyzes the semantic features of the field name and index (such as whether it contains keywords such as "lintel"), combined with the data distribution pattern (such as whether the numerical type conforms to the lintel parameters), and outputs a probability value to determine whether the table is a lintel information table. If the threshold exceeds the preset value (such as 95%), it is judged to be valid.

[0084] In the above implementation, the table features are quickly identified through the first row and first column data, and a pre-trained classification model is used to automatically determine whether the target table is a lintel information table, which significantly reduces the time and subjective deviation of manual verification of table types, improves the accuracy and efficiency of table screening, and provides a reliable data source verification basis for subsequent parameter extraction.

[0085] Step S2023: Determine the detailed drawing information corresponding to the lintel component based on the expression type of the lintel information.

[0086] Detailed drawing information, including sections and elevations of lintels, provides detailed design and dimensional information through graphical details. Specifically, details are located in CAD architectural drawings through detail name matching or universal lintel services, images are captured using wireframe boundaries, and detailed drawing types (e.g., elevation, section) are categorized using light modeling. Text, coordinates, and annotation information (e.g., rebar and support lengths) within the details are then extracted.

[0087] In some optional implementations, step S2023 includes:

[0088] Step c1: Locate a target detail that matches the detail name in the architectural drawing according to the detail name.

[0089] The target detail is the specific lintel detail located by its name. Specifically, a text matching algorithm is used to search the CAD architectural drawing for a text tag that exactly matches the extracted detail name (e.g., "Figure 10.1a"), and the target detail's location is then located using coordinate information. If the name is missing, a fuzzy match is performed based on common lintel detail naming conventions (e.g., preset keywords like "Lintel Section" and "Underhang Plate Detail"), and the coordinate range of the target detail is ultimately determined by considering its layout characteristics in the drawing (e.g., proximity to tables or general description areas).

[0090] Step c2: identifying the detailed drawing wireframe information in the target detailed drawing and determining the target image area captured by the detailed drawing wireframe information.

[0091] Detailed drawing wireframe information refers to the wireframe structure (e.g., outlines) within the detailed drawing and is used to locate the target image area. The target image area refers to the area containing key information captured based on the detailed drawing wireframe information. Specifically, CAD wireframe parsing technology is used to identify closed boundaries composed of line segments (e.g., wall outlines, rebar distribution lines) within the target detailed drawing. By analyzing the intersection density of the line segments, the shape of the closed area, and the size ratio, the core area of ​​the target detailed drawing is demarcated. Combined with the coordinate information, the image area containing the lintel detail is cropped to ensure that the text, annotations, and graphics within the wireframe are fully captured.

[0092] Step c3: extracting detailed image information from the target image area.

[0093] OCR technology is used to extract text annotations within the image area (e.g., "Φ12@150" or "Support length 300mm"), and wireframe graphics are converted into structured data (e.g., rebar length, cross-sectional dimensions) through vectorization. For complex graphics (e.g., section symbols), their meaning is analyzed using predefined business rules. For example, support orientation can be determined by line segment angle or concrete grade identification can be identified by fill pattern.

[0094] The cost engineer verifies the extracted detailed drawing information.

[0095] In the above implementation, the target detail is accurately located by the detail name, and the detail content of the target area is automatically captured and extracted in combination with the wireframe information, effectively avoiding the tediousness and errors of manual search and manual screenshots, improving the automation level and accuracy of detail information extraction, and ensuring the strict correspondence between component parameters and drawing details, providing reliable and structured detail data support for lintel model generation.

[0096] In some optional implementations, the above step c3 includes:

[0097] Step c31: input the target image area into a pre-trained second classification model, so that the second classification model predicts the image type of the target detailed image.

[0098] The second classification model is a trained image classification model used to determine the image type of the target detailed drawing. Image type refers to the type of detailed drawing, such as the lower cladding elevation view, lower cladding cross-section, lintel elevation view, and lintel cross-section. Specifically, the captured target image region undergoes standardized preprocessing and is then fed into a lightweight classification model trained on a CNN, i.e., the second classification model. The second classification model extracts features of the target image region based on training data (e.g., four types of annotated images, such as the lower cladding elevation view and lintel cross-section), and predicts the image type of the target detailed drawing.

[0099] Step c32: extract detailed image information corresponding to the image type from the image area.

[0100] Based on the image type predicted by the second classification model, the parsing template associated with that type is called. For example, if it is a "lintel cross-section," the support length and rebar anchorage information are extracted; if it is a "bottom slab elevation view," the cross-sectional dimensions and rebar spacing are extracted.

[0101] In the above embodiment, the image type of the target detailed drawing is automatically identified through the pre-trained second classification model, and the corresponding detailed drawing information is extracted according to the type, thereby avoiding the errors of manual classification and general analysis, significantly improving the accuracy and adaptability of detailed drawing information extraction, and ensuring strict matching of parameter analysis with the actual business scenario of the drawing.

[0102] Step S203: fuse the text information, table information and detailed drawing information to generate the structural parameters of the lintel component. Figure 1 Step S103 of the illustrated embodiment will not be described in detail here.

[0103] Step S204: Generate a lintel model corresponding to the lintel component according to the structural parameters. Figure 1 Step S104 of the illustrated embodiment will not be described in detail here.

[0104] In this embodiment, a lintel model generation method is provided, which can be used in computer equipment, such as desktop computers, laptop computers, etc. Figure 3 is a flow chart of a method for generating a lintel model according to an embodiment of the present invention. Figure 3 As shown, the process includes the following steps:

[0105] Step S301: Obtain architectural drawings and identify lintel information in the architectural drawings. Figure 2 Step S201 of the illustrated embodiment will not be described in detail here.

[0106] Step S302: Based on the expression type of the lintel information, determine the parameter information corresponding to the lintel component. The parameter information includes text information, table information, and detailed drawing information. Figure 2 Step S202 of the illustrated embodiment will not be described in detail here.

[0107] Step S303: Fusing the text information, table information, and detailed drawing information to generate structural parameters of the lintel component.

[0108] Specifically, the above step S303 includes:

[0109] Step S3031 , performing coordinate analysis on the text information, table information and detailed drawing information to determine the first coordinate information of the text information, the second coordinate information of the table information and the third coordinate information of the detailed drawing information.

[0110] The first coordinate information refers to the position coordinates of the text information extracted from the architectural drawing in the drawing, which is used to identify the specific spatial position of the text in the drawing. The second coordinate information refers to the position coordinates of the table information extracted from the architectural drawing in the drawing, which is used to locate the area of ​​the table in the drawing. The third coordinate information refers to the position coordinates of the detailed drawing information extracted from the architectural drawing in the drawing, which is used to identify the specific range of the detailed drawing in the drawing. Specifically, by parsing the metadata of the CAD architectural drawing or using wireframe parsing technology, the absolute coordinates of the text, table and detailed drawing in the drawing (such as the coordinates of the upper left corner and the lower right corner) are extracted. The text coordinates are determined based on their marked position, the table coordinates are calculated through the wireframe boundary, and the detailed drawing coordinates are obtained based on the geometric range of the closed wireframe, and finally the first coordinate information, the second coordinate information, and the third coordinate information are generated, which correspond to the position data of the text, table, and detailed drawing, respectively.

[0111] Step S3032: align the first coordinate information, the second coordinate information, and the third coordinate information to establish a spatial association relationship among the text information, the table information, and the detailed drawing information.

[0112] Spatial association refers to establishing a spatial relationship between text, tables, and detailed drawings by aligning their coordinate information. Specifically, based on the unified coordinate system of CAD architectural drawings, the coordinate information of the three is converted into relative positions within the same reference system. Spatial associations are established by calculating the coordinate overlap or proximity of text, tables, and detailed drawings (e.g., the table name and the corresponding detailed drawing are located in the same drawing area). For example, the coordinates of Table 7.2 are bound to the coordinates of the referenced Figure 10.1a, forming a logical link between multimodal data.

[0113] Step S3033: Match the text information, table information, and detailed drawing information according to the spatial association relationship to obtain structural parameters of the lintel component.

[0114] Based on coordinate relationships, the generation rules in the text (such as "generate a lower slab if the height is less than 200mm") are matched with the information in the table and detailed drawings by position. For example, if the table and detailed drawing coordinates are adjacent, their data is automatically merged to generate a structured parameter set containing parameters such as size, reinforcement, and support length.

[0115] In some optional implementations, the above step S3033 includes:

[0116] Step d1, using spatial association relationships to compare table information and detailed drawing information, and generating parameter comparison results.

[0117] Parameter comparison results are generated by comparing the table and detailed drawing data when merging them, identifying duplications and missing data. Specifically, the table and detailed drawing corresponding to the same lintel component are located using coordinate association, and the dimensional parameters in the table are compared with the graphical annotations in the detailed drawing (such as support length and wall thickness). If a support length parameter is missing from the table but a corresponding annotation exists in the detailed drawing, it will be marked as "missing parameter."

[0118] Step d2: If the parameter comparison result indicates that there are missing parameters in the table information, the missing parameters are supplemented based on the detailed drawing information to obtain supplemented table information.

[0119] Missing parameters are parameters that are not included in the table but are present in the detailed drawing and need to be completed using the detailed drawing. Specifically, extract the missing parameters based on the coordinates associated with the detailed drawing (e.g., extracting the support length "250mm" from the section drawing) and add them to the corresponding fields in the table. For example, if the table is missing the "Support Length" column, insert the detailed drawing data into the table based on the coordinates to form a complete parameter table.

[0120] like Figure 4As shown, the table in the upper left corner includes the information corresponding to the span Lo, lintel height, No. ① reinforcement and No. ② reinforcement. According to the predefined business conversion rules, the span is converted into the hole width parameter, the lintel height is converted into the beam height parameter, the No. ① reinforcement is converted into the bottom reinforcement parameter, and the No. ② reinforcement is converted into the surface reinforcement parameter. Figure 4 The detail in the upper right corner includes wall thickness information. Figure 4 The detailed drawing in the lower left corner includes support length information (250). According to the predefined business conversion rules, the wall thickness is converted into beam width parameters, and the support length information is converted into support length parameters. The table information and the detailed drawing information are merged to determine that the beam width parameters and support length parameters in the detailed drawing are missing in the table. The beam width parameters and support length parameters are added to the table to form a complete parameter table, that is, Figure 4 After the complete parameter table is generated, the user can verify the complete parameter table according to the information in the table and detailed drawing. If any data in the parameter table is found to be incorrect, it can be modified.

[0121] In addition, if there are repeated parameters in the table and detailed drawings, the table will be used as the main data and the same data in the detailed drawings will be deleted.

[0122] Step d3: generating structural parameters of the lintel component based on the text information and the supplemented table information.

[0123] Combine the generation rules in the text with the supplemented table data and integrate them into structured parameters based on business logic. For example, the generation rule "Height < 200mm → Lower slab" is combined with the lower slab size parameters in the table to form parameters that include type, size, and reinforcement.

[0124] The lintel model generation method provided in an embodiment of the present invention uses coordinate analysis and spatial alignment technology to accurately associate the spatial positions of text, tables and detailed drawing information in architectural drawings, eliminate the positional fragmentation of multi-source data, ensure the physical and logical consistency of parameter matching, and automatically construct an overall relationship network of cross-modal data, significantly improving the integrity and business adaptability of structured parameter generation, and avoiding the misalignment or omission problems that may be caused by manual splicing.

[0125] Step S304: generating a lintel model corresponding to the lintel component according to the structural parameters.

[0126] Specifically, the above step S304 includes:

[0127] Step S3041: Obtain the target position of the lintel to be generated in the architectural drawing.

[0128] The target location refers to the specific location in the architectural drawings where the lintel needs to be generated, such as door and window openings. Specifically, the coordinate data of the door and window openings in the 3D model of the civil engineering quantity calculation software is traversed. Combined with the lintel generation conditions in the CAD architectural drawings, the target location that meets the requirements (such as door and window openings with a height of ≥ 200mm) is selected.

[0129] Step S3042: Generate a lintel model at the target position according to the structural parameters.

[0130] Based on the structural parameters, including dimensions, reinforcement, support lengths, and generation rules, the lintel geometry model is automatically generated at the target location and filled with reinforcement layout parameters. The generated model is seamlessly integrated with the 3D model in the civil engineering quantity calculation software, and the modeling results are output in a report.

[0131] In addition, if Figure 5 As shown, the civil engineering quantity calculation software can generate layout conditions corresponding to various layout positions based on structural parameters, allowing users to view and perform operations such as importing, exporting, adding rows, and deleting rows. Users can also choose whether to generate beam slabs in the civil engineering quantity calculation software and set the generation conditions for beam slabs. For example, if the distance between the top of the opening and the bottom of the beam is less than 300mm, a beam slab will be generated, or if the distance between the top of the opening and the bottom of the beam is less than the minimum lintel height, a beam slab will be generated.

[0132] The lintel model generation method provided by the embodiment of the present invention directly drives the lintel model to be automatically generated at the target position in the architectural drawing through structured parameters, accurately matching the design requirements, avoiding the tedious operations of manual positioning and repeated parameter input, significantly improving modeling efficiency, and at the same time ensuring strict correspondence between the model and the drawing space position and business parameters, thereby reducing human errors.

[0133] This embodiment also provides a lintel model generation device for implementing the above-mentioned embodiments and preferred embodiments. Details already described will not be repeated here. As used below, the term "module" may refer to a combination of software and / or hardware that implements a predetermined function. Although the devices described in the following embodiments are preferably implemented using software, implementation using hardware, or a combination of software and hardware, is also possible and contemplated.

[0134] This embodiment provides a lintel model generation device, such as Figure 6 Shown, including:

[0135] An acquisition module 601 is used to acquire architectural drawings and identify lintel information in the architectural drawings;

[0136] A determination module 602 is configured to determine parameter information corresponding to the lintel component based on the expression type of the lintel information, where the parameter information includes text information, table information, and detailed drawing information;

[0137] A fusion module 603 is used to fuse text information, table information and detailed drawing information to generate structural parameters of the lintel component;

[0138] The generating module 604 is used to generate a lintel model corresponding to the lintel component according to the structural parameters.

[0139] In some optional implementations, the determining module 602 includes:

[0140] The first acquisition submodule is used to obtain description keywords corresponding to the lintel component;

[0141] The first extraction submodule is used to extract lintel arrangement conditions, table names and detailed drawing names from architectural drawings according to description keywords; wherein the text information includes lintel arrangement conditions, table names and detailed drawing names.

[0142] In some optional implementations, the determining module 602 further includes:

[0143] A conversion submodule, used to convert lintel arrangement conditions into generation rules corresponding to lintel components;

[0144] The association submodule is used to associate the generation rules, table names and detail drawing names to obtain association results.

[0145] In some optional implementations, the determining module 602 further includes:

[0146] The first positioning submodule is used to locate the target table that matches the table name in the architectural drawing according to the table name;

[0147] A first recognition submodule is configured to recognize table wireframe information in a target table and determine a target cell corresponding to the table wireframe information;

[0148] The second extraction submodule is used to extract table information from the target cell.

[0149] In some optional implementations, the determining module 602 further includes:

[0150] The reading submodule is used to read the first row and column data of the target table;

[0151] The first prediction submodule is used to input the first row data and the first column data into a pre-trained first classification model, so that the first classification model predicts whether the target table is a lintel information table.

[0152] In some optional implementations, the determining module 602 further includes:

[0153] The second positioning submodule is used to locate the target detail that matches the detail name in the architectural drawing according to the detail name;

[0154] A second recognition submodule is configured to recognize detailed drawing wireframe information in the target detailed drawing and determine a target image region captured by the detailed drawing wireframe information;

[0155] The third extraction submodule is used to extract detailed image information from the target image area.

[0156] In some optional implementations, the third extraction submodule includes:

[0157] A second prediction submodule is used to input the target image area into a pre-trained second classification model so that the second classification model predicts the image type of the target detailed image;

[0158] The fourth extraction submodule is configured to extract detailed image information corresponding to the image type from the image region.

[0159] In some optional implementations, the fusion module 603 includes:

[0160] A parsing submodule, configured to perform coordinate parsing on the text information, table information, and detailed drawing information to determine first coordinate information of the text information, second coordinate information of the table information, and third coordinate information of the detailed drawing information;

[0161] An alignment submodule, configured to align the first coordinate information, the second coordinate information, and the third coordinate information, and establish a spatial association relationship between the text information, the table information, and the detailed drawing information;

[0162] The matching submodule is used to match text information, table information and detailed drawing information according to spatial association relationships to obtain the structural parameters of the lintel component.

[0163] In some optional implementations, the matching submodule includes:

[0164] A comparison unit is used to compare table information and detailed drawing information using spatial association relationships to generate parameter comparison results;

[0165] A supplementing unit, configured to supplement the missing parameters based on the detailed drawing information to obtain supplemented table information if the parameter comparison result indicates that there are missing parameters in the table information;

[0166] The generating unit is used to generate structural parameters of the lintel component based on the text information and the supplemented table information.

[0167] In some optional implementations, the generating module 604 includes:

[0168] The second acquisition submodule is used to obtain the target position of the lintel to be generated in the architectural drawing;

[0169] The generation submodule is used to generate a lintel model at a target position according to structural parameters.

[0170] The further functional description of each of the above modules and units is the same as that of the above corresponding embodiments and will not be repeated here.

[0171] The lintel model generation device in this embodiment is presented in the form of a functional unit, where the unit refers to an ASIC (Application Specific Integrated Circuit) circuit, a processor and memory that executes one or more software or fixed programs, and / or other devices that can provide the above functions.

[0172] The lintel model generation device provided in an embodiment of the present invention automatically identifies text, tables and detailed drawing information in architectural drawings, integrates multi-source data to generate structural parameters of lintel components, and automatically generates a lintel model based on this, significantly reducing the steps of manual information extraction and integration, improving modeling efficiency and parameter accuracy, and avoiding errors caused by information dispersion or omission in traditional methods.

[0173] The embodiment of the present invention also provides a computer device having the above Figure 6 The lintel model generation device shown.

[0174] See also Figure 7 , Figure 7 is a structural diagram of a computer device provided by an optional embodiment of the present invention, such as Figure 7 As shown, the computer device includes: one or more processors 10, memory 20, and interfaces for connecting various components, including high-speed interfaces and low-speed interfaces. Various components utilize different buses to communicate with each other and can be installed on a common mainboard or installed in other ways as needed. The processor can process the instructions executed in the computer device, including instructions stored in the memory or on the memory to display the graphical information of the GUI on an external input / output device (such as, a display device coupled to the interface). In some optional embodiments, if necessary, multiple processors and / or multiple buses can be used together with multiple memories and multiple memories. Equally, multiple computer devices can be connected, and each device provides part of the necessary operations (for example, as a server array, a group of blade servers, or a multi-processor system). Figure 7 A processor 10 is taken as an example.

[0175] The processor 10 may be a central processing unit, a network processor, or a combination thereof. The processor 10 may further include a hardware chip. The hardware chip may be an application-specific integrated circuit, a programmable logic device, or a combination thereof. The programmable logic device may be a complex programmable logic device, a field programmable gate array, a general purpose array logic, or any combination thereof.

[0176] The memory 20 stores instructions that can be executed by at least one processor 10, so as to enable at least one processor 10 to execute the method shown in the above embodiment.

[0177] The memory 20 may include a program storage area and a data storage area, wherein the program storage area may store an operating system and application programs required for at least one function; the data storage area may store data created based on the use of the computer device, etc. In addition, the memory 20 may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some optional embodiments, the memory 20 may optionally include a memory remotely located relative to the processor 10, and these remote memories may be connected to the computer device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0178] The memory 20 may include a volatile memory, such as a random access memory; the memory may also include a non-volatile memory, such as a flash memory, a hard disk or a solid-state drive; the memory 20 may also include a combination of the above types of memory.

[0179] The computer device further includes an input device 30 and an output device 40. The processor 10, the memory 20, the input device 30 and the output device 40 may be connected via a bus or other means. Figure 7 The bus connection is taken as an example.

[0180] The input device 30 can receive input digital or character information and generate key signal input related to user settings and function control of the computer device, such as a touch screen, a keypad, a mouse, a trackpad, a touch pad, an indicator stick, one or more mouse buttons, a trackball, a joystick, etc. The output device 40 can include a display device, an auxiliary lighting device (e.g., an LED), and a tactile feedback device (e.g., a vibration motor). The above-mentioned display device includes but is not limited to a liquid crystal display, a light emitting diode, a display, and a plasma display. In some optional embodiments, the display device can be a touch screen.

[0181] The computer device further includes a communication interface for the computer device to communicate with other devices or a communication network.

[0182] The embodiment of the present invention also provides a computer-readable storage medium. The above-mentioned method according to the embodiment of the present invention can be implemented in hardware, firmware, or implemented as a computer code that can be recorded in a storage medium, or implemented as a computer code that is originally stored in a remote storage medium or a non-temporary machine-readable storage medium and downloaded through a network and will be stored in a local storage medium, so that the method described herein can be stored in such software processing on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. Among them, the storage medium can be a magnetic disk, an optical disk, a read-only storage memory, a random access memory, a flash memory, a hard disk or a solid-state drive, etc.; further, the storage medium can also include a combination of the above-mentioned types of memory. It can be understood that a computer, a processor, a microprocessor controller or programmable hardware includes a storage component that can store or receive software or computer code. When the software or computer code is accessed and executed by a computer, a processor or hardware, the method shown in the above embodiment is implemented.

[0183] A portion of the present invention may be applied as a computer program product, such as a computer program instruction, which, when executed by a computer, can call or provide the method and / or technical solution according to the present invention through the operation of the computer. Those skilled in the art should understand that the form in which the computer program instruction exists in a computer-readable medium includes, but is not limited to, a source file, an executable file, an installation package file, etc. Accordingly, the way in which the computer program instruction is executed by the computer includes, but is not limited to: the computer directly executes the instruction, or the computer compiles the instruction and then executes the corresponding compiled program, or the computer reads and executes the instruction, or the computer reads and installs the instruction and then executes the corresponding installed program. Here, the computer-readable medium may be any available computer-readable storage medium or communication medium that can be accessed by the computer.

[0184] Although the embodiments of the present invention have been described with reference to the accompanying drawings, those skilled in the art may make various modifications and variations without departing from the spirit and scope of the present invention. Such modifications and variations are all within the scope defined by the appended claims.

Claims

1. A lintel model generation method, characterized in that: The method comprises: Obtaining architectural drawings, and identifying lintel information in the architectural drawings; Determining parameter information corresponding to the lintel component based on the expression type of the lintel information, the parameter information including text information, table information and detailed drawing information; Fusing the text information, the table information, and the detailed drawing information to generate structural parameters of the lintel component; According to the structural parameters, a lintel model corresponding to the lintel component is generated.

2. The method according to claim 1, characterized in that Determining text information corresponding to the lintel component based on the expression type of the lintel information includes: Obtaining description keywords corresponding to the lintel component; extracting lintel arrangement conditions, table names, and detail drawing names from the architectural drawings according to description keywords; The text information includes the lintel arrangement conditions, the table name and the detailed drawing name.

3. The method according to claim 2, characterized in that Also includes: Converting the lintel arrangement conditions into generation rules corresponding to the lintel components; The generation rule, the table name and the detailed drawing name are associated to obtain an association result.

4. The method according to claim 2, characterized in that Based on the expression type of the lintel information, determining the table information corresponding to the lintel component includes: According to the form name, locating a target form that matches the form name in the architectural drawing; Identifying table wireframe information in the target table, and determining a target cell corresponding to the table wireframe information; The table information is extracted from the target cell.

5. The method according to claim 4, characterized in that Also includes: Read the first row and column of data of the target table; The first row of data and the first column of data are input into a pre-trained first classification model, so that the first classification model predicts whether the target table is a lintel information table.

6. The method according to claim 2, characterized in that Based on the expression type of the lintel information, the detailed drawing information corresponding to the lintel component is determined, including: According to the detailed drawing name, locating a target detailed drawing that matches the detailed drawing name in the architectural drawing; Identifying detailed drawing wireframe information in the target detailed drawing, and determining a target image area intercepted by the detailed drawing wireframe information; The detailed image information is extracted from the target image area.

7. The method according to claim 6, characterized in that The extracting the detailed image information from the target image area includes: Inputting the target image region into a pre-trained second classification model so that the second classification model predicts the image type of the target detailed image; The detailed image information corresponding to the image type is extracted from the image area.

8. The method according to claim 1, characterized in that The step of fusing the text information, the table information, and the detailed drawing information to generate structural parameters of the lintel component includes: Performing coordinate analysis on the text information, the table information, and the detailed drawing information to determine first coordinate information of the text information, second coordinate information of the table information, and third coordinate information of the detailed drawing information; Aligning the first coordinate information, the second coordinate information, and the third coordinate information to establish a spatial association relationship among the text information, the table information, and the detailed drawing information; The text information, the table information and the detailed drawing information are matched according to the spatial association relationship to obtain structural parameters of the lintel component.

9. The method according to claim 8, characterized in that The matching of the text information, the table information, and the detailed drawing information according to the spatial association relationship to obtain structural parameters of the lintel component includes: Comparing the table information and the detailed drawing information using the spatial association relationship to generate a parameter comparison result; If the parameter comparison result indicates that there are missing parameters in the table information, the missing parameters are supplemented based on the detailed drawing information to obtain supplemented table information; Based on the text information and the supplemented table information, structural parameters of the lintel component are generated.

10. The method according to claim 1, characterized in that Generating a lintel model corresponding to the lintel component according to the structural parameters includes: Obtaining a target position of a lintel to be generated in the architectural drawing; The lintel model is generated at the target position according to the structural parameters.

11. A lintel model generating device, characterized in that: The device comprises: An acquisition module, configured to acquire architectural drawings and identify lintel information in the architectural drawings; a determination module, configured to determine parameter information corresponding to the lintel component based on the expression type of the lintel information, wherein the parameter information includes text information, table information, and detailed drawing information; A fusion module, configured to fuse the text information, the table information, and the detailed drawing information to generate structural parameters of the lintel component; A generation module is used to generate a lintel model corresponding to the lintel component according to the structural parameters.

12. A computer program product, characterized in that The method comprises computer instructions for causing a computer to execute the lintel model generating method according to any one of claims 1 to 10.

Images