Intelligent generation and application method and system for structural data of engineering drawings

Abstract

The invention discloses an intelligent generation and application method and system for structural data of an engineering drawing, and the method comprises the steps: obtaining the engineering drawing, analyzing the engineering drawing, and determining a data relation, graphic data, text data and image data reflected by the engineering drawing; screening, identifying and combining the data relationship, the graphic data, the text data and the image data to obtain a drawing object, a component object and a space object; and outputting engineering drawing structured data based on the drawing object, the component object and the space object, and applying the engineering drawing structured data. According to the method, the engineering drawing is analyzed and the data of the engineering drawing is structured, so that the processing efficiency and accuracy of the engineering drawing are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of BIM architectural design, and in particular to an intelligent generation and application method and system for structured data of engineering drawings. Background Art

[0002] With the development of the construction engineering field, production tools and working methods have also undergone varying degrees of changes, and there are higher demands for the delivery and use of results, from traditional paper and electronic documents to structured data requirements with business semantics, in order to drive the automation and intelligence of business scenarios.

[0003] At present, the data carriers of construction projects are mainly document drawings and BIM models, and a large number of drawings are the main ones. The understanding and application of the existing large amount of drawing data is of great significance to the next stage of intelligent reshaping of business flows. The engineering results data will also be derived from a single drawing or model to a composite application scenario of drawings + models. Combined with the breakthrough progress made in multimodal large model technology in the field of AI in recent years, it will greatly change or reshape the existing business flow and promote industry changes in the engineering field in a more efficient way. The systematic understanding of text, graphics, and voice based on multimodal large models, and the text-generated images, graphics-generated images, and graphics-generated videos bring more possibilities to solution creation, but the breakthroughs brought in the design and construction stages with strong constraints and strong rules are limited, and this stage happens to have a large number of repetitive and low value-added processes.

[0004] Traditional documentation and electronic business based on engineering drawings requires the understanding and transmission of professionals to be used, which limits the possibility of automation and intelligence based on engineering drawings, and it is difficult to improve efficiency and quality. Summary of the invention

[0005] The technical problem to be solved by the present invention is that, in response to the above-mentioned defects of the prior art, a method and system for intelligent generation and application of structured data of engineering drawings is provided, aiming to solve the problem in the prior art that documentation and electronic business based on engineering drawings need to be understood and transmitted by professionals before they can be used, which limits the possibility of automation and intelligence of engineering drawing-based applications, and makes it difficult to improve efficiency and quality.

[0006] In order to solve the above technical problems, the technical solution adopted by the present invention is as follows:

[0007] In a first aspect, the present invention provides a method for intelligently generating and applying structured data of engineering drawings, wherein the method comprises:

[0008] Acquire engineering drawings, and parse the engineering drawings to determine data relationships, graphic data, text data, and image data reflected in the engineering drawings;

[0009] Screening, identifying and combining the data relationship, the graphic data, the text data and the image data to obtain drawing objects, component objects and space objects;

[0010] The engineering drawing structured data is output based on the drawing surface object, the component object and the space object, and the engineering drawing structured data is applied.

[0011] In one implementation, the obtaining of the engineering drawings and parsing of the engineering drawings to determine the data relationship, graphic data, text data, and image data reflected in the engineering drawings include:

[0012] Based on the business nodes, obtain the engineering drawings corresponding to each business node;

[0013] Pre-processing the engineering drawings, and parsing the pre-processed engineering drawings to obtain basic data in the engineering drawings, wherein the basic data includes any one or more of layers, primitives, line types, fonts, and dictionaries;

[0014] Based on the basic data, the data relationship, the graphic data, the text data and the image data are obtained.

[0015] In one implementation, the pre-processing includes any one or more of cleaning processing, repairing processing, binding processing, merging processing, deduplication processing, interruption processing, and cutting processing.

[0016] In one implementation, the screening, identifying and combining the data relationship, the graphic data, the text data and the image data to obtain the drawing object, the component object and the space object includes:

[0017] Performing graphic metadata screening on the data relationship, the graphic data, and the text data through a business logic algorithm;

[0018] Performing metadata recognition on the text data and the image data through a multimodal large model;

[0019] The graphic element data obtained through screening and identification are combined to obtain the drawing object, the component object and the space object.

[0020] In one implementation, the outputting of engineering drawing structured data based on the drawing object, the component object, and the space object includes:

[0021] Respectively determine the business nodes corresponding to the drawing object, the component object and the space object;

[0022] Output the engineering drawing structured data corresponding to each business node respectively.

[0023] In one implementation, the method for intelligently generating and applying engineering drawing structured data further includes:

[0024] Determine the business identification scenario based on the expression form of business nodes and engineering drawing habits;

[0025] Based on semantic inference, the business semantic relationship between single business nodes is formed to form a project structure tree.

[0026] In one implementation, the applying the engineering drawing structured data includes:

[0027] Based on the intelligent jump business identification scenario driven by the structured data of the engineering drawing, the project structure tree is accessed to intelligently organize the drawings.

[0028] In a second aspect, an embodiment of the present invention further provides an intelligent generation and application system for structured data of engineering drawings, wherein the system comprises:

[0029] A drawing parsing module, used to obtain engineering drawings, and parse the engineering drawings to determine the data relationship, graphic data, text data and image data reflected in the engineering drawings;

[0030] A graphic object recognition module, used for screening, recognizing and combining the data relationship, the graphic data, the text data and the image data to obtain a drawing object, a component object and a space object;

[0031] The structured data output module is used to output engineering drawing structured data based on the drawing surface object, the component object and the space object, and apply the engineering drawing structured data.

[0032] In a third aspect, an embodiment of the present invention further provides a terminal, wherein the terminal includes a memory, a processor, and an intelligent generation and application program of engineering drawing structured data stored in the memory and executable on the processor, and when the processor executes the intelligent generation and application program of engineering drawing structured data, the steps of the intelligent generation and application method of engineering drawing structured data of any one of the above-mentioned schemes are implemented.

[0033] In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium, wherein the computer-readable storage medium stores intelligent generation and application of engineering drawing structured data, and when the intelligent generation and application of engineering drawing structured data is executed by a processor, the steps of the method for intelligent generation and application of engineering drawing structured data described in any one of the above-mentioned schemes are implemented.

[0034] Beneficial effects: Compared with the prior art, the present invention provides an intelligent generation and application method of structured data of engineering drawings. The present invention first obtains engineering drawings, and parses the engineering drawings to determine the data relationship, graphic data, text data and image data reflected in the engineering drawings; then, the data relationship, the graphic data, the text data and the image data are screened, identified and combined to obtain drawing objects, component objects and space objects; then, based on the drawing objects, the component objects and the space objects, the structured data of the engineering drawings are output, and the structured data of the engineering drawings are applied. The present invention converts the multivariate data in the engineering drawings, including data relationships, graphics, text and image data, into manageable drawing objects, component objects and space objects through comprehensive analysis and intelligent processing, and then generates structured engineering drawing data, thereby realizing efficient extraction and application of complex drawing information, and greatly improving the accuracy and efficiency of engineering design, management and maintenance. This method not only optimizes the limitations of traditional drawing analysis, but also provides strong technical support for the digital transformation of engineering projects. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] Figure 1 A flowchart of a specific implementation method of the intelligent generation and application method of engineering drawing structured data provided by an embodiment of the present invention.

[0036] Figure 2 A schematic diagram of the decomposition of the core data of an engineering drawing set based on the project dimension in the intelligent generation and application method of engineering drawing structured data provided in an embodiment of the present invention.

[0037] Figure 3 A flow chart of parsing an engineering drawing in the intelligent generation and application method of engineering drawing structured data provided by an embodiment of the present invention.

[0038] Figure 4 A schematic diagram of the technical path of the business node image recognition engine based on the intelligent generation and application method of engineering drawing structured data provided in an embodiment of the present invention.

[0039] Figure 5 A flow chart for identifying graphic primitive objects in the intelligent generation and application method of engineering drawing structured data provided by an embodiment of the present invention.

[0040] Figure 6 A flow chart of structured data output in the intelligent generation and application method of structured data of engineering drawings provided in an embodiment of the present invention.

[0041] Figure 7 A principle block diagram of an intelligent generation and application system for structured data of engineering drawings provided in an embodiment of the present invention.

[0042] Figure 8 A functional block diagram of a terminal provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0043] In order to make the purpose, technical solution and effect of the present invention clearer and more specific, the present invention is further described in detail with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0044] In the continuous evolution of the construction engineering field, along with the innovation of production tools and working methods, the industry's expectations for delivery results have gone beyond traditional paper and electronic documents, and turned to seeking structured data rich in business semantics, aiming to promote the automation and intelligent transformation of business processes. At present, data carrying mainly relies on drawings and BIM models, especially massive drawings, whose in-depth analysis and utilization are crucial for the reconstruction of future intelligent business processes. In recent years, the breakthrough progress of multimodal big models in the field of AI indicates that the form of engineering data will transition from a single drawing or model to a "drawing + model" composite application, greatly promoting business efficiency improvement and industry innovation. However, although multimodal big models show great potential in creative generation, such as text-generated images, images-generated images, and images-generated videos, their ability to achieve breakthroughs is limited in the strong rules and constraints of design and construction, facing processes with high repetitiveness and low value density. Traditional engineering drawing documentation and electronic business rely too much on the understanding and information transmission of professionals, which not only limits the potential of engineering drawings in automation and intelligent applications, but also makes it difficult to achieve the goals of efficiency improvement and quality enhancement. Therefore, how to use advanced technology to overcome existing challenges while maintaining engineering precision has become a key issue that the industry needs to solve urgently.

[0045] Therefore, in order to solve the above problems, the present embodiment provides an intelligent generation and application method of structured data of engineering drawings. In specific implementation, the present embodiment first obtains engineering drawings, and parses the engineering drawings to determine the data relationship, graphic data, text data and image data reflected in the engineering drawings; then, the data relationship, the graphic data, the text data and the image data are screened, identified and combined to obtain drawing objects, component objects and space objects; then, based on the drawing objects, the component objects and the space objects, the structured data of the engineering drawings are output, and the structured data of the engineering drawings are applied. The present invention converts the multivariate data in the engineering drawings, including data relationships, graphics, text and image data, into manageable drawing objects, component objects and space objects through comprehensive analysis and intelligent processing, and then generates structured engineering drawing data, thereby realizing efficient extraction and application of complex drawing information, and greatly improving the accuracy and efficiency of engineering design, management and maintenance. This method not only optimizes the limitations of traditional drawing parsing, but also provides strong technical support for the digital transformation of engineering projects.

[0046] For example, when designing a large commercial complex, especially when the building contains multiple floors, and each floor has a complex structural layout and diverse equipment installation requirements, the limitations of traditional engineering drawings are highlighted. Traditional engineering drawings are usually presented in the form of two-dimensional or three-dimensional graphics, which contain rich graphics, text and image information, but this information is often unstructured, which makes information retrieval and management in the design, construction, maintenance and other stages difficult and time-consuming. At this time, the method for generating and applying structured data of engineering drawings proposed in this embodiment can be adopted. First, the engineering drawings of a large commercial complex are obtained, and the engineering drawings are parsed to determine the data relationship, graphic data, text data and image data reflected in the engineering drawings; then, the data relationship, the graphic data, the text data and the image data are screened, identified and combined to obtain drawing objects, component objects and space objects; then, the engineering drawing structured data is output based on the drawing objects, the component objects and the space objects, and the engineering drawing structured data is applied. For example, during the construction phase, engineers can quickly locate the corresponding location on the drawing by searching for specific component objects, and understand their detailed size, material, and installation requirements, without having to manually flip through a large number of drawing files. Similarly, in later maintenance work, facility managers can easily view all equipment information and historical records in a certain area through spatial objects, making it easier to arrange regular inspections and maintenance plans. The implementation of this method has greatly improved the level of informatization of engineering projects, reduced human errors, shortened work cycles, and also provided a solid foundation for subsequent digital management.

[0047] The present embodiment provides an intelligent generation and application method of structured data of engineering drawings, which can be applied to intelligent terminals, such as Figure 1 As shown in , the specific steps include:

[0048] Step S100: Acquire an engineering drawing, and parse the engineering drawing to determine the data relationship, graphic data, text data, and image data reflected in the engineering drawing.

[0049] In this embodiment, the engineering drawings are an important basis for the design and construction of engineering projects. They record in detail the structure, size, materials, process requirements and other information of the engineering projects. When drawing engineering drawings, professional designers will refer to various documents such as historical project information, industry standards and specifications, materials and equipment instructions, etc., to ensure the accuracy and feasibility of the design. The engineering drawings can be architectural drawings, mechanical drawings, electrical drawings, pipeline drawings and other types. When implementing this embodiment, it is first necessary to obtain an electronic or scanned version of the engineering drawings. The acquisition method may include directly exporting from the design software, obtaining a digital version by scanning paper drawings, etc. Next, the engineering drawings are parsed, and the parsing tools include but are not limited to ODA Drawings SDK, AutoCAD API, LibreDWG, Teigha File Converter, GEM forAutoCAD and Onshape API, etc. Then, the data relationship, graphic data, text data and image data reflected in the engineering drawings are determined. The above process is as follows: Figure 2 In summary, this embodiment converts complex, unstructured drawings into discrete data elements that can be further processed and analyzed by deeply analyzing and extracting data from the original engineering drawings, laying the foundation for subsequent screening, identification and combination operations.

[0050] In one implementation, Figure 3 As shown in , step S100 specifically includes the following steps:

[0051] Step S101: Based on the business nodes, obtain the engineering drawings corresponding to each business node;

[0052] Step S102, pre-processing the engineering drawings, and parsing the pre-processed engineering drawings to obtain basic data in the engineering drawings, wherein the basic data includes any one or more of layers, graphic elements, line types, fonts, and dictionaries;

[0053] Step S103: Based on the basic data, obtain the data relationship, the graphic data, the text data and the image data.

[0054] In one implementation, the present embodiment first obtains the engineering drawings corresponding to each business node based on the business node; then, the engineering drawings are pre-processed to ensure the quality and integrity of the drawing data, and the pre-processing includes: any one or more of cleaning, repairing, binding, merging, deduplication, interruption, and cutting; then, the pre-processed engineering drawings are parsed to obtain the basic data in the engineering drawings, and the basic data includes: any one or more of layers, primitives, line types, fonts, and dictionaries; finally, based on the basic data, the data relationship, the graphic data, the text data, and the image data are obtained. The above process is as follows. Figure 4 As shown. The data relationship refers to the logical and physical connection between the elements in the drawing. For example, in the architectural drawing, there is a spatial position relationship and connection relationship between the elements such as walls, doors, windows, stairs, etc. This relationship defines the structural layout of the building; the data relationship also includes hierarchical relationships, such as the relationship between the general drawing and the sub-drawing, and time series relationships, such as the order of construction stages. The graphic data refers to information expressed by geometric shapes, including but not limited to basic graphic elements such as points, lines, surfaces, and bodies. In engineering drawings, graphic data can include wall outlines, door and window openings, equipment shapes, pipeline directions, etc. For example, a line on a building plan can indicate the location of a wall. The text data refers to text information used for description and explanation on the drawing, which includes annotations, notes, technical requirements, material specifications, dimension values, etc. For example, "M3" on the drawing means that a bolt with a diameter of 3 mm is required at a certain position, and "C25" refers to a concrete strength grade of 25MPa. In addition, the text data can also include metadata such as project number, project name, and design unit. The image data refers to non-vector images embedded in drawings, such as photos, scans or renderings. Such data is often used to display actual scenes, complex structural details or effect previews. For example, a photo of a building facade can help illustrate the design intent, while a high-definition picture of a device can help identify and locate specific components. Through the above steps, this embodiment improves the efficiency of data processing and ensures the accuracy and consistency of data, providing strong support for the digital management and intelligent analysis of engineering projects.

[0055] Step S200: screening, identifying and combining the data relationship, the graphic data, the text data and the image data to obtain drawing objects, component objects and space objects.

[0056] After obtaining the data relationship, the graphic data, the text data and the image data, this embodiment screens, identifies and combines the data relationship, the graphic data, the text data and the image data to obtain a drawing object, a component object and a space object, such as Figure 2 As shown. The drawing objects include core business objects such as catalog, drawing frame, axis grid, description, and floor height. The component objects include professional component elements such as walls, beams, plates, pipes, and equipment. The space objects include space information such as sites, buildings, floors, apartment types, and rooms. This embodiment converts the unstructured data extracted from engineering drawings into more meaningful and easy-to-process structured objects, improves the readability and usability of the data, and enables the originally complex and unstructured drawing information to be presented in a systematic and structured manner.

[0057] In one implementation, Figure 5 As shown in , the step S200 specifically includes:

[0058] Step S201, performing graphic data screening on the data relationship, the graphic data, and the text data through a business logic algorithm;

[0059] Step S202, performing metadata recognition on the text data and the image data through a multimodal large model;

[0060] Step S203: Combine the image metadata obtained through screening and identification to obtain the drawing object, the component object and the space object.

[0061] In specific implementation, after obtaining the data relationship, the graphic data, the text data and the image data, the embodiment first performs metadata screening on the data relationship, the graphic data and the text data through a business logic algorithm. For example, in a building plan, the business logic algorithm can intelligently identify which lines represent walls and which represent doors and windows, and can even distinguish different materials or functional areas represented by different line types or line widths. For another example, when a complex equipment layout appears on the drawing, the business logic algorithm can accurately determine the connection method between the equipment, such as the direction and interface location of pipelines and cables. In addition, for text data, such as annotations, comments or technical requirements, the business logic algorithm can extract and classify this information to ensure that it is correctly reflected in subsequent structured data. Then, the text data and the image data are subjected to metadata recognition through a multimodal large model. The multimodal large model can understand the semantics in the drawing and can identify key information even in hand-drawn sketches or blurred images. For example, if an area on a drawing is marked as a "firewall", the multimodal large model can not only recognize the word "firewall", but also understand its meaning in context and correctly classify it into structured data. Similarly, for complex symbols or icons in the image, such as fire hydrants, distribution boxes, etc., the multimodal large model can also accurately identify and convert them into corresponding data entries. Then, the image metadata obtained after screening and identification are combined to obtain the drawing object, the component object and the space object. This sophisticated data division and combination ensures that the final output engineering drawing structured data not only fully reflects the information of the original drawing, but also has a high degree of readability and operability, improves the efficiency of data utilization, reduces the errors and time cost of manual interpretation of drawings, and creates conditions for intelligent design and automated construction.

[0062] Step S300: output engineering drawing structured data based on the drawing object, the component object and the space object, and apply the engineering drawing structured data.

[0063] After acquiring the drawing object, the component object and the space object, this embodiment outputs the engineering drawing structured data based on the drawing object, the component object and the space object, and applies the engineering drawing structured data. As the basis of engineering drawings, the drawing object not only includes basic elements such as catalog, drawing frame, axis grid, description, but also covers key information such as floor height, scale, annotation, legend, etc. For example, in the floor plan of a building, the axis grid is used to define the spatial layout, the drawing frame clarifies the boundaries of the drawing, and the description explains the material specifications and construction requirements in detail. The floor height accurately calibrates the vertical distance between floors. By identifying these drawing elements and giving them corresponding labels and attributes, a structured database containing all detailed information can be constructed. The component object can be a specific physical entity on the drawing, such as a beam, a window or a pipe. Each component has its own unique size, position, material and function. During the structuring process, an entry will be created for each component to record all its relevant attributes to form a component data set. For example, for a window, the structured data may include the window type (sliding window, casement window), size (width × height), installation location (floor, room, wall), opening direction, etc. The spatial object involves the spatial layout on the drawing, such as the relative position and connection between rooms, floors, and buildings. This step requires understanding the plane layout on the drawing and converting it into a three-dimensional model or a spatial relationship network. For example, through analysis, the four walls of a room, the location of the door, the relationship with the adjacent rooms, and even the streamline design of the entire floor can be identified, thereby constructing a clear spatial structure diagram. Ultimately, these structured data can be used in a variety of application scenarios, such as automatic cost estimation, construction progress simulation, material list generation, collision detection, virtual reality display, etc., greatly improving the efficiency and accuracy of engineering projects. For example, in the cost estimation scenario, the system can quickly calculate the type and quantity of required materials based on structured data, and give a project budget based on market prices; during the construction phase, through virtual reality technology, engineers can preview the construction results in person, discover and solve potential problems in advance, and the method of this embodiment makes the originally static drawing information dynamic and more interactive, providing all-round support for engineering projects. This embodiment greatly improves the management and application efficiency of information by converting the drawings, components, and spatial objects of engineering drawings into structured data, supports full-cycle project management, promotes the digital transformation of the construction industry, enhances collaborative work, reduces errors, and reduces costs.

[0064] In one implementation, Figure 6 As shown, the step S300 specifically includes:

[0065] Step S301, respectively determining the business nodes corresponding to the drawing object, the component object and the space object;

[0066] Step S302: Output the engineering drawing structured data corresponding to each business node respectively.

[0067] In the specific implementation, in the process of converting the drawing object, the component object and the space object into the structured data of the engineering drawing, the corresponding relationship between these objects and the actual engineering business process must be clarified, that is, the business nodes to which they correspond must be determined. Each business node represents a specific link in engineering management, design or construction. Through the structured data associated with it, accurate control and optimization of each link can be achieved. The mapping of the drawing object to the business node: For example, the "frame" on the engineering drawing can be mapped to the "drawing standardization and review" business node. This node ensures that all drawings follow a unified drawing standard, which is easy to identify and understand. For example, the review signature area contained in the frame is part of the quality control process, ensuring that each drawing has undergone appropriate technical review before release. The mapping of the component object to the business node: Each specific component, such as "precast concrete beam", will be linked to the "precast component production and installation" business node. The structured data under this node includes not only the size, weight and strength grade of the beam, but also its production batch, transportation and hoisting plan, etc., which ensures that the whole process of the component from manufacturing to on-site assembly is controllable. Mapping of the spatial objects to business nodes: spatial layout information, such as "office area planning", is closely linked to the "interior design and space utilization" business node. In this node, not only the room area, shape, furniture arrangement and other details are included, but also environmental factors such as ventilation, lighting, and personnel flow are taken into account to ensure that the space is both practical and comfortable. At the same time, this mapping can also help plan evacuation routes and improve safety. Collaboration of comprehensive business nodes: In large-scale engineering projects, there are complex dependencies between multiple business nodes. For example, the "structural engineering" and "water supply and drainage system design" nodes need to work closely together when dealing with the basement part. While ensuring the structural safety, it is also necessary to consider that the layout of drainage facilities will not affect the load-bearing structure. Through the integration and sharing of structured data, design conflicts can be effectively avoided and communication and coordination between cross-disciplinary teams can be promoted. Through the above-mentioned refined business node mapping, each engineering drawing structured data can directly serve the decision-making and execution monitoring in actual work, realizing seamless connection from drawings to the real world, and significantly improving the quality and efficiency of engineering projects. In addition, the accumulation of this structured data also lays a solid foundation for subsequent project review, knowledge management and even artificial intelligence-assisted design.

[0068] In addition, this embodiment explores automated and intelligent application scenarios such as intelligent conversion of drawings and automatic association of drawing models from the perspective of engineering drawings. First, based on the expression form of business nodes and the habit of drawing engineering drawings, the business identification scenario is determined. For example, in the field of architecture, one business node may refer to the "main entrance" and another business node may be the "reception area". Based on these nodes, a series of scenarios can be determined, such as "main entrance design" and "reception area layout", which helps the system understand the meaning and function of drawing elements; then, based on semantics, the business semantic relationship between single business nodes is inferred to form a project structure tree. For example, the "main entrance" may be directly related to the "external channel", while the "reception area" may be related to the "rest area" or "front desk". By analyzing these relationships, a clear project structure tree can be constructed to help users quickly understand and locate the various parts in the drawings; then, based on the intelligent jump business recognition scenario driven by the structured data of the engineering drawing, the project structure tree is accessed to intelligently organize the drawings. For example, when the user views the design of the "main entrance" on the drawing, the system can automatically identify and jump to the "external channel" part related to it, or when the user pays attention to the "reception area", the system can intelligently recommend viewing the design of the "rest area" or "front desk". This intelligent jump not only improves work efficiency, but also enhances the readability and ease of use of the drawings. Realize the intelligent jump of the drawing directory and the drawing area based on the drawing frame, verify the consistency of the drawing directory and the drawing frame, drive structured viewing and use of drawings, and greatly improve the efficiency of drawing sorting and drawing data acquisition. In addition, this embodiment proposes a diagram model intelligent positioning scenario driven by structured data of engineering drawings. The structured data of the engineering drawings output by this embodiment can be used to drive the automatic positioning between the drawings and the BIM model, and realize the precise matching of the two in spatial position. For example, during the design phase of a high-rise building, a designer may draw a detailed floor plan, including the location information of elements such as walls, doors, windows, and stairs. Through the method proposed in this embodiment, these floor plans can be quickly parsed to extract the length and height of each wall, the width of each door, and their relative positions in the floor. Subsequently, this information will be used to automatically locate the corresponding components in the BIM model to ensure that the model and the drawings are completely consistent in detail. In addition, for complex underground pipeline systems, through the analysis of structured data, the direction, diameter, and connection points of each pipeline can be accurately reproduced in the three-dimensional model, greatly improving the efficiency and accuracy of the composite use of engineering drawings and BIM models. This process not only significantly reduces the need for manual intervention, reduces the error rate, but also greatly improves work efficiency. More importantly, it provides strong support for the digital management of engineering projects, helps to achieve seamless connection of various links such as design, construction, operation and maintenance, thereby comprehensively improving engineering quality and safety.For example, in bridge construction, from the location of piers to the span of beams, to the layout of various prestressed steel bars, all these details can be automatically compared and adjusted through the method proposed in this embodiment, ensuring that on-site construction is highly consistent with the design drawings and avoiding rework and delays due to inconsistent information.

[0069] In summary, this embodiment first obtains engineering drawings, and parses the engineering drawings to determine the data relationships, graphic data, text data, and image data reflected in the engineering drawings; then, the data relationships, graphic data, text data, and image data are screened, identified, and combined to obtain drawing objects, component objects, and space objects; then, based on the drawing objects, component objects, and space objects, the engineering drawing structured data is output, and the engineering drawing structured data is applied. The present invention converts multivariate data in engineering drawings, including data relationships, graphics, text, and image data, into manageable drawing objects, component objects, and space objects through comprehensive analysis and intelligent processing, and then generates structured engineering drawing data, thereby achieving efficient extraction and application of complex drawing information, and greatly improving the accuracy and efficiency of engineering design, management, and maintenance. This method not only optimizes the limitations of traditional drawing parsing, but also provides strong technical support for the digital transformation of engineering projects.

[0070] like Figure 7 As shown in , this embodiment also provides an intelligent generation and application system for structured data of engineering drawings, which includes: a drawing parsing module 10, a graphic element object recognition module 20 and a structured data output module 30. Specifically, the drawing parsing module 10 is used to obtain engineering drawings, and parse the engineering drawings to determine the data relationships, graphic data, text data and image data reflected in the engineering drawings. The graphic element object recognition module 20 is used to screen, identify and combine the data relationships, the graphic data, the text data and the image data to obtain drawing objects, component objects and space objects. The structured data output module 30 is used to output the structured data of the engineering drawings based on the drawing objects, the component objects and the space objects, and apply the structured data of the engineering drawings.

[0071] In one implementation, the drawing parsing module 10 includes:

[0072] An engineering drawing acquisition unit, based on the business node, acquires the engineering drawing corresponding to each business node;

[0073] A drawing parsing unit pre-processes the engineering drawing and parses the pre-processed engineering drawing to obtain basic data in the engineering drawing, wherein the basic data includes any one or more of layers, primitives, line types, fonts, and dictionaries;

[0074] The data and data relationship acquisition unit obtains the data relationship, the graphic data, the text data and the image data based on the basic data.

[0075] In one implementation, the primitive object recognition module 20 includes:

[0076] A graphic metadata screening unit, used for screening the graphic metadata of the data relationship, the graphic data and the text data through a business logic algorithm;

[0077] An image metadata recognition unit, used for performing image metadata recognition on the text data and the image data through a multimodal large model;

[0078] The object acquisition unit is used to combine the image metadata obtained through screening and identification to obtain the drawing object, the component object and the space object.

[0079] In one implementation, the structured data output module 30 includes:

[0080] A service node determination unit, used to respectively determine the service nodes corresponding to the drawing object, the component object and the space object;

[0081] The structured data output unit is used to output the engineering drawing structured data corresponding to each business node respectively.

[0082] In one implementation, the method for intelligently generating and applying structured data of engineering drawings further includes:

[0083] A business identification scenario determination unit determines the business identification scenario based on the expression form of the business node and the drawing habits of the engineering drawing;

[0084] The project structure tree forming unit forms a project structure tree based on semantic inference of the business semantic relationship between single business nodes.

[0085] An intelligent drawing arrangement unit is connected to the project structure tree and intelligently arranges drawings based on an intelligent jump business recognition scenario driven by the structured data of the engineering drawing.

[0086] The working principles of each module in the intelligent generation and application system of engineering drawing structured data of this embodiment are the same as the principles of each step in the above method embodiment, and will not be repeated here.

[0087] Based on the above embodiment, the present invention further provides a terminal, the principle block diagram of the terminal can be as follows: Figure 8 The terminal may include one or more processors 100 ( Figure 8 Only one is shown in the figure), a memory 101 and a computer program 102 stored in the memory 101 and executable on one or more processors 100, for example, an intelligent generation and application of structured data of engineering drawings. When one or more processors 100 execute the computer program 102, each step in the embodiment of the method for intelligent generation and application of structured data of engineering drawings can be implemented. Alternatively, when one or more processors 100 execute the computer program 102, the functions of each module / unit in the embodiment of the method for intelligent generation and application of structured data of engineering drawings can be implemented, which is not limited here.

[0088] In one embodiment, the processor 100 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc.

[0089] In one embodiment, the memory 101 may be an internal storage unit of an electronic device, such as a hard disk or memory of the electronic device. The memory 101 may also be an external storage device of the electronic device, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the electronic device. Further, the memory 101 may also include both an internal storage unit of the electronic device and an external storage device. The memory 101 is used to store computer programs and other programs and data required by the terminal. The memory 101 may also be used to temporarily store data that has been output or is to be output.

[0090] Those skilled in the art will understand that Figure 8The principle block diagram shown in the figure is only a block diagram of a partial structure related to the scheme of the present invention, and does not constitute a limitation on the terminal to which the scheme of the present invention is applied. The specific terminal may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0091] Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, operating database or other media used in the embodiments provided by the present invention may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double operational data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0092] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. An intelligent generation and application method for structured data of engineering drawings, characterized in that: The method comprises: Acquire engineering drawings, and parse the engineering drawings to determine data relationships, graphic data, text data, and image data reflected in the engineering drawings; Screening, identifying and combining the data relationship, the graphic data, the text data and the image data to obtain drawing objects, component objects and space objects; The engineering drawing structured data is output based on the drawing surface object, the component object and the space object, and the engineering drawing structured data is applied.

2. The intelligent generation and application method of engineering drawing structured data according to claim 1 is characterized in that: The obtaining of the engineering drawings and parsing of the engineering drawings to determine the data relationship, graphic data, text data and image data reflected in the engineering drawings include: Based on the business nodes, obtain the engineering drawings corresponding to each business node; Pre-processing the engineering drawings, and parsing the pre-processed engineering drawings to obtain basic data in the engineering drawings, wherein the basic data includes any one or more of layers, primitives, line types, fonts, and dictionaries; Based on the basic data, the data relationship, the graphic data, the text data and the image data are obtained.

3. The intelligent generation and application method of engineering drawing structured data according to claim 2 is characterized in that: The pre-processing includes: any one or more of cleaning processing, repairing processing, binding processing, merging processing, deduplication processing, interruption processing, and cutting processing.

4. The intelligent generation and application method of engineering drawing structured data according to claim 1 is characterized in that: The screening, identification and combination of the data relationship, the graphic data, the text data and the image data to obtain the drawing object, the component object and the space object includes: Performing graphic metadata screening on the data relationship, the graphic data, and the text data through a business logic algorithm; Performing metadata recognition on the text data and the image data through a multimodal large model; The graphic element data obtained through screening and identification are combined to obtain the drawing object, the component object and the space object.

5. The intelligent generation and application method of engineering drawing structured data according to claim 1, characterized in that: The outputting of engineering drawing structured data based on the drawing surface object, the component object and the space object comprises: Respectively determine the business nodes corresponding to the drawing object, the component object and the space object; Output the engineering drawing structured data corresponding to each business node respectively.

6. The intelligent generation and application method of engineering drawing structured data according to claim 1, characterized in that: The method further comprises: Determine the business identification scenario based on the expression form of business nodes and engineering drawing habits; Based on semantic inference, the business semantic relationship between single business nodes is formed to form a project structure tree.

7. The intelligent generation and application method of engineering drawing structured data according to claim 6, characterized in that: The applying of the engineering drawing structured data includes: Based on the intelligent jump business identification scenario driven by the structured data of the engineering drawing, the project structure tree is accessed to intelligently organize the drawings.

8. An intelligent generation and application system for structured data of engineering drawings, characterized in that: The system comprises: A drawing parsing module, used to obtain engineering drawings, and parse the engineering drawings to determine the data relationship, graphic data, text data and image data reflected in the engineering drawings; A graphic object recognition module, used for screening, recognizing and combining the data relationship, the graphic data, the text data and the image data to obtain a drawing object, a component object and a space object; The structured data output module is used to output engineering drawing structured data based on the drawing surface object, the component object and the space object, and apply the engineering drawing structured data.

9. A terminal, characterized in that: The terminal includes a memory, a processor, and an intelligent generation and application program of engineering drawing structured data stored in the memory and executable on the processor. When the processor executes the intelligent generation and application program of engineering drawing structured data, the steps of the intelligent generation and application method of engineering drawing structured data as described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores intelligent generation and application of engineering drawing structured data. When the intelligent generation and application of engineering drawing structured data is executed by the processor, the steps of the method for intelligent generation and application of engineering drawing structured data as described in any one of claims 1 to 7 are implemented.

Images