Building engineering drawing jump link automatic generation method and device, equipment and medium

Abstract

Embodiments of the present application disclose a kind of construction engineering drawing jump link automatic generation method, device, equipment and medium, involve jump link generation technical field.The method includes: receiving drawing file, identifying jump source and jump target from the drawing file;Based on the jump source, generate jump source object and generate jump target object based on the jump target;From all the jump target object, determine the target jump target object matched with the jump source object;Establish the jump link between the jump source object and the target jump target object.The present application solves the core problems of low efficiency, insufficient accuracy and maintenance difficulty of prior art by integrated process of automatic identification, object structured construction, intelligent matching and automatic link establishment, provides efficient, accurate and sustainable maintenance drawing correlation navigation technology support for large engineering projects.

Description

Technical Field

[0001] This invention relates to the field of jump link generation technology, and in particular to a method, apparatus, equipment and medium for automatically generating jump links in architectural engineering drawings. Background Technology

[0002] In modern engineering design, particularly in industries such as architecture, machinery, and electronics, electronic drawings have become a crucial carrier of design information. To enhance the interrelationships between drawings and improve information retrieval efficiency, mainstream electronic drawing editing tools generally integrate hyperlink functionality. This feature allows designers to establish links between specific elements in a drawing (such as graphic entities, annotation symbols, identification numbers, or text areas) and other related drawings, different locations within the same drawing, or external technical documents (such as standard drawing sets and industry specification documents). By activating these links, users can easily navigate across drawings or documents, which to some extent assists in the association and traceability of design information.

[0003] However, existing hyperlink creation mechanisms have significant limitations. The core problem lies in the fact that the entire link creation process is highly dependent on manual operation: users must manually select the source object (e.g., figure or text) as the starting point for the jump, and specify the precise location of the target (e.g., the path to the target drawing file, or a specific location within the document). The system itself lacks the ability to automatically recognize design semantics, object relationships, and the internal logic of the document, and cannot intelligently infer and generate corresponding jump links based on context.

[0004] This entirely manual approach works well for small or simple projects, but it reveals fundamental flaws when dealing with large and complex engineering projects. Such projects typically involve massive amounts of drawings, complex object types, and multi-dimensional reference relationships (such as inter-drawing references, standard clause references, and component detail connections). Manually creating and maintaining such a large number of diverse jump links is not only extremely tedious, time-consuming, and inefficient, but also highly susceptible to human error leading to missing, incorrect, or broken links. As project size increases and design versions iterate, the cost of link maintenance grows non-linearly, and the accuracy and completeness of links become difficult to guarantee. Ultimately, this makes it difficult for this function to effectively support the systematic management and dynamic maintenance needs of large-scale, multi-type jump relationships in practical engineering applications.

[0005] Therefore, the bottleneck of existing technologies lies in the lack of automated and intelligent link identification and generation capabilities, resulting in a significant gap between the efficiency of creating and maintaining jump links and the urgent need for efficient information association and navigation in large-scale engineering projects. New technological approaches are urgently needed to resolve this core contradiction. Summary of the Invention

[0006] This invention provides a method, apparatus, equipment, and medium for automatically generating jump links in architectural engineering drawings, aiming to solve the problem of low efficiency caused by reliance on manual operation in existing jump link generation technologies.

[0007] In a first aspect, embodiments of the present invention provide a method for automatically generating jump links in architectural engineering drawings, comprising:

[0008] Receive drawing files and identify the jump source and jump target from the drawing files;

[0009] A jump source object is generated based on the jump source, and a jump target object is generated based on the jump target;

[0010] From all the jump target objects, determine the target jump target object that matches the jump source object;

[0011] Establish a jump link between the jump source object and the target jump object.

[0012] Optionally, identifying the jump source and jump target from the drawing file includes:

[0013] Identify the elements contained in the drawing file;

[0014] Elements of a first preset type are selected from the elements contained in the drawing file as the jump source;

[0015] Elements of a second preset type are selected from the elements contained in the drawing file as the jump target.

[0016] Optionally, the jump source object includes an anchor point and descriptive information, and generating the jump source object based on the jump source includes:

[0017] Obtain the first anchor point construction rule and the first description information construction rule corresponding to the type of the jump source;

[0018] The anchor point of the jump source object is obtained according to the first anchor point construction rule;

[0019] The description information of the jump source object is obtained by constructing rules based on the first description information.

[0020] Optionally, the jump target object includes anchor points and descriptive information, and generating the jump target object based on the jump target includes:

[0021] Obtain the second anchor point construction rule and the second description information construction rule corresponding to the type of the jump target;

[0022] The anchor point of the target object to be jumped is obtained according to the second anchor point construction rule;

[0023] The description information of the target object to be redirected is obtained based on the rule constructed according to the second description information.

[0024] Optionally, determining the target jump object that matches the jump source object from all the jump target objects includes:

[0025] The corresponding matching rules are determined based on the type of the jump source object;

[0026] Based on the matching rules, a target jump object that matches the jump source object is determined from all the jump target objects.

[0027] Optionally, the drawing file includes a title block area, and the method further includes:

[0028] Metadata is extracted from the label bar area, wherein the metadata is used to generate description information of the jump source object and / or the jump target object.

[0029] Optionally, extracting metadata from the label bar area includes:

[0030] If the drawing file is an image format drawing, an object detection model is used to identify the title bar area in the drawing file;

[0031] The original text in the title bar area is identified using OCR;

[0032] The fields in the original text are semantically classified to obtain the metadata.

[0033] Alternatively, if the drawing file is a vector format drawing, extract the text entities from the drawing file to obtain the original text;

[0034] The fields in the original text are semantically classified to obtain the metadata.

[0035] Secondly, embodiments of the present invention also provide an automatic generation device for jump links in architectural drawings, which includes a unit for performing the above-described method.

[0036] Thirdly, embodiments of the present invention also provide a computer device, which includes a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the above-described method.

[0037] Fourthly, embodiments of the present invention also provide a computer-readable storage medium storing a computer program that, when executed by a processor, can implement the above-described method.

[0038] This invention provides a method, apparatus, device, and medium for automatically generating jump links in architectural engineering drawings. The method includes: receiving drawing files; identifying jump sources and jump targets from the drawing files; generating a jump source object based on the jump source and a jump target object based on the jump target; determining a target jump target object matching the jump source object from all the jump target objects; and establishing a jump link between the jump source object and the target jump target object. This invention systematically solves the core problems of low efficiency, insufficient accuracy, and maintenance difficulties in existing technologies through an integrated process of automated identification, object structured construction, intelligent matching, and automatic link establishment, providing efficient, accurate, and sustainably maintainable drawing association navigation technology support for large-scale engineering projects. Attached Figure Description

[0039] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the following description of the embodiments will be briefly introduced. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0040] Figure 1 This is a flowchart illustrating the method for automatically generating navigation links for architectural drawings provided in an embodiment of the present invention.

[0041] Figure 2 A schematic block diagram of a computer device provided for an embodiment of the present invention. Detailed Implementation

[0042] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0043] It should be understood that, when used in this specification and the appended claims, the terms "comprising" and "including" indicate the presence of the described features, integrals, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components and / or collections thereof.

[0044] It should also be understood that the terminology used in this specification is for the purpose of describing particular embodiments only and is not intended to limit the invention. As used in this specification and the appended claims, the singular forms “a,” “an,” and “the” are intended to include the plural forms unless the context clearly indicates otherwise.

[0045] It should also be further understood that the term "and / or" as used in this specification and the appended claims refers to any combination of one or more of the associated listed items and all possible combinations, and includes such combinations.

[0046] As used in this specification and the appended claims, the term "if" may be interpreted, depending on the context, as "when," "once," "in response to determination," or "in response to detection." Similarly, the phrase "if determined" or "if [described condition or event] is detected" may be interpreted, depending on the context, as "once determined," "in response to determination," "once [described condition or event] is detected," or "in response to detection of [described condition or event]."

[0047] Please see Figure 1 This invention provides a method for automatically generating navigation links in architectural drawings, which includes the following steps:

[0048] S1, Receive drawing file, and identify the jump source and jump target from the drawing file.

[0049] In specific implementation, the drawing files can be architectural drawing files, and their format can be image format drawings (e.g., scanned blueprints, JPG format, etc.) or vector format drawings (e.g., DWG, DXF, etc.). This invention does not specifically limit the format. In this invention, drawing files can be received in batches. After receiving the drawing files, the jump source and jump target can be identified from the drawing files. For example, the jump source and jump target can be extracted from the drawing files using image recognition and text information extraction techniques commonly used in this field. This invention does not specifically limit the format.

[0050] This invention supports various types of jump sources, including but not limited to: drafting symbols (e.g., detail index symbols, section symbols, etc.), component numbers (e.g., numbers of components such as doors and windows), text (e.g., design specifications, annotations, etc.), legend symbols (including combinations of graphics and text), and entire drawings (e.g., jumping from architectural drawings to structural drawings), etc. This invention does not specifically limit these.

[0051] Furthermore, the present invention supports various types of jump targets, including but not limited to: detailed drawing areas, engineering table items, legend items, entire drawings, external specifications or drawing sets, etc., which are not specifically limited by the present invention.

[0052] In some preferred embodiments, the above step "identifying the jump source and jump target from the drawing file" includes: identifying the elements contained in the drawing file; selecting elements of a first preset type from the elements contained in the drawing file as the jump source; and selecting elements of a second preset type from the elements contained in the drawing file as the jump target.

[0053] In specific implementation, the elements contained in the drawing file and the types of the elements are identified using image recognition and text information extraction technologies commonly used in this field.

[0054] Furthermore, elements of a first preset type are selected from the elements contained in the drawing file as the jump source. The first preset type can be set by those skilled in the art, and is not specifically limited in this invention. For example, it can be a drafting symbol, component number, text, legend symbol, or the entire drawing.

[0055] Furthermore, elements of a second preset type are selected from the elements contained in the drawing file as the jump target. The second preset type can be set by those skilled in the art, and is not specifically limited in this invention. For example, detailed drawing area, engineering table item, legend item, whole drawing, external specification or drawing set, etc.

[0056] In some preferred embodiments, the drawing file includes a title block area. When establishing the jump source object and the jump target object, the present invention needs to use the information in the title block area. In order to accurately identify the information in the title block area, the method further includes: extracting metadata from the title block area, wherein the metadata is used to generate description information of the jump source object and / or the jump target object.

[0057] Specifically, this invention supports the recognition of multiple types of drawings. For different types of drawings, the method of extracting metadata from the title block area is different, as follows:

[0058] If the drawing file is an image format drawing, an object detection model is used to identify the title block area in the drawing file; the original text in the title block area is identified by OCR; and the fields in the original text are semantically classified to obtain the metadata.

[0059] In specific implementation, if the drawing file is an image-format drawing, firstly, an object detection model (such as YOLOv5, Faster R-CNN, Detectron, etc.) is used to identify the title block area in the drawing file. Further, OCR (Optical Character Recognition) is performed on the title block area to extract the original text. Further, based on row and column segmentation algorithms (such as OpenCV contour detection) or cell association analysis algorithms, the original text is reorganized into a logical table according to its physical location. Further, semantic classification is performed on the fields of the logical table to obtain at least one piece of metadata, and the type of metadata is determined. Semantic classification can be performed in the following way:

[0060] Rule engine: Keyword matching (e.g., "drawing number" → drawing_id);

[0061] Classification model: Train a field type classifier (input text, output labels such as building / floor);

[0062] Large Language Model: Call large language models such as ChatGPT to parse the text semantics of fields and determine their categories.

[0063] Furthermore, if the drawing file is a vector format drawing, the text entities in the drawing file are extracted to obtain the original text; the fields in the original text are semantically classified to obtain the metadata.

[0064] In practice, if the drawing file is a vector format drawing, such as DWG or DXF, the text entities of the drawing file can be obtained through the native API of CAD (such as the AutoCAD .NET API) or an intermediate format parser (DXF library) to obtain the original text. Further, the fields in the original text are semantically classified to obtain at least one piece of metadata, and the type of the metadata is determined. Semantic classification can be performed in the following way:

[0065] Rule engine: Keyword matching (e.g., "drawing number" → drawing_id);

[0066] Classification model: Train a field type classifier (input text, output labels such as building / floor);

[0067] Large Language Model: Call large language models such as ChatGPT to parse the text semantics of fields and determine their categories.

[0068] S2, Generate a jump source object based on the jump source and a jump target object based on the jump target.

[0069] In practice, both the source object and the target object of the jump include anchor points and descriptive information.

[0070] Anchor: A two-dimensional coordinate range in a drawing that represents the jump trigger area. It can be used to define the location of the jump source or jump target. It can be in the form of a bounding box or a full page marker.

[0071] Description information: refers to the standardized information obtained by extracting and encoding the semantic information of the jump source or jump target using preset standard fields. It usually includes information such as number, type, building, floor, and professional category, and is used to accurately match the jump relationship.

[0072] In this invention, anchor points and description information of the jump source object are generated based on the jump source; anchor points and description information of the jump target object are generated based on the jump target. These two steps can be processed in parallel to improve processing efficiency.

[0073] For example, in some preferred embodiments, the above step "generating a jump source object based on the jump source" includes: obtaining a first anchor point construction rule and a first description information construction rule corresponding to the type of the jump source; obtaining the anchor point of the jump source object according to the first anchor point construction rule; and obtaining the description information of the jump source object according to the first description information construction rule.

[0074] In specific implementations, the first anchor point construction rules and the first description information construction rules may be different for different types of jump sources, and both are set by those skilled in the art. Therefore, this invention does not specifically limit their implementation. In this embodiment, firstly, the first anchor point construction rule and the first description information construction rule corresponding to the type of the jump source are obtained; further, the anchor point of the jump source object is obtained according to the first anchor point construction rule; and the description information of the jump source object is obtained according to the first description information construction rule.

[0075] For example, in this embodiment of the invention, the construction rules for the above-mentioned drafting symbols, component numbers, text, legend symbols, and the first anchor point and first descriptive information of the entire drawing are as follows:

[0076] Drafting symbols:

[0077] Use object detection models (such as YOLOv5) to locate the graphic regions of cartographic symbols;

[0078] The bounding box of the cartographic symbol is used as the anchor point;

[0079] The drawing text extraction module is invoked to extract the numbered text within the recognition box area. Combined with the contextual content of the numbered text in the title bar area (referring to the content related to the numbered text, which can be extracted through a large language model), structured descriptive information is generated.

[0080] Component number:

[0081] First, detect the component's physical elements (such as doors and windows);

[0082] Identify the numbered text area of ​​the component body element within a preset proximity range;

[0083] Anchor points are defined as the smallest rectangle enclosed by the component's main graphic element and the numbered text area.

[0084] The structured descriptive information includes the type and number of the component, the building to which the component belongs, and the context of the component in the drawing file (referring to content related to the component, which can be identified and extracted through a large language model).

[0085] text:

[0086] Use the drawing text extraction module to obtain the text location;

[0087] The anchor point is taken from the coordinate box where the text is located;

[0088] The text is extracted using named entity recognition or a large language model to generate structured descriptive information by extracting standardized names and numbers.

[0089] Legend symbols:

[0090] Use image detection to extract the region of legend symbols, and use text recognition to extract the explanatory text of legend symbols;

[0091] Anchor points are the combined coordinate frames formed by the legend symbol and its explanatory text.

[0092] The descriptive information includes the legend category, meaning, and its context in the drawing (referring to content related to the legend symbols, which can be identified and extracted through a large language model).

[0093] The entire drawing:

[0094] No specific area needs to be detected; anchor points are defined as drawing page numbers or full-page identifiers (full-page anchor points).

[0095] The descriptive information is obtained by parsing the title block area, such as building number, floor, specialty, and drawing name.

[0096] Furthermore, in some preferred embodiments, the jump target object includes anchor points and descriptive information. The above step "generating a jump target object based on the jump target" includes: obtaining a second anchor point construction rule and a second descriptive information construction rule corresponding to the type of the jump target; obtaining the anchor points of the jump target object according to the second anchor point construction rule; and obtaining the descriptive information of the jump target object according to the second descriptive information construction rule.

[0097] In specific implementations, the rules for constructing the second anchor point and the rules for constructing the second descriptive information may differ for different types of jump targets, and these rules are all set by those skilled in the art. Therefore, this invention does not specifically limit their implementation. In this embodiment, firstly, the second anchor point construction rule and the second descriptive information construction rule corresponding to the type of the jump target are obtained; further, the anchor point of the jump target object is obtained according to the second anchor point construction rule; and the descriptive information of the jump target object is obtained according to the second descriptive information construction rule.

[0098] For example, in this embodiment of the invention, the construction rules for the second anchor points of the detailed drawing area, engineering table items, legend items, the entire drawing, external specifications or atlas, and the construction rules for the second descriptive information are as follows:

[0099] Detailed drawing area: Use an instance segmentation model (such as Mask R-CNN) to identify the detailed drawing boundary as anchor points, and call the drawing text extraction module to obtain the detailed drawing number information to generate structured description information such as "Building 2B1 Drawing Detail X".

[0100] Engineering table items: Extract the table structure and cell boxes through table recognition, obtain the text number of each item, and generate a description such as "Door and window table W-03", with the anchor point being the coordinates of that cell.

[0101] Legend item: Identify legend symbols and their explanatory text to form a combined block, obtain the coordinate range of the combined block as the anchor point, and describe the meaning of the legend item.

[0102] The entire drawing: There is no need to specifically select an area; the anchor point is the entire drawing area. The descriptive information is obtained by parsing the title block area, such as building number, floor, specialty, drawing name, etc.

[0103] External specifications or atlases: Link paths are matched to the preset database through the standard number. The anchor point is the corresponding area in the external specification or atlas, and the description information is the identification information of the external specification or atlas.

[0104] S3, determine the target jump object that matches the jump source object from all the jump target objects.

[0105] In practice, a target redirection object that matches the redirection source object is selected from all the redirection target objects. Each redirection source object corresponds to one target redirection object.

[0106] For example, in some preferred embodiments, the above step "determine the target jump object that matches the jump source object from all the jump target objects" specifically includes the following steps: determining the corresponding matching rule according to the type of the jump source object; and determining the target jump object that matches the jump source object from all the jump target objects based on the matching rule.

[0107] In practice, the matching rules for different types of jump source objects may be different and can be preset by those skilled in the art; this invention does not specifically limit this. In this invention, the matching rules corresponding to the jump source object are first obtained; further, based on the matching rules, a target jump object matching the jump source object is determined from all the jump target objects.

[0108] In this embodiment of the invention, the corresponding matching rule is automatically selected based on the type of the redirect source object, for example:

[0109] When the source object for the jump is a detail drawing index symbol, the entry in the detail drawing target set whose drawing number and detail drawing number both match the detail drawing index symbol is used as the target jump target object;

[0110] When the source object of the jump is a component number, extract the source number information of the component number and match the target cell with the same number in the table-type jump target object as the target jump target object;

[0111] When the source object for the jump is a building number, the first floor plan containing that building number in the drawing metadata is used as the target object for the jump.

[0112] When the source object for the jump is the entire drawing, the corresponding drawing is matched based on a combination of fields such as building, floor, and specialty.

[0113] When the source object for the jump is a canonical citation, the canonical number and name fields in the external reference library are directly matched.

[0114] The above matching rules are based on the structured description fields or combinations of fields in the description information (such as "drawing number + detail number", "component number + table type") for precise comparison and matching. They have clear matching constraints and avoid the problem of accidental redirection caused by fuzzy text matching in traditional retrieval methods.

[0115] Furthermore, the above matching process can be replaced by knowledge graph retrieval, rule-based pattern recognition methods, or even semantic similarity retrieval (such as BERT vector matching) as a supplement in certain scenarios with high uncertainty. In principle, the above methods still achieve jump matching by comparing "jump source-target description information", and the replacement method does not change the essence of the present invention.

[0116] S4, establish a jump link between the jump source object and the target jump object.

[0117] In practice, a jump link is established between the source object and the target object, allowing users to jump to the target object by clicking the anchor point of the source object. In this invention, all jump relationships are ultimately presented in a clickable format on the drawing browsing interface, enabling users to automatically jump to the target drawing location or external document by clicking the anchor point of the source object, achieving an efficient navigation experience across drawings, tables, and documents.

[0118] In this invention, the establishment of redirection relationships employs a type-driven rule-based matching mechanism, meaning the system automatically selects the corresponding matching logic based on the type field of the redirection source object. Different types of redirection sources use different field combinations for precise matching, as shown in the following example:

[0119] If the jump source is a detail index symbol, then match the detail area in the target where both the detail number and the drawing number are the same;

[0120] If it is a component number such as a door or window, or a construction method number, then it should match the number field in the project table;

[0121] If the entire architectural drawing is used as the jump source (e.g., Architecture → Structure), then the structural drawings with the same building, floor, and professional fields in the target drawing will be matched.

[0122] If the reference text is a specification in the design description, it will be directly matched with the specification number and name fields in the external standard document library;

[0123] All matches are based on combinations of structured fields (such as type, id, building, floor, discipline, etc.), without relying on fuzzy search or keyword search.

[0124] Furthermore, this invention supports various jump types, including detailed drawing jumps, construction table jumps, legend jumps, and jumps between drawings (e.g., architectural drawings → structural drawings), and site plan jumps (e.g., building number → first floor drawings), exhibiting high scalability. Jump results can be exported as PDF coordinate anchors, DWG element jumps, external document links, or structured data formats (e.g., JSON, XML) and integrated into the drawing management platform for easy subsequent maintenance and integration. Furthermore, the above linking methods can be replaced with SVG anchors, HTML jumps, database records, BIM platform index items, visualization system coordinate mappings, etc., depending on the target platform or drawing management system. As long as the positioning logic of "drawing content → jump to target" is maintained, all are equivalent implementations of this invention.

[0125] This invention proposes a method for automatically generating jump links in architectural engineering drawings, comprising: receiving a drawing file; identifying a jump source and a jump target from the drawing file; generating a jump source object based on the jump source and a jump target object based on the jump target; determining a target jump target object that matches the jump source object from all the jump target objects; and establishing a jump link between the jump source object and the target jump target object. This invention can improve the efficiency and accuracy of jump link generation, while also facilitating the maintenance of jump links.

[0126] The present invention provides a method for automatically generating jump links in architectural engineering drawings. This method automatically identifies jump sources and targets in drawing files, and constructs jump source objects and target objects containing anchor points and structured descriptions based on preset rules. Then, it dynamically selects matching rules according to the type of the jump source object, accurately identifies related target jump objects from all target objects, and finally automatically establishes jump links between them. This technical solution effectively overcomes the inherent defect of existing technologies that rely entirely on manual link creation, achieving significant technological progress.

[0127] Specifically, this method automates the batch identification and processing of drawing elements, replacing tedious manual selection and specification operations, significantly improving the efficiency of link generation. This is particularly beneficial in large-scale, complex engineering projects, where it significantly reduces the time cost required for link creation. Secondly, when constructing jump objects, it introduces typed anchor point construction rules and description information construction rules, combined with metadata extraction technology from the title block, to generate standardized, structured description information containing key semantic information such as number, type, and location. This structured information provides a precise comparison basis for the subsequent matching process. Coupled with matching rules designed for different jump source types (such as precise comparison based on description field combinations), it effectively avoids link errors or failures caused by traditional fuzzy matching, thus significantly improving the accuracy of link generation. Finally, because the entire link relationship is automatically generated based on standardized object descriptions and explicit matching logic, all links have clear structured definitions. This allows for automated verification, updating, or batch adjustment of links based on the same rules when drawing content is updated or projects are iterated, greatly simplifying the maintenance process of jump links and reducing the complexity and cost of long-term maintenance.

[0128] In summary, this invention systematically solves the core problems of low efficiency, insufficient accuracy, and difficult maintenance in existing technologies through an integrated process of automated identification, object structured construction, intelligent matching, and automatic link establishment. It provides efficient, accurate, and sustainably maintainable drawing association navigation technology support for large-scale engineering projects.

[0129] Corresponding to the above-described method for automatically generating links to architectural drawings, this invention also provides an apparatus for automatically generating links to architectural drawings. This apparatus includes a unit for executing the aforementioned method for automatically generating links to architectural drawings, and can be configured in a desktop computer, tablet computer, laptop computer, or other terminal. Specifically, the apparatus includes:

[0130] An identification unit is used to receive drawing files and identify the jump source and jump target from the drawing files;

[0131] The generation unit is used to generate a jump source object based on the jump source and a jump target object based on the jump target;

[0132] A determining unit is configured to determine, from all the jump target objects, a target jump object that matches the jump source object;

[0133] The establishment unit is used to establish a jump link between the jump source object and the target jump target object.

[0134] In some preferred embodiments, identifying the jump source and jump target from the drawing file includes:

[0135] Identify the elements contained in the drawing file;

[0136] Elements of a first preset type are selected from the elements contained in the drawing file as the jump source;

[0137] Elements of a second preset type are selected from the elements contained in the drawing file as the jump target.

[0138] In some preferred embodiments, the jump source object includes an anchor point and descriptive information, and generating the jump source object based on the jump source includes:

[0139] Obtain the first anchor point construction rule and the first description information construction rule corresponding to the type of the jump source;

[0140] The anchor point of the jump source object is obtained according to the first anchor point construction rule;

[0141] The description information of the jump source object is obtained by constructing rules based on the first description information.

[0142] In some preferred embodiments, the jump target object includes anchor points and descriptive information, and generating the jump target object based on the jump target includes:

[0143] Obtain the second anchor point construction rule and the second description information construction rule corresponding to the type of the jump target;

[0144] The anchor point of the target object to be jumped is obtained according to the second anchor point construction rule;

[0145] The description information of the target object to be redirected is obtained based on the rule constructed according to the second description information.

[0146] In some preferred embodiments, determining the target jump object that matches the jump source object from all the jump target objects includes:

[0147] The corresponding matching rules are determined based on the type of the jump source object;

[0148] Based on the matching rules, a target jump object that matches the jump source object is determined from all the jump target objects.

[0149] In some preferred embodiments, the drawing file includes a title block area, and the automatic generation device for architectural engineering drawing jump links further includes:

[0150] Metadata is extracted from the label bar area, wherein the metadata is used to generate description information of the jump source object and / or the jump target object.

[0151] In some preferred embodiments, extracting metadata from the label bar area includes:

[0152] If the drawing file is an image format drawing, an object detection model is used to identify the title bar area in the drawing file;

[0153] The original text in the title bar area is identified using OCR;

[0154] The fields in the original text are semantically classified to obtain the metadata.

[0155] Alternatively, if the drawing file is a vector format drawing, extract the text entities from the drawing file to obtain the original text;

[0156] The fields in the original text are semantically classified to obtain the metadata.

[0157] It should be noted that those skilled in the art can clearly understand that the specific implementation process of the above-mentioned automatic generation device for building engineering drawing jump links and each unit can be referred to the corresponding description in the foregoing method embodiments. For the sake of convenience and brevity, it will not be repeated here.

[0158] The aforementioned automatic link generation device for architectural drawings can be implemented as a computer program, which can, for example, Figure 2 It runs on the computer device shown.

[0159] Please see Figure 2 , Figure 2 This is a schematic block diagram of a computer device provided in an embodiment of this application. The computer device 500 can be a terminal or a server. The terminal can be an electronic device with communication functions, such as a smartphone, tablet, laptop, desktop computer, personal digital assistant, or wearable device. The server can be a standalone server or a server cluster composed of multiple servers.

[0160] The computer device 500 includes a processor 502, a memory, and a network interface 505 connected via a system bus 501. The memory may include a non-volatile storage medium 503 and internal memory 504.

[0161] The non-volatile storage medium 503 can store an operating system 5031 and a computer program 5032. When the computer program 5032 is executed, it causes the processor 502 to execute a method for automatically generating jump links in architectural drawings.

[0162] The processor 502 provides computing and control capabilities to support the operation of the entire computer device 500.

[0163] The internal memory 504 provides an environment for the operation of the computer program 5032 in the non-volatile storage medium 503. When the computer program 5032 is executed by the processor 502, the processor 502 can execute a method for automatically generating jump links in architectural engineering drawings.

[0164] The network interface 505 is used for network communication with other devices. Those skilled in the art will understand that the above structure is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device 500 to which the present application is applied. A specific computer device 500 may include more or fewer components than shown in the figures, or combine certain components, or have different component arrangements.

[0165] The processor 502 is used to run a computer program 5032 stored in a memory to implement the steps of the automatic generation method for building engineering drawing jump links provided in any of the above method embodiments.

[0166] It should be understood that in the embodiments of this application, the processor 502 may be a central processing unit (CPU), or it may be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor.

[0167] It will be understood by those skilled in the art that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program may be stored in a storage medium, which is a computer-readable storage medium. The computer program is executed by at least one processor in the computer system to implement the process steps of the embodiments of the above methods.

[0168] Therefore, the present invention also provides a storage medium. This storage medium can be a computer-readable storage medium. The storage medium stores a computer program. When executed by a processor, the computer program causes the processor to perform the steps of the automatic generation method for architectural drawing jump links provided in any of the above method embodiments.

[0169] The storage medium is a physical, non-transient storage medium, such as a USB flash drive, external hard drive, read-only memory (ROM), magnetic disk, or optical disk, or any other physical storage medium capable of storing program code. The computer-readable storage medium can be non-volatile or volatile.

[0170] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of the various examples have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this invention.

[0171] In the several embodiments provided by this invention, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative. For example, the division of each unit is merely a logical functional division, and there may be other division methods in actual implementation. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed.

[0172] The steps in the method of this invention can be adjusted, merged, or reduced in order according to actual needs. The units in the device of this invention can be merged, divided, or reduced according to actual needs. Furthermore, the functional units in the various embodiments of this invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0173] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, a terminal, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention.

[0174] In the above embodiments, the descriptions of each embodiment have different focuses. For parts that are not described in detail in a certain embodiment, please refer to the relevant descriptions in other embodiments.

[0175] Obviously, those skilled in the art can make various modifications and variations to this invention without departing from its spirit and scope. Since these modifications and variations fall within the scope of the claims and their equivalents, this invention also intends to include these modifications and variations.

[0176] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any person skilled in the art can easily conceive of various equivalent modifications or substitutions within the technical scope disclosed in the present invention, and these modifications or substitutions should all be covered within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. A method for automatically generating jump links in architectural engineering drawings, characterized in that, include: Receive drawing files and identify the jump source and jump target from the drawing files; A jump source object is generated based on the jump source, and a jump target object is generated based on the jump target; From all the jump target objects, determine the target jump target object that matches the jump source object; Establish a jump link between the jump source object and the target jump object; The step of identifying the jump source and jump target from the drawing file includes: Identify the elements contained in the drawing file; Elements of a first preset type are selected from the elements contained in the drawing file as the jump source; Select elements of a second preset type from the elements contained in the drawing file as the jump target; The jump source object includes an anchor point and descriptive information. Generating the jump source object based on the jump source includes: Obtain the first anchor point construction rule and the first description information construction rule corresponding to the type of the jump source; The anchor point of the jump source object is obtained according to the first anchor point construction rule; The description information of the jump source object is obtained by constructing rules based on the first description information; The jump target object includes anchor points and descriptive information. Generating the jump target object based on the jump target includes: Obtain the second anchor point construction rule and the second description information construction rule corresponding to the type of the jump target; The anchor point of the target object to be jumped is obtained according to the second anchor point construction rule; The description information of the target object to be redirected is obtained based on the rule constructed according to the second description information. The drawing file includes a title block area, and the method further includes: Metadata is extracted from the label bar area, wherein the metadata is used to generate description information of the jump source object and / or the jump target object.

2. The method for automatically generating jump links in architectural engineering drawings according to claim 1, characterized in that, The step of determining the target jump object that matches the jump source object from all the jump target objects includes: The corresponding matching rules are determined based on the type of the jump source object; Based on the matching rules, a target jump object that matches the jump source object is determined from all the jump target objects.

3. The method for automatically generating jump links in architectural engineering drawings according to claim 1, characterized in that, The extraction of metadata from the label bar area includes: If the drawing file is an image format drawing, an object detection model is used to identify the title bar area in the drawing file; The original text in the title bar area is identified using OCR; The fields in the original text are semantically classified to obtain the metadata. Alternatively, if the drawing file is a vector format drawing, extract the text entities from the drawing file to obtain the original text; The fields in the original text are semantically classified to obtain the metadata.

4. A device for automatically generating jump links in architectural engineering drawings, characterized in that, Includes a unit for performing the method as described in any one of claims 1-3.

5. A computer device, characterized in that, The computer device includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program to implement the method as described in any one of claims 1-3.

6. A computer-readable storage medium, characterized in that, The storage medium stores a computer program that, when executed by a processor, can implement the method as described in any one of claims 1-3.

Images