Construction task dispatching method and system based on drawing information recognition

Abstract

A construction task dispatching method and system based on drawing information recognition. The method comprises: acquiring a drawing to be recognized; recognizing a plurality of closed paths in the drawing; on the basis of positional relationships among the plurality of closed paths, determining a drawing frame of the drawing; on the basis of the drawing frame of the drawing and a title block range of the drawing, determining title block information; on the basis of the title block information, determining a recognition result of a target object in the drawing; and on the basis of the recognition result of the target object, performing construction task dispatching.

Description

A method and system for dispatching construction tasks based on drawing information recognition Cross-references

[0001] This application claims priority to Chinese applications filed on December 31, 2024, No. 202411978286.0; February 7, 2025, No. 202510136538.3; April 22, 2025, No. 202510507527.1; and November 3, 2025, No. 202511586952.0, the entire contents of which are incorporated herein by reference. Technical Field

[0002] This specification relates to the field of construction, and in particular to a method and system for assigning construction tasks based on drawing information recognition. Background Technology

[0003] In engineering construction and management, drawing management is a crucial link in ensuring the smooth progress of projects. With the development of digital technology, CAD electronic drawings have become an important tool for engineering design and management. Drawing management and the assignment of construction tasks based on drawings directly affect project progress efficiency, but there are currently some problems in related aspects. On the one hand, the efficiency and accuracy of drawing information extraction are insufficient. Spatial information contained in drawing sub-item names, drawing names, etc., needs to be manually entered by users, resulting in low intelligence and difficulty in processing large amounts of data. Complex electronic drawings contain rectangles with diverse positional relationships (such as non-intersecting, containing, tangent, etc.), making frame recognition difficult and inaccurate. Due to different drawing standards among design institutes, the naming and location of drawing label information vary. Existing extraction methods that rely on manual annotation or simple geometric matching are difficult to adapt to diverse layouts and rules, and need to consider both the geometric features of elements (position, size, etc.) and text content, further reducing recognition efficiency. On the other hand, the assignment of construction tasks lacks accuracy. Taking the assignment of wall construction tasks as an example, the interior and exterior walls have different orientations and require different waterproofing and plastering processes. The traditional assignment method relies on the experience of management personnel to manually assign tasks, which is subjective, inefficient, and can only roughly divide the area. It cannot assign tasks on a wall-by-wall basis, nor can it distinguish between interior and exterior walls as independent units.

[0004] Therefore, it is necessary to provide a construction task assignment method and system based on drawing information recognition to improve the effectiveness of drawing management and the efficiency and accuracy of drawing-based construction task assignment. Summary of the Invention

[0005] This specification provides one or more embodiments of a construction task assignment method based on drawing information recognition. The method includes: acquiring a drawing to be recognized; recognizing multiple closed paths in the drawing; determining the drawing frame based on the positional relationship between the multiple closed paths; determining label information based on the drawing frame and the label range of the drawing; determining the recognition result of a target object in the drawing based on the label information; and assigning construction tasks based on the recognition result of the target object.

[0006] This specification also provides a construction task dispatching system based on drawing information recognition in one or more embodiments. The system includes: a first recognition module configured to acquire a drawing to be recognized; a second recognition module configured to recognize multiple closed paths in the drawing; a first determination module configured to determine the drawing frame based on the positional relationship between the multiple closed paths; a second determination module configured to determine label information based on the drawing frame and the label range of the drawing; a third determination module configured to determine the recognition result of a target object in the drawing based on the label information; and a task dispatching module configured to dispatch construction tasks based on the recognition result of the target object.

[0007] One or more embodiments of this specification also provide a drawing frame recognition method, the method comprising: recognizing multiple closed paths in a drawing; generating one or more closed path sets based on the positional relationship between the multiple closed paths, each of the closed path sets containing one or more closed paths divided into one or more levels, wherein a first region enclosed by each lower-level closed path is contained in or intersects with a second region enclosed by a higher-level closed path; and for each of the closed path sets, determining whether the closed path set contains a target closed path corresponding to the drawing frame.

[0008] This specification also provides a method for identifying title information, the method comprising: obtaining the title range of a drawing; determining a first closed path list based on the drawing frame and the title range, the first closed path list including all first closed paths that do not contain other closed paths; determining the closed path to which the title field belongs based on the element range of text elements in a text element list and the first closed path in the first closed path list; determining the content value range of the title field based on a first intersection ratio between the belonging closed path and the element range, and the offset distance between the center point of the text element range and the center point of the belonging closed path; and obtaining the text content value within the content value range according to the content value range.

[0009] One or more embodiments of this specification also provide a method for extracting spatial information from a drawing, the method comprising: obtaining a drawing frame; the drawing frame including title information; performing title recognition based on the drawing frame to determine initial spatial information; comparing the initial spatial information with a preset spatial information database to obtain a comparison result; splitting the initial spatial information according to the comparison result to obtain spatial description information; and obtaining target spatial information of the drawing based on the spatial description information.

[0010] One or more embodiments of this specification also provide a wall task assignment method, comprising: identifying walls within a target construction area from drawings; obtaining a construction task order corresponding to the wall, the construction task order including construction task information and construction personnel information corresponding to a target construction period; determining, based on the construction task information and historical construction data of the wall, target walls to be constructed within the target construction period and construction task items corresponding to each target wall from the walls within the target construction area; and determining, based on the construction personnel information and the construction task items corresponding to each target wall, target construction personnel and the target walls and their construction task items assigned to each target construction personnel within the target construction period. Attached Figure Description

[0011] This specification will be further illustrated by way of exemplary embodiments, which will be described in detail with reference to the accompanying drawings. These embodiments are not limiting; in these embodiments, the same numbers represent the same structures, wherein: Figure 1 is a schematic diagram of an application scenario of a construction task assignment system based on drawing information recognition according to some embodiments of this specification; Figure 2 is an exemplary flowchart of a construction task assignment method based on drawing information recognition according to some embodiments of this specification; Figure 3A is an exemplary flowchart of determining the drawing frame according to some embodiments of this specification; Figure 3B is an exemplary flowchart of determining the drawing frame according to other embodiments of this specification; Figure 4 is a flowchart of an exemplary method for determining multiple closed paths according to some embodiments of this specification; Figure 5 is a schematic diagram of an exemplary method for determining multiple closed paths according to some embodiments of this specification; Figure 6 is a flowchart of an exemplary method for generating one or more closed path sets according to some embodiments of this specification; Figure 7 is a schematic diagram of an exemplary relation tree for representing a closed path set according to some embodiments of this specification; Figure 8 is a flowchart of an exemplary method for processing closed paths at the current level according to some embodiments of this specification; Figures 9A and 9B are schematic diagrams of exemplary closed path sets according to some embodiments of this specification; Figure 10 is an exemplary flowchart of determining label information according to some embodiments of this specification. Figure 11 is an exemplary schematic diagram illustrating the determination of a content value range according to some embodiments of this specification; Figure 12 is an exemplary flowchart illustrating the determination of a label range according to some embodiments of this specification; Figure 13 is an exemplary schematic diagram illustrating a label according to some embodiments of this specification; Figure 14 is an exemplary flowchart illustrating the determination of the identification result of a target object in a drawing according to some embodiments of this specification; Figure 15 is an exemplary flowchart illustrating the determination of target spatial information according to other embodiments of this specification; Figure 16 is an exemplary flowchart illustrating the verification of target spatial information based on a target drawing according to some embodiments of this specification; Figure 17 is a partial schematic diagram of the frame area of ​​a target drawing according to some embodiments of this specification; Figure 18 is an exemplary flowchart illustrating the assignment of construction tasks according to some embodiments of this specification; Figure 19 is an exemplary schematic diagram illustrating the construction plan of a target construction area according to some embodiments of this specification; Figure 20 is an exemplary flowchart illustrating the determination of target construction personnel and the target walls and their construction tasks assigned to each target construction personnel within a target construction period according to some embodiments of this specification; Figure 21 is an exemplary schematic diagram illustrating the generation of distances between walls according to some embodiments of this specification. Figure 22 is an exemplary flowchart illustrating the determination of target construction personnel and target wall surfaces and their construction tasks assigned to each target construction personnel during a target construction period, according to some embodiments of this specification.Figure 23 is an exemplary flowchart illustrating the determination of target construction personnel and the target wall surfaces and their construction tasks assigned to each target construction personnel within a target construction period, according to some embodiments of this specification; Figure 24 is an exemplary block diagram illustrating a construction task assignment system based on drawing information recognition, according to some embodiments of this specification; Figure 25 is an exemplary flowchart illustrating a frame recognition method, according to some embodiments of this specification; Figure 26 is an exemplary flowchart illustrating a label information recognition method, according to some embodiments of this specification; Figure 27 is an exemplary flowchart illustrating a drawing space information extraction method, according to some embodiments of this specification; Figure 28 is an exemplary flowchart illustrating a wall task assignment method, according to some embodiments of this specification. Detailed Implementation

[0012] To more clearly illustrate the technical solutions of the embodiments in this specification, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are merely some examples or embodiments of this specification. For those skilled in the art, these drawings can be applied to other similar scenarios without creative effort. Unless obvious from the context or otherwise specified, the same reference numerals in the drawings represent the same structures or operations.

[0013] It should be understood that the terms “system,” “device,” “unit,” and / or “module” used herein are one way to distinguish different components, elements, parts, sections, or assemblies at different levels. However, if other terms can achieve the same purpose, they may be replaced by other expressions.

[0014] As indicated in this specification and claims, unless the context clearly indicates otherwise, the words "a," "an," "an," and / or "the" are not specifically singular and may include the plural. Generally speaking, the terms "comprising" and "including" only indicate the inclusion of expressly identified steps and elements, which do not constitute an exclusive list, and the method or apparatus may also include other steps or elements.

[0015] Flowcharts are used in this specification to illustrate the operations performed by the system according to embodiments of this specification. It should be understood that the preceding or following operations are not necessarily performed in exact order. Instead, the steps can be processed in reverse order or simultaneously. Furthermore, other operations can be added to these processes, or one or more steps can be removed from them.

[0016] Figure 1 is a schematic diagram of an application scenario of a construction task assignment system based on drawing information recognition, according to some embodiments of this specification.

[0017] In some embodiments, as shown in FIG1, the application scenario 100 of the construction task dispatching system based on drawing information recognition includes drawing 110, processor 120, terminal device 120, network 130, and storage device 150, etc.

[0018] Drawing 110 refers to a schematic diagram that requires drawing information identification. For example, drawing 110 can be an architectural design drawing, construction design drawing, etc., that requires spatial information extraction. The types of target drawing 110 listed above are merely examples and do not constitute a limitation; target drawing 110 can also be any drawing that requires spatial information extraction.

[0019] In some embodiments, drawing 110 may be a physical drawing (such as a paper drawing). In other embodiments, drawing 110 may also be an electronic drawing. Further details regarding the drawing can be found in Figure 2 and its related sections.

[0020] The processor 120 is capable of processing information and / or data related to the construction task assignment system based on drawing information recognition to perform one or more functions described in this specification. In some embodiments, the processor 120 may acquire a drawing to be identified; identify multiple closed paths in the drawing; determine the drawing frame based on the positional relationship between the multiple closed paths; determine label information based on the drawing frame and the label range of the drawing; determine the identification result of a target object in the drawing based on the label information; and assign a construction task based on the identification result of the target object. Detailed descriptions of related content can be found in the following descriptions (as shown in Figures 2 to 28).

[0021] In some embodiments, processor 120 may include a central processing unit (CPU), a digital signal processor (DSP), a microcontroller unit (MCU), a computer, a user console, or any combination thereof. In some embodiments, processor 120 may include a single server or a group of servers. The server group may be centralized or distributed. In some embodiments, processor 120 may be local or remote. In some embodiments, processor 120 may be implemented on a cloud platform. By way of example only, a cloud platform may include a private cloud, a public cloud, a hybrid cloud, a community cloud, a distributed cloud, an internal cloud, a multi-tiered cloud, or any combination thereof.

[0022] Network 130 can connect various components in application scenario 100 of the construction task dispatch system based on drawing information recognition and / or connect other components outside application scenario 100. In some embodiments, one or more components of application scenario 100 of the construction task dispatch system based on drawing information recognition (e.g., processor 120, terminal 140, and storage device 150, etc.) can be connected and / or communicate with each other through network 130. For example, terminal 140 can send drawing 110 to processor 120, etc., through network 130.

[0023] Terminal 140 can provide functional components related to user interaction and enable user interaction functions (such as providing or displaying information and data to the user). The user can refer to the administrator of drawing 110, or the person searching for or using drawing 110. By way of example only, terminal 140 can be one or any combination of mobile devices, tablet computers, laptop computers, desktop computers, or other devices with input and / or output functions.

[0024] Storage device 150 is capable of storing data, instructions, and / or any other information. In some embodiments, storage device 150 may store data acquired from processor 120, terminal 140, etc., such as drawings 110, title information, etc. In some embodiments, storage device 150 may include mass storage, removable storage, volatile read-write memory, read-only memory (ROM), etc., or any combination thereof. In some embodiments, storage device 150 may be executed on a cloud platform. In some embodiments, storage device 150 may be connected to network 130 to communicate with one or more other components (e.g., processor 120, terminal 140, etc.) of application scenario 100 of a construction task dispatch system based on drawing information recognition. In some embodiments, storage device 150 may be part of processor 120.

[0025] It is important to note that the application scenario 100 of the construction task assignment system based on drawing information recognition is provided for illustrative purposes only and is not intended to limit the scope of this specification. Those skilled in the art can make various changes and modifications based on the description in this specification. For example, the application scenario 100 of the construction task assignment system based on drawing information recognition may also include a database, information sources, etc. Furthermore, the application scenario 100 of the construction task assignment system based on drawing information recognition can be implemented on other devices to achieve similar or different functions. However, these changes and modifications will not depart from the scope of this specification.

[0026] Figure 2 is an exemplary flowchart of a construction task assignment method based on drawing information identification according to some embodiments of this specification. In some embodiments, process 200 may be executed by processor 120. As shown in Figure 2, process 200 includes the following steps.

[0027] Step 210: Obtain the drawing to be identified.

[0028] The drawing to be identified refers to the drawing whose information needs to be identified in order to assign construction tasks. In some embodiments, the drawing to be identified may also be referred to as the target drawing.

[0029] Drawings are diagrams used to guide the construction of a project. Drawings can include illustrative representations of details required for construction, such as dimensions, orientation, and technical parameters, as well as illustrative representations of the actual engineering structure to be constructed.

[0030] In some embodiments, drawings may include architectural construction drawings, structural construction drawings, and equipment construction drawings. Architectural construction drawings are primarily used to represent the planned location, external shape, layout of internal rooms, interior and exterior decoration, and construction requirements of a building. Structural construction drawings primarily represent the structural type, layout, component types, quantities, sizes, and construction methods of the building's load-bearing structure. Equipment construction drawings primarily represent the layout and construction requirements of the building's water supply and drainage, heating and ventilation, power supply, and lighting equipment.

[0031] In some embodiments, the drawings can be drawings created for the entire construction project. In some embodiments, the drawings can be drawings created for a specific construction object within the construction project. A construction project is a specific project for which construction or engineering work is to be carried out. Taking the construction project as building a school as an example, the drawings can be drawings created for the entire school. The drawings can also be drawings created for a specific teaching building. The drawings can also be drawings created for a specific floor of the teaching building.

[0032] In some embodiments, the drawings may be electronic drawings generated by CAD software, or drawings that are converted from paper drawings into electronic format through scanning or other means.

[0033] Drawing information refers to the information related to the construction project contained on the drawings. For example, drawing information may include the drawing name, number, designer's name, design date, and company name. Alternatively, it may include project information, building information, floor information, construction requirements, and drawing dimensions (e.g., length, width, and area).

[0034] In some embodiments, the drawing to be identified can be obtained through user-uploaded input. In some embodiments, the drawing to be identified can also be stored in storage device 150, and processor 120 can retrieve the drawing to be identified from storage device 150 through an interface.

[0035] Step 220: Identify multiple closed paths in the drawing.

[0036] A closed path is a continuous trajectory that starts from a starting point, passes through multiple consecutive straight lines, and eventually returns to the starting point. A closed path consists of multiple interconnected straight lines that can enclose a closed region.

[0037] Specifically, in some embodiments, the processor 120 can extract multiple straight line segments (hereinafter referred to as straight lines) from a drawing. For example, the drawing can be analyzed using CAD software parsing techniques to extract multiple straight lines. Another example is the extraction of multiple straight lines from a drawing using image recognition algorithms (such as Hough transform algorithm, edge detection algorithm, etc.). Furthermore, the processor 120 can obtain the intersection information of multiple straight lines and determine whether the multiple straight lines can form a closed path based on this information. For example, the processor 120 can identify whether the endpoints of multiple straight lines intersect based on their positions, and determine whether multiple straight lines can form a closed path based on whether the intersecting endpoints of multiple consecutively intersecting lines return to the starting endpoint.

[0038] In some embodiments, the processor 120 may construct an undirected graph based on a drawing and determine multiple closed paths based on the undirected graph. A detailed description of constructing an undirected graph based on a drawing and determining multiple closed paths based on the undirected graph can be found in Figure 4 and its related description.

[0039] Step 230: Determine the drawing frame based on the positional relationship between multiple closed paths.

[0040] The drawing frame is the boundary line that marks the boundary of a drawing.

[0041] In some embodiments, the processor 120 can identify the title block in the target drawing. For example, the processor 120 can use an annotation tool to annotate the title block on the target drawing to obtain the title block of the target drawing. Exemplary annotation tools may include various CAD annotation software, etc.

[0042] In some embodiments, the processor 120 may generate one or more sets of closed paths based on the positional relationships between multiple closed paths. For each set of closed paths, it determines whether the set includes the target closed path corresponding to the frame. If the set includes the target closed path corresponding to the frame, then the target closed path constitutes the frame. Further details can be found in the relevant sections below, as shown in Figures 3A to 9B.

[0043] Step 240: Determine the title block information based on the drawing frame and the title block area of ​​the drawing.

[0044] The label area refers to the area occupied by the label on the drawing. The label is an element used to identify information on a drawing.

[0045] Drawings consist of a drawing area and a title block area. The drawing area is used to create the specific design drawings, while the title block area is used to identify title block information.

[0046] A title tag is a label on a drawing used to identify information about the drawing. For example, a title tag may include elements such as the drawing title, drawing type, drawing number, designer's name, design date, and organization name. The information contained in the title tag is called title tag information.

[0047] Generally, the specific drawing content (i.e., the drawing area) is placed in the center of the drawing frame, while the title block is placed in the inner corner of the drawing frame.

[0048] The area of ​​the label can be a rectangular region. The extent of the rectangular region can be defined by the maximum and minimum x-coordinates, maximum and minimum y-coordinates of the vertices of the shape enclosed by the rectangular region.

[0049] In some embodiments, the processor can obtain the label range in various ways. For example, the processor can determine the area of ​​the smallest bounding rectangle that completely contains the label (e.g., drawing name, drawing type, drawing number, designer's name, design date, organization name, etc.) as the label range.

[0050] In some embodiments, the processor may also generate a list of graphic element information based on text graphic elements in the drawing; determine a list of aggregation ranges based on the aggregation of text graphic elements in the list of graphic element information; and determine the label range based on the list of aggregation ranges. Further description of this embodiment can be found in Figure 10 and its related content.

[0051] In some embodiments, the processor 120 can identify the label area using image recognition (e.g., Optical Character Recognition, OCR) technology to determine the label information. Alternatively, the processor 120 can identify the frame and label area using machine vision technology, image recognition technology, or other methods, and extract the label information.

[0052] In some embodiments, the processor 120 may further determine a first closed path list based on the drawing frame and the drawing title block range, and further determine title block information based on the title block range of text elements in the first closed path list and the text element list. Further details can be found in Figures 10-13.

[0053] Step 250: Based on the label information, determine the identification result of the target object in the drawing.

[0054] The target object refers to the element in the drawing that needs to be identified. In some embodiments, the target object includes spatial information in the title block and walls in the drawing. The identification result of the target object includes the target spatial information and the walls.

[0055] Spatial information refers to information / data describing the spatial allocation of a building as shown in a drawing. For example, spatial information can indicate the specific floors and / or buildings of a building shown in the drawing. Target spatial information refers to the spatial information corresponding to buildings and floors extracted from the target drawings. For example, for the initial spatial information "Buildings 1-3, floors 1-3, equipment floors, and Buildings 5 ​​and 7, floors 2-5", the corresponding target spatial information includes: "Building 1: floors 1, 2, 3, equipment floors", "Building 2: floors 1, 2, 3, equipment floors", "Building 3: floors 1, 2, 3, equipment floors", "Building 5: floors 2, 3, 4, 5", "Building 7: floors 2, 3, 4, 5", etc.

[0056] A wall refers to a structural component within the target construction area that serves functions such as dividing space, bearing load, enclosure, insulation, and soundproofing. A wall surface refers to the outer surface of a wall. It should be noted that each wall has two surfaces, meaning each wall comprises two wall surfaces, which must be considered separately.

[0057] In some embodiments, the wall surface may include an interior wall facing inwards and an exterior wall facing outwards.

[0058] Interior walls refer to the walls facing the interior area.

[0059] Exterior walls refer to walls facing the outdoors. Outdoor areas may include open platforms, corridors, terraces, elevated areas, roofs, and other spaces.

[0060] It should be noted that when a wall is an exterior wall, one side faces outwards (i.e., the exterior wall surface) and the other side faces inwards (i.e., the interior wall surface). The construction methods for the interior and exterior walls are different, and they need to be considered separately when assigning tasks. Therefore, by identifying the interior and exterior walls, they can be used as different basic units for task assignment.

[0061] In some embodiments, the processor 120 can directly extract spatial information from the tag information. For example, the processor 120 can extract spatial information by performing semantic analysis or other methods on the tag information.

[0062] In some embodiments, the processor 120 may also determine initial spatial information based on the map label information; compare the initial spatial information with a preset spatial information database to obtain a comparison result; split the initial spatial information according to the comparison result to obtain spatial description information; and obtain the target spatial information of the drawing based on the spatial description information.

[0063] In some embodiments, the processor 120 can identify the wall based on the label information. For example, the processor 120 can identify the wall based on the drawing name in the label information. For instance, if the drawing name includes keywords such as "interior", "interior wall", or "wall of room XX", it is an interior wall. If the drawing name includes keywords such as "exterior wall", "facade", or "exterior wall surface", it is an exterior wall.

[0064] In some embodiments, the processor 120 can also determine whether the drawing is related to a wall based on the label information; if the drawing is related to a wall, the processor 120 can identify wall elements, door elements, and window elements in the drawing; based on the wall elements, door elements, and window elements in the drawing, the processor 120 can identify the room area in the drawing; finally, based on the boundary of the room area, the processor 120 can determine the walls, and the walls facing the interior space of the room area are determined as interior walls, and the walls facing the exterior space of the room area are determined as exterior walls. Further explanation of related content can be found in Figures 18-23, etc.

[0065] Step 260: Based on the identification results of the target object, the construction task is assigned.

[0066] Construction tasks refer to the construction tasks related to wall surface work assignments within the target construction period. It's important to note that these are relatively general tasks and don't specify the exact wall surface. The term "construction task item" refers to the type of construction task. Construction task items can include waterproofing, painting, plastering, tiling, etc. For example, construction task information could include waterproofing and painting tasks for interior walls and painting tasks for exterior walls within the target construction area.

[0067] In some embodiments, the processor 120 can determine the specific construction area where construction tasks need to be assigned based on target spatial information, such as Community A, Building B, Building C, etc.

[0068] In some embodiments, the processor 120 may determine, based on the wall identification results, whether the construction task to be dispatched is related to an interior wall facing indoors or an exterior wall facing outdoors.

[0069] In some embodiments, the processor 120 can also acquire a construction task sheet corresponding to the wall surface. The construction task sheet includes construction task information and construction personnel information corresponding to the target construction period. Based on the construction task information and historical construction data of the wall surface, the processor determines the target wall surface to be constructed during the target construction period and the construction task item corresponding to each target wall surface from the walls within the target construction area. Furthermore, based on the construction personnel information and the construction task item corresponding to each target wall surface, the processor determines the target construction personnel and the target wall surface and its construction task item assigned to each target construction personnel during the target construction period. Further details can be found in Figures 18-23, etc.

[0070] The construction task assignment method based on drawing information recognition described in some embodiments of this specification not only improves drawing management efficiency through efficient and accurate identification of drawing information, but also enhances the accuracy of spatial information in the drawings, facilitating the subsequent assignment of construction tasks. Furthermore, by identifying the target construction personnel and the target wall surfaces and their corresponding construction tasks for each personnel within the target construction period, automatic assignment of construction tasks to the target wall surfaces is achieved, improving assignment efficiency. The assignment unit is detailed down to the specific wall surface, distinguishing between interior and exterior walls, making the assignment of construction tasks more accurate.

[0071] Figure 3A is an exemplary flowchart illustrating the definition of a drawing according to some embodiments of this specification. In some embodiments, process 300A may be executed by processor 120. As shown in Figure 3A, process 300A includes the following steps.

[0072] Step 310: Generate one or more sets of closed paths based on the positional relationships between multiple closed paths.

[0073] The positional relationship between multiple closed paths refers to the intersection relationship between the regions enclosed by the closed paths. For example, this can include non-intersecting, intersecting, contained, vertex intersecting, and line intersecting (or tangent). Containment can also be considered a special type of intersection.

[0074] A set of closed paths is a collection generated by hierarchically dividing multiple intersecting closed paths. Each set of closed paths contains one or more closed paths divided into one or more levels. The first region enclosed by each lower-level closed path is contained within or intersects with the second region enclosed by its higher-level closed path. For example, referring to Figure 5, if the first region enclosed by the closed path meon is contained within the closed path abcd, then the closed path meon is a lower-level closed path of the closed path abcd, that is, the closed path abcd is a higher-level closed path of the closed path meon. A detailed description of generating one or more sets of closed paths can be found in Figure 6 and its related description.

[0075] Step 320: For each set of closed paths, determine whether the set of closed paths contains the target closed path corresponding to the frame.

[0076] A drawing frame is a rectangular border used to define the boundaries of a view in a drawing. A closed path to an object can be used to represent a drawing frame.

[0077] In some embodiments, the processor 120 can process closed paths at various levels in the closed path set, starting from the highest level, until the target closed path is found or all closed paths in the closed path set have been processed. Generally, the drawing frame is a large area in the drawing that contains other rectangles; therefore, closed paths at higher levels in the closed path set are more likely to be the target closed path.

[0078] For example, in response to the existence of child nodes in the root node of the relation tree corresponding to the set of closed paths, the relation tree can be traversed from the root node to obtain the second rectangular closed path that satisfies the first preset condition.

[0079] In some embodiments of this specification, by prioritizing the processing of higher-level closed paths, the most likely target closed paths can be located more quickly, improving computational efficiency. A detailed description of processing closed paths at the current level can be found in Figure 8 and its related description.

[0080] The current level of closed paths may contain multiple closed paths. For example, as shown in Figure 9B, if the current level is the second level, the closed paths at the current level include two closed paths r1r2r3r4 and r5r6r7r8. The processor 120 can determine the path characteristics of the closed paths at the current level. The path characteristics of the closed paths may include: whether the closed path at the current level is a rectangle, the intersection-union ratio between the closed path at the current level and its subordinate closed paths, whether the closed path at the current level contains subordinate closed paths passing through its vertices, and the area of ​​the region enclosed by the closed path at the current level, etc. For a detailed description of the intersection-union ratio between the closed path at the current level and its subordinate closed paths, and whether the closed path at the current level contains subordinate closed paths passing through its vertices, please refer to the relevant description in step 820 regarding whether the rectangular closed path satisfies the first preset condition.

[0081] Furthermore, the processor 120 can sort closed paths at the current level based on path characteristics. For example, closed paths at the current level that have subordinate closed paths are prioritized. As another example, among multiple closed paths at the current level that have subordinate closed paths, those containing subordinate closed paths passing through their vertices are prioritized; among multiple closed paths at the current level that contain subordinate closed paths passing through their vertices, those with a larger intersection-union ratio (IU) with their subordinate closed paths are prioritized. As yet another example, among multiple closed paths at the current level that do not have subordinate closed paths, those enclosing larger regions are prioritized. For example, if closed paths r1r2r3r4 and r5r6r7r8 do not have subordinate closed paths, then the closed path r1r2r3r4, which encloses a larger region, is prioritized.

[0082] Furthermore, the processor 120 can process the sorted closed paths sequentially until the target closed path is found or all closed paths at the current level have been processed. A detailed description of the processing can be found in Figure 8 and its related description.

[0083] In some embodiments of this specification, sorting closed paths of the same level ensures that a more likely target closed path can be quickly located, thereby improving processing efficiency.

[0084] In some embodiments, the processor 120 may first filter the set of closed paths before processing them.

[0085] Specifically, the set of closed paths within the set of closed paths is filtered to obtain a filtered set of closed paths. This filtered set contains rectangular closed paths that satisfy a first preset condition and a second preset condition. The first preset condition relates to the positional relationship between a closed path and its subordinate closed paths, while the second preset condition relates to the features of the drawing frame. For example, a detailed description of the first and second preset conditions can be found in Figure 8 and its related description. Furthermore, the highest-level closed path in the filtered set of closed paths is selected as the target closed path.

[0086] Step 330: In response to the set of closed paths including the target closed path corresponding to the frame, determine that the target closed path constitutes the frame.

[0087] In some embodiments, in response to the set of closed paths including a target closed path corresponding to a frame, the processor 120 can determine that the target closed path constitutes a frame. For example, the processor 120 can determine the target closed path as a frame.

[0088] In some embodiments of this specification, rectangular closed paths that meet the first preset condition and the second preset condition are selected, thereby directly locating the target closed path and improving the efficiency of determining the target closed path.

[0089] In some embodiments of this specification, multiple closed paths in a drawing are identified, and based on the positional relationship between the multiple closed paths, the multiple closed paths are grouped and classified into levels to obtain a set of closed paths. The target closed path corresponding to the drawing frame is determined based on the set of closed paths. The target closed path can be determined based on multiple hierarchical closed paths, realizing the automated processing of complex drawings and greatly improving the speed and accuracy of drawing frame recognition.

[0090] Figure 3B is an exemplary flowchart illustrating the determination of a drawing frame according to other embodiments of this specification. In some embodiments, process 300B may be executed by processor 120. As shown in Figure 3B, process 300B includes the following steps.

[0091] Step 340: Determine whether there is an isolated closed path among the multiple closed paths that does not intersect with any other closed path.

[0092] The processor 120 can identify isolated closed paths as those that do not intersect with any other closed paths based on the positional relationships between multiple closed paths. For example, as shown in Figure 5, the closed path uvwx does not intersect with any other closed paths and can be identified as an isolated closed path.

[0093] Step 350: In response to determining that an isolated closed path exists, determine whether the isolated closed path is the target closed path.

[0094] Specifically, the processor 120 can determine whether an isolated closed path is a rectangular closed path that satisfies a second preset condition. The second preset condition is related to the frame features. A detailed description of the second preset condition can be found in Figure 8 and its related description. Further, in response to determining that the isolated closed path is a rectangular closed path that satisfies the second preset condition, the processor 120 can designate the isolated closed path as a target closed path.

[0095] Step 360: In response to the isolated closed path being the target closed path, determine the target closed path to form a graph frame.

[0096] In some embodiments, in response to an isolated closed path being a target closed path, the processor 120 may determine that the isolated closed path constitutes a frame. For example, the processor 120 may determine an isolated closed path as a frame.

[0097] In some embodiments of this specification, identifying and judging isolated closed paths ensures that no potential target closed paths are overlooked. Furthermore, judging isolated closed paths separately eliminates the need to consider the positional relationships between multiple closed paths, thus improving judgment efficiency. Simultaneously processing the relationships between other intersecting closed paths and isolated closed paths reduces the complexity of subsequent levels of closed path processing, optimizing the overall processing flow.

[0098] Figure 4 is a flowchart illustrating an exemplary method for determining multiple closed paths according to some embodiments of this specification. In some embodiments, process 400 is used to implement step 220.

[0099] Step 410: Extract multiple straight lines from the drawing.

[0100] For a detailed description of extracting multiple straight lines from a drawing, please refer to the relevant description of step 220. Figure 5 is a schematic diagram illustrating an exemplary determination of multiple closed paths according to some embodiments of this specification. As shown in Figure 5, the processor 120 extracts multiple straight lines 510 from the drawing 110, including lines ab, me, mf, mg, ef, eg, fg, etc.

[0101] Step 420: Construct an undirected graph based on multiple straight lines.

[0102] An undirected graph is a data structure used to represent relationships (e.g., whether a line forms a line) between objects (e.g., endpoints of a line). Vertices in an undirected graph correspond to the endpoints of multiple lines, and edges correspond to multiple lines. An undirected graph can include a list of vertices representing line endpoints and a list of edges representing lines.

[0103] Specifically, the processor 120 can determine whether the intersection point of a line with other lines is an endpoint of the line. If not, the line is split into two lines based on the intersection point. For example, as shown in Figure 5, the intersection point e of line mg and line el is not an endpoint of line mg, so line mg is split into line me and line eg based on the intersection point e; the intersection point f of line eg and line fj is not an endpoint of line eg, so line eg is further split into lines ef and fg based on the intersection point f.

[0104] Furthermore, the processor 120 can extract the endpoints of all lines to form a vertex list. For example, as shown in Figure 5, the endpoints a, b, m, e, f, g of lines ab, me, ef, fg, etc., can be extracted to form a vertex list.

[0105] Furthermore, the processor 120 can traverse the vertex list and, based on the intersection information of multiple lines, find the lines passing through the current vertex to form an edge list. For example, as shown in Figure 5, starting from vertex a, taking vertex m as an example, based on the intersection information of multiple lines, the processor can find the lines me, mf, and mg passing through vertex m to form a partial edge list.

[0106] Step 430: Determine multiple closed paths based on the undirected graph.

[0107] Specifically, the processor 120 can traverse the undirected graph using a depth-first search algorithm to obtain multiple initial closed paths. For any given traversal, the initial closed path is the path that starts from the vertex corresponding to the current traversal, follows the edges of the undirected graph through a series of vertices that have not been visited repeatedly, and finally returns to the starting vertex. For example, starting from vertex m, the initial closed paths meon, mefhjlon, and mefgikjlon can be obtained; starting from vertex n, the initial closed paths nmeo, nmefhjlo, and nmefgikjlo can be obtained.

[0108] Furthermore, the processor 120 can remove duplicate closed paths from multiple initial closed paths to obtain multiple closed paths. It is understood that starting traversal with different vertices may result in duplicate initial closed paths. For example, the aforementioned initial closed paths meon and nmeo are essentially duplicate initial closed paths.

[0109] First, the processor 120 can adjust multiple initial closed paths passing through the same vertex so that they all start from that vertex, and remove duplicate closed paths from the adjusted initial closed paths. For example, multiple initial closed paths meon, mefhjlon, mefgikjlon, nmeo, nmefhjlo, nmefgikjlo passing through vertex m can be adjusted to start from m, resulting in multiple adjusted initial closed paths meon, mefhjlon, mefgikjlon, meon, mefhjlon, mefgikjlon. After removing duplicate closed paths, multiple intermediate closed paths meon, mefhjlon, mefgikjlon are obtained.

[0110] Then, the processor 120 can determine whether multiple consecutive vertices in multiple intermediate closed paths are collinear. If so, the intermediate vertices are deleted. For example, taking the aforementioned intermediate closed path mefhjlon as an example, vertices m, e, and f are collinear, and vertices f, h, and j are collinear. The intermediate vertices e and h can be deleted to obtain the intermediate closed path mfjlon.

[0111] Finally, the multiple intermediate closed paths can be adjusted again so that they all start from the same vertex. Repeated intermediate closed paths are then removed from the adjusted paths to obtain multiple closed paths. To avoid overlap, Figure 5 only shows a portion of the closed paths, and these paths are placed to the right of their original positions for illustration.

[0112] In some embodiments of this specification, by extracting multiple straight lines from a drawing and constructing an undirected graph, multiple closed paths can be determined efficiently and accurately, thereby improving the accuracy and efficiency of frame recognition.

[0113] Figure 6 is a flowchart illustrating an exemplary method for generating one or more closed path sets according to some embodiments of this specification. In some embodiments, process 600 is used to implement step 310.

[0114] Step 610: Based on the positional relationship between multiple closed paths, determine one or more sets of intersecting closed paths, and define each set of intersecting closed paths as a closed path contained in a closed path set.

[0115] In each group of intersecting closed paths, any one closed path intersects with at least one other closed path in that group. Specifically, the processor 120 can determine whether the regions enclosed by any two closed paths intersect; if they intersect, it assigns them to the same group of closed paths.

[0116] For example, as shown in Figure 5, the multiple closed paths in the dashed box can be a set of intersecting closed paths, where the multiple closed paths are the closed paths contained in the set A of closed paths.

[0117] Step 620: For each set of closed paths, determine the level of each closed path in the set of closed paths based on the area of ​​the region enclosed by each closed path. Specifically, step 620 may include the following sub-steps:

[0118] Sub-step 622: By comparing the areas of the two regions enclosed by any two intersecting closed paths, the initial superordinate closed path among the two intersecting closed paths is determined. For example, taking the aforementioned set of closed paths A as an example, if the area enclosed by the closed path abcd is greater than the area enclosed by its intersecting closed path mfjlon, then the closed path abcd is the initial superordinate closed path of the closed path mfjlon.

[0119] For each closed path, the processor 120 can determine the number of its initial parent closed paths.

[0120] Sub-step 624: In response to the fact that the number of its initial parent closed paths is zero, the closed path is determined to be the top-level closed path.

[0121] For example, if the number of initial superior closed paths of closed path abcd in the aforementioned set of closed paths A is zero, then closed path abcd is determined as the superior closed path.

[0122] Sub-step 626: In response to the fact that the number of its initial parent closed paths is one, the initial parent closed path is determined as its parent closed path.

[0123] For example, if the number of initial parent closed paths of closed path mgklon in the aforementioned set of closed paths is one, that is, the initial parent closed path abcd, then the initial parent closed path abcd is determined as the parent closed path of closed path mgklon.

[0124] Sub-step 628: In response to the number of initial parent closed paths being two or more, determine the parent closed path of the closed path based on the intersection-union ratio of the closed path and each initial parent closed path.

[0125] For example, if the number of initial parent closed paths of the closed path efjl in the aforementioned closed path set A is 8, including the initial parent closed paths abcd, mgklon, mgihjlon, ..., mfjlon, then the parent closed path of the closed path is determined according to the intersection-union ratio of the closed path efjl and each initial parent closed path.

[0126] The intersection-to-union ratio is the ratio of the area of ​​the intersection region of a closed path and its initial superior closed path to the area of ​​the unification region. Specifically, the processor 120 can determine the initial superior closed path corresponding to the maximum value of two or more intersection-to-union ratios as the superior closed path of the closed path.

[0127] For example, the intersection-union ratios of the closed path efjl and the initial parent closed paths abcd, mgklon, mgihjlon, ..., mfjlon are S, respectively. efjl / S abcd S efjl / S mgklon S efjl / S mgihjlon S efjl / S egkl The maximum value S can be obtained. efjl / S mfjlon The corresponding initial parent closed path mfjlon is determined as the parent closed path of the closed path efjl.

[0128] In some embodiments of this specification, different methods are used to determine the superior closed paths of a closed path based on the number of its initial superior closed paths. This can effectively determine the corresponding superior closed paths for different types of closed paths, thereby improving the accuracy of the level division of multiple closed paths.

[0129] In some embodiments of this specification, by analyzing the positional relationships between multiple closed paths, the closed paths included in the closed path set are determined, and by comparing the areas of the two regions enclosed by any two intersecting closed paths, the levels of multiple closed paths in the closed path set are determined. This allows for a more accurate analysis of the hierarchical relationships between multiple closed paths, thereby facilitating subsequent hierarchical analysis of multiple closed paths.

[0130] In some embodiments, the processor 120 may represent each set of closed paths using a relational tree. The top-level closed path in each set of closed paths may be determined as the root node of the relational tree, and the lower-level closed paths in each set of closed paths may be determined as child nodes of the upper-level closed paths. Figure 7 is a schematic diagram of an exemplary relational tree for representing a set of closed paths according to some embodiments of this specification. Referring to Figures 5 and 7, the top-level closed path abcd in closed path set A may be determined as the root node P1 of the relational tree, and the lower-level closed paths mgklon may be determined as child nodes P2, ... of the upper-level closed path abcd.

[0131] In some embodiments of this specification, a relationship tree is used to represent the levels between multiple closed paths in a set of closed paths, which can intuitively reflect the hierarchical structure between multiple closed paths.

[0132] Figure 8 is a flowchart of an exemplary method for processing a closed path at the current level according to some embodiments of this specification.

[0133] Step 810: Determine the rectangular closed path in the closed path of the current level.

[0134] Specifically, if a closed path at the current level conforms to the rectangular feature, it is determined to be a rectangular closed path. The rectangular feature is a characteristic used to distinguish rectangular closed paths. For example, a rectangular feature could be that the closed path has exactly two edges passing through any vertex, and the included angle between these two lines is a right angle. Another example is that a rectangular feature could be that the closed path consists of four lines connected sequentially, and the included angle between any two adjacent lines is a right angle.

[0135] For example, consider the set of closed paths A shown in Figure 5. For instance, the closed path abcd at the current level conforms to the rectangular feature, and the closed path abcd is a rectangular closed path.

[0136] Step 820: Determine whether the rectangular closed path satisfies the first preset condition and the second preset condition.

[0137] The first preset condition relates to the positional relationship between a closed path and its subordinate closed paths. In some embodiments, the first preset condition includes the existence of a subordinate closed path in which the rectangular closed path has an intersection-union ratio greater than a preset threshold, or the rectangular closed path contains a subordinate closed path passing through its vertices.

[0138] If a rectangular closed path has a lower-level closed path with an intersection-union ratio (IUR) greater than a preset threshold, it may prevent the rectangular closed path from being a meaningless closed path containing a frame. A detailed description of the IUR can be found in the relevant description of step 628. The preset threshold can be determined manually, for example, 0.8. For example, as shown in Figure 5, if the IUR of the rectangular closed path abcd with its lower-level closed path mgklon is greater than 0.8, then the rectangular closed path abcd satisfies the first preset condition.

[0139] A rectangular closed path includes subordinate closed paths passing through its vertices, which may correspond to the case where the subordinate closed path is a title block. The vertices can be determined based on the drawing habits of the drawing personnel. For example, if the drawing personnel habitually draw the title block in the lower right corner of the title block, then the vertex can be determined as the lower right point. For example, Figures 9A and 9B are schematic diagrams of exemplary closed path sets according to some embodiments of this specification. As shown in Figure 9A, the subordinate closed paths x2x5x6x7 of the rectangular closed path x1x2x3x4 pass through its lower right point x2, then the rectangular closed path x1x2x3x4 satisfies the first preset condition.

[0140] For example, as shown in Figure 9B, the intersection-union ratios of the rectangular closed path t1t2t3t4 with the lower-level closed paths r1r2r3r4 and r5r6r7r8 are all less than the preset threshold of 0.8, and the lower-level closed paths r1r2r3r4 and r5r6r7r8 do not pass through the vertices of the rectangular closed path t1t2t3t4. Therefore, the rectangular closed path t1t2t3t4 does not satisfy the first preset condition.

[0141] In some embodiments, for each rectangular closed path, the processor 120 first determines whether the rectangular closed path has a lower-level closed path with an intersection-union ratio greater than a preset threshold; if it does, it determines that it satisfies a first preset condition; if it does not, it continues to determine whether the rectangular closed path contains a lower-level closed path passing through its vertices; if it does, it determines that it satisfies the first closed path condition. In some embodiments, for each rectangular closed path, the processor 120 determines whether the rectangular closed path has a lower-level closed path with an intersection-union ratio greater than a preset threshold and whether it contains a lower-level closed path passing through its vertices, respectively, obtaining two determination results; then, based on these two determination results, it determines whether the rectangular closed path satisfies the first preset condition.

[0142] In some embodiments of this specification, the first preset condition takes into account the positional relationship between upper and lower closed paths in two special cases, thereby improving the accuracy of identifying target closed paths.

[0143] The second preset condition is related to the features of the drawing frame. In some embodiments, the second preset condition may be that the area enclosed by the rectangular closed path contains title information. Specifically, text recognition technology, such as Optical Character Recognition (OCR), can be used to recognize the text information in the area enclosed by the rectangular closed path, and then it can be retrieved whether the text information contains title keywords (e.g., drawing name, drawing number, scale, design unit, designer, date, etc.). If so, it indicates that title information is contained.

[0144] Step 830: In response to determining that the rectangular closed path satisfies the first preset condition and the second preset condition, the rectangular closed path is determined as the target closed path.

[0145] For example, as shown in Figure 5, the rectangular closed path abcd satisfies the first preset condition and the second preset condition, and the rectangular closed path abcd is determined as the target closed path.

[0146] Step 840: In response to determining that the rectangular closed path does not meet the first preset condition or the second preset condition, process the closed path of the next level.

[0147] For example, as shown in Figure 9B, the rectangular closed path t1t2t3t4 does not meet the first preset condition, so the next level closed paths r1r2r3r4 and r5r6r7r8 are processed respectively.

[0148] In some embodiments of this specification, by first verifying whether the closed path is a rectangular closed path, and then verifying whether the rectangular closed path satisfies a first preset condition related to the positional relationship with the lower-level closed path and a second preset condition related to the features of the frame, on the one hand, multiple verifications ensure that the finally determined target closed path corresponds to the frame; on the other hand, the step-by-step verification method can quickly eliminate closed paths that do not meet the conditions, avoid unnecessary calculations, thereby improving the accuracy and efficiency of target closed path recognition.

[0149] It should be noted that the above description is provided for illustrative purposes only and is not intended to limit the scope of this specification. Various changes and modifications can be made by those skilled in the art based on the content of this specification. Features, structures, methods, and other features of the exemplary embodiments described herein can be combined in various ways to obtain other and / or alternative exemplary embodiments. However, these changes and modifications will not depart from the scope of this specification.

[0150] The beneficial effects that the method for determining the drawing frame described in the embodiments of this specification may bring include, but are not limited to: (1) identifying multiple closed paths in the drawing, and grouping and classifying the multiple closed paths according to the positional relationship between them to obtain a set of closed paths, and determining the target closed path corresponding to the drawing frame according to the set of closed paths. The target closed path can be determined based on the hierarchical multiple closed paths, realizing the automated processing of complex drawings, and greatly improving the speed and accuracy of drawing frame recognition; (2) determining the closed paths contained in the set of closed paths by analyzing the positional relationship between multiple closed paths, and determining the level of multiple closed paths in the set of closed paths by comparing the areas of the two regions enclosed by any two intersecting closed paths. The hierarchical relationship between multiple closed paths can be analyzed more accurately, which helps to perform hierarchical analysis of multiple closed paths in the future; (3) using different methods to determine the upper-level closed paths of the closed paths according to the number of the initial upper-level closed paths of the closed paths. This can effectively determine the corresponding upper-level closed paths for different types of closed paths. (4) By prioritizing the processing of high-level closed paths, the target closed path with a higher probability can be located more quickly, improving computational efficiency. In addition, by first verifying whether the closed path is a rectangular closed path, and then verifying whether the rectangular closed path meets the first preset condition related to the positional relationship with the lower-level closed path and the second preset condition related to the frame feature, on the one hand, multiple verifications ensure that the final target closed path corresponds to the frame; on the other hand, the step-by-step verification method can quickly eliminate closed paths that do not meet the conditions, avoid unnecessary calculations, thereby improving the accuracy and efficiency of target closed path identification; (5) Filtering rectangular closed paths that meet the first and second preset conditions, thereby directly locating the target closed path, improving the efficiency of determining the target closed path; (6) Identifying and judging isolated closed paths, on the one hand, can ensure that potential target closed paths are not missed; on the other hand, judging isolated closed paths separately does not require considering the positional relationship between multiple closed paths, thereby improving the judgment efficiency. Simultaneously processing the relationship between other multiple intersecting closed paths and isolated closed paths reduces the complexity of subsequent multiple levels of closed path processing and optimizes the overall processing flow.

[0151] Figure 10 is an exemplary flowchart illustrating the determination of label information according to some embodiments of this specification. In some embodiments, process 1000 may be executed by processor 120.

[0152] Step 1010: Determine the first closed path list based on the drawing frame and title block range.

[0153] In engineering drawings, a drawing frame refers to the outline that defines the drawing area on a sheet of paper, usually drawn with a thick solid line. The drawing frame is used to indicate the drawing area of ​​a sheet.

[0154] The first closed path list consists of multiple first closed paths. In some embodiments, the first closed path list includes all first closed paths that do not contain other closed paths.

[0155] The first closed path refers to a closed path within the label area that does not contain any other closed paths, i.e., the smallest rectangle within the label area.

[0156] A closed path is a path that connects a starting point and an ending point. A path can be a line segment on a drawing. A closed path can form a closed shape. For example, in a tabular title block containing multiple closed rectangles, the smallest rectangle that does not contain any other rectangles is the first closed path.

[0157] In some embodiments, the processor can determine a first closed path based on a variety of methods, and then determine a list of first closed paths. For example, the processor can determine a first closed path in multiple map regions within a frame through image recognition (e.g., connected component analysis, Hough transform, etc.), and generate a list of first closed paths based on one or more first closed paths.

[0158] In some embodiments, the processor may determine the line segments that intersect the frame and the label range; construct an undirected graph based on the line segments and the intersection of the frame and the label range; traverse the undirected graph to determine multiple closed paths; and determine a first list of closed paths based on the inclusion relationship between the multiple closed paths.

[0159] In some embodiments, line segments in a drawing may include graphic outline lines, annotation line segments, dimension lines, etc.

[0160] In some embodiments, the processor can determine the straight line segments that intersect the drawing and the label area based on computer recognition algorithms (such as line intersection analysis).

[0161] An undirected graph is a mathematically structured graph consisting of vertices and edges. The vertices of an undirected graph are the intersections of line segments, and the edges are line segments. An edge is formed when the endpoints of two line segments corresponding to two intersection points are also endpoints of a line segment. The edges of an undirected graph have no direction.

[0162] In some embodiments, the processor can construct an undirected graph using various methods. For example, the processor can use a computer recognition algorithm to identify the line segments that intersect the drawing and the label area, and use the intersection points formed by the intersection of the line segments as vertices of the undirected graph; based on multiple vertices, it can determine whether any two vertices are the two endpoints of the same line segment, and if so, connect the two vertices to form an edge of the undirected graph to construct the undirected graph.

[0163] A closed path is a path that connects a starting point and an ending point, forming a closed shape. In some embodiments, multiple closed paths may have an inclusion or containment relationship.

[0164] In some embodiments, the processor may determine a closed path that does not contain other closed paths (i.e., the smallest closed path) as a first closed path and construct a first closed path list based on the first closed path.

[0165] In some embodiments of this specification, determining the first closed path list based on an undirected graph is beneficial for accurately determining closed paths that do not contain other closed paths, thereby making the first closed path list more accurate and complete.

[0166] Step 1020: Based on the text element range in the text element list and the first closed path in the first closed path list, determine the closed path to which the tag field belongs.

[0167] A text element list is a list consisting of text elements from a drawing.

[0168] Text primitives refer to the physical entities containing text in a drawing. Text primitives can include text information (e.g., drawing name, drawing number). In some embodiments, text primitives may also contain other information related to the text, such as location points (e.g., coordinates (50, 120)) and extent information (e.g., [x...]). min =50,y min =100,x max =150,y max =120], where x min and x max Let y be the minimum and maximum x-coordinates of each vertex of the rectangle containing the text primitive (i.e., the area of ​​the text primitive). min and y max These are the minimum and maximum ordinates of each vertex of the rectangle containing the text element, respectively.

[0169] In some embodiments, the processor can acquire text elements in a drawing using computer recognition algorithms. These algorithms may include image recognition, OCR recognition, etc.

[0170] In some embodiments, the processor may obtain a list of text primitives based on user input.

[0171] In some embodiments, the processor can determine the text elements contained in the drawing, and then determine a list of text elements. For example, the processor can cluster the text elements determined from the drawing, and identify text elements belonging to the same cluster category as the same text element in the list of text elements. For example, texts such as "drawing name", "drawing title", "drawing name", and "drawing name" can be clustered into the same cluster category and identified as the same text element in the list of text elements.

[0172] The processor can determine text elements from a drawing in various ways. In some embodiments, the processor can acquire elements within a drawing frame based on parsing techniques. The drawing frame may contain multiple types of elements. The processor can further determine text elements from these multiple types of elements.

[0173] Analysis techniques refer to the techniques used to analyze drawings. Analysis techniques can include geometric analysis techniques, text analysis techniques, layer analysis techniques, attribute analysis techniques, etc.

[0174] Graphical elements refer to the basic elements in a drawing. Graphical elements include various types such as text elements, line segments, and polylines. A polyline can be broken down into multiple line segments. For example, a polyline can be a closed rectangle formed by multiple line segments, or a broken line formed by connecting multiple line segments.

[0175] In some embodiments, the processor can determine text primitives from multiple types of primitives based on computer recognition technology, etc.

[0176] In some embodiments, the processor can also generate a list of graphic elements based on text graphic elements in the drawing; and generate a list of text graphic elements based on the list of graphic elements and a table of commonly used text information.

[0177] The primitive information list includes one or more text primitives.

[0178] In some embodiments, the processor can fill all the text elements identified from the drawing into the element information list one by one.

[0179] In some embodiments, the list of commonly used text information includes multiple commonly used text information.

[0180] Commonly used text information refers to the frequently used textual descriptions of the title tag field or the text corresponding to the title tag field value in different drawings. For example, the title tag field "Drawing Name" is generally "Drawing Title" in Design Institute A's drawings, and generally "Drawing Name" in Design Institute B's drawings. Therefore, both "Drawing Title" and "Drawing Name" are commonly used textual information for the title tag field "Drawing Name". Title tag field values ​​refer to the content values ​​of the title tag field. Title tag fields are fields used to represent the attributes of the title tag. For example, title tag fields may include the title tag, drawing number, and drafter's name. Title tag field values ​​may include the content values ​​corresponding to the title tag, the drawing number, and the drafter's name, etc.

[0181] In some embodiments, the list of frequently used text information may be constructed by technicians based on experience. In some embodiments, the processor may construct the list of frequently used text information based on historical data. For example, the processor may analyze drawings from different design institutes, identify text content that appears frequently (e.g., exceeding a certain threshold) as frequently used text information, and add it to the list of frequently used text information.

[0182] In some embodiments, the list of commonly used text information includes multiple commonly used text information (i.e., the text of text primitives).

[0183] In some embodiments, the processor can acquire image tag information and commonly used text information; and determine a commonly used text information table based on the image tag information and commonly used text information.

[0184] In some embodiments, the label information includes a label field and a label field value.

[0185] In some embodiments, the processor can determine a common text information table based on the title block information, common text information, and the correspondence between the title block information and the common text information. For example, the processor determines the common text information of each title block information in historical drawings based on historical data. For each title block information, the processor can determine one or more historical drawings corresponding to the title block information. Each historical drawing may include a common text information corresponding to the title block information. The title block information and the common text information in the one or more historical drawings corresponding to it are constructed into a record, and a common text information table is constructed based on multiple records.

[0186] In some embodiments, the processor can generate a list of text elements in various ways. For example, the processor can traverse the element information list and determine whether a certain text element in the element information list is included in a common text information table (i.e., the text element has at least one field in the common text information table). If it is included, the processor records the tag field corresponding to the text element and adds the tag field to the text element list; if it is not included, the processor continues to traverse the next text element in the element information list.

[0187] In some embodiments of this specification, a text primitive list is generated based on a primitive information list and a commonly used text information list. This facilitates the more accurate generation of the text primitive list and reduces errors caused by manual generation.

[0188] The primitive extent refers to the bounding rectangle containing the primitive. For example, the primitive extent of a text primitive can be the rectangular area formed by the maximum and minimum ordinates, maximum and minimum abscissas of the bounding rectangle of the text primitive. As another example, for a line segment, the primitive extent of the line segment can be the coordinates of the endpoints of the line segment and the line connecting the two endpoints.

[0189] The closed path to which a title field belongs refers to the complete containment between the text element of the title field and a closed path that does not contain other closed paths.

[0190] In some embodiments, for any text element in the text element list, the element range processor can determine the inclusion relationship between the element range and each closed path that does not contain other closed paths, and determine the closed path that completely contains the element range and does not contain other closed paths as the closed path to which the tag field corresponding to the text element belongs.

[0191] Step 1030: Based on the first intersection ratio between the closed path and the primitive range, and the offset distance between the center point of the text primitive range and the center point of the closed path, determine the content value range of the tag field.

[0192] The first intersection ratio is a metric used to measure the degree of overlap between the closed path to which a tag field belongs and the geographic extent of the corresponding text element. The first intersection ratio can be expressed numerically; the larger the value of the first intersection ratio, the greater the degree of overlap between the closed path and the geographic extent.

[0193] In some embodiments, the processor may determine the overlapping area between the closed path to which the tag field belongs and the primitive range of the text primitive corresponding to the tag field, and determine a first intersection ratio based on the overlapping area and the closed path. For example, the processor may determine the area of ​​the overlapping area between the primitive range of the text primitive and the closed path, and determine the first intersection ratio as the ratio of the area of ​​the overlapping area to the enclosed area corresponding to the closed path.

[0194] The center point of the range refers to the center point of the range of text primitives.

[0195] In some embodiments, the processor can determine the range center point based on the geometric center point of the text primitive's primitive range. For example, if the primitive range of the text primitive is a rectangular area, the processor can determine the geometric center point of that rectangular area as the range center point.

[0196] Offset distance refers to the distance in the target direction between the center point of the text element's range and the center point of the area enclosed by its closed path. The target direction can be either the horizontal or vertical axis of the drawing, and can be set according to actual needs.

[0197] In some embodiments, the processor can calculate the relative distance in the target direction between the center point of the text primitive range and the center point of the enclosed area of ​​the corresponding closed path, and thus determine the offset distance.

[0198] The content value range refers to the range of text elements corresponding to the tag field value of the tag field.

[0199] In some embodiments, the processor may base its work on a first intersection ratio between the closed path and the primitive's extent, and the offset distance between the center point of the text primitive's extent and the center point of its closed path.

[0200] For more information on how to determine the range of content values, please refer to Figure 11 and its related description.

[0201] Step 1040: Obtain the text content value within the content value range according to the content value range.

[0202] The text content value refers to the text within the content value range. For example, if cell B in the content value range A contains the text "Electrical Design Specification", then "Electrical Design Specification" is the text content value of the content value range A.

[0203] In some embodiments, the processor may acquire text content values ​​within a specified range based on computer recognition algorithms. These algorithms may include image recognition, OCR recognition, etc.

[0204] In some embodiments of this specification, a first closed path is determined based on the scope of the title block, and the corresponding closed path is determined. The content value range is determined by the intersection ratio between the corresponding closed path and the scope of the text element, as well as the offset distance between the center point of the text element's scope and the center point of the corresponding closed path, thereby extracting the text content value. This is beneficial for accurately determining the scope of title block fields in drawings from different design institutes and according to different standards, and improves the accuracy of identifying text content values.

[0205] Figure 11 is an exemplary schematic diagram illustrating the determination of a range of content values ​​according to some embodiments of this description. In some embodiments, process 1100 may be executed by processor 120.

[0206] As shown in Figure 11, in some embodiments, the processor can also determine the content value range based on the closed path to which the tag field belongs, the first intersection ratio 1110 between the tag field and the primitive range of the text primitive corresponding to the tag field, the offset distance 1120 between the center point of the range of the text primitive corresponding to the tag field and the center point of the closed path to which the tag field belongs, and the closed path to which the tag field belongs.

[0207] As shown in Figure 11, in some embodiments, the processor can determine whether the first intersection ratio 1110 and the offset distance 1120 satisfy a third preset condition; and in response to the first intersection ratio 1110 and the offset distance 1120 satisfying the third preset condition, the range of the closed path to which they belong is taken as the range of content values.

[0208] In some embodiments, the third preset condition may include a weighted sum of the first intersection ratio and the offset distance that is greater than a preset threshold. The weights corresponding to the first intersection ratio and the offset distance, and the preset threshold, may be preset by the processor based on default settings or by a technician based on experience.

[0209] In some embodiments, the third preset condition may further include a first intersection ratio less than or equal to a first threshold, and the ratio of the offset distance to the target direction length of the closed path being to which it belongs is greater than a second threshold. Here, the target direction length refers to the projected length of the closed path in the target direction.

[0210] The first threshold refers to a threshold related to the first intersection ratio. For example, the first threshold can be any value between 0.1 and 0.6. Another example is that the first threshold can be any value between 0.2 and 0.5. Yet another example is that the first threshold can also be any value between 0.25 and 0.45. When the first intersection ratio is less than or equal to the first threshold, the degree of overlap between the closed path and the primitive range is relatively small.

[0211] In some embodiments, the first threshold may be a system default value, an empirical value, a manually preset value, or any combination thereof, and can be set according to actual needs.

[0212] The second threshold is a threshold related to the offset distance. For example, the second threshold can be any value between 0.1 and 0.7. Another example is that the second threshold can be any value between 0.2 and 0.6. Yet another example is that the second threshold can also be any value between 0.25 and 0.55. When the ratio of the offset distance to the target direction length of the corresponding closed path is greater than the second threshold, the text element corresponding to the tag field and the closed path to which the tag field belongs are within the same closed path.

[0213] In some embodiments, the second threshold may be a system default value, an empirical value, a manually preset value, or any combination thereof, and can be set according to actual needs.

[0214] In some embodiments of this specification, the third preset condition is determined by using a first threshold and a second threshold, which helps to reduce erroneous identification of the content value range, improve the identification efficiency of the content value range, and reduce redundant calculations.

[0215] The scope of a closed path refers to the area enclosed by the straight line segments that make up the closed path.

[0216] In some embodiments of this specification, based on whether the first intersection ratio and offset distance meet the third preset condition, the range of the closed path to which the content value is located is taken as the content value range. This is beneficial for accurately determining the content value range of the title field in drawings of different design institutes and different standards, thereby improving the accuracy of identifying text content values.

[0217] Referring to Figure 11, in some embodiments, the processor may also, in response to the first intersection ratio 1110 and offset distance 1120 not satisfying the third preset condition, determine an adjacent closed path 1130 that shares a vertex with the corresponding closed path; determine the adjacent closed path that satisfies the filtering condition as a second closed path 1140 and generate a second closed path list 1150; and determine the content value range 1160 based on the second closed path list 1150.

[0218] In some embodiments, the first intersection ratio and offset distance not satisfying the third preset condition includes the first intersection ratio being not less than or equal to a first threshold, and / or the ratio of the offset distance to the target direction length of the closed path being not greater than a second threshold.

[0219] Adjacent closed paths refer to closed paths that share a vertex with their parent closed paths. For example, Figure 13 is an exemplary schematic diagram of a title block according to some embodiments of this specification. As shown in Figure 13, the cell containing the title block "Drawing" is the closed path to which the title block field "Drawing" belongs. Adjacent closed paths to this parent closed path may include the closed paths containing the text elements "X University Architectural Design Institute", "Personnel A", "Design", and "Personnel B".

[0220] In some embodiments, if the first intersection ratio is less than or equal to the first threshold, and the ratio of the offset distance to the target direction length of the closed path is greater than the second threshold, then the first intersection ratio and the offset distance satisfy the third preset condition. For example, as shown in FIG. 13, taking the drawing signature field "Project Name" as an example, the first intersection ratio of the range of "Project Name" (i.e., the graphic element range of the text graphic element corresponding to the text "Project Name") and the closed path to which "Project Name" belongs is between 0.1 and 0.5, and the distance projected in the target direction (i.e., the horizontal direction in the figure) between the center point of the graphic element range of the drawing signature field "Project Name" and the center point of the closed path to which it belongs is greater than 0.1 to 0.7 times the projected length of the closed path in the horizontal direction, then it is considered that the first intersection ratio and the offset distance of the drawing signature field "Project Name" and the closed path to which it belongs satisfy the third preset condition. Then it is considered that the content value "A" of the field and the text graphic element "Project Name" are within the same closed path, and the range of the closed path to which it belongs is the range of the content value of the drawing signature field, and the text content value can be determined therefrom, which is "A".

[0221] In some embodiments, if the first intersection ratio is not less than or equal to the first threshold, and / or the ratio of the offset distance to the target direction length of the closed path is not greater than the second threshold, then the first intersection ratio and / or the offset distance do not satisfy the third preset condition. For example, as shown in FIG. 13, taking the drawing signature field "Drafting" as an example, the distance projected in the target direction (i.e., the horizontal direction in the figure) between the center point of the graphic element range of "Drafting" (i.e., the graphic element range of the text graphic element corresponding to the text "Drafting") and the center point of the corresponding closed path to which it belongs is greater than 0.7 times the projected length of the closed path in the horizontal direction, it is considered that the drawing signature field "Drafting" does not satisfy the third preset condition, and the adjacent closed path sharing the same vertex with the closed path to which "Drafting" belongs is further determined.

[0222] In some embodiments, the processor can determine the adjacent closed path through various methods. For example, the processor can traverse the undirected graph to determine the adjacent closed path sharing the same vertex with the closed path to which it belongs.

[0223] The second closed path list refers to a list containing the second closed path. The second closed path refers to an adjacent closed path that is not occupied by any drawing signature field in the drawing or is occupied by the text graphic element corresponding to the value of the drawing signature field. In some embodiments, the second closed path list can be empty.

[0224] In some embodiments, the filtering criteria include that the second closed path is not occupied by any title field in the drawing or is not occupied by the text element corresponding to the title field value. For example, if among the adjacent closed paths of the belonging closed path, there is an adjacent closed path that is neither determined to be the closed path of a title field nor the closed path of a text element corresponding to a title field value, then the adjacent closed path can be used as the second closed path. As shown in Figure 13, among the adjacent closed paths "Personnel A", "Design", "X University Architectural Design Institute", and "Personnel B" that share a vertex with the closed path belonging to "Drafting", closed paths that have been occupied by title fields, such as "X University Architectural Design Institute" and "Design", are excluded; then closed paths that have been occupied by other field content values, such as the closed path occupied by the content value "Personnel B" of the "Design" title, are excluded, and the closed path belonging to "Personnel A" is used as the second closed path.

[0225] In some embodiments, the processor may determine the range of content values ​​based on the number of second closed paths in the second closed path list.

[0226] In some embodiments, the processor may determine the number of paths in the second closed path list; in response to the number of paths in the second closed path list being 0, determine the corresponding closed path as a content value range; in response to the number of paths in the second closed path list being greater than 0, determine the aggregation range of each second closed path in the second closed path list with its corresponding path range, and determine the second intersection ratio of each aggregation range with the tag range; in response to the number of second closed paths whose second intersection ratio satisfies a fourth preset condition being less than a preset number, use the second closed paths whose second intersection ratio satisfies the fourth preset condition as content value ranges; and in response to the number of second closed paths whose second intersection ratio satisfies the fourth preset condition being not less than a preset number, calculate the target distance in a preset direction between the center point of each second closed path and the center point of its corresponding closed path, and use the second closed paths whose target distance in a preset direction satisfies a third preset condition as content value ranges.

[0227] The number of paths refers to the number of second closed paths in the second closed path list.

[0228] The aggregation range can be the union of the second closed path and the path range to which the tag field belongs.

[0229] The second intersection ratio refers to the intersection ratio between the aggregation range and the label range. The second intersection ratio can be expressed numerically. The larger the second intersection ratio, the greater the intersection between the second closed path and the label range. In some embodiments, the processor can determine the second intersection ratio as the ratio between the area of ​​the aggregation range and the area of ​​the label range.

[0230] In some embodiments, the fourth preset condition includes a second intersection ratio being less than a fifth threshold. The fifth threshold can be represented by a numerical value. For example, the fifth threshold can be any value between 0.2 and 0.5.

[0231] In some embodiments, the fourth preset condition includes minimizing the second crossover ratio.

[0232] In some embodiments, the fourth preset condition may be a system default value, an empirical value, a manually preset value, or any combination thereof, and can be set according to actual needs.

[0233] The preset quantity can be expressed numerically. In some embodiments, the preset quantity can be a system default value, an empirical value, a manually preset value, or any combination thereof, and can be set according to actual needs. For example, the preset quantity can be 1.

[0234] The target distance refers to the distance between the center point of the second closed path and the center point of its parent closed path in a preset direction. In some embodiments, the preset direction may be the vertical axis of the drawing.

[0235] In some embodiments, the third preset condition includes minimizing the target distance.

[0236] In some embodiments, the processor may use a second closed path whose target distance satisfies a third preset condition as the content value range. For example, the processor may calculate the value of the center point of the second closed path and the center point of its parent closed path in the vertical axis direction, and use the second closed path corresponding to the center point of the second closed path with the smallest value in the vertical axis direction as the content value range.

[0237] As an example only, the processor can obtain the number of second closed paths contained in the second closed path list. When the number of paths is determined to be 0, the closed path belonging to the tag field is determined as the content value range. That is, when there are no adjacent closed paths, the content value range is further determined within the closed paths belonging to the tag field. When the number of second closed paths contained in the second closed path list is not 0, i.e., it contains multiple adjacent closed paths, the second intersection ratio of each second closed path in the second closed path list with the tag range is further determined, and the second closed path whose second intersection ratio is less than the fifth threshold is determined (hereinafter referred to as the target second closed path).

[0238] When the number of target second closed paths is less than the preset number, the target second closed paths are determined as the content value range; when the number of target second closed paths is not less than the preset number, the target distance between the center point of each target second closed path and the center point of its corresponding closed path in the vertical axis direction of the drawing is further determined, and the target second closed path with the smallest target distance is determined as the content value range.

[0239] In some embodiments of this specification, the content value range is determined based on the number of paths in the second closed path list, the fourth preset condition, and the preset quantity. This is beneficial for dynamically adjusting the strategy for identifying the content value range, adapting to the drawing structures of different drawings from different design institutes, thereby more accurately determining the content value range and improving the accuracy of content value range identification.

[0240] In some embodiments of this specification, adjacent closed paths are determined based on a first intersection ratio, offset distance, and a third preset condition, thereby generating a second list of closed paths and determining the range of content values. This allows for automatic adjustment of the recognition steps from analyzing the belonging closed path to analyzing adjacent closed paths, which is beneficial for improving the fault tolerance capability of the recognized content value range.

[0241] Figure 12 is an exemplary flowchart illustrating the determination of the label range according to some embodiments of this specification.

[0242] In some embodiments, process 1200 may be executed by processor 120. As shown in FIG12, process 1200 includes the following steps:

[0243] Step 1210: Generate a list of graphic element information based on the text graphic elements in the drawing.

[0244] For more information on generating a list of primitive information based on text primitives, please refer to the relevant description in Figure 10.

[0245] Step 1220: Determine the aggregation range list based on the aggregation of text elements in the element information list.

[0246] Aggregation refers to the overall overlap between text elements. For example, the aggregation between two text elements can include overlap, partial overlap, containment, partial containment, and no overlap.

[0247] In some embodiments, the processor can determine the aggregation of text primitives based on the intersection-union ratio (CIRR). The CIRR is the ratio of the intersection to the union of the primitive ranges of multiple text primitives. For example, the processor can calculate the CIRR between the primitive ranges of any two text primitives and determine the aggregation by checking whether the CIRR falls within a threshold range. The threshold range can include multiple sub-threshold ranges, each corresponding to a different aggregation. When the CIRR of two text primitives falls within a certain sub-threshold range, the aggregation corresponding to that sub-threshold range is considered the aggregation of the primitive ranges of those two text primitives. In some embodiments, the correspondence between different sub-threshold ranges and different aggregation scenarios can be pre-defined.

[0248] An aggregation range list is a list that contains aggregation ranges. In some embodiments, an aggregation range may include the range of a single text primitive, the union of the ranges of multiple text primitives, etc. In some embodiments, the aggregation range list may be empty, in which case the aggregation range list does not contain the range of any text primitive.

[0249] In some embodiments, the processor may determine an aggregate range list based on the element extent and frame extent of the text primitives. Further details on how the aggregate range list is determined can be found in the following description.

[0250] Step 1230: Determine the label range based on the aggregated range list.

[0251] In some embodiments, the processor can determine the tag range based on the frequency of occurrence of different tag fields in the aggregation range list. For example, the processor can determine the aggregation range corresponding to the tag field that appears most frequently as the tag range.

[0252] For example, the processor can calculate the intersection of other element ranges with the initial element range based on the four corner positions of the drawing (e.g., the lower left or lower right element range). If there is an intersection between the other element ranges and the initial element range, the processor takes the union of the other element ranges and the initial element range to obtain the first aggregate range. The processor then calculates the intersection of the first aggregate range with other element ranges. If there is an intersection, the processor takes the union of the first aggregate range with the other element ranges to obtain the second element range, and so on, until the last element range is merged into the nth aggregate range. The processor can then construct an aggregate range list based on the first to nth aggregate ranges, and determine the aggregate range containing the most title tag fields in the aggregate range list as the title tag range.

[0253] In some embodiments, for each text element in the element information list, the processor may further calculate a first intersection-union ratio (IUR) between the element extent of the text element and the frame extent of the frame; delete the text element from the element information list in response to the first IUR being greater than a third threshold; fill the element extent of the text element into the aggregation range list in response to the aggregation range list being empty; determine the union of each aggregation range in the aggregation range list with the element extent of the text element in response to the aggregation range list being non-empty, and calculate a second IUR between the union and the frame; fill the element extent of the text element into the aggregation range list in response to the second IUR being greater than a fourth threshold; replace the aggregation range with the union in response to the second IUR being less than or equal to the fourth threshold; and determine the tag range based on the number of occurrences of the tag field in at least one aggregation range in the aggregation range list.

[0254] The first intersection-to-union ratio (ICR) refers to the intersection-to-union ratio between the text primitive's extent and the bounding box's extent. The ICR can be represented numerically; the larger the value, the greater the overlap between the primitive's extent and the bounding box's extent.

[0255] In some embodiments, the processor may determine a first intersection-union ratio based on the size of the intersection and union between the primitive extent of the text primitive and the frame extent.

[0256] The third threshold is a threshold related to the first crossover ratio (CUP). For example, the third threshold can be any value between 0.1 and 0.2.

[0257] In some embodiments, the third threshold may be a system default value, an empirical value, a manually preset value, or any combination thereof, and can be set according to actual needs.

[0258] The second intersection-union ratio (IUU) is the intersection-union ratio between the union of the text primitive's primitive range and the aggregate range, and the bounding box range. The second IUU can be represented numerically; the larger the value, the greater the overlap between the union and the bounding box range.

[0259] In some embodiments, the processor may determine a second intersection-union ratio based on the union between the primitive extents and the aggregate extents of the text primitives, and the intersection and union sizes between the frame extents.

[0260] The fourth threshold is a threshold related to the second crossover ratio (CUP). For example, the fourth threshold can be any value between 0.1 and 0.4.

[0261] In some embodiments, the fourth threshold may be a system default value, an empirical value, a manually preset value, or any combination thereof, and can be set according to actual needs.

[0262] In some embodiments, the processor may determine the aggregate range in which the label field appears most frequently as the label range based on the number of times the label field appears in at least one aggregate range in the aggregate range list.

[0263] As an example only, for each text element in the element information list, the processor can calculate a first intersection-union ratio (IUR) between the element's extent and the frame's extent. If the first IUR is greater than a third threshold, the text element is removed from the element information list. If the first IUR is less than or equal to the third threshold, it is further determined whether the aggregation range list is empty. When the aggregation range list is empty (i.e., no aggregation range exists in the aggregation range list), the element's extent of the text element is added to the aggregation range list. When the aggregation range list is not empty (i.e., at least one aggregation range exists in the aggregation range list), the union of each aggregation range in the aggregation range list with the element's extent of the text element is determined, and a second IUR between the union and the frame is calculated. The relationship between the second IUR and a fourth threshold is determined. If the second IUR is greater than the fourth threshold, the element's extent of the text element is added to the aggregation range list. If the second IUR is less than or equal to the fourth threshold, the aggregation range is replaced with the union. Finally, the number of times the tag field appears in each aggregation range in the aggregation range list is calculated, and the aggregation range corresponding to the tag field with the most occurrences is determined as the tag range.

[0264] In some embodiments of this specification, at least one aggregation range is determined based on a first intersection-union ratio and a second intersection-union ratio, and then an aggregation range list is determined based on the aggregation range, thereby determining the tag range. This is beneficial for quickly eliminating text primitive ranges with excessive overlap, improving recognition efficiency, and reducing misjudgments.

[0265] In some embodiments of this specification, an aggregation range list is determined based on the aggregation of text elements in the element information list, thereby determining the tag range. This facilitates a more comprehensive identification of tag fields, a more accurate determination of the tag range, and simplifies the subsequent tag information extraction and parsing process.

[0266] Figure 14 is an exemplary flowchart illustrating the determination of the identification result of a target object in a drawing according to some embodiments of this specification. In some embodiments, the identification result includes target spatial information. In some embodiments, process 1400 may be executed by processor 120.

[0267] Step 1420: Perform icon recognition based on the icon frame to determine the initial spatial information.

[0268] Initial spatial information refers to unverified spatial information extracted from the target drawings. In some embodiments, the processor 120 may further process the initial spatial information to obtain more accurate and complete target spatial information. Here, spatial information refers to information / data describing the spatial ownership of buildings depicted in the drawings. For example, spatial information may indicate the specific floor and / or building of a building depicted in the drawings.

[0269] FIG. 17 is a partial schematic view of the border area of the target drawing shown in some embodiments of this specification.

[0270] In some embodiments, the spatial information may include information related to building keywords, floor keywords, building numbers, number of floors, etc. Among them, the building keywords and building numbers can be referred to as building information related to the building of the drawing; the floor keywords and number of floors can be referred to as floor information related to the floor of the drawing. For example, the title of the target drawing may include information related to building keywords, floor keywords, building numbers, number of floors, etc.

[0271] The building keyword refers to the identification information related to indicating the building in the target drawing. For example, referring to FIG. 17, the building keyword 1740 may include "building", etc. In some embodiments, the building keyword may further include other identification information that can indicate the building, such as "block", "building number" (such as "Building 1", "Building 2"), etc. In some embodiments, the processor 120 may determine whether the drawing label information is related to the building based on the building keyword. For example, when a certain drawing label information includes building keywords such as "building", "block", "building number", etc., the processor 120 may determine that the drawing label information is related to the building.

[0272] The floor keyword refers to the identification information related to indicating the floor in the target drawing. For example, referring to FIG. 17, the floor keyword 1750 may include "floor", etc. In some embodiments, the floor keyword may further include other identification information that can indicate the floor, such as "building", "F", etc. In some embodiments, the processor 120 may determine whether the drawing label information is related to the floor based on the floor keyword. For example, when a certain drawing label information includes floor keywords such as "floor", "building", "F", etc., the processor 120 may determine that the drawing label information is related to the floor.

[0273] The building number is data / information for distinguishing different buildings. In some embodiments, the building number includes numbers, connection symbols, custom buildings, etc.

[0274] The number of floors is data / information for distinguishing different floors. In some embodiments, the number of floors includes numbers, connection symbols, custom floors, prefixes, supplementary words, etc.

[0275] Numbers are used to indicate specific buildings and / or floors, including Arabic numerals (such as 1, 2, 3, etc.), Chinese numerals (such as one, two, three, etc.), Roman numerals, etc. As shown in FIG. 17, the numbers include the first number 1710 indicating a specific floor and the second number 1720 indicating a specific building, etc. For more descriptions of the first number and the second number, reference can be made to step 1440.

[0276] Connection symbols are used to connect multiple different pieces of information. As shown in Figure 17, the connection symbol 1730 can connect different building numbers and / or floor numbers, different digits, etc. Connection symbols include separator words (such as ",", ",", "and", "and" etc.) and continuous words (such as "-", "~", "to", "to" etc.). Among them, continuous words refer to words or symbols that connect multiple consecutive buildings (or floors).

[0277] A custom building is a word that indicates a non-standard description of a building. For example, custom buildings can include "basement, garage, gatehouse", etc.

[0278] A custom floor is a word that indicates a non-standard description of a floor. As shown in Figure 17, the custom floor 1760 can be the "equipment floor". In some embodiments, custom floors can also include types such as "roof, machine room floor, roof surface, top floor", etc.

[0279] Prefixes and supplementary words are used to explain and supplement some special floors. For example, prefixes such as "negative, -, B" etc. can represent underground floors; supplementary words such as "mezzanine, half floor, M" etc. can represent mezzanines, etc.

[0280] In some embodiments, the processor 120 can determine the initial spatial information in various ways. For example, the processor 120 can identify the drawing frame through technologies such as image recognition (e.g., optical character recognition, OCR), obtain the drawing label information such as the drawing name of the drawing frame, and extract building keywords, floor keywords, building numbers, floor numbers, etc. in the drawing label information as the initial spatial information. Another example is that the processor 120 can perform drawing label recognition on the drawing frame through methods such as machine vision technology and image recognition technology, and extract the initial spatial information.

[0281] Step 1420, compare the initial spatial information based on a preset spatial information database to obtain a comparison result.

[0282] A spatial information database refers to a database system used to store, manage, and retrieve the spatial information of drawings.

[0283] In some embodiments, the spatial information in the spatial information database can be obtained by collecting the spatial information of a large number of existing drawings and performing standardized processing.

[0284] Standardization processing refers to processing the spatial information related to buildings and floors in drawings based on preset rules. An exemplary preset rule may include: alternating different buildings and their corresponding floors. For example, the extracted spatial information related to buildings and floors in the drawings is arranged in the manner shown in formula (1): (α×n1+β×n2)×n3 (1) where α represents the standardized expression of building information, β represents the standardized expression of floor information, and n1, n2, and n3 represent the number of buildings, the number of floors, and the number of times building information and / or floor information appears, respectively. For example, “Building 1-3, Floors 1-3, Equipment Floor, and Building 5 and Building 7, Floors 2-5” can represent a standardized spatial information.

[0285] In some embodiments, the standardized expression of building information may include: (number|building keyword + connector) + (number|building keyword + connector) + ... + (number|building keyword + connector). For example, the standardized expression of building information may be: Buildings 1-3, 5, 7, and 9-10. The building keywords include custom building names such as "basement," "garage," and "gatekeeper."

[0286] In some embodiments, the standardized expression of floor information may include: (number|floor keyword + connector) + (number|floor keyword + connector) + ... + (number|floor keyword + connector). For example, the standardized expression of floor information may be: floors 1-3, 5, 7, 9, and equipment floors. Floor keywords include custom floor names such as "roof," "equipment floor," "machine room floor," "roof surface," and "top floor."

[0287] The above explanation of standardization processing is merely an example. Those skilled in the art can also set other standardization processing methods according to different needs of extracting spatial information from drawings. For example, a spatial information database may include various spatial information obtained after processing through different standardization methods.

[0288] In some embodiments, the processor 120 can match the initial spatial information of the target drawing with the spatial information in a spatial information database, and use the matching result as the comparison result. The matching method includes text matching, etc. For example, the processor 120 can match building keywords, floor keywords, building numbers, and floor numbers in the key information of the target drawing's frame with the spatial information in the spatial information database for comparison.

[0289] In some embodiments, the initial spatial information is compared based on a preset spatial information database, and the comparison results include multiple types. For example, when the floor keywords (including custom floors) and building keywords (including custom buildings) in the initial spatial information successfully match the floor keywords (including custom floors) and building keywords (including custom buildings) in the spatial database, the processor 120 can determine that the initial spatial information contains spatial information related to both floors and buildings, and this result is called the first comparison result; when the floor keywords (including custom floors) in the initial spatial information successfully match the floor keywords (including custom floors) in the spatial database, the processor 120 can determine that the initial spatial information contains spatial information related to floors, and this result is called the second comparison result; when the floor keywords (including custom floors) in the initial spatial information fail to match the floor keywords (including custom floors) in the spatial database, the processor 120 can determine that the initial spatial information does not contain spatial information related to floors, and further determine that the target drawing does not contain spatial information, and this result is called the third comparison result.

[0290] In some embodiments, when the comparison result satisfies the first comparison result, the processor 120 can determine the target spatial information of the target drawing by means of the method described in steps 1430-1440.

[0291] In some embodiments, when the comparison result satisfies the second comparison result, the processor 120 can determine that the title of the target drawing only includes floor information and does not include building information. The target floor information in the target spatial information can be obtained from the title, and the target building information can be obtained from the sub-item information. The processor 120 can determine the target spatial information of the target drawing by means of the method described in process 1500. For more details, please refer to Figure 15.

[0292] In some embodiments, when the comparison result meets the third comparison result, the processor 120 can determine that the target drawing does not contain spatial information and end the process.

[0293] Step 1430: Based on the comparison results, the initial spatial information is split to obtain spatial description information.

[0294] Spatial description information refers to data / information in the target drawings that describes buildings, floors, etc. In some embodiments, spatial description information includes building spatial description information describing buildings and floor spatial description information describing floors.

[0295] In some embodiments, when the comparison result meets the fifth preset condition, the processor 120 can split the initial spatial information to obtain multiple spatial information combinations; for each spatial information combination, the processor 120 can obtain floor spatial description information and building spatial description information based on a preset method.

[0296] The fifth preset condition may include the comparison result being the first comparison result. For more information about the first comparison result, please refer to step 1420.

[0297] Spatial information combination refers to the combination of building spatial description information and floor spatial description information obtained after splitting the initial spatial information. For example, processor 120 can split the initial spatial information "Building 1-3, Floors 1-3, Equipment Floor and Building 5 & 7, Floors 2-5" into spatial information combination 1: "Building 1-3, Floors 1-3, Equipment Floor" and spatial information combination 2: "Building 5 & 7, Floors 2-5".

[0298] In some embodiments, if a building keyword or custom building is preceded by a floor keyword or custom floor, the processor 120 can use the connecting symbol linking the building keyword or custom building and the preceding floor keyword or custom floor as a demarcation point to split the initial spatial information. Continuing with the aforementioned initial spatial information "Buildings 1-3, Floors 1-3, Equipment Floor and Buildings 5 ​​and 7, Floors 2-5", where the building keyword "Building 5" is preceded by the floor keyword "Floor" and the custom floor "Equipment Floor", the processor 120 can use the connecting symbol "and" as a demarcation point to split the initial spatial information into spatial information combination 1: "Buildings 1-3, Floors 1-3, Equipment Floor" and spatial information combination 2: "Buildings 5 ​​and 7, Floors 2-5".

[0299] In some embodiments, the preset method includes: extracting floor-related information based on spatial information combination to obtain floor spatial description information; and extracting building-related information based on spatial information combination to obtain building spatial description information.

[0300] In some embodiments, for each of the multiple spatial information combinations, extracting floor-related information includes: deleting the building keyword and the characters preceding it, and extracting the floor keyword and floor number from the remaining characters. For example, for spatial information combination 1: "Buildings 1-3, Floors 1-3, Equipment Floor", the processor 120 can delete the building keyword "Building" and the characters "1-3" preceding it, and extract the floor-related information "Floors 1-3, Equipment Floor" as floor spatial description information.

[0301] In some embodiments, for each of the multiple combinations of spatial information, extracting information related to the building includes: deleting the characters after the rightmost of the building keyword and the custom building, and extracting the building keyword and the building number from the remaining characters. For example, for the spatial information combination 1: "1 - 3 buildings, 1 - 3 floors, equipment floor", the processor 120 can delete the characters "1 - 3 floors, equipment floor" after the rightmost of the building keyword "building", and extract the information related to the building "1 - 3 buildings" as the building spatial description information.

[0302] Step 1440, based on the spatial description information, obtain the target spatial information of the target drawing.

[0303] The target spatial information refers to the spatial information corresponding to the building and the floor extracted from the target drawing. For example, for the initial spatial information "1 - 3 buildings, 1 - 3 floors, equipment floor and building plans of 2 - 5 floors of buildings 5 and 7", the corresponding target spatial information includes: "Building 1: Floor 1, Floor 2, Floor 3, Equipment Floor", "Building 2: Floor 1, Floor 2, Floor 3, Equipment Floor", "Building 3: Floor 1, Floor 2, Floor or", "Building 5: Floor 2, Floor 3, Floor 4, Floor 5", "Building 7: Floor 2, Floor 3, Floor 4, Floor 5", etc.

[0304] In some embodiments, for each of the multiple combinations of spatial information, the processor 120 can perform keyword extraction based on the floor spatial description information and the building spatial description information to obtain the target floor information and the target building information; combine the target floor information and the target building information to obtain the target spatial information of the target drawing.

[0305] In some embodiments, the processor 120 can extract the first number and the custom floor in the floor spatial description information; determine the first floor information based on the adjacent connecting words of the first number; determine the second floor information based on the consecutive words between the first numbers; determine the target floor information based on the first floor information and the second floor information, and use the custom floor as the supplementary floor information.

[0306] The first number refers to the number describing the specific floor number. Among them, the first number can include various forms of numbers, such as Arabic numerals (such as 1, 2, 3, etc.), Chinese numerals (such as one, two, three, etc.), Roman numerals, etc.

[0307] The adjacent connecting word refers to the word adjacent to the number (including the first number and the second number). In some embodiments, the adjacent connecting words of the first number include prefixes, supplementary words, floor keywords, etc. Taking the floor spatial description information "minus 2 floors", "underground 1 floor" as an example, the adjacent connecting words include "minus", "floor", "underground", "floor", etc. For more descriptions of prefixes, supplementary words and floor keywords, please refer to step 1410.

[0308] The first floor information refers to the floor information determined based on the first number and the adjacent connecting words of the first number.

[0309] In some embodiments, the processor 120 can process adjacent connectives of a first number and replace the first number to obtain first floor information. An exemplary processing method includes converting adjacent connectives into standardized prefixes and / or supplementary words and / or floor keywords, and combining the standardized prefixes and / or supplementary words and / or floor keywords with the first number to obtain the first floor information. For example, taking "basement 1", "-2F", "basement 1", "basement 1", etc. as examples, the processor 120 can convert adjacent connectives representing underground such as "negative", "-", "basement", "basement" etc., into standardized prefixes "-" (or other forms of prefixes as needed), convert floor keywords such as "layer", "floor", "F" etc., into standardized floor keywords "layer", and then combine the standardized prefixes "-" and standardized floor keywords "layer" with the corresponding first number to obtain the first floor information: "-1 floor", "-2 floor", "-1 floor", "-1 floor", etc. The standardized prefixes and / or supplementary words and / or floor keywords can be preset in advance.

[0310] In some embodiments, when the first number in the floor space description information does not have adjacent connecting words, the processor 120 can determine that the first floor information of the floor space description information is empty.

[0311] In some embodiments, the processor 120 may store the first floor information in a temporary floor database.

[0312] The second floor information refers to the floor information determined based on the first digit and the consecutive words between them. For more information on consecutive words, please refer to step 1410.

[0313] In some embodiments, when there are no consecutive words between the first digits, the processor 120 can directly determine the first digits and the floor keyword as the second floor information.

[0314] In some embodiments, when there are consecutive words between the first digits, the processor 120 can fill in the remaining digits between the floor numbers on both sides of the consecutive words, and use the filled-in result and the standardized floor keyword as the second floor information. For example, taking "floors 1 to 4" as an example, there is a consecutive word "to" between the first digits "1" and "4" indicating the continuity of floors. The processor 120 can fill in the digits "2" and "3" between the first digits "1" and "4", and combine the filled-in result with the standardized floor keyword "floor" as the second floor information: "floor 1", "floor 2", "floor 3", "floor 4".

[0315] In some embodiments, the processor 120 may store the second floor information in a temporary floor database.

[0316] In some embodiments, the processor 120 may merge the first floor information and the second floor information in the temporary floor database as the target floor information.

[0317] The supplementary floor information refers to the information for supplementing and explaining the target floor information. In some embodiments, the processor 120 may directly use the custom floor information as the supplementary floor information and store it in the temporary floor database.

[0318] In some embodiments, the processor 120 may also merge the supplementary floor information, the first floor information, and the second floor information as the target floor information.

[0319] In some embodiments, for each of the multiple combinations of spatial information, the processor 120 may also perform a duplicate removal process (i.e., remove duplicate floor information) on the target floor information in the spatial information combination in the temporary floor database to improve the accuracy of the subsequent obtained target spatial information.

[0320] In some embodiments, the processor 120 may extract the second number and the custom building in the building spatial description information; determine the first building information based on the adjacent connecting words of the second number; determine the second building information based on the consecutive words between the second numbers; determine the target building information based on the first building information and the second building information, and use the custom building as the supplementary floor information.

[0321] The second number refers to the number describing the specific building number. Among them, the second number may include various forms of numbers, such as natural numbers (such as 1, 2, 3, etc.), Chinese numerals (such as one, two, three, etc.), Roman numerals, etc.

[0322] In some embodiments, the adjacent connecting words of the second number include building keywords. Taking the building spatial description information "Building 3" and "Buildings 1 - 4" as examples, the adjacent connecting words include "Building", "Unit", etc. For more descriptions of building keywords, see step 220.

[0323] The first building information refers to the building information determined based on the second number and the adjacent connecting words of the second number.

[0324] In some embodiments, the processor 120 may process adjacent connecting words of the second number and obtain the first building information after replacement. Exemplary processing methods include converting the adjacent connecting words into standardized building keywords and combining the standardized building keywords with the second number to obtain the first building information. For example, taking "Building 3", "Buildings 1 - 4", "Building No. 7", etc. as examples, the processor 120 may convert adjacent connecting words such as different building keywords "building", "block", "building number", etc. into the standardized building keyword "building" (it may also be converted into other forms of building keywords according to needs), and then combine the standardized building keyword "building" with the corresponding second number to obtain the first building information: "Building 3", "Buildings 1 - 4", "Building 7", etc. The standardized building keyword may be preset in advance.

[0325] In some embodiments, the processor 120 may store the first building information in a temporary floor database.

[0326] The second building information refers to the building information determined based on the second number and the continuous words between the second numbers. For more descriptions of the continuous words, refer to step 1410.

[0327] In some embodiments, when there are no continuous words between the second numbers, the processor 120 may directly determine the second number and the building keyword as the second building information.

[0328] In some embodiments, when there are continuous words between the second numbers, the processor 120 may fill in the remaining numbers between the building numbers on both sides of the continuous words and use the filled result and the standardized building keyword as the second building information. For example, taking "Building 1 to 4" as an example, there is a continuous word "to" indicating the continuous situation of the buildings between the second numbers "1" and "4". The processor 120 may fill in the numbers "2" and "3" between the second numbers "1" and "4", and combine the filled result with the standardized building keyword "building" as the second building information: "Building 1", "Building 2", "Building 3", "Building 4".

[0329] In some embodiments, the processor 120 may store the second building information in a temporary building database.

[0330] In some embodiments, the processor 120 may merge the first building information and the second building information in the temporary building database as the target building information.

[0331] The supplementary building information refers to the information for supplementing and explaining the target building information. In some embodiments, the processor 120 may directly use the custom building information as the supplementary building information and store it in the temporary building database.

[0332] In some embodiments, the processor 120 may also merge the supplementary building information with the first building information and the second building information to obtain the target building information.

[0333] In some embodiments, for each of the multiple spatial information combinations, the processor 120 may also perform deduplication processing (i.e., remove duplicate building information) on the target building information in the temporary building database of the spatial information combination to improve the accuracy of the target spatial information subsequently acquired.

[0334] In some embodiments, for each of the multiple spatial information combinations, the processor 120 can combine the target floor information and target building information in the spatial information combination to obtain the target spatial information of the spatial information combination. For example, the target floor information of a certain spatial information combination includes "1st floor", "2nd floor", and "equipment floor", and the target building information includes "Building 1", "Building 2", and "Building 3". The processor 120 can combine each of the target floor information with each of the target building information, and then merge the combination results of the same building to obtain the target spatial information of the spatial information combination: "Building 1: 1st floor, 2nd floor, equipment floor", "Building 2: 1st floor, 2nd floor, equipment floor", "Building 3: 1st floor, 2nd floor, equipment floor".

[0335] In some embodiments, for each of the multiple spatial information combinations of the target drawing, the processor 120 may execute the method described in step 1440 (e.g., execute simultaneously or individually) to obtain the target spatial information of each spatial information combination, and then merge the target spatial information of each spatial information combination as the target spatial information of the target drawing.

[0336] The drawing spatial information extraction method described in some embodiments of this specification can intelligently and automatically identify spatial information in drawings with high accuracy and versatility. It can also accurately identify custom floor / building information. At the same time, it can accurately identify and convert spatial information in drawings even when the text description is not standardized (e.g., there are multiple building / floor keywords), making it easier to query and manage the spatial information. In addition, it can accurately supplement and identify spatial information that is implicit in the drawing text and not directly stated (e.g., for continuous floor information 1 to 4, where floors 2 and 3 are implicit spatial information), further improving the effectiveness of drawing spatial information management.

[0337] Figure 15 is an exemplary flowchart illustrating the determination of target spatial information according to other embodiments of this specification. In some embodiments, when the comparison result meets a fifth preset condition, the processor 120 can execute process 1500 to determine the target spatial information of the target drawing. That is, after executing step 1420, the processor 120 can determine whether the comparison result meets the fifth preset condition, and execute step 1500 when the comparison result meets the fifth preset condition. The fifth preset condition includes the comparison result meeting a second comparison result. Further explanation of the second comparison result can be found in step 1420.

[0338] In some embodiments, process 1500 may be executed by a processor (e.g., processor 120). As shown in FIG15, process 1500 includes the following steps.

[0339] Step 1510: Decompose the initial spatial information to obtain floor space description information.

[0340] In some embodiments, the processor 120 can decompose the initial spatial information using the same method as in step 1430 to obtain floor space description information. For a detailed explanation of the relevant content, please refer to step 1430.

[0341] Step 1520: Extract keywords based on floor space description information to obtain target floor information.

[0342] In some embodiments, the processor 120 can extract keywords from the floor space description information using the same method as in step 1440 to obtain the target floor information. For a detailed explanation of the relevant content, please refer to step 1440.

[0343] Step 1530: Obtain the sub-item information of the frame, and obtain the sub-item spatial information based on the sub-item information.

[0344] Sub-item information refers to the names of sub-items in the drawing. A sub-item refers to a next-level sub-item or sub-project within the drawing.

[0345] Sub-item spatial information refers to information such as building keywords and building numbers in the sub-item name.

[0346] In some embodiments, the processor 120 can determine the sub-item spatial information using the same method as extracting the initial spatial information. For example, the processor 120 can identify the frame using image recognition (e.g., OCR technology), obtain the sub-item names of the frame, and extract building keywords, building numbers, etc., from the sub-item names as sub-item spatial information using methods such as regular expression matching. Alternatively, the processor 120 can perform image tag recognition on the frame using machine vision technology, image recognition technology, etc., and extract the sub-item spatial information.

[0347] In some embodiments, the processor 120 may also compare the sub-item space information based on a preset spatial information database.

[0348] In some embodiments, when the comparison result indicates that the sub-item space information matches the building keyword (including custom buildings) in the spatial information database, it means that the sub-item space information includes building spatial information, and the processor 120 continues to execute steps 1540 - 1560 to determine the target spatial information of the target drawing.

[0349] In some embodiments, when the comparison result indicates that the sub-item space information does not match the building keyword (including custom buildings) in the spatial information database, it means that the sub-item space information does not include building spatial information, and the processor 120 ends the process.

[0350] Step 1540: Split the sub-item space information to obtain building spatial description information.

[0351] In some embodiments, the processor 120 may split the sub-item space information by using custom buildings and / or building keywords and / or delimiters. For example, for the sub-item space information "Buildings 1 - 3, Buildings 7 and 8", the processor may split the sub-item space information based on the delimiter "," and the building keyword "building" to obtain the building spatial information: "Buildings 1 - 3", "Building 7", "Building 8". For more descriptions of the building spatial description information, refer to step 1430.

[0352] Step 15 fifty: Extract keywords based on the building spatial description information to obtain target building information.

[0353] In some embodiments, the processor 120 may extract keywords from the building spatial description information in the same way as in step 1440 to obtain target building information. For a detailed description of the relevant content, refer to step 1440.

[0354] Step 1560: Combine the target floor information and the target building information to obtain the target spatial information of the drawing.

[0355] In some embodiments, the processor 120 may combine the target floor information and the target building information in the same way as in step 1440 to obtain the target spatial information of the target drawing. For a detailed description of the relevant content, refer to step 1440.

[0356] In some embodiments, to further improve the accuracy of the extracted target spatial information, the processor 120 can also verify the extracted target spatial information. For example, the processor 120 can compare the extracted target spatial information with the spatial information in the spatial information database. If the comparison results are consistent, the extracted target spatial information is considered to be accurate, and the target spatial information corresponding to the target drawing (i.e., the building and floor information associated with the drawing) is obtained. If they are inconsistent, the target spatial information is considered to be incorrect and needs to be modified or further verified (such as manual verification or modification).

[0357] In some embodiments, the processor 120 may also verify the target spatial information based on the target drawing.

[0358] Figure 16 is an exemplary flowchart illustrating the verification of target spatial information based on a target drawing according to some embodiments of this specification. In some embodiments, process 1600 may be executed by a processor (e.g., processor 120). As shown in Figure 16, process 1600 includes the following steps.

[0359] Step 1610: Perform image segmentation based on the target drawing to obtain drawings of one or more building areas.

[0360] Building area drawings refer to drawings obtained by dividing different buildings in the target drawing into one or more individual buildings.

[0361] In some embodiments, the processor 120 can perform image segmentation on the target drawing based on various image segmentation methods. Exemplary image segmentation methods include grayscale thresholding, region segmentation, edge segmentation, etc.

[0362] Step 1620: Determine auxiliary building information based on one or more building area drawings.

[0363] The auxiliary building information is the building information extracted from the building area drawings.

[0364] In some embodiments, the processor 120 may determine the building information based on the building information marked in the building area drawing.

[0365] Step 1630: For each of one or more building area drawings, perform floor identification based on the building area drawings to determine auxiliary floor information.

[0366] Auxiliary floor information refers to floor information extracted from each building in one or more building area drawings.

[0367] In some embodiments, the processor 120 can extract the floor information marked in the drawings of each building area using image recognition technology (such as machine vision, OCR technology, etc.) and use the extracted floor information as auxiliary floor information.

[0368] In some embodiments, the processor 120 may also determine auxiliary floor information through a machine learning model.

[0369] In some embodiments, the processor 120 can input building area drawings into a convolutional neural network to obtain convolutional feature vectors; perform enhancement processing on the convolutional feature vectors to obtain enhanced feature vectors; and input the enhanced feature vectors into a floor recognition model to determine auxiliary floor information.

[0370] In some embodiments, the convolutional neural network can be trained using a first sample and a first label. The first sample includes a large number of historical building area maps, and the first label includes floor information from the manually annotated historical building area maps. After the convolutional neural network is trained, the processor 120 can select the feature vector output from the previous layer of the convolutional neural network's output layer as the convolutional feature vector.

[0371] In some embodiments, the processor 120 can also extract annotation information based on building area drawings to obtain drawing annotation information; extract features from the drawing annotation information to obtain annotation feature vectors; and fuse the annotation feature vectors and convolutional feature vectors to obtain enhanced feature vectors.

[0372] The information marked on the drawings refers to the floor information marked on the building area drawings.

[0373] In some embodiments, the processor 120 can extract the floor information marked in the drawings of each building area using image recognition technology (such as machine vision, OCR technology, etc.) and use the extracted floor information as the drawing annotation information.

[0374] In some embodiments, the processor 120 can also acquire a preset annotation area of ​​the target drawing; and extract drawing annotation information from the preset annotation area. The preset annotation area is determined based on the annotation habits of the user who drew the target drawing.

[0375] The preset annotation area refers to the area in the building area drawing that is preset to be used to annotate floor information.

[0376] Labeling habits refer to the habits users have when labeling spatial information such as buildings and floors when drawing drawings. For example, labeling habits may include commonly used numbers (such as Arabic numerals, Roman numerals, etc.), the habit of labeling a single floor, or the habit of labeling multiple floors uniformly. In some embodiments, the user's labeling habits may be pre-stored in a storage device (such as storage device 150) in the form of vectors, and the processor 120 may retrieve the labeling habits from the storage device based on the drawing user's name in the title block information.

[0377] In some embodiments of this specification, a preset annotation area of ​​the target drawing is determined according to the annotation habits of the drawing user corresponding to the target drawing, and the drawing annotation information is extracted from the preset annotation area. This can better fit the drawing habits of different users when extracting annotation information, improve the accuracy of the subsequently determined auxiliary floor information, and improve the intelligence level of the target spatial information verification process.

[0378] In some embodiments, the processor 120 can also extract features from the drawing annotation information using methods such as text structure features, grammatical features, and word embedding to obtain annotation feature vectors.

[0379] In some embodiments, the processor 120 can fuse the labeled feature vector and the convolutional feature vector in various ways. For example, the processor 120 can concatenate the labeled feature vector and the convolutional feature vector to obtain an enhanced feature vector; or, for another example, the processor 120 can perform a weighted summation of the labeled feature vector and the convolutional feature vector to obtain an enhanced feature vector, wherein the weights of the weighted summation can be preset.

[0380] In some embodiments, by fusing the annotation feature vectors corresponding to the annotation information of the building area drawings with the convolutional feature vectors, an enhanced feature vector is obtained, which can incorporate the annotation information of the drawings and improve the accuracy of the auxiliary floor information subsequently determined by the model.

[0381] A floor identification model is a machine learning model used to determine auxiliary floor information in building area drawings. In some embodiments, the floor identification model can be a neural network model, a deep neural network model, etc.

[0382] In some embodiments, the input to the floor recognition model includes an enhanced feature vector, and the output includes auxiliary floor information.

[0383] In some embodiments, the input to the floor identification model also includes the annotation habits and annotation parsing annotations of the user who drew the target drawing. The annotation parsing annotations refer to the interpretation of the annotation habits of the user who drew the target drawing. For example, for the annotation "2nd floor", the annotation parsing annotation includes an explanation of whether the user's annotation refers to "the 2nd floor" or "the 1st and 2nd floors".

[0384] In some embodiments of this specification, the input to the floor recognition model also includes the annotation habits and annotation analysis notes of the user who drew the target drawing, which can improve the accuracy of the output auxiliary floor information and make the output results closer to the annotation habits of different drawing users, making it more intelligent.

[0385] In some embodiments, the floor identification model can be trained using a second sample and a second label. The second sample includes historical enhanced feature vectors corresponding to a large number of historical building area drawings, and the second label includes floor information from manually annotated historical building area drawings. Wherein, when a large number of historical building area drawings in the second sample are identical to a large number of historical building area drawings in the first sample, the first label and the second label can be the same.

[0386] In some embodiments, a convolutional neural network may be part of a floor recognition model.

[0387] In some embodiments of this specification, auxiliary floor information is determined by machine learning models, which is more accurate and intelligent, and can improve the accuracy and efficiency of the verification of target spatial information.

[0388] Step 1640: Combine the auxiliary building information and auxiliary floor information to obtain auxiliary space information.

[0389] Auxiliary spatial information refers to spatial information determined based on building area drawings.

[0390] In some embodiments, the processor 120 can determine auxiliary spatial information based on a method similar to that used to determine the target spatial information. For example, for each of one or more building area drawings, the processor 120 can combine the auxiliary building information and auxiliary floor information in the building area drawing to obtain the auxiliary spatial information of the building area drawing. For example, if the auxiliary floor information of a building area drawing includes "1st floor", "2nd floor", and "equipment floor", and the auxiliary building information includes "Building 1" and "Building 2", the processor 120 can combine each of the auxiliary floor information with each of the auxiliary building information, and then merge the combination results of the same buildings to obtain the auxiliary spatial information of the building area drawing: "Building 1: 1st floor, 2nd floor, equipment floor" and "Building 2: 1st floor, 2nd floor, equipment floor".

[0391] In some embodiments, for each of one or more building area drawings, the processor 120 may execute the method described in steps 1620-1640 (e.g., simultaneously or individually) to obtain auxiliary spatial information of each building area drawing, and then merge the auxiliary spatial information of each building area drawing as the auxiliary spatial information of the target drawing.

[0392] Step 1650: Determine whether the auxiliary spatial information and the target spatial information are consistent.

[0393] In some embodiments, the processor 120 can determine whether the auxiliary spatial information and the target spatial information are consistent in various ways. For example, the processor 120 can directly compare whether the auxiliary spatial information and the target spatial information are consistent; or, for another example, the processor 120 can calculate the vector distance between the auxiliary spatial information and the target spatial information. When the vector distance is less than a distance threshold, it indicates that the auxiliary spatial information and the target spatial information are consistent; otherwise, they are inconsistent. Exemplary vector distances include one or more of Euclidean distance, cosine distance, Manhattan distance, Chebyshev distance, etc.

[0394] In some embodiments, when the auxiliary spatial information and the target spatial information are consistent, it indicates that the target spatial information has been extracted correctly, and the processor 120 ends the process.

[0395] In some embodiments, when the auxiliary spatial information and the target spatial information are inconsistent, it indicates that there may be an error in the extraction of the target spatial information, and the processor 120 executes step 1660.

[0396] Step 1660: In response to the inconsistency between the auxiliary space information and the target space information, output a prompt message.

[0397] The prompt message is used to remind the user to verify the target space information. For example, the prompt message may include a pop-up reminder, a highlighted reminder, etc.

[0398] In some embodiments, the prompt information may also include specific verification details. For example, the specific building or floor of the target spatial information that is inconsistent with the auxiliary spatial information.

[0399] In some embodiments, the user can manually verify the target spatial information that is inconsistent with the auxiliary spatial information. In some embodiments, the processor 120 can also repeat one or more of processes 1400, 1500, and 1600 to automatically verify the target spatial information. For example, it can compare whether the target spatial information obtained after repeated execution is consistent with the auxiliary spatial information or the target spatial information obtained before repeated execution.

[0400] In some embodiments of this specification, verifying the target spatial information based on the target drawing can improve the accuracy of target spatial information identification. Simultaneously, it can promptly prompt the user when the extracted target spatial information is inconsistent with the auxiliary spatial information, allowing for further verification and further improving the accuracy of target spatial information identification. Furthermore, compared to directly comparing with spatial information in a spatial information database, the auxiliary spatial information of the target drawing is specific to the same drawing, making the comparison more accurate and enabling faster comparison results.

[0401] Figure 18 is an exemplary flowchart illustrating the assignment of construction tasks according to some embodiments of this specification. In some embodiments, the identification result includes a wall, and the processor 120 can assign construction tasks based on the method shown in flowchart 1800. In some embodiments, flowchart 1800 can be executed by the processor 120.

[0402] Step 1810: Obtain the construction task sheet corresponding to the wall surface.

[0403] In some embodiments, the identification result includes walls, and the processor 120 can identify the walls within the target construction area from the construction plan of the target construction area.

[0404] The target construction area refers to the area where wall work needs to be assigned. For example, the target construction area may include multiple floors. Alternatively, it may include only one floor. Or, it may include a specific area within a single floor.

[0405] In some embodiments, since it is necessary to distinguish between exterior and interior walls later, but the underground area is buried in the soil and there is no distinction between exterior and interior walls, the target construction area only includes the above-ground area.

[0406] A construction plan is a drawing used to guide the execution of construction tasks in a target construction area. For example, a construction plan can be a two-dimensional drawing used to represent the spatial layout and functional division of a building corresponding to the target construction area on a horizontal cross-section. For instance, a construction plan can show information such as the spatial layout, room areas, wall structures, and door and window arrangements on a specific floor of the target construction area. A construction plan is a type of drawing. For example, drawing 110 may include a construction plan.

[0407] In some embodiments, a construction floor plan may include graphic elements (e.g., wall elements, door elements, window elements, etc.), text elements, etc. Here, a graphic element refers to a basic drawing element in the construction floor plan. For example, graphic elements may include, but are not limited to, straight line elements, curved line elements, polyline elements, block elements, text elements, etc. For example, as shown in FIG19, room area 1910 may include wall element 1920, door element 1930, and window element 1940.

[0408] In some embodiments, since it is necessary to distinguish between exterior and interior walls later, but non-plan views usually do not distinguish between interior and exterior walls (e.g., detailed views are only partial views and do not distinguish between interior and exterior walls), a construction plan view needs to be selected. Furthermore, since the target construction area only includes the above-ground area, an above-ground construction plan view needs to be selected.

[0409] A wall refers to a structural component within the target construction area that serves functions such as dividing space, bearing load, enclosure, insulation, and soundproofing. A wall surface refers to the outer surface of a wall. It should be noted that each wall has two surfaces, meaning each wall comprises two wall surfaces, which must be considered separately.

[0410] In some embodiments, the wall surface may include an interior wall facing inwards and an exterior wall facing outwards.

[0411] Interior walls refer to the walls facing the interior area.

[0412] Exterior walls refer to walls facing the outdoors. Outdoor areas may include open platforms, corridors, terraces, elevated areas, roofs, and other spaces.

[0413] It should be noted that when a wall is an exterior wall, one side faces outwards (i.e., the exterior wall surface) and the other side faces inwards (i.e., the interior wall surface). The construction methods for the interior and exterior walls are different, and they need to be considered separately when assigning tasks. Therefore, by identifying the interior and exterior walls, they can be used as different basic units for task assignment.

[0414] In some embodiments, the processor can identify wall elements, door elements, and window elements in a construction floor plan. For example, the processor can first identify and parse the title fields of multiple construction drawings to determine the type of each drawing; if the drawing belongs to the profession of "architecture" and the drawing name contains keywords such as "floor plan", then the drawing is identified as a construction floor plan; then, layers containing keywords such as "WALL" or "wall" in their names are selected from the layers of the construction floor plan, and line segments, arcs, and other elements in these layers are extracted as wall elements; layers containing keywords such as "door" or "DOOR" in their names are selected, and line segments, arcs, and other elements in these layers are extracted as door elements; layers containing keywords such as "window" or "WINDOW" in their names are selected, and line segments, arcs, and other elements in these layers are extracted as window elements.

[0415] The processor can further identify room areas in the construction plan based on wall, door, and window elements. For example, the processor can obtain the endpoint coordinates of each element and determine whether there is a connection between the elements based on the spatial distance between them. If the distance between the endpoint coordinates of one element and the endpoint coordinates of another element is less than or equal to a spacing threshold, the two elements are considered to be connected. When the endpoints of multiple elements are connected and form a closed area, this closed area can be identified as a room area. The spacing threshold can be set by the user (such as project managers) based on actual engineering experience. For example, the spacing threshold can be 200mm. As another example, the processor can recursively traverse the endpoint coordinates of adjacent elements starting from any element, and determine whether the traversal path can return to the starting element. If the traversal path forms a closed path without breaks, the path can form a closed area, thus identifying a room area. It should be noted that if the distance between the endpoints of adjacent elements in the path is less than or equal to the spacing threshold, it is considered to be a continuous connection and form a path without breaks.

[0416] The processor can further determine the walls based on the boundaries of the room area, and define the walls facing the interior space of the room area as interior walls and the walls facing the exterior space of the room area as exterior walls.

[0417] In some embodiments of this specification, based on the connection relationship between wall elements, door elements, and window elements, the room area in the construction plan can be automatically derived, thereby identifying the interior and exterior walls. This does not require relying on the area boundaries explicitly marked in the construction drawings, and can be adapted to drawings of different design styles. It has stronger versatility and adaptability, and provides support for the subsequent assignment of construction tasks in the wall dimension.

[0418] In some embodiments, the processor can determine multiple outdoor grids and multiple indoor grids in the construction plan; starting from at least one of the multiple indoor grids, it moves to its adjacent indoor grids until it determines the target indoor grid corresponding to the spatial barrier element; starting from at least one of the multiple outdoor grids, it moves to its adjacent outdoor grids until it determines the target outdoor grid corresponding to the spatial barrier element; and, based on the target indoor grids and target outdoor grids, it identifies the interior and exterior wall surfaces within the target construction area from the construction plan. Specifically, the processor can identify the interior and exterior wall surfaces within the target construction area from the construction plan based on steps S1-S4.

[0419] Step S1: Determine multiple outdoor grids and multiple indoor grids in the construction plan.

[0420] Outdoor grid refers to the grid corresponding to the outdoor area. Indoor grid refers to the grid corresponding to the indoor area.

[0421] In some embodiments, the processor can first perform a rough division of areas on the construction plan to determine approximate indoor and outdoor areas. For example, the processor can identify straight lines on the construction plan, find the area enclosed by the straight lines, identify that area as an indoor area, and identify the other areas as outdoor areas. Alternatively, the processor can identify keywords related to outdoor areas, identify the areas corresponding to these keywords as outdoor areas, and identify the other areas as indoor areas. Keywords for outdoor areas include open platforms, corridors, terraces, elevated areas, and roofs. It should be noted that this is a rough division, and the accuracy is relatively low.

[0422] The processor can perform mesh generation for indoor and outdoor areas separately. Mesh generation refers to dividing the indoor and outdoor areas into simple, regular micro-units (e.g., triangles, quadrilaterals, squares, hexagons, etc.). The collection of these micro-units is called a "mesh." The side lengths of the micro-units can be the same or different. For ease of explanation, the following description uses a square as an example of a micro-unit.

[0423] In some embodiments, the size of the outdoor grid is larger than that of the indoor grid. For example, the outdoor grid can be a square with a side length of 200mm, and the indoor grid can be a square with a side length of 50mm. Understandably, if the grid size is set too large, the accuracy will be too low; if the grid size is set too small, the computational efficiency will be too low. Since the width of a door is typically over 600mm, choosing a square with a side length of 200mm for the outdoor grid ensures that no indoor-outdoor connection methods with similar doorway widths are missed. Because the indoor area is usually smaller than the outdoor area, and there are more walls inside, the size of the indoor grid needs to be set smaller to ensure accuracy.

[0424] In some embodiments, the size of the indoor grid is determined based on the area of ​​the indoor region. For example, the processor can first determine the size of the indoor region, and when the indoor region is relatively small, we can set a smaller size for the indoor grid to ensure that a sufficient number of grids are created.

[0425] In some embodiments, the size of the outdoor grid can be preset.

[0426] Step S2: Starting from at least one of the multiple indoor grids, walk towards its adjacent indoor grids until the target indoor grid corresponding to the spatial barrier element is determined.

[0427] Spatial barrier elements are elements that serve to block space. For example, spatial elements can include walls, doors, windows, etc.

[0428] The target indoor grid refers to the grid corresponding to the spatial barrier element within the indoor grid. For example, as shown in Figure 19, the black grid 5 is the target indoor grid corresponding to the wall.

[0429] In some embodiments, the processor can select a starting point to begin the spread, processing only the unspread grids at each spread stage. The starting point refers to any one of the multiple indoor grids. When the starting point cannot be spread (e.g., there are two unconnected buildings, A and B, in the target construction area, making it impossible to spread from building A to building B), another unspread starting point is selected from the multiple indoor grids to begin the spread, continuing until all indoor grids in the multiple indoor grids have been spread, thus identifying the target indoor grids corresponding to all spatial barrier elements. This method is computationally efficient. For example, as shown in Figure 19, starting from grid 1, the spread extends to the four grids 2 above, below, left, and right of grid 1. No spatial barrier elements are identified in these four grids. Continuing with the four grids 2 as starting points, excluding previously visited grids, the spread extends to eight grids 3. No spatial barrier elements are identified in these eight grids… When the spread reaches 15 grids 5, the black-background grid 5 is identified as the target indoor grid corresponding to a spatial barrier element… until all target indoor grids corresponding to spatial barrier elements are identified.

[0430] In some embodiments, the processor can propagate independently, starting from each of the multiple indoor grids. More information on propagation methods can be found above and in their respective descriptions.

[0431] Step S3: Starting from at least one of the multiple outdoor grids, walk towards its adjacent outdoor grids until the target outdoor grid corresponding to the spatial barrier element is determined.

[0432] The target outdoor grid refers to the grid corresponding to the spatial barrier element in the outdoor grid.

[0433] The process of determining the target outdoor grid corresponding to the spatial barrier element (i.e., step S3) is similar to the process of determining the target indoor grid corresponding to the spatial barrier element (i.e., step S2), and you can refer to step S2 and its corresponding description.

[0434] It should be noted that in the process of determining the target outdoor grid corresponding to the spatial barrier element, the starting point can be selected from the four corner points of the construction plan or the grid where the keyword corresponding to the outdoor area identified in the construction plan is located.

[0435] Step S4: Based on the target indoor grid and the target outdoor grid, identify the interior and exterior wall surfaces within the target construction area from the construction plan.

[0436] In some embodiments, the processor can determine the walls in the drawings based on the target indoor grid and the target outdoor grid. The overlapping area of ​​the target indoor grid and the target outdoor grid is the area where the walls separating the indoor and outdoor areas are located. The non-overlapping area of ​​the target indoor grid is the area where the walls separating different rooms within the interior are located. For example, the processor can combine line elements or rectangular elements in the construction plan and use the line elements or rectangular elements located in the overlapping area of ​​the target indoor grid and the target outdoor grid as wall elements. As another example, the processor can combine line elements or rectangular elements in the construction plan and use the line elements or rectangular elements in the non-overlapping area of ​​the target indoor grid as wall elements. Once the wall elements are determined, the processor can designate the side of the wall element facing the outdoor area as the exterior wall and the side of the wall element facing the indoor area as the interior wall.

[0437] In some embodiments of this specification, the mesh propagation method can accurately determine the interior and exterior wall surfaces. Furthermore, by making the outdoor mesh larger than the indoor mesh, and by determining the size of the indoor mesh based on the area of ​​the indoor region, both accuracy and computational efficiency are balanced.

[0438] It should be noted that, considering the need to calculate the distance between walls during later task allocation, inaccurate distance calculations will occur if the length differences between walls are too large. Therefore, excessively long walls need to be split into walls with lengths not exceeding a preset threshold, and correspondingly, wall segments are also split. The preset threshold can be a pre-defined length threshold. For example, the processor can treat a wall shorter than the preset length of 3m as a single wall, and split walls longer than the preset length of 3m. For instance, a 9m wall can be split into 3 segments of 3m+3m+3m; a 10m wall can be split into 4 segments of 3m+3m+3m+1m. Splitting walls longer than the preset length prevents distance distortion. For example, directly calculating the distance between a 100m wall and a 1m wall would be inaccurate. Splitting the 100m wall into 200 wall segments and calculating the distance between each wall segment and the 1m wall is more accurate.

[0439] A construction task sheet is a document issued by the project department to construction workers as work instructions during the construction process.

[0440] In some embodiments, a construction task order may include construction task information and construction personnel information corresponding to the target construction period.

[0441] The target construction period refers to the time frame during which the construction task needs to be completed. For example, the target construction period can be any time frame such as one day, one week, or one month.

[0442] Construction personnel information refers to the information associated with personnel assigned to wall painting tasks within the target construction period. For example, construction personnel information may include the number of construction personnel, their user IDs, the construction tasks each person is responsible for, and the area that can be worked on per unit time. The user ID is a unique code for each construction worker. It can be a worker's identification (ID) and can be a combination of letters, numbers, and symbols. The area that can be worked on per unit time may include N square meters of waterproofing per day, M square meters of latex paint per day, etc.

[0443] In some embodiments, a construction task order may include pre-defined construction personnel information.

[0444] In other embodiments, the processor can dynamically allocate construction personnel information based on the overall construction task and the amount of work already completed in the target construction area at the current construction stage. For example, the construction task is to paint 1000 square meters of walls on one floor, which is expected to take 10 days to complete. Each construction worker can paint 10 square meters per day. At the start of the task, the plan is to paint 100 square meters per day, requiring 10 construction workers. However, the actual situation may vary. After 5 days of painting, theoretically 500 square meters should have been painted, leaving 500 square meters to be painted. But in reality, 800 square meters remain to be painted. Therefore, the plan is revised to paint 160 square meters per day, requiring 16 construction workers. It should be noted that the above method uses a linear algorithm to determine the construction personnel information. Other algorithms can also be used to determine the construction personnel information. For example, painting can be faster in the first few days and slower in the later days, and the allocation is not even.

[0445] In some embodiments, since the wall surface can be divided into exterior and interior walls, the task types and construction personnel for the exterior and interior walls are different, and each will have its own corresponding construction task order. Therefore, the construction task order may include a first construction task order for the interior walls and a second construction task order for the exterior walls. The assignment of tasks for the interior walls is based on the first construction task order, and the assignment of tasks for the exterior walls is based on the second construction task order.

[0446] Step 1820: Based on the construction task information and the historical construction data of the wall, determine the target wall to be constructed during the target construction period and the construction task item corresponding to each target wall from the walls in the target construction area.

[0447] Historical construction data refers to wall construction data up to the current moment.

[0448] The target wall surface refers to the wall surface that needs to be constructed during the target construction period.

[0449] The construction task item corresponding to each target wall surface refers to the construction task item determined on a unit basis for each target wall surface. For more information on construction task items, please refer to the above text and its corresponding description.

[0450] In some embodiments, based on construction task information and historical construction data of the walls, and with reference to task allocation rules, it is determined which walls need to be constructed during the target construction period, designating them as target walls, and identifying the corresponding construction task items for each target wall. The construction task information broadly defines what work needs to be done on the walls in the target construction area. The historical construction information of the walls can be used to determine the current construction progress of the walls in the target construction area.

[0451] Task allocation rules specify the construction tasks required for different types of rooms and different types of walls, as well as the order in which these tasks must be performed. For example, waterproofing is suitable for interior bathroom walls. Similarly, installing exterior glass curtain walls is suitable for exterior walls. And tiling requires waterproofing as a prerequisite. Understandably, some tasks are unrelated to the wall's location, such as cleaning the floor of the room where the wall is located. Other tasks are related to the wall's location; for example, if wall A is adjacent to wall B, and wall B is an interior bathroom wall, then wall A must be waterproofed before latex paint can be applied.

[0452] For example, for each wall in the target construction area, the processor can predict the construction tasks that need to be performed on that wall during the target construction period based on task allocation rules, current construction progress, wall type, and the room where the wall is located. If the aforementioned construction tasks are included in the construction task list, then that wall is the target wall, and the aforementioned construction tasks are the construction tasks corresponding to that target wall.

[0453] Step 1830: Based on the construction personnel information and the construction task items corresponding to each target wall, determine the target construction personnel and the target walls and their construction task items assigned to each target construction personnel within the target construction period.

[0454] The target construction personnel refers to the construction personnel actually assigned to the construction tasks corresponding to the target wall surface. The target construction personnel may include all construction personnel or a portion of them.

[0455] The target wall surface and its construction tasks for the target construction personnel refer to the target wall surface that the target construction personnel need to handle, and the corresponding construction tasks for that target wall surface.

[0456] In some embodiments, the processor can determine the target construction personnel and the target wall surface and construction tasks for each target construction personnel through the process shown in Figure 20. More details regarding the determination of the target construction personnel and the target wall surface and construction tasks for each target construction personnel can be found in Figure 20 and its corresponding description.

[0457] In some embodiments of this specification, by determining the target construction personnel and the target wall surfaces and their construction tasks assigned to each target construction personnel within the target construction period, automatic allocation of construction tasks corresponding to the target wall surfaces is achieved, improving allocation efficiency. Furthermore, the allocation unit is detailed down to specific wall surfaces and distinguishes between interior and exterior wall surfaces, making the allocation more accurate.

[0458] It should be noted that the above description of the wall task assignment process is merely for illustration and explanation, and does not limit the scope of the invention. Those skilled in the art can make various modifications and changes to the wall task assignment process under the guidance of this invention. However, these modifications and changes are still within the scope of this invention. For example, the order of steps S2 and S3 can be interchanged.

[0459] Figure 20 is an exemplary flowchart illustrating, according to some embodiments of this specification, the determination of target construction personnel and the target wall surface and construction tasks assigned to each target construction personnel within a target construction period. In some embodiments, as shown in Figure 20, process 2000 may include steps 2010-2020. In some embodiments, as shown in Figure 20, process 2000 may further include steps 2030-2040.

[0460] In some embodiments, the processor may divide the target wall into at least one wall group corresponding to at least one type of construction task item based on the construction task item corresponding to each target wall; for each type of construction task item, based on the construction personnel information, determine the construction personnel who can handle the construction task item and their workable area during the target construction period; generate a wall list based on the location information of the walls in the wall group corresponding to the construction task item; and, based on the wall list and the workable area of ​​the construction personnel, determine the target construction personnel corresponding to the construction task item, and determine the target wall and its construction task item assigned to each target construction personnel in the wall group corresponding to the construction task item.

[0461] In some embodiments, the processor may further determine the sum of the workable areas of the construction personnel capable of handling the construction task items, and the sum of the wall areas in the wall group; in response to the sum of the workable areas being less than the sum of the wall areas, estimate the delay losses caused by the construction period delay and the additional personnel costs caused by dispatching additional construction personnel; send a task order update request to the initiator of the construction task order, the task order update request including the delay losses and additional personnel costs; and update the construction personnel information and / or the target construction period based on the updated construction task order received from the initiator.

[0462] Step 2010: Based on the construction task item corresponding to each target wall, divide the target wall into at least one wall group corresponding to at least one type of construction task item.

[0463] Construction task type refers to the specific category of construction task. Construction task types can include waterproofing tasks, spray painting tasks, plastering tasks, tiling tasks, etc. Each type of construction task can correspond to at least one wall surface. Therefore, at least one type of construction task can correspond to at least one wall surface group, and each wall surface group can include at least one target wall surface.

[0464] In some embodiments, the target wall and the corresponding construction task item for each target wall have been determined in step 1820. The processor can divide the target wall into at least one wall group based on the construction task item type corresponding to each target wall. For example, the processor can divide the target wall into wall groups A1-A1 corresponding to construction task item type A. i The wall group B1-B corresponding to construction task item type B. j .

[0465] For ease of explanation, the wall group will be referred to as A1-A below. i Let's take an example to illustrate.

[0466] Step 2020: For each type of construction task item, determine the target construction personnel corresponding to the construction task item, as well as the target wall surface and its construction task item assigned to each target construction personnel.

[0467] In some embodiments, step 2020 may be implemented by steps 2021-2023.

[0468] Step 2021: Based on the construction personnel information, determine the construction personnel who can handle the construction tasks and their workable area during the target construction period.

[0469] As mentioned above, construction personnel information can include the number of construction personnel, their user IDs, the construction tasks each person is responsible for, and the workable area per unit time. More information about construction personnel can be found in Figure 18 and its corresponding description.

[0470] In some embodiments, for each type of construction task, the processor can determine, based on the construction personnel information, the N construction personnel capable of performing that type of construction task, and the workable area that each of the N construction personnel can complete within the target construction period. For example, if the target construction period is one week, then the workable area that a certain construction personnel can complete within the target construction period could be N square meters of waterproofing in one week, M square meters of latex paint in one week, etc.

[0471] Step 2022: Generate a wall list based on the location information of the walls in the wall group corresponding to the construction task item.

[0472] Wall location information is data used to reflect the spatial location of a wall. For example, wall location information may include the coordinates (X, Y, F, Z) of the wall's center point. i ,Y j The coordinate values ​​can be location data in a preset coordinate system, where the preset coordinate system can be a coordinate system with a point in the target construction area as the origin, the east-west direction as the X-axis, and the north-south direction as the Y-axis.

[0473] It should be noted that if an excessively long wall is split into smaller sections, the positional information of each section includes the spatial location data of that section. For example, the positional information may include the coordinates of the center point of each section. More information on wall splitting can be found in Figure 18 and its corresponding description.

[0474] A wall list is a list generated by arranging adjacent walls. For example, a wall list can be wall A1, wall A2, ... wall A i In some embodiments, the wall list includes relevant information for each wall, such as its number, location, corresponding construction task, and area.

[0475] Understandably, when assigning target walls and their construction tasks, it's desirable to minimize the walking distance for construction workers to improve work efficiency. Therefore, wall groups A1-A can be configured... i The walls in the list are sorted by their spatial location, so that walls that are close in location are adjacent in the list.

[0476] The wall list can include a list of interior walls and a list of exterior walls.

[0477] Because the interior walls are easily accessible, construction workers can reach different interior wall locations via doors, corridors, etc. In some embodiments, for interior walls, the processor can use the center point of any wall 'a' in the wall group as a reference point, connect the reference point to the center points of other walls in the wall group to obtain multiple lines, and use wall 'a' as the first wall in the wall list. Then, arbitrarily select one of the other walls, wall 'b', as the second wall in the wall list. Using the line connecting wall 'a' and wall 'b' as the starting line, sort the remaining walls according to the order of the remaining lines (e.g., clockwise) to generate the wall list. In some embodiments, for interior walls, the processor can use a space-filling curve to map two-dimensional coordinates to a one-dimensional sequence for sorting. In some embodiments, if the walls are arranged approximately linearly, the processor can directly sort them by x-coordinate or y-coordinate.

[0478] In some embodiments, for interior walls, the processor can select wall group A1-A i Starting from any wall A1 (for example, the processor can choose a wall near the construction elevator exit), find the wall A2 closest to wall A1, then find the wall A3 closest to wall A2, and so on, until all walls have been processed. Then process wall A1, wall A2, wall A3... wall A... i List the wall surfaces.

[0479] The distance between walls refers to the distance between the center points of the walls. For example, as shown in Figure 21, the distance between wall A and wall B is the distance between the center point p of wall A and the center point q of wall B.

[0480] Since doors and unfinished walls are passable, spatial blocking elements can be set as windows and completed walls, excluding doors and unfinished walls. Whether a wall is completed can be determined by whether key task sheets related to wall construction have been completed. The processor can identify impassable windows and completed walls using the method shown in Figure 18 for identifying interior and exterior walls. Since windows are mounted on walls, their locations are not marked in Figure 21; they are simply represented by the wall itself. For more information on identifying interior and exterior walls, please refer to Figure 18 and its corresponding description.

[0481] As shown in Figure 21, when it is necessary to determine the distance between wall A and wall B, the processor can start from the grid 6 closest to the center point p of wall A, and extend to the three grids 7 above, to the left and to the right of grid 6; continuing from grid 7 (since the grids 7 above and to the left are far from wall B, the extension of these two grids is not shown in the figure), first eliminating the grids that have already been traversed and the grids that are impassable, and extending to grid 8... When extending to grid 13, it reaches the center point q of wall B. Therefore, from the center point p of wall A to the center point q of wall B, it extends a total of 7 times. If each grid is 1m, then the distance between wall A and wall B is 7m.

[0482] However, for exterior walls, construction can only proceed in a specific order, for example, starting from the top floor and working downwards. The list of walls can be generated based on 3D models corresponding to multiple floors.

[0483] In some embodiments, the target construction area may include at least two floors, the construction plan includes a construction plan corresponding to each floor, the walls include exterior walls facing the outside, and the wall list corresponding to the exterior walls is generated based on the following: for each floor, a first 3D model corresponding to the floor is generated based on the floor height and the walls in its corresponding construction plan; a reference area corresponding to the common vertical space of multiple floors in the first 3D model is determined; based on the reference area in the first 3D models of at least two floors, the first 3D models of at least two floors are aligned and stacked to generate a second 3D model of the target construction area; and based on the second 3D model, a wall list corresponding to the exterior walls is generated.

[0484] The list of walls corresponding to the exterior walls can be generated based on steps P1-P3.

[0485] Step P1: For each floor, based on the floor height and the walls in the corresponding construction plan, generate the first 3D model corresponding to the floor; determine the reference area corresponding to the common vertical space of multiple floors in the first 3D model.

[0486] The first 3D model refers to the 3D model of each floor.

[0487] In some embodiments, for each floor, the processor can determine the room outline of that floor based on the walls identified in the floor plan. Further, the processor can generate a first 3D model of that floor based on its floor height.

[0488] Shared vertical space refers to vertical spaces that are common to different floors. For example, shared vertical space can include elevators and staircases. Understandably, regardless of how the rooms on at least two floors change, the location of the shared vertical space remains fixed.

[0489] The reference area corresponding to the shared vertical space refers to the area corresponding to the shared vertical space in the first 3D model of each floor.

[0490] In some embodiments, for each floor, the processor can identify the corresponding textual elements in the construction plan to determine the location of the shared vertical space and find the corresponding area in the first 3D model.

[0491] Step P2: Based on the reference areas in the first 3D model of at least two floors, align and stack the first 3D model of at least two floors to generate a second 3D model of the target construction area.

[0492] Alignment refers to the process of matching at least two floors so that their corresponding sections are aligned. Stacking refers to the process of overlapping at least two floors in a specific floor order.

[0493] The second 3D model refers to a 3D model with at least two floors.

[0494] In some embodiments, for each group of adjacent floors, the processor can align the reference areas corresponding to the common vertical space of the adjacent floors, and then stack the first 3D models corresponding to the adjacent floors to generate a second 3D model of the target construction area. For example, for the group of adjacent floors 2 and 3, both floors have four elevator spaces with dimensions of 2500m × 2500m. Since elevators are usually vertically aligned, the processor can align the reference areas corresponding to the four elevator spaces on floors 2 and 3, and then stack the first 3D models corresponding to floors 2 and 3 to generate a second 3D model of the target construction area.

[0495] Step P3: Based on the second 3D model, generate a list of walls corresponding to the exterior walls.

[0496] In some embodiments, the processor can determine multiple columns of exterior walls located on different floors in the same vertical plane (e.g., the exterior wall corresponding to an elevator) based on a second 3D model. From the multiple columns of exterior walls, an arbitrary column of exterior walls *r* is selected, and the exterior walls on different floors of that column *r* are sorted from top to bottom to form the first part of the wall list; the exterior walls on different floors of the adjacent column *r+1* are then sorted from top to bottom to form the second part of the wall list adjacent to the first part… until all columns of walls are covered, generating a wall list corresponding to the exterior walls.

[0497] In some embodiments of this specification, the wall list corresponding to the exterior wall is determined based on a 3D model, making task allocation more in line with the general practice of exterior wall construction and improving construction efficiency.

[0498] Step 2023: Based on the wall list and the workable area of ​​the construction personnel, determine the target construction personnel corresponding to the construction task item, and determine the target wall and its construction task item to be assigned to each target construction personnel in the wall group corresponding to the construction task item.

[0499] In some embodiments, the processor can determine the target construction personnel corresponding to the construction task items, as well as the target wall surfaces and construction task items assigned to each target construction personnel, through the process shown in Figure 22. More details regarding the determination of the target construction personnel corresponding to the construction task items, and the target wall surfaces and construction task items assigned to each target construction personnel, can be found in Figure 22 and its corresponding description.

[0500] In some embodiments, the processor can determine the target construction personnel corresponding to the construction task items, as well as the target wall surfaces and construction task items assigned to each target construction personnel, through the process shown in Figure 23. More details regarding the determination of the target construction personnel corresponding to the construction task items, and the target wall surfaces and construction task items assigned to each target construction personnel, can be found in Figure 23 and its corresponding description.

[0501] In some embodiments, there may be a situation where there are many construction tasks but few construction workers on the work order, resulting in some tasks not being assigned to workers. In such cases, it is advisable to consider whether to extend the construction period or to add more workers. Specifically, the processor may further execute steps 2030-2040.

[0502] Step 2030: Determine the sum of the workable areas of the construction personnel who can handle the construction tasks, and the sum of the wall areas in the wall group.

[0503] In some embodiments, for each type of construction task item, the processor can add up the workable areas of the construction personnel who can handle the construction task item within the target construction period to obtain the sum of the workable areas of the construction personnel who can handle the construction task item; and the processor can add up the wall areas in the wall group corresponding to the construction task item to obtain the sum of the wall areas in the wall group.

[0504] Step 2040: In response to the sum of workable areas being less than the sum of wall areas, update the construction personnel information and / or the target construction period.

[0505] When the sum of the workable areas is less than the sum of the wall areas, it indicates that there are not enough construction workers. In this case, the following two methods can be adopted: 1. Delay the construction period and spend more time to complete the construction task. For example, if the target construction period is 3 days, it needs to be extended to 7 days to complete the task; 2. Arrange more construction workers to complete the task within the target construction period.

[0506] Step 2041: Estimate the delay losses caused by the construction period delay and the additional personnel costs caused by sending additional construction personnel.

[0507] Delay losses refer to the economic losses caused by delays in the construction period.

[0508] Additional staff costs refer to the increased costs incurred by dispatching additional construction personnel.

[0509] In some embodiments, the processor can determine, based on the construction contract, whether there is any delay compensation; if so, the delay compensation constitutes a first delay loss. The processor can determine whether the delay will affect the progress of subsequent construction tasks; if so, whether it will cause monetary loss; if it will cause monetary loss, the monetary loss constitutes a second delay loss. The processor can determine the first delay loss and / or the second delay loss as a total delay loss.

[0510] In some embodiments, the processor can estimate how many additional construction workers are needed to complete the task on time based on the difference between the sum of the workable areas and the sum of the wall areas, and add up the cost of the additional construction workers as the additional personnel cost.

[0511] Step 2042: Send a task order update request to the party that initiated the construction task order.

[0512] The party that initiates a construction task order is the party that initiates the construction task order.

[0513] A work order update request is a decision request that requires the initiator of a work order to make a choice. For example, a work order update request may include delay losses and additional staffing costs.

[0514] In some embodiments, the processor may send the latency loss and additional staffing costs as information in the task order update request to the initiator of the construction task order as a decision-making reference.

[0515] Step 2043: Based on the updated work order received from the initiator, update the construction personnel information and / or the target construction period.

[0516] Based on the information in the task order update request, the initiator selects to delay the construction period and / or increase the number of construction personnel. If the initiator chooses to increase the number of personnel, the processor can update the construction personnel information; if the initiator chooses to delay the construction period, the processor can update the target construction period; if the initiator chooses to increase the number of personnel and delay the construction period (for example, increasing a small number of construction personnel while delaying some construction period), the processor can update both the construction personnel information and the target construction period.

[0517] In some embodiments of this specification, by identifying the target construction personnel corresponding to each type of construction task item, and determining the target wall and its construction task item assigned to the target construction personnel in the corresponding wall group, it is possible to minimize the walking distance of construction personnel and ensure that the sum of the wall areas does not exceed the sum of the workable areas. Furthermore, by updating the construction personnel information and / or the target construction period, the normal progress of the construction task can be guaranteed, while costs can be saved. Providing the initiator with more decision-making reference information can improve the accuracy of decision-making.

[0518] It should be noted that the above description of the process for determining the target construction personnel and the target wall surfaces and their construction tasks assigned to each target construction personnel within the target construction period is merely for illustration and explanation, and does not limit the scope of the invention. Those skilled in the art can make various modifications and changes to the process for determining the target construction personnel and the target wall surfaces and their construction tasks assigned to each target construction personnel within the target construction period, under the guidance of this invention. However, these modifications and changes are still within the scope of this invention. In some embodiments, steps 2330-2340 can be performed after step 2020.

[0519] Figure 22 is an exemplary flowchart illustrating the determination of target construction personnel and target wall surfaces and their construction tasks assigned to each target construction personnel within a target construction period, according to some embodiments of this specification. In some embodiments, as shown in Figure 22, process 2200 may include steps 2210-2240.

[0520] In some embodiments, the processor may determine a target number of construction workers as target construction workers, such that the sum of the workable areas of the target construction workers is equal to the sum of the wall areas in the wall group corresponding to the construction task item; determine a target number of wall intervals in the wall list, each wall interval starting with a randomly determined target wall, and the sum of the wall areas in the wall interval is equal to the average workable area of ​​the target construction workers; perform at least one round of updates on the wall intervals until non-overlapping target wall intervals are generated, wherein each round of updates includes a first update and a second update, the first update being based on the sum of the distances from each target wall in the wall interval to other target walls therein, and the second update being based on the target walls that overlap between the wall intervals; and assign the target wall intervals to the target construction workers respectively.

[0521] Step 2210: Determine the target number of construction workers as target construction workers, and determine the target construction area corresponding to each target construction worker, so that the sum of the target construction areas of the target construction workers is equal to the sum of the wall areas in the wall group corresponding to the construction task item.

[0522] In some embodiments, it is assumed that when identifying walls within the target construction area, the walls are divided by area, resulting in walls with the same area. The processor can determine the target number of target construction workers and the target construction area corresponding to each target construction worker based on the sum of the wall areas and the workable area of ​​each worker, such that the sum of the target construction areas of the target workers equals the sum of the wall areas in the wall group corresponding to the construction task item. For example, assuming there are 200 walls of 1 square meter each to be allocated, and each worker has a workable area of ​​20 square meters, the processor can determine that the target number of target construction workers is 10, and the target construction area of ​​each worker is 20 square meters. As another example, assuming there are 200 walls of 1 square meter each to be allocated, and each worker has a workable area of ​​19 square meters, the processor can determine that the target number of target construction workers is 11, with 10 workers having a target construction area of ​​19 square meters and 1 worker having an area of ​​10 square meters.

[0523] Step 2220: Determine the target number of wall intervals in the wall list. Each wall interval starts with a randomly determined target wall, and the sum of the areas of the walls in the wall interval is equal to the target construction area of ​​a target construction worker.

[0524] In some embodiments, the processor may randomly select any number of target walls from the wall list as starting walls and determine a wall interval starting from the starting wall, wherein the sum of the areas of the walls in the interval is equal to the target construction area of ​​a target construction worker.

[0525] For example, suppose there are 200 walls, each 1 square meter, to be assigned to 10 target construction workers. Each worker's target construction area is 20 square meters. The processor can randomly select any 10 walls (e.g., wall A1, wall B1, wall C1, etc.) as starting walls. Starting from each starting wall, it determines a wall interval containing 20 walls. Thus, 10 wall intervals can be determined, each containing a total wall area of ​​20 square meters, which can be assigned to one target construction worker. As another example, suppose there are 200 walls, each 1 square meter, to be assigned to 11 target construction workers. Ten of these workers have a target construction area of ​​19 square meters, and each worker has an area of ​​10 square meters. The processor can randomly select any 11 walls as starting walls, and determine a total of 11 wall intervals starting from each starting wall. Among them, the total area of ​​the walls in 10 wall intervals is 19 square meters, which can be assigned to 10 target construction workers; the total area of ​​the walls in 1 wall interval is 10 square meters, which can be assigned to 1 target construction worker.

[0526] Step 2230: Update the wall area at least once until non-overlapping target wall areas are generated.

[0527] Each round of updates includes a first update and a second update.

[0528] The first update can be based on the sum of the distances from each target wall within a wall interval to all other target walls in that interval. For example, in a group of 20 walls, the distances from each wall to the other 19 walls are summed, and the wall with the smallest sum is taken as the new starting point. Based on the new starting point, the 19 walls closest to the new starting point are determined, forming a new group.

[0529] The second update can be based on target walls that overlap between wall intervals. For example, after the first update, there are usually overlapping parts between these 10 wall intervals. If the overlapping part includes wall A falling in wall interval 1 and wall interval 2, the first distance between wall A and the other 19 walls in wall interval 1, and the second distance between wall A and the other 19 walls in wall interval 2 are summed. In response to the first distance being less than the second distance, wall A is assigned to wall interval 1. In response to the first distance being greater than the second distance, wall A is assigned to wall interval 2. In response to the first distance being equal to the second distance, wall A is assigned to either wall interval 1 or wall interval 2. For wall intervals not assigned to wall A, the processor can add the wall with the smallest sum of distances to the 19 walls in that wall interval to form 20 walls.

[0530] The processor can repeat the first and second updates until non-overlapping target wall intervals are generated, which can eventually divide the 200 walls into 10 groups of 20 walls each.

[0531] Step 2240: Assign the target wall area to the target construction personnel respectively.

[0532] In some embodiments, each target wall area is assigned to a target construction worker; that is, the target wall within a target wall area and its corresponding target task item are assigned to a single target construction worker. Furthermore, the total area of ​​the target walls within a target wall area does not exceed the workable area of ​​the corresponding target construction worker.

[0533] In some embodiments of this specification, the method of at least one round of updates can minimize the walking distance of construction workers and ensure that the wall area allocated to each target construction worker does not exceed their workable area.

[0534] Figure 23 is an exemplary flowchart illustrating, according to some embodiments of this specification, the determination of target construction personnel and the target wall surface and construction tasks assigned to each target construction personnel within a target construction period. In some embodiments, as shown in Figure 23, process 2300 may include steps 2310-2320. In some embodiments, as shown in Figure 23, process 2300 may further include steps 2330-2340.

[0535] In some embodiments, the processor may sort the construction workers capable of handling construction tasks to generate a list of construction workers; sequentially perform task assignment operations on the construction workers in the list of construction workers until all construction workers in the list of construction workers have performed task assignment operations or all walls in the wall list have been assigned; for the current construction worker, the task assignment operation includes: determining the first unassigned wall in the wall list as the starting wall; determining the ending wall in the wall list such that the cumulative sum of the wall surfaces from the starting wall to the ending wall is less than or equal to the current construction worker's workable area, and the cumulative sum of the wall surfaces of the next wall from the starting wall to the ending wall is greater than the current construction worker's workable area; and designating the current construction worker as the target construction worker, and designating the starting wall, the ending wall, and the wall in between, along with their construction tasks, as the target wall and their construction tasks assigned to the target construction worker.

[0536] In some embodiments, the processor may also determine whether there are construction workers who have not performed the task assignment operation; and, in response to determining that there are construction workers who have not performed the task assignment operation, send a reminder to the initiator of the construction task order that there are remaining construction workers.

[0537] Step 2310: Sort the construction personnel who can handle construction tasks to generate a list of construction personnel.

[0538] A construction worker list is a form that arranges construction workers in a specific order. For example, a construction worker list of N workers would be P1-P2. n .

[0539] In some embodiments, the processor can sort the construction workers according to preset rules. Preset rules refer to rules that are pre-defined. For example, preset rules may include random sorting, sorting by the workable area corresponding to the construction workers from largest to smallest, or sorting by the rating score of the construction workers from largest to smallest.

[0540] Step 2320: Perform task assignment operations on the construction workers in the construction worker list in sequence until all construction workers in the construction worker list have performed task assignment operations or all walls in the wall list have been assigned.

[0541] In some embodiments, for the current construction worker, the processor may determine the first unassigned wall in the wall list as the starting wall; determine the ending wall in the wall list such that the cumulative sum of the wall surfaces from the starting wall to the ending wall is less than or equal to the current construction worker's workable area, and the cumulative sum of the wall surfaces of the next wall from the starting wall to the ending wall is greater than the current construction worker's workable area; and designate the current construction worker as the target construction worker, and designate the starting wall, the ending wall, and the wall in between, along with their construction tasks, as the target wall and their construction tasks assigned to the target construction worker.

[0542] For example, when the list of construction workers is P1-P n For the current worker P1, whose workable area is S1, the processor can start from the first unassigned wall in the wall list and calculate the cumulative sum of the wall surfaces from the first wall to the first wall in turn, until a termination wall for worker P1 that meets the termination condition is found. The termination condition is that the cumulative sum of the wall surfaces from the first wall to the termination wall is ≤ S1, and the cumulative sum of the wall surfaces from the first wall to the next wall is > S1. For the current worker P2, the processor starts from the first remaining wall in the wall list and assigns walls to worker P2 using a similar method as worker P1, until a termination wall for worker P2 is determined. This process continues until all workers in the worker list have performed task assignment operations or all walls in the wall list have been assigned.

[0543] The processor can designate the construction worker who has performed the task assignment operation as the target construction worker. For each target construction worker, the processor can designate the starting wall, the ending wall, and the wall between the two walls as target walls and assign them to that target construction worker.

[0544] In some embodiments, there may be a situation where there are fewer construction tasks but more construction workers on the construction task order, and some construction workers may not be able to be assigned tasks. In this case, the task order initiator can be reminded that there are remaining construction workers, and this can be done through steps 2330-2340.

[0545] Step 2330: Determine if there are any construction workers who have not performed the task assignment operation.

[0546] After assigning tasks, the processor can compare the target construction workers with the construction workers in the task list to determine whether there are any construction workers who have not performed the task assignment operation.

[0547] Step 2340: In response to the determination that there are construction workers who have not performed the task assignment operation, a reminder that there are remaining construction workers is sent to the initiator of the construction task order.

[0548] In response to the determination that there are construction workers who have not performed the task assignment operation, the construction workers in the task order are described.

[0549] The reminders for remaining work by construction workers can be in the form of text, voice, or light.

[0550] In some embodiments, the processor can send a reminder from the construction workers that there are remaining issues to the initiator's user terminal via a network, so that the information can be presented to the initiator through the user terminal.

[0551] In some embodiments of this specification, the task allocation operation can minimize the walking distance of construction workers and ensure that the total wall area allocated to each target construction worker does not exceed the total workable area. By sending a reminder to the initiator of the construction task order that there are remaining construction workers, new tasks can be assigned to the remaining construction workers to prevent waste of personnel and improve personnel utilization.

[0552] It should be noted that the above descriptions of processes 200-2300 are for illustrative purposes only and do not limit the scope of this specification. Those skilled in the art can make various modifications and changes to processes 200-2300 under the guidance of this specification. However, these modifications and changes remain within the scope of this specification.

[0553] Figure 24 is an exemplary block diagram of a construction task assignment system based on drawing information recognition according to some embodiments of this specification. In some embodiments, the construction task assignment system 2400 based on drawing information recognition may be disposed in the processor 120. As shown in Figure 24, the construction task assignment system 2400 based on drawing information recognition includes a first recognition module 2410, a second recognition module 2420, a first determination module 2430, a second determination module 2440, a third determination module 2450, and a task assignment module 2460.

[0554] The first recognition module 2410 is configured to acquire the drawing to be recognized.

[0555] The second recognition module 2420 is configured to recognize multiple closed paths in the drawing.

[0556] The first determining module 2430 is configured to determine the drawing frame based on the positional relationship between multiple closed paths.

[0557] The second determining module 2440 is configured to determine the title information based on the drawing frame and the title range of the drawing.

[0558] The third determination module 2450 is configured to determine the identification result of the target object in the drawing based on the drawing label information.

[0559] The task dispatch module 2460 is configured to dispatch construction tasks based on the identification results of the target object.

[0560] It should be noted that the above description of the construction task assignment system 2400 and its modules based on drawing information recognition is for convenience only and should not limit this specification to the scope of the embodiments described. In some embodiments, the first identification module 2410, the second identification module 2420, the first determination module 2430, the second determination module 2440, the third determination module 2450, and the task assignment module 2460 in FIG. 24 can be different modules in one system, or one module can implement the functions of two or more of the above modules. For example, each module can share a storage module, or each module can have its own storage module. Such variations are all within the protection scope of this specification.

[0561] This specification also provides a frame recognition method in some embodiments. Figure 25 is an exemplary flowchart of a frame recognition method according to some embodiments of this specification. In some embodiments, process 2500 can be executed by processor 120. As shown in Figure 25, process 2500 includes the following steps.

[0562] Step 2510: Identify multiple closed paths in the electronic drawing.

[0563] In some embodiments, the processor 120 can parse the drawing and extract multiple straight lines from it. For example, multiple straight lines in the electronic drawing can be extracted using image recognition algorithms (such as Hough transform, edge detection, etc.). Furthermore, the processor 120 can obtain the intersection information of the multiple straight lines and determine whether the multiple straight lines can form a closed path based on this information. For example, the processor 120 can identify whether the endpoints of the multiple straight lines intersect based on their positions, and determine whether the multiple straight lines can form a closed path based on whether the lines with consecutive intersecting endpoints return to their starting endpoints.

[0564] In some embodiments, the processor 120 may construct an undirected graph based on electronic drawings and determine multiple closed paths based on the undirected graph.

[0565] Step 2520: Generate one or more sets of closed paths based on the positional relationships between multiple closed paths.

[0566] In some embodiments, each set of closed paths contains one or more closed paths divided into one or more levels, wherein a first region enclosed by each lower-level closed path is contained within or intersects with a second region enclosed by a higher-level closed path. A detailed description of generating one or more sets of closed paths can be found in Figure 6 and its related description.

[0567] Step 2530: For each set of closed paths, determine whether the set of closed paths contains the target closed path corresponding to the frame.

[0568] Step 2540: Determine whether there exists an isolated closed path among the multiple closed paths that does not intersect with any other closed path.

[0569] Step 2550: In response to determining that an isolated closed path exists, determine whether the isolated closed path is the target closed path.

[0570] For more details on the above process 2500, please refer to the relevant sections above, as shown in Figures 2 to 9B.

[0571] This specification also provides a method for identifying image tag information in some embodiments. Figure 26 is an exemplary flowchart of an image tag information identification method according to some embodiments of this specification. In some embodiments, process 2600 may be executed by processor 120. As shown in Figure 26, process 2600 includes the following steps.

[0572] Step 2610: Obtain the label range of the drawing.

[0573] Step 2620: Determine the first closed path list based on the drawing frame and title block range.

[0574] Step 2630: Based on the text element range in the text element list and the first closed path in the first closed path list, determine the closed path to which the tag field belongs.

[0575] Step 2640: Based on the first intersection ratio between the closed path and the primitive range, and the offset distance between the center point of the text primitive range and the center point of the closed path, determine the content value range of the tag field.

[0576] Step 2650: Obtain the text content value within the content value range based on the content value range.

[0577] For more information on the above process 2600, please refer to the relevant sections above, as shown in Figure 2, Figures 10 to 13, etc.

[0578] This specification also provides a method for extracting drawing space information in some embodiments. Figure 27 is an exemplary flowchart of a method for extracting drawing space information according to some embodiments of this specification. In some embodiments, process 2700 can be executed by processor 120. As shown in Figure 27, process 2700 includes the following steps.

[0579] Step 2710: Obtain the drawing frame.

[0580] Step 2720: Perform icon recognition based on the icon frame to determine the initial spatial information.

[0581] Step 2730: Compare the initial spatial information with the preset spatial information database to obtain the comparison results.

[0582] Step 2740: Based on the comparison results, the initial spatial information is split to obtain spatial description information.

[0583] Step 2750: Based on the spatial description information, obtain the target spatial information of the target drawing.

[0584] For further explanation of the above process 2700, please refer to the relevant sections above, as shown in Figure 2, Figures 14 to 17, etc.

[0585] This specification also provides a wall task assignment method in some embodiments. Figure 28 is an exemplary flowchart of a wall task assignment method according to some embodiments of this specification. In some embodiments, process 2800 may be executed by processor 120. As shown in Figure 28, process 2800 includes the following steps.

[0586] Step 2810: Identify the walls within the target construction area from the construction plan of the target construction area.

[0587] Step 2820: Obtain the construction task sheet corresponding to the wall surface.

[0588] Step 2830: Based on the construction task information and the historical construction data of the wall, determine the target wall to be constructed during the target construction period and the construction task item corresponding to each target wall from the walls in the target construction area.

[0589] Step 2840: Based on the construction personnel information and the construction task items corresponding to each target wall, determine the target construction personnel and the target walls and their construction task items assigned to each target construction personnel within the target construction period.

[0590] For further explanation of the above process 2700, please refer to the relevant sections above, such as Figure 2, Figures 18 to 23, etc.

[0591] The basic concepts have been described above. Obviously, for those skilled in the art, the detailed disclosure above is merely illustrative and does not constitute a limitation of this specification. Furthermore, this specification uses specific terms to describe embodiments thereof. For example, "an embodiment," "one embodiment," and / or "some embodiments" refer to a particular feature, structure, or characteristic related to at least one embodiment of this specification. Therefore, it should be emphasized and noted that "an embodiment," "one embodiment," or "an alternative embodiment" mentioned twice or more in different locations in this specification do not necessarily refer to the same embodiment.

[0592] It should be noted that, in order to simplify the descriptions disclosed herein and thus aid in the understanding of one or more embodiments, the foregoing description of embodiments in this specification sometimes combines multiple features into a single embodiment, drawing, or description thereof. However, this method of disclosure does not imply that the subject matter of this specification requires more features than those mentioned in the claims. In fact, the embodiments contain fewer features than all the features of the single embodiments disclosed above.

Claims

1. A method for dispatching construction tasks based on drawing information recognition, characterized in that, The method includes: Obtain the drawing to be identified; Identify multiple closed paths in the drawing; The drawing frame is determined based on the positional relationship between the multiple closed paths; Based on the drawing frame and the title block area of ​​the drawing, determine the title block information; Based on the label information, the identification result of the target object in the drawing is determined; Based on the identification results of the target object, construction tasks are assigned.

2. The method according to claim 1, characterized in that, Determining the drawing frame based on the positional relationship between the multiple closed paths includes: Based on the positional relationship between the multiple closed paths, one or more sets of closed paths are generated. Each set of closed paths includes one or more closed paths divided into one or more levels. The first region enclosed by each of the lower-level closed paths is contained in or intersects with the second region enclosed by the closed path of its upper level. For each set of closed paths, determine whether the set of closed paths includes the target closed path corresponding to the frame.

3. The method according to claim 1, characterized in that, The identification of multiple closed paths in the drawing includes: Extract multiple straight lines from the drawing; Based on the multiple straight lines, an undirected graph is constructed, wherein the vertices of the undirected graph correspond to the endpoints of the multiple straight lines, and the edges of the undirected graph correspond to the multiple straight lines; Based on the undirected graph, determine the plurality of closed paths.

4. The method according to claim 2, characterized in that, The generation of one or more sets of closed paths based on the positional relationships between the multiple closed paths includes: Based on the positional relationship between the multiple closed paths, one or more sets of intersecting closed paths are determined, and each set of intersecting closed paths is defined as a closed path contained in a set of closed paths. For each set of closed paths, the level of each closed path in the set of closed paths is determined based on the area of ​​the region enclosed by each closed path in the set of closed paths.

5. The method according to claim 4, characterized in that, Determining the level of each of the closed paths in the set of closed paths includes: The initial superior closed path is determined by comparing the areas of the two regions enclosed by any two intersecting closed paths. For each of the closed paths In response to the fact that the number of its corresponding initial upper-level closed paths is zero, the closed path is determined to be the uppermost closed path; In response to the fact that the number of the initial superior closed path is one, the initial superior closed path is determined to be the superior closed path corresponding to it; In response to the fact that there are two or more initial superior closed paths, the superior closed path of the closed path is determined according to the intersection-union ratio of the closed path and each initial superior closed path.

6. The method of claim 5, further comprising representing each set of closed paths using a relation tree, including: The topmost closed path in each set of closed paths is determined as the root node of the relation tree; The lower-level closed path in each set of closed paths is determined as a child node of the upper-level closed path.

7. The method according to claim 2, characterized in that, Determining whether the closed path set includes the target closed path corresponding to the frame includes: processing the closed paths at each level in the closed path set starting from the highest level, until the target closed path is found or all the closed paths in the closed path set are processed, wherein processing the closed paths at the current level includes: Determine the rectangular closed path in the closed path at the current level; Determine whether the rectangular closed path satisfies a first preset condition and a second preset condition. The first preset condition is related to the positional relationship between the closed path and its subordinate closed paths, and the second preset condition is related to the features of the drawing frame. In response to determining that the rectangular closed path satisfies the first preset condition and the second preset condition, the rectangular closed path is determined as the target closed path; In response to determining that the rectangular closed path does not meet the first preset condition or the second preset condition, the closed path at the next level is processed.

8. The method according to claim 7, characterized in that, The first preset condition includes that the rectangular closed path has a lower-level closed path with an intersection-union ratio greater than a preset threshold, or that the rectangular closed path contains a lower-level closed path passing through its vertices.

9. The method according to claim 2, characterized in that, Determining whether the set of closed paths includes the target closed path corresponding to the frame includes: The closed paths in the set of closed paths are filtered to obtain a set of filtered closed paths. The set of filtered closed paths includes rectangular closed paths that satisfy a first preset condition and a second preset condition. The first preset condition is related to the positional relationship between the closed path and its subordinate closed paths, and the second preset condition is related to the features of the drawing frame. The highest-level closed path in the set of filtered closed paths is taken as the target closed path.

10. The method according to claim 1, characterized in that, The method further includes: Determine whether there exists an isolated closed path among the plurality of closed paths that does not intersect with any other closed path; In response to determining the existence of the isolated closed path, Determine whether the isolated closed path is a rectangular closed path that satisfies a second preset condition, the second preset condition being related to the features of the drawing frame; In response to determining that the isolated closed path is a rectangular closed path that satisfies the second preset condition, the isolated closed path is determined as the target closed path.

11. The method according to claim 1, characterized in that, The step of determining the title information based on the drawing frame and the title range of the drawing includes: determining a first closed path list based on the drawing frame and the title range of the drawing, wherein the first closed path list includes all first closed paths that do not contain other closed paths; Based on the text element range in the text element list and the first closed path in the first closed path list, determine the closed path to which the tag field belongs. Based on the first intersection ratio between the closed path and the primitive range, and the offset distance between the center point of the text primitive range and the center point of the closed path, the content value range of the tag field is determined; Based on the specified content value range, the text content value within the specified content value range is obtained as the tag information.

12. The method according to claim 11, characterized in that, The determination of the content value range of the tag field based on the first intersection ratio between the closed path and the primitive range, and the offset distance between the center point of the text primitive's range and the closed path includes: Determine whether the first intersection ratio and the offset distance satisfy the third preset condition; and In response to the first intersection ratio and the offset distance satisfying a third preset condition, the range of the closed path to which the content value belongs is taken as the range of the content value.

13. The method according to claim 12, characterized in that, The third preset condition includes that the first intersection ratio is less than or equal to the first threshold, and the ratio of the offset distance to the target direction length of the closed path is greater than the second threshold.

14. The method according to claim 12, characterized in that, The method includes: In response to the first intersection ratio and / or the offset distance not meeting the third preset condition, an adjacent closed path sharing a vertex with the corresponding closed path is determined; The adjacent closed paths that meet the filtering criteria are identified as second closed paths, and a list of second closed paths is generated; and Based on the second list of closed paths, the range of content values ​​is determined.

15. The method according to claim 14, characterized in that, The determination of the content value range based on the second closed path list includes: Determine the number of paths in the second closed path list; In response to the fact that the number of paths in the second closed path list is 0, the corresponding closed path is determined to be within the content value range; In response to the fact that the number of paths in the second closed path list is greater than 0, a second intersection ratio between the second closed path and the map label range is determined; In response to the fact that the number of second closed paths in the second closed path list whose second intersection ratio with the tag range satisfies a fourth preset condition is less than a preset number, the second closed paths whose second intersection ratio satisfies the fourth preset condition are taken as the content value range; and In response to the fact that the number of second closed paths in the second closed path list that satisfy the fourth preset condition with the second intersection ratio of the tag range is not less than the preset number, the target distance between the center point of each second closed path and the center point of the corresponding closed path in a preset direction is determined, and the second closed path whose target distance with the center point of the corresponding closed path in the preset direction satisfies the fifth preset condition is taken as the content value range.

16. The method according to claim 11, characterized in that, The determination of the first closed path list based on the drawing frame and the title block range of the drawing includes: Determine the straight line segments that intersect the frame and the label area; An undirected graph is constructed based on the line segments and the intersection of the frame and the label area. Traverse the undirected graph to determine multiple third closed paths; and The first list of closed paths is determined based on the inclusion relationships among the plurality of third closed paths.

17. The method according to claim 11, characterized in that, The list of text elements is obtained through the following steps: Based on the text elements in the drawing, generate an element information list; and Based on the graphic element information list and the commonly used text information table, the text graphic element list is generated.

18. The method according to claim 11, characterized in that, The title page range of the drawing is obtained through the following steps: Based on the text elements in the drawing, generate an element information list; Based on the aggregation of text elements in the element information list, an aggregation range list is determined, wherein the aggregation range list includes the element range of at least one of the text elements; and The scope of the image tag is determined based on the aggregated scope list.

19. The method according to claim 18, characterized in that, Determining the label range based on the aggregated range list includes: For each text element in the element information list, calculate the first intersection-union ratio between the element range of the text element and the frame range of the frame; In response to the first intersection-union ratio being greater than a third threshold, the text primitive is removed from the primitive information list; In response to the first intersection-union ratio being less than or equal to the third threshold, it is determined whether the aggregation range list is empty; In response to the fact that the aggregation range list is empty, the element range of the text element is filled into the aggregation range list; In response to the fact that the list of aggregate ranges is not empty, the union of each aggregate range in the list of aggregate ranges with the range of the text primitive is determined, and the second intersection-union ratio of the union with the frame is calculated; In response to the second intersection-union ratio being greater than the fourth threshold, the primitive range of the text primitive is filled into the aggregation range list; In response to the second intersection-union ratio being less than or equal to the fourth threshold, the aggregation range is replaced with the union set; and The tag range is determined based on the number of times the tag field appears in at least one aggregation range in the aggregation range list.

20. The method according to claim 1, characterized in that, The identification result includes target spatial information. The step of determining the identification result of the target object in the drawing based on the title information includes: Based on the map information, determine the initial spatial information; The initial spatial information is compared with a preset spatial information database to obtain the comparison results. Based on the comparison results, the initial spatial information is split to obtain spatial description information; Based on the spatial description information, the target spatial information of the target drawing is obtained.

21. The method according to claim 20, characterized in that, The step of splitting the initial spatial information based on the comparison result to obtain spatial description information includes: When the comparison result meets the fifth preset condition, the initial spatial information is split to obtain multiple spatial information combinations; For each combination of spatial information, floor space description information and building space description information are obtained based on a preset method.

22. The method according to claim 21, characterized in that, The step of obtaining the target spatial information of the target drawing based on the spatial description information includes: Based on the floor space description information and the building space description information, keyword extraction is performed to obtain the target floor information and the target building information; The target floor information and the target building information are combined to obtain the target spatial information of the target drawing.

23. The method according to claim 21, characterized in that, The process of obtaining floor space description information and building space description information based on a preset method includes: Based on the spatial information combination, information related to the floor is extracted to obtain the floor spatial description information; Based on the spatial information combination, information related to the building is extracted to obtain the building spatial description information.

24. The method according to claim 22, characterized in that, The step of extracting keywords based on the floor space description information and the building space description information to obtain target floor information and target building information includes: Extract the first number and the custom floor from the floor space description information; Based on the adjacent connecting words of the first number, determine the information of the first floor; The second floor information is determined based on the consecutive words between the first digits; Based on the first floor information and the second floor information, the target floor information is determined, and the custom floor is used as supplementary floor information; Extract the second number and the custom building from the building space description information; Based on the adjacent connectives of the second number, determine the information of the first building; Based on the consecutive words between the second digits, the information of the second building is determined; Based on the first building information and the second building information, the target building information is determined, and the custom building is used as supplementary building information.

25. The method according to claim 20, characterized in that, The method further includes: When the comparison result meets the sixth preset condition, the initial spatial information is split to obtain floor space description information; Based on the floor space description information, keyword extraction is performed to obtain the target floor information; Obtain the sub-item information of the frame, and based on the sub-item information, obtain the sub-item spatial information; The spatial information of the sub-items is broken down to obtain the spatial description information of the buildings; Based on the building space description information, keyword extraction is performed to obtain the target building information; The target floor information and the target building information are combined to obtain the target spatial information of the target drawing.

26. The method according to claim 20, characterized in that, The method further includes: Image segmentation is performed based on the target drawing to obtain drawings of one or more building areas; Based on the drawings of the one or more building areas, determine the auxiliary building information; For each of the one or more building area drawings, floor identification is performed based on the building area drawings to determine auxiliary floor information; The auxiliary building information and the auxiliary floor information are combined to obtain auxiliary space information; Determine whether the auxiliary spatial information and the target spatial information are consistent; In response to the inconsistency between the auxiliary spatial information and the target spatial information, a prompt message is output; the prompt message is used to prompt the user to verify the target spatial information.

27. The method according to claim 26, characterized in that, The step of identifying floors based on the building area drawings and determining auxiliary floor information includes: The building area drawings are input into a convolutional neural network to obtain convolutional feature vectors; The convolutional feature vector is enhanced to obtain an enhanced feature vector; The enhanced feature vector is input into the floor recognition model to determine the auxiliary floor information.

28. The method according to claim 1, characterized in that, The identification result includes the wall surface, and the assignment of construction tasks based on the identification result of the target object includes: Obtain the construction task order corresponding to the wall surface, the construction task order including construction task information and construction personnel information corresponding to the target construction period; Based on the construction task information and the historical construction data of the wall surface, the target walls to be constructed during the target construction period and the corresponding construction task items for each target wall surface are determined from the walls within the target construction area; and, Based on the construction personnel information and the construction task items corresponding to each target wall, the target construction personnel and the target wall and its construction task items allocated to each target construction personnel during the target construction period are determined.

29. The method according to claim 1, characterized in that, The wall surface includes an interior wall surface facing the interior and an exterior wall surface facing the exterior. The construction task sheet includes a first construction task sheet corresponding to the interior wall surface and a second construction task sheet corresponding to the exterior wall surface. The task assignment for the interior wall surface is based on the first construction task sheet, and the task assignment for the exterior wall surface is based on the second construction task sheet.

30. The method according to claim 29, characterized in that, The step of determining the identification result of the target object in the drawing based on the label information includes: Based on the title block information, the drawing is determined to be a construction site plan. Multiple outdoor grids and multiple indoor grids are defined in the construction plan; Starting from at least one of the multiple indoor grids, walk to its adjacent indoor grids until the target indoor grid corresponding to the spatial barrier element is determined. Starting from at least one of the multiple outdoor grids, walk to its adjacent outdoor grids until the target outdoor grid corresponding to the spatial barrier element is determined. as well as, Based on the target indoor grid and the target outdoor grid, the inner wall surface and the outer wall surface within the target construction area are identified from the construction plan.

31. The method according to claim 28, characterized in that, The step of determining the target construction personnel and the target wall surfaces and their construction tasks assigned to each target construction personnel within the target construction period, based on the construction personnel information and the construction task items corresponding to each target wall surface, includes: Based on the construction task item corresponding to each target wall, the target wall is divided into at least one wall group corresponding to at least one type of construction task item; For each type of construction task, Based on the construction personnel information, determine the construction personnel who can handle the construction tasks and their workable area during the target construction period; Based on the location information of the walls in the wall group corresponding to the construction task item, a wall list is generated; and... Based on the wall list and the workable area of ​​the construction personnel, the target construction personnel corresponding to the construction task item are determined, and the target wall and its construction task item are assigned to each target construction personnel in the wall group corresponding to the construction task item.

32. The method according to claim 31, characterized in that, The process of determining the target construction worker corresponding to the construction task item based on the wall list and the workable area of ​​the construction worker, and determining the target wall and its construction task item assigned to each target construction worker in the wall group corresponding to the construction task item, includes: A target number of construction workers is determined as the target construction workers, and a target construction area is determined for each target construction worker, so that the sum of the target construction areas of the target construction workers is equal to the sum of the wall areas in the wall group corresponding to the construction task item; The target number of wall intervals are determined in the wall list. Each wall interval starts with a randomly determined target wall, and the sum of the areas of the walls in the wall interval is equal to the target construction area of ​​one target construction worker. The wall intervals are updated at least once until non-overlapping target wall intervals are generated. Each update includes a first update and a second update. The first update is based on the sum of distances from each target wall in the wall interval to other target walls therein. The second update is based on overlapping target walls between the wall intervals. The target wall area is assigned to the target construction personnel respectively.

33. The method according to claim 31, characterized in that, The process of determining the target construction worker corresponding to the construction task item based on the wall list and the workable area of ​​the construction worker, and determining the target wall and its construction task item assigned to each target construction worker in the wall group corresponding to the construction task item, includes: The construction personnel who can handle the construction tasks are sorted to generate a list of construction personnel. The task assignment operation is performed sequentially on the construction workers in the construction worker list until all construction workers in the construction worker list have performed the task assignment operation or all walls in the wall list have been assigned. For the current construction workers, the task allocation process includes: The first unassigned wall in the wall list is designated as the starting wall. A termination wall is determined in the wall list such that the cumulative sum of the wall surfaces from the starting wall to the termination wall is less than or equal to the workable area of ​​the current worker, and the cumulative sum of the wall surfaces of the next wall from the starting wall to the termination wall is greater than the workable area of ​​the current worker; and, The current construction worker is designated as the target construction worker, and the starting wall, the ending wall, and the wall in between, along with their construction tasks, are designated as the target wall and their construction tasks assigned to the target construction worker.

34. The method according to claim 31, characterized in that, The method further includes: Determine whether there are any construction workers who have not performed the task assignment operation; and, In response to the determination that there are construction workers who have not performed the task assignment operation, a reminder is sent to the initiator of the construction task order that there are remaining construction workers.

35. The method according to claim 31, characterized in that, The method further includes: Determine the sum of the workable areas of the construction personnel capable of handling the construction tasks, and the sum of the wall areas in the wall group; In response to the fact that the sum of the workable areas is less than the sum of the wall areas, Estimate the losses caused by project delays and the additional personnel costs incurred by deploying additional construction workers; Send a task order update request to the initiator of the construction task order, the task order update request including delay losses and additional personnel costs; and, Based on the updated construction task order received from the initiator, update the construction personnel information and / or the target construction period.

36. The method according to claim 31, characterized in that, The target construction area includes at least two floors, the construction plan includes a construction plan for each floor, the walls include exterior walls facing the outside, and the list of walls corresponding to the exterior walls is generated based on the following method: For each floor, Based on the floor height and the corresponding wall surface in the construction plan, a first 3D model of the floor is generated. Determine the reference area corresponding to the shared vertical space of multiple floors in the first 3D model; Based on the reference area in the first 3D model of the at least two floors, the first 3D models of the at least two floors are aligned and stacked to generate a second 3D model of the target construction area; and, Based on the second 3D model, a list of wall surfaces corresponding to the exterior wall surface is generated.

37. A construction task dispatching system based on drawing information recognition, characterized in that, The system includes: The first recognition module is configured to acquire the drawing to be recognized; The second recognition module is configured to recognize multiple closed paths in the drawing; The first determining module is configured to determine the drawing frame of the drawing based on the positional relationship between the multiple closed paths; The second determining module is configured to determine the title block information based on the title block of the drawing and the title block range of the drawing; The third determining module is configured to determine the identification result of the target object in the drawing based on the label information; The task dispatch module is configured to dispatch construction tasks based on the identification results of the target object.

38. A method for recognizing picture frames, characterized in that, The method includes: Identify multiple closed paths in a drawing; Based on the positional relationship between the multiple closed paths, one or more sets of closed paths are generated. Each set of closed paths contains one or more closed paths divided into one or more levels. The first region enclosed by each lower-level closed path is contained in or intersects with the second region enclosed by the closed path of its upper level. For each set of closed paths, determine whether the set of closed paths contains the target closed path corresponding to the frame.

39. A method for identifying image tag information, characterized in that, The method includes: Obtain the title block area of ​​the drawing; Based on the drawing frame and the label range of the drawing, a first closed path list is determined, which includes all first closed paths that do not contain other closed paths. Based on the text element range in the text element list and the first closed path in the first closed path list, determine the closed path to which the tag field belongs. Based on the first intersection ratio between the closed path and the primitive range, and the offset distance between the center point of the text primitive range and the center point of the closed path, the content value range of the tag field is determined; Based on the content value range, obtain the text content value within the content value range.

40. A method for extracting spatial information from drawings, characterized in that, The method includes: Obtain the drawing frame; the drawing frame includes title information; Based on the image frame, image tag recognition is performed to determine the initial spatial information; The initial spatial information is compared with a preset spatial information database to obtain the comparison results. Based on the comparison results, the initial spatial information is split to obtain spatial description information; Based on the spatial description information, the target spatial information of the target drawing is obtained.

41. A method for assigning tasks on a wall, characterized in that, include: Identify the walls within the target construction area from the drawings; Obtain the construction task order corresponding to the wall surface, the construction task order including construction task information and construction personnel information corresponding to the target construction period; Based on the construction task information and the historical construction data of the wall surface, the target walls to be constructed during the target construction period and the corresponding construction task items for each target wall surface are determined from the walls within the target construction area; and, Based on the construction personnel information and the construction task items corresponding to each target wall, the target construction personnel and the target wall and its construction task items allocated to each target construction personnel during the target construction period are determined.

Images