CN115374502A

CN115374502A - Method and system for processing standard monomer drawings

Info

Publication number: CN115374502A
Application number: CN202210763212.XA
Authority: CN
Inventors: 郭思佳; 张婧鹤; 郑于锷; 王骏
Original assignee: Shenzhen Jindi Digital Technology Co ltd
Current assignee: Shenzhen Jindi Digital Technology Co ltd
Priority date: 2022-06-30
Filing date: 2022-06-30
Publication date: 2022-11-22

Abstract

The present application provides methods and systems for processing standard monomer drawings, wherein the methods comprise: obtaining a standard monomer drawing to be subjected to drawing verification; performing structural information extraction and example segmentation on the standard monomer drawing, wherein the example segmentation is used for obtaining pattern block mask information; summarizing intersecting elements of the image blocks belonging to the bay to each image layer of the standard monomer drawing under the control of image block mask information according to bay space information obtained by extracting the structural information; generating tile level information for the tile summary belonging to the bay by matching between the intersecting elements and the preconfigured standard tiles, the tile level information encapsulating all elements of the tiles; and forming the pattern block level information of the standard single body by using the pattern block level information of the pattern blocks which belong to the bays, wherein the pattern block level information of the standard single body is used for executing the drawing verification of the standard single body drawing. The method provided by the application realizes and guarantees the merging and packaging of the discrete graphic block elements, and further eliminates the dispersion of the graphic block elements in the standard single drawing.

Description

Method and system for processing standard monomer drawings

Technical Field

The application relates to the technical field of computer application, in particular to a method and a system for processing standard monomer drawings.

Background

With the development of CAD (Computer-Aided Design) tool series, wind tides for standard single Design drawing by computers are driven. The designer draws drawings on a computer through a CAD tool, great convenience can be achieved in the aspects of accurate size drawing, standard block drawing and the like, and further more focus on the design.

However, after years of process optimization, the drawing reviewer finds that the drawing specifications of the designer are not sufficiently constrained during the drawing process due to the flexibility of the CAD tool set, thereby resulting in a great deal of manpower consumption during the drawing review stage.

Specifically, in a drawing auditing stage in which a drawing is automatically and normally audited by using a computer, because the convenience brought by drawing of the drawing is brought by a CAD tool series, the drawn standard single drawing, such as a CAD standard single drawing, has the problem that elements of a drawing block are discrete and not packed, so that the standard single drawing cannot be extracted, analyzed and logically summarized through dotted line relative relation analysis, simple digital image processing and the like performed by the computer, and further, the standard single drawing is adapted to a drawing auditing rule to perform normal automatic auditing.

At present, the practical usability of automatic verification of drawings is poor, and the limitation that the elements of the blocks in the standard monomer drawings are discrete and not packed needs to be solved urgently.

Disclosure of Invention

An object of this application aims at handling discrete not block element of packing in the standard monomer drawing, promotes the technical problem of the automatic actual availability and the efficiency of examining and verifying of drawing.

According to an aspect of an embodiment of the present application, a method for processing a standard monomer drawing is disclosed, the method comprising:

obtaining a standard monomer drawing to be subjected to drawing verification, wherein the standard monomer drawing is obtained by drawing through computer paper;

performing structural information extraction and example segmentation on the standard monomer drawing, wherein the example segmentation is used for obtaining block mask information in the standard monomer drawing, and the block mask information is adapted to a pre-configured standard block;

according to the bay space information obtained by extracting the structural information, summarizing intersecting elements of the blocks belonging to the bay to each layer of the standard monomer drawing under the control of the block mask information;

generating tile-level information for a tile summary belonging to a bay by matching between the intersecting elements and preconfigured standard tiles, the tile-level information encapsulating all elements of the tile;

and forming the pattern block level information of the standard single body through the pattern block level information of the pattern block to which the bay belongs, wherein the pattern block level information of the standard single body is used for executing the drawing verification of the standard single body drawing.

According to an aspect of the embodiment of the present application, the performing instance segmentation on the standard monomer drawing includes:

combining all layers of the standard monomer drawing to obtain a standard monomer picture;

extracting graph line information describing a graph block from the standard single picture;

obtaining a target area corresponding to the image block through frame regression of the graph line information;

performing a mask representation of the target region generates tile mask information in the standard unitary drawing, the tile mask information including tile masks corresponding to tile bounding boxes, categories, and tile coarse locations.

According to an aspect of an embodiment of the present application, the extracting of the graph information describing a tile from the standard single picture includes:

coding the standard monomer picture through a coding-decoding frame to obtain the description information of the image blocks in the standard monomer drawing;

generating a candidate region through target detection of the tile description information, wherein the candidate region possibly contains a tile;

and obtaining the graph information describing the graph blocks in the standard single drawing through the feature mapping of the candidate region.

According to an aspect of the embodiment of the present application, the performing of the structure information extraction on the standard individual drawing includes:

splitting the pattern blocks of the standard monomer drawing according to the layers to obtain pattern blocks placed on each layer;

and performing space disassembly and target extraction according to the space name and the wall line placed in the appointed layer to obtain the inter-bay space information.

According to an aspect of the embodiment of the application, the space disassembling and the target extraction are performed according to the space name and the wall line placed in the specified layer, and the inter-bay space information is obtained, including:

positioning a layer related to the space names on the standard monomer drawing, and extracting the space names of the bays from the layer;

performing spatial decomposition according to the wall lines in the layers related to the wall lines and the corresponding relation between the wall lines and the coordinates, and extracting an open space range corresponding to the space name for the decomposed open space;

extracting element information which is matched with the bay space range from the image blocks split by each image layer, wherein the element information describes elements distributed in the corresponding bay and coordinate positions of the elements;

and packaging the element information of the inter-opening space range according to a hierarchical relationship to generate inter-opening space information, wherein the inter-opening space information is used for describing elements in the inter-opening according to the hierarchy of the layer where the inter-opening space information is located.

According to an aspect of the embodiment of the present application, the summarizing intersecting elements of the segment belonging to the division to each layer of the standard single drawing under the control of the segment mask information according to the division space information obtained by extracting the structure information includes:

carrying out space attribution induction on the pattern block mask information on the standard monomer drawing to obtain a coordinate interval of the pattern block mask;

for each bay, matching elements described by corresponding bay space information to each layer of a standard monomer drawing by using the coordinate interval of the block mask to obtain a candidate layer belonging to the bay;

extracting elements intersecting a patch mask represented by the patch mask information from the candidate image layer.

According to an aspect of an embodiment of the application, the generating of tile-level information for the summarization of inter-related tiles through matching between the intersection element and a preconfigured standard tile comprises:

carrying out template matching on a new image block formed by the intersecting element set by taking a pre-configured standard image block as a template, and judging whether the template matching is successful or not;

if the template matching is successful and the new image block is matched with the pattern under the coordinate interval of the image block mask, generating image block level information of an image block to which an interval belongs for the intersected element, wherein the image block to which the interval belongs is a new image block formed by the intersected element;

correcting a tile position in the tile hierarchy information from a tile coarse position in the tile mask information to a corresponding coordinate position of the element in the inter-bay space information.

According to an aspect of an embodiment of the present application, the generating, through matching between the intersection element and the pre-configured standard tile, tile level information for the tile summary belonging to the bay further includes:

if the template matching fails, carrying out differential processing between a new image block formed by the intersected element set and the template to obtain a differential image;

and performing intersection element induction of the image blocks belonging to the bay under the control of the image block mask information again according to the difference image until a new image block formed by the intersection element set is successfully matched with the template and the new image block is matched with the pattern in the coordinate interval of the image block mask.

According to an aspect of an embodiment of the present application, a system for processing a standard monomer drawing, the system comprising:

the drawing obtaining module is used for obtaining a standard monomer drawing for which drawing verification is to be performed, wherein the standard monomer drawing is obtained by drawing through computer paper;

the processing module is used for extracting structural information and performing example segmentation on the standard monomer drawing, wherein the example segmentation is used for obtaining block mask information in the standard monomer drawing, and the block mask information is adapted to a pre-configured standard block;

the belonging induction module is used for inducing intersecting elements of the image blocks belonging to the bays to each image layer of the standard monomer drawing under the control of the image block mask information according to the bay space information obtained by extracting the structural information;

a matching module for generating tile level information for the tile summary belonging to the bay by matching between the intersecting elements and preconfigured standard tiles, the tile level information encapsulating all elements of the tiles;

and the standard single body information acquisition module is used for forming the image block level information of the standard single body through the image block level information of the image block to which the bay belongs, and the image block level information of the standard single body is used for executing the drawing verification of the standard single body drawing.

According to an aspect of the embodiments of the present application, a computer program medium has computer readable instructions stored thereon, which, when executed by a processor of a computer, cause the computer to perform any one of the methods described above.

In the embodiment of the application, for a given standard single drawing, namely a standard single drawing to be subjected to drawing auditing, structural information extraction and example segmentation are performed, block mask information in the standard single drawing is obtained through the example segmentation, the block mask information is adaptive to a pre-configured standard block, then according to bay space information obtained through the structure information extraction, intersecting elements of blocks belonging to bays are summarized to all layers of the standard single drawing under the control of the block mask information, block hierarchy information of the blocks belonging to the bays is generated through matching and summarization between the intersecting elements and the pre-configured standard blocks, finally, block hierarchy information of the standard single drawing is formed through the block hierarchy information of the blocks belonging to the bays, therefore, the blocks belonging to each bay in the standard single drawing are summarized to generate block hierarchy information, the block hierarchy information of the blocks belonging to the bays is generated to realize and guarantee packing and merging of discrete block elements, further, the dispersion of the block elements in the standard single drawing is eliminated, and the formed block hierarchy information of the standard single drawing can improve the practical usability and efficiency of the automatic auditing.

Other features and advantages of the present application will be apparent from the following detailed description, or may be learned by practice of the application.

It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the application.

Drawings

The above and other objects, features and advantages of the present application will become more apparent by describing in detail exemplary embodiments thereof with reference to the attached drawings.

Fig. 1 is an architecture applied to an embodiment of the present application.

FIG. 2 shows a flow diagram of a method of processing a standard monomer drawing according to one embodiment of the present application.

FIG. 3 illustrates a graph block diagram with rich lines and semantics according to one embodiment to be disclosed.

FIG. 4 shows a flow diagram of a method of processing a standard monomer drawing according to another embodiment of the present application.

Fig. 5 shows a flowchart of the step of extracting the graph information describing the tile from the standard single picture according to the embodiment of fig. 4.

Fig. 6 shows a flow chart of the step of performing structural information extraction on a standard monomer drawing according to fig. 2 in another embodiment.

Fig. 7 shows a flowchart describing steps of performing space decomposition and target extraction according to space names and wall lines placed in a specified layer to obtain bay space information according to an embodiment of the present application.

Fig. 8 is a flowchart illustrating a step of summarizing intersecting elements of blocks belonging to a bay to layers of a standard simplex drawing under control of block mask information according to bay space information obtained by extracting structural information according to an embodiment of the present application.

FIG. 9 shows a flow diagram of a method of processing a standard monomer drawing according to another embodiment of the present application.

FIG. 10 shows an overall architecture diagram according to one embodiment of the present application.

FIG. 11 shows a schematic diagram of an example segmentation model based on deep learning according to an embodiment of the present application.

FIG. 12 shows a schematic of a system for processing standard monomer drawings.

FIG. 13 is a diagram illustrating a hardware configuration of the intelligent processing tool of the embodiment.

Detailed Description

Example embodiments will now be described more fully with reference to the accompanying drawings. Example embodiments may, however, be embodied in many different forms and should not be construed as limited to the examples set forth herein; rather, these example embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the concept of example embodiments to those skilled in the art. The drawings are merely schematic illustrations of the present application and are not necessarily drawn to scale. The same reference numerals in the drawings denote the same or similar parts, and a repetitive description thereof will be omitted.

Furthermore, the described features, structures, or characteristics may be combined in any suitable manner in one or more example embodiments. In the following description, numerous specific details are provided to give a thorough understanding of example embodiments of the present application. One skilled in the relevant art will recognize, however, that the subject matter of the present application can be practiced without one or more of the specific details, or with other methods, components, steps, and so forth. In other instances, well-known structures, methods, implementations, or operations are not shown or described in detail to avoid obscuring aspects of the application.

Some of the block diagrams shown in the figures are functional entities and do not necessarily correspond to physically or logically separate entities. These functional entities may be implemented in the form of software, or in one or more hardware modules or integrated circuits, or in different networks and/or processor devices and/or microcontroller devices.

Referring to fig. 1, fig. 1 is a system architecture applied in the embodiment of the present application, where the system architecture may include an intelligent drawing processing tool 11 and an automatic drawing review platform 12 to which the intelligent drawing processing tool 11 is connected, where the intelligent drawing processing tool 11 is implemented by the method for processing a standard simplex drawing according to an embodiment of the present application, and the intelligent drawing processing tool 11 may be a plug-in tool of the automatic drawing review platform 12 or an independently deployed standard simplex drawing processing node, and regardless of the form of the intelligent drawing processing tool 11, the intelligent drawing processing tool is connected to the automatic drawing review platform 12, so as to implement data interaction between the two, and finally complete automatic review of a standard simplex drawing.

It should be understood that the drawing intelligent processing tool 11 of FIG. 1 and the architecture in which it resides are merely illustrative. The adjustment and the transformation can be carried out at will according to the implementation requirements.

Some of the solutions of the embodiments of the present application may be embodied based on the architecture shown in fig. 1 or a variant architecture thereof.

Referring to fig. 2, fig. 2 shows a flow diagram of a method of processing a standard monomer drawing according to one embodiment of the present application. The embodiment of the application provides a method for processing a standard monomer drawing, which comprises the following steps:

step S210, obtaining a standard monomer drawing to be subjected to drawing verification, wherein the standard monomer drawing is obtained by drawing through computer paper;

step S220, performing structural information extraction and example segmentation on the standard monomer drawing, wherein the example segmentation is used for obtaining pattern block mask information in the standard monomer drawing, and the pattern block mask information is adapted to a pre-configured standard pattern block;

step S230, summarizing intersecting elements of the corresponding pattern blocks of the bay to the standard monomer drawing under the control of the pattern block mask information according to the bay space information obtained by extracting the structural information;

step S240, generating image block level information for the image blocks belonging to the bay in a summarizing way through matching between the intersecting elements and the pre-configured standard image blocks, and packaging all elements of the image blocks by the image block level information;

and S250, forming the image block level information of the standard single body through the image block level information of the image block to which the bay belongs, wherein the image block level information of the standard single body is used for executing the drawing verification of the standard single body drawing.

These 5 steps are described in detail below.

In step S210, to implement automatic checking of a standard monomer drawing with high availability, a standard monomer drawing to be subjected to automatic drawing checking is first obtained, in other words, discrete block elements are summarized through execution of subsequent steps on a standard monomer drawing to be subjected to drawing checking by an automatic drawing checking platform, so as to package the discrete block elements for automatic drawing checking.

It should be noted that the standard monomer drawing is referred to for describing the design of a single building (structure) obtained by computer paper drawing.

In step S220, structure information extraction and example segmentation are performed on the standard individual drawing to be subjected to drawing verification. The structural information extraction is used for performing space disassembly and target extraction on the layers on the standard single drawing and the image blocks on the layers according to the structural information on the drawings such as the dotted-line relative relationship, so as to obtain the inter-division space information with the hierarchical relationship.

Example segmentation is used to extract tile mask information that fits recognizable tiles for a standard monomer drawing. The recognizable blocks refer to blocks with rich lines and semantics on a standard single drawing, for example, fig. 3 shows a block diagram with rich lines and semantics according to an embodiment to be disclosed, just as the blocks of the bed shown in fig. 3, for the blocks with rich lines and semantics, the block masks corresponding to the blocks and the corresponding classes and rough positions of the blocks can be extracted through execution of example segmentation, and then the corresponding block mask information is obtained.

Executing example division, and providing corresponding pattern block mask information for recognizable pattern blocks in the standard monomer drawing; and extracting the structural information by performing target extraction on the intervals distributed in the standard single drawing and the elements distributed in the intervals according to the levels, so that the structural information can describe the intervals distributed in the standard single drawing, the elements distributed on each layer and the coordinate positions of the elements.

It should be understood that, for the blocks with discrete elements thereon, since the blocks are not packaged together in the drawing process, it is often difficult to accurately identify and locate the discrete unpacked blocks for the performed structure information extraction, and therefore, the structure information extraction and the instance segmentation need to be performed on the standard single drawing synchronously to achieve the complete identification and accurate location of the blocks on the standard single drawing.

For example, the example segmentation of the standard monomer drawing may be implemented by a pre-configured deep learning network, i.e., an example segmentation network. Under the action of an example segmentation network, a standard monomer drawing is used as input, and pattern block mask information is generated through feature extraction, border regression and mask representation, so that segmentation and mask representation of recognizable pattern blocks in the standard monomer drawing are completed.

It should be noted that either the tiles in the standard simplex drawing or the tile masks in the tile mask information obtained from the example segmentation should be able to adapt to the pre-configured standard tiles. The block mask is obtained by identifying and extracting blocks which are rich in lines and have semantics on a standard monomer drawing, wherein the blocks can be discrete and unpacked blocks, although the blocks are not drawn according to the drawing specification, the blocks can be identified and extracted through example division to obtain the corresponding block mask, and therefore, the block mask is matched with a pre-configured standard block.

It should be added that, for the extraction of the structural information performed in step S220, after the inter-space information is obtained, extraction of semantic point and line planes is also performed, so as to reconstruct the tile level information of the standard cell.

The semantic point line surface refers to a simple line (point, line, surface) which has semantics but can not be effectively recognized through deep learning, such as a wall line, a kitchen table surface and the like, and because the image feature points are too few, the efficient recognition through the deep learning can not be performed. Just like the kitchen table top, which only draws a single line and cannot be identified according to the image characteristic points, the kitchen table top has a range of the surface because the kitchen table top is in the space area of the kitchen and is surrounded by the wall surface of the kitchen space, so that the kitchen table top can be identified according to objects such as a kitchen range, a hand sink and the like on the surface.

During the extraction of the structural information, the hierarchical information of the standard single body is finally constructed, which is embodied in that, according to the layer relationship, the obtained graphic block hierarchical information of the standard single body includes:

the topmost layer, namely the total information of the standard single drawing → the total information of each house type → the total information of each space → the information of the object in the space → the information of the child object on the object.

And extracting the structure information, namely identifying and positioning identifiable blocks for example segmentation, and on the other hand, forming the block level information of the standard single drawing together with the block level information obtained by example segmentation.

Referring to fig. 4, fig. 4 shows a flow chart of a method of processing a standard monomer drawing according to another embodiment of the present application. In this embodiment, the step S220 of executing example division on the standard monomer drawing may include the following steps:

step S221a, all layers of the standard monomer drawing are combined to obtain a standard monomer picture;

step S222a, extracting graph line information describing a graph block from a standard single picture;

step S223a, obtaining a target area corresponding to the image block through frame regression of the graph line information;

in step S224a, performing mask representation of the target region to generate block mask information in the standard single drawing, where the block mask information includes block masks, categories, and rough block positions corresponding to block bounding boxes.

These steps are described in detail below.

In step S221a, as indicated above, the standard single drawing is drawn by the CAD tool series via the computer, so that the standard single drawing is composed of several layers, each layer is disposed with several tiles thereon, it should be noted that, of course, a tile may have sub-tiles, but sub-tiles may be disposed on other layers, and a tile has a reference relationship with the sub-tiles.

In other words, for a layer, a plurality of layers of the standard single drawing are provided with a plurality of blocks, wherein some blocks are blocks which contain elements packaged under the standard drawing, and some blocks are blocks which have discrete elements and are not packaged.

For example segmentation oriented to pictures, a standard monomer drawing is not processable, and therefore, all layers of the standard monomer drawing need to be merged, so that a standard monomer picture describing image blocks included in all layers in picture content is obtained.

And (4) merging all layers of the standard single drawing, and deriving a picture for inputting a subsequent example segmentation network for prediction.

In step S222a, the standard single picture is used as an input of the example segmentation network, and the example segmentation network first performs extraction of initial picture features for the standard single picture, so as to obtain graph information describing a graph block. The graph information is used as the description of the graph blocks in the standard single picture and is used as the input of the feature map generated by extracting the features.

Referring also to fig. 5, fig. 5 is a flowchart illustrating a step of extracting graph information describing a tile from a standard single picture according to an embodiment of fig. 4. In this embodiment, the step S222a of extracting the graph information describing the graph block from the standard single picture may include the following steps:

step S301, encoding the standard monomer picture through an encoding-decoding frame to obtain the image block description information in the standard monomer picture;

step S302, performing target detection through the image block description information to generate a candidate region, wherein the candidate region possibly comprises an image block;

step S303, obtaining the graph information describing the graph blocks in the standard monomer drawing through the feature mapping of the candidate region.

These steps are described below.

In step S301, the standard monomer picture is encoded by an Encoder-Decoder model under an encoding-decoding framework, and the standard monomer picture is converted into a fixed-length sequence, and the standard monomer picture is encoded by the Encoder, and a fixed-length sequence vector, that is, the tile description information in the standard monomer picture, is output by the Encoder.

In step S302, by performing object detection, a candidate region prediction that may include a tile is performed based on the tile description information. Illustratively, the process is implemented by using the coded tile description information as an input through a two-stage network of a two-stage model, i.e., mask RCNN.

In step S303, the image feature extraction of the standard single image is completed through the feature mapping performed by the candidate region, and then the image line information for describing the image blocks in the standard single image is obtained.

It should be understood that, for the standard single drawing, any drawing block on any drawing layer is formed by a line, and the drawing block in the standard single drawing can be accurately described through the drawing line information.

In step S223a, for the graph information extracted from the standard single picture to describe the tile, the target region corresponding to the tile in the standard single picture will be obtained by performing border regression.

In the example segmentation network, the frame regression is performed through the RPN network. And processing a characteristic diagram generated by the processing of the core bone network, namely the backhaul, namely the graph line information describing the graph blocks through an RPN network, so as to obtain a target area corresponding to the graph blocks in the standard monomer drawing under the control of a loss function.

In step S224a, the block mask information in the standard cell drawing is generated by the mask representation, i.e. ROI Align process, performed on the target region. The ROI Align process comprises an execution process of sampling of non-uniform points and bilinear interpolation, and through the process, on one hand, a tile block mask corresponding to a tile block boundary box is generated, and on the other hand, the tile block is used as a target to obtain an attributive class and a rough location of the tile block.

For the blocks that can be identified and located by the example segmentation, namely the blocks with rich lines and semantics as indicated in the foregoing, the classes corresponding to the blocks to be identified and the rough positions of the blocks are represented by masks, so that the coordinate positions of the blocks can be obtained through the inter-space information obtained by the structure information extraction.

Therefore, example segmentation is realized for the standard single drawing, and then the mask of the image blocks, the category of the image blocks and the rough position of the image blocks are obtained for the recognizable image blocks.

Referring to fig. 6, fig. 6 shows a flowchart of the step of performing structural information extraction on a standard monomer drawing in accordance with fig. 2 in another embodiment. In this embodiment, the step S220 of performing the structure information extraction on the standard monomer drawing may include the following steps:

step S221b, splitting the pattern blocks of the standard monomer drawing according to the layers to obtain pattern blocks placed on each layer;

step S222b, performing space disassembly and target extraction according to the space name and the wall line placed in the specified layer, and obtaining the inter-opening space information.

These steps are described below.

In step S221b, most of the tiles of the same type are placed in the same layer, the tiles are split according to the layer, so that a plurality of tiles corresponding to the same layer are obtained by splitting currently, that is, tiles placed in each layer are obtained, thereby providing assistance and convenience for subsequently executed tile identification.

In step S222b, it should be noted that, for the standard simplex drawing, the image blocks placed on each layer belong to the same category, specifically, the standard simplex drawing includes a layer related to space names and a layer related to wall lines, where the layer related to space names is a layer on which the space names of the respective intervals are placed, and the layer related to wall lines is used for placing, forming, and partitioning the wall lines of the respective intervals.

And according to the wall lines distributed on the appointed layer and the corresponding relation between the wall lines and the coordinates, performing space disassembly for the existing bays so as to obtain bay space ranges, and mapping the bay space ranges with space names.

And for each bay, taking the bay space range as a limit, taking the space name of each bay and the elements arranged in the bay as targets, and executing target extraction to obtain the element information of each bay. The element information of each bay describes elements arranged in the bay and coordinate positions of the elements; and packing the element information of each bay according to the hierarchical relationship to obtain the bay space information of the standard monomer drawing.

Referring also to fig. 7, fig. 7 is a flowchart illustrating steps of performing space decomposition and target extraction according to space names and wall lines placed in a specified layer to obtain bay space information according to an embodiment of the present application. In this embodiment, the step S222b of performing space decomposition and target extraction on the space name and the wall line placed in the specified layer to obtain the inter-bay space information may include the following steps:

step S401, in the map layer related to the standard monomer drawing positioning space name, extracting the space name of each bay from the map layer.

Step S402, performing space disassembly according to the layer related to the wall line and the corresponding relation between the layer and the coordinate, and extracting an open space range corresponding to the space name for the disassembled open space;

step S403, extracting element information which is adapted to the space range of the bay from the image blocks split by each image layer, wherein the element information describes elements distributed in the corresponding bay and coordinate positions of the elements;

step S404, packing the element information of the inter-space range according to the hierarchical relationship to generate inter-space information, wherein the inter-space information is used for describing the elements in the inter-space according to the hierarchy of the layer where the inter-space information is located.

These steps are described below.

In step S401, similar blocks in the standard simplex drawing are placed in the same layer. The standard monomer drawing is used for realizing a standard monomer, for example, a building structural design, which describes elements such as a booth in which the standard monomer is arranged and an article table top in the booth in a line form; in addition, the space name corresponding to each bay also exists in a layer in the form of a graphic block.

Based on the method, the space names of the bays are extracted in the layer by positioning the layer related to the space names in the standard single drawing, and the extracted space names are used for marking the information related to the bays.

In step S402, the standard cells are spatially disassembled in units of bay by the execution of step S402, so as to obtain the bay space distributed in the drawing of the standard cells and the corresponding relationship between the bay space and the coordinates.

For example, in a standard monomer drawing, the layer associated with a wall line may be a "build-wall-brick" layer, and the "build-wall-brick" layer is placed with wall lines. And (3) performing spatial decomposition on the wall surface line drawn on the 'building-wall-brick' layer according to the corresponding relation between the wall surface line and the coordinates to obtain the bay distribution of the standard monomers and the coordinate range mapped on the coordinates by each bay, thereby extracting and obtaining the bay spatial range, and associating the bay spatial range with the corresponding spatial name.

In step S403, it should be understood that each bay has various items, table tops, and other elements, and therefore, according to the bay space range, information corresponding to the items, table tops, and other elements belonging to the bay space range is extracted from the image blocks split in the remaining image layers, for example, the furniture image layer, the sanitary ware image layer, and the like, that is, the element information adapted to the bay space range corresponding to each bay is extracted from the image blocks split in the image layers.

The extracted element information describes which article table tops are arranged in the corresponding bay on one hand, and records the coordinate positions of the article table tops on the other hand. Therefore, the obtained coordinate position is obtained based on the corresponding relation between the element and the coordinate, so that the coordinate position obtained through the extracted element information is an accurate position for the element and the image block where the element is located.

In step S404, adapting the inter-bay space range to extract the image blocks from each image layer, so that the obtained element information has a hierarchical relationship in which the elements are all disposed on each image layer, and therefore, the element information of the inter-bay space range corresponding to each inter-bay is packed according to the hierarchical relationship to generate the inter-bay space information through the execution of step S404, so that the inter-bay space information can describe the elements in the inter-bay according to the hierarchy of the image layer where the inter-bay space information is disposed.

The bay space information will contain information of all objects, table tops in the bay space. It should be noted that the hierarchical relationship of the inter-bay space information is represented by indicating the information of various objects and tables in the inter-bay space, and the information of sub-objects on the objects and tables, and the hierarchical relationship between the object tables and the sub-objects exists and is referred to each other.

In step S230, for each bay determined by the space decomposition, the bay space information obtained by extracting the structure information is combined to summarize and fuse the space attribute of the block mask information to the standard simplex drawing, and the elements which are combined and packed together and intersect with the block masks in the block mask information are obtained.

And the pattern block mask information is rough information which is obtained by deep learning prediction of example segmentation and can identify the pattern block. Through the spatial subsumption, the coordinate interval of the block mask contained in the block mask information is obtained, and the coordinate interval indicates the coordinate range covered by the block mask.

And then finding a layer related to the block mask in the standard single drawing by utilizing the block mask coordinate interval obtained by induction, namely the layer containing the block with the intersection with the block mask coordinate interval, and extracting the layer as a candidate layer.

And finally extracting the image blocks which have intersection with the coordinate intervals of the image block mask or point-line planes, namely intersection elements from the candidate image layers.

Through the execution of the step S230, the summary of the segment to which the bay belongs is realized, and the segment to which the bay belongs is a segment matched with the segment mask, and is also a discrete and unpacked segment in the standard simplex drawing.

With continuing reference to fig. 8, fig. 8 is a flowchart illustrating a step of summarizing intersecting elements of blocks belonging to a bay to layers of a standard simplex drawing under control of block mask information according to bay space information obtained by structure information extraction according to an embodiment of the present application. In this embodiment, the step S230 of summarizing intersecting elements of the corresponding drawing blocks in the division to each drawing layer of the standard simplex drawing under the control of the drawing block mask information according to the division space information extracted from the structure information may include the following steps:

step S231, carrying out space attribution induction of the pattern block mask information on the standard monomer drawing to obtain a coordinate interval of the pattern block mask;

step S232, for each bay, matching elements described by corresponding bay space information to each layer of the standard monomer drawing by using the coordinate interval of the block mask to obtain candidate layers belonging to the bay;

in step S233, elements intersecting the patch mask represented by the patch mask information are extracted from the candidate layer.

These steps are described below.

In step S231, as described above, the tile mask information includes the tile mask, the category, and the rough location of the tile, and the execution of step S231 can spatially summarize the tile mask on the standard simplex drawing to obtain the coordinate interval of the tile mask. And the coordinate interval of the block mask is the coordinate range covered by the corresponding block in the standard monomer drawing.

In step S232, after the coordinate interval of the tile mask is obtained through the induction, matching between the coordinate interval of the tile mask and the element described by the interval space information may be performed on the standard single drawing, so as to obtain a tile including a tile intersecting with the tile mask, and use this layer as a candidate layer.

In step S233, the intersecting elements are extracted from the candidate layers with respect to the patch mask represented by the patch mask information. It should be appreciated that for a tile mask, its intersecting elements will be packed and merged into a new tile, thereby eliminating discrete and unpacked tiles in the standard simplex drawing that do not meet the drawing specification.

In step S240, matching is performed between the intersection elements extracted through a tile mask and the pre-configured standard tiles for the intersection elements, i.e., the elements matching the tile mask, so as to obtain the tile level information of the tiles belonging to the inter-division.

The tile hierarchy information of the tile to which the bay belongs refers to the tile to which the bay belongs, the elements presented in a hierarchical relationship and referenced to each other, and the tile location. Therefore, the segment to which the bay belongs corresponds to the discrete and unpacked segment in the standard single drawing.

Therefore, for discrete and unpacked blocks in the standard single drawing, the block level information of the blocks to which the interlude belongs is generalized and generated through the continuous matching between the intersected elements and the preset standard blocks.

By now, it should be noted that, for facilitating the implementation of the matching process, matching between the extracted intersecting elements and the pre-configured standard tiles may be implemented after merging and packaging, so as to ensure consistency and accuracy of matching.

The matching between the intersecting elements and the pre-configured standard tiles is used for searching all elements for the discrete and unpacked tiles, so that the matched elements are completely adapted to the discrete and unpacked tiles, and the integrity of the obtained elements is guaranteed for the tiles.

Under the matching of the intersected elements and the pre-configured standard image blocks, image block level information is generated by summarizing the image blocks belonging to each bay, if the matching is unsuccessful, the elements are summarized again, missing or redundant elements such as the missing image blocks or point and line surfaces are searched, and then the intersected elements are obtained again for matching until the matching is successful.

Illustratively, the basis for the re-induction of elements is that the new tiles formed by the intersecting elements can be matched to the pattern under the coordinate bin of the tile mask. For the intersecting elements successfully matched with the pre-configured standard image blocks, if the similarity between the intersecting elements and the patterns under the coordinate intervals of the image block masks is too low, the induction is illustrated, namely the induction of the intersecting elements obtained by induction is wrong, and the induction of the elements needs to be performed again.

Continuing still with FIG. 9, FIG. 9 shows a flow diagram of a method of processing standard monomer drawings in accordance with another embodiment of the present application. In this embodiment, the step S240 of generating the tile level information for summarizing the tiles belonging to the bay through matching between the intersecting elements and the preconfigured standard tiles may include the following steps:

step S241, taking a pre-configured standard image block as a template, carrying out template matching on a new image block formed by the intersecting element set, judging whether the template matching is successful, if so, executing step S242, and if not, executing step S244;

step S242, if the template matching is successful and the new image block is matched with the pattern in the coordinate interval of the image block mask, generating image block level information of the image block to which the interlude belongs for the intersected elements, wherein the image block to which the interlude belongs is the new image block formed by the intersected elements;

step S243, correcting the image block position in the image block layer level information from the image block rough position in the image block mask information to the corresponding coordinate position of the element in the inter space information;

step S244, if the template matching fails, carrying out differential processing between a new image block formed by the intersecting element set and the template to obtain a differential image;

step S245, the induction of the intersecting elements of the segment under the control of the segment mask information is executed again according to the difference image until the new segment formed by the intersecting element set is successfully matched with the template and the new segment is matched with the pattern in the coordinate interval of the segment mask.

These steps are described below.

In step S241, the matching between the pre-configured standard tile and the new tile formed by the intersecting element set can be implemented by using an algorithm such as ORB (ordered FAST and rotaed BRIEF).

In step S242, if the new tile in the shape of the set of intersecting elements is successfully matched, further determining whether the pattern formed by the intersecting elements is similar to the pattern in the coordinate interval of the tile mask, and if the pattern formed by the intersecting elements is similar to the pattern in the coordinate interval of the tile mask, it indicates that there is no missing or redundant portion of the intersecting elements for the discrete unpacked tile; if the similarity between the pattern formed by the intersecting elements and the pattern in the coordinate interval of the block mask is too low, it indicates that the generalization of the elements is missed, and the generalization of the elements needs to be performed again through the execution of step S244 and step S245.

To this end, the intersection elements resulting from the successful match are generated as tile level information for the inter-tile belonging tile, i.e., the new tile. The elements described by the tile hierarchy information are distributed in different layers, so the elements and the location description are performed according to a hierarchical relationship.

In step S243, for the obtained new tile, the position thereof is determined by the matched tile mask, i.e., the coarse position of the tile mask obtained by the example segmentation. However, in terms of the problem of image block positioning, a computer vision recognition technology based on deep learning is adopted, that is, the error of example segmentation is far greater than the coordinate precision required by normative review of drawings, and in order to compensate for the image block positioning with rough example segmentation, the obtained mask coordinates, that is, the coordinate positions of the extracted intersecting elements under the image block mask coordinate interval obtained by summarizing the rough image block position through the space, are required.

In step S244, if the template matching fails, a difference image is obtained by performing a difference process on the new tile and the template. It should be appreciated that the difference image indicates the difference of the new tile with respect to the template, and therefore, the intersection element generalization of the interdependent subordinate tile of step S245 can be performed again from the difference image.

In the execution of step S245, based on the difference of the new tile indicated by the difference image with respect to the template, generalization of the intersecting elements is performed again through the tile mask until the pattern of the new tile that can be formed collectively can match the pattern in the coordinate section of the tile mask.

In step S250, the block level information of the standard single block is finally formed according to the block level information of the blocks belonging to all the bays, so as to provide discrete and packaged blocks and accurate positions for the subsequent standard single block drawing audit, and further meet the drawing normative audit requirements and adapt to the CAD standard single block drawing audit rules for automatic audit.

The following describes the processing procedure performed before the automatic review by the computer, taking a standard monomer drawing as an example.

After a designer has made a standard one-piece design drawing through a CAD tool family, because of the flexibility of the CAD tool family, the designer's drawing specifications are not constrained enough during the drawing process, e.g., the elements of the tiles are often not packed together, which results in poor generalization of automated review by computers and poor usability in the actual "drawing-reviewing" flow.

On the basis, a computer vision identification technology is introduced and applied to the checking of the CAD standard monomer drawing so as to solve the problem of identifying and positioning unpacked dispersed image blocks in the standard monomer drawing, thereby carrying out the normative checking of the standard monomer drawing.

Specifically, referring to fig. 10, fig. 10 shows an overall architecture diagram according to an embodiment of the present application. As shown in fig. 10, a CAD standard monomer drawing is used as an input, and CAD information extraction and analysis, i.e., structure information extraction, and example segmentation based on deep learning are performed on the standard monomer drawing in parallel, so that on one hand, for the patches formed by discrete unpacked elements, the patches can be identified and merged through the execution of example segmentation; on the other hand, the defect that the positions of the image blocks cannot be accurately identified by a computer vision identification technology is overcome by extracting and analyzing CAD information, and the rough coordinate positions extracted by example segmentation, namely the rough positions of the image blocks, are provided while corresponding image blocks are identified and extracted, and the accurate positions are provided.

For the CAD standard monomer drawing to be subjected to normative review, the extraction and analysis of the CAD information comprise the following processes which are sequentially executed, namely:

the method comprises the steps of splitting image blocks according to image layers, extracting inter-opening space information, extracting semantic point and line surfaces and constructing single image block level information.

The extracted inter-space information is introduced into information fusion between the single block image block level information obtained by executing the CAD information extraction and analysis and the block mask information obtained by the example segmentation, so as to finally obtain the accurate standard single block image block level information, namely the aforementioned layer information of the standard single block.

For the CAD standard single drawing to be subjected to normative review, the example segmentation is carried out, after all the layers are combined to derive the pictures, rough information obtained by identifying and positioning discrete unpacked blocks is output through the example segmentation based on deep learning, namely identifiable block mask information.

As indicated previously, the output of the instance segmentation and CAD information extraction and analysis, both, is used to obtain the intersecting elements corresponding to the tile masks by performing information fusion, and the intersecting elements will be confirmed by matching with standard tiles to form new tiles, completing the packing and positioning of the discrete unpacked tiles.

It should be added that, for the information fusion, the process of performing spatial attribution induction and extracting the candidate layer is performed.

Thereby, the intersecting elements of the block mask represented by the block mask information can be obtained. And performing template matching on the intersected elements and the standard image blocks after merging and packaging, and continuously performing matching to obtain accurate information, namely accurate hierarchical information of the standard single image blocks.

Referring also to fig. 11, fig. 11 shows a schematic diagram of an example segmentation model based on deep learning according to an embodiment of the present application. Illustratively, as shown in FIG. 11, example segmentation models include a Backbone (core bone network), two-stage (two-stage) and three-head (head) network.

The core bone network is based on a UNet network structure and used for extracting graph line information of a graph block, and the three-head network respectively outputs a graph block mask, a class and rectangular frame coordinates.

Therefore, by the implementation, the obtained layer information of the standard monomer is equivalent to equivalently converting the design drawing of the standard monomer into logic information which can be identified and analyzed by a computer, so that manual work can be replaced in subsequent drawing verification, and the labor cost is greatly reduced.

Through the implementation, the computer vision technology based on CAD structure information extraction and the deep learning neural network is integrated for automatic verification of drawings, the condition that machine analysis is influenced but not wrong mapping is reduced, the mapping requirement is reduced, the generalization capability is greatly enhanced, higher usability is obtained, the requirement on mapping is lower, the requirement on verification operation is less, and the verification is more intelligently realized.

Referring to fig. 12, according to an embodiment of the present application, fig. 12 provides a system for processing a standard cell drawing, wherein the system for processing a standard cell is integrated in the drawing intelligent processing tool 11 in fig. 1, and the system for processing a standard cell includes:

a drawing obtaining module 510, configured to obtain a standard monomer drawing to be subjected to drawing verification, where the standard monomer drawing is obtained by computer paper drawing;

a processing module 520, configured to perform structure information extraction and example segmentation on the standard monomer drawing, where the example segmentation is used to obtain tile mask information in the standard monomer drawing, and the tile mask information is adapted to a preconfigured standard tile;

the attribution summarizing module 530 is configured to summarize intersecting elements of the attributed drawing blocks of the division to each drawing layer of the standard monomer drawing under the control of the drawing block mask information according to the division space information obtained by extracting the structure information;

a matching module 540 for generating tile-level information for a summary of tiles belonging to a bay by matching between the intersecting elements and preconfigured standard tiles, the tile-level information encapsulating all elements of the tiles;

and a standard single block information obtaining module 550, configured to form the block level information of the standard single block according to the block level information of the block to which the bay belongs, where the block level information of the standard single block is used to perform the drawing audit of the standard single block drawing.

In one embodiment, the processing module 520 includes:

In one embodiment, the extracting of the graph information describing the tile from the standard single picture includes:

In one embodiment, the processing module 520 includes:

splitting the pattern blocks of the standard monomer drawing according to the pattern layers to obtain pattern blocks placed on each pattern layer;

In an embodiment, the performing space dismantling and target extraction according to the space name and the wall line placed in the specified layer to obtain the inter-bay space information includes:

In one embodiment, the summarization module 530 comprises:

In one embodiment, the generating tile level information for the tile summary belonging to the bay by matching between the intersecting elements and the preconfigured standard tiles comprises:

carrying out template matching on a new image block formed by an intersecting element set by taking a pre-configured standard image block as a template, and judging whether the template matching is successful or not;

if the template matching is successful and the new image block is matched with the pattern under the coordinate interval of the image block mask, generating image block level information of an inter-division affiliated image block for the intersected elements, wherein the inter-division affiliated image block is a new image block formed by the intersected elements;

In one embodiment, the generating tile level information for the tile summary belonging to the bay by matching between the intersecting elements and the preconfigured standard tiles further comprises:

if the template matching fails, carrying out differential processing between a new image block formed by the intersecting element set and the template to obtain a differential image;

The method for processing the standard monomer drawing according to the embodiment of the application can be realized by the drawing intelligent processing tool 11 shown in fig. 13. The intelligent drawing processing tool 11 according to the embodiment of the present application is described below with reference to fig. 13. The intelligent processing tool 11 shown in fig. 13 is only an example, and should not bring any limitation to the functions and the scope of use of the embodiments of the present application.

As shown in FIG. 13, the intelligent processing tool 11 is embodied in the form of a general purpose computing device. The components of the drawing intelligent processing tool 11 may include, but are not limited to: the at least one processing unit 810, the at least one memory unit 820, and a bus 830 that couples the various system components including the memory unit 820 and the processing unit 810.

Wherein the storage unit stores program code that can be executed by the processing unit 810, such that the processing unit 810 performs the steps according to various exemplary embodiments of the present invention described in the description part of the above exemplary methods of the present specification. For example, the processing unit 810 may perform various steps as shown in fig. 2.

The storage unit 820 may include readable media in the form of volatile memory units such as a random access memory unit (RAM) 8201 and/or a cache memory unit 8202, and may further include a read only memory unit (ROM) 8203.

The storage unit 820 may also include a program/utility 8204 having a set (at least one) of program modules 8205, such program modules 8205 including, but not limited to: an operating system, one or more application programs, other program modules, and program data, each of which, or some combination thereof, may comprise an implementation of a network environment.

Bus 830 may be any of several types of bus structures including a memory unit bus or memory unit controller, a peripheral bus, an accelerated graphics port, a processing unit, or a local bus using any of a variety of bus architectures.

The drawing intelligent processing tool 11 may also communicate with one or more external devices 700 (e.g., keyboard, pointing device, bluetooth device, etc.). Such communication may occur via an input/output (I/O) interface 650. Also, base station 11 may communicate with one or more networks (e.g., a Local Area Network (LAN), a Wide Area Network (WAN) and/or a public network such as the Internet) via network adapter 860. As shown, a network adapter 860 communicates with the other modules of the automated review platform 12 via bus 830. It should be understood that, although not shown in the figures, other hardware and/or software modules may be used in conjunction with the drawing intelligent processing tool 11, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems, among others.

Through the above description of the embodiments, those skilled in the art will readily understand that the exemplary embodiments described herein may be implemented by software, or by software in combination with necessary hardware. Therefore, the technical solution according to the embodiments of the present application may be embodied in the form of a software product, which may be stored in a non-volatile storage medium (which may be a CD-ROM, a usb disk, a removable hard disk, etc.) or on a network, and includes several instructions to enable a computing device (which may be a personal computer, a server, a terminal device, or a network device, etc.) to execute the method according to the embodiments of the present application.

In an exemplary embodiment of the present application, there is also provided a computer program medium having stored thereon computer readable instructions which, when executed by a processor of a computer, cause the computer to perform the method described in the above method embodiment section.

According to an embodiment of the present application, there is also provided a program product for implementing the method in the above method embodiment, which may employ a portable compact disc read only memory (CD-ROM) and include program code, and may be run on a terminal device, such as a personal computer. However, the program product of the present invention is not limited in this regard and, in the present document, a readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device.

The program product may employ any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. The readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples (a non-exhaustive list) of the readable storage medium include: an electrical connection having one or more wires, a portable disk, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

A computer readable signal medium may include a propagated data signal with readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take any of a variety of forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A readable signal medium may also be any readable medium that is not a readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device.

Program code embodied on a readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

Program code for carrying out operations for aspects of the present invention may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, C + + or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computing device, partly on the user's device, as a stand-alone software package, partly on the user's computing device and partly on a remote computing device, or entirely on the remote computing device or server. In the case of a remote computing device, the remote computing device may be connected to the user computing device through any kind of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or may be connected to an external computing device (e.g., through the internet using an internet service provider).

It should be noted that although in the above detailed description several modules or units of the device for action execution are mentioned, such a division is not mandatory. Indeed, the features and functionality of two or more modules or units described above may be embodied in one module or unit, according to embodiments of the application. Conversely, the features and functions of one module or unit described above may be further divided into embodiments by a plurality of modules or units.

Moreover, although the steps of the methods herein are depicted in the drawings in a particular order, this does not require or imply that the steps must be performed in this particular order, or that all of the depicted steps must be performed, to achieve desirable results. Additionally or alternatively, certain steps may be omitted, multiple steps combined into one step execution, and/or one step broken down into multiple step executions, etc.

Through the above description of the embodiments, those skilled in the art will readily understand that the exemplary embodiments described herein may be implemented by software, and may also be implemented by software in combination with necessary hardware. Therefore, the technical solution according to the embodiments of the present application can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a usb disk, a removable hard disk, etc.) or on a network, and includes several instructions to enable a computing device (which can be a personal computer, a server, a mobile terminal, or a network device, etc.) to execute the method according to the embodiments of the present application.

Other embodiments of the present application will be apparent to those skilled in the art from consideration of the specification and practice of the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of the invention following, in general, the principles of the application and including such departures from the present disclosure as come within known or customary practice within the art to which the invention pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the application being indicated by the following claims.

Claims

1. A method of processing a standard monomer drawing, the method comprising:

2. The method of claim 1, wherein the performing instance segmentation on the standard monomer drawing comprises:

3. The method of claim 2, wherein the extracting of the graph information describing the tile from the standard monomer picture comprises:

coding the standard monomer picture through a coding-decoding frame to obtain the picture block description information in the standard monomer drawing;

and obtaining the graph information describing the graph blocks in the standard monomer drawing through the feature mapping of the candidate region.

4. The method of claim 1, wherein the performing structural information extraction on the standard monomer drawing comprises:

5. The method according to claim 4, wherein the performing space decomposition and target extraction according to the space name and the wall line placed in the specified layer to obtain the inter-opening space information comprises:

positioning a layer related to the space name on the standard monomer drawing, and extracting the space name of each bay from the layer;

performing space disassembly according to the layer related to the wall surface line and the corresponding relation between the layer and the coordinate, and extracting an inter-bay space range corresponding to the space name for the inter-bay space obtained by the disassembly;

and packaging the element information of the inter-bay space range according to a hierarchical relationship to generate inter-bay space information, wherein the inter-bay space information is used for describing elements in the inter-bay according to the hierarchy of the layer where the inter-bay space information is located.

6. The method as claimed in claim 1, wherein the summarizing intersecting elements of the blocks belonging to the bays to each layer of the standard single drawing under the control of the block mask information according to the bay space information extracted from the structure information comprises:

carrying out space attribution induction of the block mask information on the standard monomer drawing to obtain a coordinate interval of the block mask;

extracting elements from the candidate layers that intersect a tile mask represented by the tile mask information.

7. The method of claim 1, wherein generating tile level information for a tile summary belonging to a bay by matching between the intersecting elements and preconfigured standard tiles comprises:

8. The method of claim 7, wherein generating tile level information for a tile summary belonging to a bay by matching between the intersecting elements and preconfigured standard tiles, further comprises:

and carrying out induction of intersecting elements of the image blocks under the control of the image block mask information according to the difference image again until a new image block formed by the intersecting element set is successfully matched with the template and the new image block is matched with the pattern in the coordinate interval of the image block mask.

9. A system for processing standard monomer drawings, the system comprising:

the attribution summarizing module is used for summarizing intersecting elements of the attributive image blocks of the bays to each image layer of the standard monomer drawing under the control of the image block mask information according to the bay space information obtained by extracting the structure information;

a matching module for generating tile level information for the generalization of inter-related tiles by matching the intersecting elements with preconfigured standard tiles, the tile level information encapsulating all elements of the tiles;

10. A computer program medium having computer readable instructions stored thereon, which when executed by a processor of a computer, cause the computer to perform the method of any one of claims 1-8.