Information extraction method, system, storage medium and device based on architectural drawings

Abstract

The present invention discloses an information extraction method, system, storage medium and device based on architectural drawings, the method comprising: obtaining a preset format file storing drawings, parsing the preset format file to obtain multiple architectural drawings; analyzing the multiple architectural drawings to determine the target architectural drawings where the design instructions are located from the multiple architectural drawings; identifying the target architectural drawings to obtain the number of columns and the column positions of the target architectural drawings; extracting information from the target architectural drawings in a preset order according to the number of columns and the column positions. The present invention solves the problem of low accuracy in the prior art when extracting information from the design instructions in the architectural drawings.

Description

Technical Field

[0001] The present invention relates to the technical field of information extraction, and in particular to an information extraction method, system, storage medium and device based on architectural drawings. Background Art

[0002] With economic development and urbanization, a large number of CAD architectural design drawings will be generated in every city's construction projects. Whether the manually designed CAD drawings meet the national construction review standards currently requires experienced engineers to manually review. However, the diversity of CAD engineering drawings and the complexity of the review rules lead to problems such as large workload, high cost, low efficiency, and unavoidable omissions in manual review, which in turn lead to delays in construction and waste of funds. On the other hand, with the development of artificial intelligence technology, artificial intelligence can already solve problems in relatively complex industrial fields. It has become a trend to use artificial intelligence technology to improve the accuracy and efficiency of drawing review. Through intelligent drawing review, the time and personnel for checking drawings can be reduced, the time for closed review can be shortened, the labor cost can be reduced, the quality of drawings can be improved, and the delays in construction and the high cost of capital turnover caused by drawing quality problems during the construction phase can be reduced.

[0003] Design description is an important part of CAD drawings, the outline of construction drawings, the description of drawings, quantity orders, and practices that are not fully expressed, and the explanation of solutions to issues that the review agency is concerned about. During the strong clause verification process, the reviewer needs to judge whether the drawing design complies with the national building review specifications based on the design description, such as judging whether the design is made according to the design data recognized by the power supply, communication, and fire departments based on the "design basis". Therefore, the automatic extraction of design descriptions is an important step in intelligent review.

[0004] In the prior art, there are development difficulties in how to automatically extract design specifications from CAD drawings. This is because computers cannot automatically obtain column layout information, and most computers read design specifications in a fixed column manner. Due to the different column layout habits of different design institutes and designers, and the inconsistent design specification writing templates, it is easy to cause inaccurate information extraction from architectural drawings. Summary of the invention

[0005] In view of this, the purpose of the present invention is to provide an information extraction method, system, storage medium and device based on architectural drawings, aiming to solve the problem of low accuracy in the prior art when extracting information from design specifications in architectural drawings.

[0006] The embodiment of the present invention is implemented as follows: a method for extracting information based on architectural drawings, the method comprising:

[0007] Acquire a preset format file storing drawings, and parse the preset format file to obtain a plurality of architectural drawings;

[0008] Analyzing the plurality of architectural drawings to determine a target architectural drawing where the design specification is located from the plurality of architectural drawings;

[0009] Identify the target architectural drawing to obtain the number of columns and column positions of the target architectural drawing;

[0010] Information is extracted from the target building drawing in a preset order according to the number of columns and the positions of the columns.

[0011] Furthermore, in the above-mentioned information extraction method based on architectural drawings, the step of analyzing the plurality of architectural drawings to determine the target architectural drawing where the design specification is located from the plurality of architectural drawings comprises:

[0012] The drawing name information of the plurality of architectural drawings is obtained, and the target architectural drawing where the design specification is located is determined according to the drawing name information.

[0013] Furthermore, in the above-mentioned information extraction method based on architectural drawings, before the step of identifying the target architectural drawing to obtain the number of columns and the position of the columns of the target architectural drawing, the method further includes:

[0014] The target architectural drawing is converted into a preset format.

[0015] Furthermore, in the above-mentioned information extraction method based on architectural drawings, the step of identifying the target architectural drawings to obtain the number of columns and the positions of the columns of the target architectural drawings comprises:

[0016] Converting the target building drawing into a grayscale image, performing binary inversion processing on the grayscale image to obtain a binary image, and obtaining the number of black pixels in each column of the binary image;

[0017] Creating a blank image that is the same size as the target architectural drawing, and filling the blank image according to the number of black pixels in each column of the binary image;

[0018] The filled blank image is closed and then inverted into a binary image, and the image contour after the binary image processing is detected, and the number of columns of the target building drawing is determined according to the number of image contours.

[0019] Furthermore, the above-mentioned information extraction method based on architectural drawings, wherein the step of performing a closing operation on the filled blank image and then performing an inverted binary image processing, detecting the image contour after the binary image processing, and determining the number of columns of the target architectural drawing according to the number of image contours, further comprises:

[0020] The burrs and small bridges in the white area of ​​the blank image after the closing operation are removed.

[0021] Furthermore, in the above-mentioned information extraction method based on architectural drawings, the step of identifying the target architectural drawings to obtain the number of columns and the positions of the columns of the target architectural drawings comprises:

[0022] Obtaining the minimum circumscribed moment of each image contour, and determining the horizontal coordinates of the lower left corner pixel point and the lower right corner pixel point of the minimum circumscribed moment;

[0023] The column start position and the column end position are determined according to the horizontal coordinate of the lower left pixel point and the horizontal coordinate of the lower right pixel point.

[0024] Furthermore, in the above-mentioned information extraction method based on architectural drawings, after the step of respectively determining the column starting position and the column ending position according to the horizontal coordinate of the lower left corner pixel point and the horizontal coordinate of the lower right corner pixel point, the step further includes:

[0025] The middle line of the adjacent sides of two adjacent minimum circumscribed moments is obtained, the column dividing line position is determined according to the middle line, and the column position is determined according to the column dividing line position, the column starting position and the column ending position.

[0026] Another object of the present invention is to provide an information extraction system based on architectural drawings, the system comprising:

[0027] A drawing acquisition module is used to acquire a preset format file storing drawings, and parse the preset format file to acquire multiple architectural drawings;

[0028] A drawing analysis module, used for analyzing the plurality of architectural drawings to determine a target architectural drawing where the design specification is located from the plurality of architectural drawings;

[0029] An identification module, used for identifying the target architectural drawing to obtain the number of columns and the positions of the columns of the target architectural drawing;

[0030] The information extraction module is used to extract information from the target building drawing in a preset order according to the number of columns and the positions of the columns.

[0031] Another object of an embodiment of the present invention is to provide a readable storage medium having a computer program stored thereon, wherein the program implements the steps of the above method when executed by a processor.

[0032] Another object of an embodiment of the present invention is to provide a computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the above method when executing the program.

[0033] The present invention parses a preset format file storing drawings to obtain multiple architectural drawings, and analyzes the multiple architectural drawings to determine the target architectural drawing containing the design specification, identifies the target architectural drawing to obtain the number of columns and the column positions of the target architectural drawing, extracts information from the design specification according to the preset order of the number of columns and the column positions, and can accurately identify the column positions and extract the content in the drawing according to the column positions when the column layout of the design specification is different, thereby solving the problem of low accuracy in extracting information from the design specification in the architectural drawing in the prior art. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] Figure 1 It is a flowchart of the information extraction method based on architectural drawings provided in the first embodiment of the present invention;

[0035] Figure 2 It is a flow chart of the information extraction method based on architectural drawings provided in the second embodiment of the present invention;

[0036] Figure 3 A schematic diagram of a grayscale image in an information extraction method based on architectural drawings provided in one embodiment of the present invention;

[0037] Figure 4 for Figure 3 Schematic diagram of converting a grayscale image into a binary image;

[0038] Figure 5 A schematic diagram of a blank image in an information extraction method based on architectural drawings provided in one embodiment of the present invention;

[0039] Figure 6 for Figure 5 Schematic diagram after inverting binary image processing;

[0040] Figure 7 A schematic diagram of image contour detection in an information extraction method based on architectural drawings provided in one embodiment of the present invention;

[0041] Figure 8 for Figure 3 Schematic diagram after the middle column;

[0042] Fig. 9 This is a structural block diagram of an information extraction system based on architectural drawings provided in a third embodiment of the present invention.

[0043] The following specific implementation manner will further illustrate the present invention in conjunction with the above-mentioned drawings. DETAILED DESCRIPTION

[0044] In order to facilitate the understanding of the present invention, the present invention will be described more fully below with reference to the relevant drawings. Several embodiments of the present invention are given in the drawings. However, the present invention can be implemented in many different forms and is not limited to the embodiments described herein. On the contrary, the purpose of providing these embodiments is to make the disclosure of the present invention more thorough and comprehensive.

[0045] It should be noted that when an element is referred to as being "fixed to" another element, it may be directly on the other element or there may be a central element. When an element is considered to be "connected to" another element, it may be directly connected to the other element or there may be a central element at the same time. The terms "vertical", "horizontal", "left", "right" and similar expressions used herein are for illustrative purposes only.

[0046] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which the present invention belongs. The terms used herein in the specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. The term "and / or" used herein includes any and all combinations of one or more of the related listed items.

[0047] The following will describe in detail how to improve the accuracy of extracting information from design specifications in architectural drawings in conjunction with specific embodiments and drawings.

[0048] Embodiment 1

[0049] See also Figure 1 , shown is an information extraction method based on architectural drawings in a first embodiment of the present invention, the method includes steps S10~S13.

[0050] Step S10, obtaining a preset format file storing drawings, and parsing the preset format file to obtain a plurality of architectural drawings.

[0051] Among them, most of the architectural drawings are drawn through CAD. Correspondingly, in this embodiment, the preset format file is a DWG format file, and the DWG format file is parsed to obtain the architectural drawings stored in the DWG format file. Specifically, the ObjectARX tool is used to parse the DWG format file.

[0052] Step S11, analyzing the plurality of architectural drawings to determine the target architectural drawing where the design specification is located from the plurality of architectural drawings.

[0053] Specifically, a DWG format file usually includes drawings such as design instructions, energy-saving design, section drawings, elevation drawings, etc. In this embodiment, the information in the design instructions needs to be extracted, so it is necessary to analyze multiple architectural drawings to first determine the drawings where the design instructions are located.

[0054] More specifically, in some optional embodiments of the present invention, the step of analyzing the plurality of architectural drawings to determine the target architectural drawing where the design specification is located from the plurality of architectural drawings may specifically include:

[0055] The drawing name information of the plurality of architectural drawings is obtained, and the target architectural drawing where the design specification is located is determined according to the drawing name information.

[0056] It can be understood that each drawing is marked with corresponding drawing name information at a fixed position, and the target building drawing where the design description is located can be determined by obtaining the drawing name information on the drawing.

[0057] Step S12: Identify the target architectural drawing to obtain the number of columns and column positions of the target architectural drawing.

[0058] The number of columns and the specific classification positions can be used to accurately and independently read the information in the column-divided area, thus avoiding inaccurate content after reading due to ambiguity and uncertainty of the column positions.

[0059] Step S13: extracting information from the target building drawing in a preset order according to the number of columns and the positions of the columns.

[0060] Among them, the preset order is the order of arrangement of text in the specification. For example, the text is arranged from left to right in the picture. At this time, the information in the design specification can be extracted from left to right, and the starting position of information extraction can be determined according to the number of columns and the position of the columns, avoiding the problem of inaccurate information extraction from architectural drawings due to failure to consider column lines during extraction and inability to determine column lines.

[0061] In summary, the information extraction method based on architectural drawings in the above embodiment of the present invention parses a preset format file storing drawings to obtain multiple architectural drawings, and analyzes the multiple architectural drawings to determine the target architectural drawing containing the design specification, identifies the target architectural drawing to obtain the number of columns and column positions of the target architectural drawing, and extracts the information in the design specification according to the preset order of the number of columns and the column positions. When the column layout of the design specification is different, the column position can be accurately identified and the content in the drawing can be extracted according to the column position, thereby solving the problem of low accuracy in extracting information from the design specification in the architectural drawing in the prior art.

[0062] Embodiment 2

[0063] See also Figure 2 , shown is an information extraction method based on architectural drawings in a second embodiment of the present invention, the method includes steps S20~S27.

[0064] Step S20, obtaining a preset format file storing drawings, and parsing the preset format file to obtain a plurality of architectural drawings.

[0065] Step S21: analyzing the plurality of architectural drawings to determine the target architectural drawing where the design specification is located from the plurality of architectural drawings.

[0066] Step S22: convert the target building drawing into a grayscale image, perform binary inversion processing on the grayscale image to obtain a binary image, and obtain the number of black pixels in each column of the binary image.

[0067] Among them, after the grayscale image is binary inverted, Figure 3 As shown, the text of the design description in the design drawing is displayed in black and the background is white. The number of black pixels in each column of the binary image can be counted column by column.

[0068] In addition, in some optional embodiments of the present invention, in order to facilitate the recognition of the target architectural drawings, the format of the target architectural drawings can be converted before recognition (that is, before the target architectural drawings are converted into grayscale images). In this embodiment, the preset format is JPG format.

[0069] Step S23, creating a blank image with the same size as the target architectural drawing, and filling the blank image according to the number of black pixels in each column of the binary image.

[0070] Create a blank image of the same size as the target architectural drawing, and fill it with the number of black pixels in each column of the binary image. Figure 4As shown, after filling, the upper part of each column in the blank image is white and the lower part is black. It can be understood that the more black pixels a column has, the more text appears in the column, and the less likely it is to be a column position; conversely, the fewer black pixels a column has, the less text appears in the column, and the more likely it is to be a column position.

[0071] Step S24, performing a closing operation on the filled blank image and then performing inverted binary image processing, detecting the image contour after the inverted binary image processing, and determining the number of columns of the target building drawing according to the number of image contours.

[0072] Among them, Figure 5 As shown, the filled blank image is closed and then the binary image is inverted. Figure 6 As shown, the image contour is detected. At this time, the number of image contours is the number of columns in the target building drawing. By performing horizontal and vertical closing operations on the blank image, the connected pixels between each image contour can be removed, which is conducive to accurately identifying the number and position of the columns.

[0073] In addition, in some optional embodiments of the present invention, in order to improve the accuracy of determining the number of columns, the step of performing a closing operation on the filled blank image and then performing an inverted binary image processing, detecting the image contour after the binary image processing, and determining the number of columns of the target architectural drawing according to the number of image contours further includes:

[0074] The burrs and small bridges in the white area of ​​the blank image after the closing operation are removed.

[0075] It can be understood that removing the influencing factors such as burrs and small bridges in the white area of ​​the blank image after the closing operation improves the accuracy of image contour detection and further improves the accuracy of determining the number of columns.

[0076] Step S25, obtaining the minimum circumscribed moment of each image contour, and determining the horizontal coordinates of the lower left corner pixel point and the lower right corner pixel point of the minimum circumscribed moment.

[0077] The width of the minimum circumscribed rectangle is the column width, and the horizontal coordinates of the lower left corner pixel and the lower right corner pixel can be obtained according to the minimum circumscribed rectangle.

[0078] Step S26, determining the column start position and the column end position according to the horizontal coordinate of the lower left pixel point and the horizontal coordinate of the lower right pixel point.

[0079] Specifically, Figure 7 As shown, the horizontal coordinate of the lower left corner pixel of the rectangle is the starting position of the column, and the horizontal coordinate of the lower right corner pixel is the ending position of the column.

[0080] In addition, in some optional embodiments of the present invention, in order to determine the specific position of the column, after the step of respectively determining the column starting position and the column ending position according to the horizontal coordinate of the lower left corner pixel point and the horizontal coordinate of the lower right corner pixel point, the step further includes:

[0081] The middle line of the adjacent sides of two adjacent minimum circumscribed moments is obtained, the column dividing line position is determined according to the middle line, and the column position is determined according to the column dividing line position, the column starting position and the column ending position.

[0082] Understandable, specific, such as Figure 8 As shown, the specific position of the column can be accurately determined according to the starting position of the column, the ending position of the column and the position of the dividing line.

[0083] Step S27: extracting information from the target building drawing in a preset order according to the number of columns and the positions of the columns.

[0084] In summary, the information extraction method based on architectural drawings in the above embodiment of the present invention parses a preset format file storing drawings to obtain multiple architectural drawings, and analyzes the multiple architectural drawings to determine the target architectural drawing containing the design specification, identifies the target architectural drawing to obtain the number of columns and the column positions of the target architectural drawing, and extracts the information in the design specification according to the preset order of the number of columns and the column positions. When the column layout of the design specification is different, the column position can be accurately identified and the content in the drawing can be extracted according to the column position, which solves the problem of low accuracy in extracting information from the design specification in the architectural drawing in the prior art.

[0085] Embodiment 3

[0086] See also Fig. 9 , which is shown as an information extraction system based on architectural drawings proposed in the third embodiment of the present invention, and the system includes:

[0087] The drawing acquisition module 100 is used to acquire a preset format file storing drawings, and parse the preset format file to acquire a plurality of architectural drawings;

[0088] A drawing analysis module 200 is used to analyze the plurality of architectural drawings to determine a target architectural drawing where the design specification is located from the plurality of architectural drawings;

[0089] An identification module 300 is used to identify the target architectural drawing to obtain the number of columns and column positions of the target architectural drawing;

[0090] The information extraction module 400 is used to extract information from the target building drawing according to the number of columns and the positions of the columns in a preset order.

[0091] Furthermore, in the above-mentioned information extraction system based on architectural drawings, the drawing analysis module is specifically used for:

[0092] The drawing name information of the plurality of architectural drawings is obtained, and the target architectural drawing where the design specification is located is determined according to the drawing name information.

[0093] Furthermore, the above-mentioned information extraction system based on architectural drawings, wherein the system also includes:

[0094] The conversion module is used to convert the target architectural drawing into a preset format.

[0095] Furthermore, in the above-mentioned information extraction system based on architectural drawings, the recognition module includes:

[0096] An arrangement mode acquisition unit, used for converting the target building drawing into a grayscale image, performing binary inversion processing on the grayscale image to obtain a binary image, and obtaining the number of black pixels in each column of the binary image;

[0097] A filling unit, used to create a blank image with the same size as the target architectural drawing, and fill the blank image according to the number of black pixels in each column of the binary image;

[0098] The column number determination unit is used to perform inverted binary image processing after closing operation on the filled blank image, detect the image contour after binary image processing, and determine the number of columns of the target building drawing according to the number of image contours.

[0099] Furthermore, in the above-mentioned information extraction system based on architectural drawings, the recognition module further comprises:

[0100] A coordinate determination unit, used for obtaining the minimum circumscribed moment of each image contour, and determining the horizontal coordinate of the lower left corner pixel point and the horizontal coordinate of the lower right corner pixel point of the minimum circumscribed moment;

[0101] The column position determination unit is used to determine the column start position and the column end position respectively according to the horizontal coordinate of the lower left corner pixel point and the horizontal coordinate of the lower right corner pixel point.

[0102] Furthermore, the above-mentioned information extraction system based on architectural drawings, wherein the system also includes:

[0103] The dividing line position acquisition module is used to obtain the middle line of the adjacent sides of two adjacent minimum circumscribed moments, determine the column dividing line position according to the middle line, and determine the column position according to the column dividing line position, the column starting position and the column ending position.

[0104] Furthermore, the above-mentioned information extraction system based on architectural drawings, wherein the system also includes:

[0105] The removal module is used to remove burrs and small bridges in the white area of ​​the filled blank image.

[0106] The functions or operation steps implemented when the above modules are executed are substantially the same as those in the above method embodiments, and will not be repeated here.

[0107] In summary, the above-mentioned embodiment of the present invention parses a preset format file storing drawings to obtain multiple architectural drawings, and analyzes the multiple architectural drawings to determine the target architectural drawing containing the design specification, identifies the target architectural drawing to obtain the number of columns and the column positions of the target architectural drawing, and extracts the information in the design specification according to the preset order of the number of columns and the column positions. When the column layout of the design specification is different, the column position can be accurately identified and the content in the drawing can be extracted according to the column position, thereby solving the problem of low accuracy in extracting information from the design specification in the architectural drawing in the prior art.

[0108] Embodiment 4

[0109] Another aspect of the present invention further provides a readable storage medium having a computer program stored thereon, and when the program is executed by a processor, the steps of the method described in any one of the above embodiments 1 to 2 are implemented.

[0110] Embodiment 5

[0111] Another aspect of the present invention provides a computer device, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the method described in any one of the above-mentioned embodiments 1 to 2 when executing the program.

[0112] The technical features of the above embodiments can be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0113] Those skilled in the art will appreciate that the logic and / or steps represented in the flowchart or otherwise described herein, for example, may be considered as an ordered list of executable instructions for implementing logical functions, and may be specifically implemented in any computer-readable storage medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in conjunction with such instruction execution systems, devices or apparatuses. For purposes of this specification, a "computer-readable storage medium" may be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in conjunction with such instruction execution systems, devices or apparatuses.

[0114] More specific examples (a non-exhaustive list) of computer-readable storage media include the following: an electrical connection with one or more wires (electronic device), a portable computer disk case (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable storage medium may even be a paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering or, if necessary, processing in another suitable manner, and then stored in a computer memory.

[0115] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or a combination thereof: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0116] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "examples", "specific examples", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner.

[0117] The above-mentioned embodiments only express several implementation methods of the present invention, and the description thereof is relatively specific and detailed, but it cannot be understood as limiting the scope of the patent of the present invention. It should be pointed out that, for ordinary technicians in this field, several variations and improvements can be made without departing from the concept of the present invention, which all belong to the protection scope of the present invention. Therefore, the protection scope of the patent of the present invention shall be subject to the attached claims.

Claims

1. A method for extracting information based on architectural drawings, characterized in that: The method comprises: Acquire a preset format file storing drawings, and parse the preset format file to obtain a plurality of architectural drawings; Analyzing the plurality of architectural drawings to determine a target architectural drawing where the design specification is located from the plurality of architectural drawings; Identify the target architectural drawing to obtain the number of columns and column positions of the target architectural drawing; Extracting information from the target building drawing in a preset order according to the number of columns and the positions of the columns; The step of identifying the target architectural drawing to obtain the number of columns and the position of the columns of the target architectural drawing comprises: Convert the target building drawing into a grayscale image, perform binary inversion processing on the grayscale image to obtain a binary image, and obtain the number of black pixels in each column of the binary image; Creating a blank image that is the same size as the target architectural drawing, and filling each column of the blank image in turn according to the number of black pixels in each column of the binary image; Performing a closing operation on the filled blank image and then performing an inverted binary image processing, detecting the image contour after the inverted binary image processing, and determining the number of columns of the target building drawing according to the number of the image contours; Obtaining the minimum circumscribed moment of each image contour, and determining the horizontal coordinates of the lower left corner pixel point and the lower right corner pixel point of the minimum circumscribed moment; The column start position and the column end position are determined according to the horizontal coordinate of the lower left pixel point and the horizontal coordinate of the lower right pixel point.

2. The information extraction method based on architectural drawings according to claim 1 is characterized in that: The step of analyzing the plurality of architectural drawings to determine the target architectural drawing where the design specification is located from the plurality of architectural drawings comprises: The drawing name information of the plurality of architectural drawings is obtained, and the target architectural drawing where the design specification is located is determined according to the drawing name information.

3. The information extraction method based on architectural drawings according to claim 1 is characterized in that: Before the step of identifying the target architectural drawing to obtain the number of columns and the position of the columns of the target architectural drawing, the step further includes: The target architectural drawing is converted into a preset format.

4. The information extraction method based on architectural drawings according to claim 3 is characterized in that: The step of performing a closing operation on the filled blank image and then performing an inverted binary image processing, detecting the image contour after the binary image processing, and determining the number of columns of the target architectural drawing according to the number of image contours also includes: The burrs and small bridges in the white area of ​​the blank image after the closing operation are removed.

5. The information extraction method based on architectural drawings according to claim 4 is characterized in that: After the step of determining the column start position and the column end position according to the horizontal coordinate of the lower left pixel point and the horizontal coordinate of the lower right pixel point respectively, the following step further comprises: The middle line of the adjacent sides of two adjacent minimum circumscribed moments is obtained, the column dividing line position is determined according to the middle line, and the column dividing line position, the column starting position and the column ending position are determined.

6. An information extraction system based on architectural drawings, characterized in that: For implementing the information extraction method based on architectural drawings according to any one of claims 1 to 5, the system comprises: A drawing acquisition module is used to acquire a preset format file storing drawings, and parse the preset format file to acquire multiple architectural drawings; A drawing analysis module, used for analyzing the plurality of architectural drawings to determine a target architectural drawing where the design specification is located from the plurality of architectural drawings; An identification module, used for identifying the target architectural drawing to obtain the number of columns and the positions of the columns of the target architectural drawing; The information extraction module is used to extract information from the target building drawing in a preset order according to the number of columns and the positions of the columns.

7. A readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the steps of the method according to any one of claims 1 to 5 are implemented.

8. A computer device, characterized in that: The method comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of any one of the methods of claims 1 to 5 when executing the program.

Images