AI-based axis network identification method and system, terminal and medium

Abstract

The invention discloses an AI-based axis net recognition method and system, a terminal and a medium, and the method comprises the steps: analyzing an architectural drawing, traversing drawing frames in a layout space of the architectural drawing, and obtaining basic primitive information in each drawing frame range, the basic primitive information comprising lines, characters and circles; identifying an axis net drawing area, identifying an axis coil, an axis number and an axis lead in the axis net drawing area based on the basic primitive information, and identifying an axis based on the axis coil, the axis number and the axis lead; and based on the axis, determining an axis net, and setting an axis net graph name. According to the method, the problems that time and labor are wasted and errors are easy to make due to manual shaft net recognition can be solved, an intelligent and automatic solution can be better for a construction party to manage a project, and a large amount of labor cost and a large amount of time cost are saved.

Description

Technical Field

[0001] The present invention relates to the technical field of drawing recognition, and in particular to an AI-based axis network recognition method, system, terminal and medium. Background Art

[0002] With the development of various industries in society, automation and intelligence are becoming more and more popular. The same is true for the construction engineering field. The design and construction process depends on detailed drawings. At present, domestic design and construction drawings are basically based on BIM software and data formats, and DWG drawings as a CAD file format are widely used. In CAD drawings, the identification and extraction of axis grids is a very important core item. However, if this identification and extraction process is done manually, it is very time-consuming, labor-intensive and error-prone. In addition, the scale of current construction projects is getting larger and larger, the complexity is getting higher and higher, and the maintainability is becoming more and more difficult.

[0003] Therefore, the prior art still needs to be improved and enhanced. Summary of the invention

[0004] The technical problem to be solved by the present invention is that, in view of the above-mentioned defects of the prior art, an AI-based axis network identification method, system, terminal and medium are provided, aiming to solve the problem that the process of AI-based axis network identification and extraction in the prior art is completed manually, which is very time-consuming, labor-intensive and prone to errors.

[0005] In order to solve the above technical problems, the technical solution adopted by the present invention is as follows:

[0006] In a first aspect, the present invention provides an AI-based axis network identification method, the method comprising:

[0007] Parse the architectural drawing, traverse the drawing frames under the layout space of the architectural drawing, and obtain basic graphic element information within each drawing frame, wherein the basic graphic element information includes lines, texts, and circles;

[0008] Identify the axis grid drawing area, and identify the axis coil, axis number, and axis lead in the axis grid drawing area based on the basic graphic element information, and identify the axis line based on the axis coil, axis number, and axis lead;

[0009] Based on the axis line, determine the axis grid and set the axis grid drawing name.

[0010] In one implementation, parsing the architectural drawing, traversing the drawing frames under the layout space of the architectural drawing, and obtaining basic graphic element information within the range of each drawing frame includes:

[0011] For the elements that are not displayed in the architectural drawing analysis, clean up the unused data and filter the visible elements based on the layer switch, freeze, and whether to print;

[0012] Block reference clipping and viewport clipping are adopted, and the basic element information in the frame under the layout space is mapped based on the viewport.

[0013] In one implementation, identifying the grid drawing area includes:

[0014] By training the YOLO model, a target detection model is obtained, and the axis grid drawing area is identified based on the target detection model.

[0015] In one implementation, the step of identifying the axis coil, axis number, and axis lead in the axis grid drawing area based on the basic graphic element information includes:

[0016] Adopt C++ open source geometric algorithm library to determine the combination of axis coil and axis number through the collision relationship between text and circle in basic graphic element information;

[0017] If there are multiple characters in the circle, the characters in the same circle are merged according to their positions, and the combination of the axis lead and the axis coil is determined based on the collision between the axis coil and the line segment.

[0018] The shaft coil, shaft number, and shaft lead are determined based on a combination of the shaft coil and the shaft number and a combination of the shaft lead and the shaft coil.

[0019] In one implementation, the identifying the axis line based on the axis coil, the axis number, and the axis lead wire includes:

[0020] The shaft coils, shaft numbers, and shaft leads are grouped according to shaft number prefixes, and the combinations of coaxial numbers are further grouped according to shaft leads;

[0021] Two axis numbers with the same axis number and axis leads on the same straight line are regarded as double axis numbers, and the axis line is obtained by directly connecting the double axis numbers with the axis leads.

[0022] In one implementation, the identifying the axis line based on the axis coil, the axis number, and the axis lead line further includes:

[0023] If the axis line of a single axis number is connected by collision starting from the axis lead line, until the last axis line cannot obtain a line segment that collides with it, then this line passing through the axis coil, axis lead line, axis number and axis line is an axis line of a single axis number.

[0024] In one implementation, determining the axis grid based on the axis includes:

[0025] Group parallel axes to form an axis grid;

[0026] If there are at least two groups of parallel axes in the axis grid, including no less than two axes, the axis grid is determined to be valid.

[0027] In a second aspect, an embodiment of the present invention further provides an AI-based axis grid identification system, wherein the system comprises:

[0028] The graphic element information analysis module is used to parse the architectural drawings, traverse the drawing frames under the layout space of the architectural drawings, and obtain the basic graphic element information within each drawing frame, wherein the basic graphic element information includes lines, texts and circles;

[0029] An axis recognition module is used to recognize an axis grid drawing area, and recognize an axis coil, an axis number, and an axis lead in the axis grid drawing area based on the basic graphic element information, and recognize an axis based on the axis coil, axis number, and axis lead;

[0030] The axis grid determination module is used to determine the axis grid based on the axis line and set the axis grid drawing name.

[0031] In a third aspect, an embodiment of the present invention further provides a terminal, wherein the terminal includes a memory, a processor, and an AI-based axis network identification program stored in the memory and executable on the processor, and when the processor executes the AI-based axis network identification program, the steps of the AI-based axis network identification method of any one of the above-mentioned schemes are implemented.

[0032] In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium, wherein an AI-based axis grid recognition program is stored on the computer-readable storage medium, and when the AI-based axis grid recognition program is executed by a processor, the steps of the AI-based axis grid recognition method described in any one of the above-mentioned schemes are implemented.

[0033] Beneficial effects: Compared with the prior art, the present invention provides an AI-based axis grid recognition method. The present invention first parses the architectural drawings, traverses the drawing frames under the layout space of the architectural drawings, and obtains the basic graphic element information within each frame range, wherein the basic graphic element information includes lines, text, and circles. Then, the axis grid drawing area is identified, and the axis coils, axis numbers, and axis leads in the axis grid drawing area are identified based on the basic graphic element information, and the axis lines are identified based on the axis coils, axis numbers, and axis leads. Finally, based on the axis line, the axis grid is determined, and the axis grid drawing name is set. The present invention can solve the time-consuming, labor-intensive, and error-prone problems caused by manual identification of the axis grid, and the intelligent and automated solutions can also help the construction party better manage the project, saving a lot of manpower costs and a lot of time costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] Figure 1A flowchart of a specific implementation of the AI-based axis network identification method provided in an embodiment of the present invention.

[0035] Figure 2 A schematic diagram of the shaft coil, shaft number, and shaft lead determined in the AI-based shaft network identification method provided in an embodiment of the present invention.

[0036] Figure 3 A first schematic diagram of a method for determining axis lines in an AI-based axis network identification method provided in an embodiment of the present invention.

[0037] Figure 4 A second schematic diagram of the method for determining the axis line in the AI-based axis network identification method provided in an embodiment of the present invention.

[0038] Figure 5 A third schematic diagram of a method for determining an axis line in the AI-based axis network identification method provided in an embodiment of the present invention.

[0039] Figure 6 A functional schematic diagram of an AI-based axis grid identification system provided in an embodiment of the present invention.

[0040] Figure 7 A functional block diagram of a terminal provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0041] In order to make the purpose, technical solution and effect of the present invention clearer and more specific, the present invention is further described in detail with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0042] The present embodiment provides an axis grid recognition method based on AI. When it is applied specifically, the present embodiment can first parse the architectural drawings, traverse the drawing frames under the layout space of the architectural drawings, and obtain the basic graphic element information within each frame range, wherein the basic graphic element information includes lines, text, and circles. Then, the axis grid drawing area is identified, and the axis coils, axis numbers, and axis leads in the axis grid drawing area are identified based on the basic graphic element information, and the axis lines are identified based on the axis coils, axis numbers, and axis leads. Finally, based on the axis lines, the axis grid is determined, and the axis grid drawing name is set. The present embodiment can solve the time-consuming, labor-intensive, and error-prone problems caused by manual identification of axis grids, and the intelligent and automated solutions can also help the construction party better manage the project, saving a lot of manpower costs and a lot of time costs.

[0043] The AI-based axis network recognition method of this embodiment can be applied to a terminal, which can be a computer, a smart TV, a mobile phone or other intelligent product terminal. Figure 1 As shown in , the AI-based axis network recognition method includes the following steps:

[0044] Step S100: parsing the architectural drawing, traversing the drawing frames under the layout space of the architectural drawing, and obtaining basic graphic element information within the range of each drawing frame, wherein the basic graphic element information includes lines, texts and circles.

[0045] Specifically, this embodiment implements intelligent identification of axis grids based on a preset development environment, such as Windows, Linux, and C++17. First, the architectural drawings are parsed, including analysis of blocks, block reference nesting relationships, and the like. In this embodiment, basic primitive information such as lines, text, and circles are parsed based on CAD architectural drawings, and these basic primitive information can be used to obtain and identify the smallest unit of the axis grid. In actual application, this embodiment can be divided into directly obtaining primitives of the layout space and primitives of the model space in the viewport by acquiring basic primitive information of the layout space. In the analysis of DWG architectural drawings, undisplayed primitives may be parsed, and screening and filtering are required. Specifically, this embodiment cleans up unused data and filters visible primitives based on the switch, freeze, and printing of the layer. Then, block reference clipping and viewport clipping are used, and the basic primitive information in the frame under the viewport mapping layout space is used. Clipping includes forward clipping and reverse clipping. Forward clipping is used for the axis grid within the clipping frame, and reverse clipping is used for the axis grid outside the clipping frame.

[0046] Step S200, identifying the axis grid drawing area, and identifying the axis coils, axis numbers, and axis leads in the axis grid drawing area based on the basic graphic element information, and identifying the axis lines based on the axis coils, axis numbers, and axis leads.

[0047] In this embodiment, the target detection model can be obtained by training the YOLO model, and the axis grid drawing area can be identified based on the target detection model. The target detection model uses 2500 axis grid images during training, which are divided into training set, validation set, and test set according to 8:1:1. The training set and validation set are annotated with labeling data. A total of 2000 axis grids are labeled, 250 for the validation set, and 250 for the test set. In this embodiment, the axis grid drawing area can also be identified by a graphic algorithm.

[0048] After identifying the axis grid drawing area, this embodiment uses the C++ open source geometry algorithm library to determine the combination of the axis coil and the axis number through the collision relationship between the text and the circle in the basic graphic element information; if there are multiple characters in the circle, the characters in the same circle are merged according to the position, and the combination of the axis lead and the axis coil is determined based on the collision of the axis coil and the line segment, and the axis coil, axis number, and axis lead are determined based on the combination of the axis coil and the axis number and the combination of the axis lead and the axis coil. In actual applications, the axis coil and the axis line are obtained through collision, and multiple axis leads may collide. The one that best meets the requirements is screened according to the specific business scenario. The determined axis coil, axis number, and axis lead, such as Figure 2 as shown in .

[0049] Furthermore, this embodiment utilizes the axis number prefix to group. Generally, the axes with the same prefix belong to the same axis network. The direction of the axis lead in the combination (axis coil, axis lead, axis number) and the axis number determine whether they belong to the same axis. For example, two axis numbers both include "1-E" and are grouped according to the axis number prefix. They belong to the same axis network. At this time, the axis leads are sorted on the same straight line, and the two axis numbers can be determined according to the text position and the direction of the axis lead to determine which two axis numbers belong to the same axis. Because there are multiple axis numbers on the same straight line, it is necessary to sort and group them according to the position. The two axis leads are relatively considered to be an axis with two axis numbers. Based on this, this embodiment can regard two axis numbers with the same axis number and axis leads on the same straight line as dual axis numbers, and directly connect the dual axis numbers with the axis leads to obtain the axis line. When the dual axis numbers and axis leads are on the same straight line, the paired axis number units (axis number, axis lead) are matched, and the axis lines are directly connected, as shown in the following example. Figure 3 In practical application, this embodiment can also be used to judge the shaft lead, such as Figure 4 As shown, the axis coil collides with the intersecting line segment 1, and line segment 1 continues to collide to obtain line segment 2. If line segment 1 and line segment 2 are not in the same direction, and the angle between line segment 1 and line segment 2 is less than 90 degrees, then line segment 2 is the axis lead, and the axis lead is directly connected to the double axis number. In addition, in another implementation method, if it belongs to a double axis number but the axis lead is not on the same straight line, you can only keep looking through the axis until the last connected line segment, such as Figure 5 Further, if the axis of a single axis number is an axis connected by collision from the axis lead until the last axis line cannot obtain a line segment that collides with it, then this line passing through the axis coil, the axis lead, the axis number and the axis number is an axis of a single axis number.

[0050] Step S300: Based on the axis line, determine the axis grid and set the axis grid drawing name.

[0051] Since the same prefix may belong to different axis grids, this embodiment can further group them according to whether the boundingBox of the axis intersects, that is, group the parallel axis grids. For example, multiple axis grids in the drawing frame are grouped according to the axis number prefix, and then grouped according to whether they intersect when the prefix is ​​the same. In this way, multiple different axis grids are obtained. In this way, the unit after two groupings is a single axis grid, and then the validity of the axis grid is verified. In this embodiment, if there are at least two groups of parallel axes in the axis grid containing no less than two axes, the axis grid is determined to be valid. In addition, this embodiment can also put the axis grids without axis number prefixes together and then group them according to whether they intersect.

[0052] For the axis grid outside the drawing frame, there is generally only one axis line, which does not conform to the business scenario. This embodiment filters it. For the axis grid in multiple drawing frames under the layout space, this embodiment can filter the line segments, texts, and circles in each drawing frame. After screening, a small number of primitives can effectively improve the efficiency of the algorithm. At the same time, the information of the drawing frame is set on the axis grid, so that the axis grid name can be set. For example, according to the axis grid's boundingbox, a length is extended outward. If there are underlined texts in this range and include keywords: "plane", "schematic", "positioning", "reinforcement", "roof", "roof", "framework", "shelf", "RF", "machine room", the axis grid name can be set based on this. If multiple keywords are found, the axis grid name can be set based on the closest to the midpoint of the lower edge of the axis grid boundingbox. If there is no text in this range, the axis grid name is set with the name in the drawing frame. In another implementation, this embodiment can also combine the LLM large language model to infer the axis grid name. For example, according to the text relationship between the axis grid range and the name feature, the correct axis grid name is inferred. The characteristics of the drawing name include "plane", "schematic", "positioning", "reinforcement", "roof", "structure", "rack", "RF", "machine room", etc. The axis grid drawing name is determined based on the text relationship.

[0053] In summary, this embodiment starts from the axis number feature based on the axis network feature, identifies the axis line, and then groups the axis network according to the axis number prefix and the intersection of the axis line, and then sets the axis network drawing name. In the normal identification process, the project business is added to determine the number of entries of the axis line in the axis network to determine whether the axis network is valid and to check for interference. It can solve the time-consuming, labor-intensive and error-prone problems caused by manual identification of the axis network, and the intelligent and automated solution can also help the construction party better manage the project, saving a lot of manpower costs and a lot of time costs.

[0054] Based on the above embodiments, the present invention also provides an AI-based axis network identification system, such as Figure 6As shown in , the system includes: a graphic element information analysis module 10, an axis identification module 20 and an axis network determination module 30. Specifically, the graphic element information analysis module 10 is used to parse the architectural drawings, traverse the drawing frames under the layout space of the architectural drawings, and obtain the basic graphic element information within each drawing frame range, wherein the basic graphic element information includes lines, texts and circles. The axis identification module 20 is used to identify the axis network drawing area, and identify the axis coil, axis number, and axis lead in the axis network drawing area based on the basic graphic element information, and identify the axis based on the axis coil, axis number, and axis lead. The axis network determination module 30 is used to determine the axis network based on the axis, and set the axis network drawing name.

[0055] In one implementation, the primitive information analysis module 10 includes:

[0056] The filtering unit is used to clean up unused data for the elements that are not displayed in the architectural drawing analysis, and filter the visible elements based on the switch, freeze, and printing of the layer;

[0057] The clipping unit is used to adopt block reference clipping and viewport clipping, and to map the basic primitive information in the frame under the layout space based on the viewport.

[0058] In one implementation, the axis identification module 20 includes:

[0059] The model recognition unit is used to obtain a target detection model by training the YOLO model, and recognize the axis grid drawing area based on the target detection model.

[0060] In one implementation, the axis identification module 20 includes:

[0061] A combination analysis unit is used to determine the combination of axis coils and axis numbers by analyzing the collision relationship between text and circles in basic graphic element information using a C++ open source geometric algorithm library;

[0062] A collision analysis unit, for merging the characters in the same circle according to positions if there are multiple characters in the circle, and determining a combination of the shaft lead and the shaft coil based on the collision between the shaft coil and the line segment;

[0063] The axis line analysis unit is used to determine the axis coil, the axis number, and the axis lead based on the combination of the axis coil and the axis number and the combination associated with the axis lead and the axis coil.

[0064] In one implementation, the axis identification module 20 includes:

[0065] A shaft lead grouping unit, used for grouping the shaft coil, shaft number, and shaft lead according to the shaft number prefix, and further grouping the combination of the same shaft number according to the shaft lead;

[0066] The double-axis number axis identification unit is used to take two axis numbers with the same axis number and axis leads on the same straight line as double-axis numbers, and directly connect the double-axis numbers to the axis leads to obtain the axis line.

[0067] In one implementation, the axis identification module 20 further includes:

[0068] The single-axis number axis identification unit is used for if the axis of the single-axis number is an axis connected by collision starting from the axis lead until the last axis cannot obtain a line segment that collides with it, then the line passing through the axis coil, axis lead, axis number and axis is a single-axis number axis.

[0069] In one implementation, the axis network determination module 30 includes:

[0070] Axis grid forming unit, used to group parallel axes to form an axis grid;

[0071] The axis network validity determination unit is used to determine that the axis network is valid if there are at least two groups of parallel axes in the axis network, including no less than two axes.

[0072] The working principles of each module in the AI-based axis network identification system of this embodiment are the same as the principles of each step in the above method embodiment, and will not be repeated here.

[0073] Based on the above embodiment, the present invention further provides a terminal, the principle block diagram of the terminal can be as follows: Figure 7 The terminal may include one or more processors 100 ( Figure 7 Only one is shown in the figure), a memory 101 and a computer program 102 stored in the memory 101 and executable on one or more processors 100, for example, an AI-based axis network recognition program. When one or more processors 100 execute the computer program 102, the various steps in the embodiment of the AI-based axis network recognition method can be implemented. Alternatively, when one or more processors 100 execute the computer program 102, the functions of the various modules / units in the embodiment of the AI-based axis network recognition device can be implemented, which is not limited here.

[0074] In one embodiment, the processor 100 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc.

[0075] In one embodiment, the memory 101 may be an internal storage unit of an electronic device, such as a hard disk or memory of the electronic device. The memory 101 may also be an external storage device of the electronic device, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the electronic device. Further, the memory 101 may also include both an internal storage unit of the electronic device and an external storage device. The memory 101 is used to store computer programs and other programs and data required by the terminal. The memory 101 may also be used to temporarily store data that has been output or is to be output.

[0076] Those skilled in the art will understand that Figure 7 The principle block diagram shown in the figure is only a block diagram of a partial structure related to the scheme of the present invention, and does not constitute a limitation on the terminal to which the scheme of the present invention is applied. The specific terminal may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0077] Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, operating database or other media used in the embodiments provided by the present invention may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double operational data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0078] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. An AI-based axis network identification method, characterized in that: The method comprises: Parse the architectural drawing, traverse the drawing frames under the layout space of the architectural drawing, and obtain basic graphic element information within each drawing frame, wherein the basic graphic element information includes lines, texts, and circles; Identify the axis grid drawing area, and identify the axis coil, axis number, and axis lead in the axis grid drawing area based on the basic graphic element information, and identify the axis line based on the axis coil, axis number, and axis lead; Based on the axis line, determine the axis grid and set the axis grid drawing name.

2. The AI-based axis network identification method according to claim 1, characterized in that: The parsing of the architectural drawings, traversing the frames under the layout space of the architectural drawings, and obtaining basic graphic element information within the range of each frame, includes: For the elements that are not displayed in the architectural drawing analysis, clean up the unused data and filter the visible elements based on the layer switch, freeze, and whether to print; Block reference clipping and viewport clipping are adopted, and the basic element information in the frame under the layout space is mapped based on the viewport.

3. The AI-based axis network identification method according to claim 1, characterized in that: The identification grid drawing area includes: By training the YOLO model, a target detection model is obtained, and the axis grid drawing area is identified based on the target detection model.

4. The AI-based axis network identification method according to claim 1, characterized in that: The step of identifying the axis coil, axis number, and axis lead in the axis grid drawing area based on the basic graphic element information includes: Adopt C++ open source geometric algorithm library to determine the combination of axis coil and axis number through the collision relationship between text and circle in basic graphic element information; If there are multiple characters in the circle, the characters in the same circle are merged according to their positions, and the combination of the axis lead and the axis coil is determined based on the collision between the axis coil and the line segment. The shaft coil, shaft number, and shaft lead are determined based on a combination of the shaft coil and the shaft number and a combination of the shaft lead and the shaft coil.

5. The AI-based axis network identification method according to claim 1, characterized in that: The method of identifying the axis line based on the axis coil, the axis number, and the axis lead wire comprises: The shaft coils, shaft numbers, and shaft leads are grouped according to shaft number prefixes, and the combinations of coaxial numbers are further grouped according to shaft leads; Two axis numbers with the same axis number and axis leads on the same straight line are regarded as double axis numbers, and the axis line is obtained by directly connecting the double axis numbers with the axis leads.

6. The AI-based axis network identification method according to claim 5, characterized in that: The method of identifying the axis line based on the axis coil, the axis number, and the axis lead wire further includes: If the axis line of a single axis number is connected by collision starting from the axis lead line, until the last axis line cannot obtain a line segment that collides with it, then this line passing through the axis coil, axis lead line, axis number and axis line is an axis line of a single axis number.

7. The AI-based axis network identification method according to claim 6, characterized in that: The step of determining the axis grid based on the axis line comprises: Group parallel axes to form an axis grid; If there are at least two groups of parallel axes in the axis grid, including no less than two axes, the axis grid is determined to be valid.

8. An AI-based axis network identification system, characterized in that: The system comprises: The graphic element information analysis module is used to parse the architectural drawings, traverse the drawing frames under the layout space of the architectural drawings, and obtain the basic graphic element information within each drawing frame, wherein the basic graphic element information includes lines, texts and circles; An axis recognition module is used to recognize an axis grid drawing area, and recognize an axis coil, an axis number, and an axis lead in the axis grid drawing area based on the basic graphic element information, and recognize an axis based on the axis coil, axis number, and axis lead; The axis grid determination module is used to determine the axis grid based on the axis line and set the axis grid drawing name.

9. A terminal, characterized in that: The terminal includes a memory, a processor, and an AI-based axis network identification program stored in the memory and executable on the processor. When the processor executes the AI-based axis network identification program, the steps of the AI-based axis network identification method as described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores an AI-based axis grid recognition program, and when the AI-based axis grid recognition program is executed by the processor, the steps of the AI-based axis grid recognition method according to any one of claims 1 to 7 are implemented.

Images