Method and system for automatically picking up explosion hazardous gas release source information
By converting 2D CAD files to PDF and automatically extracting and releasing source information using an AI model platform, the problem of low efficiency due to reliance on manual drawing in existing technologies has been solved. This has enabled the intelligent and automated design of explosion hazard zone delineation maps, improving work efficiency and reducing costs.
Patent Information
- Application Number
- CN202511390823.4
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-09-26
- Publication Date
- 2026-01-30
AI Technical Summary
Existing technologies rely on manual drawing in the design of explosion hazard zone delineation maps, which leads to low efficiency and dependence on professional expertise. Furthermore, the digitization process is complex and increases labor costs.
By converting non-digital 2D CAD files into PDF files and using an AI model platform for natural language processing, the release source information is automatically extracted and a 2D array is generated to facilitate reading by CAD plugins and automatic drawing of explosion hazard areas.
It has greatly improved work efficiency, reduced labor costs, and enabled intelligent and automated processing of the design of explosion hazard zone delineation maps.
Smart Images
Figure CN121435673A_ABST
Abstract
Description
Technical Field
[0001] This application belongs to the technical field of explosion hazard zone delineation map design, and in particular relates to a method and system for automatically picking up information on explosion hazard gas release sources. Background Technology
[0002] Currently, AI application platforms based on the DEEPSEEK-R1 open-source model are all based on natural language communication between users and AI models. However, when designing explosion hazard zone delineation maps, the necessary input conditions (i.e., explosion hazard gas release source condition map) are digitized and structured, which is based on the drawing interaction of two-dimensional CAD (.dwg format file) software.
[0003] However, process engineering companies currently typically use the following two processes and methods when designing explosion hazard zone delineation maps: The first method involves receiving a non-digital, unstructured 2D CAD (.dwg format file) diagram of explosive hazardous gas release sources. The designer of the explosion hazard zone delineation map directly locates the release sources on the diagram, along with the gas names and elevation information marked on the drawing. They then find the corresponding clauses in the design specifications and draw circles of different radii. By sequentially locating all release sources in the diagram and drawing all corresponding circles according to the marked information, they finally fit all the circles into a single planar area, thus completing the explosion hazard zone delineation map design.
[0004] The second method involves the personnel proposing the conditional diagram of explosive gas release sources. When drawing the conditional diagram in 2D CAD (.dwg format file), they digitally design the release sources in the diagram. Specifically, when placing the release source in the 2D CAD (.dwg format file) diagram, the gas name and elevation information are entered as graphic element parameters into the release source graphic element. This information can be retrieved through a secondary development plugin. After receiving this digital and structured conditional diagram, the designers of the explosion hazard zone delineation diagram use a secondary development CAD plugin to extract the gas name and elevation information of each release source in the conditional diagram. Simultaneously, they integrate the relevant clauses from the design specifications into the secondary development plugin, automatically drawing the corresponding circles and fitting them into a planar area, thus completing the design of the explosion hazard zone delineation diagram.
[0005] The two methods described above have the following technical problems; The first method relies heavily on the professional competence of the designers of the explosion hazard zone delineation map, and human error is possible. In addition, this method is entirely based on manual drawing, which is time-consuming and labor-intensive. According to the publicly available time quotas of some industry companies, the time consumption for this type of drawing for a project is around 600 hours.
[0006] The second method heavily relies on the professional competence and work attitude of the personnel who propose the explosive hazardous gas release source condition diagram. The designers of the explosive hazardous area division diagram need to check whether each release source has been digitized. Although this saves a lot of manpower in the final drawing generation process, it adds a lot of manpower in the process of the condition diagram proposer drawing and the process of the division diagram designer checking the input conditions. Summary of the Invention
[0007] In view of this, this application aims to propose a method and system for automatically acquiring information on the release source of explosive hazardous gases, in order to solve at least one of the above-mentioned problems.
[0008] To achieve the above objectives, the technical solution of this application is implemented as follows: In a first aspect, this application provides a method for automatically acquiring information on the release source of explosive hazardous gases, including: Based on the input explosive hazardous gas release source condition diagram, file processing is performed to save multiple PDF files and name them respectively; By extracting the filenames of the PDF files, corresponding natural language description text is generated; The PDF file and the natural language description text are uploaded to the AI model application platform. The AI model application platform extracts information on the release source of the explosive hazardous gas based on the file content and user requirements. The release source information is presented in natural language.
[0009] Secondly, based on the same inventive concept, this application also provides an automatic acquisition system for information on the release source of explosive hazardous gases, comprising: The file processing module is configured to process the input explosive hazardous gas release source condition diagram to save multiple PDF files and name them respectively. The file extraction module is configured to extract the filenames of the PDF files to generate corresponding natural language description text; The information acquisition module is configured to upload the PDF file and the natural language description text to the AI model application platform. The AI model application platform acquires information on the release source of the explosive hazardous gas based on the file content and user requirements. The release source information is presented in natural language.
[0010] Thirdly, based on the same inventive concept, this application also provides a non-transitory computer-readable storage medium, wherein the non-transitory computer-readable storage medium stores computer instructions for causing the computer to perform the method as described in the first aspect.
[0011] Fourthly, based on the same inventive concept, this application also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the method described in the first aspect.
[0012] Compared with existing technologies, the automatic acquisition method and system for explosive hazardous gas release source information described in this application have the following advantages: The automatic acquisition method for explosive hazardous gas release source information described in this application utilizes existing AI application platforms to automatically acquire release source information from non-digital, unstructured 2D CAD (.dwg format files) explosive hazardous gas release source condition diagrams into a 2D array. The AI application platform then outputs this 2D array to the user in natural language. This release source information can be read by existing CAD secondary development plugins, which can then automatically draw corresponding circles and fit them into a planar region, thus completing the design of the explosive hazardous area division map. This method realizes half of the original workflow through AI intelligent work, significantly improving work efficiency and saving development costs. Attached Figure Description
[0013] The accompanying drawings, which form part of this application, are used to provide a further understanding of this application. The illustrative embodiments and descriptions of this application are used to explain this application and do not constitute an undue limitation of this application. In the drawings: Figure 1 This is a flowchart of a method for automatically acquiring information on the release source of explosive hazardous gases according to an embodiment of this application; Figure 2 This is a schematic diagram of the structure of an automatic information acquisition system for explosive hazardous gas release sources as described in an embodiment of this application; Figure 3 This is a schematic diagram of the hardware structure of the electronic device described in an embodiment of this application. Detailed Implementation
[0014] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with specific embodiments and the accompanying drawings.
[0015] It should be noted that, unless otherwise defined, the technical or scientific terms used in the embodiments of this application should have the ordinary meaning understood by one of ordinary skill in the art to which this application pertains. The terms "first" and similar words used in the embodiments of this application do not indicate any order, quantity, or importance, but are merely used to distinguish different components. Terms such as "comprising" or "including" mean that the element or object preceding the word covers the element or object listed after the word and its equivalents, without excluding other elements or objects. Terms such as "connected" or "linked" are not limited to physical or mechanical connections, but can include electrical connections, whether direct or indirect. Terms such as "upper," "lower," "left," and "right" are only used to indicate relative positional relationships; when the absolute position of the described object changes, the relative positional relationship may also change accordingly.
[0016] Currently, AI application platforms based on the DEEPSEEK-R1 open-source model are all based on natural language communication between users and AI models. However, when designing explosion hazard zone delineation maps, the necessary input conditions (i.e., explosion hazard gas release source condition map) are digitized and structured, which is based on the drawing interaction of two-dimensional CAD (.dwg format file) software.
[0017] This application extracts the interactive drawings from 2D CAD (.dwg format files) software into standard natural language descriptions and PDF files that can be accurately recognized by AI application platforms based on the DEEPSEEK-R1 open-source model. These PDF files are then provided to the DEEPSEEK-R1 open-source model-based AI application platform. The AI application platform can then accurately extract the content and user requirements from the 2D CAD (.dwg format files) drawings based on the user-provided standard natural language descriptions and PDF files. It then performs analysis and calculations by calling the DEEPSEEK-R1 model and finally outputs the release source information in natural language form. This enables the digitization and structuring of necessary input conditions (i.e., the explosion hazard gas release source condition diagram) during the design of explosion hazard zone delineation maps.
[0018] The embodiments of this application are described in detail below with reference to the accompanying drawings.
[0019] Please see Figure 1 As shown in the figure, this embodiment provides a method for automatically acquiring information on the release source of explosive hazardous gases, which specifically includes the following steps: Step S101: Based on the input explosion hazard gas release source condition diagram, perform file processing to save multiple PDF files and name them respectively.
[0020] Step S102: Extract the filenames from the PDF files to generate corresponding natural language description text.
[0021] Step S103: Upload the PDF file and natural language description text to the AI model application platform. The AI model application platform will extract the release source information of the explosive hazardous gas according to the file content and user needs. The release source information is presented in natural language.
[0022] The automatic acquisition method for explosive hazardous gas release source information described in this embodiment utilizes an existing AI application platform to automatically acquire release source information from a non-digital, unstructured 2D CAD (.dwg format file) explosive hazardous gas release source condition diagram into a 2D array. The AI application platform then outputs this 2D array to the user in natural language. This release source information can be read by existing CAD secondary development plugins, which can then automatically draw corresponding circles and fit them into a planar region, thus completing the design of the explosive hazardous area division map. This method realizes half of the original workflow through AI intelligent work, significantly improving work efficiency and saving development costs.
[0023] In some implementations, a typical example of a release source in the release source condition diagram is saved as a separate PDF file and named "First Example".
[0024] Specifically, in this embodiment, the typical legend of the release source (such as solid dots, lead lines and text) in the explosive hazardous gas release source condition diagram is exported as a separate PDF file and named "Typical Legend of Release Source (corresponding to the first legend above).pdf". At the same time, it is ensured that the legend is clearly visible and contains all necessary elements (elevation values, medium name).
[0025] In some implementations, the natural language description generated from the PDF file named "First Legend" includes a description of the legend style and a description of the relative positions of relevant information within the legend.
[0026] Specifically, in this embodiment, based on the PDF file generated in the above steps, natural language description text is generated by extracting the file name of the PDF file; wherein, the description of the legend: describes the content of "Release Source Typical Legend.pdf", including the legend structure and information location.
[0027] The description of the "Typical Legend of Release Source" content in the PDF file includes the representation of the legend style and the description of the relative positions of relevant information in the legend; for example: the legend of hazardous medium release source in the attached drawing shows the typical legend structure of hazardous medium release source in actual drawings. It usually consists of a solid dot, a leader line and text. The text above the leader line indicates the elevation of the release source (only the numerical part is extracted, and the unit is omitted), and the text below the leader line indicates the medium of the release source.
[0028] In some implementations, it also includes: After partitioning and marking the release source condition graph, the graphics inside the graph frame are grouped and cut according to each partition to save them as separate PDF files, and the multiple PDF files are named according to a preset sequence.
[0029] Furthermore, in the release source condition diagram, the lower left corner of the inner side of the drawing frame is marked as the origin of the coordinate system. Starting from this point, boxes of predetermined sizes are placed inside the drawing frame according to the drawing scale. The coordinates of the lower left corner of each box relative to the starting point are marked in the form of a one-dimensional array in each box. This work is automatically completed by a secondary CAD plugin. In this embodiment, the graphics inside the conditional diagram frame with the boxes already placed are cut into several parts, and each part is saved as a separate PDF file named "Release Source Conditional Diagram + Serial Number". This task is automatically completed by a secondary-developed CAD plugin.
[0030] Specifically, in this embodiment, an explosive gas release source condition diagram is selected, and the lower left corner of the inner side of the diagram frame is marked as the origin (0, 0). Starting from the marked point (x=0, y=0), 1m×1m squares are placed sequentially according to the current drawing scale (e.g., 1:100) to fill the entire diagram frame. Simultaneously, the coordinates of the lower left corner of each square relative to the origin are marked in the form of a one-dimensional array within each square, in the format "(X, Y)", where X and Y are integer coordinate values (unit: m). For example, the first square is marked as "(0, 0)", the next as "(1, 0)", and so on. It should be noted that this work is automatically completed by a secondary-developed CAD plugin (this plugin is a conventional plugin in the field, and this application has not improved it, so it will not be described in detail further; this plugin ensures that the coordinate markings are clear and readable, avoiding overlap with other graphics).
[0031] Use a CAD plugin to cut the graphics inside the conditional diagram frame, which already has 1m x 1m boxes, into several parts (each part contains no more than 10 x 10 boxes), and save each part as a separate PDF file, named "Release Source Conditional Diagram + Serial Number", for example, "Release Source Conditional Diagram". Figure 1 .pdf”, “Release source conditions” Figure 2 .pdf, etc. It is important to note that when cutting, each PDF file should contain complete release source information and coordinate boxes.
[0032] In some implementations, the natural language description generated from PDF files sorted in a preset sequence includes a description of the method for obtaining the relative coordinates of the release source, as well as a description of the requirements for the types of information to be obtained.
[0033] Specifically, in this embodiment, the condition graph is described as follows: each "Release Source Condition Graph X.pdf" file is described, and it is explained how to obtain the release source information.
[0034] The description of the "Release Source Condition Diagram + Serial Number" content in the PDF file includes a description of the method for obtaining the relative coordinates of the release source and a description of the required types of information to be obtained; for example: the attached drawing "Release Source Conditions" Figure 1 "This is a drawing showing the locations of hazardous medium release sources and information about the medium. Now, please carefully examine the drawing and output the X-coordinate, Y-coordinate, elevation, medium, and floor elevation of all release sources in the drawing as a two-dimensional array." The method for obtaining relative X and Y coordinates is explained below: The relative X and Y coordinates of the release source are the graphic elements in the diagram that appear in the (NA, NA) structure closest to the solid circle representing the release source. The number part before the comma in this graphic element is the relative X coordinate, and the number part after the comma is the relative Y coordinate. …Describe all conditional diagram PDF files in sequence.
[0035] The textual description of the standardized output format includes how to integrate the above individual arrays and the format of the output array. For example: Please update the arrays in sequence according to the above requirements, output the final updated array, then merge the updated arrays into a two-dimensional array, and finally output it in a strict JSON array format.
[0036] In some implementations, it also includes: The information on the release source of explosive hazardous gases extracted by the AI model application platform is output in the form of a two-dimensional array.
[0037] Specifically, in this embodiment, the PDF file and natural language description text generated after the above steps are uploaded to an AI application platform based on the DEEPSEEK-R1 open-source model (such as the web version of deepseek, Doubao, Tencent Yuanbao, and other large model application platforms), and wait for the large model to analyze and calculate, and give the results in the form of a two-dimensional array.
[0038] In some implementations, the two-dimensional array is converted into a programming language to generate a map of explosion hazard zones.
[0039] Specifically, in this embodiment, a secondary development plugin is used to read the natural language response output by the AI, extract a two-dimensional array string in JSON format, and parse the string into a programming language array (such as string[][] or double[][] in C#).
[0040] Based on the release source coordinates (X, Y), elevation, medium, and other information in the array, the plugin automatically draws circles (representing release sources) in the CAD drawing and fits them into a planar area to complete the design of the explosion hazard zone zoning map.
[0041] For example, in C#, parsing a JSON array can be done using the Newtonsoft.Json library, and then the plugin can draw circles based on the coordinates of each release source and set different properties based on the media type.
[0042] The method described in this embodiment can automatically extract the release source information from the non-digital, unstructured two-dimensional CAD (.dwg format file) explosive hazardous gas release source condition diagram into digital input conditions for the automatic design of explosive hazardous area division maps. This method realizes AI intelligent work for half of the original workflow, which greatly improves work efficiency and reduces personnel costs.
[0043] It should be noted that the above description describes some embodiments of this application. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in a different order than that shown in the above embodiments and still achieve the desired result. Furthermore, the processes depicted in the drawings do not necessarily require a specific or sequential order to achieve the desired result. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.
[0044] Based on the same inventive concept, and corresponding to the methods of any of the above embodiments, the embodiments of this application also provide an automatic acquisition system for information on the release source of explosive hazardous gases.
[0045] like Figure 2 As shown, the automatic acquisition system for information on the release source of explosive hazardous gases includes: The file processing module 11 is configured to process the input explosive hazardous gas release source condition diagram to save multiple PDF files and name them respectively. The file extraction module 12 is configured to extract the filenames of PDF files to generate corresponding natural language description text; The information acquisition module 13 is configured to upload PDF files and natural language description text to the AI model application platform. The AI model application platform acquires information on the release source of explosive hazardous gases based on the file content and user requirements. The release source information is presented in natural language.
[0046] For ease of description, the above system is described by dividing it into various modules based on their functions. Of course, in implementing the embodiments of this application, the functions of each module can be implemented in one or more software and / or hardware.
[0047] The system described in the above embodiments is used to implement the corresponding method in any of the foregoing embodiments and has the beneficial effects of the corresponding method embodiments, which will not be repeated here.
[0048] Based on the same inventive concept, corresponding to the methods of any of the above embodiments, this application also provides a non-transitory computer-readable storage medium that stores computer instructions for causing the computer to perform the methods described in any of the above embodiments.
[0049] Based on the same inventive concept, corresponding to the methods of any of the above embodiments, embodiments of this application also provide an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the methods described in any of the above embodiments.
[0050] Figure 3 This embodiment illustrates a more specific hardware structure of an electronic device, which may include a processor 1010, a memory 1020, an input / output interface 1030, a communication interface 1040, and a bus 1050. The processor 1010, memory 1020, input / output interface 1030, and communication interface 1040 are interconnected internally via the bus 1050.
[0051] The processor 1010 can be implemented using a general-purpose CPU (Central Processing Unit), microprocessor, application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of this specification.
[0052] The memory 1020 can be implemented in the form of ROM (Read Only Memory), RAM (Random Access Memory), static storage device, dynamic storage device, etc. The memory 1020 can store the operating system and other applications. When the technical solutions provided in the embodiments of this specification are implemented by software or firmware, the relevant program code is stored in the memory 1020 and is called and executed by the processor 1010.
[0053] The input / output interface 1030 is used to connect input / output modules to realize information input and output. The input / output modules can be configured as components in the device (not shown in the figure) or externally connected to the device to provide corresponding functions. Input devices may include keyboards, mice, touch screens, microphones, various sensors, etc., and output devices may include displays, speakers, vibrators, indicator lights, etc.
[0054] The communication interface 1040 is used to connect a communication module (not shown in the figure) to enable communication between this device and other devices. The communication module can communicate via wired means (such as USB, Ethernet cable, etc.) or wireless means (such as mobile network, WIFI, Bluetooth, etc.).
[0055] Bus 1050 includes a pathway for transmitting information between various components of the device, such as processor 1010, memory 1020, input / output interface 1030, and communication interface 1040.
[0056] It should be noted that although the above-described device only shows the processor 1010, memory 1020, input / output interface 1030, communication interface 1040, and bus 1050, in specific implementations, the device may also include other components necessary for normal operation. Furthermore, those skilled in the art will understand that the above-described device may only include the components necessary for implementing the embodiments of this specification, and not necessarily all the components shown in the figures.
[0057] The electronic devices described above are used to implement the corresponding methods in any of the foregoing embodiments and have the beneficial effects of the corresponding method embodiments, which will not be repeated here.
[0058] The computer-readable medium of this embodiment includes permanent and non-permanent, removable and non-removable media, and information storage can be implemented by any method or technology. Information can be computer-readable instructions, data structures, program modules, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transfer medium that can be used to store information accessible by a computing device.
[0059] The computer instructions stored in the storage medium of the above embodiments are used to cause the computer to perform the methods described in any of the above embodiments, and have the beneficial effects of the corresponding method embodiments, which will not be repeated here.
[0060] Those skilled in the art should understand that the discussion of any of the above embodiments is merely exemplary and is not intended to imply that the scope of this application (including the claims) is limited to these examples; within the framework of this application, the technical features of the above embodiments or different embodiments can also be combined, the steps can be implemented in any order, and there are many other variations of different aspects of the embodiments of this application as described above, which are not provided in the details for the sake of brevity.
[0061] Additionally, to simplify the description and discussion, and to avoid obscuring the embodiments of this application, the well-known power / ground connections to integrated circuit (IC) chips and other components may or may not be shown in the provided drawings. Furthermore, the apparatus may be shown in block diagram form to avoid obscuring the embodiments of this application, and this also takes into account the fact that the details of the implementation of these block diagram apparatuses are highly dependent on the platform on which the embodiments of this application will be implemented (i.e., these details should be fully understood by those skilled in the art). While specific details (e.g., circuits) have been set forth to describe exemplary embodiments of this application, it will be apparent to those skilled in the art that the embodiments of this application can be implemented without these specific details or with variations thereof. Therefore, these descriptions should be considered illustrative rather than restrictive.
[0062] Although this application has been described in conjunction with specific embodiments thereof, many substitutions, modifications, and variations of these embodiments will be apparent to those skilled in the art from the foregoing description. For example, other memory architectures (e.g., dynamic RAM (DRAM)) may be used with the embodiments discussed.
[0063] The embodiments of this application are intended to cover all such substitutions, modifications, and variations that fall within the broad scope of the appended claims. Therefore, any omissions, modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the embodiments of this application should be included within the protection scope of this application.
Claims
1. An automatic pickup method of information of a release source of an explosive dangerous gas, characterized by, The method comprises the following steps: file processing is performed on the input explosion-hazardous gas release source condition diagram to save multiple PDF files and name them respectively; a corresponding natural language description text is generated by extracting the file name of the PDF file; the PDF file and the natural language description text are uploaded to an AI model application platform, and the AI model application platform picks up explosion-hazardous gas release source information according to file content and user demand, wherein the release source information is in the form of natural language.
2. The method of claim 1, wherein: a release source typical legend in the release source condition diagram is saved as a PDF file, and the file is named "first legend".
3. The method of claim 2, wherein: the natural language description generated by the PDF file with the file name "first legend" includes a description of the legend style and a description of the relative position of the related information in the legend.
4. The method according to claim 1 or 2, characterized in that, Further comprising: after the release source condition diagram is marked by zones, the graphics inside the frame are grouped and cut according to each zone to save them as separate PDF files, and the multiple PDF files are named in a preset sequence.
5. The method of claim 4, wherein, The marking of the release source condition diagram by zones comprises: in the release source condition diagram, the lower left corner inside the frame is marked as the coordinate origin, and starting from this point, a square of a predetermined size is placed inside the frame according to the drawing scale, and the coordinates of the lower left corner of each square relative to the starting point are marked in each square in the form of a one-dimensional array.
6. The method of claim 4, wherein: the natural language description generated by the PDF file sorted in a preset sequence includes a description of the method of obtaining the release source relative coordinates and a description of the information category requirement.
7. The method of claim 1, wherein, Further comprising: the explosion-hazardous gas release source information extracted by the AI model application platform is output in the form of a two-dimensional array.
8. The method of claim 7, wherein: the two-dimensional array is converted into a programming language to generate an explosion-hazardous area division diagram.
9. An automatic pick-up system of information of a source of release of explosive dangerous gas, characterized in that, The method comprises the following steps: a file processing module configured to perform file processing on an input explosion-hazardous gas release source condition diagram to save multiple PDF files and name them respectively; a file extraction module configured to generate a corresponding natural language description text by extracting the file name of the PDF file; an information pickup module configured to upload the PDF file and the natural language description text to an AI model application platform, and the AI model application platform picks up explosion-hazardous gas release source information according to file content and user demand, wherein the release source information is in the form of natural language.
10. A non-transitory computer-readable storage medium, comprising: wherein: the non-transitory computer-readable storage medium stores computer instructions for causing a computer to execute the method of any one of claims 1-8.