Nuclear power engineering drawing semi-structured and search method, device and electronic equipment

By using object detection and text recognition algorithms to perform semi-structured processing on nuclear power plant drawings, functional location codes and data tables are generated, solving the problem that nuclear power plant drawings cannot be directly searched and achieving efficient and accurate extraction and query of drawing data.

CN117251600BActive Publication Date: 2026-02-17YANGJIANG NUCLEAR POWER +1
View PDF 2 Cites 0 Cited by

Patent Information

Application Number
CN202310946436.9
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2023-07-28
Publication Date
2026-02-17
Estimated Expiration
2043-07-28

AI Technical Summary

Technical Problem

Nuclear power plant engineering drawings cannot be directly searched and queried. Relying on manual search is time-consuming, labor-intensive, and prone to errors, leading to delays in upstream tasks and cost overruns.

Method used

The system employs object detection algorithms to detect symbols and markings on drawings, combines text recognition algorithms to identify the content of the markings, generates functional location codes, and constructs a data table linking to the drawings, thereby achieving semi-structured drawing.

Benefits of technology

Significantly reduce labor costs, improve the efficiency and quality of drawing data extraction, achieve instant drawing search and identification, and improve work efficiency and accuracy on-site.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN117251600B_ABST
    Figure CN117251600B_ABST
Patent Text Reader

Abstract

The present application relates to nuclear power engineering drawing semi-structured and search method, device and electronic equipment, including: the drawing to be processed is detected, and the symbol, identification and position information of all objects in the drawing are obtained; the figure text association is carried out; the identification of the figure text association is identified, and the text content of the identification is obtained; the type of the object is determined; the text content is compiled to generate the function position code of the object; the data table is formed based on the text content, the object type, the position information, the function position code and the drawing number of the drawing to be processed; the link relationship of the data table and the drawing, the link relationship of the data entry and the object in the drawing page are constructed, and the semi-structured of the drawing to be processed is completed. The present application greatly reduces the labor cost of engineering drawing data extraction; greatly improves the efficiency and quality of engineering drawing data extraction; also can realize the second search and second determination of the drawing, and effectively improves the efficiency and accuracy of the use of engineering drawing in the business field.
Need to check novelty before this filing date? Find Prior Art

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of drawing data processing, and more particularly to a nuclear power engineering drawing semi-structured and search method, device and electronic equipment. BACKGROUND

[0002] The common drawing of nuclear power plant is almost composed of symbols representing components and pipelines and other basic illustrations, which describe the relationship between components and components in the nuclear power plant. Each symbol represents a specific type of component, such as valve, pump, pipeline, heat exchanger, flow transmitter, etc., and each symbol is associated with a unique name as an identifier. The shape of these symbols and the meaning of their identifiers are defined in a file for each power plant. These engineering drawings are one of the basic and most important inputs for daily operation data analysis and safety analysis of nuclear power plants. The existing drawings of nuclear power plants are mostly in PDF hard copy format, which cannot be directly searched and queried, and the query and extraction of information in the drawings all rely on manpower. At present, the application of these traditional drawings in nuclear power plants usually requires experienced engineers to search for target drawings in a large number of drawings, and then manually check the drawings to obtain target information. The whole process requires a lot of manpower and time cost, and is easy to make mistakes, which can also cause delay of upstream tasks and cost overrun. SUMMARY

[0003] The technical problem to be solved by the present application is to provide a nuclear power engineering drawing semi-structured and search method, device and electronic equipment.

[0004] The technical scheme adopted by the present application to solve the technical problem is: a nuclear power engineering drawing semi-structured and search method is constructed, comprising the following steps:

[0005] Detecting the to-be-processed drawing by using a target detection algorithm to obtain the symbol, identifier and position information of all objects in the drawing;

[0006] Associating the symbol and identifier of the object with the symbol text;

[0007] Recognizing the identifier of the object whose symbol text association has been completed by using a text recognition algorithm to obtain the text content of the identifier;

[0008] Performing type recognition according to the text content to determine the type of the object corresponding to the text content;

[0009] Compiling the text content to generate a function position code of the object;

[0010] Forming a data table based on the text content, the type of the object, the position information, the function position code and the drawing number of the to-be-processed drawing;

[0011] The link relationship between the data table and the drawing is constructed, the link relationship between the data entry and the object in the drawing page is constructed, and the semi-structured of the to-be-processed drawing is completed.

[0012] In the nuclear power engineering drawing semi-structured and search method, the target detection algorithm is used to detect the to-be-processed drawing, and the symbol, the identification and the position information of all objects in the drawing are obtained.

[0013] The target detection algorithm is used to detect the to-be-processed drawing, and the symbol and the identification of all objects in the drawing are obtained.

[0014] In the detection process, the rectangular coordinate system is established, and the position information is determined.

[0015] The position information is extracted and stored.

[0016] In the nuclear power engineering drawing semi-structured and search method, the symbol and the identification of the object are associated with the icon text, and the symbol and the identification of the object are associated with the icon text.

[0017] The identification located around each symbol is obtained.

[0018] The distance between each symbol and the identification around the symbol is calculated.

[0019] The icon text association is performed according to the nearest distance principle.

[0020] In the nuclear power engineering drawing semi-structured and search method, the identification text content is obtained by using the text recognition algorithm to recognize the identification after the icon text association is completed.

[0021] The text recognition algorithm is used to recognize the identification after the icon text association is completed, and the recognition text is obtained.

[0022] The recognition text is verified according to the preset identification content library, and the text content after verification is extracted; the text content after verification is the recognized text content.

[0023] In the nuclear power engineering drawing semi-structured and search method, the type of the object corresponding to the text content is determined according to the type recognition of the text content.

[0024] The type of the object corresponding to the text content is determined according to the type recognition of the text content and the naming rules of the drawing component name.

[0025] In the nuclear power engineering drawing semi-structured and search method, the function position code of the object is generated by compiling the text content.

[0026] The function position code coding rule of the power plant is obtained.

[0027] According to the function position code coding rule of the power plant, the text content is compiled to generate the function position code of the object.

[0028] In the method for semi-structuring and searching of nuclear power engineering drawings provided by the application, the method further comprises:

[0029] The data table, the link relationship between the data table and the drawing, and the link relationship between the data entry and the object in the drawing page are stored.

[0030] In the method for semi-structuring and searching of nuclear power engineering drawings provided by the application, the method further comprises:

[0031] The function position code or the object name of the object to be searched is obtained;

[0032] The data table matched with the object to be searched is determined according to the function position code or the object name.

[0033] The drawing corresponding to the object to be searched is determined based on the data table and the link relationship between the data table and the drawing.

[0034] The position of the object to be searched in the drawing is determined according to the link relationship between the data entry and the object in the drawing page, and the object to be searched is highlighted in the drawing.

[0035] The application further provides a device for semi-structuring and searching of nuclear power engineering drawings, comprising:

[0036] A drawing element detection unit is configured to detect the drawing to be processed by using a target detection algorithm to obtain the symbol, the identification and the position information of all objects in the drawing;

[0037] An identification association unit is configured to associate the symbol and the identification of the object by using a drawing-text association algorithm.

[0038] An identification unit is configured to identify the identification associated by using a text recognition algorithm to obtain the text content of the identification.

[0039] A type division unit is configured to identify the type of the object according to the text content.

[0040] A function position code generation unit is configured to compile the text content to generate the function position code of the object.

[0041] A data table construction unit is configured to form a data table based on the text content, the type of the object, the position information, the function position code and the drawing number of the drawing to be processed.

[0042] The association relationship construction unit is configured to construct a link relationship between the data table and the drawing and a link relationship between the data entry and the object in the drawing page, and complete the semi-structuring of the to-be-processed drawing.

[0043] The application further provides an electronic device comprising a memory and a processor, wherein the memory stores a computer program, and the processor executes the steps of the nuclear power engineering drawing semi-structuring and searching method according to the above item by calling the computer program stored in the memory.

[0044] The nuclear power engineering drawing semi-structuring and searching method, device and electronic device provided by the application have the following beneficial effects: the to-be-processed drawing is detected to obtain the symbol, identification and position information of all objects in the drawing, the symbol text association is performed, the identification of the symbol text association is identified to obtain the text content of the identification, the type of the object is determined, the text content is compiled to generate the function position code, the data table is formed based on the text content, the type of the object, the position information, the function position code and the drawing number of the to-be-processed drawing, the link relationship between the data table and the drawing and the link relationship between the data entry and the object in the drawing page are constructed, and the semi-structuring of the to-be-processed drawing is completed. The application greatly reduces the labor cost of engineering drawing data extraction, greatly improves the efficiency and quality of engineering drawing data extraction, and can also realize the second search and second determination of the drawing, thereby effectively improving the efficiency and accuracy of the use of engineering drawings in the business field. BRIEF DESCRIPTION OF DRAWINGS

[0045] The application will be further described below in combination with the drawings and embodiments, wherein:

[0046] Figure 1 FIG. 1 is a flowchart of the nuclear power engineering drawing semi-structuring and searching method according to an embodiment of the application;

[0047] Figure 2 FIG. 2 is a flowchart of the nuclear power engineering drawing semi-structuring and searching method according to another embodiment of the application;

[0048] Figure 3 FIG. 3 is a structural diagram of the nuclear power engineering drawing semi-structuring and searching device according to the application. DETAILED DESCRIPTION

[0049] The technical solutions in the embodiments of the application will be clearly and completely described below in combination with the drawings in the embodiments of the application. Obviously, the described embodiments are only part of the embodiments of the application, rather than all the embodiments of the application. Based on the embodiments in the application, all other embodiments obtained by those skilled in the art without creative labor fall within the protection scope of the application.

[0050] Figure 1A flowchart of a first embodiment of the semi-structured and searching method of nuclear power engineering drawings provided by the present application is shown.

[0051] As shown in Figure 1 , the semi-structured and searching method of nuclear power engineering drawings comprises the following steps:

[0052] In step S101, a target detection algorithm is used to detect the to-be-processed drawing to obtain the symbols, labels and position information of all objects in the drawing.

[0053] In this embodiment, the target detection algorithm is used to detect the to-be-processed drawing to obtain the symbols and labels of all objects in the drawing, a rectangular coordinate system is established during the detection process to determine the position information, and the position information is extracted and stored.

[0054] Specifically, after the to-be-processed drawing is input, a target detection algorithm is used to detect the symbols and labels of each object included in the drawing. The objects in the drawing can be devices, components, etc. When the object is a device, the symbol is the symbol of the device, and when the object is a component, the symbol is the symbol of the component. In this embodiment, the symbol is the symbol used to represent the object, such as a rectangular frame which can represent a resistor and its label is "R". During the detection process, a rectangular coordinate system is established to extract and store the position information of the detected objects in the drawing, i.e. the position coordinates of the detection frame. The position information includes the position information of the symbol and the position information of the label.

[0055] In step S102, the symbol of the object is associated with the label.

[0056] In this embodiment, associating the symbol of the object with the label comprises obtaining the labels located around each symbol, calculating the distance between each symbol and the labels around it, and associating the symbols with the labels according to the nearest distance principle.

[0057] Specifically, after all the symbols and labels in the to-be-processed drawing are detected in step S101, the distance between each detected symbol and the labels around it is calculated, and the label with the nearest distance is associated with the symbol according to the nearest distance principle to complete the binding of the symbol and its label (the label corresponding to the nearest distance). Through this method, the association and binding of all symbols and their labels of the to-be-processed drawing can be completed. It should be noted that in this embodiment, each symbol in the drawing is associated with a unique label, which is the label of the object.

[0058] In step S103, a text recognition algorithm is used to recognize the labels that have completed the symbol-text association to obtain the text content of the labels.

[0059] In this embodiment, the text recognition algorithm is used to recognize the completed icon-text association identification, and the text content of the identification is obtained, including: using the text recognition algorithm to recognize the completed icon-text association identification, obtaining the recognized text; checking the recognized text according to the preset identification content library, and extracting the text content after checking; the text content after checking is the recognized text content.

[0060] Specifically, after all the symbols in the to-be-processed drawing are associated and bound with their identifications in step S102, a text recognition algorithm is used to recognize each identification, and the recognized text is checked according to the preset identification content library, and finally the text content after checking is extracted. Among them, the recognized text is checked according to the preset identification content library: the recognized text is compared with the reference text in the preset identification content library, if the recognized text is the same as the reference text, it is determined as correct text, and the text is extracted, otherwise, it is determined as incorrect text.

[0061] Step S104, type recognition is performed according to the text content to determine the type of the object corresponding to the text content.

[0062] In this embodiment, the type of the object corresponding to the text content is determined according to the naming rule of the drawing component name and the text content, including: performing type recognition according to the naming rule of the drawing component name and the text content, and determining the type of the object corresponding to the text content.

[0063] Specifically, in this embodiment, according to the drawing component name definition file of the nuclear power plant (such as the equipment function code list), the physical meaning represented by the text content (such as component type, model, etc.) is recognized based on the naming rule of the drawing component name, so as to determine the type of the object corresponding to the text content. For example, the end of the text content is EX, which represents that the object corresponding to the text content represents a heat exchanger; for another example, the end of the text content is VV, which represents that the object corresponding to the text content represents a steam valve, etc. Further, the recognized object type is added to the originally extracted data (i.e. the corresponding text content extracted in step S102) in the form of a string.

[0064] Step S105, compiling the text content to generate the function position code of the object.

[0065] In this embodiment, the text content is compiled to generate the function position code of the object, including: obtaining the function position code coding rule of the power plant; compiling the text content according to the function position code coding rule of the power plant to generate the function position code of the object.

[0066] Specifically, in this embodiment, the text content is compiled according to the functional location code encoding rules of nuclear power plants (i.e., adding a string representing power plant / unit information before the text content) to generate a string-type functional location code.

[0067] Step S106: A data table is formed based on the text content, object type, location information, function location code, and drawing number of the drawing to be processed.

[0068] Specifically, in this embodiment, based on all the information extracted in the aforementioned steps, a data table is established that includes the object's functional location code, identification content, text content, object type, location information (i.e., symbol coordinates, identification coordinates), and drawing number.

[0069] Step S107: Construct the link relationship between the data table and the drawing, and the link relationship between the data entries and objects within the drawing page, to complete the semi-structured drawing to be processed.

[0070] Specifically, in this embodiment, after obtaining the data table of the drawing to be processed in step S106, the link relationship between the data table and the drawing, and the link relationship between data entries and objects within the drawing page can be further established, thereby completing the semi-structured processing of the drawing to be processed. The link relationship between the data table and the drawing can be used to directly determine the corresponding drawing based on the data table, or to directly locate the corresponding data table based on the drawing. The link relationship between data entries and objects within the drawing page can be used to quickly locate the specific position of the object to be searched within the drawing based on the determined drawing.

[0071] Furthermore, in this embodiment, the semi-structured and search method for nuclear power engineering drawings also includes: storing data tables, the link relationship between data tables and drawings, and the link relationship between data entries and objects within the drawing pages.

[0072] Figure 2 The diagram shows a flowchart of Embodiment 2 of the semi-structured and search method for nuclear power engineering drawings provided by the present invention.

[0073] like Figure 2 As shown, in this embodiment, the semi-structured and search method for nuclear power engineering drawings further includes:

[0074] Step S201: Obtain the function location code or object name of the object to be searched.

[0075] Step S202: Search according to the function location code or object name to determine the data table that matches the object to be searched.

[0076] Step S203: Based on the data table and the link relationship between the data table and the drawings, determine the drawing corresponding to the object to be searched.

[0077] Step S204, according to the linking relationship between the data entry and the object in the drawing page, the location of the object to be searched in the drawing is determined, and the object to be searched is highlighted in the drawing.

[0078] Specifically, in the embodiment, when the user needs to search for a device or component in multiple drawings, the function location code or component name is input, at this time, the background can directly determine the data table containing the function location code or component name according to the function location code or component name input by the user, and quickly determine the drawing linked to the data table and locate the corresponding data entry in the data table in combination with the linking relationship between the data table and the drawing, and then open the drawing linked to the data table, quickly locate the device / component according to the symbol coordinates and identification coordinates in the data entry, and highlight the device / component in the drawing (such as yellow highlighting), thereby realizing second search and second positioning of drawing information.

[0079] The present application adopts target detection algorithm and text recognition algorithm, develops a semi-structured method for nuclear power engineering drawings and supports fast query and search of drawing information. The method uses a target detection algorithm based on deep neural network to automatically detect the symbols and identification of component objects in the drawing page, uses a text recognition algorithm to recognize the identification, and then recognizes the object function type (i.e. component type, model, etc.) according to the naming rules of drawing component name definition files, encodes the identification content according to the function location code coding rules of the power plant to generate the function location code, forms a data table containing the object function location code, text identification content, object type, text identification coordinates, corresponding symbol coordinates, and drawing number based on the data obtained in the above steps, and links the drawing to realize semi-structuring of the drawing. For the semi-structured drawing generated by the above steps, the fast query and positioning of drawing information can be supported based on the linking relationship between the data table and the drawing and the linking relationship between the data entry and the component object in the drawing page: the user inputs the function location code / component name, which is equivalent to querying the function location code / text identification content in the database containing these drawing data, the background can quickly locate the corresponding data entry of the corresponding data table, open the drawing linked to the data table, locate the device / component linked to the data entry, and highlight it, thereby realizing second search and second positioning of drawing information. This method can greatly improve the work efficiency and data accuracy of the user in the application scenarios of drawing query / drawing data extraction, reduce the cost of drawing automation, and greatly promote the development of intelligent operation and maintenance technology of nuclear power plants based on basic data.

[0080] The present application does not need to spend a lot of manpower to consult drawings and extract data: can greatly reduce the labor cost of engineering drawing data extraction, greatly improve the efficiency and quality of engineering drawing data extraction. In addition, the present application does not need the on-site staff to repeatedly review a large number of drawings, realizes the second search and second determination of the drawings, improves the work efficiency: can greatly reduce the time cost of business on-site engineering drawings, greatly improve the efficiency and accuracy of business on-site engineering drawings.

[0081] As shown in Figure 3 The present application also provides a nuclear power engineering drawing semi-structured and search device, comprising:

[0082] The drawing element detection unit 301 is used for detecting the to-be-processed drawing by using a target detection algorithm, and obtaining the symbol, identification and position information of all objects in the drawing.

[0083] The identification association unit 302 is used for associating the symbol with the identification.

[0084] The recognition unit 303 is used for recognizing the identification which has completed the symbol-text association by using a text recognition algorithm, and obtaining the text content of the identification.

[0085] The type division unit 304 is used for type recognition according to the text content, and determining the type of the object corresponding to the text content.

[0086] The function position code generation unit 305 is used for compiling the text content, and generating the function position code of the object.

[0087] The data table construction unit 306 is used for forming a data table based on the text content, the type of the object, the position information, the function position code and the drawing number of the to-be-processed drawing.

[0088] The association relationship construction unit 307 is used for constructing the link relationship between the data table and the drawing, and the link relationship between the data entry and the object in the drawing page, and completing the semi-structuring of the to-be-processed drawing.

[0089] Specifically, the specific cooperation operation process between each unit in the nuclear power engineering drawing semi-structured and search device can refer to the above-mentioned nuclear power engineering drawing semi-structured and search method, which will not be described here.

[0090] In addition, an electronic device of the present application includes a memory and a processor; the memory is configured to store a computer program; and the processor is configured to execute the computer program to implement the method for semi-structured search of nuclear power engineering drawings according to any one of the above embodiments. Specifically, according to the embodiments of the present application, the processes described above with reference to the flowcharts can be implemented as a computer software program. For example, an embodiment of the present application includes a computer program product including a computer program carried on a computer readable medium, the computer program including program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed by an electronic device and executed to perform the above functions defined in the method of the embodiments of the present application. The electronic device in the present application can be a notebook computer, a desktop computer, a tablet computer, a smart phone, or the like, and can also be a server.

[0091] The embodiments in the specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the embodiments can be referred to each other. For the device disclosed in the embodiments, since it corresponds to the method disclosed in the embodiments, the description is relatively simple, and the relevant parts can be referred to the method part.

[0092] The skilled person can further realize that the units and algorithm steps of the examples described in combination with the embodiments disclosed herein can be realized by electronic hardware, computer software or a combination of both. In order to clearly illustrate the interchangeability of hardware and software, the components and steps of the examples have been described in the above description in general terms. Whether the functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. The skilled person can use different methods to realize the described functions for each specific application, but such implementation should not be considered beyond the scope of the present application.

[0093] The steps of the method or algorithm described in combination with the embodiments disclosed herein can be directly implemented by hardware, a software module executed by a processor, or a combination of both. The software module can be placed in a random access memory (RAM), a memory, a read-only memory (ROM), an electrically programmable ROM, an electrically erasable programmable ROM, a register, a hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.

[0094] The above embodiments are only for illustrating the technical concept and characteristics of the present application, and the purpose is to enable those skilled in the art to understand the content of the present application and implement it accordingly, and cannot limit the protection scope of the present application. Any equivalent changes and modifications made within the scope of the claims of the present application shall be included in the scope of the claims of the present application.

Claims

1. A method for semi-structuring and searching nuclear engineering drawings, characterized in that, The method comprises the following steps: detecting the to-be-processed drawing by using a target detection algorithm to obtain symbol, identification and position information of all objects in the drawing, including: detecting the to-be-processed drawing by using a target detection algorithm to obtain symbol and identification of all objects in the drawing; establishing a rectangular coordinate system during the detection process to determine the position information; extracting and storing the position information; the position information includes symbol position information and identification position information; associating the symbol of the object with the identification, including: obtaining the identification located around each symbol; calculating the distance between each symbol and the identification around the symbol; associating the symbol with the identification according to the nearest distance principle; recognizing the identification associated with the symbol by using a text recognition algorithm to obtain the text content of the identification; performing type identification according to the text content to determine the type of the object corresponding to the text content; compiling the text content to generate a function position code of the object; forming a data table based on the text content, the type of the object, the position information, the function position code and the drawing number of the to-be-processed drawing; constructing the link relationship between the data table and the drawing and the link relationship between the data entry and the object in the drawing page to complete the semi-structured of the to-be-processed drawing.

2. The method of claim 1, wherein, The method of recognizing the identification associated with the symbol by using a text recognition algorithm to obtain the text content of the identification comprises: recognizing the identification associated with the symbol by using a text recognition algorithm to obtain the recognition text; verifying the recognition text according to a preset identification content library and extracting the text content after verification; the text content after verification is the recognized text content.

3. The method of claim 1, wherein, The method of performing type identification according to the text content to determine the type of the object corresponding to the text content comprises: performing type identification according to the text content and combining the naming rules of the drawing component name to determine the type of the object corresponding to the text content.

4. The method of claim 1, wherein, The method of compiling the text content to generate a function position code of the object comprises: obtaining the function position code coding rules of the power plant; compiling the text content according to the function position code coding rules of the power plant to generate a function position code of the object.

5. The method of claim 1, wherein, The method further comprises: storing the data table, the link relationship between the data table and the drawing and the link relationship between the data entry and the object in the drawing page.

6. The method for semi-structured search and retrieval of nuclear engineering drawings according to any of claims 1 to 5, characterized in that, The method further comprises: obtaining the function position code or the object name of the to-be-searched object; finding the data table matching the to-be-searched object according to the function position code or the object name; determining the drawing corresponding to the to-be-searched object based on the data table and combining the link relationship between the data table and the drawing; determining the position of the to-be-searched object in the drawing according to the link relationship between the data entry and the object in the drawing page and highlighting the to-be-searched object in the drawing.

7. A nuclear engineering drawing semi-structured and search apparatus, characterized by, The method comprises: The figure element detection unit is configured to detect the to-be-processed drawing by using a target detection algorithm to obtain symbol and identification of all objects in the drawing and position information of the objects, including: detecting the to-be-processed drawing by using a target detection algorithm to obtain symbol and identification of all objects in the drawing; establishing a rectangular coordinate system during the detection to determine the position information; extracting and storing the position information; the position information includes position information of the symbol and position information of the identification; The identification association unit is configured to associate the symbol and the identification of the object, including: obtaining the identification located around each symbol; calculating the distance between each symbol and the identification around the symbol; and associating the symbol and the identification according to the nearest distance principle; The recognition unit is configured to recognize the identification after the symbol and the identification are associated by using a text recognition algorithm to obtain text content of the identification; The type division unit is configured to identify the type of the object according to the text content to determine the type of the object corresponding to the text content; The function position code generation unit is configured to compile the text content to generate a function position code of the object; The data table construction unit is configured to form a data table based on the text content, the type of the object, the position information, the function position code and a drawing number of the to-be-processed drawing; The association relationship construction unit is configured to construct a link relationship between the data table and the drawing and a link relationship between a data entry and an object in a page of the drawing to complete semi-structuring of the to-be-processed drawing.

8. An electronic device, comprising: The device comprises a memory and a processor, the memory stores a computer program, and the processor executes the steps of the method according to any one of claims 1 to 6 by calling the computer program stored in the memory.

Citation Information

Patent Citations

  • Engineering drawing association method

    CN110704880A

  • Browsing method based on drawing association

    CN111475663A