Aircraft equipment engineering drawing standard matching recognition method and system based on segmented modeling

Abstract

This invention provides a method and system for matching and recognizing aviation equipment engineering drawing standards based on segmented modeling, belonging to the field of text information processing and retrieval technology. The method includes: S1, acquiring aviation equipment engineering drawings and extracting candidate strings; S2, standardizing the aviation equipment engineering drawings, performing structured segmentation, and constructing candidate standard matching strings; S3, constructing database normalization fields for aviation equipment engineering drawing standards; and S4, performing hierarchical retrieval and recognition of aviation equipment engineering drawing standards based on prefix matching. This invention provides stable recognition and mapping of engineering drawing standard numbers with noise, missing numbers, and inconsistent formats in engineering documents, improving the text processing performance of non-standard aviation equipment engineering drawing standards; employing segmented modeling and prefix matching, it exhibits high processing efficiency and stability in large-scale standard database scenarios; and enhances the analysis efficiency of aviation equipment engineering drawing standard application.

Description

Technical Field

[0001] This invention relates to the field of text information processing and retrieval technology, specifically to a method and system for standard matching and recognition of aviation equipment engineering drawings based on segmented modeling. Background Technology

[0002] In the fields of science, technology, industry, and engineering, standard documents are numerous and diverse. Standard numbers, as crucial indexing information, are widely used for document citation, tracing quality issues, and engineering management. However, in practical applications, standard numbers often suffer from problems such as inconsistent expression, writing errors, and incomplete structure. These problems manifest primarily in three ways: First, inconsistent standard number formats, with multiple symbol representations appearing in different documents. Second, the presence of noise in standard numbers, such as redundant symbols and inconsistent capitalization. Third, missing or redundant standard numbering information, such as missing years or additional chapter numbers.

[0003] In existing systems, the recognition and matching algorithms operate independently. The recognition stage lacks database support, while the matching stage suffers from significant input noise. Traditional string similarity-based matching methods require traversing the database, resulting in high computational complexity and failing to meet the demands of engineering applications. Therefore, improving the recognition accuracy and matching efficiency of standard numbers in the presence of numerous non-standard expressions has become a pressing technical problem that needs to be solved. Summary of the Invention

[0004] To address the shortcomings of existing technologies, this invention aims to provide a method and system for matching and recognizing aviation equipment engineering drawing standards based on segmented modeling. This method significantly improves the mapping success rate and enhances the processing performance of non-standard aviation equipment engineering drawing standard text by stably identifying and mapping engineering drawing standard numbers that contain noise, missing information, or inconsistent formats within engineering documents. Employing segmented modeling and prefix matching avoids full-database similarity calculations, it demonstrates high processing efficiency and stability in large-scale standard database scenarios. The automatic association between aviation equipment engineering drawing standard numbers and aviation equipment model data and technical documents improves the efficiency of analyzing the application of aviation equipment engineering drawing standards. Furthermore, it unifies and matches engineering drawing standard reference information scattered across various aviation equipment engineering drawing documents, supporting standard system management and application analysis, and improving the management and application level of engineering drawing standard resources.

[0005] Specifically, on the one hand, the present invention provides a method and system for matching and recognizing engineering drawing standards for aerospace equipment based on segmented modeling, which includes the following steps: S1: Obtain aviation equipment engineering drawings; extract aviation equipment engineering drawing standards. Standard data for engineering drawing text and corresponding location information According to the standard data location information in the engineering drawings. Filtering yields standard data for engineering drawing text filtering. ; Filter standard data for engineering drawings The scan extracts candidate strings D for aviation equipment engineering drawing standards; the candidate fragments are further filtered using prefixes to obtain a set of candidate engineering drawing standard number strings. ; Obtain candidate strings for engineering drawing standards based on character composition rules. ; Obtain candidate character elements for engineering drawing standards based on prefix rules ; S2: For each engineering drawing standard candidate character element obtained in step S1 Perform character-level standardization; standard candidate strings for engineering drawings After standardization conversion, the standardized string of the engineering drawing is obtained. The structured engineering drawing is segmented according to character type; the standard segmented structured engineering drawing is concatenated to construct a candidate standard matching string for aerospace equipment engineering drawings. ; S3: Construct database normalization fields for aviation equipment engineering drawing standards; use a data table in the aviation equipment engineering drawing standard database to record standard number and standard name information for auxiliary matching; S4: Perform hierarchical retrieval and identification of aviation equipment engineering drawing standards based on prefix matching. Based on the standardized engineering drawing string from step S2... Constructed engineering drawing standard multi-level candidate string set The set of multi-level candidate strings for engineering drawing standards The strings in the code are sorted by length to form a multi-level candidate string list for engineering drawing standards. Following the order of the multi-level candidate string list of engineering drawing standards, the database normalized field is extracted from the database standard information table to perform prefix matching of aviation equipment engineering drawing standards, thereby obtaining hierarchical retrieval and identification results.

[0006] Preferably, step S1 specifically includes: S11: Obtain aviation equipment engineering drawings and identify the extracted first standard set. Second standard set ; Forming a standard class of aviation equipment engineering drawings ; S12: Extract standard data for aviation equipment engineering drawings. For each aviation equipment engineering drawing standard... Extract the standard data of the engineering drawing text. and corresponding location information Set location information filtering threshold The filtered data yields standard data for engineering drawing text filtering. ; S13: Filter standard data for engineering drawing text. The scan is performed to extract candidate strings D for aviation equipment engineering drawings; the candidate fragments are further filtered using prefixes to obtain a set of candidate engineering drawing standard number strings. .

[0007] Preferably, in step S12, the engineering drawing text standard data and corresponding location information The method for obtaining it is as follows: ; in, Standard data for engineering drawings; This refers to the location information of standard data in engineering drawings and text. For engineering drawing text recognition parameters; For layout recognition model; Standards for aviation equipment engineering drawings; This is a text character recognition model.

[0008] Preferably, the method for obtaining the candidate string of the aviation equipment engineering drawing standard in S13 is as follows: ; Where D represents a candidate string for aviation equipment engineering drawing standards; Candidate strings for engineering drawing standards; A standard scanned model of engineering drawings; This is a set of rules for forming the standard letter numbers of engineering drawings.

[0009] Preferably, the set of candidate engineering drawing standard number strings in step S13 is: ; in, A set of candidate engineering drawing standard number strings; Candidate character elements for engineering drawing standards; A set of letter prefixes for standard engineering drawing numbers; This is a function for processing prefix rules.

[0010] Preferably, step S2 specifically includes: S21: Standardize the processing of noisy characters in aviation equipment engineering drawings, and standardize candidate strings for engineering drawings. After standardization conversion, the standardized string of the engineering drawing is obtained. ; S22: Perform structured segmentation of aviation equipment engineering drawings; standardize the processed engineering drawings into strings. The characters are segmented into structured segments according to their type to form an ordered sequence. S23: Construct candidate standard matching strings for aerospace equipment engineering drawings; segment the results of structured engineering drawing standards. Concatenate the strings to construct a multi-level candidate string set for engineering drawing standards. .

[0011] Preferably, the structured segmentation rules in step S22 are as follows: First rule: If a character that is neither a number nor a letter appears, use that character as a delimiter for structured segmentation; Rule 2: If there is a part where numbers and letters are directly connected, separate the numbers and letters in that part.

[0012] Preferably, the multi-level candidate string list for engineering drawing standards in step S4 is as follows: ; in, For the first A multi-level candidate string for each engineering drawing standard; A function for identifying string length; For engineering drawing standards, multi-level candidate string numbering; This represents the total number of candidate strings for the engineering drawing standard at multiple levels.

[0013] On the other hand, the present invention provides an aviation equipment engineering drawing standard identification and matching system based on a segmented modeling method, which includes: a drawing generation module, a drawing management module, a drawing parsing module, and a standard information storage module; The drawing generation module generates configuration and standard numbering information for aviation equipment components; The drawing management module downloads aviation equipment engineering drawing files in batches on a daily schedule for use by the parsing module; The drawing parsing module performs character extraction and entity disambiguation on the standard numbers of engineering drawings in aviation equipment engineering drawings, mapping noisy standard numbers of engineering drawings to unique standard numbers in the aviation equipment engineering drawing standard database; The standard information storage module is used to store information from the general library of engineering drawing standards and the database of aerospace equipment engineering drawing standards.

[0014] Compared with the prior art, the beneficial effects of the present invention are as follows: (1) The present invention can improve the performance of non-standard aviation equipment engineering drawing standard text processing; it can stably identify and map the standard numbers of engineering drawings that have noise, missing parts and inconsistent formats in the engineering documents, and greatly improve the mapping success rate.

[0015] (2) The present invention can reduce computational complexity and improve engineering applicability; by adopting segmented modeling and prefix matching, it avoids full database similarity calculation and has high processing efficiency and stability in large-scale standard database scenarios.

[0016] (3) The present invention can support the association and analysis of engineering data; it can automatically associate the standard number of aviation equipment engineering drawings with aviation equipment model data and technical documents, thereby improving the analysis efficiency of the application of aviation equipment engineering drawing standards.

[0017] (4) This invention can improve the management and application level of engineering drawing standard resources; it can collect and match the engineering drawing standard reference information scattered in various aviation equipment engineering drawing documents in a unified manner, and support the management and application analysis of the standard system. Attached Figure Description

[0018] Figure 1 This is a flowchart of the aviation equipment engineering drawing standard recognition and matching method based on segmented modeling of the present invention; Figure 2 This is a detailed flowchart of the steps in the aviation equipment engineering drawing standard recognition and matching method based on segmented modeling of the present invention; Figure 3 This is a flowchart illustrating the overall process of standard number identification and matching in this embodiment of the invention. Figure 4 This is an example diagram of an engineering drawing application object in an embodiment of the present invention; Figure 5 This is a diagram illustrating the process of extracting candidate standard numbers and structural segmentation in an embodiment of the present invention. Figure 6 This diagram illustrates the database normalization field construction and hierarchical prefix matching mechanism in an embodiment of the present invention. Detailed Implementation

[0019] Hereinafter, embodiments of the present invention will be described with reference to the accompanying drawings.

[0020] This invention proposes a method for identifying and matching standards in aerospace equipment engineering drawings based on segmented modeling, such as... Figure 1 As shown, the process involves obtaining aviation equipment engineering drawings and extracting candidate strings; standardizing the aviation equipment engineering drawings by performing structured segmentation and constructing candidate standard matching strings; constructing a database normalized field for aviation equipment engineering drawing standards; and performing hierarchical retrieval and identification of aviation equipment engineering drawing standards based on prefix matching. Figure 2 The diagram shows a detailed flowchart of the steps in the aerospace equipment engineering drawing standard recognition and matching method based on segmented modeling of the present invention. The technical operations and details of each step are explained. The detailed matching and recognition execution process of the aerospace equipment engineering drawing standard recognition and matching method based on segmented modeling in this embodiment of the invention is as follows: Figure 3 As shown, the specific steps include: Step S1: Obtain aviation equipment engineering drawings and extract candidate strings from the aviation equipment engineering drawings; extract the standard number candidate set from the original aviation equipment engineering drawings, specifically including the following steps: Step S11: Obtain aviation equipment engineering drawings. This embodiment of the invention has been deployed as a practical engineering project on a standard platform. The aviation equipment engineering drawings in this embodiment are, for example... Figure 4 The image shown is a standard part drawing of a specific aerospace equipment component, including the drawing and necessary information. It was obtained from an aerospace equipment engineering drawing standard platform. Collection of all standard aviation equipment engineering drawings uploaded at the time Specifically, they can be divided into two categories: one is to directly use layout recognition tools. Directly extract the first standard set Another type is scanned aerospace equipment engineering drawings, which require text character recognition. Extracting the second standard set after model recognition ; Forming a standard class of aviation equipment engineering drawings .

[0021] Step S12: Extract standard data for aviation equipment engineering drawings. For each aviation equipment engineering drawing standard... Extract the standard data of the engineering drawing text. and corresponding location information Specifically: ; in, Standard data for engineering drawings; This refers to the location information of standard data in engineering drawings and text. These are the text recognition parameters for engineering drawings, used when the document can be recognized using a layout recognition tool. ,otherwise ; For layout recognition model; Standards for aviation equipment engineering drawings; This is a text character recognition model.

[0022] Due to engineering requirements, standard text data in certain areas of aviation equipment engineering drawings should not be included in the recognition scope. For example, the preface section of the technical document in the embodiment is set as a location information filtering threshold. According to the standard data location information in the engineering drawings. Filtering yields standard data for engineering drawing text filtering. .

[0023] Step S13: Extract standard candidate strings for aviation equipment engineering drawings. Filter standard data from the engineering drawing text. The scan was performed to extract strings containing letters, numbers, and hyphens as candidate strings for aerospace equipment engineering drawings. Specifically: ; Where D represents a candidate string for aviation equipment engineering drawing standards; Candidate strings for engineering drawing standards; A standard scanned model of engineering drawings; This is a set of rules for forming the standard letter numbers of engineering drawings.

[0024] Meanwhile, since the standard numbering of engineering drawings has a specific letter prefix, it is a set of letter prefixes for the standard numbering of engineering drawings. Further filtering of candidate fragments using prefixes yields the following set of candidate engineering drawing standard number strings: .

[0025] in, A set of candidate engineering drawing standard number strings; Candidate character elements for engineering drawing standards; A set of letter prefixes for standard engineering drawing numbers; This is a function for processing prefix rules.

[0026] The document is retrieved from the system. Below is a document example. In this example, the initial candidate strings for aviation equipment engineering drawings extracted by the OCR model are: 3. Drawing instructions according to Q / 800106; 2. Cleanliness level according to Q / 8S01582 Class C; 1. *Standard dimensions in the component processing standard; AECC608, surface roughness; Some text appears outside the extraction range. After deletion, the engineering drawing text filtering standard data is obtained. The results obtained through step S1 are as follows: 3. Drawings and specifications are in accordance with Z800106. 2. Cleanliness level is in accordance with Q / 8S01582 grade c. 1. *Standard dimensions are the machining standards in the components.

[0027] Candidate strings for engineering drawing standards are obtained based on character composition rules. Z800106 and Q / 8S01582 c.

[0028] Candidate character elements for engineering drawing standards are obtained based on prefix rules. : Q / 8S01582 c, prefixed with Q / 8S.

[0029] Step S2: Standardize the aviation equipment engineering drawings, perform structured segmentation, and construct candidate standard matching strings for the aviation equipment engineering drawings; such as... Figure 5 The diagram shows the process of candidate standard number extraction and structured segmentation in an embodiment of the present invention. The specific execution process includes the following steps: Step S21: Standardize noisy characters in aerospace equipment engineering drawings. For each candidate standard character element obtained in step S1... Perform character-level normalization. The process is divided into two categories: one is replacement, such as converting lowercase letters to uppercase letters and replacing special characters, such as ·→. and -→-; the other is deletion, such as removing some non-alphanumeric characters. The final result is a standardized string for the engineering drawing. .

[0030] Candidate strings for engineering drawing standards After standardization conversion, the standardized string of the engineering drawing is obtained. Q / 8S01582C, in the specific operation of the embodiment, is to replace 'c' with 'C' and remove the spaces between characters.

[0031] Step S22: Perform structured segmentation of the aerospace equipment engineering drawings. Standardize the processed engineering drawings into strings. The characters are segmented in a structured manner according to their type, forming an ordered sequence, including: letter prefix segment, number body segment, year segment, or additional information segment; the structured segmentation rules are as follows: First rule: If a non-numeric or non-alphanumeric character appears, use that character as a delimiter for structured segmentation.

[0032] Rule 2: If there is a part where numbers and letters are directly connected, separate the numbers and letters in that part.

[0033] Specifically, in this embodiment of the invention, GJB 207-2003AG contains two characters that satisfy the first rule: a space and a hyphen (-), and one character that satisfies the second rule, case 3A. The final structured engineering drawing standard segmentation is [GJB, 207, 2003, AG]. The structured engineering drawing standard segmentation result is... Based on the splitting rules, standardize the engineering drawing into a string. Split into .

[0034] Step S23: Construct candidate standard matching strings for aerospace equipment engineering drawings. Based on the characteristic that the numbering order is relatively stable but information is easily missing, the segmented structured engineering drawing standard is concatenated, and the tail fields are gradually truncated to construct a multi-level candidate string set for engineering drawing standards. The segmentation results of the structured engineering drawing standards are then analyzed. Construct a multi-level candidate string set for engineering drawing standards. , For the first A structured engineering drawing standard segmented structure. The multi-level candidate string set for the engineering drawing standard obtained in this embodiment is specifically as follows: .

[0035] Step S3: Construct database normalization fields for aviation equipment engineering drawing standards. For example... Figure 6 The diagram illustrates the database normalization field construction and hierarchical prefix matching mechanism according to an embodiment of the present invention. In the standard system for aviation equipment engineering drawings, a data table recording information such as standard numbers and standard names in the aviation equipment engineering drawing standard database needs to be constructed in this data table for auxiliary matching. Based on the existing standard numbers, the following operations are performed: Remove all non-alphanumeric characters from the standard characters of the engineering drawing.

[0036] Standardize the capitalization of engineering drawings.

[0037] Form a continuous standard string representation of engineering drawings.

[0038] The final result is the normalized field g in the standard database of engineering drawings.

[0039] In this embodiment of the invention, the actual standard number in the database of aviation equipment engineering drawing standards is Q / 8S01582-2008, and the normalized field g of the engineering drawing standard database in step S4 is Q8S015822008.

[0040] Step S4: Perform hierarchical retrieval and identification of aviation equipment engineering drawing standards based on prefix matching. This is done based on the standardized strings of the engineering drawings. Constructed engineering drawing standard multi-level candidate string set The set of multi-level candidate strings for engineering drawing standards The strings in the code are sorted from longest to shortest to form a multi-level candidate string list for engineering drawing standards: .

[0041] in, For the first A multi-level candidate string for each engineering drawing standard; A function for identifying string length; For engineering drawing standards, multi-level candidate string numbering; This represents the total number of candidate strings for the engineering drawing standard at multiple levels.

[0042] Following the order of the multi-level candidate string list of engineering drawing standards, the normalized field is extracted from the standard information table in the database for prefix matching. The SQL statement used is: `SELECT; standard_database FROM; WHERE normalized_field_g LIKE 'candidate_string'` %'; ORDER BY drawing standard number DESC. When multiple drawing standard matching results exist, the drawing standard number with the oldest year is selected as the final matching result.

[0043] In the embodiment, the multi-level candidate string set of engineering drawing standards is used. Convert to a multi-level candidate string list for engineering drawing standards The SQL statements in step S4 are executed sequentially. Finally, when SELECT standard number, FROM standard library, WHERE normalized field g LIKE 'Q8S01582%', ORDER BY standard number DESC, the standard number Q / 8S 01582-2008 is retrieved, and the final engineering drawing standard matching result is obtained.

[0044] The second aspect of this invention proposes an aviation equipment engineering drawing standard identification and matching system based on a segmented modeling method, specifically including: a drawing generation module, a drawing management module, a drawing parsing module, and a standard information storage module.

[0045] The drawing generation module uses professional drawing tools such as UG to draw the configuration of aircraft equipment parts, and the drawings will contain explanatory information such as the standard number on which they are based.

[0046] The drawing management module downloads uploaded aviation equipment engineering drawing files in batches daily at set times for use by the parsing module.

[0047] The drawing parsing module performs character extraction and entity disambiguation on the engineering drawing standard numbers in aviation equipment engineering drawings, mapping noisy engineering drawing standard numbers to unique engineering drawing standard numbers in the aviation equipment engineering drawing standard database.

[0048] The standard information storage module stores two types of information: one is the overall database of engineering drawing standards, which contains information such as the engineering drawing standard number and engineering drawing standard name of all standards of interest; the other is the database of aviation equipment engineering drawing standards for each aviation equipment model, which maintains the engineering drawing standard number information used in the design process for each aviation equipment model.

[0049] The beneficial effects of the embodiments of the present invention are as follows: The present invention proposes a method and system for identifying and matching aviation equipment engineering drawing standards based on segmented modeling, which can improve the text processing performance of non-standard aviation equipment engineering drawing standards; reduce computational complexity, improve engineering applicability, and have high processing efficiency and stability in large-scale standard database scenarios; support engineering data association and analysis, improve the analysis efficiency of aviation equipment engineering drawing standard application, and improve the level of engineering drawing standard resource management and application.

[0050] The embodiments described above are merely preferred embodiments of the present invention and are not intended to limit the scope of the present invention. Various modifications and improvements made by those skilled in the art to the technical solutions of the present invention without departing from the spirit of the present invention should fall within the protection scope defined by the claims of the present invention.

Claims

1. A method for standard matching and recognition of aerospace equipment engineering drawings based on segmented modeling, characterized in that: It includes: S1: Obtain aviation equipment engineering drawings; extract aviation equipment engineering drawing standards. Standard data for engineering drawing text and corresponding location information According to the standard data location information in the engineering drawings. Filtering yields standard data for engineering drawing text filtering. ; Filter standard data for engineering drawings The scan extracts candidate strings D for aviation equipment engineering drawing standards; the candidate fragments are further filtered using prefixes to obtain a set of candidate engineering drawing standard number strings. ; Obtain candidate strings for engineering drawing standards based on character composition rules. ; Obtain candidate character elements for engineering drawing standards based on prefix rules ; S2: For each engineering drawing standard candidate character element obtained in step S1 Perform character-level standardization; Candidate strings for engineering drawing standards After standardization conversion, the standardized string of the engineering drawing is obtained. The structured engineering drawing is segmented according to character type; the standard segmented structured engineering drawing is concatenated to construct a candidate standard matching string for aerospace equipment engineering drawings. ; S3: Construct database normalization fields for aviation equipment engineering drawing standards; use a data table in the aviation equipment engineering drawing standard database to record standard number and standard name information for auxiliary matching; S4: Perform hierarchical retrieval and identification of aviation equipment engineering drawing standards based on prefix matching. Based on the standardized engineering drawing string from step S2... Constructed engineering drawing standard multi-level candidate string set The set of multi-level candidate strings for engineering drawing standards The strings in the code are sorted by length to form a multi-level candidate string list for engineering drawing standards. Following the order of the multi-level candidate string list of engineering drawing standards, the database normalized field is extracted from the database standard information table to perform prefix matching of aviation equipment engineering drawing standards, thereby obtaining hierarchical retrieval and identification results.

2. The method for standard matching and recognition of aerospace equipment engineering drawings based on segmented modeling according to claim 1, characterized in that: Step S1 is as follows: S11: Obtain aviation equipment engineering drawings and identify the extracted first standard set. Second standard set ; Composition of standard categories of aviation equipment engineering drawings ; S12: Extract standard data for aviation equipment engineering drawings. For each aviation equipment engineering drawing standard... Extract the standard data of the engineering drawing text. and corresponding location information ; Set location information filtering threshold The filtered data yields standard data for engineering drawing text filtering. ; S13: Filter standard data for engineering drawing text. The scan is performed to extract the candidate string D of the aviation equipment engineering drawing standard; the candidate fragments are further filtered using a prefix to obtain a set of candidate engineering drawing standard number strings. .

3. The method for standard matching and recognition of aerospace equipment engineering drawings based on segmented modeling according to claim 1, characterized in that: Standard data for engineering drawing text in step S12 and corresponding location information The method for obtaining it is as follows: ； in, Standard data for engineering drawings; This refers to the location information of standard data in engineering drawings and text. For engineering drawing text recognition parameters; For layout recognition model; Standards for aviation equipment engineering drawings; This is a text character recognition model.

4. The method for standard matching and recognition of aerospace equipment engineering drawings based on segmented modeling according to claim 1, characterized in that: The method for obtaining the candidate strings for the aviation equipment engineering drawing standards in S13 is as follows: ； Where D represents a candidate string for aviation equipment engineering drawing standards; Candidate strings for engineering drawing standards; A standard scanned model of engineering drawings; This is a set of rules for forming the standard letter numbers of engineering drawings.

5. The method for standard matching and recognition of aerospace equipment engineering drawings based on segmented modeling according to claim 1, characterized in that: The set of candidate engineering drawing standard number strings in step S13 is as follows: ； in, A set of candidate engineering drawing standard number strings; Candidate character elements for engineering drawing standards; A set of letter prefixes for standard engineering drawing numbers; This is a function for processing prefix rules.

6. The method for standard matching and recognition of aerospace equipment engineering drawings based on segmented modeling according to claim 1, characterized in that: Step S2 is as follows: S21: Standardize the processing of noisy characters in aviation equipment engineering drawings, and standardize candidate strings for engineering drawings. After standardization conversion, the standardized string of the engineering drawing is obtained. ; S22: Perform structured segmentation of aviation equipment engineering drawings; standardize the processed engineering drawings into strings. The characters are segmented into structured segments according to their type to form an ordered sequence. S23: Construct candidate standard matching strings for aerospace equipment engineering drawings; segment the results of structured engineering drawing standards. Concatenate the strings to construct a multi-level candidate string set for engineering drawing standards. .

7. The method for standard matching and recognition of aerospace equipment engineering drawings based on segmented modeling according to claim 1, characterized in that: The structured segmentation rules in step S22 are as follows: First rule: If a character that is neither a number nor a letter appears, use that character as a delimiter for structured segmentation; Rule 2: If there is a part where numbers and letters are directly connected, separate the numbers and letters in that part.

8. The method for standard matching and recognition of aerospace equipment engineering drawings based on segmented modeling according to claim 1, characterized in that: The multi-level candidate string list for engineering drawing standards in step S4 is as follows: ； in, For the first A multi-level candidate string for each engineering drawing standard; A function for identifying string length; For engineering drawing standards, multi-level candidate string numbering; This represents the total number of multi-level candidate strings for engineering drawing standards.

9. A recognition and matching system for the aviation equipment engineering drawing standard recognition and matching method based on segmented modeling as described in any one of claims 1 to 8, characterized in that: It includes: The system includes a drawing generation module, a drawing management module, a drawing parsing module, and a standard information storage module. The drawing generation module generates configuration and standard numbering information for aviation equipment components; The drawing management module downloads aviation equipment engineering drawing files in batches on a daily schedule for use by the parsing module; The drawing parsing module performs character extraction and entity disambiguation on the engineering drawing standard numbers in aviation equipment engineering drawings, mapping noisy engineering drawing standard numbers to unique engineering drawing standard numbers in the aviation equipment engineering drawing standard database; The standard information storage module is used to store information from the general library of engineering drawing standards and the database of aerospace equipment engineering drawing standards.

Images