AO document compilation method, system, device and medium based on typical parameter library

Abstract

The present invention relates to the field of aircraft manufacturing technology, and specifically, to an AO document compilation method, system, equipment and medium based on a typical parameter library; the method first calls a semantic parsing method to obtain structured description content; secondly, it obtains structured process knowledge, and logically analyzes and constructs a process knowledge parameter library; then, it analyzes the logical association relationship between the process knowledge parameter library and the AO document structure, and constructs an AO document compilation parameter search logic diagram; finally, it processes the AO structured fields and generates the AO document content; through the structured processing of the process knowledge, a graph network for AO document compilation is formed, and in the reasoning algorithm of the knowledge graph, an AO document compilation method based on the typical parameter library is realized.

Description

Technical Field

[0001] The present invention relates to the technical field of aircraft manufacturing, and in particular to a method, system, device and medium for compiling an AO document based on a typical parameter library. Background Art

[0002] The assembly outline, or AO, is a crucial component of assembly execution during aircraft manufacturing. The transition from cards to AOs mirrors the shift from paper to paperless documentation. However, AOs have long been compiled manually, lacking the ability to evolve with technological advancements.

[0003] The manual compilation of AO has problems such as low efficiency, strong dependence on manual experience, low knowledge reuse rate, and poor knowledge inheritance. Process personnel are often busy compiling AO documents and neglect to conduct process analysis and optimization of the assembly process. The compilation process of AO documents is characterized by being cumbersome, involving many aspects of knowledge, and having relatively fixed compilation content. It requires process personnel to have extensive knowledge of process details. This knowledge is often stored in the form of documents, tables, etc., lacking structured, explicit, and intuitive expression. At the same time, the compilation of AO documents requires process personnel to have in-depth theoretical knowledge of the process in certain areas. This knowledge is often based on the experience of process personnel and often needs to be obtained through communication between process personnel. There are potential problems such as low efficiency in knowledge transfer and incomplete information transfer. The loss of process knowledge may be caused by the loss of a certain process personnel. Summary of the Invention

[0004] In response to the potential problems of low knowledge transfer efficiency and incomplete information transfer in the above-mentioned AO document compilation, the present invention proposes an AO document compilation method, system, equipment and medium based on a typical parameter library; first, the semantic parsing method is called to obtain structured description content; secondly, structured process knowledge is acquired, and a process knowledge parameter library is constructed through logical analysis; then, the logical association relationship between the process knowledge parameter library and the AO document structure is analyzed, and an AO document compilation parameter search logic diagram is constructed; finally, the AO structured fields are processed to generate the AO document content; through the structured processing of process knowledge, a graph network for AO document compilation is formed, and the reasoning algorithm of the knowledge graph is used to realize the AO document compilation method based on the typical parameter library.

[0005] The specific implementation contents of the present invention are as follows:

[0006] A method for compiling AO documents based on a typical parameter library specifically includes the following steps:

[0007] Step S1: calling the semantic parsing method to parse the process knowledge file and obtain structured description content;

[0008] Step S2: Obtain structured process knowledge based on the structured description content, and logically analyze and construct a process knowledge parameter library;

[0009] Step S3: Analyze the logical relationship between the process knowledge parameter library and the AO document structure, and construct an AO document compilation parameter search logic diagram;

[0010] Step S4: Search the logic diagram according to the AO document compilation parameters, process the AO structured fields, and generate the AO document content.

[0011] In order to better implement the present invention, further, step S2 specifically includes the following steps:

[0012] Step S21: obtaining structured process knowledge content from the structured description content, and classifying and analyzing it to obtain structured process knowledge content after classification and analysis;

[0013] Step S22: Obtaining the structured stored process knowledge content, adding field content according to aircraft characteristics and cleaning it up to obtain the cleaned structured stored process knowledge content;

[0014] Step S23: construct a process knowledge parameter library based on the structured process knowledge content after classification analysis and the cleaned and structured stored process knowledge content to form a process parameter library logic map.

[0015] In order to better implement the present invention, further, step S21 specifically includes the following steps:

[0016] Step S211: calling a clustering classification algorithm to preliminarily classify and obtain structured process knowledge content from the structured description content;

[0017] Step S212: using the data structure of the AO document as input, reanalyze the process knowledge content after preliminary classification;

[0018] Step S213: performing classification analysis based on the classification structure to obtain structured process knowledge content after classification analysis.

[0019] In order to better implement the present invention, further, step S3 specifically includes the following steps:

[0020] Step S31: Analyze the structured field content of the AO document and split it into corresponding categories;

[0021] Step S32: Analyze the relationship between the split categories and the corresponding parameter library, construct the relationship between the AO document structure field and the parameter library, and store it in the form of triples;

[0022] Step S33: Based on the triple content, a relationship logic diagram between the AO document fields and the parameter library fields is formed, and an AO document compilation parameter search logic diagram is constructed.

[0023] In order to better implement the present invention, further, step S4 specifically includes the following steps:

[0024] Step S41: Process according to the set processing logic and construct the logical processing relationship of the triple; the processing logic is L{L1, L2, L3...Li}, recorded as<Ai,Di,Ci,Li> , where Ai is the AO document field, Di is the parameter library name, Ci is the parameter library field, Li is the processing logic, and i is the number of categories of the AO document structured field;

[0025] Step S42: Process the AO document root nodes one by one, assemble the processed contents according to the AO document format, and generate AO document contents that meet the requirements.

[0026] In order to better implement the present invention, further, the semantic analysis method includes lexical analysis, grammatical analysis, and syntax analysis.

[0027] In order to better implement the present invention, further, the process knowledge file includes process knowledge text, process knowledge table, process knowledge graph, and process knowledge three-dimensional model.

[0028] Based on the above-mentioned AO document compilation method based on a typical parameter library, in order to better implement the present invention, further, an AO document compilation system based on a typical parameter library is proposed, which is used to execute the above-mentioned AO document compilation method based on a typical parameter library; the system includes a parsing unit, a parameter library construction unit, a logic diagram construction unit, and a generation unit;

[0029] The parsing unit is used to call a semantic parsing method to parse the process knowledge file to obtain structured description content;

[0030] The parameter library construction unit is used to obtain structured process knowledge according to the structured description content, and to construct a process knowledge parameter library through logical analysis;

[0031] The logic diagram construction unit is used to analyze the logical association between the process knowledge parameter library and the AO document structure and construct the AO document compilation parameter search logic diagram;

[0032] The generating unit is used to search the logic diagram according to the AO document compilation parameters, process the AO structured fields, and generate the AO document content.

[0033] Based on the above-mentioned AO document compilation method based on a typical parameter library, in order to better realize the present invention, further, an electronic device is proposed, including a memory and a processor; a computer program is stored on the memory; when the computer program is executed on the processor, the above-mentioned AO document compilation method based on a typical parameter library is implemented.

[0034] Based on the above-mentioned AO document compilation method based on the typical parameter library, in order to better realize the present invention, a computer-readable storage medium is further proposed, on which computer instructions are stored; when the computer instructions are executed on the electronic device such as the above-mentioned one, the above-mentioned AO document compilation method based on the typical parameter library is implemented.

[0035] The present invention has the following beneficial effects:

[0036] (1) The present invention constructs a graph for AO document content compilation by extracting, analyzing, and storing existing process knowledge in a structured manner and performing logical analysis on it using clustering and other methods. Based on the graph, AO document content is retrieved and generated.

[0037] (2) The present invention forms a graph network for AO document compilation through structured processing of process knowledge, and realizes an AO document compilation method based on a typical parameter library by using the reasoning algorithm of the knowledge graph. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] Figure 1 This is a schematic block diagram of the process of the AO document compilation method based on the typical parameter library provided by the present invention.

[0039] Figure 2 A schematic diagram of the processing flow of the AO document compilation method based on a typical parameter library provided by the present invention. DETAILED DESCRIPTION

[0040] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. It should be understood that the described embodiments are only part of the embodiments of the present invention, not all of the embodiments, and therefore should not be regarded as limiting the scope of protection. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technical personnel in this field without making creative work are within the scope of protection of the present invention.

[0041] In the description of the present invention, it should be noted that, unless otherwise expressly specified or limited, the terms "disposed," "connected," and "connected" should be understood in a broad sense. For example, they may refer to fixed connections, detachable connections, or integral connections; mechanical connections, electrical connections; direct connections, indirect connections through an intermediate medium, or internal connections between two components. Those skilled in the art will understand the specific meanings of the above terms in the present invention based on the specific circumstances.

[0042] Example 1:

[0043] This embodiment proposes an AO document compilation method based on a typical parameter library, which specifically includes the following steps:

[0044] Step S1: Call the semantic parsing method to parse the process knowledge file to obtain structured description content.

[0045] The semantic analysis method includes lexical analysis, grammatical analysis, and syntax analysis.

[0046] The process knowledge file includes process knowledge text, process knowledge table, process knowledge graph, and process knowledge three-dimensional model.

[0047] Step S2: Obtain structured process knowledge based on the structured description content, and logically analyze and construct a process knowledge parameter library.

[0048] The step S2 specifically includes the following steps:

[0049] Step S21: obtaining structured process knowledge content from the structured description content, and classifying and analyzing it to obtain structured process knowledge content after classification and analysis;

[0050] The step S21 specifically includes the following steps:

[0051] Step S211: calling a clustering classification algorithm to preliminarily classify and obtain structured process knowledge content from the structured description content;

[0052] Step S212: using the data structure of the AO document as input, reanalyze the process knowledge content after preliminary classification;

[0053] Step S213: performing classification analysis based on the classification structure to obtain structured process knowledge content after classification analysis.

[0054] Step S22: Obtaining the structured stored process knowledge content, adding field content according to aircraft characteristics and cleaning it up to obtain the cleaned structured stored process knowledge content;

[0055] Step S23: construct a process knowledge parameter library based on the structured process knowledge content after classification analysis and the cleaned and structured stored process knowledge content to form a process parameter library logic map.

[0056] Step S3: Analyze the logical relationship between the process knowledge parameter library and the AO document structure, and construct an AO document compilation parameter search logic diagram.

[0057] The step S3 specifically includes the following steps:

[0058] Step S31: Analyze the structured field content of the AO document and split it into corresponding categories;

[0059] Step S32: Analyze the relationship between the split categories and the corresponding parameter library, construct the relationship between the AO document structure field and the parameter library, and store it in the form of triples;

[0060] Step S33: Based on the triple content, a relationship logic diagram between the AO document fields and the parameter library fields is formed, and an AO document compilation parameter search logic diagram is constructed.

[0061] Step S4: Search the logic diagram according to the AO document compilation parameters, process the AO structured fields, and generate the AO document content.

[0062] The step S4 specifically includes the following steps:

[0063] Step S41: Process according to the set processing logic and construct the logical processing relationship of the triple; the processing logic is L{L1, L2, L3...Li}, recorded as<Ai,Di,Ci,Li> , where Li represents the processing logic;

[0064] Step S42: Process the AO document root nodes one by one, assemble the processed contents according to the AO document format, and generate AO document contents that meet the requirements.

[0065] Working principle: This embodiment first calls the semantic parsing method to obtain structured description content; secondly, it obtains structured process knowledge, and logically analyzes and constructs a process knowledge parameter library; then it analyzes the logical association between the process knowledge parameter library and the AO document structure, and constructs an AO document compilation parameter search logic diagram; finally, it processes the AO structured fields and generates the AO document content; through the structured processing of process knowledge, a graph network for AO document compilation is formed, and with the reasoning algorithm of the knowledge graph, an AO document compilation method based on a typical parameter library is realized.

[0066] Example 2:

[0067] This embodiment is based on the above embodiment 1. Figure 1 、 Figure 2 As shown, a specific embodiment is used for description.

[0068] Step S1: Use semantic analysis methods such as lexical analysis, grammatical analysis, and syntax analysis to process existing process knowledge documents or tables to obtain structured description content.

[0069] To further expand the breadth and depth of process knowledge, semantic analysis is required for the large number of process documents and process summary documents currently stored in text or table formats. This semantic analysis utilizes established algorithms, including rule-based and machine learning-based algorithms. Parsed objects include text, tables, graphs, and 3D models. The analysis primarily focuses on common nouns, specialized nouns, parameter values, special requirements, and bills of materials.

[0070] Through this step, the standard parts list, aircraft material list (including drawing number, name, cabin space and other information), hole making information, tooling information, etc. are obtained.

[0071] Step S2: Perform logical analysis on the structured process knowledge, build a process knowledge parameter library, and form a process parameter library logic map.

[0072] The construction of process knowledge parameter library is mainly divided into two parts:

[0073] (1) Structured process knowledge content obtained in step S1;

[0074] (2) Process knowledge content that has been stored in a structured manner.

[0075] For the second portion of structured process knowledge, we retained the existing parameter library structure and added required fields based on aircraft characteristics. The focus for this portion of process knowledge was data cleansing, removing erroneous, outdated, and dirty data.

[0076] Regarding the process knowledge of the structure obtained in step 1 of the first part, since it only contains vocabulary, parameters and other contents, it has not been classified and analyzed. Therefore, the following steps need to be used to process this part:

[0077] 1) With the help of existing clustering and classification algorithms, such as K-Means, DBSCAN, GMM, swarm intelligence clustering algorithm, etc., the analyzed process knowledge is preliminarily classified.

[0078] 2) Using the data structure of the AO document as input, the process knowledge is analyzed again.

[0079] 3) Based on the classification structure, a parameter library is constructed. The fields of the parameter library are based on the extracted structured parameter content.

[0080] According to the classification, it is mainly divided into two parts: process content and process supporting content. It can be further divided into: hole making information, installation information, material information, tooling information, etc.

[0081] Step S3: Analyze the logical relationship between the process knowledge parameter library and the AO document structure, and construct an AO document compilation parameter search logic diagram.

[0082] Analyze the structured field content of the AO document and split it into corresponding categories. For each category, analyze the relationship with the corresponding parameter library, build the relationship between the AO document structure field and the parameter library, and store it in the form of triples.<Ai,Di,Ci> , where Ai represents the AO document field, Di represents the parameter library name, and Ci represents the parameter library field.

[0083] Based on the triple content, a logical diagram of the relationship between the AO document fields and the parameter library fields is formed.

[0084] The main contents are as follows <Material column, Bill of Materials, Drawing number>, <Toolbar, Tool parameter library, Tool drawing number>...

[0085] Step S4: Generate AO document content.

[0086] The process of generating AO documents is the process of processing AO structured fields. According to a certain processing logic, the processing logic is defined as L{L1, L2, L3...Li}, and the logical processing relationship of the triples is constructed and recorded as<Ai,Di,Ci,Li> , where Li represents the processing logic.

[0087] According to the AO document root node, each node is processed one by one, and the processed content is assembled according to the AO document format, and finally the AO document content that meets the requirements is generated.

[0088] The main processing logic consists of replacement, combination and other relationships. Replacement means replacing variable parameters, and combination means splicing multiple fields into one field content.

[0089] Working Principle: This embodiment constructs a graph for AO document content compilation by extracting, analyzing, and storing existing process knowledge in a structured manner, and applying logical analysis methods such as clustering. Based on this graph, AO document content is retrieved and generated. Through the structured processing of process knowledge, a graph network for AO document compilation is formed. Using the knowledge graph's inference algorithm, an AO document compilation method based on a typical parameter library is implemented.

[0090] The rest of this embodiment is the same as that of the above-mentioned embodiment 1, and therefore will not be described in detail.

[0091] Example 3:

[0092] This embodiment, based on any one of the above-mentioned embodiments 1-2, proposes an AO document compilation system based on a typical parameter library, which is used to execute the above-mentioned AO document compilation method based on a typical parameter library; the system includes a parsing unit, a parameter library construction unit, a logic diagram construction unit, and a generation unit;

[0093] The parsing unit is used to call a semantic parsing method to parse the process knowledge file to obtain structured description content;

[0094] The parameter library construction unit is used to obtain structured process knowledge according to the structured description content, and to construct a process knowledge parameter library through logical analysis;

[0095] The logic diagram construction unit is used to analyze the logical association between the process knowledge parameter library and the AO document structure and construct the AO document compilation parameter search logic diagram;

[0096] The generating unit is used to search the logic diagram according to the AO document compilation parameters, process the AO structured fields, and generate the AO document content.

[0097] This embodiment also proposes an electronic device, including a memory and a processor; a computer program is stored in the memory; when the computer program is executed on the processor, the above-mentioned AO document compilation method based on the typical parameter library is implemented.

[0098] This embodiment further proposes a computer-readable storage medium, on which computer instructions are stored; when the computer instructions are executed on the above-mentioned electronic device, the above-mentioned AO document compilation method based on the typical parameter library is implemented.

[0099] The rest of this embodiment is the same as any of the above-mentioned embodiments 1 and 2, and thus will not be described in detail.

[0100] The above description is only a preferred embodiment of the present invention and does not limit the present invention in any form. Any simple modification or equivalent change made to the above embodiment based on the technical essence of the present invention shall fall within the scope of protection of the present invention.

Claims

1. A method for compiling AO documents based on a typical parameter library, characterized in that: The specific steps include: Step S1: calling the semantic parsing method to parse the process knowledge file and obtain structured description content; Step S2: Obtain structured process knowledge based on the structured description content, and logically analyze and construct a process knowledge parameter library; Step S21: obtaining structured process knowledge content from the structured description content, and classifying and analyzing it to obtain structured process knowledge content after classification and analysis; Step S22: Obtaining the structured stored process knowledge content, adding field content according to aircraft characteristics and cleaning it up to obtain the cleaned structured stored process knowledge content; Step S23: constructing a process knowledge parameter library based on the structured process knowledge content after classification analysis and the cleaned and structured stored process knowledge content, and forming a process parameter library logic map; The step S21 specifically includes the following steps: Step S211: calling a clustering classification algorithm to preliminarily classify and obtain structured process knowledge content from the structured description content; Step S212: using the data structure of the AO document as input, reanalyze the process knowledge content after preliminary classification; Step S213: performing classification analysis based on the classification structure to obtain structured process knowledge content after classification analysis; Step S3: Analyze the logical relationship between the process knowledge parameter library and the AO document structure, and construct an AO document compilation parameter search logic diagram; Step S31: Analyze the structured field content of the AO document and split it into corresponding categories; Step S32: Analyze the relationship between the split categories and the corresponding parameter library, construct the relationship between the AO document structure field and the parameter library, and store it in the form of triples; Step S33: Based on the triple content, a relationship logic diagram between the AO document fields and the parameter library fields is formed, and an AO document compilation parameter search logic diagram is constructed; Step S4: searching the logic diagram according to the AO document compilation parameters, processing the AO structured fields, and generating the AO document content; Step S41: Process according to the set processing logic and construct the logical processing relationship of the triple; the processing logic is L{L1, L2, L3...Li}, recorded as<Ai,Di,Ci,Li> , where A i is the AO document field, D i is the parameter library name, C i is the parameter library field, Li is the processing logic, and i is the number of categories of the AO document structured field; Step S42: Process the AO document root nodes one by one, assemble the processed contents according to the AO document format, and generate AO document contents that meet the requirements.

2. The AO document compilation method based on a typical parameter library according to claim 1, characterized in that: The semantic analysis method includes lexical analysis, grammatical analysis, and syntax analysis.

3. The AO document compilation method based on a typical parameter library according to claim 1, characterized in that: The process knowledge file includes process knowledge text, process knowledge table, process knowledge graph, and process knowledge three-dimensional model.

4. An AO document compilation system based on a typical parameter library, used to execute the AO document compilation method based on a typical parameter library according to claim 1; characterized in that: It includes parsing unit, parameter library building unit, logic diagram building unit and generation unit; The parsing unit is used to call a semantic parsing method to parse the process knowledge file to obtain structured description content; The parameter library construction unit is used to obtain structured process knowledge according to the structured description content, and to construct a process knowledge parameter library through logical analysis; The logic diagram construction unit is used to analyze the logical association between the process knowledge parameter library and the AO document structure and construct the AO document compilation parameter search logic diagram; The generating unit is used to search the logic diagram according to the AO document compilation parameters, process the AO structured fields, and generate the AO document content.

5. An electronic device, characterized in that: It comprises a memory and a processor; a computer program is stored in the memory; when the computer program is executed on the processor, the AO document compilation method based on the typical parameter library as described in any one of claims 1 to 3 is implemented.

6. A computer-readable storage medium, characterized in that The computer-readable storage medium stores computer instructions; when the computer instructions are executed on the electronic device as described in claim 5, the AO document compilation method based on the typical parameter library as described in any one of claims 1-3 is implemented.

Images