Automatic question answering method, device and equipment for aeronautical manufacturing process knowledge and medium

Abstract

The invention discloses an aeronautical manufacturing process knowledge automatic question answering method, device and equipment and a medium. The method comprises the following steps: acquiring a natural language question statement in the aeronautical manufacturing process field input by a user side; identifying a named entity in the aeronautical manufacturing process field in the natural language question statement, obtaining at least one entity keyword, and determining a question intention according to the entity keyword; constructing a graph data query statement according to the question intention and the entity keyword, and querying in a pre-constructed aeronautical manufacturing process knowledge graph according to the graph data query statement to obtain a query result; and displaying the query result and the document index position of the query result in the aeronautical manufacturing process knowledge base at a user side. According to the technical scheme, the automatic question and answer method is provided for the field of aeronautical manufacturing process knowledge, the interpretability of a question and answer system is enhanced, the knowledge retrieval time is shortened, meanwhile, the accuracy of a query result is improved, and the use experience of a user is improved.

Description

Technical Field

[0001] The present invention relates to the field of natural language processing technology, and in particular to a method, device, equipment and medium for automatically answering questions about aviation manufacturing process knowledge. Background Art

[0002] With the development of the aviation industry, the complexity of aviation parts is increasing, and aviation manufacturing has become more and more a knowledge-intensive process. The mastery and application of aviation manufacturing process knowledge has become an essential skill for process designers.

[0003] In the past, during the process of process design, technicians could find knowledge content related to keywords by looking through paper materials or searching for keywords in electronic documents. In addition to the most traditional document retrieval keywords, there are also some technologies involving natural language question answering. In terms of natural language question answering, it is composed of multiple technologies such as word segmentation technology, entity recognition technology, and information retrieval methods.

[0004] However, when using mainstream Chinese word segmentation technology to process natural language problems, there is a problem of poor word segmentation accuracy. At the same time, when using traditional machine learning methods and deep learning methods for entity recognition, there are problems such as high parameter dependence and ambiguous semantic information. Summary of the Invention

[0005] Based on this, the present invention provides a method, device, equipment and medium for automatic question answering of aviation manufacturing process knowledge to solve the problems of poor word segmentation accuracy and ambiguous semantic information faced by automatic question answering systems when processing natural language questions.

[0006] In a first aspect, an embodiment of the present invention provides a method for automatically answering questions about aviation manufacturing process knowledge, the method comprising:

[0007] Obtaining natural language question statements in the field of aviation manufacturing process input by the user;

[0008] Identify named entities in the field of aviation manufacturing processes in natural language question sentences, obtain at least one entity keyword, and determine the question intent based on the entity keyword;

[0009] A graph data query statement is constructed based on the question intent and entity keywords, and query results are obtained in the pre-built aviation manufacturing process knowledge graph based on the graph data query statement; the aviation manufacturing process knowledge graph is constructed using various knowledge documents in the aviation manufacturing process knowledge base;

[0010] The query results and the document index location of the query results in the aviation manufacturing process knowledge base are displayed on the user side.

[0011] In a second aspect, an embodiment of the present invention further provides an automatic question-answering device for aviation manufacturing process knowledge, the device comprising:

[0012] A question statement acquisition module is used to obtain natural language question statements in the field of aviation manufacturing technology input by the user;

[0013] A question intention determination module is used to identify named entities in the field of aviation manufacturing processes in a natural language question statement, obtain at least one entity keyword, and determine the question intention based on the entity keyword;

[0014] A query result acquisition unit is used to construct a graph data query statement based on the question intent and entity keywords, and to query and obtain query results in a pre-constructed aviation manufacturing process knowledge graph based on the graph data query statement; wherein the aviation manufacturing process knowledge graph is constructed using various knowledge documents in the aviation manufacturing process knowledge base;

[0015] The query result display module is used to display the query results and the document index position of the query results in the aviation manufacturing process knowledge base on the user side.

[0016] In a third aspect, an embodiment of the present invention further provides an electronic device, comprising:

[0017] at least one processor; and

[0018] a memory communicatively connected to the at least one processor; wherein,

[0019] The memory stores a computer program that can be executed by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the automatic question-answering method for aviation manufacturing process knowledge described in any embodiment of the present invention.

[0020] In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement an automatic question-answering method for aviation manufacturing process knowledge as described in any embodiment of the present invention when executed.

[0021] The technical solution of the embodiment of the present invention proposes an automatic question-answering method for the field of aviation manufacturing process knowledge. First, a knowledge graph of vertical fields is constructed based on the characteristics of similar knowledge structure and content in the field of aviation manufacturing process, thereby enhancing the interpretability of the question-answering system; secondly, different from conventional named entity recognition technology, the embodiment of the present invention realizes the rapid recognition of multiple keywords and the determination of entity keywords, thereby accurately matching the question intention according to the keywords, achieving accurate intention recognition of the question statement, shortening the knowledge retrieval time while improving the accuracy of the query results; finally, the query results and the source of the query results are displayed in an expanded manner to help users better understand the relevant knowledge and enhance the user experience.

[0022] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present invention, nor is it intended to limit the scope of the present invention. Other features of the present invention will become readily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0024] Figure 1 This is a flow chart of an automatic question-answering method for aviation manufacturing process knowledge provided in accordance with the first embodiment of the present invention;

[0025] Figure 2 This is a flow chart of another method for automatic question-answering of aviation manufacturing process knowledge provided in accordance with the second embodiment of the present invention;

[0026] Figure 3 This is a schematic diagram of the structure of an automatic question-answering device for aviation manufacturing process knowledge provided in accordance with a third embodiment of the present invention;

[0027] Figure 4 The present invention is a schematic diagram of the structure of an electronic device for implementing an automatic question-answering method for aviation manufacturing process knowledge according to an embodiment of the present invention. DETAILED DESCRIPTION

[0028] In order to enable those skilled in the art to better understand the solutions 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. Obviously, the embodiments described are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts should fall within the scope of protection of the present invention.

[0029] It should be noted that the terms "first", "second", etc. in the description and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that the numbers used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0030] Example 1

[0031] Figure 1 This is a flowchart of an automatic question-answering method for aviation manufacturing process knowledge provided in the first embodiment of the present invention. This embodiment is applicable to the situation of automatically answering natural language questions in the field of aviation manufacturing process knowledge. The method can be executed by an automatic question-answering device for aviation manufacturing process knowledge. The device can be implemented in the form of hardware and / or software. The device can be configured in an automatic question-answering system based on a knowledge graph, and the question-answering system is configured in electronic devices such as terminals or servers. Figure 1 As shown, the method includes:

[0032] S110 : Obtain a natural language question statement in the field of aviation manufacturing technology input by the user.

[0033] The embodiment of the present invention is oriented to the field of aviation manufacturing technology, so the questions input by the user also revolve around knowledge related to aviation manufacturing technology, and the natural language question statement is a textual description of the input question based on the user's thinking.

[0034] S120. Identify named entities in the field of aviation manufacturing technology in the natural language question statement, obtain at least one entity keyword, and determine the question intention based on the entity keyword.

[0035] As a conventional entity recognition technology, named entity recognition technology is mainly used to identify proper nouns such as names of people, places and organizations in the open domain. In the embodiment of the present invention, it is used to identify entity keywords in the field of aviation manufacturing technology, such as: process, procedure, equipment, parts and related personnel, etc. Specifically, in the embodiment of the present invention, a string matching algorithm is used to quickly identify the input text data, and it is possible to quickly detect whether multiple keywords appear in the text. At the same time, considering that the field of aviation manufacturing technology involves many relatively uncommon Chinese and English expressions, users may make mistakes in entering the above-mentioned words when entering questions. Therefore, when performing named entity recognition, the Levenshtein distance algorithm can be used to calculate the similarity to find the named entity closest to the user input content as the entity keyword.

[0036] The question intent refers to the specific question type for the entity keyword obtained after keyword extraction from the natural language question statement initiated by the user. In a specific example, if the part entity keyword is identified as "titanium alloy hexagon head screw", then "titanium alloy hexagon head screw" can correspond to multiple question intents, such as meaning, appearance characteristics, and technical requirements, etc.

[0037] Optionally, after determining the question intent based on entity keywords, you can also include:

[0038] Constructing a question statement in natural language based on the entity keywords and the question intention, and providing the question statement to the user terminal for question confirmation;

[0039] If a negative response message is received from the user terminal, obtaining candidate replacement entity keywords corresponding to each entity keyword, and providing each entity keyword and each candidate replacement entity keyword to the user terminal for replacement confirmation;

[0040] According to the replacement confirmation response of the user terminal, new entity keywords are re-determined, and according to the new entity keywords, new question intention is re-determined.

[0041] It should be noted that to ensure the accuracy of intent recognition, after determining the question intent, the entity keyword is combined with the question intent. The resulting rhetorical question is used to confirm with the user whether the generated question is semantically consistent with the question the user intended. Continuing with the above example, when the entity keyword is "titanium alloy hexagon head screw" and keywords containing meaning such as "definition," "concept," or "popular explanation" appear at the same time, the question intent is determined to be a query for meaning. In this case, combining "titanium alloy hexagon head screw" with "meaning" creates a rhetorical question: "Do you want to inquire about the meaning of titanium alloy hexagon head screw?"

[0042] A user's negative response indicates that the question generated by the rhetorical question is semantically inconsistent with the natural language question input by the user, indicating that the entity keyword recognition was incorrect. Therefore, the process returns to the entity keyword acquisition step and re-determines new entity keywords. This issue may occur because the entity keywords selected based on the highest similarity may not necessarily match the actual query the user intended.

[0043] In the above example, the entity keyword recognition phase for the target natural language question sentence yields several entity keywords similar to "titanium alloy hexagonal screw," such as "titanium alloy," "screw," or "titanium alloy screw." Once "titanium alloy hexagonal screw" is selected as the final entity keyword, the remaining entity keywords are considered candidate replacement entity keywords. Upon receiving a negative response from the user, this indicates that "titanium alloy hexagonal screw," selected based on the similarity score, is not the entity the user is actually searching for. In this case, the keywords previously selected as candidate replacement entity keywords are fed back to the front-end as selectable, as a post-negation operation, until the user selects a replacement entity keyword from the numerous replacement entity keywords that matches their question and answer requirements. When the entity keyword changes, the question intent corresponding to the entity keyword also changes. The question intent is then redefined based on the replaced entity keyword, ensuring the accuracy of intent recognition by revising the entity keyword.

[0044] S130. Construct a graph data query statement based on the question intention and entity keywords, and query and obtain query results in the pre-constructed aviation manufacturing process knowledge graph based on the graph data query statement; wherein, the aviation manufacturing process knowledge graph is constructed using various knowledge documents in the aviation manufacturing process knowledge base.

[0045] Graph data query statements primarily refer to a query language capable of performing semantic queries based on graph structures. In other words, since computers cannot directly understand natural language question statements entered by users, it is necessary to convert these natural language question statements into a query language that computers can execute. For example, if entity keywords A and B are extracted and the query intent is "relationship," the graph database query statement can be specifically expressed as the structure "A + B = relationship."

[0046] Among them, in an embodiment of the present invention, the graph structure based on the graph data query statement is a pre-constructed knowledge graph in the field of aviation manufacturing process, and the aviation manufacturing process knowledge base includes open databases such as design manuals, manufacturing outlines, process standards and process regulations.

[0047] Furthermore, before querying and obtaining query results in the pre-built aviation manufacturing process knowledge graph according to the graph data query statement, the following steps may also be included:

[0048] Acquiring aviation process knowledge raw data from documents in at least one aviation manufacturing process knowledge base;

[0049] The neo4j database is used to store the original data of aviation process knowledge to obtain the knowledge graph in the field of aviation manufacturing process.

[0050] The target knowledge documents can be open repositories such as design manuals, manufacturing outlines, process standards, and process procedures. These documents capture a large number of knowledge items and serve as the raw data source for constructing the knowledge graph. Common representations of knowledge graphs include (entity, relationship, entity) and (entity, attribute, attribute value). Entities, the basic units of a knowledge graph, are distributed as nodes within the knowledge graph network. By identifying text within the raw aviation manufacturing process data, specific strings are extracted and mapped to the knowledge graph's representation structure to form corresponding inter-entity links.

[0051] S140: Display the query result and the document index position of the query result in the aviation manufacturing process knowledge base on the user end.

[0052] Specifically, in addition to displaying the answers to the questions required by the user to the front end, in an embodiment of the present invention, the source of the answer (paper, book or website) can be fed back to the user in the form of a document index link by linking the information source, helping the user to further understand the queried knowledge, such as: this paragraph of content comes from the paper "xx", author, year, included in...

[0053] Optionally, after displaying the document index location of the query result in the aviation manufacturing process knowledge base on the user end, the following may also be included:

[0054] In response to the user's selection of the document index location, locating a target knowledge document in the aviation manufacturing process knowledge base;

[0055] After the target knowledge document is opened locally on the user terminal, the document content is displayed by jumping to the location matching the query result.

[0056] When the user clicks on the target document index, the location of the query result in the aviation manufacturing process knowledge base is searched according to the document index content. After locating the document location, the document content is expanded and displayed to the user as an extended result.

[0057] The technical solution of the embodiment of the present invention proposes an automatic question-answering method for the field of aviation manufacturing process knowledge. First, a knowledge graph of vertical fields is constructed based on the characteristics of similar knowledge structure and content in the field of aviation manufacturing process, thereby enhancing the interpretability of the question-answering system; secondly, different from conventional named entity recognition technology, the embodiment of the present invention realizes the rapid recognition of multiple keywords and the determination of entity keywords, thereby accurately matching the question intention according to the keywords, achieving accurate intention recognition of the question statement, shortening the knowledge retrieval time while improving the accuracy of the query results; finally, the query results and the source of the query results are displayed in an expanded manner to help users better understand the relevant knowledge and enhance the user experience.

[0058] Example 2

[0059] Figure 2 This is a flowchart of another method for automatically answering questions about aviation manufacturing process knowledge provided in the second embodiment of the present invention. This embodiment is based on the above embodiment and is refined. Figure 2 As shown, the method includes:

[0060] S210: Obtain a natural language question statement in the field of aviation manufacturing technology input by the user.

[0061] S220: Automatically identify keywords in the natural language question based on a pre-built knowledge graph to obtain multiple candidate keywords.

[0062] In the aviation process knowledge question-and-answer scenario of an embodiment of the present invention, there is a large amount of process knowledge with similar semantics. These process knowledge not only have similar textual expressions, but also easily lead to deviations in user descriptions due to their similar meanings. This means that users may make spelling errors or use inaccurate words when entering questions, resulting in multiple keywords with similar meanings or forms, that is, multiple alternative keywords, being generated in a question statement.

[0063] S230: Input each candidate keyword into a pre-built keyword automaton to calculate a similarity score of each candidate keyword.

[0064] Specifically, following the above example, the multiple candidate keywords are: "titanium alloy", "screw", "titanium alloy screw" and "titanium alloy hexagon head screw". The similarity score between each candidate keyword and the keywords pre-stored in the keyword automaton is calculated and arranged from high to low.

[0065] S240: Determine candidate keywords whose similarity scores meet a preset similarity threshold as entity keywords.

[0066] The similarity score of each candidate keyword is compared with the preset similarity threshold. Keywords with a score higher than the similarity threshold are considered to have higher consistency. The candidate keyword with the highest similarity score is used as the entity keyword, that is, the question subject centered around the question entered by the user.

[0067] S250: Input the at least one entity keyword into a pre-built intent recognition mapping library, and determine the question intent based on the at least one entity keyword.

[0068] Among them, the intent recognition mapping library is a database that reflects the mapping relationship between entity keywords and question intentions. Compared with open domain answers, in the vertical fields of the embodiments of the present invention, the question types are relatively fixed. Therefore, multiple types of questions accompanied by specific keywords can be pre-constructed, and each type of question has keyword features that express the same meaning. In addition to the keywords that express meanings such as "definition", "concept" or "popular explanation" mentioned in the above embodiments, there can also be keywords such as: "specifications", "requirements" or "principles" that express technical requirements. Each question represents a question intention, and then the corresponding question intention is determined for the entity keyword matching, such as: technical requirements for manufacturing titanium alloy hexagon head screws, that is, the question intention is technical requirements.

[0069] S260: Determine a question framework in a pre-built query statement template library according to the question intention.

[0070] A question frame is a query template for a sentence to be filled in. That is, different question intentions have corresponding question frames, such as: "manufacturing" + "entity keyword A" + "of" + "question intention" Figure 1 ” + “What are they” + “?” That is, the question frame is a complete question statement based on the question intention, which is expanded to include the entity keyword to be filled. When the question intention is technical requirements, the corresponding question frame can be: What are the technical requirements for manufacturing entity keyword A?

[0071] S270. Fill the at least one keyword into the question frame to obtain a graph database query statement.

[0072] When at least one keyword is "titanium alloy hexagon head screws", after filling the keyword into the question frame, the question statement becomes: "manufacturing" + "titanium alloy hexagon head screws" + "of" + "technical requirements" + "what are" + "?", that is, the final graph database query statement is: "What are the technical requirements for manufacturing titanium alloy hexagon head screws?".

[0073] S280. Query and obtain query results in a pre-built aviation manufacturing process knowledge graph according to the graph data query statement.

[0074] By identifying entities in a graph data query statement, we can find the corresponding node in the aviation manufacturing process knowledge graph, retrieve the relevant data under that node, and generate a query result. For example, the query results include: a) L increments are 1mm per level, with a tolerance of ±0.20mm; b) threads are in accordance with GJB3.2A-2003 and GJB52-1985; c) general tolerances are in accordance with HB5800-1999, and geometric tolerances are in accordance with HB7368-1996.

[0075] S290: Display the query result and the document index position of the query result in the aviation manufacturing process knowledge base on the user end.

[0076] The technical solution of the embodiment of the present invention provides a detailed description of the construction process of the graph data query statement by refining the overall solution. Specifically, first, the entity keywords are determined by introducing a keyword automaton to calculate the scores of alternative keywords. Secondly, the question intention is searched in the intent recognition mapping library based on the determined entity keywords. The determination of the question intention ensures the accurate recognition of the semantics of the user's question. Furthermore, the question framework is determined according to the question intention to realize the conversion of natural language questions into graph database query statements, thereby automatically completing the query of the question. The whole process helps users realize the active question and answer and retrieval of aviation manufacturing process knowledge, greatly improving the efficiency of process knowledge use.

[0077] Example 3

[0078] Figure 3 This is a schematic diagram of the structure of an automatic question-answering device for aviation manufacturing process knowledge provided in the third embodiment of the present invention. Figure 3 As shown, the device includes:

[0079] The question statement acquisition module 310 is used to acquire a natural language question statement in the field of aviation manufacturing technology input by the user;

[0080] The question intention determination module 320 is configured to identify named entities in the field of aviation manufacturing processes in a natural language question statement, obtain at least one entity keyword, and determine the question intention based on the entity keyword;

[0081] The query result acquisition unit 330 is configured to construct a graph data query statement based on the question intent and entity keywords, and to query and obtain query results in a pre-constructed aviation manufacturing process knowledge graph based on the graph data query statement; wherein the aviation manufacturing process knowledge graph is constructed using various knowledge documents in the aviation manufacturing process knowledge base;

[0082] The query result display module 340 is used to display the query results and the document index position of the query results in the aviation manufacturing process knowledge base on the user end.

[0083] The technical solution of the embodiment of the present invention proposes an automatic question-answering method for the field of aviation manufacturing process knowledge. First, a knowledge graph of vertical fields is constructed based on the characteristics of similar knowledge structure and content in the field of aviation manufacturing process, thereby enhancing the interpretability of the question-answering system; secondly, different from conventional named entity recognition technology, the embodiment of the present invention realizes the rapid recognition of multiple keywords and the determination of entity keywords, thereby accurately matching the question intention according to the keywords, achieving accurate intention recognition of the question statement, shortening the knowledge retrieval time while improving the accuracy of the query results; finally, the query results and the source of the query results are displayed in an expanded manner to help users better understand the relevant knowledge and enhance the user experience.

[0084] Based on the above embodiments, the question intention determination module 320 may include:

[0085] Automatically identify keywords in the natural language question based on a pre-built knowledge graph to obtain multiple candidate keywords;

[0086] Input each candidate keyword into a pre-built keyword automaton and calculate the similarity score of each candidate keyword;

[0087] The candidate keywords whose similarity scores meet a preset similarity threshold are determined as entity keywords.

[0088] Based on the above embodiments, the question intention determination module 320 may further include:

[0089] The at least one entity keyword is input into a pre-built intent recognition mapping library, and the question intent is determined according to the at least one entity keyword.

[0090] Based on the above embodiments, the query result obtaining unit 330 may include:

[0091] Determine the question framework from the pre-built query statement template library based on the question intention;

[0092] Fill the at least one keyword into the question frame to obtain a graph database query statement.

[0093] Based on the above embodiments, it further includes a knowledge graph construction module for:

[0094] Before querying and obtaining query results in a pre-built aviation manufacturing process knowledge graph according to a graph data query statement, obtaining aviation process knowledge original data from documents in at least one aviation manufacturing process knowledge base;

[0095] The neo4j database is used to store the original data of aviation process knowledge to obtain the knowledge graph in the field of aviation manufacturing process.

[0096] Based on the above embodiment, the system further includes a question clarification module for:

[0097] After determining the question intention based on the entity keywords, constructing a question rhetorical statement in natural language form based on the entity keywords and the question intention, and providing the question rhetorical statement to the user terminal for question confirmation;

[0098] If a negative response message is received from the user terminal, obtaining candidate replacement entity keywords corresponding to each entity keyword, and providing each entity keyword and each candidate replacement entity keyword to the user terminal for replacement confirmation;

[0099] According to the replacement confirmation response of the user terminal, new entity keywords are re-determined, and according to the new entity keywords, new question intention is re-determined.

[0100] Based on the above embodiment, a source display module may also be included, which is used to:

[0101] After displaying the document index position of the query result in the aviation manufacturing process knowledge base on the user terminal, locating the target knowledge document in the aviation manufacturing process knowledge base in response to the user terminal selecting the document index position;

[0102] After the target knowledge document is opened locally on the user terminal, the document content is displayed by jumping to the location matching the query result.

[0103] An automatic question-answering device for aviation manufacturing process knowledge provided by an embodiment of the present invention can execute an automatic question-answering method for aviation manufacturing process knowledge provided by any embodiment of the present invention, and has functional modules and beneficial effects corresponding to the execution method.

[0104] Example 4

[0105] Figure 4A schematic diagram of the structure of an electronic device 10 that can be used to implement an embodiment of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital assistants, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or claimed herein.

[0106] like Figure 4 As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., which is communicatively connected to the at least one processor 11. The memory stores a computer program that can be executed by the at least one processor. The processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 into the random access memory (RAM) 13. Various programs and data required for the operation of the electronic device 10 can also be stored in the RAM 13. The processor 11, ROM 12, and RAM 13 are connected to each other via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0107] Multiple components in the electronic device 10 are connected to the I / O interface 15, including an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a magnetic disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices via a computer network such as the Internet and / or various telecommunication networks.

[0108] The processor 11 can be any general-purpose and / or specialized processing component with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various specialized artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any other suitable processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as a method for automatic question-answering of aviation manufacturing process knowledge.

[0109] That is: obtaining natural language question sentences in the field of aviation manufacturing technology input by the user;

[0110] Identify named entities in the field of aviation manufacturing processes in natural language question sentences, obtain at least one entity keyword, and determine the question intent based on the entity keyword;

[0111] A graph data query statement is constructed based on the question intent and entity keywords, and query results are obtained in the pre-built aviation manufacturing process knowledge graph based on the graph data query statement; the aviation manufacturing process knowledge graph is constructed using various knowledge documents in the aviation manufacturing process knowledge base;

[0112] The query results and the document index location of the query results in the aviation manufacturing process knowledge base are displayed on the user side.

[0113] In some embodiments, a method for automatic question-answering of aviation manufacturing process knowledge may be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the method for automatic question-answering of aviation manufacturing process knowledge described above may be performed. Alternatively, in other embodiments, the processor 11 may be configured to execute a method for automatic question-answering of aviation manufacturing process knowledge in any other appropriate manner (e.g., by means of firmware).

[0114] Various embodiments of the systems and techniques described herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), system-on-chip systems (SOCs), programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include being implemented in one or more computer programs that are executable and / or interpreted on a programmable system that includes at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0115] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when the computer program is executed by the processor, the functions / operations specified in the flowcharts and / or block diagrams are implemented. The computer program may be executed entirely on the machine, partially on the machine, as a stand-alone software package, partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0116] In the context of the present invention, computer-readable storage media can be tangible media that can contain or store a computer program for use with an instruction execution system, device or equipment or used in combination with an instruction execution system, device or equipment. Computer-readable storage media can include but are not limited to electronic, magnetic, optical, electromagnetic, infrared or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, computer-readable storage media can be machine-readable signal media. More specific examples of machine-readable storage media can include electrical connections based on one or more lines, portable computer disks, hard disks, random access memories (RAM), read-only memories (ROM), erasable programmable read-only memories (EPROM or flash memory), optical fibers, portable compact disk read-only memories (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0117] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0118] The systems and techniques described herein can be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0119] A computing system may include clients and servers. The clients and servers are typically remote from each other and typically interact via a communication network. This client-server relationship arises through computer programs running on the respective computers, creating a client-server relationship. The server may be a cloud server, also known as a cloud computing server or cloud host. This server is a hosting product within the cloud computing service ecosystem that addresses the management difficulties and limited scalability of traditional physical hosting and VPS services.

[0120] It should be understood that the various forms of the processes shown above can be used to reorder, add, or delete steps. For example, the steps described in the present invention can be performed in parallel, sequentially, or in a different order, as long as the desired results of the technical solution of the present invention can be achieved. This is not limited herein.

[0121] The above specific embodiments do not limit the scope of protection of the present invention. Those skilled in the art will appreciate that various modifications, combinations, sub-combinations, and substitutions may be made based on design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention are intended to be included within the scope of protection of the present invention.

Claims

1. An automatic question-answering method for aviation manufacturing process knowledge, characterized in that: include: Obtaining natural language question statements in the field of aviation manufacturing process input by the user; Identify named entities in the field of aviation manufacturing processes in natural language question sentences, obtain at least one entity keyword, and determine the question intent based on the entity keyword; A graph data query statement is constructed based on the question intent and entity keywords, and query results are obtained in the pre-built aviation manufacturing process knowledge graph based on the graph data query statement; the aviation manufacturing process knowledge graph is constructed using various knowledge documents in the aviation manufacturing process knowledge base; The query results and the document index location of the query results in the aviation manufacturing process knowledge base are displayed on the user side.

2. The method according to claim 1, characterized in that Before querying and obtaining the query results in the pre-built aviation manufacturing process knowledge graph according to the graph data query statement, the following is also included: Acquiring aviation process knowledge raw data from documents in at least one aviation manufacturing process knowledge base; The neo4j database is used to store the original data of aviation process knowledge to obtain the knowledge graph in the field of aviation manufacturing process.

3. The method according to claim 1, characterized in that Identify named entities in the field of aviation manufacturing processes in natural language question sentences and obtain at least one entity keyword, including: Automatically identify keywords in the natural language question based on a pre-built knowledge graph to obtain multiple candidate keywords; Input each candidate keyword into a pre-built keyword automaton and calculate the similarity score of each candidate keyword; The candidate keywords whose similarity scores meet a preset similarity threshold are determined as entity keywords.

4. The method according to claim 1, wherein Determine the question intent based on entity keywords, including: The at least one entity keyword is input into a pre-built intent recognition mapping library, and the question intent is determined according to the at least one entity keyword.

5. The method according to any one of claims 1 to 4, characterized in that After determining the question intent based on entity keywords, it also includes: Constructing a question statement in natural language based on the entity keywords and the question intention, and providing the question statement to the user terminal for question confirmation; If a negative response message is received from the user terminal, obtaining candidate replacement entity keywords corresponding to each entity keyword, and providing each entity keyword and each candidate replacement entity keyword to the user terminal for replacement confirmation; According to the replacement confirmation response of the user terminal, new entity keywords are re-determined, and according to the new entity keywords, new question intention is re-determined.

6. The method according to claim 1, characterized in that Construct graph data query statements based on question intent and entity keywords, including: Determine the question framework from the pre-built query statement template library based on the question intention; Fill the at least one keyword into the question frame to obtain a graph database query statement.

7. The method according to claim 1, characterized in that After displaying the document index location of the query result in the aviation manufacturing process knowledge base on the user end, it also includes: In response to the user's selection of the document index location, locating a target knowledge document in the aviation manufacturing process knowledge base; After the target knowledge document is opened locally on the user terminal, the document content is displayed by jumping to the location matching the query result.

8. An automatic question-answering device for aviation manufacturing process knowledge, characterized in that: include: A question statement acquisition module is used to obtain natural language question statements in the field of aviation manufacturing technology input by the user; A question intention determination module is used to identify named entities in the field of aviation manufacturing processes in a natural language question statement, obtain at least one entity keyword, and determine the question intention based on the entity keyword; A query result acquisition unit is used to construct a graph data query statement based on the question intent and entity keywords, and to query and obtain query results in a pre-constructed aviation manufacturing process knowledge graph based on the graph data query statement; wherein the aviation manufacturing process knowledge graph is constructed using various knowledge documents in the aviation manufacturing process knowledge base; The query result display module is used to display the query results and the document index position of the query results in the aviation manufacturing process knowledge base on the user side.

9. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the automatic question-answering method for aviation manufacturing process knowledge according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement an automatic question-answering method for aviation manufacturing process knowledge according to any one of claims 1 to 7 when executed.

Images