CN112949324A - Method, system and terminal for translating and managing aircraft maintenance technical manual data - Google Patents
Method, system and terminal for translating and managing aircraft maintenance technical manual data Download PDFInfo
- Publication number
- CN112949324A CN112949324A CN202110148567.3A CN202110148567A CN112949324A CN 112949324 A CN112949324 A CN 112949324A CN 202110148567 A CN202110148567 A CN 202110148567A CN 112949324 A CN112949324 A CN 112949324A
- Authority
- CN
- China
- Prior art keywords
- translation
- original
- aircraft maintenance
- technical manual
- maintenance technical
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000012423 maintenance Methods 0.000 title claims abstract description 292
- 238000000034 method Methods 0.000 title claims abstract description 65
- 238000013519 translation Methods 0.000 claims abstract description 180
- 238000006243 chemical reaction Methods 0.000 claims abstract description 31
- 230000014616 translation Effects 0.000 claims description 179
- 238000013523 data management Methods 0.000 claims description 29
- 238000003780 insertion Methods 0.000 claims description 15
- 230000037431 insertion Effects 0.000 claims description 15
- 230000036961 partial effect Effects 0.000 claims description 8
- 238000007781 pre-processing Methods 0.000 claims description 8
- 239000000463 material Substances 0.000 claims description 6
- 210000002569 neuron Anatomy 0.000 claims description 6
- 238000012216 screening Methods 0.000 claims description 6
- 238000012986 modification Methods 0.000 claims description 5
- 230000004048 modification Effects 0.000 claims description 5
- 238000012795 verification Methods 0.000 claims description 5
- 238000005192 partition Methods 0.000 claims description 3
- 238000012552 review Methods 0.000 claims 1
- 230000002829 reductive effect Effects 0.000 abstract description 10
- 230000008569 process Effects 0.000 abstract description 7
- 230000001915 proofreading effect Effects 0.000 abstract description 3
- 230000003252 repetitive effect Effects 0.000 abstract description 2
- 230000009897 systematic effect Effects 0.000 abstract description 2
- 230000000875 corresponding effect Effects 0.000 description 37
- 230000006872 improvement Effects 0.000 description 26
- 238000007726 management method Methods 0.000 description 12
- 238000012545 processing Methods 0.000 description 11
- 238000010586 diagram Methods 0.000 description 8
- 210000004027 cell Anatomy 0.000 description 6
- 230000008439 repair process Effects 0.000 description 5
- 230000002159 abnormal effect Effects 0.000 description 3
- 230000009471 action Effects 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 238000004519 manufacturing process Methods 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 230000008901 benefit Effects 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000008030 elimination Effects 0.000 description 2
- 238000003379 elimination reaction Methods 0.000 description 2
- 230000002452 interceptive effect Effects 0.000 description 2
- 230000008520 organization Effects 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 230000006978 adaptation Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 230000002596 correlated effect Effects 0.000 description 1
- 230000006837 decompression Effects 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 230000009977 dual effect Effects 0.000 description 1
- 230000001788 irregular Effects 0.000 description 1
- 238000002955 isolation Methods 0.000 description 1
- 230000000670 limiting effect Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000012797 qualification Methods 0.000 description 1
- 230000000717 retained effect Effects 0.000 description 1
- 238000000926 separation method Methods 0.000 description 1
- 239000004557 technical material Substances 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/40—Processing or translation of natural language
- G06F40/58—Use of machine translation, e.g. for multi-lingual retrieval, for server-side translation for client devices or for real-time translation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/10—Text processing
- G06F40/12—Use of codes for handling textual entities
- G06F40/151—Transformation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/205—Parsing
- G06F40/211—Syntactic parsing, e.g. based on context-free grammar [CFG] or unification grammars
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
- G06F40/284—Lexical analysis, e.g. tokenisation or collocates
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
- G06F40/289—Phrasal analysis, e.g. finite state techniques or chunking
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Machine Translation (AREA)
Abstract
The invention provides a method for translating and managing data of an aircraft maintenance technical manual, a system and a terminal thereof, wherein Chinese conversion is realized on various manuals through translation, proofreading and auditing, so that the risk of understanding deviation of a manual by maintenance personnel is reduced to the lowest; a large amount of repetitive work in the translation process is completed by a computer, only a small amount of manual intervention is needed, and meanwhile, quick tracking and revising are achieved; the maintenance experience of the aircraft of the airline company is inserted, the key steps, the key parts and the key values are optimized, the efficiency is improved, and meanwhile, the maintenance errors can be effectively reduced; the extensible markup language is adopted to realize systematic and structured system full link, so that the jump positioning among manuals is realized, and the method is convenient, quick and accurate; and the unique mobile terminal browses pages, thereby greatly facilitating the work of basic-level maintenance personnel.
Description
Technical Field
The invention relates to the technical field of maintenance of aviation aircrafts, in particular to a translation method and a management method of aircraft maintenance technical manual data and a corresponding system.
Background
With the deep development of the aviation industry in China, the strong national strategy of civil aviation puts higher requirements on the aspects of the civil aviation industry. Various technical manuals of aircraft manufacturers and component manufacturers are basic airworthiness data which must be complied with in aircraft maintenance, and play an increasingly important role in improving the depth and the breadth of aircraft maintenance.
In recent years, various Aircraft manufacturers gradually integrate all relevant service technical manuals, including AMM (Aircraft Maintenance Manual), TSM (traditional shutdown Manual), IPC (Illustrated Part catalog), CML (configurable Material List Consumable parts List), TEM (Tool & Equipment Manual), AWL (Aircraft wire List Aircraft circuit diagram), SRM (structural Repair Manual), SPM (Standard Practice Manual), and the like, into a set of technical Manual data platform for the convenience of service personnel.
However, the technical manual data of each aircraft manufacturer is in English, the English capability of the current aircraft maintenance personnel is not uniform from the aspect of customers, and the requirement for the normal operation of the aircraft inside and outside the industry is increased in recent years. From the perspective of human factors, the superposition of dual factors of release pressure and English capacity deficiency can cause frequent occurrence of events breaking through a safety bottom line, and the consequence of air crash caused by improper maintenance of an airplane is just a time problem.
In order to avoid potential safety hazards generated under the conditions, the civil aviation bureau also strengthens the requirement of English ability of airplane maintenance personnel, issues a new requirement for license management of the maintenance personnel, aims to couple the requirement of work qualification with the English ability, but needs time for improving the English ability of the maintenance personnel, and is not practical in the situation that the civil aviation industry is increasingly prosperous, and a large number of English maintenance manuals and technical literature data are faced to ensure that a large number of maintenance personnel are off-production for a long time to master a large number of professional English words of the civil aviation and the reading ability of English literature in the maintenance technical field. Thus, if the English level is not sufficient for autonomous reading of English technical material, qualified personnel translation instructions or Chinese version manuals must be available.
In addition, for the maintenance technical manual data, the original manual content of the manufacturer is downloaded and uploaded to the server according to the manual type by the traditional technical data management method. Various manuals cannot be correlated and integrated into a set of technical manual data platform, so that basic-level maintenance personnel are inconvenient to consult.
Moreover, in many years of work, the airline Maintenance department summarizes a large amount of experience and specifications, including APS (architecture Procedure Standard airline aircraft Maintenance concept), MT (Maintenance Tip), MSL (Maintenance Service Letter), and the like, and although the APS can also be inserted into a Maintenance technical manual, the APS cannot be accurately positioned at a required task, and can only be placed at the start position of a corresponding chapter, and cannot fully play the role of prompting and guiding basic-level Maintenance personnel.
Finally, when the airplane is maintained, all relevant data need to be printed, so that paper is wasted, the airplane is inconvenient to carry, and the maintenance efficiency is seriously influenced.
Disclosure of Invention
In order to facilitate the airplane maintenance staff to use Chinese to look up the airplane maintenance technical manual integrating a large amount of experience and specifications in real time during maintenance work, the invention provides a translation method, a translation system, a data management method, a data management system and a look-up terminal for the data of the airplane maintenance technical manual. The technical scheme is as follows:
in one aspect, a method for translating aircraft maintenance technical manual data is provided, comprising the following steps:
establishing a basic corpus, converting English single sentences and corresponding Chinese single sentences in the Chinese-English aircraft maintenance work card into extensible markup language, generating a corpus, and storing the corpus in the basic corpus;
breaking the sentence of the manufacturer original aircraft maintenance technical manual to be decomposed into original single sentences;
matching the original text single sentence with an English single sentence in a basic corpus, if the matching degree is 100%, directly outputting the Chinese single sentence in the corpus as a translation, otherwise, preprocessing the original text single sentence according to the matching degree, and allowing a translator to translate and output the translation;
and converting the translated text and the corresponding original text single sentence into extensible markup language to generate new language material, and storing the new language material into the basic language database.
The translation method can be improved as follows:
as an improvement, before the chinese-english aircraft service card is converted into the extensible markup language, format conversion is performed on the chinese-english aircraft service card to form a list of table files which are a chinese single sentence and a list of english single sentences and are mutually contrasted, and one line in the table files is a corpus.
As an improvement, before the new corpus is stored in the basic corpus, if a plurality of corpuses with identical original single sentences and inconsistent translated text occur, only one corpus is reserved for storing in the basic corpus.
As an improvement, before sentence breaking is carried out on the manufacturer original aircraft maintenance technical manual, whether the markup language of the manufacturer original aircraft maintenance technical manual is the extensible markup language or not is determined, if yes, the manufacturer original aircraft maintenance technical manual is directly decomposed into original single sentences, otherwise, the manufacturer original aircraft maintenance technical manual is converted into the extensible markup language, and then sentence breaking is carried out on the content of the manufacturer original aircraft maintenance technical manual to be decomposed into the original single sentences.
As an improvement, after a fake table existing in the factory original aircraft maintenance technical manual is converted into an extensible markup language, tab characters in the fake table are replaced by tags for expressing table attributes, so that the contents in the fake table can be correctly decomposed into original single sentences.
As an improvement, all original text single sentences decomposed by the manufacturer original aircraft maintenance technical manual are counted, and all unrepeated original text single sentences are screened out.
As an improvement, the pretreatment comprises:
if the matching degree is lower than 100% but not lower than 70%, highlighting the text which is inconsistent with the English single sentence of the corpus in the original text single sentence to generate a single sentence to be translated, and outputting the translated text after manual translation by a translator;
and if the matching degree is lower than 70%, translating the original single sentence by using the neuron cloud to generate a reference translation for a translator to refer to the reference translation, checking and modifying the reference original single sentence, and outputting the translation.
As an improvement, whether the non-translated elements in the corpus correspond to the non-translated elements in the translated text or not is checked, and if not, a warning is popped up to request the translator to modify.
As an improvement, a basic term library is established, professional terms in a manufacturer original text aircraft maintenance technical manual are extracted and translated, the translated text and the original text are converted into the extensible markup language and then serve as basic terms, and the basic terms are stored in the basic term library;
and searching whether the original text of the basic terms in the basic term library corresponds to partial words or phrases in the English single sentence or not, and if so, prompting for reference of a translator.
As a modification, if the translator considers that a specific word or phrase needs to be added as a base term, the specific word or phrase may be added to the term library.
As an improvement, if the translation of the specific word or phrase translated in advance does not correspond to the translation of the basic term in the term library, an error is reported to require the translator to make a correction.
In another aspect, a translation system for aircraft service technical manual data is provided, comprising:
the corpus generating module is used for converting English single sentences and corresponding Chinese single sentences in the Chinese-English aircraft maintenance work card into extensible markup language to generate corpuses;
a basic corpus used for storing the corpus;
the manual data conversion module is used for breaking sentences of a manufacturer original aircraft maintenance technical manual to be decomposed into original single sentences;
the machine translation module is used for matching the original text single sentence with the English single sentence in the basic corpus and outputting a translation according to the matching degree or outputting the translation after being preprocessed for a translator to translate and then output the translation;
the corpus generating module also converts the translated text and the corresponding original text single sentence into extensible markup language to generate new corpus and stores the new corpus into the basic corpus.
The translation system can be further improved as follows:
as an improvement, the corpus generating module includes a work card format conversion submodule, configured to perform format conversion on a chinese-english aircraft maintenance work card, so as to form a list of table files which are chinese single sentences and a list of english single sentences and are mutually contrasted, where one line in the table files is a corpus.
As an improvement, the corpus generating module further includes a corpus duplication elimination sub-module, configured to determine whether multiple corpora with identical original sentences and inconsistent translations appear before the new corpus is stored in the basic corpus, and if yes, only one corpus is reserved for storing in the basic corpus.
As an improvement, the manual data conversion module comprises:
the markup language judgment submodule is used for determining whether the markup language of the manufacturer original text aircraft maintenance technical manual is the extensible markup language;
and the markup language conversion submodule is used for converting the manufacturer original text aircraft maintenance technical manual into the extensible markup language.
As an improvement, the manual data conversion module further comprises a sentence-breaking rule submodule, which is used for decomposing the content of the manufacturer original aircraft maintenance technical manual into original single sentences according to the sentence-breaking marks after a specific label in the extensible mark language is defined to make a sentence-breaking mark.
As an improvement, the manual data conversion module further comprises a false table conversion sub-module, after the false table existing in the factory original aircraft maintenance technical manual is converted into the extensible markup language, the false table is used for replacing tab making symbols in the false table with tags for expressing table attributes, so that the contents in the false table can be correctly decomposed into original single sentences.
As an improvement, the manual data conversion module further comprises a statistics submodule, which is used for performing statistics on all original text single sentences decomposed by the manufacturer original aircraft maintenance technical manual, and screening out all unrepeated original text single sentences.
As an improvement, the machine translation module further comprises:
the corpus retrieval submodule is used for retrieving the English single sentence which is most similar to the original single sentence in the basic corpus and judging the matching degree of the original single sentence and the English single sentence;
and the original single sentence preprocessing submodule is used for highlighting the text which is inconsistent with the English single sentence of the corpus in the original single sentence to generate a single sentence to be translated or generating a reference translation after carrying out neuron cloud translation on the original single sentence.
As an improvement, the translation system further comprises:
the term generation module is used for extracting and translating professional terms in a manufacturer original text aircraft maintenance technical manual, and converting the translated text and the original text into the extensible markup language as basic terms;
a base term base for storing the base term;
and the term library retrieval module is used for retrieving whether the original text of the basic terms in the basic term library corresponds to partial words or phrases in the English single sentence or not, and prompting for reference of a translator if the original text of the basic terms in the basic term library corresponds to partial words or phrases in the English single sentence.
As an improvement, the translation system further includes a term verification module for determining whether a translation of the specific word or phrase translated in advance corresponds to a translation of the base term in the term library.
As an improvement, the translation system also comprises an untranslated element checking module which is used for checking whether the untranslated elements in the corpus correspond to the untranslated elements in the translated text or not, and if the untranslated elements do not correspond to the untranslated elements, a warning is popped up to serve as a modification request.
In another aspect, a method for managing data of an aircraft maintenance technical manual is provided, which includes the following steps:
translating the aircraft maintenance technical manual data by using the translation system of the aircraft maintenance technical manual data through a translation method of the aircraft maintenance technical manual data, and integrating the output translated text into a Chinese-English contrast maintenance manual big database;
combining the translation in the large database of the Chinese-English comparison maintenance manual with the original single sentence according to a directory structure in an original aircraft maintenance technical manual of a manufacturer to generate Chinese-English bilingual paragraphs with the original single sentence on top and the corresponding translation on bottom, and displaying the Chinese-English bilingual paragraphs on a terminal;
and inserting the picture in the original aircraft maintenance technical manual of the manufacturer into the Chinese and English paragraphs of the corresponding translation according to the position of the picture in the original aircraft maintenance technical manual of the manufacturer corresponding to the original text.
And providing a search interface for a maintenance worker to retrieve the large database of the Chinese-English comparison maintenance manual through the keywords at the terminal.
The data management method can be further improved as follows:
as a further improvement, receiving original text revision data of an aircraft maintenance technical manual sent by an aircraft manufacturer, and revising original text single sentences in a large database of the Chinese-English comparison maintenance manual;
and translating the revised original text single sentence by using the translation system of the aircraft maintenance technical manual data through the translation method of the aircraft maintenance technical manual data to generate a new translation, and replacing the original translation corresponding to the revised original text single sentence in the Chinese-English contrast maintenance manual large database with the new translation.
As a further improvement, APS, MT and MSL which are originally inserted into the original aircraft maintenance technical manual of the manufacturer are inserted into the Chinese and English bilingual paragraphs in a foldable manner in an attachment mode, and keywords of the relevant tasks of the APS, MT and MSL corresponding to the translations are used as insertion points.
In yet another aspect, a data management system for an aircraft maintenance technical manual is provided, comprising:
the database generation module is used for integrating the output translated text into a Chinese-English contrast maintenance manual big database after the aircraft maintenance technical manual data are translated by the aircraft maintenance technical manual data translation system through the aircraft maintenance technical manual data translation method;
the display text generation module is used for generating Chinese and English bilingual paragraphs with the original single sentence on the upper part and the corresponding translation on the lower part according to the translated text in the large database of the Chinese-English comparison maintenance manual and the directory structure in the original aircraft maintenance technical manual of the manufacturer in combination with the original single sentence, and displaying the Chinese and English bilingual paragraphs to the terminal;
and the searching interface is used for searching the large database of the Chinese-English comparison maintenance manual by the maintenance personnel through the keywords at the terminal.
The data management system can be further improved as follows:
as a further improvement, the aircraft maintenance system further comprises a manual revision module, which is used for receiving revision data of original texts of an aircraft maintenance technical manual sent by an aircraft manufacturer, revising the original text single sentences in the large database of the chinese-english comparison maintenance manual, translating the revised original text single sentences by using a translation system of the aircraft maintenance technical manual data through a translation method of the aircraft maintenance technical manual data, and generating new translations, wherein the new translations replace the original translations corresponding to the revised original text single sentences in the large database of the chinese-english comparison maintenance manual.
As a further improvement, the system also comprises a self-editing content insertion module which is used for inserting the APS, MT and MSL which are originally inserted into the original aircraft maintenance technical manual of the manufacturer into the bilingual paragraphs in Chinese and English in a folding way in an attachment mode by taking the keywords of the relevant tasks of the APS, MT and MSL corresponding to the translations as insertion points.
In a further aspect, an aircraft maintenance technical manual consulting terminal is provided, which includes:
the display text and picture receiving module is used for receiving the Chinese and English bilingual paragraphs generated by the data management system of the aircraft maintenance technical manual and the pictures inserted into the Chinese and English paragraphs, and displaying the Chinese and English paragraphs on a display screen of the terminal;
and the retrieval module is connected with a retrieval interface of the data management system of the aircraft maintenance technical manual, provides a retrieval frame in a display screen of the terminal and provides a keyword for a maintenance worker to retrieve the large database of the Chinese-English comparison maintenance manual at the terminal.
The reference terminal can be improved as follows:
as a further improvement, the system further comprises a terminal display interface generating module, which is used for displaying the Chinese and English paragraphs, the pictures and the directory structures in a partition manner on a terminal display screen.
As a further improvement, the reference terminal is a mobile terminal, and the mobile terminal is provided with a display interface self-adaptive module for realizing single-screen skip display among a directory structure, Chinese and English paragraphs and pictures.
Compared with the prior art, the invention has the advantages that:
(1) by the translation method and the translation system for the aircraft maintenance technical manual data, the original aircraft maintenance technical manual of the manufacturers of two foreign aircraft manufacturers can be realized to be Chinese, the maintenance management risk is prevented, and the maintenance production efficiency is improved;
(2) through the data management method and the data management system of the aircraft maintenance technical manual, the international passing interactive structured language standard is applied, so that various maintenance technical data have interactive link access relations, including an AAMM (APS aircraft maintenance manual), an IPC (part and part map manual), an FIM (fault isolation manual), a CML (expendable component bill of materials), a TEM (tool equipment manual), an SRM (structure repair manual), an SPM (normative construction manual) and the like, and the data management system realizes the query of single-machine applicable contents;
(3) the method effectively breaks through the limitation of a maintenance Technical Document Management (TDMS) system of an airline company, can better reflect maintenance letters and maintenance prompt information at the accurate position of the AAMM original text, changes the current situation that the current situation is limited by conditions and has to be managed crudely, improves the use experience of a manual of maintenance personnel, and assists in maintenance and production;
(4) the method is beneficial to organizing the professional English learning of the crew maintenance personnel, the structured technical file data can be more conveniently used for professional English training and the learning of each subsystem of the airplane, so that the knowledge of the crew on the airplane can conveniently span from the knowledge (knock) stage to the deep knowledge (understand) stage;
(5) according to the method, the excellent APS project is sublimated from the training guide to be a working basis with airworthiness, the excellent APS content summarized from the maintenance practice is combined with the manufacturer original aircraft maintenance technical manual of the aircraft manufacturer to form a maintenance basis file, multi-dimensional prompt and warning are carried out on key steps and operation, the situation that the engineering management and quality management requirements are difficult to fall to the ground is changed, and the engineering maintenance engineering management capability is further improved;
(6) the invention builds basic term library, basic language database and final Chinese and English paragraph from the initially accumulated work card, and lays the foundation of the bottom data for intelligent translation and intelligent quick revision of the machine;
(7) by using the basic term library, the basic language database and the Chinese and English paragraphs and adding a small amount of manual intervention, the rapid translation and revision of the aircraft maintenance technical manual data can be realized, the efficiency of the data processing of the aircraft maintenance technical manual is greatly improved, the tracking and updating of the aircraft maintenance technical manual data become possible, and the legality and navigability of the AAMM manual system are ensured.
(8) The built Chinese-English comparison maintenance manual big database adopts the international popular XML extensible markup language, so that documents can be identified and utilized by other management systems like data;
in conclusion, Chinese conversion is realized on various manuals through translation, proofreading and auditing, so that the risk of understanding deviation of the manuals by maintenance personnel is reduced to the minimum; a large amount of repetitive work in the translation process is completed by a computer, only a small amount of manual intervention is needed, and meanwhile, quick tracking and revising are achieved; the maintenance experience of the aircraft of the airline company is inserted, the key steps, the key parts and the key values are optimized, the efficiency is improved, and meanwhile, the maintenance errors can be effectively reduced; the extensible markup language is adopted to realize systematic and structured system full link, so that the jump positioning among manuals is realized, and the method is convenient, quick and accurate; and the unique mobile terminal browses pages, thereby greatly facilitating the work of basic-level maintenance personnel.
Drawings
FIG. 1 is a flowchart of a translation method according to an embodiment;
FIG. 2 is a schematic view of a service card;
FIG. 3 is a file of components of a docx file after decompression;
FIG. 4 is a sample XML file tag;
FIG. 5 is program code for category identification;
FIG. 6 is a flowchart of a sentence merging procedure;
FIG. 7 is a diagram of a paragraph merge effect;
FIGS. 8 and 9 are both deduplication examples;
FIG. 10 is an example of deduplication that requires special attention and cannot be considered as a repeat sentence;
FIG. 11 is a false representation;
FIG. 12 is the corresponding XML document code for the fake table portion;
FIG. 13 is a pseudo table converted XML document code;
FIGS. 14-20 are exemplary diagrams for demonstrating sentence break procedures;
FIG. 21 is a flowchart of a translation method according to the second embodiment;
FIG. 22 is an example of the contents of a portion of a base term library;
FIG. 23 is a block diagram showing a structure of a translation system according to a third embodiment;
FIG. 24 is a block diagram showing a configuration of a translation system according to the fourth embodiment;
FIG. 25 is an interface of the term verification module in error reporting;
FIG. 26 is a flowchart illustrating a data management method according to a fifth embodiment;
FIG. 27 is a block diagram showing a configuration of a data management system according to a sixth embodiment;
FIGS. 28-30 are exemplary diagrams illustrating the operation of the self-programming content insertion module;
FIG. 31 is a batch document source code excerpt showing repair experience, i.e., self-catalogued, batch insertion into manual;
FIGS. 32-33 are exemplary diagrams illustrating the operation of a display interface adaptation module of a mobile terminal;
fig. 34 is a chinese-english comparison form file for completing the format conversion of the chinese-english service card.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, embodiments of the present invention will be described in detail with reference to the accompanying drawings.
Example one
The invention provides a method for translating data of an aircraft maintenance technical manual, which comprises the following steps as shown in figure 1.
And 102, breaking the sentence of the manufacturer original aircraft maintenance technical manual to be decomposed into original single sentences.
And 103, counting all original text single sentences decomposed by the manufacturer original aircraft maintenance technical manual, and screening all unrepeated original text single sentences.
Specifically, the AAMM platform needs to process a huge amount of data, and 350 ten thousand sentence segments need to be translated in only one item of the a320 AMM manual. In order to complete such a difficult task, besides the hard payment of engineers, translation software also provides important help for us, a technical maintenance manual usually has a large number of repeated sentences, and according to the characteristic, all non-repeated sentence segments can be screened out by using the statistical report function of trados, so that the workload is greatly reduced;
taking an AMM manual of an air passenger A320 series as an example, through screening, the maintenance manual of A320 has 462688 unrepeated periods which are less than one seventh of the total period of the whole manual, and a working plan is made according to the report, so that the working intensity of translators is greatly reduced, and the working efficiency is improved.
104, matching the original text single sentence with an English single sentence in a basic corpus, and judging the matching degree;
if the matching degree is 100%, execute step 104 a: directly outputting the Chinese single sentence in the corpus as a translation; otherwise, executing step 104b, and after correspondingly preprocessing the original text single sentence according to the matching degree, allowing the translator to translate and output the translated text.
And 105, converting the translated text and the corresponding original text single sentence into an extensible markup language, generating a new corpus, and storing the new corpus into the basic corpus.
Specifically, the basic corpus can be arranged on the server, and each translator can share the basic corpus, so that any sentence of the audited sentence translation can be used by all the translators, the translation efficiency is greatly improved, and the unification of translation standards is also ensured.
The translation method may further include step 106, checking whether the untranslated elements in the corpus correspond to the untranslated elements in the translated text, and popping up a warning to require the translator to modify if the untranslated elements do not correspond to the untranslated elements in the translated text.
The step 101 includes the following steps:
step 1011, format conversion is performed on the Chinese and English aircraft maintenance work card to form a list of Chinese single sentences and a list of English single sentences which are mutually contrasted, and one line in the list of form files is a corpus.
Specifically, the existing service card is doc document, as shown in fig. 2, the specific process of format conversion is as follows, and the programming language used by the processing program is python.
Firstly converting doc into docx, because the organizing modes of Word 2003 and previous versions are different from the organizing modes of Word 2007 and later versions, in order to meet the updating requirement and the subsequent use of a Python docx library function, the doc format file needs to be converted into the docx format, and the mode of directly changing the postfix of the file can cause the problem of later analysis, so that a win32 program is called, and the doc file is stored as the docx file in batch through office software;
decompressing the docx file, because the docx file is a compressed file which integrates texts, pictures, a large amount of format settings and the like, decompressing the docx file into various components through the zipfile, as shown in fig. 3, by analyzing the components, finding that the required texts are all in document.xml under the doc folder, so that only the xml file can be saved;
through analyzing the xml tag of Word transformation, the basic organization form is para, as shown in FIG. 4, the text is in the < w: t > tag in the < w: p >, and the content needing to be extracted is locked;
extracting numbered paragraphs, because the content extracted according to < w: t > tags is many and miscellaneous, the initial processing mode is to find the object to be deleted, then deleting the object by using a regular expression, later, it is found that the processing mode of each industrial card is different, the individual content is also layered endlessly, the method relying on the deleted content is not efficient, the universality is not strong, because the content required by people appears in the original Word by steps with numbers, in addition, special contents such as warning, note and the like are also provided, other contents are basically not required, therefore, the content of the step with numbers in the original Word needs to be extracted next, according to the official openxml document of office, the number information body appears in < w: ilvl > and < w: numId >, the problem of parsing numspace in the numId parent tag of the document is parsed by using the lxml library of Python (in addition, when the xml document generated by using lxml Word encounters namespace, the information is in the initial position of the corresponding xml file, and only the statement in the program is needed), only the numbered content in the standard format and the numbered content in the text form are extracted in the process, and no relevant information exists in the label, so that the information needs to be extracted by using a logical relationship;
combining texts which are split into a plurality of paragraphs, through the steps, required text information is basically extracted, but a text of a paragraph in a plurality of words is split into a plurality of paragraphs, a sentence is split into a plurality of incomplete sentences, so that the split sentences need to be recombined, in addition, the content of each engineering instruction or work card has a certain organization rule, or the upper English corresponding to the upper Chinese is lower or the upper English corresponding to the lower Chinese, on the basis, when each document is analyzed, the upper and lower language judgment of the document is firstly made, then the document is classified by the current paragraph, and a category mark is added, and a specific program code is shown as fig. 5:
1) paragraphs numbered according to Word format;
2) paragraphs numbered in text form;
3) paragraphs in the form of Warning, Caution, NOTE, etc.;
after the identification is completed, all the paragraphs with step numbers and paragraphs with special forms (Warning, route, NOTE) in the Word document are marked, the remaining paragraphs without marks are the paragraphs to be merged, the merging rules are shown as fig. 6, the detached paragraphs can be merged through the program flow of fig. 6, and finally the merging effect of the text of the repair work card split into multiple paragraphs as shown in fig. 7 is obtained, so that errors are prevented from occurring during the subsequent bilingual comparison;
and (3) dividing sentences, and then dividing sentences in the paragraphs, wherein the simplification is made by considering the complexity of sentence components, firstly dividing the whole paragraph into Chinese and English parts according to soft carriage return, and then dividing the Chinese part into Chinese parts. Splitting, splitting English parts according to 'once', merging Chinese and English when the number of split Chinese sentence segments is equal to that of English sentence segments, so that the split Chinese sentence segments become a desirable sentence segment comparison format, because the special condition of abbreviation plus 'once' exists in English, when splitting English sentence segments, a sentence library is split by using nltk natural language, and the problem of abnormal punctuation in English sentences can be perfectly solved;
writing into Excel for storage, after sentence separation, organizing English and corresponding Chinese, operating Excel with xlwings, storing English and Chinese comparison texts to form a list of Chinese single sentences and a list of English single sentences which are mutually compared, as shown in fig. 34, one line in the table file is a corpus for subsequent storage in a basic corpus.
In step 1012, if there are multiple corpora with consistent original sentence but inconsistent translated text, only one corpus is reserved for storing in the basic corpus.
Specifically, the same sentence of english may also result in different corresponding chinese characters due to different work card translators. Some of them are translation problems and need to judge and retain correct translation. Some of the phrases are only idiomatic phrase differences, and redundant translation segments need to be removed to unify the translation segments into a smoother translation, as shown in fig. 8 and 9.
In addition, it should be particularly noted that, in the chinese-english comparison table file after conversion and arrangement, there are a large number of repeated sentence segments, and many sentences in the original text are extremely similar in their entirety and have only slight differences, such as numbers, position class names (up/down, front/back, left/right, etc.), as in the example shown in fig. 10, two sentence segments are nearly 30 words, differ by only one letter but point to parts in different positions, which can never be counted as repeated sentences, otherwise, serious translation errors can be caused.
The step 102 comprises the following steps:
step 1021, determining whether the markup language of the manufacturer original aircraft maintenance technical manual is the extensible markup language, if so, directly decomposing the manufacturer original aircraft maintenance technical manual into original single sentences, otherwise, converting the manufacturer original aircraft maintenance technical manual into the extensible markup language, and then segmenting the contents of the manufacturer original aircraft maintenance technical manual to decompose the manufacturer original aircraft maintenance technical manual into the original single sentences.
Specifically, currently, part of manufacturer original text airplane maintenance manuals such as an AMM manual of an airbus 320 manual and a boeing 737NG use SGML format files, and maintenance personnel in the existing maintenance work establish file rules of an APS-based AMM platform in an XML format by combining maintenance experience and analysis of the files, so that the manufacturer original text airplane maintenance manuals are conveniently subjected to subsequent processing, and finally the AMM manuals in the SGML format are converted into XML files by using an Arbor text, so that the parts are cut into appropriate section files as required to be further translated.
Step 1022, after the fake table in the manufacturer original aircraft maintenance technical manual is converted into the extensible markup language, replacing the tab in the fake table with a label for expressing the table attribute, so that the content in the fake table can be correctly decomposed into original single sentences.
Specifically, the AMM manual includes an irregular chart display as shown in fig. 11, which uses punctuation marks such as exclamation marks as tab making symbols to draw a table frame, uses the length of a space control table, which is a temporary table making method in early text processing, and analyzes an XML file to find that the label is < txtgtgraphic >, the sub-label is < txtLine >, and each action is a < txtLine > label as shown in fig. 12, such a table is called a false table, and the existence of the false table causes the original text of the continuous manual to be scattered and mixed into different labels, and the file is analyzed in the unit of the label in software, which causes the situation that the contents of different cells are mixed into the same cell or different cells are mixed into the same cell, and brings great difficulty to data processing; to solve this problem, we can first extract the < txgraphic > tag in XML and draw a new table according to the content of each false table in a form conforming to the XML structure, the converted table is displayed in XML with the < table > tag inserted after the txgrphc tag, as shown in fig. 13, and an attribute "xylinkid" is defined for the < table > tag to identify the table, and the sub-tag meanings are as follows:
| tgroup | define the number of columns |
| Colspec | Defining column width ratio and column identification number |
| Thead | Defining the number of columns of a header |
| Tbody | Defining text of a table |
| Row | Definition line |
| Para | Defining text within cells |
| Morerows | Defining merge cells |
By the method, the hard-to-process false table is converted into the form with a uniform format and meeting the format requirement, the content in the false table can be correctly analyzed, and the subsequent processing is facilitated.
And 1023, after a specific label in the extensible markup language is defined to mark a sentence break, decomposing the content of the manufacturer original aircraft maintenance technical manual into an original single sentence according to the sentence break mark.
Specifically, a sentence break error is generally caused by the sentence break rule of Trados identifying some tags in the XML file as end characters, so that Trados needs to change the processing of the tags. As shown in FIG. 14, a sentence is divided into 3 lines, i.e. 44-46 lines, and it is necessary to find whether the content corresponding to the original XML file has tags. Opening the corresponding XML file by a browser, searching the content of 45 lines as shown in FIG. 15, dividing the file by a label < REFINT > </REFINT >, continuously searching the label 'REFINT' in the XML file, confirming the action of the label at other positions of the file, and if no other action exists, setting the label in the Tracos as 'embedded', so that the label is not regarded as a sentence break symbol after encountering the label.
After the setting is successful, the file is opened, as shown in fig. 16, the tag "REFINT" is displayed, during translation, the tags must be retained, and generally appear in pairs (if there is a tag at the beginning of a sentence, fig. 17 cannot be shown), the relative positions of the tags in the sentence can be modified according to the Chinese language sequence as shown in fig. 18, because there are a large number of tags in the XML file and the functions of the tags are different, during translation, different definitions need to be performed on different tags to parse the XML file, so that the sentence break of the document meets the requirement of the meaning, when the parsing rule is formulated, all the tags in the XML file of the manual are listed, as shown in fig. 19, so as to parse the file and translate the file, and when an abnormal sentence break caused by the tag is found in the translation process, a parsing rule is modified, so that the context of all the tags needs to be analyzed, time and labor are wasted, the rule of the resolver needs to be continuously adjusted according to feedback in the translation process, and projects need to be reestablished every adjustment, so that a large amount of repeated work is caused;
by way of summary, the tag rules are redefined by means of XPATH. By utilizing the corresponding relation of XPATH sub-tags, all sub-tags and sub-tags under the minimum unit tag 'PARA' of a sentence are subjected to set definition translation attributes, as shown in figure 20, so that the problem of abnormal sentence break in translation is solved at one time, the number of tags needing to be analyzed is effectively reduced, and the file parsing efficiency is greatly improved.
The preprocessing in step 104 includes:
and step 1041, if the matching degree is lower than 100% but not lower than 70%, highlighting the text in the original text single sentence which is inconsistent with the English single sentence of the corpus to generate a single sentence to be translated, and outputting the translated text after manual translation by a translator.
And 1042, if the matching degree is lower than 70%, translating the original text single sentence by using the neuron cloud to generate a reference translation for a translator to refer to the reference translation, checking and modifying the reference original text single sentence, and outputting the translation.
Example two
On the basis of the first embodiment, as shown in fig. 21, the method for translating the aircraft maintenance technical manual data may further include the following steps:
Specifically, 2181 aircraft maintenance basic terms selected in the embodiment are used as a basic term library, and part of the basic terms and translations are shown in fig. 22.
In step 203, if the translator considers that the specific word or phrase needs to be added as the base term, the specific word or phrase may be added to the term library.
In step 204, if the translation of the specific word or phrase translated in advance does not correspond to the translation of the basic term in the term library, an error is reported to require the translator to correct the word or phrase.
EXAMPLE III
The present invention also provides a system for translating aircraft maintenance technical manual data, as shown in fig. 23, including:
the corpus generating module is used for converting English single sentences and corresponding Chinese single sentences in the Chinese-English aircraft maintenance work card into extensible markup language to generate corpuses;
a basic corpus used for storing the corpus;
the manual data conversion module is used for breaking sentences of a manufacturer original aircraft maintenance technical manual to be decomposed into original single sentences;
the machine translation module is used for matching the original text single sentence with the English single sentence in the basic corpus and outputting a translation according to the matching degree or outputting the translation after being preprocessed for a translator to translate and then output the translation;
the corpus generating module also converts the translated text and the corresponding original text single sentence into extensible markup language to generate new corpus and stores the new corpus into the basic corpus.
Wherein, the corpus generation module includes:
the work card format conversion submodule is used for carrying out format conversion on the Chinese and English aircraft maintenance work card to form a list of table files which are Chinese single sentences and English single sentences and are mutually contrasted, and one line in each table file is a corpus;
and the corpus duplication elimination submodule is used for judging whether a plurality of corpora with consistent original single sentences and inconsistent translated texts exist before the new corpus is stored in the basic corpus, and if so, only one corpus is reserved for storing in the basic corpus.
Wherein, manual data conversion module includes:
the markup language judgment submodule is used for determining whether the markup language of the manufacturer original text aircraft maintenance technical manual is the extensible markup language;
the markup language conversion submodule is used for converting the manufacturer original text aircraft maintenance technical manual into an extensible markup language;
the sentence break rule submodule is used for decomposing the content of a manufacturer original aircraft maintenance technical manual into original single sentences according to the sentence break marks after a specific label in the extensible mark language is defined to mark the sentence break;
the false table conversion submodule is used for replacing tab making symbols in the false table with labels for expressing table attributes after the false table existing in the manufacturer original text aircraft maintenance technical manual is converted into extensible markup language, so that the content in the false table can be correctly decomposed into original text single sentences;
and the counting submodule is used for counting all original text single sentences decomposed by the manufacturer original aircraft maintenance technical manual and screening all unrepeated original text single sentences.
Wherein the machine translation module further comprises:
the corpus retrieval submodule is used for retrieving the English single sentence which is most similar to the original single sentence in the basic corpus and judging the matching degree of the original single sentence and the English single sentence;
and the original single sentence preprocessing submodule is used for highlighting the text which is inconsistent with the English single sentence of the corpus in the original single sentence to generate a single sentence to be translated or generating a reference translation after carrying out neuron cloud translation on the original single sentence.
Example four
On the basis of the third embodiment, as shown in fig. 24, the translation system for aircraft maintenance technical manual data further includes:
the term generation module is used for extracting and translating professional terms in a manufacturer original text aircraft maintenance technical manual, and converting the translated text and the original text into the extensible markup language as basic terms;
a base term base for storing the base term;
a term library retrieval module, configured to retrieve whether an original text of a basic term in the basic term library corresponds to a partial word or phrase in the english single sentence, and if so, prompt the translator for reference;
the term verification module is used for judging whether the translated text of the specific word or phrase translated in advance corresponds to the translated text of the basic term in the term library;
specifically, the term verification module summarizes 163 common key words which are easy to be mistaken, establishes a logical relationship, if a certain key word appears in the original text, the Chinese language must have a corresponding translation, otherwise, as shown in fig. 25, manual processing is required by error reporting;
the non-translation element checking module is used for checking whether a non-translation element in the corpus corresponds to a non-translation element in the translation, and if not, popping up a warning as a modification request;
specifically, the non-translated element checking module can verify the complete consistency of the number and the numerical value of the number in the translated sentence and the original sentence when checking the non-translated element such as the number, and if the number and the numerical value are different, a warning is given to require the translator to modify.
EXAMPLE five
The invention also provides a data management method of the aircraft maintenance technical manual, as shown in fig. 26, comprising the following steps:
305, receiving original text revision data of an aircraft maintenance technical manual sent by an aircraft manufacturer, and revising original text single sentences in a large database of the Chinese-English comparison maintenance manual;
EXAMPLE six
The present invention also provides a data management system of an aircraft maintenance technical manual, as shown in fig. 27, which includes:
the database generation module is used for integrating the output translated text into a Chinese-English contrast maintenance manual big database after the aircraft maintenance technical manual data are translated by the aircraft maintenance technical manual data translation system through the aircraft maintenance technical manual data translation method;
specifically, the database generation module uses the existing aircrafts for air passenger A320 and Boeing B737NG to maintain Chinese and English work cards, establishes a basic corpus and a basic term library, uses the basic corpus and the term library by the machine translation module, translates AMM manuals of original manufacturers of air passenger A320 aircrafts and Boeing B737NG, and continuously improves the accuracy of machine translation through manual proofreading/auditing, thereby finally forming a complete large database of a Chinese and English comparison maintenance manual.
The display text generation module is used for generating Chinese and English bilingual paragraphs with the original single sentence on the upper part and the corresponding translation on the lower part according to the translated text in the large database of the Chinese-English comparison maintenance manual and the directory structure in the original aircraft maintenance technical manual of the manufacturer in combination with the original single sentence, and displaying the Chinese and English bilingual paragraphs to the terminal;
and the searching interface is used for searching the large database of the Chinese-English comparison maintenance manual by the maintenance personnel through the keywords at the terminal.
The data management system also comprises a manual revision module, a Chinese-English comparison maintenance manual database and a Chinese-English comparison maintenance manual database, wherein the manual revision module is used for receiving the revision data of the original text of the aircraft maintenance manual sent by an aircraft manufacturer, revising the original text single sentence in the Chinese-English comparison maintenance manual database, translating the revised original text single sentence by using the translation system of the aircraft maintenance technical manual data through the translation method of the aircraft maintenance technical manual data and generating a new translation, and replacing the original translation corresponding to the revised original text single sentence in the Chinese-English comparison maintenance manual database with the new translation;
specifically, based on a large database of a Chinese-English contrast maintenance manual, rapid translation, revision, digitalization and structuralization of English technical data of manufacturers under manual intervention are realized, and the workload of manual translation/revision is reduced to the maximum extent, so that the latest and effective manual system is ensured;
and the self-editing content insertion module is used for inserting APS, MT and MSL which are originally inserted into the original aircraft maintenance technical manual of the manufacturer into the Chinese and English bilingual paragraphs in a foldable manner in an attachment form and by taking keywords of the relevant tasks of the APS, MT and MSL corresponding to the translation as insertion points.
Specifically, the self-editing contents are divided into an airline maintenance management concept (APS) and maintenance experience (MT, MSL and the like), which are important components of an AAMM manual in a data management system of an aircraft maintenance technical manual, APS items are inserted for maintenance, excellent APS contents summarized by an airline from years of maintenance practice are combined with an aircraft manufacturer manual, and are explained in the form of inserting characters or pictures, so that key steps, key parts and key numerical values are optimized, efficiency is improved, maintenance errors can be effectively reduced, the self-editing contents of the airlines are inserted into the AAMM manual, the situation that engineering management and quality management requirements are difficult to fall on the ground is changed, and the maintenance engineering management capability of the airline is further improved.
The APS related content is directly inserted into the AAMM manual in the form of text or picture, as shown in fig. 28, when the APS related content is inserted, the APS related content can be set in a foldable form, so as to avoid that the self-editing content occupies too large reading space and affects the use experience, and the maintenance experience (MT, MSL, etc.) is inserted into the AAMM manual system related task in the form of an attachment, as shown in fig. 29, the primary layer maintenance personnel can expand by clicking a specific icon before performing the related task, and obtain the maintenance prompt as shown in fig. 30.
Meanwhile, due to the fact that the number of maintenance experiences is large, insertion positions are various, related batch processing files are compiled by development groups, each maintenance experience file is compared with corresponding insertion points one by one, and automatic batch insertion is successfully achieved. This way, the insertion workload is greatly reduced, and the work efficiency is improved, as shown in fig. 31, the source code of the batch processing file is selected by inserting the repair experience, i.e., the self-editing content into the manual in batch.
EXAMPLE seven
The invention also provides a consulting terminal of the aircraft maintenance technical manual, which comprises:
the display text and picture receiving module is used for receiving the Chinese and English bilingual paragraphs generated by the data management system of the aircraft maintenance technical manual and the pictures inserted into the Chinese and English paragraphs, and displaying the Chinese and English paragraphs on a display screen of the terminal;
the retrieval module is connected with a retrieval interface of a data management system of the aircraft maintenance technical manual, and provides a retrieval frame in a display screen of the terminal for a maintenance worker to retrieve the large database of the Chinese-English comparison maintenance manual through keywords at the terminal;
and the terminal display interface generating module is used for displaying the Chinese and English paragraphs, the pictures and the directory structures in a partition manner on a terminal display screen.
The reference terminal is a mobile terminal, and the mobile terminal is provided with a display interface self-adaptive module for realizing single-screen skip display among a directory structure, Chinese and English paragraphs and pictures. Specifically, as shown in fig. 32 and 33, when one of the types of the service manuals in fig. 32, such as the AMM, is clicked, the screen jumps to the directory in fig. 33.
It will be understood by those skilled in the art that all or part of the steps for implementing the above embodiments may be implemented by hardware, or may be implemented by hardware related to instructions of a program, where the program may be stored in a computer-readable storage medium, and the above-mentioned storage medium may be a read-only memory, a magnetic disk, an optical disk, or the like.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents, improvements and the like made within the spirit and principle of the present invention should be considered as within the scope of the present invention.
Claims (31)
1. A translation method for aircraft maintenance technical manual data comprises the following steps:
establishing a basic corpus, converting English single sentences and corresponding Chinese single sentences in the Chinese-English aircraft maintenance work card into extensible markup language, generating a corpus, and storing the corpus in the basic corpus;
breaking the sentence of the manufacturer original aircraft maintenance technical manual to be decomposed into original single sentences;
matching the original text single sentence with an English single sentence in a basic corpus, if the matching degree is 100%, directly outputting the Chinese single sentence in the corpus as a translation, otherwise, preprocessing the original text single sentence, and allowing a translator to translate and output the translation;
and converting the translated text and the corresponding original text single sentence into extensible markup language to generate new language material, and storing the new language material into the basic language database.
2. A method for the translation of aircraft maintenance technical manual data according to claim 1, characterized in that: before the Chinese and English aircraft maintenance work card is converted into the extensible markup language, format conversion is carried out on the Chinese and English aircraft maintenance work card to form a list of Chinese single sentences and a list of English single sentences which are mutually contrasted, and one line in the list of form files is a corpus.
3. A method for the translation of aircraft maintenance technical manual data according to claim 2, characterized in that: before the new corpus is stored in the basic corpus, if a plurality of corpuses with identical original sentences and inconsistent translated text appear, only one corpus is reserved for storing in the basic corpus.
4. A method for the translation of aircraft maintenance technical manual data according to claim 3, characterized in that: before sentence breaking is carried out on the manufacturer original aircraft maintenance technical manual, whether the markup language of the manufacturer original aircraft maintenance technical manual is the extensible markup language or not is determined, if yes, the manufacturer original aircraft maintenance technical manual is directly decomposed into original single sentences, otherwise, the manufacturer original aircraft maintenance technical manual is converted into the extensible markup language, and then sentence breaking is carried out on the content of the manufacturer original aircraft maintenance technical manual so as to be decomposed into the original single sentences.
5. Method for the translation of aircraft maintenance technical manual data according to claim 4, characterized in that: and after the fake table existing in the factory original aircraft maintenance technical manual is converted into the extensible markup language, replacing tab making symbols in the fake table with tags for expressing table attributes, so that the content in the fake table can be correctly decomposed into original single sentences.
6. Method for the translation of aircraft maintenance technical manual data according to claim 5, characterized in that: and counting all original text single sentences decomposed by the manufacturer original aircraft maintenance technical manual, and screening all unrepeated original text single sentences.
7. A method for the translation of aircraft maintenance technical manual data according to claim 6, wherein said preprocessing comprises:
if the matching degree is lower than 100% but not lower than 70%, highlighting the text which is inconsistent with the English single sentence of the corpus in the original text single sentence to generate a single sentence to be translated, and outputting the translated text after manual translation by a translator;
and if the matching degree is lower than 70%, translating the original single sentence by using the neuron cloud to generate a reference translation for a translator to refer to the reference translation, checking and modifying the reference original single sentence, and outputting the translation.
8. A method for the translation of aircraft maintenance technical manual data according to claim 7, characterized in that: checking whether the non-translated elements in the corpus correspond to the non-translated elements in the translated text, and popping up a warning to request the translator to modify if the non-translated elements in the corpus do not correspond to the non-translated elements in the translated text.
9. A method for the translation of aircraft maintenance technical manual data according to claim 1 or 8, characterized in that it comprises the following further steps:
establishing a basic term library, extracting and translating professional terms in a manufacturer original text aircraft maintenance technical manual, converting the translated text and the original text into the extensible markup language, then using the extensible markup language as basic terms, and storing the basic terms in the basic term library;
and searching whether the original text of the basic terms in the basic term library corresponds to partial words or phrases in the English single sentence or not, and if so, prompting for reference of a translator.
10. A method for the translation of aircraft maintenance technical manual data according to claim 9, characterized in that: if the translator considers that a specific word or phrase needs to be added as a base term, the specific word or phrase can be added to the term library.
11. A method for the translation of aircraft maintenance technical manual data according to claim 10, characterized in that: if the translation of the specific word or phrase translated in advance does not correspond to the translation of the basic term in the term library, an error is reported to require the translator to correct the word or phrase.
12. A translation system for aircraft maintenance technical manual data, comprising:
the corpus generating module is used for converting English single sentences and corresponding Chinese single sentences in the Chinese-English aircraft maintenance work card into extensible markup language to generate corpuses;
a basic corpus used for storing the corpus;
the manual data conversion module is used for breaking sentences of a manufacturer original aircraft maintenance technical manual to be decomposed into original single sentences;
the machine translation module is used for matching the original text single sentence with the English single sentence in the basic corpus and outputting a translation according to the matching degree or outputting the translation after being preprocessed for a translator to translate and then output the translation;
the corpus generating module also converts the translated text and the corresponding original text single sentence into extensible markup language to generate new corpus and stores the new corpus into the basic corpus.
13. The translation system for aircraft maintenance technical manual data according to claim 12, wherein: the corpus generating module comprises a work card format conversion submodule for converting the format of a Chinese-English aircraft maintenance work card to form a list of Chinese single sentences and a list of English single sentences which are mutually contrasted, wherein one line in the list of form files is a corpus.
14. The translation system for aircraft maintenance technical manual data according to claim 13, wherein: the corpus generating module further comprises a corpus duplication removing submodule for judging whether a plurality of corpuses with identical original single sentences and inconsistent translations appear in the new corpus before the new corpus is stored in the basic corpus, and if so, only one corpus is reserved for storing in the basic corpus.
15. The system for translating aircraft maintenance technical manual data according to claim 12, wherein the manual data conversion module comprises:
the markup language judgment submodule is used for determining whether the markup language of the manufacturer original text aircraft maintenance technical manual is the extensible markup language;
and the markup language conversion submodule is used for converting the manufacturer original text aircraft maintenance technical manual into the extensible markup language.
16. The translation system for aircraft maintenance technical manual data according to claim 15, wherein: the manual data conversion module also comprises a sentence-breaking rule submodule used for decomposing the content of the factory original aircraft maintenance technical manual into original single sentences according to the sentence-breaking marks after the specific labels in the extensible mark language are defined to make sentence-breaking marks.
17. The translation system for aircraft maintenance technical manual data according to claim 16, wherein: the manual data conversion module further comprises a false table conversion submodule, and after the false table existing in the factory original aircraft maintenance technical manual is converted into the extensible markup language, the false table is used for replacing tab making symbols in the false table with labels used for expressing table attributes, so that the content in the false table can be correctly decomposed into original single sentences.
18. The translation system for aircraft maintenance technical manual data according to claim 17, wherein: the manual data conversion module further comprises a statistics submodule for performing statistics on all original text single sentences decomposed by the manufacturer original aircraft maintenance technical manual and screening out all unrepeated original text single sentences.
19. The translation system for aircraft maintenance technical manual data according to claim 12, wherein the machine translation module further comprises:
the corpus retrieval submodule is used for retrieving the English single sentence which is most similar to the original single sentence in the basic corpus and judging the matching degree of the original single sentence and the English single sentence;
and the original single sentence preprocessing submodule is used for highlighting the text which is inconsistent with the English single sentence of the corpus in the original single sentence to generate a single sentence to be translated or generating a reference translation after carrying out neuron cloud translation on the original single sentence.
20. A translation system for aircraft maintenance technical manual data according to any one of claims 12 to 19, further comprising:
the term generation module is used for extracting and translating professional terms in a manufacturer original text aircraft maintenance technical manual, and converting the translated text and the original text into the extensible markup language as basic terms;
a base term base for storing the base term;
and the term library retrieval module is used for retrieving whether the original text of the basic terms in the basic term library corresponds to partial words or phrases in the English single sentence or not, and prompting for reference of a translator if the original text of the basic terms in the basic term library corresponds to partial words or phrases in the English single sentence.
21. The system of claim 20, further comprising a term verification module for determining whether a previously translated translation of the particular word or phrase corresponds to a translation of a base term in a term library.
22. The system for translating aircraft maintenance technical manual data according to claim 21, further comprising an untranslated element checking module for checking whether an untranslated element in the corpus corresponds to an untranslated element in the translation, and popping up a warning as a modification request if the untranslated element does not correspond to the untranslated element in the translation.
23. A data management method of an aircraft maintenance technical manual comprises the following steps:
translating the aircraft maintenance technical manual data by using the translation system of the aircraft maintenance technical manual data according to any one of claims 12 to 22 through the translation method of the aircraft maintenance technical manual data according to any one of claims 1 to 11, and integrating the output translated text into a Chinese-English comparison maintenance manual big database;
combining the translation in the large database of the Chinese-English comparison maintenance manual with the original single sentence according to a directory structure in an original aircraft maintenance technical manual of a manufacturer to generate Chinese-English bilingual paragraphs with the original single sentence on top and the corresponding translation on bottom, and displaying the Chinese-English bilingual paragraphs on a terminal;
and inserting the picture in the original aircraft maintenance technical manual of the manufacturer into the Chinese and English paragraphs of the corresponding translation according to the position of the picture in the original aircraft maintenance technical manual of the manufacturer corresponding to the original text.
And providing a search interface for a maintenance worker to retrieve the large database of the Chinese-English comparison maintenance manual through the keywords at the terminal.
24. A method for data management in an aircraft maintenance technical manual according to claim 23, further comprising the steps of:
receiving original text revision data of an aircraft maintenance technical manual sent by an aircraft manufacturer, and revising original text single sentences in a large database of the Chinese-English comparison maintenance manual;
and translating the revised original text single sentence by using the translation system of the aircraft maintenance technical manual data through the translation method of the aircraft maintenance technical manual data to generate a new translation, and replacing the original translation corresponding to the revised original text single sentence in the Chinese-English contrast maintenance manual large database with the new translation.
25. A method for data management in an aircraft maintenance technical manual according to claim 24, further comprising the steps of:
and folding and inserting APS, MT and MSL which are originally inserted into the original aircraft maintenance technical manual of the manufacturer into the Chinese and English bilingual paragraphs in an attachment form by taking keywords of the related tasks of the APS, MT and MSL corresponding to the translation as insertion points.
26. A data management system for an aircraft maintenance technical manual, comprising:
the database generation module is used for integrating the output translated text into a Chinese-English contrast maintenance manual big database after the aircraft maintenance technical manual data are translated by the aircraft maintenance technical manual data translation system through the aircraft maintenance technical manual data translation method;
the display text generation module is used for generating Chinese and English bilingual paragraphs with the original single sentence on the upper part and the corresponding translation on the lower part according to the translated text in the large database of the Chinese-English comparison maintenance manual and the directory structure in the original aircraft maintenance technical manual of the manufacturer in combination with the original single sentence, and displaying the Chinese and English bilingual paragraphs to the terminal;
and the searching interface is used for searching the large database of the Chinese-English comparison maintenance manual by the maintenance personnel through the keywords at the terminal.
27. The aircraft maintenance technical manual data management system of claim 26, wherein: the aircraft maintenance system further comprises a manual revision module, wherein the manual revision module is used for receiving revision data of original texts of the aircraft maintenance technical manual sent by an aircraft manufacturer, after the original text single sentences in the large database of the Chinese-English contrast maintenance manual are revised, the revised original text single sentences are translated by the translation system of the aircraft maintenance technical manual data through the translation method of the aircraft maintenance technical manual data, new translations are generated, and the new translations replace the original translations corresponding to the revised original text single sentences in the large database of the Chinese-English contrast maintenance manual.
28. The aircraft maintenance technical manual data management system of claim 27, wherein: the system also comprises a self-editing content insertion module which is used for inserting APS, MT and MSL which are originally inserted into the original aircraft maintenance technical manual of the manufacturer into the bilingual paragraphs in Chinese and English in a foldable manner in an attachment mode and by taking keywords of the relevant tasks of the APS, MT and MSL corresponding to the translation as insertion points.
29. An aircraft maintenance technical manual review terminal comprising:
the display text and picture receiving module is used for receiving the Chinese and English bilingual paragraphs generated by the data management system of the aircraft maintenance technical manual and the pictures inserted into the Chinese and English paragraphs, and displaying the Chinese and English paragraphs on a display screen of the terminal;
and the retrieval module is connected with a retrieval interface of the data management system of the aircraft maintenance technical manual, provides a retrieval frame in a display screen of the terminal and provides a keyword for a maintenance worker to retrieve the large database of the Chinese-English comparison maintenance manual at the terminal.
30. An aircraft maintenance technical manual data management system according to claim 29, wherein: the terminal display interface generating module is used for displaying the Chinese and English paragraphs, the pictures and the directory structures in a partition manner on a terminal display screen.
31. The aircraft maintenance technical manual data management system of claim 30, wherein: the reference terminal is a mobile terminal, and the mobile terminal is provided with a display interface self-adaptive module for realizing single-screen skip display among a directory structure, Chinese and English paragraphs and pictures.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110148567.3A CN112949324A (en) | 2021-01-28 | 2021-01-28 | Method, system and terminal for translating and managing aircraft maintenance technical manual data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110148567.3A CN112949324A (en) | 2021-01-28 | 2021-01-28 | Method, system and terminal for translating and managing aircraft maintenance technical manual data |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112949324A true CN112949324A (en) | 2021-06-11 |
Family
ID=76242182
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110148567.3A Pending CN112949324A (en) | 2021-01-28 | 2021-01-28 | Method, system and terminal for translating and managing aircraft maintenance technical manual data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112949324A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113590882A (en) * | 2021-08-03 | 2021-11-02 | 武汉品致汽车技术有限公司 | Automobile circuit electronic atlas integrating method |
| CN114970564A (en) * | 2022-06-16 | 2022-08-30 | 北京汉端科技有限公司 | Cloud platform based micro-service civil aviation safety management SOP system |
| CN115829549A (en) * | 2023-02-17 | 2023-03-21 | 中国航空工业集团公司西安飞机设计研究所 | Aircraft maintenance process management method |
| CN117291399A (en) * | 2023-11-24 | 2023-12-26 | 中航材利顿航空科技股份有限公司 | Visual chemical card data processing method and system based on XML |
| CN117743286A (en) * | 2024-02-20 | 2024-03-22 | 商飞软件有限公司 | System and method for generating structured airplane electronic maintenance log |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2004220266A (en) * | 2003-01-14 | 2004-08-05 | Cross Language Inc | Machine translation device and machine translation method |
| CN101539933A (en) * | 2009-01-21 | 2009-09-23 | 北京跳网无限科技发展有限公司 | Intelligent content direct technology |
| CN103823796A (en) * | 2014-02-25 | 2014-05-28 | 武汉传神信息技术有限公司 | System and method for translation |
| CN107943797A (en) * | 2017-11-22 | 2018-04-20 | 语联网（武汉）信息技术有限公司 | A kind of translation on line system of full original text reference |
| CN108519979A (en) * | 2018-02-28 | 2018-09-11 | 成都优译信息技术股份有限公司 | The method and system that translation memory library and MT are combined in a kind of CAT systems |
| CN109783826A (en) * | 2019-01-15 | 2019-05-21 | 四川译讯信息科技有限公司 | A kind of document automatic translating method |
-
2021
- 2021-01-28 CN CN202110148567.3A patent/CN112949324A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2004220266A (en) * | 2003-01-14 | 2004-08-05 | Cross Language Inc | Machine translation device and machine translation method |
| CN101539933A (en) * | 2009-01-21 | 2009-09-23 | 北京跳网无限科技发展有限公司 | Intelligent content direct technology |
| CN103823796A (en) * | 2014-02-25 | 2014-05-28 | 武汉传神信息技术有限公司 | System and method for translation |
| CN107943797A (en) * | 2017-11-22 | 2018-04-20 | 语联网（武汉）信息技术有限公司 | A kind of translation on line system of full original text reference |
| CN108519979A (en) * | 2018-02-28 | 2018-09-11 | 成都优译信息技术股份有限公司 | The method and system that translation memory library and MT are combined in a kind of CAT systems |
| CN109783826A (en) * | 2019-01-15 | 2019-05-21 | 四川译讯信息科技有限公司 | A kind of document automatic translating method |
Non-Patent Citations (1)
| Title |
|---|
| 解倩倩 等: "混合策略的汉维辅助翻译系统的设计与实现", 现代电子技术, vol. 40, no. 20, pages 5 - 8 * |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113590882A (en) * | 2021-08-03 | 2021-11-02 | 武汉品致汽车技术有限公司 | Automobile circuit electronic atlas integrating method |
| CN113590882B (en) * | 2021-08-03 | 2024-01-05 | 武汉品致汽车技术有限公司 | Automobile circuit electronic album integration method |
| CN114970564A (en) * | 2022-06-16 | 2022-08-30 | 北京汉端科技有限公司 | Cloud platform based micro-service civil aviation safety management SOP system |
| CN114970564B (en) * | 2022-06-16 | 2023-02-03 | 北京汉端科技有限公司 | Cloud platform based micro-service civil aviation safety management SOP system |
| CN115829549A (en) * | 2023-02-17 | 2023-03-21 | 中国航空工业集团公司西安飞机设计研究所 | Aircraft maintenance process management method |
| CN115829549B (en) * | 2023-02-17 | 2023-05-05 | 中国航空工业集团公司西安飞机设计研究所 | Aircraft maintenance process management method |
| CN117291399A (en) * | 2023-11-24 | 2023-12-26 | 中航材利顿航空科技股份有限公司 | Visual chemical card data processing method and system based on XML |
| CN117291399B (en) * | 2023-11-24 | 2024-01-26 | 中航材利顿航空科技股份有限公司 | Visual chemical card data processing method and system based on XML |
| CN117743286A (en) * | 2024-02-20 | 2024-03-22 | 商飞软件有限公司 | System and method for generating structured airplane electronic maintenance log |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112949324A (en) | Method, system and terminal for translating and managing aircraft maintenance technical manual data | |
| US6014680A (en) | Method and apparatus for generating structured document | |
| US6654950B1 (en) | Software rehosting system and method | |
| US7721201B2 (en) | Automatic authoring and publishing system | |
| US7478092B2 (en) | Key term extraction | |
| US20070101259A1 (en) | Automatic Authoring and Publishing System | |
| CN102262621A (en) | Device and method for checking translated text | |
| US20090083300A1 (en) | Document processing device and document processing method | |
| CN112667563A (en) | Document management and operation method and system | |
| US8423888B2 (en) | Document conversion and use system | |
| US20080052616A1 (en) | Document Processing Method and Device | |
| CN114385679A (en) | Meter structure inspection method, meter structure inspection device and electronic equipment | |
| US20080005662A1 (en) | Server Device and Name Space Issuing Method | |
| US20070260973A1 (en) | Document Processing Method and Device | |
| US20090287994A1 (en) | Document processing device and document processing method | |
| EP1837776A1 (en) | Document processing device and document processing method | |
| CN111159979A (en) | Method and program for generating pdf document by integrating dynamic data | |
| EP1744271A1 (en) | Document processing device | |
| Ott | Strategies and tools for textual scholarship: the Tübingen System of Text Processing Programs (TUSTEP) | |
| Tursunov | Description of the management system programs of the national corpus of the uzbek language | |
| Lutsky | Automating testing by reverse engineering of software documentation | |
| JP2762934B2 (en) | Test item design support system | |
| Karshiev et al. | SOFTWARE OF THE NATIONAL CORPUS OF THE UZBEK | |
| Iomdin et al. | Structure editor: a powerful environment for tagged corpora | |
| JP3378267B2 (en) | Machine translation equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |