CN112487791A - Multi-language hybrid intelligent translation method - Google Patents
Multi-language hybrid intelligent translation method Download PDFInfo
- Publication number
- CN112487791A CN112487791A CN202011359255.9A CN202011359255A CN112487791A CN 112487791 A CN112487791 A CN 112487791A CN 202011359255 A CN202011359255 A CN 202011359255A CN 112487791 A CN112487791 A CN 112487791A
- Authority
- CN
- China
- Prior art keywords
- original text
- language
- translation
- sub
- literature
- 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.)
- Granted
Links
- 238000013519 translation Methods 0.000 title claims abstract description 59
- 238000000034 method Methods 0.000 title claims abstract description 25
- 230000014616 translation Effects 0.000 claims description 56
- 238000013507 mapping Methods 0.000 claims description 9
- 238000012216 screening Methods 0.000 claims description 4
- 230000010354 integration Effects 0.000 claims description 3
- 238000004806 packaging method and process Methods 0.000 claims description 3
- 238000012545 processing Methods 0.000 claims description 3
- 230000000694 effects Effects 0.000 abstract description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/263—Language identification
-
- 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
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
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 discloses a multilingual hybrid intelligent translation method, which belongs to the technical field of intelligent translation and comprises the following steps: s1, introduction of literature; s2, traversing the literature, and analyzing the language types contained in the literature; s3, respectively translating according to the language type in the literature; s4, displaying the translated text, the method for translating the multilingual documents has high efficiency, high accuracy and good display effect.
Description
Technical Field
The invention belongs to the technical field of intelligent translation, and particularly relates to a multi-language hybrid intelligent translation method.
Background
For the society today, international communication is more and more frequent. The translation amount is larger and larger, and the language types contained in the files are more and more.
At present, the translation tools on the market only translate the documents word by word, and when the documents with multi-language structures are encountered, the translation tools have long translation time, the translation results cannot be well adapted to the original text, and sometimes the translation tools directly display the single words of mixed languages contained in the original text without translating.
Disclosure of Invention
1. Technical problem to be solved by the invention
The object of the present invention is to solve the drawbacks of the prior art.
2. Technical scheme
In order to achieve the purpose, the technical scheme provided by the invention is as follows:
the invention discloses a multilingual hybrid intelligent translation method, which comprises the following steps:
s1, introduction of literature;
s2, traversing the literature, and analyzing the language types contained in the literature;
s3, respectively translating according to the language type in the literature;
and S4, displaying the translated text.
Preferably, step S2 is followed by the following steps:
s2.1, dividing the document into a plurality of sub-documents according to the number of language types of the document, wherein each sub-document only contains one language;
s2.2, analyzing each sub-document respectively, judging whether the sub-document contains proper nouns or not, if so, extracting the proper nouns and sending the proper nouns into a proper frame, otherwise, entering a step S2.3;
s2.3, performing original text mapping on the contents in the sub-literature and binding the contents one by one;
preferably, step S3 is preceded by the following steps:
and S2.4, carrying out grading processing according to the mapping relation between the sub-literature and the original text, if the content and the original text are in a paragraph structure, entering the step S2.5, if the content and the original text are in a single sentence structure, entering the step S2.6, and if the content and the original text are in a single word structure, entering the step S2.7.
Preferably, the method in step S2.5 is to directly call the original text of the paragraph structure to a language translation machine corresponding to the system for translation.
Preferably, the method of step S2.6 is to select the upper and lower sentences of the original text of the sentence structure, and translate and adjust the original text of the sentence structure according to the translated contents of the upper and lower sentences.
Preferably, the method in step S2.7 is to select a single-character-structure original text to perform big data comparison, and perform translation according to the comparison result and the original text environment.
Preferably, the proper nouns entered into the proper boxes in step S2.2 are used for big data screening, if proper translation exists, the proper translation display is directly selected, and if no proper translation exists, machine translation is displayed and annotation is performed.
Preferably, step S4 is preceded by the following steps:
s3.1, respectively projecting the contents of the translated texts into corresponding original text structures according to the mapping relation, and keeping the consistency of the whole sequence;
s3.2, displaying an editable page and providing the editable page for an operator to modify;
and S3.3, judging whether the operator modifies, if so, packaging the modified content and the original text and transmitting the packaged modified content and the original text to a cloud end for integration, and if not, entering the step S4.
3. Advantageous effects
Compared with the prior art, the technical scheme provided by the invention has the following beneficial effects:
(1) according to the multi-language hybrid intelligent translation method, the special translation tools in the system are respectively called for translation according to the language types of the documents, so that the integrity of translation is ensured, and missing of translation is avoided.
(2) According to the multi-language hybrid intelligent translation method, the system calls big data for screening proper nouns and specific characters, the translations conforming to the use habits are displayed, and the preparation rate of the translations is improved.
(3) The invention relates to a multi-language hybrid intelligent translation method, which translates the content of the mixed language and adjusts the semanteme according to the context so as to accord with the use habit.
Drawings
FIG. 1 is a flow chart of a multilingual hybrid intelligent translation method according to the present invention.
Detailed Description
In order to facilitate an understanding of the invention, the invention will now be described more fully hereinafter with reference to the accompanying drawings, in which several embodiments of the invention are shown, but which may be embodied in many different forms and are not limited to the embodiments described herein, but rather are provided for the purpose of providing a more thorough disclosure of the invention.
It will be understood that when an element is referred to as being "secured to" another element, it can be directly on the other element or intervening elements may also be present; when an element is referred to as being "connected" to another element, it can be directly connected to the other element or intervening elements may also be present; the terms "vertical," "horizontal," "left," "right," and the like as used herein are for illustrative purposes only.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs; the terminology used herein in the description of the invention is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention; as used herein, the term "and/or" includes any and all combinations of one or more of the associated listed items.
Example 1
Referring to fig. 1, the multi-language hybrid intelligent translation method of the embodiment includes the following steps:
s1, introduction of literature;
s2, traversing the literature, and analyzing the language types contained in the literature;
s3, respectively translating according to the language type in the literature;
and S4, displaying the translated text.
Step S2 of the present embodiment is followed by the following steps:
s2.1, dividing the document into a plurality of sub-documents according to the number of language types of the document, wherein each sub-document only contains one language;
s2.2, analyzing each sub-document respectively, judging whether the sub-document contains proper nouns or not, if so, extracting the proper nouns and sending the proper nouns into a proper frame, otherwise, entering a step S2.3;
s2.3, performing original text mapping on the contents in the sub-literature and binding the contents one by one;
step S3 of the present embodiment is preceded by the following steps:
and S2.4, carrying out grading processing according to the mapping relation between the sub-literature and the original text, if the content and the original text are in a paragraph structure, entering the step S2.5, if the content and the original text are in a single sentence structure, entering the step S2.6, and if the content and the original text are in a single word structure, entering the step S2.7.
In the method of step S2.5 in this embodiment, the original text of the paragraph structure is directly called to the language translation machine corresponding to the system for translation.
The method of step S2.6 in this embodiment is to select the upper and lower sentences of the original text of the sentence structure, and translate and adjust the original text of the sentence structure according to the translated contents of the upper and lower sentences.
In the method of step S2.7 in this embodiment, a big data comparison is performed on the original text with a single character structure, and translation is performed according to the comparison result and the original text environment.
In step S2.2 of this embodiment, the proper noun sent into the proper frame is used to perform big data filtering, and if there is a proper translation, the proper translation display is directly selected, and if there is no proper translation, the machine translation is displayed and annotated.
Step S4 of the present embodiment further includes the following steps:
s3.1, respectively projecting the contents of the translated texts into corresponding original text structures according to the mapping relation, and keeping the consistency of the whole sequence;
s3.2, displaying an editable page and providing the editable page for an operator to modify;
and S3.3, judging whether the operator modifies, if so, packaging the modified content and the original text and transmitting the packaged modified content and the original text to a cloud end for integration, and if not, entering the step S4.
It should be noted that the above-mentioned "single-word structure" is the basic component of the language, and the corresponding "single-sentence structure" is meant to include a punctuation mark.
The above process is exemplified as follows:
example 1; a document is introduced which contains 3 segments of 5 languages in total, the languages in the 3 segments being different, the first segment being a single language, the second segment containing 3 sentences, wherein the first sentence is one language and the last two sentences are the other language, and the third segment containing two languages, wherein one language is only the occurrence of a single word. During translation, the system traverses the document, divides the document into 5 sub-documents, each sub-document only contains one language, so that the first section is an independent sub-document, the second section is divided into two sub-documents, the third section is divided into two sub-documents, and during translation, the first section is directly translated as a sub-document 1; a second split two sub-documents are marked as a sub-document 2 and a sub-document 3, wherein the sub-document 2 only contains one sentence for transliteration, the sub-document 3 contains two sentences, the former sentence in the two sentences is adjusted according to the translation result of the sub-document 2, and the latter sentence is adjusted according to the former sentence in the sub-document 3; the third segmented sub-document is respectively marked as a sub-document 4 and a sub-document 5, wherein the sub-document 5 only has single characters, when in translation, the sub-document 4 is directly translated, the sub-document 5 is compared with big data, and preferably translated in a similar or common meaning with the content of the sub-document 4.
Example 2, a document is introduced, the whole document is a language, only proper nouns appear in the document, the system directly translates according to the original text during translation, the proper nouns are selected to be sent into a proper frame, big data screening is carried out on the proper nouns sent into the proper frame, if the proper nouns exist, the special nouns are directly displayed, if the proper nouns do not exist, translation is carried out according to the environment of the original text and annotation is carried out, and the annotation result is displayed below the document.
The above-mentioned embodiments only express a certain implementation mode of the present invention, and the description thereof is specific and detailed, but not construed as limiting the scope of the present invention; it should be noted that, for those skilled in the art, without departing from the concept of the present invention, several variations and modifications can be made, which are within the protection scope of the present invention; therefore, the protection scope of the present patent shall be subject to the appended claims.
Claims (8)
1. A multi-language hybrid intelligent translation method is characterized by comprising the following steps:
s1, introduction of literature;
s2, traversing the literature, and analyzing the language types contained in the literature;
s3, respectively translating according to the language type in the literature;
and S4, displaying the translated text.
2. The intelligent translation method with multiple language mixing according to claim 1, wherein said step S2 is followed by the following steps:
s2.1, dividing the document into a plurality of sub-documents according to the number of language types of the document, wherein each sub-document only contains one language;
s2.2, analyzing each sub-document respectively, judging whether the sub-document contains proper nouns or not, if so, extracting the proper nouns and sending the proper nouns into a proper frame, otherwise, entering a step S2.3;
and S2.3, performing original text mapping on the contents in the sub-literature and binding the contents one by one.
3. The intelligent translation method with multiple language mixing according to claim 1, wherein said step S3 is preceded by the following steps:
and S2.4, carrying out grading processing according to the mapping relation between the sub-literature and the original text, if the content and the original text are in a paragraph structure, entering the step S2.5, if the content and the original text are in a single sentence structure, entering the step S2.6, and if the content and the original text are in a single word structure, entering the step S2.7.
4. The intelligent translation system with multi-lingual mixing of claim 3, wherein; and the method of the step S2.5 is to directly call the original text of the paragraph structure to a language translation machine corresponding to the system for translation.
5. The intelligent translation system with multi-lingual mixing of claim 3, wherein; the method of step S2.6 is to select the upper and lower sentences of the original text of the sentence structure, and translate and adjust the original text of the sentence structure according to the transliteration content of the upper and lower sentences.
6. The intelligent translation system with multi-lingual mixing of claim 3, wherein; the method of step S2.7 is to select the original text of the single character structure to perform big data comparison, and perform translation according to the comparison result and the original text environment.
7. The intelligent translation system with multi-lingual mixing of claim 2, wherein; the proper nouns of the special frames in the step S2.2 are subjected to big data screening, if the special translations exist, the special translation display is directly selected, and if the special translations do not exist, the machine translation is displayed and annotation is carried out.
8. The intelligent translation method with multiple language mixing according to claim 1, wherein said step S4 is preceded by the steps of:
s3.1, respectively projecting the contents of the translated texts into corresponding original text structures according to the mapping relation, and keeping the consistency of the whole sequence;
s3.2, displaying an editable page and providing the editable page for an operator to modify;
and S3.3, judging whether the operator modifies, if so, packaging the modified content and the original text and transmitting the packaged modified content and the original text to a cloud end for integration, and if not, entering the step S4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011359255.9A CN112487791B (en) | 2020-11-27 | 2020-11-27 | Multi-language hybrid intelligent translation method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011359255.9A CN112487791B (en) | 2020-11-27 | 2020-11-27 | Multi-language hybrid intelligent translation method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112487791A true CN112487791A (en) | 2021-03-12 |
| CN112487791B CN112487791B (en) | 2024-06-28 |
Family
ID=74936482
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011359255.9A Active CN112487791B (en) | 2020-11-27 | 2020-11-27 | Multi-language hybrid intelligent translation method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112487791B (en) |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20010029455A1 (en) * | 2000-03-31 | 2001-10-11 | Chin Jeffrey J. | Method and apparatus for providing multilingual translation over a network |
| CN103246645A (en) * | 2013-05-27 | 2013-08-14 | 江苏圆坤科技发展有限公司 | Translation method and translation system |
| CN103377188A (en) * | 2012-04-24 | 2013-10-30 | 苏州引角信息科技有限公司 | Translation library construction method and system |
| CN105760542A (en) * | 2016-03-15 | 2016-07-13 | 腾讯科技（深圳）有限公司 | Display control method, terminal and server |
| CN106383818A (en) * | 2015-07-30 | 2017-02-08 | 阿里巴巴集团控股有限公司 | Machine translation method and device |
| CN106528546A (en) * | 2016-10-31 | 2017-03-22 | 用友网络科技股份有限公司 | ERP term machine translation method |
| CN106528535A (en) * | 2016-11-14 | 2017-03-22 | 北京赛思信安技术股份有限公司 | Multi-language identification method based on coding and machine learning |
| CN106844354A (en) * | 2017-01-11 | 2017-06-13 | 中国科学院合肥物质科学研究院 | A kind of webpage takes word Chinese interpretation method and its device |
| CN107656922A (en) * | 2017-09-25 | 2018-02-02 | 广东小天才科技有限公司 | Translation method, translation device, translation terminal and storage medium |
| CN108491398A (en) * | 2018-03-26 | 2018-09-04 | 深圳市元征科技股份有限公司 | A kind of method that newer software text is translated and electronic equipment |
| CN109033096A (en) * | 2018-09-12 | 2018-12-18 | 合肥汇众知识产权管理有限公司 | The classification interpretation method and system of patent document |
| 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 |
-
2020
- 2020-11-27 CN CN202011359255.9A patent/CN112487791B/en active Active
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20010029455A1 (en) * | 2000-03-31 | 2001-10-11 | Chin Jeffrey J. | Method and apparatus for providing multilingual translation over a network |
| CN103377188A (en) * | 2012-04-24 | 2013-10-30 | 苏州引角信息科技有限公司 | Translation library construction method and system |
| CN103246645A (en) * | 2013-05-27 | 2013-08-14 | 江苏圆坤科技发展有限公司 | Translation method and translation system |
| CN106383818A (en) * | 2015-07-30 | 2017-02-08 | 阿里巴巴集团控股有限公司 | Machine translation method and device |
| CN105760542A (en) * | 2016-03-15 | 2016-07-13 | 腾讯科技（深圳）有限公司 | Display control method, terminal and server |
| CN106528546A (en) * | 2016-10-31 | 2017-03-22 | 用友网络科技股份有限公司 | ERP term machine translation method |
| CN106528535A (en) * | 2016-11-14 | 2017-03-22 | 北京赛思信安技术股份有限公司 | Multi-language identification method based on coding and machine learning |
| CN106844354A (en) * | 2017-01-11 | 2017-06-13 | 中国科学院合肥物质科学研究院 | A kind of webpage takes word Chinese interpretation method and its device |
| CN107656922A (en) * | 2017-09-25 | 2018-02-02 | 广东小天才科技有限公司 | Translation method, translation device, translation terminal and storage medium |
| CN108491398A (en) * | 2018-03-26 | 2018-09-04 | 深圳市元征科技股份有限公司 | A kind of method that newer software text is translated and electronic equipment |
| CN109033096A (en) * | 2018-09-12 | 2018-12-18 | 合肥汇众知识产权管理有限公司 | The classification interpretation method and system of patent document |
| 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 (2)
| Title |
|---|
| CHEUNG, PERCY CHI SHUN;FUNG, PASCALE N.: "Translation disambiguation in mixed language queries", MACHINE TRANSLATION, vol. 18, no. 4, pages 251, XP019235877, DOI: 10.1007/s10590-004-7692-5 * |
| 罗季美: "机器翻译中的术语错译分析", 中国科技术语, no. 1, pages 43 - 47 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112487791B (en) | 2024-06-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104933041B (en) | A kind of file beneficial to translation is extracted and restoring method | |
| US5826219A (en) | Machine translation apparatus | |
| US7111011B2 (en) | Document processing apparatus, document processing method, document processing program and recording medium | |
| US7783472B2 (en) | Document translation method and document translation device | |
| EP0447157B1 (en) | Data format conversion | |
| EP0797155A2 (en) | Translating machine | |
| EP4105840A1 (en) | Patent document creating device, method, computer program, computer-readable recording medium, server and system | |
| US9817887B2 (en) | Universal text representation with import/export support for various document formats | |
| JP3038079B2 (en) | Automatic translation device | |
| US20010029442A1 (en) | Translation system, translation processing method and computer readable recording medium | |
| CN111191470A (en) | Document translation method and device | |
| CN112364669A (en) | Method, device, equipment and storage medium for translating translated terms by machine translation | |
| CN106873971B (en) | Multi-language display method and system for flash application | |
| KR20210013991A (en) | Apparatus, method, computer program, computer-readable storage device, server and system for drafting patent document | |
| CN106257442A (en) | Computer-aided translation method | |
| JP2022055305A (en) | Text processing method for generating text summarization, apparatus, device, and storage medium | |
| US10157238B2 (en) | Transformation of marked-up content to a reversible file format for automated browser based pagination | |
| CN112487791A (en) | Multi-language hybrid intelligent translation method | |
| JPS59165179A (en) | Dictionary look-up system | |
| Greulich | Indexing with Excel, Part 4. Conversions 2 | |
| CN112487828A (en) | Error correction improved translation big data integration method | |
| Downes et al. | The amsart, amsproc, and amsbook document classes | |
| JP3995186B2 (en) | Parser | |
| JP2002132764A (en) | Machine translation preprocessor | |
| JP6564910B2 (en) | CONVERSION DEVICE, CONVERSION METHOD, AND PROGRAM |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |