CN110362837A - A kind of artificial intelligence translation integrated system - Google Patents
A kind of artificial intelligence translation integrated system Download PDFInfo
- Publication number
- CN110362837A CN110362837A CN201910668494.3A CN201910668494A CN110362837A CN 110362837 A CN110362837 A CN 110362837A CN 201910668494 A CN201910668494 A CN 201910668494A CN 110362837 A CN110362837 A CN 110362837A
- Authority
- CN
- China
- Prior art keywords
- data
- module
- translated
- translation
- neural network
- 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
- 238000013519 translation Methods 0.000 title claims abstract description 60
- 238000013473 artificial intelligence Methods 0.000 title claims abstract description 16
- 238000000605 extraction Methods 0.000 claims abstract description 7
- 238000003062 neural network model Methods 0.000 claims abstract description 6
- 238000006243 chemical reaction Methods 0.000 claims abstract description 5
- 230000011218 segmentation Effects 0.000 claims abstract description 4
- 238000013528 artificial neural network Methods 0.000 claims description 23
- 230000006870 function Effects 0.000 claims description 7
- 238000000034 method Methods 0.000 claims description 4
- 238000012549 training Methods 0.000 claims description 3
- 230000007306 turnover Effects 0.000 claims description 3
- 210000005036 nerve Anatomy 0.000 claims description 2
- 238000012545 processing Methods 0.000 abstract description 3
- 238000004891 communication Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 2
- 230000008859 change Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computational Linguistics (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- Molecular Biology (AREA)
- Biophysics (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Biomedical Technology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Machine Translation (AREA)
Abstract
The invention discloses a kind of artificial intelligence to translate integrated system, comprising: acquisition module, data format conversion module, data characteristics extraction module, data categorization module, data segmentation orchestration module, data translation module and human translation module data to be translated.The present invention is based on neural network models to realize identification data to be translated, format analysis processing and automatic translation, and interpretative system is flexible, configures different translation models for different clause, can satisfy the different translation demand of user, and the accuracy translated is higher.
Description
Technical field
The present invention relates to translating equipment fields, and in particular to a kind of artificial intelligence translation integrated system.
Background technique
With the development of science and technology and economic globalization, either in daily life or sphere of learning is linked up,
International exchange communication has been the experience that almost everyone had, but across communication scene is to the multilingual of participant
Level requirement is higher, and exchange participant would generally with the help of a dictionary or translation software even interpreter carries out across communication.In
It is under such requirement background, portable machine interpreting equipment comes into being in recent years.
But existing traditional type portable machine interpreting equipment can't accomplish the translation of entirely accurate, therefore, need
User is wanted to be modified for the text that translation software is translated, the clause especially used in the text that translation software is translated
With required for user when clause difference, the change carried out needed for user is with regard to more.Meanwhile the mode of whole sentence translation, it is also possible to
User can be lost and want the content expressed by object language, the accuracy of translation is not also high, therefore, translation in the prior art
System, not only interpretative system is inflexible, and it is impossible to meet the translation demands of user, and the accuracy translated is not also high.
Summary of the invention
To solve the above problems, the present invention provides a kind of artificial intelligence to translate integrated system, it is based on neural network model
Identification data to be translated, format analysis processing and automatic translation are realized, interpretative system is flexible, can satisfy that user is different to be turned over
Demand is translated, and the accuracy translated is higher.
To achieve the above object, the technical scheme adopted by the invention is as follows:
A kind of artificial intelligence translation integrated system, comprising:
Acquisition module data to be translated, for carrying out acquisition data to be translated；
Data format conversion module, for completing standardization data to be translated；
Data characteristics extraction module, using MapReduce to the extraction data to be translated for carrying out characteristic；
Data categorization module, for realizing the classification of data by classifier based on characteristic；
Data divide orchestration module, will be to be translated for the corresponding neural network parted pattern of call by result according to data classification
Data are divided into the several modules being made of word, phrase, and complete these words, phrase number based on neural network formatting model
According to the layout of format；
Data translation module, for according to the data to be translated and target translation language information calling pair for completing data segmentation layout
The neural network translation model answered exports corresponding translation result；
Human translation module starts when the translation result of data translation module is blank, and completing data format, treated
Data to be translated to be sent to corresponding human translation terminal through server, human translation terminal receives data and uploads corresponding turn over
Cypher text is sent corresponding account by translation sheet to server, server, while starting neural network model building module,
New neural network translation model is constructed based on data to be translated and corresponding cypher text.
Further, the acquisition module data to be translated is based on text data input module, audio data input module
It is inputted with image data input module.
Further, the classifier is to obtain after BP neural network carries out off-line training using Adaboost method.
Further, the neural network parted pattern, neural network formatting model, neural network translation model are stored in
In server, it is equipped with independent logical number.
Further, the data format conversion module be used for by picture source it is data to be translated, data to be translated turn of audio
It is data to be translated to be changed to text source.
Further, further includes:
Sound-recording function opens and closes module, for realizing the opening and closing of sound-recording function.
Further, further includes:
Target translates languages selecting module, for realizing the selection of target translation languages.
It further, further include cypher text outgoing route selecting module, for realizing the choosing of cypher text outgoing route
It selects.
The invention has the following advantages:
1) identification data to be translated, format analysis processing and automatic translation, interpretative system spirit are realized based on neural network model
It is living, configure different translation models for different clause, can satisfy the different translation demand of user, and the accuracy translated compared with
It is high.
2) it carries human translation module and neural network translation model constructs module, it is real while reducing translation blind area
The self promotion of system interpretative function is showed.
Detailed description of the invention
Fig. 1 is the system block diagram that a kind of artificial intelligence of the embodiment of the present invention translates integrated system.
Specific embodiment
The present invention is described in detail combined with specific embodiments below.Following embodiment will be helpful to the technology of this field
Personnel further understand the present invention, but the invention is not limited in any way.It should be pointed out that the ordinary skill of this field
For personnel, without departing from the inventive concept of the premise, various modifications and improvements can be made.These belong to the present invention
Protection scope.
As shown in Figure 1, the embodiment of the invention provides a kind of artificial intelligence to translate integrated system, including pass through internet phase
Server even and cell phone application are equipped in the cell phone application:
Acquisition module data to be translated, for carrying out acquisition data to be translated；
Target translates languages selecting module, for realizing the selection of target translation languages；
Data format conversion module, it is picture source is data to be translated, audio is to be translated for completing standardization data to be translated
It is data to be translated that data are converted to text source；
Data characteristics extraction module, using MapReduce to the extraction data to be translated for carrying out characteristic；
Data categorization module, for realizing the classification of data by classifier based on characteristic；The classifier is BP nerve
Network obtains after carrying out off-line training using Adaboost method；It realizes the identification of languages data to be translated first, based on knowledge
Other result carries out the first subseries data to be translated, then in the identification for carrying out sentence format data to be translated, is based on format
Recognition result carries out the second subseries data to be translated；
Data divide orchestration module, for the result (result including the first subseries and the second subseries) according to data classification
It calls corresponding neural network parted pattern by the several modules data to be translated for being divided into and being made of word, phrase, and is based on
Neural network formatting model completes the layout of these words, phrase data format；
Data translation module, for according to the data to be translated and target translation language information calling pair for completing data segmentation layout
The neural network translation model answered exports corresponding translation result；
Sound-recording function opens and closes module, for realizing the opening and closing of sound-recording function；
Cypher text outgoing route selecting module, for realizing the selection of cypher text outgoing route；
Human translation module starts when the translation result of data translation module is blank, and completing data format, treated
Data to be translated to be sent to corresponding human translation terminal through server, human translation terminal receives data and uploads corresponding turn over
Cypher text is sent corresponding account by translation sheet to server, server, while starting neural network model building module,
New neural network translation model is constructed based on data to be translated and corresponding cypher text.
In the present embodiment, the acquisition module data to be translated is based on text data input module, audio data inputs mould
Block and the input of image data input module.
In the present embodiment, the neural network parted pattern, neural network formatting model, the storage of neural network translation model
In server, it is equipped with independent logical number.
Specific embodiments of the present invention are described above.It is to be appreciated that the invention is not limited to above-mentioned
Particular implementation, those skilled in the art can make a variety of changes or modify within the scope of the claims, this not shadow
Ring substantive content of the invention.In the absence of conflict, the feature in embodiments herein and embodiment can any phase
Mutually combination.
Claims (8)
1. a kind of artificial intelligence translates integrated system, it is characterised in that: include:
Acquisition module data to be translated, for carrying out acquisition data to be translated；
Data format conversion module, for completing standardization data to be translated；
Data characteristics extraction module, using MapReduce to the extraction data to be translated for carrying out characteristic；
Data categorization module, for realizing the classification of data by classifier based on characteristic；
Data divide orchestration module, will be to be translated for the corresponding neural network parted pattern of call by result according to data classification
Data are divided into the several modules being made of word, phrase, and complete these words, phrase number based on neural network formatting model
According to the layout of format；
Data translation module, for according to the data to be translated and target translation language information calling pair for completing data segmentation layout
The neural network translation model answered exports corresponding translation result；
Human translation module starts when the translation result of data translation module is blank, and completing data format, treated
Data to be translated to be sent to corresponding human translation terminal through server, human translation terminal receives data and uploads corresponding turn over
Cypher text is sent corresponding account by translation sheet to server, server, while starting neural network model building module,
New neural network translation model is constructed based on data to be translated and corresponding cypher text.
2. a kind of artificial intelligence as described in claim 1 translates integrated system, it is characterised in that: the acquisition data to be translated
Module is based on text data input module, audio data input module and the input of image data input module.
3. a kind of artificial intelligence as described in claim 1 translates integrated system, it is characterised in that: the classifier is BP nerve
Network obtains after carrying out off-line training using Adaboost method.
4. a kind of artificial intelligence as described in claim 1 translates integrated system, it is characterised in that: the neural network divides mould
Type, neural network formatting model, neural network translation model are stored in server, are equipped with independent logical number.
5. a kind of artificial intelligence as described in claim 1 translates integrated system, it is characterised in that: the Data Format Transform mould
Block is used for the data to be translated, audio by picture source, and data to be translated to be converted to text source data to be translated.
6. a kind of artificial intelligence as described in claim 1 translates integrated system, it is characterised in that: further include:
Sound-recording function opens and closes module, for realizing the opening and closing of sound-recording function.
7. a kind of artificial intelligence as described in claim 1 translates integrated system, it is characterised in that: further include:
Target translates languages selecting module, for realizing the selection of target translation languages.
8. a kind of artificial intelligence as described in claim 1 translates integrated system, it is characterised in that: further include: cypher text is defeated
Outbound path selecting module, for realizing the selection of cypher text outgoing route.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910668494.3A CN110362837A (en) | 2019-07-23 | 2019-07-23 | A kind of artificial intelligence translation integrated system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910668494.3A CN110362837A (en) | 2019-07-23 | 2019-07-23 | A kind of artificial intelligence translation integrated system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110362837A true CN110362837A (en) | 2019-10-22 |
Family
ID=68219877
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910668494.3A Pending CN110362837A (en) | 2019-07-23 | 2019-07-23 | A kind of artificial intelligence translation integrated system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110362837A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112905189A (en) * | 2021-02-24 | 2021-06-04 | 嘉楠明芯(北京)科技有限公司 | Model translation method, device and computer readable storage medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2018010455A1 (en) * | 2016-07-12 | 2018-01-18 | 华为技术有限公司 | Neural network-based translation method and apparatus |
| CN108563644A (en) * | 2018-03-29 | 2018-09-21 | 河南工学院 | A kind of English Translation electronic system |
| CN108628836A (en) * | 2017-03-22 | 2018-10-09 | 湖南本来文化发展有限公司 | The robot of voiced translation is carried out using artificial intelligence BP neural network algorithm |
| CN109299481A (en) * | 2018-11-15 | 2019-02-01 | 语联网（武汉）信息技术有限公司 | MT engine recommended method, device and electronic equipment |
-
2019
- 2019-07-23 CN CN201910668494.3A patent/CN110362837A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2018010455A1 (en) * | 2016-07-12 | 2018-01-18 | 华为技术有限公司 | Neural network-based translation method and apparatus |
| CN108628836A (en) * | 2017-03-22 | 2018-10-09 | 湖南本来文化发展有限公司 | The robot of voiced translation is carried out using artificial intelligence BP neural network algorithm |
| CN108563644A (en) * | 2018-03-29 | 2018-09-21 | 河南工学院 | A kind of English Translation electronic system |
| CN109299481A (en) * | 2018-11-15 | 2019-02-01 | 语联网（武汉）信息技术有限公司 | MT engine recommended method, device and electronic equipment |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112905189A (en) * | 2021-02-24 | 2021-06-04 | 嘉楠明芯(北京)科技有限公司 | Model translation method, device and computer readable storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| KR101925440B1 (en) | Method for providing vr based live video chat service using conversational ai | |
| JP2021021955A (en) | Method and device for generating and registering voiceprint | |
| CN109101545A (en) | Natural language processing method, apparatus, equipment and medium based on human-computer interaction | |
| CN109740447A (en) | Communication means, equipment and readable storage medium storing program for executing based on artificial intelligence | |
| CN108960126A (en) | Method, apparatus, equipment and the system of sign language interpreter | |
| CN109005190B (en) | Method for realizing full duplex voice conversation and page control on webpage | |
| CN112632244A (en) | Man-machine conversation optimization method and device, computer equipment and storage medium | |
| CN107734160A (en) | A kind of language mutual aid method based on smart mobile phone | |
| CN108563644A (en) | A kind of English Translation electronic system | |
| CN110266900A (en) | Recognition methods, device and the customer service system that client is intended to | |
| CN109448698A (en) | Simultaneous interpretation method, apparatus, computer equipment and storage medium | |
| CN110633475A (en) | Natural language understanding method, device and system based on computer scene and storage medium | |
| CN110114765A (en) | Context by sharing language executes the electronic equipment and its operating method of translation | |
| Voronov et al. | Development of a software package designed to support distance education for disabled people | |
| WO2018169276A1 (en) | Method for processing language information and electronic device therefor | |
| CN114862286A (en) | Hotel guest room service judgment method and device, electronic equipment and storage medium | |
| CN112447168A (en) | Voice recognition system and method, sound box, display device and interaction platform | |
| CN110362837A (en) | A kind of artificial intelligence translation integrated system | |
| CN207718803U (en) | Multiple source speech differentiation identifying system | |
| CN116189663A (en) | Training method and device of prosody prediction model, and man-machine interaction method and device | |
| CN113792607B (en) | Neural network sign language classification and identification method based on Transformer | |
| CN115273828A (en) | Training method and device of voice intention recognition model and electronic equipment | |
| CN115171673A (en) | Role portrait based communication auxiliary method and device and storage medium | |
| CN110362838A (en) | A kind of translating equipment based on artificial intelligence | |
| CN113434663A (en) | Conference summary generation method based on edge calculation and related 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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20191022 |