CN106708810A - Machine translation method, device and terminal device - Google Patents
Machine translation method, device and terminal device Download PDFInfo
- Publication number
- CN106708810A CN106708810A CN201611178393.0A CN201611178393A CN106708810A CN 106708810 A CN106708810 A CN 106708810A CN 201611178393 A CN201611178393 A CN 201611178393A CN 106708810 A CN106708810 A CN 106708810A
- Authority
- CN
- China
- Prior art keywords
- vocabulary
- translation result
- preset kind
- translation
- types
- 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
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
Abstract
The invention discloses a machine translation method, a machine translation device and a terminal device, and belongs to the technical field of machine study. The machine translation method includes steps of receiving text information to be translated; extracting preset type word and other type of words in the text information; through the preset template base, acquiring the translation result of the preset type word, and acquiring the translation result corresponding to the other type word through a decoder, wherein the preset template base is used for storing the preset type word and corresponding translation result; according to the translation result of the preset type word and the translation result corresponding to the other type word, confirming the translation result of the text information. The machine translation method, the machine translation device and the terminal device improve the accuracy of the translation result.
Description
Technical field
The present invention relates to machine learning techniques field, more particularly to a kind of machine translation method, device and terminal device.
Background technology
It is real based on browser/server application mode under the network that internet is opened with continuing to develop for science and technology
Online transaction between shopping online, the trade company of existing consumer and it is online pay by mails and various commercial activitys, transaction,
A kind of new commercial operation pattern of the activity such as finance activities.
In the new commercial operation pattern, the client of country variant is had, typically by the mode of machine translation
By a certain language translation into multiple national language, to meet the demand of different clients.Machine translation is to people using computer
Natural language carries out the technology of automatic translation, is that a kind of natural language is converted into another natural language using computer
Process.Specially:After client is input into one section of text message, directly text information is translated by machine translation,
So as to get the corresponding translation result of text information, but, during machine translation, can be because the spy of text message
Different vocabulary, such as place name, name etc. so that the result of translation is inaccurate.
Therefore, using existing machine translation mode so that the accuracy rate of translation result is not high.
The content of the invention
The present invention provides a kind of machine translation method, device and terminal device, to improve the accuracy of translation result.
The embodiment of the present invention provides a kind of machine translation method, including:
Receive text message to be translated;
Extract the preset kind vocabulary and other types vocabulary in the text message;
Obtain the translation result of the preset kind vocabulary by presetting ATL, and by decoder obtain described in its
His corresponding translation result of type vocabulary, the default ATL is used to store preset kind vocabulary and its corresponding translation knot
Really;
Translation result and the corresponding translation result of the other types vocabulary according to the preset kind vocabulary determine institute
State the translation result of text message.
In an embodiment of the present invention, the translation result that the preset kind vocabulary is obtained by presetting ATL,
Including:
The preset kind vocabulary is matched with the preset kind vocabulary in the default ATL;
The translation result of the preset kind vocabulary is obtained according to matching result.
In an embodiment of the present invention, the corresponding translation knot of the other types vocabulary obtained by decoder
Really, including:
The corresponding translation knot of the other types vocabulary is obtained by the corresponding default Machine Translation Model of the decoder
Really, the default Machine Translation Model is following at least one Machine Translation Models:
Reverse transcription syntactic model;
Bracket transcribes syntactic model;
Maximum entropy bracket transcribes syntactic model.
In an embodiment of the present invention, the corresponding translation result of the other types vocabulary obtained by decoder
Afterwards, also include:
Judge whether the attribute of the other types vocabulary is identical with the attribute of the preset kind vocabulary;
If so, the corresponding translation result of the other types vocabulary is stored into the default ATL.
In an embodiment of the present invention, also include:
Pre-build the default ATL.
The embodiment of the present invention also provides a kind of machine translation apparatus, including:
Receiver module, for receiving text message to be translated;
Extraction module, for extracting the preset kind vocabulary in the text message and other types vocabulary;
Acquisition module, the translation result for obtaining the preset kind vocabulary by presetting ATL, and by decoding
Device obtain the corresponding translation result of the other types vocabulary, the default ATL be used for store preset kind vocabulary and its
Corresponding translation result;
Determining module, for the translation result according to the preset kind vocabulary and the other types vocabulary is corresponding turns over
Translate the translation result that result determines the text message.
In an embodiment of the present invention, the acquisition module, specifically for the preset kind vocabulary is default with described
Preset kind vocabulary in ATL is matched;The translation result of the preset kind vocabulary is obtained according to matching result.
In an embodiment of the present invention, the acquisition module, specifically for by the corresponding default machine of the decoder
Translation model obtains the corresponding translation result of the other types vocabulary, and the default Machine Translation Model is following at least one
Machine Translation Model:
Reverse transcription syntactic model;
Bracket transcribes syntactic model;
Maximum entropy bracket transcribes syntactic model.
In an embodiment of the present invention, memory module, the attribute for judging the other types vocabulary is default with described
Whether the attribute of type vocabulary is identical;If so, the corresponding translation result of the other types vocabulary is stored to the default mould
In plate storehouse.
In an embodiment of the present invention, also include:
Module is set up, for pre-building the default ATL.
The embodiment of the present invention also provides a kind of terminal device, including:
Machine translation apparatus described in any of the above-described embodiment.
Embodiment of the present invention machine translation method, device and terminal device, after text message to be translated is received,
First extract the preset kind vocabulary and other types vocabulary in text message;It is logical to preset kind vocabulary and other types vocabulary again
Cross different modes to be translated, the preset kind vocabulary directly can be obtained by default ATL for preset kind vocabulary
Translation result, can be translated by decoder for other kinds of vocabulary, further according to the translation of preset kind vocabulary
Result and the corresponding translation result of other types vocabulary determine the translation result of text message, so as to improve the standard of translation result
True property.
Brief description of the drawings
In order to illustrate more clearly about the embodiment of the present invention or technical scheme of the prior art, below will be to embodiment or existing
The accompanying drawing to be used needed for having technology description does one and simply introduces, it should be apparent that, drawings in the following description are this hairs
Some bright embodiments, for those of ordinary skill in the art, without having to pay creative labor, can be with
Other accompanying drawings are obtained according to these accompanying drawings.
Fig. 1 is a kind of schematic flow sheet of machine translation method provided in an embodiment of the present invention;
Fig. 2 is the schematic flow sheet of another machine translation method provided in an embodiment of the present invention;
Fig. 3 is a kind of structural representation of machine translation apparatus provided in an embodiment of the present invention;
The structural representation of another machine translation apparatus that Fig. 4 is provided for inventive embodiments;
Fig. 5 is a kind of structural representation of terminal device provided in an embodiment of the present invention.
Specific embodiment
To make the purpose, technical scheme and advantage of the embodiment of the present invention clearer, below in conjunction with the embodiment of the present invention
In accompanying drawing, the technical scheme in the embodiment of the present invention is clearly and completely described, it is clear that described embodiment is
A part of embodiment of the present invention, rather than whole embodiments.Based on the embodiment in the present invention, those of ordinary skill in the art
The every other embodiment obtained under the premise of creative work is not made, belongs to the scope of protection of the invention.
Term " first ", " second ", " the 3rd ", " in description and claims of this specification and above-mentioned accompanying drawing
Four " etc. (if present) is for distinguishing similar object, without for describing specific order or precedence.Should manage
Solution so data for using can be exchanged in the appropriate case, so as to embodiments of the invention described herein, for example can be with
Order in addition to those for illustrating herein or describing is implemented.Additionally, term " comprising " and " having " and they appoint
What deforms, it is intended that covering is non-exclusive to be included, for example, contain the process of series of steps or unit, method, system,
Product or equipment are not necessarily limited to those steps clearly listed or unit, but may include not list clearly or for
These processes, method, product or other intrinsic steps of equipment or unit.
It should be noted that these specific embodiments can be combined with each other below, for same or analogous concept
Or process may be repeated no more in certain embodiments.
Fig. 1 is a kind of schematic flow sheet of machine translation method provided in an embodiment of the present invention, and the machine translation method can
Performed with by machine translation apparatus, optionally, the machine translation apparatus can be independently arranged, it is also possible to it is integrated within a processor,
Here, the present invention is not particularly limited.Shown in Figure 1, the embodiment of the present invention is to be illustrated by taking Fig. 1 as an example, but simultaneously
Do not represent present invention is limited only by this.The machine translation method can include:
S101, reception text message to be translated.
Example, text information can be the text message of the preset kind vocabulary such as name comprising place name, or
The text message of unconventional word order.Certainly, the embodiment of the present invention is to be illustrated as example, but does not represent the present invention only
It is confined to this.
S102, the preset kind vocabulary and other types vocabulary extracted in text message.
Wherein, preset kind vocabulary can be name, place name, trade name or building name etc., and certainly, the embodiment of the present invention is only
It is, with preset kind vocabulary as name, to be illustrated as a example by place name, trade name or building name, but do not represent the present invention and only limited to
In this.Other types vocabulary can be common words, for example, you, I, she etc. common major terms, or, like, dislike etc.
Common conventional verb etc., naturally it is also possible to form word etc. for beautiful, bright-coloured grade is commonly conventional, here, the present invention do not do into
The limitation of one step ground.
S103, by preset ATL obtain preset kind vocabulary translation result, and by decoder obtain other
The corresponding translation result of type vocabulary.
Wherein, presetting ATL is used to store preset kind vocabulary and its corresponding translation result.
In embodiments of the present invention, the vocabulary of the preset kind for extracting, directly can be obtained by default ATL
The translation result of preset kind vocabulary is taken, so as to avoid for the vocabulary of the preset kind causing translation knot by decoder translation
It is really inaccurate, for the other types vocabulary commonly used, directly corresponding can be turned over by the other types vocabulary of decoder acquisition
Result is translated, so as to improve the accuracy of storage preset kind vocabulary translation.
S104, the translation result according to preset kind vocabulary and the corresponding translation result of other types vocabulary determine text envelope
The translation result of breath.
After the translation result of preset kind vocabulary and the corresponding translation result of other types vocabulary is got respectively, just
The translation result of preset kind vocabulary and the corresponding translation result of other types vocabulary can be processed, so that according to default
The translation result and the corresponding translation result of other types vocabulary of type vocabulary determine the translation result of text message, so as to improve
The accuracy of the translation result of text message.
Machine translation method provided in an embodiment of the present invention, after text message to be translated is received, first extracts text
Preset kind vocabulary and other types vocabulary in this information;Again to preset kind vocabulary and other types vocabulary by different
Mode is translated, for the translation knot that preset kind vocabulary can directly obtain the preset kind vocabulary by presetting ATL
Really, can be translated by decoder for other kinds of vocabulary, translation result further according to preset kind vocabulary and its
His the corresponding translation result of type vocabulary determines the translation result of text message, so as to improve the accuracy of translation result.
It is further, shown in Figure 2 on the basis of the corresponding embodiments of Fig. 1 based on the corresponding embodiments of Fig. 1,
Fig. 2 is the schematic flow sheet of another machine translation method provided in an embodiment of the present invention, certainly, the embodiment of the present invention be with
Illustrated as a example by Fig. 2, but do not represented present invention is limited only by this.The machine translation method can include:
S201, pre-build default ATL.
Wherein, presetting ATL is used to store preset kind vocabulary and its corresponding translation result.
Example, the preset kind vocabulary such as some names, place name, trade name or building name can be stored in default ATL
And its corresponding translation result.For example, the preset kind vocabulary that is stored with default ATL:Name A, name B, name C, place name
D, place name E, place name F, building name G and building name H, additionally, also stored for the corresponding translation result of preset kind vocabulary:Name
The corresponding translation results of A are a, the corresponding translation results of name B are b, the corresponding translation results of name C are that c, place name D are corresponding
Translation result is d, the corresponding translation results of place name E are e, the corresponding translation results of place name F are that the corresponding translation of f, building name G is tied
Fruit is g and the corresponding translation results of building name H are h.Certainly, the embodiment of the present invention is to be said by taking the default ATL as an example
It is bright, but do not represent present invention is limited only by this.
S202, reception text message to be translated.
Example, in embodiments of the present invention, with comprising name, the text envelope of the preset kind vocabulary of place name and building name
Illustrated as a example by breath, text information can be:My name is B, and my local is D, and my office is in H mansions.When
So, the embodiment of the present invention is to be illustrated by taking text information as an example, but is not represented present invention is limited only by this.
S203, the preset kind vocabulary and other types vocabulary extracted in text message.
Getting text message:My name is B, and my local is D, my office in H mansions, afterwards, so that it may
To extract the preset kind vocabulary in text information and other types vocabulary.Example, in embodiments of the present invention, extract
Preset kind vocabulary be:B, D and H, other types vocabulary is:I, name, be, local, office, in, mansion.
S204, the translation result that preset kind vocabulary is obtained by presetting ATL.
Optionally, in embodiments of the present invention, S204 obtains the translation result of preset kind vocabulary by presetting ATL,
Can be accomplished by the following way, it is specific as follows:
Preset kind vocabulary is matched with the preset kind vocabulary in default ATL, and is obtained according to matching result
The translation result of preset kind vocabulary.
Example, after preset kind vocabulary B, D and H is got, by preset kind vocabulary B, D and the H and default mould
The preset kind vocabulary prestored in plate storehouse is matched, if being previously stored with the corresponding translation of B, D and H in default ATL
As a result, then the match is successful, and B, D and H corresponding translation result b, d and h as default class are previously stored with default ATL
The corresponding translation results of type vocabulary B, D and H, specially:The corresponding translation results of B are b, and the corresponding translation results of D are d, H correspondences
Translation result be h, so as to avoid by vocabulary B, D and H of the preset kind by decoder translate and cause translation result not
Accurately, so as to improve the accuracy that storage preset kind vocabulary B, D and H are translated.
S205, the corresponding translation result of other types vocabulary obtained by decoder.
Optionally, in embodiments of the present invention, other can be obtained by the corresponding default Machine Translation Model of decoder
The corresponding translation result of type vocabulary, it is following at least one Machine Translation Models to preset Machine Translation Model:Reverse transcription language
Method model;Bracket transcribes syntactic model;Maximum entropy bracket transcribes syntactic model.
Example, get other types vocabulary I, name, be, local, office, and mansion after, can be with
Directly by the other types vocabulary I, name, be, local, office, and mansion pass through the corresponding default machine of decoder
Translation model obtains the corresponding translation result of other types vocabulary.For example, my corresponding translation result is my, name is corresponding
Translation result is name, is corresponding is, and the corresponding translation result in local is hometown, and the corresponding translation result of office is
Office, is in corresponding translation result, and the corresponding translation result in mansion is building.Certainly, the embodiment of the present invention
To be illustrated so that translation result is as English as an example, it is of course also possible to be other kinds of language, here, the present invention do not do into
The limitation of one step ground.
It should be noted that in embodiments of the present invention, sequencing is had no before S204 and S205, can first carry out
S204, then perform S205, it is of course also possible to limit S205, then performs S204, the embodiment of the present invention be to first carry out S204,
Perform again and illustrate as a example by S205, but do not represent present invention is limited only by this.
S206, the translation result according to preset kind vocabulary and the corresponding translation result of other types vocabulary determine text envelope
The translation result of breath.
The translation result of the preset kind vocabulary and the corresponding translation result determination of other types vocabulary are being got respectively
After the translation result of text message, it is possible to translation result and the corresponding translation of other types vocabulary to preset kind vocabulary
Result is processed, so as to the corresponding translation result of translation result and other types vocabulary according to preset kind vocabulary determines text
The translation result of this information.
Example, getting the corresponding translation result of preset kind vocabulary B, D and H, and other types vocabulary I, name
Word, be, local, office, and the corresponding translation result in mansion after, it is possible to obtain text information:My name is
B, my local is D, and in the translation result of H mansions, the corresponding translation result of text information is for my office:my name
Is b, my hometown is d, my office in the building of h, so as to improve the accurate of translation result
Property.
Further, S206 is true according to the translation result and the corresponding translation result of other types vocabulary of preset kind vocabulary
Determine after the translation result of text message, can also include:
Whether the attribute of S207, the attribute for judging other types vocabulary and preset kind vocabulary is identical;If so, by other classes
The corresponding translation result of type vocabulary is stored into default ATL.
Example, by judge the attribute of other types vocabulary and preset kind vocabulary in default ATL attribute whether
It is identical, if identical, for example, the attribute of other types vocabulary also be place name, name or building name, then by the other types vocabulary
Corresponding translation result is stored into default ATL, so as to next time can directly according to direct access in default ATL other
The corresponding translation result of type vocabulary, such that it is able to improve the accuracy of translation result.
In actual application, after text message to be translated is received, the default class in text message is extracted
Type vocabulary and other types vocabulary, for preset kind vocabulary, directly can obtain preset kind vocabulary by default ATL
Translation result, so as to avoid by the vocabulary of the preset kind by decoder translate and cause translation result it is inaccurate, for
Other types vocabulary, can obtain the corresponding translation knot of other types vocabulary by the corresponding default Machine Translation Model of decoder
Really, afterwards, translation result and the corresponding translation result of other types vocabulary to preset kind vocabulary is processed, so that basis
The translation result and the corresponding translation result of other types vocabulary of preset kind vocabulary determine the translation result of text message, improve
The accuracy of translation result.
Fig. 3 is a kind of structural representation of machine translation apparatus 30 provided in an embodiment of the present invention, shown in Figure 3,
Certainly, the embodiment of the present invention is to be illustrated by taking Fig. 3 as an example, but is not represented present invention is limited only by this.The machine translation
Device 30 includes:
Receiver module 301, for receiving text message to be translated.
Extraction module 302, for extracting the preset kind vocabulary in text message and other types vocabulary.
Acquisition module 303, the translation result for obtaining preset kind vocabulary by presetting ATL, and by decoder
The corresponding translation result of other types vocabulary of acquisition, default ATL is used to store preset kind vocabulary and its corresponding translation
As a result.
Determining module 304, for the corresponding translation knot of the translation result according to preset kind vocabulary and other types vocabulary
Fruit determines the translation result of text message.
Optionally, acquisition module 303, specifically for by the preset kind vocabulary in preset kind vocabulary and default ATL
Matched;The translation result of preset kind vocabulary is obtained according to matching result.
Optionally, acquisition module 303, specifically for obtaining other classes by the corresponding default Machine Translation Model of decoder
The corresponding translation result of type vocabulary, it is following at least one Machine Translation Models to preset Machine Translation Model:
Reverse transcription syntactic model;
Bracket transcribes syntactic model;
Maximum entropy bracket transcribes syntactic model.
Optionally, it is shown in Figure 4, the structure of another machine translation apparatus 30 that Fig. 4 is provided for inventive embodiments
Schematic diagram, the machine translation apparatus 30 also include:
Whether memory module 305, the attribute for judging other types vocabulary is identical with the attribute of preset kind vocabulary;If
It is to store into default ATL the corresponding translation result of other types vocabulary.
Optionally, the machine translation apparatus 30 also include:
Module 306 is set up, for pre-building default ATL.
Machine translation apparatus 30 shown in the embodiment of the present invention, can perform the technical side shown in above method embodiment
Case, its realization principle and beneficial effect are similar to, and are no longer repeated herein.
Fig. 5 is a kind of structural representation of terminal device 50 provided in an embodiment of the present invention, shown in Figure 5, certainly,
The embodiment of the present invention is to be illustrated by taking Fig. 5 as an example, but is not represented present invention is limited only by this.The terminal device 50 is wrapped
Include:
Machine translation apparatus 30 shown in above-described embodiment.
Terminal device 50 shown in the embodiment of the present invention, can perform the technical scheme shown in above method embodiment, its
Realization principle and beneficial effect are similar, are no longer repeated herein.
One of ordinary skill in the art will appreciate that:Realizing all or part of step of above-mentioned each method embodiment can lead to
The related hardware of programmed instruction is crossed to complete.Foregoing program can be stored in a computer read/write memory medium.The journey
Sequence upon execution, performs the step of including above-mentioned each method embodiment;And foregoing storage medium includes:ROM, RAM, magnetic disc or
Person's CD etc. is various can be with the medium of store program codes.
Finally it should be noted that:Various embodiments above is merely illustrative of the technical solution of the present invention, rather than its limitations;To the greatest extent
Pipe has been described in detail with reference to foregoing embodiments to the present invention, it will be understood by those within the art that:Its according to
The technical scheme described in foregoing embodiments can so be modified, or which part or all technical characteristic are entered
Row equivalent;And these modifications or replacement, the essence of appropriate technical solution is departed from various embodiments of the present invention technology
The scope of scheme.
Claims (11)
1. a kind of machine translation method, it is characterised in that including:
Receive text message to be translated;
Extract the preset kind vocabulary and other types vocabulary in the text message;
The translation result of the preset kind vocabulary is obtained by presetting ATL, and by other classes described in decoder acquisition
The corresponding translation result of type vocabulary, the default ATL is used to store preset kind vocabulary and its corresponding translation result;
Translation result and the corresponding translation result of the other types vocabulary according to the preset kind vocabulary determine the text
The translation result of this information.
2. method according to claim 1, it is characterised in that described that the preset kind word is obtained by default ATL
The translation result of remittance, including:
The preset kind vocabulary is matched with the preset kind vocabulary in the default ATL;
The translation result of the preset kind vocabulary is obtained according to matching result.
3. method according to claim 2, it is characterised in that the other types vocabulary obtained by decoder
Corresponding translation result, including:
The corresponding translation result of the other types vocabulary, institute are obtained by the corresponding default Machine Translation Model of the decoder
Default Machine Translation Model is stated for following at least one Machine Translation Models:
Reverse transcription syntactic model;
Bracket transcribes syntactic model;
Maximum entropy bracket transcribes syntactic model.
4. method according to claim 3, it is characterised in that the other types vocabulary obtained by decoder
After corresponding translation result, also include:
Judge whether the attribute of the other types vocabulary is identical with the attribute of the preset kind vocabulary;
If so, the corresponding translation result of the other types vocabulary is stored into the default ATL.
5. the method according to claim any one of 2-4, it is characterised in that also include:
Pre-build the default ATL.
6. a kind of machine translation apparatus, it is characterised in that including:
Receiver module, for receiving text message to be translated;
Extraction module, for extracting the preset kind vocabulary in the text message and other types vocabulary;
Acquisition module, for obtaining the translation result of the preset kind vocabulary by presetting ATL, and is obtained by decoder
The corresponding translation result of the other types vocabulary for taking, the default ATL is used to store preset kind vocabulary and its correspondence
Translation result;
Determining module, for the corresponding translation knot of the translation result according to the preset kind vocabulary and the other types vocabulary
Fruit determines the translation result of the text message.
7. device according to claim 6, it is characterised in that
The acquisition module, specifically for the preset kind vocabulary is entered with the preset kind vocabulary in the default ATL
Row matching;The translation result of the preset kind vocabulary is obtained according to matching result.
8. device according to claim 7, it is characterised in that
The acquisition module, specifically for obtaining the other types by the corresponding default Machine Translation Model of the decoder
The corresponding translation result of vocabulary, the default Machine Translation Model is following at least one Machine Translation Models:
Reverse transcription syntactic model;
Bracket transcribes syntactic model;
Maximum entropy bracket transcribes syntactic model.
9. device according to claim 8, it is characterised in that also include:
Whether memory module, the attribute for judging the other types vocabulary is identical with the attribute of the preset kind vocabulary;
If so, the corresponding translation result of the other types vocabulary is stored into the default ATL.
10. the device according to claim any one of 7-9, it is characterised in that also include:
Module is set up, for pre-building the default ATL.
A kind of 11. terminal devices, it is characterised in that including:
Machine translation apparatus described in the claims any one of 6-10.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201611178393.0A CN106708810A (en) | 2016-12-19 | 2016-12-19 | Machine translation method, device and terminal device |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201611178393.0A CN106708810A (en) | 2016-12-19 | 2016-12-19 | Machine translation method, device and terminal device |
Publications (1)
Publication Number | Publication Date |
---|---|
CN106708810A true CN106708810A (en) | 2017-05-24 |
Family
ID=58938312
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201611178393.0A Pending CN106708810A (en) | 2016-12-19 | 2016-12-19 | Machine translation method, device and terminal device |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106708810A (en) |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103631772A (en) * | 2012-08-29 | 2014-03-12 | 阿里巴巴集团控股有限公司 | Machine translation method and device |
CN104699675A (en) * | 2015-03-18 | 2015-06-10 | 北京交通大学 | Message translating method and device |
-
2016
- 2016-12-19 CN CN201611178393.0A patent/CN106708810A/en active Pending
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103631772A (en) * | 2012-08-29 | 2014-03-12 | 阿里巴巴集团控股有限公司 | Machine translation method and device |
CN104699675A (en) * | 2015-03-18 | 2015-06-10 | 北京交通大学 | Message translating method and device |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108399169A (en) | Dialog process methods, devices and systems based on question answering system and mobile device | |
CN110929094B (en) | Video title processing method and device | |
KR20180025121A (en) | Method and apparatus for inputting information | |
CN107766371A (en) | A kind of text message sorting technique and its device | |
CN110262273A (en) | A kind of home equipment control method, device, storage medium and smart home system | |
CN105096121A (en) | Voiceprint authentication method and device | |
CN107704453A (en) | A kind of word semantic analysis, word semantic analysis terminal and storage medium | |
CN108447471A (en) | Audio recognition method and speech recognition equipment | |
CN109545183A (en) | Text handling method, device, electronic equipment and storage medium | |
CN107862005A (en) | User view recognition methods and device | |
CN106802885A (en) | A kind of meeting summary automatic record method, device and electronic equipment | |
CN108984650A (en) | Computer readable recording medium and computer equipment | |
CN107357787A (en) | Semantic interaction method, apparatus and electronic equipment | |
CN107943914A (en) | Voice information processing method and device | |
CN104866308A (en) | Scenario image generation method and apparatus | |
CN106709804A (en) | Interactive wealth planning consulting robot system | |
CN110223678A (en) | Audio recognition method and system | |
CN111142834B (en) | Service processing method and system | |
CN107341157B (en) | Customer service conversation clustering method and device | |
CN113918698A (en) | Customer service processing system and device | |
CN109698798A (en) | A kind of recognition methods of application, device, server and storage medium | |
CN107888989A (en) | A kind of interactive system and method live based on internet | |
CN104915458A (en) | Automatic association method and system during application search by user, and mobile terminal | |
CN106933798A (en) | The method and device of information analysis | |
CN112989008A (en) | Multi-turn dialog rewriting method and device and electronic equipment |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170524 |
|
RJ01 | Rejection of invention patent application after publication |