CN107391500A - Text interpretation method, device and equipment - Google Patents
Text interpretation method, device and equipment Download PDFInfo
- Publication number
- CN107391500A CN107391500A CN201710718020.6A CN201710718020A CN107391500A CN 107391500 A CN107391500 A CN 107391500A CN 201710718020 A CN201710718020 A CN 201710718020A CN 107391500 A CN107391500 A CN 107391500A
- Authority
- CN
- China
- Prior art keywords
- text
- sentence pattern
- target
- pattern template
- language text
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/237—Lexical tools
- G06F40/242—Dictionaries
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
This specification embodiment provides a kind of text interpretation method, device and equipment, the translation dictionary of different language type is not only provided in the present embodiment, there is different scenes dictionary also directed to the different business scene configuration of same language form, because scene dictionary includes translation result that original language information is translated as to object language under the business scenario, therefore, obtaining source language text to be translated, and after determining target language type and business scenario type belonging to source language text, target scene dictionary corresponding with target language type and business scenario type can be determined, and the source language text is translated as target language text using target scene dictionary.
Description
Technical field
This specification is related to data processing field, more particularly to text interpretation method, device and equipment.
Background technology
With the fast development of internet, various forms of business are continued to bring out, and such as on-line payment, online shopping is based on
The service business of internet.User has received and has increasingly been accustomed to carrying out various commercial activitys on the net.With different user
It is different to language requirement, there is provided the service end of service needs country variant language text to meet user's need of country variant
Ask.For example, when page info is updated or entered row information push, according to requirement of the user to language, it is necessary to by original language
Text is converted to target language text.
It is particularly important in consideration of it, providing a kind of reliable text translation scheme.
The content of the invention
To overcome problem present in correlation technique, present description provides text interpretation method, device and equipment.
A kind of text interpretation method, there are different scenes dictionary, scene word for the different business scene configuration of object language
Allusion quotation includes original language information is translated as to the translation result of object language under the business scenario, and methods described includes:
Obtain source language text to be translated;
Determine target language type and the business scenario type belonging to the source language text;
It is determined that target scene dictionary corresponding with the target language type and business scenario type;
The source language text is translated as target language text using the target scene dictionary.
Optionally, the target scene dictionary includes sentence pattern template collection and fixed words and phrases collection, and the sentence pattern template is concentrated every
Individual sentence pattern template includes fixed part and variable part, described to be translated the source language text using the target scene dictionary
For target language text, including:
If the source language text belongs to fixed words and phrases, using the fixation words and phrases collection in the target scene dictionary by institute
State source language text and be translated as target language text;
If the source language text is not belonging to fix words and phrases, will using the sentence pattern template collection in the target scene dictionary
The source language text is translated as target language text.
Optionally, each sentence pattern template is corresponding with the cypher text for being translated as object language, described to utilize the target field
The source language text is translated as target language text by the sentence pattern template collection in scape dictionary, including:
Concentrated from the sentence pattern template in the target scene dictionary, search the clause mould matched with the source language text
Plate;
By multidate information corresponding with the variable part of the sentence pattern template of matching in the source language text, with described
Cypher text corresponding to the sentence pattern template matched somebody with somebody combines, and obtains target language text.
Optionally, each sentence pattern template is corresponding with the cypher text for being translated as object language, described to utilize the target field
The source language text is translated as target language text by the sentence pattern template collection in scape dictionary, including:
Concentrated from the sentence pattern template in the target scene dictionary, search what fixed part matched with the source language text
Sentence pattern template;
If the quantity of the sentence pattern template found is 1, by the change of sentence pattern template in the source language text with finding
The corresponding multidate information in part is measured, cypher text corresponding with the sentence pattern template found combines, and obtains object language
Text;
If the quantity of the sentence pattern template found is more than 1, obtained from the sentence pattern template found and original language text
The target sentence pattern template of this matching, dynamic corresponding with the variable part of target sentence pattern template in the source language text is believed
Breath, cypher text corresponding with the sentence pattern template of the matching combine, and obtain target language text.
Optionally, the scene dictionary is stored and updated in default multilingual management platform, and methods described is also wrapped
Include:
Timing obtains the version identifier of scene dictionary from the multilingual management platform;
By acquired version identifier compared with the version identifier for the scene dictionary being locally stored;
If version identifier is inconsistent, the difference between the scene dictionary of different editions is obtained from the multilingual management platform
Data;
The scene dictionary being locally stored using variance data renewal, and the version identifier of the scene dictionary is updated to
It is consistent with acquired version identifier.
A kind of text translating equipment, there are different scenes dictionary, scene word for the different business scene configuration of object language
Allusion quotation includes original language information is translated as to the translation result of object language under the business scenario, and described device includes:
Text obtains module, for obtaining source language text to be translated;
Determination type module, for determining target language type and the business scenario class belonging to the source language text
Type;
Dictionary determination module, for determining target scene word corresponding with the target language type and business scenario type
Allusion quotation;
Text translation module, for the source language text to be translated as into object language text using the target scene dictionary
This.
Optionally, the target scene dictionary includes sentence pattern template collection and fixed words and phrases collection, and the sentence pattern template is concentrated every
Individual sentence pattern template includes fixed part and variable part, and the text translation module includes:
Static translation module, if belonging to fixed words and phrases for the source language text, utilize the target scene dictionary
In fixation words and phrases collection the source language text is translated as target language text;
Dynamic translation module, if being not belonging to fix words and phrases for the source language text, utilize the target scene word
The source language text is translated as target language text by the sentence pattern template collection in allusion quotation.
Optionally, each sentence pattern template is corresponding with the cypher text for being translated as object language, the dynamic translation module, tool
Body is used for:
Concentrated from the sentence pattern template in the target scene dictionary, search the clause mould matched with the source language text
Plate;
By multidate information corresponding with the variable part of the sentence pattern template of matching in the source language text, with described
Cypher text corresponding to the sentence pattern template matched somebody with somebody combines, and obtains target language text.
Optionally, each sentence pattern template is corresponding with the cypher text for being translated as object language, the dynamic translation module, tool
Body is used for:
Concentrated from the sentence pattern template in the target scene dictionary, search what fixed part matched with the source language text
Sentence pattern template;
If the quantity of the sentence pattern template found is 1, by the change of sentence pattern template in the source language text with finding
The corresponding multidate information in part is measured, cypher text corresponding with the sentence pattern template found combines, and obtains object language
Text;
If the quantity of the sentence pattern template found is more than 1, obtained from the sentence pattern template found and original language text
The target sentence pattern template of this matching, dynamic corresponding with the variable part of target sentence pattern template in the source language text is believed
Breath, cypher text corresponding with the sentence pattern template of the matching combine, and obtain target language text.
Optionally, the scene dictionary is stored and updated in default multilingual management platform, and described device is also wrapped
Dictionary updating module is included, is used for:
Timing obtains the version identifier of scene dictionary from the multilingual management platform;
By acquired version identifier compared with the version identifier for the scene dictionary being locally stored;
If version identifier is inconsistent, the difference between the scene dictionary of different editions is obtained from the multilingual management platform
Data;
The scene dictionary being locally stored using variance data renewal, and the version identifier of the scene dictionary is updated to
It is consistent with acquired version identifier.
A kind of computer equipment, including:
Processor;
For storing the memory of processor-executable instruction;
Wherein, the different business scene configuration for object language has different scenes dictionary, and scene dictionary includes the industry
Original language information is translated as to the translation result of object language, the processor is configured as under business scene:
Obtain source language text to be translated;
Determine target language type and the business scenario type belonging to the source language text;
It is determined that target scene dictionary corresponding with the target language type and business scenario type;
The source language text is translated as target language text using the target scene dictionary.
The technical scheme that the embodiment of this specification provides can include the following benefits:
In this specification embodiment, the translation dictionary of different language type is not only provided, also directed to same language form
Different business scene configuration has different scenes dictionary, because scene dictionary includes translating original language information under the business scenario
For the translation result of object language, therefore, source language text to be translated is being obtained, and determine target language type and source
After business scenario type belonging to language text, target scene word can be determined according to target language type and business scenario type
Allusion quotation, and when being translated using target scene dictionary to source language text, the translation knot met under the business scenario can be obtained
Fruit, improve the accuracy of translation.
It should be appreciated that the general description and following detailed description of the above are only exemplary and explanatory, not
This specification can be limited.
Brief description of the drawings
Accompanying drawing herein is merged in specification and forms the part of this specification, shows the reality for meeting this specification
Apply example, and be used for together with specification the principle for explaining this specification.
Figure 1A is a kind of application scenario diagram of text interpretation method of this specification according to an exemplary embodiment;
Figure 1B is the application scenario diagram of another text interpretation method of this specification according to an exemplary embodiment;
Fig. 2 is a kind of flow chart of text interpretation method of this specification according to an exemplary embodiment;
Fig. 3 is the flow chart of another text interpretation method of this specification according to an exemplary embodiment;
Fig. 4 is a kind of hardware structure diagram of computer equipment where this specification text translating equipment;
Fig. 5 is a kind of block diagram of text translating equipment of this specification according to an exemplary embodiment.
Embodiment
Here exemplary embodiment will be illustrated in detail, its example is illustrated in the accompanying drawings.Following description is related to
During accompanying drawing, unless otherwise indicated, the same numbers in different accompanying drawings represent same or analogous key element.Following exemplary embodiment
Described in embodiment do not represent all embodiments consistent with this specification.On the contrary, they are only and such as institute
The example of the consistent apparatus and method of some aspects be described in detail in attached claims, this specification.
It is only merely for the purpose of description specific embodiment in the term that this specification uses, and is not intended to be limiting this explanation
Book." one kind " of used singulative, " described " and "the" are also intended to bag in this specification and in the appended claims
Most forms are included, unless context clearly shows that other implications.It is also understood that term "and/or" used herein is
Refer to and any or all may be combined comprising the associated list items purpose of one or more.
It will be appreciated that though various information may be described using term first, second, third, etc. in this specification, but
These information should not necessarily be limited by these terms.These terms are only used for same type of information being distinguished from each other out.For example, do not taking off
In the case of this specification scope, the first information can also be referred to as the second information, and similarly, the second information can also be claimed
For the first information.Depending on linguistic context, word as used in this " if " can be construed to " ... when " or
" when ... " or " in response to determining ".
With the fast development of internet, various forms of business are continued to bring out, and such as on-line payment, online shopping is based on
The service business of internet.As different user is different to language requirement, there is provided the service end of service needs country variant language
Text is sayed to meet the user's request of country variant.It is particularly important in consideration of it, providing a kind of reliable text translation scheme.
Text translation can be applied in different application scenarios.For example, the translation request based on user instruction generation, will
The information of user's input is translated as the information that corresponding user it is expected language form.And for example, in instant communication process, it would be desirable to
The information of transmission or the information of reception are translated as the information that corresponding user it is expected language form.And for example, service end is provided
Content of pages is translated as the information that user it is expected language form.And for example, the information that service end pushes is translated as user and it is expected language
Say information of type etc..This specification is mainly translated as user with the information for providing service end and it is expected language form (target language
Speech type) information exemplified by illustrated.
As shown in Figure 1A, it is a kind of applied field of text interpretation method of this specification according to an exemplary embodiment
Jing Tu.In the application scenarios, service end can return to corresponding information according to the request of client to client, for example, please
Ask into next page etc..Client can also send fresh information etc. when page info is updated to client.
During service end sends information to client, the demand according to user to language form can be in client by reception
Information is translated as the information of target language type, information to be sent can also be translated as into target language type in service end
Information.For example, the original language type of current page is Chinese, user it is expected that the target language type of displaying is English, Yong Huke
To trigger the button that language form is switched to English, then client or service end perform text translating operation.
Because the application program of displayed page information can provide a variety of service business, different service business may be by being distributed
Different service ends in formula system provide, and each service end can have multilingual official documents and correspondence translation ability.In order to realize unified pipe
Reason, this specification embodiment also provide a kind of multilingual management platform, and translation when institute is stored and update in multilingual management platform
The dictionary needed.Multilingual management platform provides the multilingual official documents and correspondence management under system granular, such as the increase of information in dictionary, deletes
Remove, change.As shown in Figure 1B, it is answering for another text interpretation method of this specification according to an exemplary embodiment
Use scene graph.Client is connected by network with distributed system, in distributed system each service end respectively with multilingual pipe
Platform is connected, and newest dictionary is obtained from multilingual management platform to realize.Information can the operation based on user in dictionary
Instruction is updated, and can also be counted and is updated by big data.Service end in service end system can be by original language
Text is translated as target language text, and target language text is sent to client.
In order to provide a kind of reliable text translation scheme, this specification embodiment not only provides turning over for different language type
Dictionary is translated, has different scenes dictionary also directed to the different business scene configuration of same language form, because scene dictionary includes
Original language information is translated as to the translation result of object language under the business scenario, therefore, is getting original language to be translated
Text, and after determining target language type and business scenario type belonging to source language text, can be according to object language
Type and business scenario type determine target scene dictionary, and when being translated using target scene dictionary to source language text,
The translation result met under the business scenario can be obtained, improves the accuracy of translation.
As shown in Fig. 2 be a kind of flow chart of text interpretation method of this specification according to an exemplary embodiment,
There is different scenes dictionary for the different business scene configuration of object language, scene dictionary is included source language under the business scenario
Speech information is translated as the translation result of object language, and methods described includes:
In step 201, source language text to be translated is obtained.
In step 202, target language type and the business scenario type belonging to the source language text are determined.
In step 203, it is determined that target scene dictionary corresponding with the target language type and business scenario type.
In step 204, the source language text is translated as target language text using the target scene dictionary.
Wherein, text can be shown with different language type.Language form can be word corresponding to various languages
Type, such as Chinese, English, French, Spanish, Russian, Arabic, Italian, German etc..Source language text can be with
It is the text that language form is original language type, target language text can be the text that language form is target language type,
Target language type is that user it is expected to translate the language form of the cypher text obtained.Original language type and target language type are
In order to distinguish text current language type and it is expected the language form of conversion, and carry out different names.Original language type with
Target language type is different.For example, source language text can be Chinese text, target language text can be English text.
Different dictionaries can be configured with for different language form, dictionary is used for supplementary translation.It can be wrapped in dictionary
Include original language information, original language information is translated as to the translation result of object language, the achievable language of dictionary can also be included
Translation type.For example, dictionary can be that Chinese is converted into the dictionary of English or Chinese is converted to the dictionary of Japanese
Deng.
However, because same vocabulary often has multiple translation results, in consideration of it, this specification embodiment is for same
The different business scene configuration of language form has different scenes dictionary.Business scenario can be the field divided by type of service
Scape.For example, business scenario type can be transfer accounts scene type, credit card repayment scene type, financing scene type, shared list
Car scene type etc..The result that same vocabulary is translated under different business scene may be different, for example, in some business scenarios
Middle China is translated as China, and china is translated as porcelain in some business scenarios.Therefore, scene can be configured by business scenario
Dictionary, the translation result based on business scenario limitation vocabulary in scene dictionary, so as to avoid same vocabulary from having a variety of translation knots
Tab phenolphthaleinum causes the inaccurate situation of translation.
Wherein, the translation knot that original language information is translated as to object language under the business scenario is comprised at least in scene dictionary
Fruit, can also be including the business scenario type and the achievable language of scene dictionary corresponding to original language information, the scene dictionary
Say translation type etc..For example, dictionary of the translator of Chinese for English is subdivided into:Scene of transferring accounts dictionary, credit card repayment scene word
Allusion quotation, shared bicycle scene dictionary etc..In different scene dictionaries, original language information, which is corresponding with, to be adapted under the business scenario
Translation result.For example, in scene dictionary of transferring accounts, the english vocabulary for the scene that is translated as being adapted to transferring accounts by Chinese vocabulary is configured with.
In shared bicycle scene dictionary, it is configured with and is translated as Chinese vocabulary to be adapted to the english vocabulary for sharing bicycle scene.
During source language text to be translated is translated as into target language text, original language to be translated can be obtained
Text.Can need to be translated as the text of object language on source language text.Source language text is translated as object language
On the opportunity of text, can be translated according to translation request or backed up after translating in advance, to need to cut
Directly obtained when changing language form.
In one example, if source language text often changes, can be translated according to translation request.For example,
Receive original language type is switched into the instruction of target language type when, can using current page information as original language text
This;And for example, after receiving original language type switching to the instruction of target language type, if current page needs to carry out letter
The default language type of breath renewal and fresh information is not target language type, then using fresh information as source language to be translated
Say text.And for example, after receiving original language type switching to the instruction of target language type, enter row information if desired and push away
The information default language form sent and pushed is not target language type, then using information to be pushed as source language to be translated
Say text etc..
Because the different business scene configuration for object language has different scenes dictionary, therefore, by source to be translated
Language text is translated as during target language text, it may be determined that the business belonging to target language type and source language text
Scene type.In one example, target language type can ask to obtain based on the translation that user instruction generates.Translation request
In at least carry it is expected translate obtain translation result language form.For example, user it is expected current page switching to English
Literary pattern, then target language type can be English.
It on business scenario type, can be determined based on the business belonging to source language text, user can also be based on and set
Instruction determination etc..If source language text is the information that service end provides, for example, page info, fresh information, pushed information
Deng, then can according to source language text belong to business determine source language text belonging to business scenario type.For example, original language
The information that information belongs in shared bicycle scene service, then the business scenario type belonging to original language information is shared bicycle scene
Type.If source language text is not the information that service end provides, business scenario type can set instruction to obtain based on user
.For example, the text that the needs that source language text is user's input are translated, when user triggers translation button, sets the source language
The business scenario belonging to text is sayed, so as to obtain the business scenario type belonging to source language text.
Because scene dictionary corresponding to different language type and business scenario type is different, therefore it is determined that object language
After business scenario type belonging to type and source language text, it may be determined that with target language type and business scenario type pair
The target scene dictionary answered, so as to obtain the target language text for source language text to be translated as to the suitable business scenario
Target scene dictionary.In consideration of it, source language text is translated as target language text using the target scene dictionary, in target
Translation result based on business scenario limitation vocabulary in scene dictionary, so as to avoid same vocabulary from thering are a variety of translation results to cause to turn over
The situation of inaccuracy is translated, improves translation accuracy.
Source language text is translated as target language text in order to realize, active language can be configured in target scene dictionary
Say translation result etc. corresponding to information and original language information.By the way that source language text is matched with original language information, and
Translation result that the original language information matched with source language text is corresponding is as target language text.
In some cases, source language text content to be translated is relatively fixed.Particularly in the information provided service end
In the scene translated, for example, in the page info that some service ends provide, based on type of service, in page info
Words and phrases are often fixed, therefore words and phrases that can be independent and fixed by content are referred to as fixed words and phrases or static official documents and correspondence.For this
Category information, the information that finds and matched completely with source language text can be concentrated in fixed words and phrases.
In consideration of it, the fixation words and phrases collection needed for being configured with target scene dictionary under the business scenario.Fixed word
Sentence, which integrates, includes fixation vocabulary or sentence of the language form as original language type, and such, which fixes vocabulary or sentence, can be based on the business
Depending on information needed.Fixed it is understood that also including concentrating fixed words and phrases under the business scenario in target scene dictionary
Words and phrases are translated as the translation result of object language.For example, original language type is Chinese, target language type is English, business field
Scape type is bill type, then fixes vocabulary " today " and be corresponding with translation result " Today ", fixed sentence " my bill " is corresponding
There are translation result " My bill " etc..In an optional implementation, it can utilize in target scene dictionary and fix words and phrases collection
Source language text is translated as target language text.For example, because the language form of source language text is original language type, it is fixed
It is original language type that words and phrases, which concentrate language form, therefore can carry out the fixation words and phrases that source language text is concentrated with fixed words and phrases
Hash mapping, the fixation words and phrases matched with source language text are obtained, so as to obtain mesh based on translation result corresponding to fixed words and phrases
Mark language text.In this example embodiment, matched rule can be matched completely.
It can be seen that source language text is translated as target language using the fixation words and phrases collection in target scene dictionary in the embodiment
Text is sayed, realizes and fixed clause is translated.
In some service business, although often there is many words and phrases to have a similitude, partial information is present poor in words and phrases
It is different, this kind of words and phrases are properly termed as on-fixed words and phrases (being not belonging to fix words and phrases) or dynamic official documents and correspondence.In order to improve this category information
The accuracy of translation, cypher text corresponding to words and phrases can be configured with target scene dictionary;Accounted for simultaneously in order to save words and phrases
Resource, different piece in similar words and phrases can be abstracted as to a variable, and be obtained based on same section and meet rule
Sentence pattern template.
In consideration of it, the one of embodiment of this specification is provided with sentence pattern template collection, clause mould in target scene dictionary
Plate concentrates each sentence pattern template to include fixed part and variable part, and fixed part can be identical part in similar words and phrases,
Variable part can be parts different in similar words and phrases, and therefore, fixed part can be translated, and translation, which obtains, to be adapted to be somebody's turn to do
The translation information of the target language type of business scenario, and the position based on variable part in sentence pattern template, in translation result
Middle setting variable identifier, so as to obtain cypher text corresponding to sentence pattern template.It can be seen that it is source language that sentence pattern template, which is language form,
The template of type is sayed, each sentence pattern template is corresponding with the cypher text for being translated as object language.With the language form of sentence pattern template
Exemplified by Chinese, sentence pattern template can be " my account balance is (d+) member ".So that target language type is English as an example, clause
Cypher text corresponding to template can be " My account balance is { 0 } yuan ".In this embodiment it is possible to utilize
Source language text is translated as target language text by the sentence pattern template collection in target scene dictionary, is realized and is improved information translation accurately
Property while, save the storage resource that a large amount of words and phrases take in target scene dictionary.
For how using the sentence pattern template collection in target scene dictionary source language text to be translated as into target language text,
In one example, can be concentrated from the sentence pattern template in the target scene dictionary, lookup matches with the source language text
Sentence pattern template;By multidate information corresponding with the variable part of the sentence pattern template of matching in the source language text, with institute
State cypher text corresponding to the sentence pattern template of matching to combine, obtain target language text.
Wherein, the present embodiment can be concentrated from the sentence pattern template in target scene dictionary, and lookup matches with source language text
Sentence pattern template.As one of which implementation, sentence pattern template can be expressed with regular expression.Regular expression uses single
Individual character string come describe, match it is a series of matching some syntactic rule character strings.For example, sentence pattern template concentration can be traveled through
Sentence pattern template, whether matched by matching regular expressions source language text with sentence pattern template, obtain the sentence pattern template of matching.Sentence
The matched rule of formula template and source language text can be:Relevant position in fixed part and source language text in sentence pattern template
Information match completely, or matching degree is more than predetermined threshold value etc..It can be seen that sentence pattern template is expressed by regular expression, can be with
Find the sentence pattern template matched with source language text.
The cypher text of object language is translated as because each sentence pattern template is corresponding with, therefore the clause of matching can be utilized
Cypher text corresponding to template and the sentence pattern template obtains target language text.For example, the dynamic in source language text is believed
Cease cypher text corresponding with the sentence pattern template matched to combine, obtain target language text.Wherein, multidate information is original language text
The information corresponding with the variable part of the sentence pattern template of matching in this.Using source language text including " my account balance is 11
Exemplified by member ", the sentence pattern template of matching is " my account balance is (d+) member ", and multidate information corresponding to variable part (d+) is
“11”.Combine, multidate information is directly appended in cypher text corresponding to the sentence pattern template of matching, example as one of which
Such as, target language text is " My account balance is 11yuan ", can be by multidate information as another kind combination
The translation of target language type is translated as, and translation is added in cypher text corresponding to the sentence pattern template of matching, for example, mesh
Mark language text is " My account balance is eleven yuan ".The variable part of this kind of sentence pattern template is provided with
Specific demand, to realize the translation that multidate information corresponding to variable part is translated as to target language type.Further, for
Different sentence pattern templates, the identification information of sentence pattern template can be pre-set, the identification information is used to identify whether clause mould
Multidate information corresponding to the variable part of plate is translated.When being combined, can determine it is by dynamic according to identification information
Information is translated as the translation of target language type, and translation is added in cypher text corresponding to the sentence pattern template of matching, also
It is that directly multidate information is directly appended in cypher text corresponding to the sentence pattern template of matching.For example, it is directed to variable part pair
When the multidate information answered is the pet name, multidate information directly can be directly appended to cypher text corresponding to the sentence pattern template of matching
In, for multidate information corresponding to variable part for numeral or during specified type information, multidate information can be translated as target
The translation of language form, and translation is added in cypher text corresponding to the sentence pattern template of matching.It is understood that may be used also
To be other combinations, will not enumerate herein.
However, source language text is directly matched with sentence pattern template, it is necessary to by all information in source language text
Matched with all information in sentence pattern template, performance can be influenceed, in order to reduce the influence to performance, this specification embodiment
Sentence pattern template can be filtered with whether the fixed part in sentence pattern template matches using source language text, will filtered
The sentence pattern template of acquisition is matched with source language text, reduces the number for directly being matched source language text with sentence pattern template
Amount, and then the performance of matching consumption is reduced, performance consumption particularly caused by canonical matching.Specifically, can be from the target
Sentence pattern template in scene dictionary is concentrated, and searches the sentence pattern template that fixed part matches with the source language text.Wherein, search
The sentence pattern template that fixed part matches with the source language text, fixed part can be to look for and be present in source language text
Sentence pattern template.When the fixed part in sentence pattern template is matched with source language text, source language text can be to look for
In whether there is whole fixed parts, or with the presence or absence of part fixed part, determine whether to filter the sentence pattern template.
For example, the position relationship based on variable part and fixed part, if variable part in the centre of fixed part, can
So that the part above of variable part in fixed part is referred to as into prefix part, the following sections of variable part in fixed part are claimed
For suffix portion, when the fixed part in sentence pattern template is matched with source language text, prefix portion can also be only judged
Divide or suffix portion whether there is in source language text, so as to realize the filtering to sentence pattern template.Merely with fixed part
Partial information sentence pattern template is filtered, filter efficiency can be improved.
After sentence pattern template is found, if the quantity of the sentence pattern template found is 1, then it is assumed that the clause mould found
Plate is the template matched with source language text, can be relative by the variable part of the sentence pattern template in source language text with finding
The multidate information answered, cypher text corresponding with the sentence pattern template found combine, and obtain target language text.Wherein,
Multidate information can be the corresponding information of the variable part of the sentence pattern template with finding in source language text, by multidate information
Cypher text corresponding with the sentence pattern template found, which combines, obtains target language text.For example, can be direct by multidate information
It is added in cypher text corresponding to the sentence pattern template found.And for example, multidate information can be translated as target language type
Translation, and translation is added in cypher text corresponding to the sentence pattern template of matching.
If the quantity of the sentence pattern template found is 1, can be obtained from the sentence pattern template found and the source language
The target sentence pattern template of text matches is sayed, is moved corresponding with the variable part of target sentence pattern template in the source language text
State information, cypher text corresponding with the sentence pattern template of the matching combine, and obtain target language text.It is understood that
If the quantity of the sentence pattern template found is 1, whether the sentence pattern template that can also judge to find matches with source language text,
Realization determines whether to sentence pattern template, to determine the need for entering multidate information and cypher text according to judged result
Row combines, and then improves the accuracy of translation.
If the quantity of the sentence pattern template found is more than 1, indicate the sentence pattern template of multiple candidates, then can be by source language
Speech text is matched with the sentence pattern template found, the target sentence pattern template matched with source language text is obtained, so as to utilize
Source language text is translated as target language text by cypher text corresponding to target sentence pattern template and target sentence pattern template.
As seen from the above-described embodiment, whether matched using the fixed part in sentence pattern template with source language text, so as to right
Sentence pattern template is filtered, and the sentence pattern template for filtering acquisition is matched with source language text, is reduced original language text directly
This quantity matched with sentence pattern template, reduces the time of matching consumption, while reduces performance consumption.
In practical application, in information to be translated, some information belong to fixed words and phrases, and some information are not belonging to fix word
Sentence, in consideration of it, this specification embodiment can be translated the source language text for belonging to fixed words and phrases using fixed words and phrases collection,
The source language text that will not belong to fix words and phrases is translated using sentence pattern template collection.In this embodiment, target scene dictionary
Including sentence pattern template collection and fixed words and phrases collection, the sentence pattern template concentrates each sentence pattern template to include fixed part and variable portion
Point, it is described that the source language text is translated as target language text using the target scene dictionary, including:
If the source language text belongs to fixed words and phrases, using the fixation words and phrases collection in the target scene dictionary by institute
State source language text and be translated as target language text;
If the source language text is not belonging to fix words and phrases, will using the sentence pattern template collection in the target scene dictionary
The source language text is translated as target language text.
In this embodiment it is possible to first determine whether source language text belongs to fixed words and phrases.In one example, Ke Yitong
Crossing user sets instruction to determine whether source language text belongs to fixed words and phrases.In another example, page layout is usually pre-
First setting, the sound state for the information that diverse location is laid out in the page is relatively fixed, wherein, sound state is to be used to describe
Whether source language text belongs to the state of fixed words and phrases, therefore, can determine source based on position of the source language text in the page
Whether language text belongs to fixed words and phrases.It is understood that it can also determine whether source language text belongs to by other means
It is numerous to list herein in fixed words and phrases.
It can be seen that when source language text belongs to fixed words and phrases, using the fixation words and phrases collection in target scene dictionary by source language
Speech text is translated as target language text, can improve translation efficiency, when source language text belongs to on-fixed words and phrases, utilize mesh
Source language text is translated as target language text by the sentence pattern template collection in mark scene dictionary, can improve translation accuracy rate, real
Now both support static official documents and correspondence to translate, and support the translation of dynamic official documents and correspondence again.
Further, sentence pattern template collection can be individually divided into dynamic dictionary, fixed words and phrases collection is individually divided into quiet
State dictionary, i.e. target scene dictionary can include dynamic dictionary and static dictionary, by different dictionary management different sets, realize
Manage respectively, be easy to be updated respectively.
The scene dictionary being locally stored can also be updated.In an optional implementation, the scene dictionary
Stored and updated in default multilingual management platform, methods described also includes:
Timing obtains the version identifier of scene dictionary from the multilingual management platform;
By acquired version identifier compared with the version identifier for the scene dictionary being locally stored;
If version identifier is inconsistent, the difference between the scene dictionary of different editions is obtained from the multilingual management platform
Data;
The scene dictionary being locally stored using variance data renewal, and the version identifier of the scene dictionary is updated to
It is consistent with acquired version identifier.
Wherein, multilingual management platform can realize dictionary with the scene dictionary of each service end in managing distributing type system
Storage and renewal.For example, renewal can include deletion, addition, modification of sentence pattern template and its cypher text etc..In order to avoid
Service end obtains the unwanted dictionary information of local terminal from multilingual management platform, and multilingual management platform can manage each respectively
The scene dictionary of service end.Every time during renewal dictionary, the version identifier for identifying the scene dictionary is changed, such as version identifier
It can be version number, when updating dictionary every time, the version number of the dictionary be increased, and record modification information (difference number
According to).
In one example, a number can be pulled by setting interval time to realize timing, such as at interval of 5 minutes
According to.
In this actuating station, the version identifier of scene dictionary is regularly obtained from multilingual management platform, and will be acquired
Version identifier is compared with the version identifier for the scene dictionary being locally stored, if version identifier is inconsistent, represents to be locally stored
Scene dictionary and scene dictionary that multilingual management platform stores it is inconsistent, then obtain different editions from multilingual management platform
Scene dictionary between variance data;And using the scene dictionary that is locally stored of variance data renewal, while and by the scene word
The version identifier of allusion quotation be updated to it is consistent with acquired version identifier, to carry out version identifier comparison next time.
It can be seen that the present embodiment judges whether scene dictionary is updated by way of version identifier, if scene word
Allusion quotation is updated, then actively pulls variance data from multilingual management platform, is locally stored using variance data renewal
Scene dictionary, realize that scene dictionary upgrades in time.
Furthermore, it is possible in multilingual management platform more new scene dictionary, actively variance data (fresh information) is pushed
To service end, service end updates the scene dictionary being locally stored using the variance data of reception, is not limited herein.
Various technical characteristics in embodiment of above can be arbitrarily combined, as long as the combination between feature is not present
Conflict or contradiction, but as space is limited, do not described one by one, therefore the various technical characteristics in above-mentioned embodiment is any
It is combined the scope for falling within this disclosure.
Illustrated below with one of which combination.
As shown in figure 3, Fig. 3 is the stream of another text interpretation method of this specification according to an exemplary embodiment
Cheng Tu, in this embodiment, there is different scenes dictionary for the different business scene configuration of object language, scene dictionary includes
Original language information is translated as to the translation result of object language, methods described includes under the business scenario:
In step 301, source language text to be translated is obtained.
In step 302, target language type, the business scenario type belonging to the source language text, Yi Jisuo are determined
State the sound state of source language text.
Wherein, sound state is whether to belong to the state of fixed words and phrases for describing source language text, can will belong to solid
The source language text for determining words and phrases is judged to, in static state, the source language text for belonging to on-fixed words and phrases being determined as in dynamic.
In step 303, it is determined that target scene dictionary corresponding with the target language type and business scenario type.
Wherein, the target scene dictionary includes the dynamic dictionary containing sentence pattern template and the static word containing fixed words and phrases
Allusion quotation, each sentence pattern template includes fixed part and variable part in the dynamic dictionary.
In step 304, if the source language text belongs to fixed words and phrases, using quiet in the target scene dictionary
The source language text is translated as target language text by state dictionary.
In step 305, if the source language text is not belonging to fix words and phrases, using in the target scene dictionary
The source language text is translated as target language text by dynamic dictionary.
Further, dictionary can also be managed collectively by multilingual management platform, and in this actuating station to field
Scape dictionary is updated, and dictionary updating process can include:
Within step 306, the version identifier of scene dictionary is regularly obtained from the multilingual management platform.
In step 307, by acquired version identifier compared with the version identifier for the scene dictionary being locally stored.
In step 308, if version identifier is inconsistent, the scene of different editions is obtained from the multilingual management platform
Variance data between dictionary.
In a step 309, using the scene dictionary that is locally stored of variance data renewal, and by the version of the scene dictionary
This mark is updated to consistent with acquired version identifier.
Step 301 is to 309 identical with correlation technique in previous embodiment, and this is no longer going to repeat them.
As seen from the above-described embodiment, the embodiment has different scenes for the different business scene configuration of same language form
Dictionary, because scene dictionary includes translation result that original language information is translated as to object language under the business scenario, therefore,
When being translated using target scene dictionary to source language text, the translation result met under the business scenario can be obtained, is carried
The accuracy of height translation;Meanwhile realize that multilingual static official documents and correspondence is translated, dynamic official documents and correspondence turns over by dynamic dictionary and static dictionary
Translate, furthermore it is also possible to judge whether scene dictionary is updated by way of version identifier, if scene dictionary is carried out
Renewal, then variance data actively is pulled from multilingual management platform, the scene dictionary being locally stored using variance data renewal,
Realize that scene dictionary upgrades in time.
Corresponding with the embodiment of aforementioned texts interpretation method, this specification additionally provides text translating equipment and its answered
The embodiment of electronic equipment.
The embodiment of this specification text translating equipment can be applied in computer equipment.Device embodiment can be by soft
Part is realized, can also be realized by way of hardware or software and hardware combining.Exemplified by implemented in software, as a logical meaning
On device, be by corresponding computer program instructions in nonvolatile memory by the processor of computer equipment where it
Read what operation in internal memory was formed.For hardware view, as shown in figure 4, being counted where this specification text translating equipment
Calculate machine equipment a kind of hardware structure diagram, except the processor 410 shown in Fig. 4, internal memory 430, network interface 420 and it is non-easily
Outside the property lost memory 440, the computer equipment in embodiment where device 431 is gone back generally according to the actual functional capability of the equipment
Other hardware can be included, this is repeated no more.
As shown in figure 5, be a kind of block diagram of text translating equipment of this specification according to an exemplary embodiment, pin
There is different scenes dictionary to the different business scene configuration of object language, scene dictionary is included original language under the business scenario
Information is translated as the translation result of object language, and described device includes:
Text obtains module 52, for obtaining source language text to be translated;
Determination type module 54, for determining target language type and the business scenario class belonging to the source language text
Type;
Dictionary determination module 56, for determining target scene corresponding with the target language type and business scenario type
Dictionary;
Text translation module 58, for the source language text to be translated as into object language using the target scene dictionary
Text.
Optionally, the target scene dictionary includes sentence pattern template collection and fixed words and phrases collection, and the sentence pattern template is concentrated every
Individual sentence pattern template includes fixed part and variable part, and the text translation module includes:
Static translation module, if belonging to fixed words and phrases for the source language text, utilize the target scene dictionary
In fixation words and phrases collection the source language text is translated as target language text;
Dynamic translation module, if being not belonging to fix words and phrases for the source language text, utilize the target scene word
The source language text is translated as target language text by the sentence pattern template collection in allusion quotation.
Optionally, each sentence pattern template is corresponding with the cypher text for being translated as object language, the dynamic translation module, tool
Body is used for:
Concentrated from the sentence pattern template in the target scene dictionary, search the clause mould matched with the source language text
Plate;
By multidate information corresponding with the variable part of the sentence pattern template of matching in the source language text, with described
Cypher text corresponding to the sentence pattern template matched somebody with somebody combines, and obtains target language text.
Optionally, each sentence pattern template is corresponding with the cypher text for being translated as object language, the dynamic translation module, tool
Body is used for:
Concentrated from the sentence pattern template in the target scene dictionary, search what fixed part matched with the source language text
Sentence pattern template;
If the quantity of the sentence pattern template found is 1, by the change of sentence pattern template in the source language text with finding
The corresponding multidate information in part is measured, cypher text corresponding with the sentence pattern template found combines, and obtains object language
Text;
If the quantity of the sentence pattern template found is more than 1, obtained from the sentence pattern template found and original language text
The target sentence pattern template of this matching, dynamic corresponding with the variable part of target sentence pattern template in the source language text is believed
Breath, cypher text corresponding with the sentence pattern template of the matching combine, and obtain target language text.
Optionally, the scene dictionary is stored and updated in default multilingual management platform, and described device is also wrapped
Dictionary updating module is included, is used for:
Timing obtains the version identifier of scene dictionary from the multilingual management platform;
By acquired version identifier compared with the version identifier for the scene dictionary being locally stored;
If version identifier is inconsistent, the difference between the scene dictionary of different editions is obtained from the multilingual management platform
Data;
The scene dictionary being locally stored using variance data renewal, and the version identifier of the scene dictionary is updated to
It is consistent with acquired version identifier.
For device embodiment, because it corresponds essentially to embodiment of the method, so related part is real referring to method
Apply the part explanation of example.Device embodiment described above is only schematical, wherein described be used as separating component
The module of explanation can be or may not be physically separate, can be as the part that module is shown or can also
It is not physical module, you can with positioned at a place, or can also be distributed on multiple mixed-media network modules mixed-medias.Can be according to reality
Need to select some or all of module therein to realize the purpose of this specification scheme.Those of ordinary skill in the art are not
In the case of paying creative work, you can to understand and implement.
A kind of computer equipment, including:
Processor;
For storing the memory of processor-executable instruction;
Wherein, the different business scene configuration for object language has different scenes dictionary, and scene dictionary includes the industry
Original language information is translated as to the translation result of object language, the processor is configured as under business scene:
Obtain source language text to be translated;
Determine target language type and the business scenario type belonging to the source language text;
It is determined that target scene dictionary corresponding with the target language type and business scenario type;
The source language text is translated as target language text using the target scene dictionary.
Each embodiment in this specification is described by the way of progressive, identical similar portion between each embodiment
Divide mutually referring to what each embodiment stressed is the difference with other embodiment.It is real especially for equipment
For applying example, because it is substantially similar to embodiment of the method, so description is fairly simple, related part is referring to embodiment of the method
Part explanation.
A kind of computer-readable storage medium, have program stored therein in the storage medium instruction, for the not of the same trade or business of object language
Business scene configuration has different scenes dictionary, and scene dictionary includes original language information is translated as into object language under the business scenario
Translation result, described program instruction include:
Obtain source language text to be translated;
Determine target language type and the business scenario type belonging to the source language text;
It is determined that target scene dictionary corresponding with the target language type and business scenario type;
The source language text is translated as target language text using the target scene dictionary.
This specification embodiment can use wherein includes the storage medium of program code (including but not in one or more
Be limited to magnetic disk storage, CD-ROM, optical memory etc.) on the form of computer program product implemented.Computer is available to be deposited
Storage media includes permanent and non-permanent, removable and non-removable media, can realize letter by any method or technique
Breath storage.Information can be computer-readable instruction, data structure, the module of program or other data.The storage of computer is situated between
The example of matter includes but is not limited to:Phase transition internal memory (PRAM), static RAM (SRAM), dynamic random access memory
Device (DRAM), other kinds of random access memory (RAM), read-only storage (ROM), the read-only storage of electrically erasable
Device (EEPROM), fast flash memory bank or other memory techniques, read-only optical disc read-only storage (CD-ROM), digital versatile disc
(DVD) or other optical storages, magnetic cassette tape, the storage of tape magnetic rigid disk or other magnetic storage apparatus or any other non-biography
Defeated medium, the information that can be accessed by a computing device available for storage.
Those skilled in the art will readily occur to this specification after considering specification and putting into practice the invention applied here
Other embodiments.This specification is intended to any modification, purposes or adaptations of this specification, these modifications,
Purposes or adaptations follow the general principle of this specification and not applied in the art including this specification
Common knowledge or conventional techniques.Description and embodiments be considered only as it is exemplary, the true scope of this specification and
Spirit is pointed out by following claim.
It should be appreciated that the precision architecture that this specification is not limited to be described above and is shown in the drawings,
And various modifications and changes can be being carried out without departing from the scope.The scope of this specification is only limited by appended claim
System.
The preferred embodiment of this specification is the foregoing is only, it is all in this explanation not to limit this specification
Within the spirit and principle of book, any modification, equivalent substitution and improvements done etc., the model of this specification protection should be included in
Within enclosing.
Claims (11)
1. a kind of text interpretation method, there are different scenes dictionary, scene dictionary for the different business scene configuration of object language
Include original language information is translated as to the translation result of object language under the business scenario, methods described includes:
Obtain source language text to be translated;
Determine target language type and the business scenario type belonging to the source language text;
It is determined that target scene dictionary corresponding with the target language type and business scenario type;
The source language text is translated as target language text using the target scene dictionary.
2. according to the method for claim 1, the target scene dictionary includes sentence pattern template collection and fixed words and phrases collection, described
Sentence pattern template concentrates each sentence pattern template to include fixed part and variable part, described to utilize the target scene dictionary by described in
Source language text is translated as target language text, including:
If the source language text belongs to fixed words and phrases, using the fixation words and phrases collection in the target scene dictionary by the source
Language text is translated as target language text;
If the source language text is not belonging to fix words and phrases, using the sentence pattern template collection in the target scene dictionary by described in
Source language text is translated as target language text.
3. according to the method for claim 2, each sentence pattern template is corresponding with the cypher text for being translated as object language, described
The source language text is translated as target language text using the sentence pattern template collection in the target scene dictionary, including:
Concentrated from the sentence pattern template in the target scene dictionary, search the sentence pattern template matched with the source language text;
By multidate information corresponding with the variable part of the sentence pattern template of matching in the source language text, with the matching
Cypher text corresponding to sentence pattern template combines, and obtains target language text.
4. according to the method for claim 2, each sentence pattern template is corresponding with the cypher text for being translated as object language, described
The source language text is translated as target language text using the sentence pattern template collection in the target scene dictionary, including:
Concentrated from the sentence pattern template in the target scene dictionary, search the clause that fixed part matches with the source language text
Template;
If the quantity of the sentence pattern template found is 1, by the variable portion of sentence pattern template in the source language text with finding
Multidate information corresponding to split-phase, cypher text corresponding with the sentence pattern template found combine, and obtain target language text;
If the quantity of the sentence pattern template found is more than 1, obtained from the sentence pattern template found and the source language text
The target sentence pattern template matched somebody with somebody, by multidate information corresponding with the variable part of target sentence pattern template in the source language text,
Cypher text corresponding with the sentence pattern template of the matching combines, and obtains target language text.
5. according to the method described in any one of Claims 1-4, the scene dictionary is carried out in default multilingual management platform
Storage and renewal, methods described also include:
Timing obtains the version identifier of scene dictionary from the multilingual management platform;
By acquired version identifier compared with the version identifier for the scene dictionary being locally stored;
If version identifier is inconsistent, the difference number between the scene dictionary of different editions is obtained from the multilingual management platform
According to;
It is updated to and institute using the scene dictionary that is locally stored of variance data renewal, and by the version identifier of the scene dictionary
The version identifier of acquisition is consistent.
6. a kind of text translating equipment, there are different scenes dictionary, scene dictionary for the different business scene configuration of object language
Include original language information is translated as to the translation result of object language under the business scenario, described device includes:
Text obtains module, for obtaining source language text to be translated;
Determination type module, for determining target language type and the business scenario type belonging to the source language text;
Dictionary determination module, for determining target scene dictionary corresponding with the target language type and business scenario type;
Text translation module, for the source language text to be translated as into target language text using the target scene dictionary.
7. device according to claim 6, the target scene dictionary includes sentence pattern template collection and fixed words and phrases collection, described
Sentence pattern template concentrates each sentence pattern template to include fixed part and variable part, and the text translation module includes:
Static translation module, if belonging to fixed words and phrases for the source language text, using in the target scene dictionary
The source language text is translated as target language text by fixed words and phrases collection;
Dynamic translation module, if being not belonging to fix words and phrases for the source language text, using in the target scene dictionary
Sentence pattern template collection the source language text is translated as target language text.
8. device according to claim 7, each sentence pattern template is corresponding with the cypher text for being translated as object language, described
Dynamic translation module, it is specifically used for:
Concentrated from the sentence pattern template in the target scene dictionary, search the sentence pattern template matched with the source language text;
By multidate information corresponding with the variable part of the sentence pattern template of matching in the source language text, with the matching
Cypher text corresponding to sentence pattern template combines, and obtains target language text.
9. device according to claim 7, each sentence pattern template is corresponding with the cypher text for being translated as object language, described
Dynamic translation module, it is specifically used for:
Concentrated from the sentence pattern template in the target scene dictionary, search the clause that fixed part matches with the source language text
Template;
If the quantity of the sentence pattern template found is 1, by the variable portion of sentence pattern template in the source language text with finding
Multidate information corresponding to split-phase, cypher text corresponding with the sentence pattern template found combine, and obtain target language text;
If the quantity of the sentence pattern template found is more than 1, obtained from the sentence pattern template found and the source language text
The target sentence pattern template matched somebody with somebody, by multidate information corresponding with the variable part of target sentence pattern template in the source language text,
Cypher text corresponding with the sentence pattern template of the matching combines, and obtains target language text.
10. according to the device described in any one of claim 6 to 9, the scene dictionary enters in default multilingual management platform
Row storage and renewal, described device also include dictionary updating module, are used for:
Timing obtains the version identifier of scene dictionary from the multilingual management platform;
By acquired version identifier compared with the version identifier for the scene dictionary being locally stored;
If version identifier is inconsistent, the difference number between the scene dictionary of different editions is obtained from the multilingual management platform
According to;
It is updated to and institute using the scene dictionary that is locally stored of variance data renewal, and by the version identifier of the scene dictionary
The version identifier of acquisition is consistent.
11. a kind of computer equipment, including:
Processor;
For storing the memory of processor-executable instruction;
Wherein, the different business scene configuration for object language has different scenes dictionary, and scene dictionary includes the business field
Original language information is translated as to the translation result of object language, the processor is configured as under scape:
Obtain source language text to be translated;
Determine target language type and the business scenario type belonging to the source language text;
It is determined that target scene dictionary corresponding with the target language type and business scenario type;
The source language text is translated as target language text using the target scene dictionary.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710718020.6A CN107391500A (en) | 2017-08-21 | 2017-08-21 | Text interpretation method, device and equipment |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710718020.6A CN107391500A (en) | 2017-08-21 | 2017-08-21 | Text interpretation method, device and equipment |
Publications (1)
Publication Number | Publication Date |
---|---|
CN107391500A true CN107391500A (en) | 2017-11-24 |
Family
ID=60353903
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710718020.6A Pending CN107391500A (en) | 2017-08-21 | 2017-08-21 | Text interpretation method, device and equipment |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107391500A (en) |
Cited By (20)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107153541A (en) * | 2017-04-20 | 2017-09-12 | 北京小米移动软件有限公司 | Browse interaction processing method and device |
CN108415905A (en) * | 2018-03-06 | 2018-08-17 | 喻海联 | Real time translating method, intelligent glasses and computer readable storage medium |
CN108763228A (en) * | 2018-05-21 | 2018-11-06 | 王伟宙 | A kind of natural language secondary treatment system |
CN108959274A (en) * | 2018-06-27 | 2018-12-07 | 维沃移动通信有限公司 | A kind of interpretation method and server of application program |
CN109861904A (en) * | 2019-02-19 | 2019-06-07 | 天津字节跳动科技有限公司 | Nametags display methods and device |
CN110008468A (en) * | 2019-03-04 | 2019-07-12 | 广州虎牙信息科技有限公司 | Language system management method, information conversion method, server and storage medium |
CN111008524A (en) * | 2019-12-05 | 2020-04-14 | 网易(杭州)网络有限公司 | Language translation processing method and device |
CN111177318A (en) * | 2019-12-23 | 2020-05-19 | 杭州安恒信息技术股份有限公司 | Method, device and computer readable storage medium for executing international business |
CN111209755A (en) * | 2019-12-25 | 2020-05-29 | 广东飞企互联科技股份有限公司 | Efficient translation method |
CN111369973A (en) * | 2020-02-28 | 2020-07-03 | 广州三星通信技术研究有限公司 | Method and device for selecting translation tool in electronic terminal |
CN111368560A (en) * | 2020-02-28 | 2020-07-03 | 北京字节跳动网络技术有限公司 | Text translation method and device, electronic equipment and storage medium |
CN112037074A (en) * | 2020-09-11 | 2020-12-04 | 中国银行股份有限公司 | Visualization-based data file analysis method and device |
CN112069439A (en) * | 2020-09-15 | 2020-12-11 | 成都知道创宇信息技术有限公司 | Document request processing method and device, document providing server and storage medium |
CN112100987A (en) * | 2020-09-27 | 2020-12-18 | 中国建设银行股份有限公司 | Transcoding method and device for multi-source data dictionary |
CN112347794A (en) * | 2020-10-27 | 2021-02-09 | 深圳前海微众银行股份有限公司 | Data translation method, device, equipment and computer storage medium |
CN112699692A (en) * | 2021-01-04 | 2021-04-23 | 安徽希施玛数据科技有限公司 | Text translation control method and device, electronic equipment and storage medium |
CN112817655A (en) * | 2021-01-29 | 2021-05-18 | 北京达佳互联信息技术有限公司 | Document information processing method, device, storage medium and electronic equipment |
CN112988290A (en) * | 2019-12-12 | 2021-06-18 | 腾讯科技(深圳)有限公司 | Multi-language configuration file generation method, page display method, device and terminal |
CN113539271A (en) * | 2021-07-23 | 2021-10-22 | 北京梧桐车联科技有限责任公司 | Speech recognition method, device, equipment and computer readable storage medium |
CN115797815A (en) * | 2021-09-08 | 2023-03-14 | 荣耀终端有限公司 | AR translation processing method and electronic device |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1308748A (en) * | 1998-05-04 | 2001-08-15 | 特雷道斯股份有限公司 | Machine-assisted translation tools |
CN101206643A (en) * | 2006-12-21 | 2008-06-25 | 中国科学院计算技术研究所 | Translation method syncretizing sentential form template and statistics mechanical translation technique |
CN101571854A (en) * | 2009-06-11 | 2009-11-04 | 四川国腾通讯股份有限公司 | System and method for exchange and communication among multinational languages |
CN102084417A (en) * | 2008-04-15 | 2011-06-01 | 移动技术有限责任公司 | System and methods for maintaining speech-to-speech translation in the field |
CN104025079A (en) * | 2011-09-09 | 2014-09-03 | 谷歌公司 | User interface for translation webpage |
US20150088484A1 (en) * | 2013-09-26 | 2015-03-26 | International Business Machines Corporation | Domain specific salient point translation |
CN106649282A (en) * | 2015-10-30 | 2017-05-10 | 阿里巴巴集团控股有限公司 | Machine translation method and device based on statistics, and electronic equipment |
CN106959943A (en) * | 2016-01-11 | 2017-07-18 | 阿里巴巴集团控股有限公司 | Languages recognize update method and device |
-
2017
- 2017-08-21 CN CN201710718020.6A patent/CN107391500A/en active Pending
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1308748A (en) * | 1998-05-04 | 2001-08-15 | 特雷道斯股份有限公司 | Machine-assisted translation tools |
CN101206643A (en) * | 2006-12-21 | 2008-06-25 | 中国科学院计算技术研究所 | Translation method syncretizing sentential form template and statistics mechanical translation technique |
CN102084417A (en) * | 2008-04-15 | 2011-06-01 | 移动技术有限责任公司 | System and methods for maintaining speech-to-speech translation in the field |
CN101571854A (en) * | 2009-06-11 | 2009-11-04 | 四川国腾通讯股份有限公司 | System and method for exchange and communication among multinational languages |
CN104025079A (en) * | 2011-09-09 | 2014-09-03 | 谷歌公司 | User interface for translation webpage |
US20150088484A1 (en) * | 2013-09-26 | 2015-03-26 | International Business Machines Corporation | Domain specific salient point translation |
CN106649282A (en) * | 2015-10-30 | 2017-05-10 | 阿里巴巴集团控股有限公司 | Machine translation method and device based on statistics, and electronic equipment |
CN106959943A (en) * | 2016-01-11 | 2017-07-18 | 阿里巴巴集团控股有限公司 | Languages recognize update method and device |
Cited By (27)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107153541A (en) * | 2017-04-20 | 2017-09-12 | 北京小米移动软件有限公司 | Browse interaction processing method and device |
CN108415905A (en) * | 2018-03-06 | 2018-08-17 | 喻海联 | Real time translating method, intelligent glasses and computer readable storage medium |
CN108763228A (en) * | 2018-05-21 | 2018-11-06 | 王伟宙 | A kind of natural language secondary treatment system |
CN108959274A (en) * | 2018-06-27 | 2018-12-07 | 维沃移动通信有限公司 | A kind of interpretation method and server of application program |
CN108959274B (en) * | 2018-06-27 | 2022-09-02 | 维沃移动通信有限公司 | Translation method of application program and server |
CN109861904A (en) * | 2019-02-19 | 2019-06-07 | 天津字节跳动科技有限公司 | Nametags display methods and device |
US11283740B2 (en) | 2019-02-19 | 2022-03-22 | Tianjin Bytedance Technology Co., Ltd. | Name label display method and apparatus |
CN110008468A (en) * | 2019-03-04 | 2019-07-12 | 广州虎牙信息科技有限公司 | Language system management method, information conversion method, server and storage medium |
CN111008524A (en) * | 2019-12-05 | 2020-04-14 | 网易(杭州)网络有限公司 | Language translation processing method and device |
CN112988290B (en) * | 2019-12-12 | 2024-01-26 | 腾讯科技(深圳)有限公司 | Multi-language configuration file generation method, page display method, device and terminal |
CN112988290A (en) * | 2019-12-12 | 2021-06-18 | 腾讯科技(深圳)有限公司 | Multi-language configuration file generation method, page display method, device and terminal |
CN111177318A (en) * | 2019-12-23 | 2020-05-19 | 杭州安恒信息技术股份有限公司 | Method, device and computer readable storage medium for executing international business |
CN111209755A (en) * | 2019-12-25 | 2020-05-29 | 广东飞企互联科技股份有限公司 | Efficient translation method |
CN111369973A (en) * | 2020-02-28 | 2020-07-03 | 广州三星通信技术研究有限公司 | Method and device for selecting translation tool in electronic terminal |
CN111368560A (en) * | 2020-02-28 | 2020-07-03 | 北京字节跳动网络技术有限公司 | Text translation method and device, electronic equipment and storage medium |
CN112037074A (en) * | 2020-09-11 | 2020-12-04 | 中国银行股份有限公司 | Visualization-based data file analysis method and device |
CN112037074B (en) * | 2020-09-11 | 2024-04-19 | 中国银行股份有限公司 | Visualization-based data file analysis method and device |
CN112069439A (en) * | 2020-09-15 | 2020-12-11 | 成都知道创宇信息技术有限公司 | Document request processing method and device, document providing server and storage medium |
CN112069439B (en) * | 2020-09-15 | 2023-10-13 | 成都知道创宇信息技术有限公司 | Document request processing method and device, document providing server and storage medium |
CN112100987A (en) * | 2020-09-27 | 2020-12-18 | 中国建设银行股份有限公司 | Transcoding method and device for multi-source data dictionary |
CN112347794A (en) * | 2020-10-27 | 2021-02-09 | 深圳前海微众银行股份有限公司 | Data translation method, device, equipment and computer storage medium |
CN112699692A (en) * | 2021-01-04 | 2021-04-23 | 安徽希施玛数据科技有限公司 | Text translation control method and device, electronic equipment and storage medium |
CN112817655A (en) * | 2021-01-29 | 2021-05-18 | 北京达佳互联信息技术有限公司 | Document information processing method, device, storage medium and electronic equipment |
CN112817655B (en) * | 2021-01-29 | 2024-05-14 | 北京达佳互联信息技术有限公司 | Document information processing method and device, storage medium and electronic equipment |
CN113539271A (en) * | 2021-07-23 | 2021-10-22 | 北京梧桐车联科技有限责任公司 | Speech recognition method, device, equipment and computer readable storage medium |
CN115797815A (en) * | 2021-09-08 | 2023-03-14 | 荣耀终端有限公司 | AR translation processing method and electronic device |
CN115797815B (en) * | 2021-09-08 | 2023-12-15 | 荣耀终端有限公司 | AR translation processing method and electronic equipment |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107391500A (en) | Text interpretation method, device and equipment | |
Maekawa et al. | Balanced corpus of contemporary written Japanese | |
CN107256269B (en) | Method, computer-readable non-transitory storage medium and system | |
EP2570974B1 (en) | Automatic crowd sourcing for machine learning in information extraction | |
US9224103B1 (en) | Automatic annotation for training and evaluation of semantic analysis engines | |
CN110413738A (en) | A kind of information processing method, device, server and storage medium | |
CN105045852A (en) | Full-text search engine system for teaching resources | |
JP6663826B2 (en) | Computer and response generation method | |
KR20100038378A (en) | A method, system and computer program for intelligent text annotation | |
CN102314440B (en) | Utilize the method and system in network operation language model storehouse | |
JP6165955B1 (en) | Method and system for matching images and content using whitelist and blacklist in response to search query | |
US20180089335A1 (en) | Indication of search result | |
CN110134970A (en) | Header error correction method and apparatus | |
Dong et al. | Multichannel LSTM-CRF for named entity recognition in Chinese social media | |
CN110489032B (en) | Dictionary query method for electronic book and electronic equipment | |
US20080040352A1 (en) | Method for creating a disambiguation database | |
Kuć et al. | Elasticsearch Server | |
CN110362656A (en) | A kind of semantic feature extracting method and device | |
CN110209780A (en) | A kind of question template generation method, device, server and storage medium | |
JPWO2009048149A1 (en) | Electronic document equivalence judgment system and equivalence judgment method | |
US20090182759A1 (en) | Extracting entities from a web page | |
März et al. | Data centric domain adaptation for historical text with OCR errors | |
Tschirschwitz et al. | A dataset for analysing complex document layouts in the digital humanities and its evaluation with Krippendorff’s alpha | |
JP5739352B2 (en) | Dictionary generation apparatus, document label determination system, and computer program | |
CN113268600B (en) | Method, device, electronic equipment and storage medium for correcting wrongly written or mispronounced search name |
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: 20171124 |