CN108255940A - A kind of cross-language search method and apparatus, a kind of device for cross-language search - Google Patents

A kind of cross-language search method and apparatus, a kind of device for cross-language search Download PDF

Info

Publication number
CN108255940A
CN108255940A CN201711298752.0A CN201711298752A CN108255940A CN 108255940 A CN108255940 A CN 108255940A CN 201711298752 A CN201711298752 A CN 201711298752A CN 108255940 A CN108255940 A CN 108255940A
Authority
CN
China
Prior art keywords
language
source language
language search
translation results
translation
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
Application number
CN201711298752.0A
Other languages
Chinese (zh)
Inventor
许静芳
张嘉成
翟飞飞
戴磊
刘祺
方菲
丁彦卓
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Beijing Sogou Technology Development Co Ltd
Original Assignee
Beijing Sogou Technology Development Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Beijing Sogou Technology Development Co Ltd filed Critical Beijing Sogou Technology Development Co Ltd
Priority to CN201711298752.0A priority Critical patent/CN108255940A/en
Publication of CN108255940A publication Critical patent/CN108255940A/en
Priority to PCT/CN2018/100990 priority patent/WO2019109663A1/en
Pending legal-status Critical Current

Links

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/30Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
    • G06F16/33Querying
    • G06F16/338Presentation of query results
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/30Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
    • G06F16/33Querying
    • G06F16/3331Query processing
    • G06F16/3332Query translation
    • G06F16/3337Translation of the query language, e.g. Chinese to English

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Computational Linguistics (AREA)
  • Data Mining & Analysis (AREA)
  • Databases & Information Systems (AREA)
  • Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Machine Translation (AREA)

Abstract

An embodiment of the present invention provides a kind of cross-language search method and apparatus, a kind of device for cross-language search, method therein specifically includes:Source language search word is translated as object language search term;For the object language search term, its corresponding object language search result and source language translation results are obtained;Wherein, the source language translation results is are translated to obtain to the object language search result;The keyword to match with the object language search term is obtained from the source language translation results;Display is marked to the keyword in the source language translation results.The embodiment of the present invention can improve the coverage rate of the red content of the corresponding source language translation results acceptance of the bid of object language search term, and then can improve the efficiency that information is obtained from the corresponding source language translation results of object language search term.

Description

A kind of cross-language search method and apparatus, a kind of device for cross-language search
Technical field
The present invention relates to information search technique field, more particularly to a kind of cross-language search method and apparatus, Yi Zhongyong In the device of cross-language search.
Background technology
With the continuous growth of internet information, user proposes higher requirement for information search, is no longer satisfied with It is searched in same languages database, and requires to obtain a variety of languages data.For example, search term (query) input by user For " March ", the search in Chinese database can not may farthest meet user demand, the English from American-European website There may be more excellent, more search results in database.
Cross-language search technology combines information retrieval technique and machine translation mothod.Existing cross-language search process tool Body can include:First, source language search word is converted to the search term of object language form by machine translation mothod, so Afterwards, it is examined in corresponding database into row information respectively according to source language search word and the search term of object language form respectively Rope, to obtain multilingual search result, wherein, multilingual search result can include:The search result of source language With object language search result.
In order to meet the need for the limited user of reading ability for not having object language reading ability or object language It asks, existing scheme can translate object language search result, and the source language translation results that translation is obtained are supplied to User.However, in practical applications, user usually requires conscientiously to understand could obtain required pass from source language translation results Key information, this obtains the efficiency of information by user is influenced from source language translation results.
Invention content
In view of the above problems, it is proposed that the embodiment of the present invention overcomes the above problem or at least partly in order to provide one kind Cross-language search method, cross-language search device and the device for cross-language search to solve the above problems, the present invention are implemented Example can improve the corresponding source language translation results of object language search term and get the bid the coverage rate of red content, so can improve from The efficiency of information is obtained in the corresponding source language translation results of object language search term.
To solve the above-mentioned problems, the embodiment of the invention discloses a kind of cross-language search method, including:
Source language search word is translated as object language search term;
For the object language search term, its corresponding object language search result and source language translation results are obtained; Wherein, the source language translation results is are translated to obtain to the object language search result;
The keyword to match with the object language search term is obtained from the source language translation results;
Display is marked to the keyword in the source language translation results.
On the other hand, the embodiment of the invention discloses a kind of cross-language search device, including:
Search term translation module, for source language search word to be translated as object language search term;
As a result acquisition module for being directed to the object language search term, obtains its corresponding object language search result And source language translation results;Wherein, the source language translation results is are translated to obtain to the object language search result;
Keyword acquisition module, for being obtained and the object language search term phase from the source language translation results The keyword matched;And
Display module is marked, for display to be marked to the keyword in the source language translation results.
Optionally, the keyword acquisition module includes:
Map setting up submodule, for establish target language vocabulary that the object language search result includes with it is described Mapping relations between the original language vocabulary that source language translation results include;And
Map Searching submodule, for according to the object language search term, being searched in the mapping relations, with Obtain keyword that the source language translation results include, matching with the object language search term.
Optionally, the label display module, if specifically between the keyword and the source language search word Matching degree meets preset matching degree condition, then display is marked to the keyword in the source language translation results.
Optionally, described device further includes:
Judgment module, for being obtained from the source language translation results and the target in the keyword acquisition module Before the keyword that language search word matches, judge whether the source language translation results include the source language search word, If the source language translation results do not include the source language search word, the keyword acquisition module is triggered from the source language The keyword to match with the object language search term is obtained in speech translation result.
Optionally, described device further includes:
Second label display module, if including the source language search word for the source language translation results, to institute Display is marked in the source language search word stated in source language translation results.
Optionally, described device further includes:
Translation result acquisition module, for obtaining corresponding at least two translation result of the object language search term;
Third mark display module, for in the source language translation results, it is corresponding with the object language search term The content that matches of at least two translation results display is marked.
Optionally, the source language translation results acquisition submodule includes:
Screening unit, for carrying out the translation from object language to original language to the object language search term, from translation Screening obtains the translation result of at least two original language in obtained result;
Wherein, the screening unit includes:
First screening subelement, for confidence level being selected to meet preset confidence level condition from described translate in obtained result At least two original language translation result;Alternatively,
Second screening subelement, for the part of speech according to the source language search word, from the result translated and obtained Screening obtains at least two translation results.
In another aspect, the embodiment of the invention discloses a kind of device for cross-language search, include memory and One either more than one program one of them or more than one program be stored in memory, and be configured to by one A or more than one processor performs the one or more programs and includes the instruction for being operated below:
Source language search word is translated as object language search term;
For the object language search term, its corresponding object language search result and source language translation results are obtained; Wherein, the source language translation results is are translated to obtain to the object language search result;
The keyword to match with the object language search term is obtained from the source language translation results;
Display is marked to the keyword in the source language translation results.
Another aspect, the embodiment of the invention discloses one or more machine readable medias, are stored thereon with instruction, when by When one or more processors perform so that device performs the cross-language search method described in aforementioned one or more.
The embodiment of the present invention includes advantages below:
The embodiment of the present invention obtains the keyword to match with object language search term from source language translation results, and right Display is marked in the keyword in the source language translation results, can improve the corresponding source language of object language search term It says the coverage rate of the red content of translation result acceptance of the bid, and then source language translation results corresponding from object language search term can be improved The middle efficiency for obtaining information.
Description of the drawings
Fig. 1 is a kind of schematic diagram of the application environment of cross-language search method of the present invention;
Fig. 2 is a kind of step flow chart of cross-language search embodiment of the method one of the present invention;
Fig. 3 is a kind of step flow chart of cross-language search embodiment of the method two of the present invention;
Fig. 4 is a kind of step flow chart of cross-language search embodiment of the method three of the present invention;
Fig. 5 is a kind of step flow chart of cross-language search embodiment of the method four of the present invention;
Fig. 6 is a kind of structure diagram of cross-language search device embodiment of the present invention;
Fig. 7 be the present invention a kind of device 900 for cross-language search as terminal when block diagram;And
Fig. 8 be the present invention a kind of device for cross-language search as server when structure diagram.
Specific embodiment
In order to make the foregoing objectives, features and advantages of the present invention clearer and more comprehensible, it is below in conjunction with the accompanying drawings and specific real Applying mode, the present invention is described in further detail.
Inventor has found that existing scheme can turn over object language search result during the embodiment of the present invention is implemented Translate original language, and in the source language translation results obtained to translation, the content identical with source language search word it is red into rower.Example Such as, if source language search word is " Donald Trump ", corresponding object language search term is " Trump ", then can be corresponding by " Trump " Source language translation results in " Donald Trump " that occurs it is red into rower, it is possible thereby to make user's quick obtaining source language translation As a result the key message included, and then user can be made quickly to judge whether certain source language translation results meet the letter of itself Breath demand.
However, in practical applications, the factors such as translation quality cause original language may be not present in source language translation results Search term;In such cases, will be unable to realize red for the mark of source language translation results so that mark the coverage rate of red content compared with It is low, and then influence the acquisition efficiency of key message that user includes Mr. Yu source language translation results.For example, it is assumed that original language Search term is " March ", it is assumed that " March " corresponding object language search term is " March ", it is assumed that " March " corresponding target language Say that search result includes " March-Wikipedia ", it is assumed that the source language translation obtained for " March-Wikipedia " translation As a result it is " March-wikipedia ", it is seen that there is no source language search word " March " in source language translation results, therefore can not be real It is red referring now to the mark of key message in source language translation results.
For source language translation results in existing scheme get the bid red content coverage rate it is low the technical issues of, the present invention is implemented Example provides a kind of cross-language search scheme, and source language search word can be translated as object language search term by the program;For The object language search term obtains its corresponding object language search result and source language translation results;Wherein, the source language Speech translation result can be that the object language search result is translated to obtain;It is obtained from the source language translation results The keyword to match with the object language search term;And to the keyword in the source language translation results into rower Note display.
The embodiment of the present invention obtains the keyword to match with object language search term from source language translation results, and right Display is marked in the keyword in the source language translation results, can improve the corresponding source language of object language search term It says the coverage rate of the red content of translation result acceptance of the bid, and then source language translation results corresponding from object language search term can be improved The middle efficiency for obtaining information.
In the embodiment of the present invention, the corresponding search result of object language search term can include:Object language search result And source language translation results, wherein, source language translation results can be that the object language search result is translated to obtain, Object language search result and source language translation results can correspond to identical search result (such as identical webpage, video, figure Piece, music etc.), one of difference of the two is the difference of linguistic form.
In a kind of application example of the present invention, it is assumed that source language search word is " March ", it is assumed that " March " corresponding target Language search word is " March ", it is assumed that " March " corresponding object language search result includes " March-Wikipedia ", needle The source language translation results obtained to " March-Wikipedia " translation are " March-wikipedia ", then the embodiment of the present invention can To determine the keyword to match with " March " from " March " corresponding source language translation results " March-wikipedia " " March ", and display is marked to " March " in " March " corresponding source language translation results " March-wikipedia ", It is possible thereby to improve the coverage rate of the red content of source language translation results acceptance of the bid.
The embodiment of the present invention can be applied to search APP (application program, Application), search website (as search is drawn Hold up) etc. have the function of in the platform environment of cross-language search, with improve obtained from the corresponding search result of object language search term It wins the confidence the efficiency of breath.The embodiment of the present invention mainly carries out the cross-language search method of the embodiment of the present invention for searching for APP Illustrate, the corresponding cross-language search method of other platforms such as search website is cross-referenced.
Cross-language search method provided in an embodiment of the present invention can be applied in application environment shown in FIG. 1, such as Fig. 1 institutes Show, client 100 and server 200 are located in wired or wireless network, by the wired or wireless network, client 100 and Server 200 carries out data interaction.
The cross-language search flow of the embodiment of the present invention can be by any or combination in client 100 and server 200 It performs:
For example, client 100 can receive source language search word input by user, and the source language is sent to server 200 Say search term;Source language search word can be translated as object language search by server 200 after the source language search word is received Word obtains the corresponding object language search result of the object language search term, to the object language search result carry out from Object language to original language translation, to obtain source language translation results;And from the source language translation results obtain with The keyword that the object language search term matches;And send above-mentioned source language translation results and above-mentioned pass to client 100 Keyword, so that client 100 shows the source language translation results, and to the keyword in the source language translation results Display is marked.
For another example, client 100 can receive source language search word input by user, and receive the source language search word Afterwards, source language search word is translated as object language search term first, then obtains the corresponding mesh of the object language search term Lingual search results are marked, the translation from object language to original language are then carried out to the object language search result, to obtain Source language translation results;And the key to match with the object language search term is obtained from the source language translation results Word;And then show the source language translation results, and the keyword in the source language translation results is marked aobvious Show.
Wherein, in source language translation results and source language translation results the acquisition process of keyword by server 200 During execution, the abundant advantage of 200 computing resource of server can be played, improves source language translation results and source language translation As a result the acquisition efficiency of middle keyword and acquisition accuracy rate.For example, the calculating that Cloud Server can be deployed with numerous high configurations is set It is standby, therefore the acquisition of keyword in source language translation results and source language translation results is carried out using these computing devices, to carry The acquisition efficiency of keyword and acquisition accuracy rate in high source language translation results and source language translation results;It can save simultaneously The calculation resources of 100 side of client are saved, improve the performance of terminal corresponding to client 100.Certainly, source language translation results and source The acquisition process of keyword can be by any execution in server 200 and client 100 in language translation results, and the present invention is implemented Example is not added with the corresponding specific executive agent of the acquisition process of keyword in source language translation results and source language translation results With limitation.
Optionally, client 100 may operate in terminal, and above-mentioned terminal specifically includes but unlimited:Smart mobile phone, tablet Computer, E-book reader, MP3 (dynamic image expert's compression standard audio level 3, Moving Picture Experts Group Audio Layer III) player, MP4 (dynamic image expert's compression standard audio level 4, Moving Picture Experts Group Audio Layer IV) player, pocket computer on knee, vehicle-mounted computer, desktop computer, machine top Box, intelligent TV set, wearable device etc..
Embodiment of the method one
With reference to Fig. 2, a kind of step flow chart of cross-language search embodiment of the method one of the present invention is shown, it specifically can be with Include the following steps:
Source language search word is translated as object language search term by step 201;
Step 202, for the object language search term, obtain its corresponding object language search result and original language turn over Translate result;Wherein, the source language translation results can be that the object language search result is translated to obtain;
Step 203 obtains the keyword to match with the object language search term from the source language translation results;
Display is marked to the keyword in the source language translation results in step 204.
In the embodiment of the present invention, source language search word can be the search term that user uses original language to input.Actually should In, UI (user interface, User Interface) can be provided by searching for the client of APP or search website, then user can In a manner of by search box, speech interface on the UI etc. source language search word is submitted to client.No matter which kind of user passes through Mode submits source language search word to client, and client can include the source language search word received in search box In, therefore, in the embodiment of the present invention, source language search word input by user can include:User is by any way to client Hold the source language search word submitted.It is appreciated that the embodiment of the present invention obtains the specific of source language search word input by user Mode is taken not limit.
In the embodiment of the present invention, source language and the target language can be used for representing different bilinguals, above-mentioned original language and Object language can be obtained by user is preset, also can by search for APP or search for website by analyze user search behavior and/or Navigation patterns obtain.Optionally, searching for APP or search website can will remove using the most common language of user as original language Used language is as object language except original language.For example, the search behavior of user show user before use search Rope word is Chinese search word, then original language can be determined for Chinese;The navigation patterns of user are also shown that user accessed translation Website, and pass through the translation web site and carried out mutual translational action between Chinese and English, therefore it can determine that object language is English.It is appreciated that the quantity of the object language of the embodiment of the present invention can be one or more, for example, for Chinese For the user of mother tongue, original language can be Chinese, and object language can be in English, Japanese, Korean, German, French A kind of or combination.The embodiment of the present invention is mainly to the embodiment of the present invention by taking original language is Chinese, object language is English as an example Cross-language search method illustrate, the corresponding cross-language search method of other source language and the target language it is cross-referenced i.e. It can.
In practical applications, source language search word can be translated as object language by step 201 by client or server Search term.Optionally, during source language search word is translated as object language search term, a variety of differences may be obtained Translation result, in such cases, a kind of highest translation result of confidence level can be selected from a variety of different translation results As object language search term, it will be understood that the embodiment of the present invention by source language search word for being translated as object language search The detailed process of word does not limit.In a kind of application example of the present invention, if source language search word is " March ", target Language search word can be " March ".In the another kind application example of the present invention, if source language search word is " Disney ", Then object language search term can be " disney ".
In practical applications, step 202 can be according to the object language search term that step 201 obtains, in object language It is retrieved in database, to obtain object language search result.It is appreciated that the embodiment of the present invention searches for object language As a result specific acquisition modes do not limit.
Since the performance of object language search result is object language form in step 202, which is generally this and searches The non-mother language of rope user is the unfamiliar language of search user, this will influence user and letter is obtained from search result The efficiency of breath.The efficiency of information is obtained to improve user from search result, step 202 can search for the object language As a result the translation from object language to original language is carried out, to obtain source language translation results.Wherein, object language search result and Source language translation results can correspond to identical search result (such as identical webpage, video, picture, music), the area of the two One of other difference for being linguistic form.
In practical applications, the acquisition process of source language translation results can include:Using translation model, to the target Lingual search results carry out the translation from object language to original language;Wherein, which can be general in translation field Translation model, or the dedicated translation model of search result, the embodiment of the present invention for specific translation model and The specific translation process carried out from object language to original language to the object language search result does not limit.
It, can be by improving to the object language search result from target language in a kind of alternative embodiment of the present invention It says the translation process of original language, realizes the translation result of object content and the one of source language search word in source language translation results Cause property, in this way, the coverage rate for marking red content can be improved.Correspondingly, the acquisition process of source language translation results can include: During carrying out the translation from object language to original language to the object language search result, the object language is searched for As a result middle object content is translated as the translation result consistent with the source language search word;Wherein, the object content is described The content identical with the object language search term in object language search result.Although for example, target search word " Trump " Translation result can include:" river is general ", " Donald Trump ", " trump ", " good person ", " honest man " etc., however, due to marking red object For the keyword, therefore the embodiment of the present invention can be by improving the translation result of object content and source in source language translation results The consistency of language search word improves the coverage rate for marking red content.If the in this way, corresponding source of object language search term " Trump " Language search word is " Donald Trump ", then can be translated as object language search term " Trump " " Donald Trump ", and by the target All " Trump " that lingual search results include are translated as " Donald Trump ";If alternatively, object language search term " Trump " corresponding source language search word is " river is general ", then can object language search term " Trump " be translated as " river is general ", And all " Trump " that the object language search result includes is translated as " river is general ";It is possible thereby to it is red interior to improve mark The coverage rate of appearance.
Step 203 can obtain the key to match with the object language search term from the source language translation results Word.Wherein, the corresponding linguistic form of keyword can be source language namely the corresponding linguistic form of keyword and original language The corresponding linguistic form of translation result is consistent.
In the embodiment of the present invention, keyword matches with object language search term, can include:The corresponding semanteme of keyword Semanteme corresponding with object language search term matches, alternatively, keyword is to effect and target language caused by original language reader Speech search term matches to effect caused by object language reader.
According to a kind of embodiment, step 203 obtains and the object language search term from the source language translation results The process of the keyword to match can include:The pass to match with the object language search term is obtained according to dictionary for translation Keyword, and the content identical with the keyword is searched from the source language translation results.Wherein, above-mentioned dictionary for translation can be with Corresponding original language vocabulary, the original language word such as provided for target language vocabulary " March " are provided for target language vocabulary Remittance can include:" March ", " March ", " advance " etc., it is possible thereby to be obtained and the target from the source language translation results The keyword that language search word matches.
According to another embodiment, step 203 can be obtained by word alignment technology from the source language translation results The keyword to match with the object language search term.Word alignment refers to the original language vocabulary and target language in bilingual sentence pair Words, which converge, to be corresponded to.For example, bilingual sentence pair is " I plays in classroom and play ", " I play game in the classroom ", word Alignment techniques can by " I ", " ", " classroom ", " object for appreciation ", " game " respectively with " I ", " in ", " classroom ", " play ", " game " is mapped.It is closed since above-mentioned word alignment technology considers in bilingual sentence the alignment between the vocabulary pair of translation each other System, therefore the accuracy rate of keyword can be improved.
Above by word alignment technology, obtained and the object language search term phase from the source language translation results The process for the keyword matched can include:Establish target language vocabulary that the object language search result includes with it is described Mapping relations between the original language vocabulary that source language translation results include;According to the object language search term, reflected described Penetrate in relationship and searched, with obtain it is that the source language translation results include, match with the object language search term Keyword.
Wherein it is possible to by word alignment technology, the target language vocabulary that the object language search result includes is established Mapping relations between the original language vocabulary included with the source language translation results specifically, can obtain object language and search The bilingual sentence that hitch fruit and source language translation results include, and the target language vocabulary of translation and the source language each other in bilingual sentence Words establish mapping relations between converging.
In practical applications, word alignment model can be utilized, establishes the target that the object language search result includes Mapping relations between the original language vocabulary that language vocabulary and the source language translation results include.Wherein it is possible to using bilingual Alignment language material trains to obtain above-mentioned word alignment model, so that the word alignment model includes to determine in bilingual sentence translation each other The statistical information of vocabulary pair, due to the relevant technologies that word alignment model is this field, therefore not to repeat here.
In a kind of application example of the embodiment of the present invention, it is assumed that source language search word is " March ", it is assumed that " March " is corresponding Object language search term be " March ", it is assumed that " March " corresponding object language search result include " March- Wikipedia ", it is assumed that obtained for " March-Wikipedia " translation, " March " corresponding source language translation results packet " March-wikipedia " is included, then word alignment model may be used in the embodiment of the present invention, to object language search result and original language The corresponding bilingual sentence of translation result is aligned, for example, for bilingual sentence " March-Wikipedia " and " March-Wiki hundred " March ", " Wikipedia " can be mapped, thus, it is possible to obtain source by section " with " March ", " wikipedia " respectively The keyword " March " to match with " March " that language translation results " March-wikipedia " include.
It is appreciated that it is obtained above by dictionary for translation or by word alignment technology, from the source language translation results The process of keyword to match with the object language search term is taken to be intended only as alternative embodiment, actually art technology Personnel can obtain and the object language search term phase according to practical application request using from the source language translation results Other processes of matched keyword, such as the attention mechanism of neural network machine translation model can be utilized, judge target Language search word has been translated into which word of source language, etc., wherein, attention mechanism is one limited for distributing Information processing capability selection mechanism, attention refers to, is selectively absorbed in certain information experienced, these information May be either objectively or subjectively, while to ignore the other information that synchronization receives, this cognitive process.The embodiment of the present invention For obtaining the detailed process of keyword to match with the object language search term from the source language translation results not It limits.
In practical applications, the corresponding content that shows of source language translation results can include:Title, abstract, promotional content Etc. contents, the then keyword that step 204 corresponding to the source language translation results can show in content be marked Display.For example, displaying can be marked to the keyword that title or abstract include, alternatively, can be in popularization Displaying is marked in the keyword that appearance includes.
It is alternatively possible to font or color by marking the keyword, display is marked to the keyword; For example, can by the font-weight of the keyword, underline, tilt, three-dimensional, be set as red etc., this is relative to normal The identification for showing content, the keyword being improved of font or normal color.Alternatively, showing the keyword Meanwhile the mark of the displaying keyword.For example, correspondence can be showed in positions such as subscript, the subscripts of the keyword Icon etc., it will be understood that the embodiment of the present invention does not limit specific marker-display process.
It in some embodiments of the invention, can be using the corresponding search result of the object language search term as first Search result, can also obtain corresponding second search result of source language search word, and by object language form and/or original language First search result of form mix showing with the second search result;It is possible thereby to it provides a user from multilingual number According to the search result in library.It is alternatively possible to retrieved in the database of original language, it is corresponding to obtain source language search word Second search result.
To sum up, the cross-language search method of the embodiment of the present invention is obtained from source language translation results and is searched with object language The keyword that rope word matches, and display is marked to the keyword in the source language translation results, it can improve The coverage rate of the red content of the corresponding source language translation results acceptance of the bid of object language search term, and then can improve and be searched from object language The efficiency of information is obtained in the corresponding source language translation results of rope word.
Embodiment of the method two
With reference to Fig. 3, a kind of step flow chart of cross-language search embodiment of the method two of the present invention is shown, it specifically can be with Include the following steps:
Source language search word is translated as object language search term by step 301;
Step 302, for the object language search term, obtain its corresponding object language search result and original language turn over Translate result;Wherein, the source language translation results can be that the object language search result is translated to obtain;
Step 303 obtains the keyword to match with the object language search term from the source language translation results;
If the matching degree between step 304, the keyword and the source language search word meets preset matching degree condition, Display then is marked to the keyword in the source language translation results.
Relative to embodiment of the method one shown in Fig. 2, in the source language translation results in embodiment of the method two shown in Fig. 3 The keyword process of display is marked can include:If between the keyword and the source language search word Meet preset matching degree condition with degree, then display is marked to the keyword in the source language translation results.Due to The matching degree between the keyword of display and the source language search word is marked to meet preset matching degree condition, therefore mark can be improved Remember being associated with, and then the keyword that can show label is more in line with user between the keyword of display and source language search word Information requirement.
In the embodiment of the present invention, the matching degree between the keyword and the source language search word can include:It is described Similarity between keyword and the source language search word etc., preset matching degree condition can include:Similarity is more than similar Spend threshold value.In practical applications, corresponding first term vector of the keyword and the source language search can be determined respectively Then corresponding second term vector of word, by measuring similarities such as Euclidean distance, included angle cosines, calculates the first term vector and the Similarity between two term vectors.
Certainly, above-mentioned similarity is intended only as a kind of alternative embodiment of matching degree, in fact, those skilled in the art can With according to practical application request, using other matching degrees, such as semantic relevancy, the embodiment of the present invention is for specific matching degree It does not limit.
It, can be to keyword " March " and source language search word " March " in a kind of application example of the embodiment of the present invention Matching degree judgement is carried out, it, can be to the keyword in source language translation results if the matching degree meets preset matching degree condition Display is marked in " March ".
Can be " Disney " and source language search word to keyword in the another kind application example of the embodiment of the present invention " Disney " carries out matching degree judgement, can be in source language translation results if the matching degree meets preset matching degree condition Keyword " Disney " display is marked.
It is appreciated that in other embodiments of the invention, if between the keyword and the source language search word Matching degree does not meet preset matching degree condition, then the keyword in the source language translation results can not be marked It has been shown that, display is labeled to avoid the relatively low keyword that is associated between source language search word.
Embodiment of the method three
With reference to Fig. 4, a kind of step flow chart of cross-language search embodiment of the method three of the present invention is shown, it specifically can be with Include the following steps:
Source language search word is translated as object language search term by step 401;
Step 402, for the object language search term, obtain its corresponding object language search result and original language turn over Translate result;Wherein, the source language translation results can be that the object language search result is translated to obtain;
Step 403 judges whether the source language translation results include the source language search word;
If step 404, the source language translation results do not include the source language search word, from the source language translation As a result the keyword that middle acquisition matches with the object language search term;
Display is marked to the keyword in the source language translation results in step 405.
Relative to embodiment of the method one shown in Fig. 2, embodiment of the method three shown in Fig. 4 is from the source language translation results Before the keyword that acquisition matches with the object language search term, it can be determined that whether the source language translation results include The source language search word matches if it is not, then being obtained from the source language translation results with the object language search term Keyword, and display is marked to the keyword in the source language translation results;It is possible thereby to it is turned in original language It translates in result there is no in the case of source language search word, realizes red for the mark of source language translation results.
It is appreciated that it is above-mentioned in the case where the source language translation results do not include the source language search word, from institute The keyword for obtaining in source language translation results and matching with the object language search term is stated, is intended only as alternative embodiment, In fact, the embodiment of the present invention from the source language translation results for " obtaining and matching with the object language search term Keyword " corresponding execution condition do not limit.For example, include the source language search in the source language translation results In the case of word, the key to match with the object language search term can also be obtained from the source language translation results Word, it is possible thereby to be marked while realizing source language search word and keyword in source language translation results red.Correspondingly, the present invention is real The method for applying example can also include:If the source language translation results include the source language search word, to the original language Display is marked in the source language search word in translation result.
Embodiment of the method four
With reference to Fig. 5, a kind of step flow chart of cross-language search embodiment of the method four of the present invention is shown, it specifically can be with Include the following steps:
Source language search word is translated as object language search term by step 501;
Step 502, for the object language search term, obtain its corresponding object language search result and original language turn over Translate result;Wherein, the source language translation results can be that the object language search result is translated to obtain;
Step 503 obtains the keyword to match with the object language search term from the source language translation results;
Display is marked to the keyword in the source language translation results in step 504;
Relative to embodiment of the method one shown in Fig. 2, embodiment of the method four shown in Fig. 5 can also include:
Step 505 obtains corresponding at least two translation result of the object language search term;
Step 506, in the source language translation results, it is corresponding with the object language search term at least two translation As a result display is marked in the content to match.
Since source language translation results is are translated to obtain to the object language search result, therefore source language translation knot Fruit often have a variety of possibilities, if in this way, only by the content in source language translation results, identical with source language search word into Rower is red, then causes the coverage rate for marking red content relatively low.For example, the content " Trump " included for object language search result For, source language translation results may include:A variety of translations such as " Donald Trump ", " river is general " are possible, if source language search word is " Donald Trump " is then merely capable of realizing that a kind of this possible mark of translation is red for " Donald Trump ", and can not realize for " river is general " It is red Deng the possible mark of other translations, therefore cause the coverage rate for marking red content relatively low.
For the red content of above-mentioned mark coverage rate it is low the technical issues of, the embodiment of the present invention can obtain object language search At least two corresponding translation results of word, and in the source language translation results, it is corresponding with the object language search term The content that matches of at least two translation results display is marked.Since at least two translation results can reflect target language Say search term to original language at least two translation possibility, therefore the embodiment of the present invention can be realized by source language translation results to Few possible mark of two kinds of translations is red, therefore can improve the coverage rate of the red content of source language translation results acceptance of the bid, and then can carry Height obtains the efficiency of information from the corresponding search result of object language search term.
In a kind of application example of the present invention, if source language search word is " Donald Trump ", corresponding object language search Word is " Trump ", and for content that the corresponding object language search result of object language search term " Trump " includes For " Trump ", corresponding source language translation results may include:A variety of translations such as " Donald Trump ", " river is general " are possible, then originally Inventive embodiments can obtain " Donald Trump ", " river is general " etc. at least two and translate possibility, and pass through source language translation results and realize The possible mark of at least two translations is red, therefore can improve the coverage rate for marking red content.
For obtaining corresponding at least two translation result of the object language search term, the embodiment of the present invention can provide Following acquisition scheme:
Acquisition scheme 1
Acquisition scheme 1 can carry out the object language search term translation from object language to original language, from translation Screening obtains the translation result of at least two original language in obtained result.It is alternatively possible to using translation model by target language Speech search term is translated as multiple translation results, and screening obtains therein at least two from the result that translation obtains.
In a kind of alternative embodiment of the present invention, screened in the above-mentioned result obtained from translation and obtain at least two source languages The translation result of speech can specifically include:Selection confidence level meets preset confidence level condition from the result translated and obtained At least two original language translation result.Multiple translation results are obtained for example, can be translated according to " Trump ":" river is general ", " Donald Trump ", " trump ", " good person ", " honest man ", " means ", " surmounting " etc., and for " Trump " corresponding multiple translation knots Fruit, at least two translation results for selecting confidence level higher, such as " river is general ", " Donald Trump ".Optionally, source language translation results Confidence level can be object language search term to the translation probability of source language translation results, which can be by translation model It is calculated, it will be understood that the embodiment of the present invention does not limit the confidence level and its acquisition modes of source language translation results System.
In another alternative embodiment of the present invention, screened in the above-mentioned result obtained from translation and obtain at least two sources The translation result of language can specifically include:According to the part of speech of the source language search word, from the result translated and obtained Screening obtains at least two translation results.By taking " Trump " corresponding translation result as an example, wherein can include:Noun " river is general ", " Donald Trump ", " trump ", " good person ", " honest man ", " means " and verb " surmounting " etc., this alternative embodiment can foundation The part of speech of source language search word screens at least two translation results, consistent with the part of speech of source language search word to obtain Translation result, therefore the accuracy of translation result can be improved.For example, source language search word is " Donald Trump ", original language is searched The part of speech of rope word is " noun " or " proper noun ", then can filter out verb " surmounting " according to " noun ";Alternatively, can be with According to " proper noun ", verb " surmounting " and non-proprietary noun " trump ", " good person ", " honest man ", " means " are filtered out.
Acquisition scheme 2
Acquisition scheme 2 can carry out the object language search result translation process from object language to original language In, the corresponding translation result of object content in the object language search result is recorded, to obtain the target language Say corresponding at least two translation result of search term;Wherein, the object content in the object language search result with institute State the identical content of object language search term.
In practical applications, the factors such as the background of object language search result, context lead to object language search result In same content different translation results can be corresponded in different background and context, for example, " Apple " can be translated into " fruit " can also be translated into " iPhone ", can also be translated into " bomb " etc..
In order to obtain the corresponding translation result of object content in object language search result, obtaining scheme 2 can be right The object language search result is carried out in the translation process from object language to original language, to the target in described search result The corresponding translation result of content is recorded;Due to the object content in the object language search result with the target language It says the identical content of search term, therefore, after the completion of translation, object language search term pair can be obtained from the record content At least two translation results answered.By taking object language search term " Trump " as an example, corresponding object content is also " Trump ", can What is translated into, such as corresponding different with " Trump " that is included by translation model record object language search result Linguistic context or context may be translated for " Donald Trump ", " river is general " or " trump " etc., the occurred translation of record As a result, to obtain corresponding at least two translation result of the object language search term.Optionally, it is above-mentioned, to described search knot The corresponding translation result of object content, which carries out record, in fruit to include:To object content, each corresponding translation result carries out Record, alternatively, the corresponding current translation result of object content is compared with the translation result recorded, if it is different, then carrying out Record, if identical, does not record.
It is turned over above by acquisition scheme 1 with acquisition scheme 2 to obtaining the object language search term corresponding at least two The process for translating result is described in detail, it will be understood that those skilled in the art can be according to practical application request, using obtaining Any or combination in scheme 1 and acquisition scheme 2 is taken, alternatively, other acquisition schemes can also be used, it will be understood that this hair Bright embodiment is not limited for obtaining the detailed process of corresponding at least two translation result of the object language search term.
To sum up, the cross-language search method of the embodiment of the present invention can carry out from target language object language search result The translation of original language is sayed, to obtain source language translation results, and to being searched in the source language translation results, with object language Display is marked in the content that at least two translation results corresponding to word match;Since above-mentioned at least two translation result can be with At least two translations for reflecting object language search term to original language are possible, therefore the embodiment of the present invention can pass through source language translation As a result realize at least two translation it is possible mark it is red, therefore can not only realize in source language translation results with source language search The mark of the identical content of word is red, moreover it is possible to realize in source language translation results from source language search word related content (form is different, but Corresponding object language translation result is identical) mark it is red, so as to improve the source language translation results of source language acceptance of the bid The coverage rate of red content, and then the efficiency that user obtains information from source language translation results can be improved.
It should be noted that for embodiment of the method, in order to be briefly described, therefore it is dynamic that it is all expressed as to a series of movement It combines, but those skilled in the art should know, the embodiment of the present invention is not limited by described athletic performance sequence System, because of embodiment according to the present invention, certain steps may be used other sequences or be carried out at the same time.Secondly, art technology Personnel should also know that embodiment described in this description belongs to preferred embodiment, and involved athletic performance simultaneously differs Surely necessary to being the embodiment of the present invention.
Device embodiment
With reference to Fig. 6, show a kind of structure diagram of cross-language search device embodiment of the present invention, can specifically wrap It includes:Search term translation module 601, result acquisition module 602, keyword acquisition module 603 and label display module 603.
Wherein, search term translation module 601, for source language search word to be translated as object language search term;
As a result acquisition module 602 for being directed to the object language search term, obtain its corresponding object language search knot Fruit and source language translation results;Wherein, the source language translation results is to the object language search result translate It arrives;
Keyword acquisition module 603, for being obtained and the object language search term from the source language translation results The keyword to match;
Display module 604 is marked, for display to be marked to the keyword in the source language translation results.
Optionally, the keyword acquisition module 603 can include:
Map setting up submodule, for establish the target language vocabulary that can include in the object language search result with Mapping relations between the original language vocabulary that the source language translation results can include;And
Map Searching submodule, for according to the object language search term, being searched in the mapping relations, with Obtain keyword that the source language translation results can include, matching with the object language search term.
Optionally, the label display module 604, if specifically between the keyword and the source language search word Matching degree meet preset matching degree condition, then display is marked to the keyword in the source language translation results.
Optionally, described device can also include:
Judgment module, for being obtained from the source language translation results and the target in the keyword acquisition module Before the keyword that language search word matches, judge whether the source language translation results can include the source language search Word, if the source language translation results cannot include the source language search word, trigger the keyword acquisition module from The keyword to match with the object language search term is obtained in the source language translation results.
Optionally, described device can also include:
Second label display module, if the source language search word can be included for the source language translation results, Display is marked to the source language search word in the source language translation results.
Optionally, described device can also include:
Translation result acquisition module, for obtaining corresponding at least two translation result of the object language search term;
Third mark display module, for in the source language translation results, it is corresponding with the object language search term The content that matches of at least two translation results display is marked.
Optionally, the source language translation results acquisition submodule can include:
Screening unit, for carrying out the translation from object language to original language to the object language search term, from translation Screening obtains the translation result of at least two original language in obtained result;
Wherein, the screening unit can include:
First screening subelement, for confidence level being selected to meet preset confidence level condition from described translate in obtained result At least two original language translation result;Alternatively,
Second screening subelement, for the part of speech according to the source language search word, from the result translated and obtained Screening obtains at least two translation results.
For device embodiment, since it is basicly similar to embodiment of the method, so description is fairly simple, it is related Part illustrates referring to the part of embodiment of the method.
Each embodiment in this specification is described by the way of progressive, the highlights of each of the examples are with The difference of other embodiment, just to refer each other for identical similar part between each embodiment.
About the device in above-described embodiment, wherein modules perform the concrete mode of operation in related this method Embodiment in be described in detail, explanation will be not set forth in detail herein.
The embodiment of the invention discloses a kind of device for cross-language search, include memory and one or More than one program, either more than one program is stored in memory and is configured to by one or one for one of them A Yi Shang processor performs the one or more programs and includes the instruction for being operated below:Original language is searched Rope word is translated as object language search term;For the object language search term, its corresponding object language search result is obtained And source language translation results;Wherein, the source language translation results is are translated to obtain to the object language search result; The keyword to match with the object language search term is obtained from the source language translation results;To the source language translation As a result display is marked in the keyword in.
Optionally, it is described that the key to match with the object language search term is obtained from the source language translation results Word, including:
The target language vocabulary that the object language search result includes is established with the source language translation results to include Original language vocabulary between mapping relations;
It according to the object language search term, is searched in the mapping relations, to obtain the source language translation As a result keyword including, matching with the object language search term.
Optionally, display is marked in the keyword in the source language translation results, including:
If the matching degree between the keyword and the source language search word meets preset matching degree condition, to described Display is marked in the keyword in source language translation results.
Optionally, described device be also configured to by one either more than one processor perform it is one or one Procedure above includes the instruction for being operated below:
It is described obtained from the source language translation results keyword that matches with the object language search term it Before, judge whether the source language translation results include the source language search word;
If the source language translation results do not include the source language search word, perform described from the source language translation As a result the step of keyword that middle acquisition matches with the object language search term.
Optionally, described device be also configured to by one either more than one processor perform it is one or one Procedure above includes the instruction for being operated below:
If the source language translation results include the source language search word, to the institute in the source language translation results It states source language search word and display is marked.
Optionally, described device be also configured to by one either more than one processor perform it is one or one Procedure above includes the instruction for being operated below:
Obtain corresponding at least two translation result of the object language search term;
To in the source language translation results, at least two translation results phase corresponding with the object language search term Display is marked in the content matched.
Optionally, it is described to obtain corresponding at least two translation result of the object language search term, including:
Translation from object language to original language is carried out to the object language search term, is sieved in the result obtained from translation Choosing obtains the translation result of at least two original language;
Wherein, screening obtains the translation results of at least two original language and includes in the obtained result from translation:
Selection confidence level meets at least two original language of preset confidence level condition from the result translated and obtained Translation result;Alternatively,
According to the part of speech of the source language search word, screened from the result translated and obtained and obtain at least two translations As a result.
Fig. 7 be according to a kind of device 900 for cross-language search shown in an exemplary embodiment as terminal when Block diagram.For example, device 900 can be mobile phone, and computer, digital broadcast terminal, messaging devices, game console, Tablet device, Medical Devices, body-building equipment, personal digital assistant etc..
With reference to Fig. 7, device 900 can include following one or more components:Processing component 902, memory 904, power supply Component 906, multimedia component 908, audio component 910, the interface 912 of input/output (I/O), sensor module 914 and Communication component 916.
The integrated operation of 902 usual control device 900 of processing component, such as with display, call, data communication, phase Machine operates and record operates associated operation.Processing element 902 can refer to including one or more processors 920 to perform It enables, to perform all or part of the steps of the methods described above.In addition, processing component 902 can include one or more modules, just Interaction between processing component 902 and other assemblies.For example, processing component 902 can include multi-media module, it is more to facilitate Interaction between media component 908 and processing component 902.
Memory 904 is configured as storing various types of data to support the operation in equipment 900.These data are shown Example includes the instruction of any application program or method for being operated on device 900, contact data, and telephone book data disappears Breath, picture, video etc..Memory 904 can be by any kind of volatibility or non-volatile memory device or their group It closes and realizes, such as static RAM (SRAM), electrically erasable programmable read-only memory (EEPROM) is erasable to compile Journey read-only memory (EPROM), programmable read only memory (PROM), read-only memory (ROM), magnetic memory, flash Device, disk or CD.
Power supply module 906 provides electric power for the various assemblies of device 900.Power supply module 906 can include power management system System, one or more power supplys and other generate, manage and distribute electric power associated component with for device 900.
Multimedia component 908 is included in the screen of one output interface of offer between described device 900 and user.One In a little embodiments, screen can include liquid crystal display (LCD) and touch panel (TP).If screen includes touch panel, screen Curtain may be implemented as touch screen, to receive input signal from the user.Touch panel includes one or more touch sensings Device is to sense the gesture on touch, slide, and touch panel.The touch sensor can not only sense touch or sliding motion The boundary of action, but also detect duration and pressure associated with the touch or slide operation.In some embodiments, Multimedia component 908 includes a front camera and/or rear camera.When equipment 900 is in operation mode, mould is such as shot When formula or video mode, front camera and/or rear camera can receive external multi-medium data.Each preposition camera shooting Head and rear camera can be a fixed optical lens system or have focusing and optical zoom capabilities.
Audio component 910 is configured as output and/or input audio signal.For example, audio component 910 includes a Mike Wind (MIC), when device 900 is in operation mode, during such as call model, logging mode and speech recognition mode, microphone by with It is set to reception external audio signal.The received audio signal can be further stored in memory 904 or via communication set Part 916 is sent.In some embodiments, audio component 910 further includes a loud speaker, for exports audio signal.
I/O interfaces 912 provide interface between processing component 902 and peripheral interface module, and above-mentioned peripheral interface module can To be keyboard, click wheel, button etc..These buttons may include but be not limited to:Home button, volume button, start button and lock Determine button.
Sensor module 914 includes one or more sensors, and the state for providing various aspects for device 900 is commented Estimate.For example, sensor module 914 can detect opening/closed state of equipment 900, and the relative positioning of component, for example, it is described Component is the display and keypad of device 900, and sensor module 914 can be with 900 1 components of detection device 900 or device Position change, the existence or non-existence that user contacts with device 900,900 orientation of device or acceleration/deceleration and device 900 Temperature change.Sensor module 914 can include proximity sensor, be configured to detect without any physical contact Presence of nearby objects.Sensor module 914 can also include optical sensor, such as CMOS or ccd image sensor, for into As being used in application.In some embodiments, which can also include acceleration transducer, gyro sensors Device, Magnetic Sensor, pressure sensor or temperature sensor.
Communication component 916 is configured to facilitate the communication of wired or wireless way between device 900 and other equipment.Device 900 can access the wireless network based on communication standard, such as WiFi, 2G or 3G or combination thereof.In an exemplary implementation In example, communication component 916 receives broadcast singal or broadcast related information from external broadcasting management system via broadcast channel. In one exemplary embodiment, the communication component 916 further includes near-field communication (NFC) module, to promote short range communication.Example Such as, NFC module can be based on radio frequency identification (RFID) technology, Infrared Data Association (IrDA) technology, ultra wide band (UWB) technology, Bluetooth (BT) technology and other technologies are realized.
In the exemplary embodiment, device 900 can be believed by one or more application application-specific integrated circuit (ASIC), number Number processor (DSP), digital signal processing appts (DSPD), programmable logic device (PLD), field programmable gate array (FPGA), controller, microcontroller, microprocessor or other electronic components are realized, for performing the above method.
In the exemplary embodiment, a kind of non-transitorycomputer readable storage medium including instructing, example are additionally provided Such as include the memory 904 of instruction, above-metioned instruction can be performed to complete the above method by the processor 920 of device 900.For example, The non-transitorycomputer readable storage medium can be ROM, random access memory (RAM), CD-ROM, tape, floppy disk With optical data storage devices etc..
Fig. 8 be according to a kind of device for cross-language search shown in an exemplary embodiment as server when frame Figure.The server 1900 can generate bigger difference due to configuration or different performance, can include in one or more Central processor (central processing units, CPU) 1922 (for example, one or more processors) and memory 1932, one or more storage application programs 1942 or data 1944 storage medium 1930 (such as one or one with Upper mass memory unit).Wherein, memory 1932 and storage medium 1930 can be of short duration storage or persistent storage.It is stored in The program of storage medium 1930 can include one or more modules (diagram does not mark), and each module can be included to clothes The series of instructions operation being engaged in device.Further, central processing unit 1922 could be provided as communicating with storage medium 1930, The series of instructions operation in storage medium 1930 is performed on server 1900.
Server 1900 can also include one or more power supplys 1926, one or more wired or wireless nets Network interface 1950, one or more input/output interfaces 1958, one or more keyboards 1956 and/or, one or More than one operating system 1941, such as Windows ServerTM, Mac OS XTM, UnixTM, LinuxTM, FreeBSDTM Etc..
A kind of non-transitorycomputer readable storage medium, when the instruction in the storage medium is by device (terminal or clothes Be engaged in device) processor perform when so that terminal is able to carry out a kind of cross-language search method, the method includes:By original language Search term is translated as object language search term;For the object language search term, its corresponding object language search knot is obtained Fruit and source language translation results;Wherein, the source language translation results is to the object language search result translate It arrives;The keyword to match with the object language search term is obtained from the source language translation results;To the original language Display is marked in the keyword in translation result.
Those skilled in the art will readily occur to the present invention its after considering specification and putting into practice invention disclosed herein Its embodiment.The present invention is directed to cover the present invention any variations, uses, or adaptations, these modifications, purposes or Person's adaptive change follows the general principle of the present invention and including the undocumented common knowledge in the art of the disclosure Or conventional techniques.Description and embodiments are considered only as illustratively, and true scope and spirit of the invention are by following Claim is pointed out.
It should be understood that the invention is not limited in the precision architecture for being described above and being shown in the drawings, and And various modifications and changes may be made without departing from the scope thereof.The scope of the present invention is only limited by appended claim
The foregoing is merely presently preferred embodiments of the present invention, is not intended to limit the invention, it is all the present invention spirit and Within principle, any modification, equivalent replacement, improvement and so on should all be included in the protection scope of the present invention.
Above to a kind of cross-language search method provided by the present invention, a kind of cross-language search device and it is a kind of be used for across The device of language search, is described in detail, specific case used herein to the principle of the present invention and embodiment into Elaboration is gone, the explanation of above example is only intended to facilitate the understanding of the method and its core concept of the invention;Meanwhile for this The those skilled in the art in field, thought according to the present invention, there will be changes in specific embodiments and applications, In conclusion the content of the present specification should not be construed as limiting the invention.

Claims (10)

  1. A kind of 1. cross-language search method, which is characterized in that including:
    Source language search word is translated as object language search term;
    For the object language search term, its corresponding object language search result and source language translation results are obtained;Wherein, The source language translation results is are translated to obtain to the object language search result;
    The keyword to match with the object language search term is obtained from the source language translation results;
    Display is marked to the keyword in the source language translation results.
  2. 2. according to the method described in claim 1, it is characterized in that, it is described from the source language translation results obtain with it is described The keyword that object language search term matches, including:
    Establish the source that the target language vocabulary that the object language search result includes includes with the source language translation results Mapping relations between language vocabulary;
    It according to the object language search term, is searched in the mapping relations, to obtain the source language translation results Including, the keyword that matches with the object language search term.
  3. 3. method according to claim 1 or 2, which is characterized in that described to described in the source language translation results Display is marked in keyword, including:
    If the matching degree between the keyword and the source language search word meets preset matching degree condition, to the source language Display is marked in the keyword in speech translation result.
  4. 4. method according to claim 1 or 2, which is characterized in that obtained from the source language translation results described Before the keyword to match with the object language search term, the method further includes:
    Judge whether the source language translation results include the source language search word;
    If the source language translation results do not include the source language search word, perform described from the source language translation results The step of keyword that middle acquisition matches with the object language search term.
  5. 5. method according to claim 1 or 2, which is characterized in that the method further includes:
    If the source language translation results include the source language search word, to the source in the source language translation results Display is marked in language search word.
  6. 6. method according to claim 1 or 2, which is characterized in that the method further includes:
    Obtain corresponding at least two translation result of the object language search term;
    To in the source language translation results, at least two translation result corresponding with the object language search term matches Display is marked in content.
  7. 7. according to the method described in claim 6, it is characterized in that, the acquisition object language search term is corresponding at least Two kinds of translation results, including:
    Translation from object language to original language is carried out to the object language search term, is screened in the result obtained from translation To the translation result of at least two original language;
    Wherein, screening obtains the translation results of at least two original language and includes in the obtained result from translation:
    Selection confidence level meets the translation of at least two original language of preset confidence level condition from the result translated and obtained As a result;Alternatively,
    According to the part of speech of the source language search word, screened from the result translated and obtained and obtain at least two translation knots Fruit.
  8. 8. a kind of cross-language search device, which is characterized in that including:
    Search term translation module, for source language search word to be translated as object language search term;
    As a result acquisition module for being directed to the object language search term, obtains its corresponding object language search result and source Language translation results;Wherein, the source language translation results is are translated to obtain to the object language search result;
    Keyword acquisition module, for obtaining what is matched with the object language search term from the source language translation results Keyword;And
    Display module is marked, for display to be marked to the keyword in the source language translation results.
  9. 9. a kind of device for cross-language search, which is characterized in that include memory and one or more than one Program, either more than one program is stored in memory and is configured to by one or more than one processing for one of them Device performs the one or more programs and includes the instruction for being operated below:
    Source language search word is translated as object language search term;
    For the object language search term, its corresponding object language search result and source language translation results are obtained;Wherein, The source language translation results is are translated to obtain to the object language search result;
    The keyword to match with the object language search term is obtained from the source language translation results;
    Display is marked to the keyword in the source language translation results.
  10. 10. one or more machine readable medias, are stored thereon with instruction, when executed by one or more processors so that Device performs the cross-language search method as described in one or more in claim 1 to 7.
CN201711298752.0A 2017-12-08 2017-12-08 A kind of cross-language search method and apparatus, a kind of device for cross-language search Pending CN108255940A (en)

Priority Applications (2)

Application Number Priority Date Filing Date Title
CN201711298752.0A CN108255940A (en) 2017-12-08 2017-12-08 A kind of cross-language search method and apparatus, a kind of device for cross-language search
PCT/CN2018/100990 WO2019109663A1 (en) 2017-12-08 2018-08-17 Cross-language search method and apparatus, and apparatus for cross-language search

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201711298752.0A CN108255940A (en) 2017-12-08 2017-12-08 A kind of cross-language search method and apparatus, a kind of device for cross-language search

Publications (1)

Publication Number Publication Date
CN108255940A true CN108255940A (en) 2018-07-06

Family

ID=62722397

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201711298752.0A Pending CN108255940A (en) 2017-12-08 2017-12-08 A kind of cross-language search method and apparatus, a kind of device for cross-language search

Country Status (2)

Country Link
CN (1) CN108255940A (en)
WO (1) WO2019109663A1 (en)

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109408822A (en) * 2018-10-30 2019-03-01 中译语通科技股份有限公司 Across the language books Controlling UEP method and system of one kind
WO2019109663A1 (en) * 2017-12-08 2019-06-13 北京搜狗科技发展有限公司 Cross-language search method and apparatus, and apparatus for cross-language search
CN111126087A (en) * 2019-12-25 2020-05-08 北京百度网讯科技有限公司 Domain translation processing method, device and equipment
CN112163433A (en) * 2020-09-29 2021-01-01 北京字跳网络技术有限公司 Key vocabulary matching method and device, electronic equipment and storage medium
CN112528129A (en) * 2019-08-28 2021-03-19 搜狗(杭州)智能科技有限公司 Language searching method and device for multi-language translation system

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103838774A (en) * 2012-11-26 2014-06-04 英业达科技有限公司 Webpage inquiring system and inquiring method thereof
CN106599206A (en) * 2016-12-15 2017-04-26 北京小米移动软件有限公司 Method and device for searching information
CN106919642A (en) * 2017-01-13 2017-07-04 北京搜狗科技发展有限公司 A kind of cross-language search method and apparatus, a kind of device for cross-language search

Family Cites Families (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108304412B (en) * 2017-01-13 2022-09-30 北京搜狗科技发展有限公司 Cross-language search method and device for cross-language search
CN108334526A (en) * 2017-01-20 2018-07-27 北京搜狗科技发展有限公司 The methods of exhibiting and device of search result items
CN108255940A (en) * 2017-12-08 2018-07-06 北京搜狗科技发展有限公司 A kind of cross-language search method and apparatus, a kind of device for cross-language search

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103838774A (en) * 2012-11-26 2014-06-04 英业达科技有限公司 Webpage inquiring system and inquiring method thereof
CN106599206A (en) * 2016-12-15 2017-04-26 北京小米移动软件有限公司 Method and device for searching information
CN106919642A (en) * 2017-01-13 2017-07-04 北京搜狗科技发展有限公司 A kind of cross-language search method and apparatus, a kind of device for cross-language search

Cited By (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2019109663A1 (en) * 2017-12-08 2019-06-13 北京搜狗科技发展有限公司 Cross-language search method and apparatus, and apparatus for cross-language search
CN109408822A (en) * 2018-10-30 2019-03-01 中译语通科技股份有限公司 Across the language books Controlling UEP method and system of one kind
CN112528129A (en) * 2019-08-28 2021-03-19 搜狗(杭州)智能科技有限公司 Language searching method and device for multi-language translation system
CN112528129B (en) * 2019-08-28 2024-03-22 北京搜狗科技发展有限公司 Language searching method and device for multilingual translation system
CN111126087A (en) * 2019-12-25 2020-05-08 北京百度网讯科技有限公司 Domain translation processing method, device and equipment
CN111126087B (en) * 2019-12-25 2023-08-29 北京百度网讯科技有限公司 Domain translation processing method, device and equipment
CN112163433A (en) * 2020-09-29 2021-01-01 北京字跳网络技术有限公司 Key vocabulary matching method and device, electronic equipment and storage medium

Also Published As

Publication number Publication date
WO2019109663A1 (en) 2019-06-13

Similar Documents

Publication Publication Date Title
CN108255940A (en) A kind of cross-language search method and apparatus, a kind of device for cross-language search
CN108255939A (en) A kind of cross-language search method and apparatus, a kind of device for cross-language search
CN109189879B (en) Electronic book display method and device
CN109657236B (en) Guidance information acquisition method, apparatus, electronic apparatus, and storage medium
CN110175223A (en) A kind of method and device that problem of implementation generates
CN108121736A (en) A kind of descriptor determines the method for building up, device and electronic equipment of model
CN109144285B (en) Input method and device
CN107527619A (en) The localization method and device of Voice command business
CN112269853B (en) Retrieval processing method, device and storage medium
CN108958503A (en) input method and device
CN108073292A (en) A kind of intelligent word method and apparatus, a kind of device for intelligent word
CN108304412A (en) A kind of cross-language search method and apparatus, a kind of device for cross-language search
CN108538284A (en) Simultaneous interpretation result shows method and device, simultaneous interpreting method and device
CN108345608A (en) A kind of searching method, device and equipment
CN111428522B (en) Translation corpus generation method, device, computer equipment and storage medium
CN111984749A (en) Method and device for ordering interest points
CN106919642A (en) A kind of cross-language search method and apparatus, a kind of device for cross-language search
CN110929137B (en) Article recommendation method, device, equipment and storage medium
CN113936697B (en) Voice processing method and device for voice processing
CN108628461A (en) A kind of input method and device, a kind of method and apparatus of update dictionary
KR102327790B1 (en) Information processing methods, devices and storage media
CN112632222B (en) Terminal equipment and method for determining data belonging field
CN111428523B (en) Translation corpus generation method, device, computer equipment and storage medium
CN110399468A (en) A kind of data processing method, device and the device for data processing
CN109542244A (en) A kind of input method, device and medium

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

Application publication date: 20180706

RJ01 Rejection of invention patent application after publication