KR101505673B1 - Multi-language searching system, multi-language searching method, and image searching system based on meaning of word - Google Patents
Multi-language searching system, multi-language searching method, and image searching system based on meaning of word Download PDFInfo
- Publication number
- KR101505673B1 KR101505673B1 KR1020130031068A KR20130031068A KR101505673B1 KR 101505673 B1 KR101505673 B1 KR 101505673B1 KR 1020130031068 A KR1020130031068 A KR 1020130031068A KR 20130031068 A KR20130031068 A KR 20130031068A KR 101505673 B1 KR101505673 B1 KR 101505673B1
- Authority
- KR
- South Korea
- Prior art keywords
- semantic
- search
- meaning
- word
- language
- Prior art date
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/3331—Query processing
- G06F16/3332—Query translation
- G06F16/3337—Translation 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)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The present invention relates to a multilingual search system, a multilingual search method, and an image search system using the multilingual search system based on the meaning of a word. The multi-language search system according to the present invention includes: a semantic-based word database in which a plurality of semantic groups registered by being grouped according to the meanings of words of a plurality of different languages are stored; A multi-language query extracting unit for extracting words of each language in a meaning group to which the inputted search word belongs, when a search word of a specific language is inputted through a communication network; And a multilingual search unit for providing search results based on the words of each language extracted by the multilingual search term extraction unit through the communication network. Accordingly, when a word of a specific language is input as a search term, only a search result for another language having the same meaning as the word corresponding to the search term can be provided.
Description
The present invention relates to a multilingual search system, a multilingual search method, and an image search system using the multilingual search system. More particularly, the present invention relates to a multilingual search system, The present invention relates to a multilingual search system, a multilingual search method, and an image search system using the multilingual search system.
As the use of the Internet becomes popular, users can acquire various information through the Internet search. That is, users access the Internet search site through a terminal device such as a personal computer or a notebook capable of accessing the Internet, and then search various contents related to news, knowledge, games, and the community.
In recent years, with the spread of a portable terminal device which can be connected to a communication network, such as a smart phone or a tablet terminal device, while being portable, users can search for desired information at any time without restriction on a place, Development is accelerating.
Such a search site mainly provides a search interface based on text data. The search site receives a search word for a search from a user and provides a search result list matching the input search word to a user.
For this purpose, search sites generally include a search engine. In general, a search engine provides a search interface through the following process.
First, the search engine collects a number of web documents existing on the network. This process is performed by a web crawler, which functions to visit web documents existing on the network and store the visited web documents.
More specifically, the web crawler sequentially searches for and stores web documents included in a predetermined seed list, analyzes HTML links of the stored web documents, and searches for other web documents associated with the stored web documents The search target is expanded, and as a result, all the web documents accessible from the web documents included in the seed list are searched and stored.
Then, the search engine arranges and analyzes web documents stored by the web crawler according to a series of criteria, and extracts information for generation of index data. More specifically, a page rank operation is performed to remove redundant data among the crawl data and measure the importance of the web document using the link information included in the crawl data.
Finally, the search engine refers to the crawled data and the result of performing the page rank, and generates index data. Here, the index data is generated using a predetermined data structure such as B Tree, hash, etc. so that the user can easily acquire web documents corresponding to the search term when the user inputs a search word to the search engine .
The index data generated in the above manner may include a plurality of web documents written in various languages. That is, since the web crawler of the search engine collects the web documents using the link information included in the web document, the web crawler collects the web documents without distinguishing the collection language of the collected web documents. Therefore, , Japanese, Chinese, and so on.
However, since the search interface provided using the conventional index data provides a web document matching the search word input by the user, when a user inputs 'car' as a search term, , But can not provide web documents in which 'car' is written in another language such as 'car' or 'automobile'.
In order to solve the above problem, Korean Patent Laid-Open Publication No. 2004-60858 discloses a method of translating a search word input by a user in a specific language into another language and performing a search using the translated search word, We propose a technique that can provide search results for documents.
However, the technique disclosed in Korean Patent Laid-Open Publication may be useful in translating a language of a specific country into a foreign language to provide search results of various languages. However, when a plural word, that is, There is a problem that a search result that the user does not want is provided.
For example, suppose that a Korean boat is entered as a search term, and that it is assumed that a general boat is searched for. In this case, 'ship', 'boat', and 'vessel' Such as 'pear' which is the meaning of the eating belly, 'abdomen' which is the meaning of the abdomen of the person, and the like.
This means that if the range of the language to be translated is extended to English, Chinese, and the like, the ratio of the information desired by the user in the final overall search result is reduced, thereby deteriorating the performance of the search engine.
SUMMARY OF THE INVENTION Accordingly, the present invention has been made in view of the above problems, and it is an object of the present invention to provide a method and apparatus for providing a search result for a language having the same meaning as a word corresponding to a search word, A multilingual search system, a multilingual search method, and an image search system using the multilingual search system.
According to another aspect of the present invention, there is provided a multilingual search system based on the meaning of a word, the multilingual search system comprising: a semantic-based word database storing a plurality of semantic groups, Wow; A multi-language query extracting unit for extracting words of each language in a meaning group to which the inputted search word belongs, when a search word of a specific language is inputted through a communication network; And a multilingual search unit for providing a search result based on the words of each language extracted by the multilingual search term extraction unit through the communication network.
Here, the semantic-based word database stores contents for semantic selection for intuitively recognizing the meaning of words belonging to each semantic group, corresponding to each semantic group; Wherein the search term extraction unit is operable to select, through the communication network, any one of the meaning selection contents corresponding to the semantic groups when the input search word belongs to at least two semantic groups among the plurality of semantic groups, It is possible to extract words of each language in a meaning group corresponding to a selected one of the contents for meaning selection.
The meaning selection content may include an image corresponding to the meaning of the word.
According to another aspect of the present invention, there is provided a multilingual search method based on the meaning of a word according to another embodiment of the present invention. The multilingual search method comprises the steps of: (a) Building a semantic-based word database in which the semantic group of the semantic-based word database is stored; (b) inputting a search word of a specific language through a communication network; (c) extracting words of each language in a meaning group to which the input search word belongs among the plurality of semantic groups; and (d) a search result based on the extracted words of each language is provided through the communication network. The multilingual search method is also based on the meaning of the word.
Wherein the step (a) further comprises the step of registering, for each of the meaning groups, a content for semantic selection that allows intuitively recognizing the meaning of words belonging to the respective semantic groups, Wherein the step (c) comprises the steps of: (c1) determining whether the inputted search word belongs to at least two semantic groups among the plurality of semantic groups, (c2) belonging to two or more semantic groups in the step (c1) Selecting one of the semantic selection contents corresponding to the semantic groups if the semantic selection content is selected via the communication network; and (c3) extracting words of each language in the semantic group corresponding to the selected one of the provided semantic selection contents.
The meaning selection content may include an image corresponding to the meaning of the word.
According to another aspect of the present invention, there is provided an image retrieval system, comprising: a semantic-based word database storing a plurality of semantic groups registered in a grouping manner according to the meaning of words in a plurality of different languages; Wow; An image database storing a plurality of images; A multi-language query extracting unit for extracting words of each language in a meaning group to which the inputted search word belongs, when a search word of a specific language is inputted through a communication network; And a multilingual search unit for searching the image database for images corresponding to the extracted words of each language based on the words of each language extracted by the multilingual query extracting unit and providing the search through the communication network. Which can be accomplished by an image retrieval system.
Here, the semantic-based word database stores contents for semantic selection for intuitively recognizing the meaning of words belonging to each semantic group, corresponding to each semantic group; Wherein the search term extraction unit is operable to select, through the communication network, any one of the meaning selection contents corresponding to the semantic groups when the input search word belongs to at least two semantic groups among the plurality of semantic groups, It is possible to extract words of each language in a meaning group corresponding to a selected one of the contents for meaning selection.
The meaning selection content may include an image corresponding to the meaning of the word.
Also, at least one of the images stored in the image database is registered to match at least one of the plurality of semantic groups; The multilingual search unit may provide a search result including images matched to a semantic group corresponding to a selected one of the provided semantic selection contents through the communication network.
Also, the images stored in the image database are registered with at least one keyword included therein; The multilingual search unit may search for an image from the image database by matching words of each language extracted by the multilingual search term extraction unit with the keyword.
According to the present invention, when a word of a specific language is input as a search term, the meaning of a word that can be provided only as a search result for another language having the same meaning as the word corresponding to the search word A multilingual search system, and an image search system using the multilingual search system.
1 is a diagram illustrating an example of a search structure to which the multilingual search system according to the present invention is applied,
FIG. 2 is a diagram illustrating a configuration of a multi-language search system according to the present invention,
FIG. 3 is a diagram illustrating an example of a semantic group stored in the semantic-based word database of the multilingual search system according to the present invention,
4 is a diagram illustrating an example of a search window provided in the multilingual search system according to the present invention,
5 is a diagram for explaining a multilingual search method according to the present invention,
6 is a diagram illustrating a configuration of an image retrieval system to which the multi-language retrieval system according to the present invention is applied.
Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings.
1 is a diagram illustrating an example of a search structure to which the multilingual search system according to the present invention is applied. The multilingual search system according to the present invention may be applied to various types of
Here, the
The
2 is a diagram illustrating a configuration of a multilingual search system according to the present invention. Referring to FIG. 2, the multilingual search system according to the present invention includes a semantic-based database, a multilingual
The semantic-
Here, the words stored in the semantic-
3 is a diagram illustrating an example of a semantic group stored in the semantic-
Referring to FIG. 3, the meaning group 1 shows an example of grouping words meaning a ship carrying a person or a cargo, in which a ship, a vessel, and an English ship, a boat, and a vessel are grouped in Korean .
Semantic group 2 is an example of grouping words meaning eating fish, which is one of the fruits. It is an example of grouping pear in English and pear in Korean. Semantic group 3 means a boat which is a part of body such as man. , Which is an example of grouping abdomen and belly in abdomen and abdomen in English, and abdomen and belly in English.
In the same way, the meaning group N shows an example in which words meaning arms of a person are grouped, and arm is grouped in Korean and arm in English.
In this way, in the multilingual search system according to the present invention, the words of the respective languages are not linked to each other based on the words belonging to the specific language, but the meaning of the words, that is, Are registered in the meaning-based
When a search word of a specific language is inputted through the
At this time, the
Here, in the meaning-based
The meaning selection content corresponding to each semantic group includes a content intuitively recognizing the meaning of words belonging to each semantic group. FIG. 3 shows an example in which an image corresponding to the meaning of a word is applied to the content for meaning selection. That is, the image for the meaning selection of the semantic group 1 is an image of 'a ship carrying a person or a cargo', the image for the semantic selection of the semantic group 2 is the image of the ' The image of the 'abdomen of a person or the like' may be used as the meaning selection content, and the image of 'arm of the person or the like' may be applied to the meaning selection contents of the meaning group N.
Here, when the search word input from the
4 is a diagram illustrating an example of a search window SW provided in the multilingual search system according to the present invention. 4, when a user inputs' boat 'as a search word through the
Then, the multilingual search
At this time, when the user selects one of the contents for semantic selection in the selection window (SNW) shown in Fig. 4, the retrieval term extraction unit extracts words of the respective languages in the semantic group corresponding to the selected semantic content , And the
According to the above configuration, even when a search word is created in a specific language and searched, the search result for the languages of other countries is also provided, and a meaning group having a meaning requiring a search among a plurality of semantic groups is selected, It is possible to exclude undesired search results that occur in the search results, thereby improving the accuracy of the search results.
For example, in the example shown in FIG. 3, when 'boat' is inputted as a search term, if a search is performed through translation of a word as in the conventional search method, Korean 'ship', English, 'ship' pear ',' abdomen ', and' belly 'in addition to' boat ',' vessel ', and' pear ' Quot; can be excluded.
Hereinafter, the multilingual search method according to the present invention will be described in detail with reference to FIG.
First, as described above with reference to the multilingual search system, after the user accesses the multilingual search system through the
Here, the multi-lingual search
4, the multilingual search
Then, the multilingual search
Hereinafter, FIG. 6 is a diagram illustrating a configuration of an image retrieval system according to the present invention. The multilingual search system described above is applied to the image search system according to the present invention. Here, the image search system according to the present invention is applied to an image sharing center for sharing images, and is applied to search for images registered by users.
6, the image search system according to the present invention includes a semantic-based
As described above, the semantic-based
The
When a search word of a specific language is input through the
The
At least one of the images stored in the
In this case, the
As described above, the images stored in the
Although several embodiments of the present invention have been shown and described, those skilled in the art will appreciate that various modifications may be made without departing from the principles and spirit of the invention . The scope of the invention will be determined by the appended claims and their equivalents.
100: search providing server 110: semantic-based word database
120: Multilanguage query extracting unit 130: Multilingual search unit
310, 320, 330: user terminal 500:
Claims (11)
A semantic-based word database in which a plurality of semantic groups registered in a grouped manner according to the meaning of words of a plurality of different languages are stored;
A multi-language query extracting unit for extracting words of each language in a meaning group to which the inputted search word belongs, when a search word of a specific language is inputted through a communication network;
And a multilingual search unit for providing search results based on words of each language extracted by the multilingual search term extraction unit through the communication network,
Wherein the semantic-based word database stores content for semantic selection that allows intuitively recognizing the meaning of words belonging to each semantic group, corresponding to each semantic group;
The search term extraction unit
Providing, through the communication network, any one of the meaning selection contents corresponding to the semantic groups when the input search word belongs to two or more semantic groups among the plurality of semantic groups,
Extracting words of each language in a semantic group corresponding to a selected one of the provided contents for semantic selection, based on the meaning of the word.
Wherein the meaning selection content includes an image corresponding to a meaning of a word.
(a) constructing a semantic-based word database in which a plurality of semantic groups registered by being grouped according to the meaning of words of a plurality of different languages are stored;
(b) inputting a search word of a specific language into a user terminal and inputting the search word to a search providing server through a communication network;
(c) extracting, from the semantic-based word database, words of each language in a semantic group to which the input search word belongs among the plurality of semantic groups by the search providing server;
(d) providing a search result based on the words of the extracted language by the search providing server to the user terminal through the communication network,
The step (a)
Further comprising the step of registering, in the semantic-based word database, the semantic-based content corresponding to each of the semantic groups, the semantic-based content enabling intuitively recognizing the semantic meaning of words belonging to each semantic group;
The step (c) performed by the search providing server
(c1) determining whether the input search word belongs to at least two semantic groups among the plurality of semantic groups,
(c2) when it is determined in step (c1) that one of the semantic selection contents corresponding to the semantic groups is selected to belong to two or more semantic groups, the semantic selection contents are provided to the user terminal via the communication network Wow;
(c3) extracting words of each language in a semantic group corresponding to any one of the provided semantic selection contents from the semantic-based word database. .
Wherein the meaning selection content includes an image corresponding to a meaning of a word.
A semantic-based word database in which a plurality of semantic groups registered in a grouped manner according to the meaning of words of a plurality of different languages are stored;
An image database storing a plurality of images;
A multi-language query extracting unit for extracting words of each language in a meaning group to which the inputted search word belongs, when a search word of a specific language is inputted through a communication network;
And a multilingual search unit for searching the image database for images corresponding to the extracted words of the respective languages based on the words of the respective languages extracted by the multilingual search term extraction unit and providing the images through the communication network,
Wherein the semantic-based word database stores content for semantic selection that allows intuitively recognizing the meaning of words belonging to each semantic group, corresponding to each semantic group;
The search term extraction unit
Providing, through the communication network, any one of the meaning selection contents corresponding to the semantic groups when the input search word belongs to two or more semantic groups among the plurality of semantic groups,
And extracting words of each language in a semantic group corresponding to one of the provided semantic selection contents.
Wherein the meaning selection content includes an image corresponding to a meaning of a word.
At least one of the images stored in the image database is registered to match at least one of the plurality of semantic groups;
Wherein the multilingual search unit provides a search result including images matched with a semantic group corresponding to a selected one of the provided semantic selection contents through the communication network.
Wherein the images stored in the image database are registered including at least one keyword;
Wherein the multilingual search unit searches for an image from the image database by matching the words of each language extracted by the multilingual search term extraction unit with the keyword.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| KR1020130031068A KR101505673B1 (en) | 2013-03-22 | 2013-03-22 | Multi-language searching system, multi-language searching method, and image searching system based on meaning of word |
| PCT/KR2013/002473 WO2014148664A1 (en) | 2013-03-22 | 2013-03-26 | Multi-language search system, multi-language search method, and image search system, based on meaning of word |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| KR1020130031068A KR101505673B1 (en) | 2013-03-22 | 2013-03-22 | Multi-language searching system, multi-language searching method, and image searching system based on meaning of word |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| KR20140115849A KR20140115849A (en) | 2014-10-01 |
| KR101505673B1 true KR101505673B1 (en) | 2015-03-24 |
Family
ID=51580327
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| KR1020130031068A KR101505673B1 (en) | 2013-03-22 | 2013-03-22 | Multi-language searching system, multi-language searching method, and image searching system based on meaning of word |
Country Status (2)
| Country | Link |
|---|---|
| KR (1) | KR101505673B1 (en) |
| WO (1) | WO2014148664A1 (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR102098283B1 (en) * | 2018-07-25 | 2020-05-15 | 주식회사 아이포트폴리오 | Data processing system and method for language learning |
| KR102125341B1 (en) * | 2018-07-25 | 2020-06-22 | 주식회사 아이포트폴리오 | Quiz creation system and method for language learning |
| KR102236847B1 (en) * | 2019-01-30 | 2021-04-06 | 주식회사 이볼케이노 | Language learning system using concept maker of words |
| CN110347904A (en) * | 2019-05-28 | 2019-10-18 | 成都美美臣科技有限公司 | One multilingual electronic business web site handles language search method |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2004157623A (en) * | 2002-11-05 | 2004-06-03 | Hitachi Ltd | Search system and search method |
| KR20060107289A (en) * | 2005-04-08 | 2006-10-13 | 김동암 | Method for providing query language chain made from informations for internet search |
| KR20090119383A (en) * | 2008-05-16 | 2009-11-19 | 한국과학기술정보연구원 | System and method for providing terminology resource |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20010097802A (en) * | 2000-04-26 | 2001-11-08 | 신재균 | System for multi-language search and auto-translation of searched information/sorting, and multi-language searching method using the system |
| US7099860B1 (en) * | 2000-10-30 | 2006-08-29 | Microsoft Corporation | Image retrieval systems and methods with semantic and feature based relevance feedback |
| WO2005033909A2 (en) * | 2003-10-08 | 2005-04-14 | Any Language Communications Inc. | Relationship analysis system and method for semantic disambiguation of natural language |
| US8255376B2 (en) * | 2006-04-19 | 2012-08-28 | Google Inc. | Augmenting queries with synonyms from synonyms map |
| KR100782047B1 (en) * | 2006-04-27 | 2007-12-04 | 인하대학교 산학협력단 | Automatic Generation Method of the Initial Query Set for Image Search on the Mobile Web |
| US8402046B2 (en) * | 2008-02-28 | 2013-03-19 | Raytheon Company | Conceptual reverse query expander |
-
2013
- 2013-03-22 KR KR1020130031068A patent/KR101505673B1/en not_active IP Right Cessation
- 2013-03-26 WO PCT/KR2013/002473 patent/WO2014148664A1/en active Application Filing
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2004157623A (en) * | 2002-11-05 | 2004-06-03 | Hitachi Ltd | Search system and search method |
| KR20060107289A (en) * | 2005-04-08 | 2006-10-13 | 김동암 | Method for providing query language chain made from informations for internet search |
| KR100819846B1 (en) * | 2005-04-08 | 2008-04-07 | 김동암 | Method For Providing Query Language Chain Made from Informations For Internet Search |
| KR20090119383A (en) * | 2008-05-16 | 2009-11-19 | 한국과학기술정보연구원 | System and method for providing terminology resource |
Also Published As
| Publication number | Publication date |
|---|---|
| KR20140115849A (en) | 2014-10-01 |
| WO2014148664A1 (en) | 2014-09-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US9411827B1 (en) | Providing images of named resources in response to a search query | |
| US9489401B1 (en) | Methods and systems for object recognition | |
| US9305089B2 (en) | Search engine device and methods thereof | |
| US8280902B2 (en) | High precision search system and method | |
| US8880559B2 (en) | Location activity search engine computer system | |
| US20110106805A1 (en) | Method and system for searching multilingual documents | |
| US8874590B2 (en) | Apparatus and method for supporting keyword input | |
| US8631097B1 (en) | Methods and systems for finding a mobile and non-mobile page pair | |
| EP2570937A1 (en) | Data search device, data search method and program | |
| CN104903886A (en) | Structured search queries based on social-graph information | |
| JP6165955B1 (en) | Method and system for matching images and content using whitelist and blacklist in response to search query | |
| CN109710732B (en) | Information query method, device, storage medium and electronic equipment | |
| US20150161175A1 (en) | Alternative image queries | |
| KR101505673B1 (en) | Multi-language searching system, multi-language searching method, and image searching system based on meaning of word | |
| CN110569419A (en) | question-answering system optimization method and device, computer equipment and storage medium | |
| US20160154885A1 (en) | Method for searching a database | |
| JP2014102827A (en) | Retrieval system and retrieval method for the same | |
| CN104778232A (en) | Searching result optimizing method and device based on long query | |
| KR20190011176A (en) | Search method and apparatus using property language | |
| Tabarcea et al. | Framework for location-aware search engine | |
| KR20140119217A (en) | Photo sharing system and photo sharing method for searching photo by keyword search | |
| JP2017220179A (en) | Content processing device, content processing method and program | |
| GENTILE | Using Flickr geotags to find similar tourism destinations | |
| KR20210071500A (en) | Apparatus and method for providing search service based on artificial intelligence | |
| JP2002123541A (en) | Retrieval system for problem solution database and computer-readable storage medium with problem solution database retrieving program recorded thereon |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| A201 | Request for examination | ||
| E902 | Notification of reason for refusal | ||
| E701 | Decision to grant or registration of patent right | ||
| LAPS | Lapse due to unpaid annual fee |