-
公开(公告)号：KR1020160064826A
公开(公告)日：2016-06-08
申请号：KR1020140168996
申请日：2014-11-28
Applicant: 한국전자통신연구원
IPC: G06F17/30
CPC classification number: G06F17/30 , G06F17/30002 , G06F17/30005
Abstract: 본발명은지식그래프기반에서의의미적검색서비스제공장치및 그방법에관한것으로, 정보획득부, 매핑전처리부, 지식그래프매핑부, 의미적검색서비스제공부를포함할수 있으며, 이를통해사용자검색문에매핑되는지식그래프구성요소의순서쌍인튜플의개수를줄임으로써빠르고효율적인지식그래프기반의미적검색시스템의성능을높이게하는의미적검색서비스제공장치및 방법을제공하는데에있다.
Abstract translation: 本发明涉及一种基于知识图形的语义搜索服务提供装置及其方法。 语义搜索服务提供装置及其方法技术领域本发明涉及语义搜索服务提供装置及其方法。 语义搜索服务提供装置可以包括信息获取部分，映射预处理部分，知识映射部分，语义搜索服务提供部分。 因此，可以通过减少作为映射到用户搜索文档的知识图组件的有序对的元组的数量来改进基于快速有效的知识的语义搜索系统的性能。
-
2.发明公开컨텐츠 내용 기반 매쉬업 서비스 관리 시스템 및 이의 컨텐츠 내용 기반 매쉬업 서비스 관리 방법 审中-实审基于内容中包含的内容的MASHUP服务管理系统和基于其内容中包含的语境的MASHUP服务管理方法
公开(公告)号：KR1020150058745A
公开(公告)日：2015-05-29
申请号：KR1020130141887
申请日：2013-11-21
Applicant: 한국전자통신연구원
IPC: H04N21/25 , H04N21/2343
CPC classification number: H04N21/25891 , H04N21/23418 , H04N21/2353 , H04N21/23614 , H04N21/4348 , H04N21/44008 , H04N21/4532 , H04N21/458 , H04N21/8133
Abstract: 본발명은컨텐츠내용기반매쉬업서비스관리시스템및 이의컨텐츠내용기반매쉬업서비스관리방법에관한것으로, 사용자프로파일정보를기반으로사용자가시청중인컨텐츠의내용과관련된태스크(Task)를추론하고, 이를수행할수 있는매쉬업서비스(Mashup)를구성하여제공함으로써기존의컨텐츠재생환경에있어서의정보제공의제약및 한계점을극복하여사용자의컨텐츠시청환경을개선할수 있도록한 것이다.
Abstract translation: 本发明涉及一种基于内容来管理混搭服务的系统和方法，由此可以基于用户简档信息推断与用户正在观看的内容有关的任务的混搭服务并执行该任务。 本发明旨在通过消除在现有内容播放环境中提供内容的限制和缺点来改善用户的内容观看环境。
-
-
公开(公告)号：KR101700820B1
公开(公告)日：2017-02-01
申请号：KR1020120075688
申请日：2012-07-11
Applicant: 한국전자통신연구원
Inventor： 김형우
IPC: G06F17/30
CPC classification number: G06F17/30663 , G06F17/30864
Abstract: 본발명은사용자코멘트기반개인화컨텐츠검색장치및 방법에관한것으로, 사용자코멘트기반검색기술을이용해사용자선호도가고려된개인화된컨텐츠를검색하여사용자에게제공함으로써검색에대한개인만족도와정확도를향상시킬수 있도록한 것이다.
Abstract translation: 提供了一种基于用户评论搜索个性化内容的设备和方法，旨在使用基于用户评论的搜索技术，基于用户的偏好来搜索并提供个性化内容，从而提高用户对搜索结果的满意度和增强 搜索精度。
-
公开(公告)号：KR1020140109729A
公开(公告)日：2014-09-16
申请号：KR1020130024090
申请日：2013-03-06
Applicant: 한국전자통신연구원
IPC: G06F17/30
CPC classification number: G06F17/2785 , G06F17/30684 , G06F17/30699
Abstract: The present invention relates to a semantic-based search system capable of enhancing precision of searching by ranking interpretation alternatives in consideration of user preference when a plurality of interpretation alternatives are searched according to a keyword input by a user, and a search method thereof. According to the present invention, the semantic-based search system includes: a log generating unit configured to generate a common log storing knowledge corresponding to general knowledge and a user log stored by reflecting user preference; an instance analyzing unit configured to analyze vector characteristics corresponding to an instance among interpretation alternatives according to a keyword input by a user; a weight calculating unit configured to calculate weights of confidence values and cosine similarity values of interpretation alternatives including vector characteristics of the instance with respect to at least one of the common log and the user log; and an aligning unit configured to align rankings of the interpretation alternatives according to the keyword input on the basis of the calculated weights of the confidence values and the cosine similarity values. Accordingly, since interpretation alternatives according to user keyword search based on a calculation of weights of confidence values and cosine similarity values are aligned as rankings in consideration of user preference, user search satisfaction can be enhanced.
Abstract translation: 本发明涉及一种基于语义的搜索系统，其能够根据用户输入的关键词搜索多个解释替代方案时，考虑到用户偏好，通过排名解释替代方法提高搜索精度，以及其搜索方法。 根据本发明，基于语义的搜索系统包括：日志生成单元，被配置为生成存储与一般知识对应的知识的公共日志和通过反映用户偏好而存储的用户日志; 实例分析单元，被配置为根据用户输入的关键字来分析与解释替换中的实例相对应的向量特征; 权重计算单元，被配置为计算相对于所述公共日志和所述用户日志中的至少一个的所述实例的向量特征的解释替换的置信度值和余弦相似度值的权重; 以及对齐单元，其被配置为基于所计算的置信度的权重和余弦相似度值来根据关键字输入来对准解释替换的排列。 因此，考虑到用户偏好，由于基于用户关键字搜索的基于置信度权重和余弦相似度值的权重的解释替换被排列为排名，因此可以提高用户搜索满足度。
-
Patent Agency Ranking
公开(公告)号：KR1020140060806A
公开(公告)日：2014-05-21
申请号：KR1020120127588
申请日：2012-11-12
Applicant: 한국전자통신연구원
Inventor： 김형우
CPC classification number: G06F17/30424
Abstract: The present invention relates to a similar content search device based on user preference and a similar content search method thereof. The present invention improves the search reliability with excellent results of similar content search by searching and providing similar content based on the user preference using the user′s comments extracted from a text input as a user′s response for the content.
Abstract translation: 本发明涉及一种基于用户偏好的类似内容搜索装置及其类似的内容搜索方法。 本发明通过使用从文本输入提取的用户评论作为用户对内容的响应，基于用户偏好进行搜索和提供类似的内容，从而提高了搜索可靠性以及类似内容搜索的优异结果。
-
公开(公告)号：KR1020140059591A
公开(公告)日：2014-05-16
申请号：KR1020120126195
申请日：2012-11-08
Applicant: 한국전자통신연구원
CPC classification number: G06Q50/01 , G06Q30/0282
Abstract: The present invention relates to an apparatus and a method for recommending a content based on a social media, which compensate the limitation of a recommended technology and user profile based searching by recommending a popular content, which is an issue on the social media, to a user. The apparatus for recommending a content based on a social media according to the present invention includes: an information collection part for delivering social media information collected by searching one ore more than two social mediae on the basis of the received social media profile information; an information analysis part which extracts one or more than two representative words according to appearance frequency on the basis of the received social media information, and judges whether each extracted representative word has a positive meaning or a negative meaning, and generates and delivers content analysis information including the judgment result; and a content recommendation part which discriminates a recommended content on the basis of the received content analysis information, and delivers information about the discriminated recommended content.
Abstract translation: 本发明涉及一种用于基于社交媒体推荐内容的装置和方法，其通过将在社交媒体上的一个问题推荐到流行内容来补偿推荐技术和基于用户简档的搜索的限制。 用户。 根据本发明的用于推荐基于社交媒体的内容的装置包括：信息收集部分，用于通过基于接收到的社交媒体简档信息来搜索一个以上的两个以上的社交媒体收集的社交媒体信息; 信息分析部，根据接收到的社交媒体信息，根据出现频率提取一个或多于两个的代表词，并且判断每个提取的代表词是否具有正的含义或否定意义，并且生成并传递内容分析信息 包括判决结果; 以及基于所接收的内容分析信息来区分推荐内容的内容推荐部分，并且传送关于所识别的推荐内容的信息。
-
公开(公告)号：KR1020140008732A
公开(公告)日：2014-01-22
申请号：KR1020120075688
申请日：2012-07-11
Applicant: 한국전자통신연구원
Inventor： 김형우
IPC: G06F17/30
CPC classification number: G06F17/30663 , G06F17/30864 , G06F17/30023
Abstract: The present invention relates to a searching device and a method of searching personalized content based on a user's comments. The present invention allows improvement of a user's personal satisfaction and accuracy by providing personalized content, in which the user's preferences are considered, using a search based on the user's technological comments. [Reference numerals] (110) Preference analysis unit; (120) Query expansion unit; (130) Content search unit; (140) Comment information DB; (150) Content indexer; (160) Content index DB; (170) Searching result providing unit; (180) Query input unit; (AA) User terminal
Abstract translation: 本发明涉及一种基于用户意见搜索个性化内容的搜索装置和方法。 本发明通过使用基于用户的技术评论的搜索来提供其中考虑了用户偏好的个性化内容来提高用户的个人满意度和准确性。 （附图标记）（110）偏好分析单元; （120）查询扩展单元; （130）内容搜索单元; （140）评论信息DB; （150）内容索引器; （160）内容索引DB; （170）搜索结果提供单元; （180）查询输入单元; （AA）用户终端
-
公开(公告)号：KR1020150104882A
公开(公告)日：2015-09-16
申请号：KR1020140026793
申请日：2014-03-06
Applicant: 한국전자통신연구원
IPC: G06F17/00
Abstract: 본 발명은 콘텐츠에 대하여 작성된 코멘트를 분석하여 콘텐츠의 요소들을 추출하고, 추출된 요소들을 비교하여 두 콘텐츠 간의 유사도를 계산하고, 계산된 유사도를 바탕으로 많은 수의 콘텐츠를 연결해 주는 멀티미디어 콘텐츠 연관 콘텐츠 네트워크를 생성장치 및 그 방법으로, 콘텐츠 연관 콘텐츠 네트워크는 콘텐츠 유사도 산출부, 사용자 유사도 산출부, 네트워크 생성부를 포함할 수 있으며, 이를 통해 서비스를 제공받는 사용자와 코멘트를 작성한 사용자 간의 유사도를 고려하여 실제 사용자가 선호하는 요소들을 영화의 특징으로 포함함으로써 콘텐츠들의 특징을 비교하여 콘텐츠 연관 콘텐츠 네트워크를 생성하여 개인 사용자에게 정확하고 만족스러운 결과를 제공하는 데에 그 목적이 있다.
Abstract translation: 本发明涉及一种用于生成多媒体内容相关内容网络的装置，其分析为内容写入的评论并提取内容的元素，比较所提取的元素并计算两条内容之间的相似度，并连接多条内容 基于所计算的相似度及其方法。 内容相关内容网络包括内容相似度计算单元，用户相似度计算单元和网络生成单元。 本发明旨在通过考虑通过内容相关内容网络接收服务的用户和写入评论的用户之间的相似性，通过包括实际用户喜欢的电影的特征来提供准确和令人满意的结果，以及 通过比较内容的特点和生成内容相关的内容网络。
-
公开(公告)号：KR1020140047952A
公开(公告)日：2014-04-23
申请号：KR1020120114352
申请日：2012-10-15
Applicant: 한국전자통신연구원
CPC classification number: G06F17/30292 , G06F17/2705 , G06F17/30595
Abstract: The present invention relates to a knowledge base generating device and a knowledge base generating method thereof which is capable of quickly and easily generating the knowledge base by generating a final knowledge base after generating multiple unit knowledge bases including only some basic knowledge and then merging after performing independent reasoning. [Reference numerals] (111) Metadata extractor; (112) Text analysis unit; (113) Basic knowledge storage unit; (120) Unit knowledge base generating unit; (130) Unit knowledge base reasoning unit; (140) Knowledge base building unit; (150) Schema modeling unit; (160) Web document collection unit; (AA) Web document storage DB; (BB) Schema modeling information DB; (CC) Basic knowledge DB; (DD) Knowledge base DB; (EE) Unit knowledge base reasoning unit DB
Abstract translation: 本发明涉及一种知识库生成装置及其知识库生成方法，其能够通过在生成包括仅一些基本知识的多个单元知识库，然后在执行之后合并的方式生成最终知识库来快速且容易地生成知识库 独立推理。 （111）元数据提取器; （112）文本分析单元; （113）基础知识储存单位; （120）单位知识库生成单位; （130）单位知识库推理单位; （140）知识库建设单位; （150）模式建模单元; （160）网络文件收集单元; （AA）Web文档存储DB; （BB）模式建模信息DB; （CC）基础知识DB; （DD）知识库DB; （EE）单位知识库推理单元DB
-
-
-
-
-
-
-
-
-
Search Results
10
records
(took 0.025 seconds)
