-
公开(公告)号：KR101500874B1
公开(公告)日：2015-03-10
申请号：KR1020130142714
申请日：2013-11-22
Applicant: 포항공과대학교 산학협력단
CPC classification number: G06Q30/0264 , G06Q30/02 , G06Q30/0247
Abstract: 컨텐츠 추천을 위한 사용자 상황 인지 컨텐츠 추천 장치가 개시된다. 컨텐츠 추천 장치에서 수행되는 컨텐츠 추천 방법으로 사용자의 컨텐츠 사용 정보를 모니터링하여, 상기 모니터링된 결과에 기초하여 사용자에게 컨텐츠 추천하는 것에 대한 편리도와 곤란도를 산출하고, 산출된 결과를 비교하여 사용자에게 컨텐츠 추천 시점을 판단하는 과정을 포함한다. 따라서, 사용자의 상황을 인지하여 컨텐츠를 추천함으로써, 사용자의 컨텐츠 사용에 방해되지 않는 컨텐츠 추천을 제공할 수 있다.
Abstract translation: 公开了一种用于推荐内容推荐用户上下文感知内容的设备。 在内容推荐装置中执行的内容推荐方法包括监视用户的内容使用信息的步骤，以基于监视结果计算向用户推荐内容的便利性和不便，并且确定向用户推荐内容的时间 通过比较计算结果。 因此，通过意识到用户的上下文来推荐内容，提供不中断用户的内容使用的内容推荐。
-
公开(公告)号：KR1020130139547A
公开(公告)日：2013-12-23
申请号：KR1020120063086
申请日：2012-06-13
Applicant: 포항공과대학교 산학협력단
IPC: G06F17/00
CPC classification number: G06F17/30598 , G06F17/18 , G06F17/30 , G06F17/30386
Abstract: A method and apparatus for sampling data is disclosed. According to one embodiment of the present invention, a method for sampling data comprises the steps of: generating an interest model in which the interest of a user is reflected on the basis of original data; and determining a sampling model according to comparison of a model sampled on the basis of the original data and the interest model. According to the present invention, a sampling model in which the interest of a user is reflected can be obtained quickly and easily. [Reference numerals] (AA) Start;(BB) End;(S100) Generate an interest model in which the interest of a user is reflected on the basis of original data;(S200) Determine a sampling model according to comparison of the interest model and a model sampled on the basis of the original data
Abstract translation: 公开了一种采样数据的方法和装置。 根据本发明的一个实施例，一种用于采样数据的方法包括以下步骤：产生利用原始数据反映用户兴趣的兴趣模型; 以及根据基于原始数据采样的模型与兴趣模型的比较来确定抽样模型。 根据本发明，可以快速且容易地获得反映用户兴趣的抽样模型。 （参考号）（AA）开始;（BB）结束;（S100）生成利用原始数据反映用户兴趣的兴趣模型;（S200）根据兴趣比较确定抽样模型 模型和基于原始数据采样的模型
-
公开(公告)号：KR1020110009744A
公开(公告)日：2011-01-31
申请号：KR1020090067086
申请日：2009-07-23
Applicant: 포항공과대학교 산학협력단
Inventor： 유환조
IPC: G06F17/30
CPC classification number: G06F17/3053
Abstract: PURPOSE: A method for searching a database using relevance feedback and a recording medium with a program for executing the same are provided to derive an accurate correlation function from a small amount of feedback, thereby efficiently searching a database. CONSTITUTION: Correlation feedback about the first search result is received(S110). A correlation function is derived based on the correlation feedback(S120). The second search result arranged according to a correlation degree applies the first search result to the correlation function(S130). The correlation feedback is multi-level relevance feedback about the first search result or relative relevance ordering feedback for the first search result.
Abstract translation: 目的：提供一种使用相关性反馈搜索数据库的方法和具有用于执行相关性反馈的程序的记录介质，以从少量反馈中导出准确的相关函数，从而有效地搜索数据库。 规定：收到关于第一搜索结果的相关反馈（S110）。 基于相关反馈导出相关函数（S120）。 根据相关度排列的第二搜索结果将第一搜索结果应用于相关函数（S130）。 相关反馈是关于第一搜索结果或第一搜索结果的相关相关性排序反馈的多级相关性反馈。
-
公开(公告)号：KR102022794B1
公开(公告)日：2019-09-18
申请号：KR1020180033655
申请日：2018-03-23
Applicant: 포항공과대학교 산학협력단
IPC: H03M7/30
-
公开(公告)号：KR101678779B1
公开(公告)日：2016-12-06
申请号：KR1020150060206
申请日：2015-04-29
Applicant: 포항공과대학교 산학협력단
Abstract: 콘텐츠추천방법및 장치가개시된다. 본발명의일 실시예에따른콘텐츠추천방법은다수의콘텐츠각각에서추출된메타데이터들간의유사도를기반으로다수의콘텐츠간의관계를나타내는이종그래프를구축하는단계, 사용자로부터콘텐츠추천요청이수신됨에따라사용자의콘텐츠사용이력을이용하여사용자가선호하는콘텐츠의패턴을추출하는단계및 사용자가선호하는콘텐츠의패턴을이용하여이종그래프에서사용자에게추천할콘텐츠를추출하는단계를포함한다. 따라서, 사용자의콘텐츠선호도가반영된맞춤형콘텐츠추천서비를제공하여사용자의편의성및 콘텐츠추천의유효성을향상시킬수 있다.
-
Patent Agency Ranking
公开(公告)号：KR101305732B1
公开(公告)日：2013-09-06
申请号：KR1020120075666
申请日：2012-07-11
Applicant: 포항공과대학교 산학협력단
IPC: H04N21/232
CPC classification number: G06F17/30825 , G06F17/30784 , H04N5/144 , H04N21/41407 , H04N21/44008 , H04N21/4722
Abstract: PURPOSE: A block producing method for searching a video and a query processing method based on a block produced using the same are provided to process a query based on a tilt block produced using positional information and directional information of a frame that changes linearly, thereby processing an amount of queries using less memory. CONSTITUTION: A block producing device generates a regression line based on a start frame and an end frame among frames of a video (S110). The device selects a point on the regression line (S120). If the distance between the point and an arbitrary frame is greater than a predefined reference distance, the device decides the arbitrary frame as a reference frame (S130,S140). The device divides the frames into at least two groups based on the reference frame (S310). The device produces a tilt block that is parallel to the line that is made by the start frame and the end frame (S320). [Reference numerals] (AA) Start; (BB) End; (CC) Calculate distance > reference distance; (DD) Yes; (EE) End; (S110) Generate a regression line based on a start frame and an end frame; (S120) Select a point on the regression line; (S130) Calculate the distance between an arbitrary point and an arbitrary frame; (S140) Decide the arbitrary frame as a reference frame; (S310) Divide the frames into at least two groups based on the reference frame; (S320) Produce a tilt block that is parallel to the line that is made by the start frame and the end frame
Abstract translation: 目的：提供一种用于搜索视频的块生成方法和基于使用其生成的块的查询处理方法，以基于使用位置信息产生的倾斜块和线性改变的帧的方向信息来处理查询，从而处理 使用较少内存的查询量。 构成：块生成装置基于视频的帧中的开始帧和结束帧生成回归线（S110）。 设备选择回归线上的一个点（S120）。 如果点与任意帧之间的距离大于预定义的参考距离，则设备将任意帧判定为参考帧（S130，S140）。 该设备基于参考帧将帧划分成至少两个组（S310）。 该装置产生与由起始框架和端框架制成的线平行的倾斜块（S320）。 （附图标记）（AA）开始; （BB）结束; （CC）计算距离>参考距离; （DD）是; （EE）结束; （S110）基于起始帧和结束帧生成回归线; （S120）在回归线上选择一个点; （S130）计算任意点与任意帧之间的距离; （S140）将任意帧决定为参照帧; （S310）基于参考帧将帧划分成至少两个组; （S320）生成与由起始框架和端框制成的线平行的倾斜块
-
公开(公告)号：KR101592670B1
公开(公告)日：2016-02-11
申请号：KR1020140017645
申请日：2014-02-17
Applicant: 포항공과대학교 산학협력단
IPC: G06F17/30
Abstract: 인덱스를이용하는데이터검색장치및 방법이개시된다. 인덱스를이용하는데이터검색장치는사용자질의에상응하여데이터베이스에서검색된적어도하나의데이터를수신하고데이터식별 ID 및특성벡터를포함하는데이터식별정보를기반으로수신된적어도하나의데이터를식별하는데이터수집부, 적어도하나의데이터에서데이터식별정보를추출하고추출된데이터식별정보를조합하여인덱스(index)를생성하는인덱스생성부및 인덱스와미리구축된데이터정렬모델을이용하여적어도하나의데이터에대한랭킹점수를산출하는랭킹연산부를포함한다. 따라서, 데이터검색의속도및 효율성을향상시킬수 있다.
-
公开(公告)号：KR1020150061700A
公开(公告)日：2015-06-05
申请号：KR1020130145512
申请日：2013-11-27
Applicant: 포항공과대학교 산학협력단
IPC: G06Q50/10
Abstract: 컨텐츠추천을위한사용자프로파일링방법및 장치가개시된다. 사용자프로파일링장치에서수행되는사용자프로파일링방법으로사용자의컨텐츠사용이력을미리설정된시간단위로분할한후, 각시간대의사용이력에기초하여컨텐츠를사용하는사용자그룹을매핑하여생성되는시간단위별사용자그룹을유사도에기초하여통합하고생성된시간단위별사용자그룹을상기유사도에기초하여최종적인사용자그룹으로적용할것인지판단하는과정을포함한다. 따라서, 컨텐츠추천을위한사용자프로파일링방법및 장치는시간에기반한컨텐츠사용자그룹을통해서, 컨텐츠추천시스템에서컨텐츠를사용하는다양한사용자의취향을분리하여집약함으로써사용자에게원하는컨텐츠를정확하게추천하여제공할수 있다.
Abstract translation: 公开了一种用于内容推荐系统的用户分析的方法和装置。 在用户分析设备中执行用户分析的方法包括以下步骤：以预定时间单位分割用户的内容使用历史; 根据每个时区的使用历史映射内容用户组，每次生成用户组; 基于相似度，每个时间整合用户组; 并且基于相似性来确定每个时间生成的用户组是否将被应用为最终用户组。 因此，用于内容推荐的用户分析的方法和装置可以通过使用来自内容推荐系统的内容分离各种用户的口味并通过基于时间的内容用户组进行集成来准确地推荐和提供用户想要的内容。
-
公开(公告)号：KR1020130035064A
公开(公告)日：2013-04-08
申请号：KR1020110099314
申请日：2011-09-29
Applicant: 삼성전자주식회사 , 포항공과대학교 산학협력단
CPC classification number: G06F17/30867
Abstract: PURPOSE: A personalized service providing method based on a personal preference and a system thereof are provided to increase the satisfaction of a user who has a lot of preferences without decreasing the recommendation satisfaction of a user who has a few preferences. CONSTITUTION: A service server(300) generates a user preference profile based on the user information and metadata of the content. The service server extracts a candidate recommendation result using a personalized type or a non-personalized type. The service server compares the extracted candidate recommendation result with the user preference profile. The service server ranks the candidate recommendation results corresponding to the user preference profile again. The service server outputs a customized recommendation result to a corresponding client(100). [Reference numerals] (200) Network; (300) Service server;
Abstract translation: 目的：提供一种基于个人偏好的个性化服务提供方法及其系统，以增加具有很多偏好的用户的满意度，而不降低具有少数偏好的用户的推荐满意度。 构成：服务服务器（300）基于内容的用户信息和元数据生成用户偏好简档。 服务服务器使用个性化类型或非个性化类型提取候选推荐结果。 服务服务器将提取的候选推荐结果与用户偏好简档进行比较。 服务服务器再次对与用户偏好配置文件相对应的候选推荐结果进行排序。 服务服务器向相应的客户机（100）输出定制的推荐结果。 （附图标记）（200）网络; （300）服务器;
-
公开(公告)号：KR101072691B1
公开(公告)日：2011-10-11
申请号：KR1020090067086
申请日：2009-07-23
Applicant: 포항공과대학교 산학협력단
Inventor： 유환조
IPC: G06F17/30
CPC classification number: G06F17/3053
Abstract: 랭킹방법을데이터베이스시스템에적용하여효율적인데이터베이스검색을가능하게하는연관성피드백을이용한데이터베이스검색방법및 이를수행하는프로그램을기록한기록매체가개시된다. 데이터베이스검색방법은, (a) 제1 검색결과에대한연관성피드백을제공받는단계와, (b) 제공된연관성피드백에기초하여연관성함수를도출하는단계및 (c) 제1 검색결과를연관성함수에적용하여연관성정도에따라정렬된제2 검색결과를제공하는단계를포함한다. 따라서연관성피드백과랭킹방법을이용하여적은양의피드백으로부터정확한연관성함수를도출할수 있어서사용자가원하는결과를얻기위하여모든검색결과를검토할필요가없이효율적인데이터베이스검색이가능하다.
-
-
-
-
-
-
-
-
-
Search Results
20
records
(took 0.059 seconds)
