-
公开(公告)号:KR1020000037702A
公开(公告)日:2000-07-05
申请号:KR1019980052351
申请日:1998-12-01
Applicant: 한국전자통신연구원
IPC: G06K9/00
Abstract: PURPOSE: A position recognition method of a pattern is proposed to recognize the position of a pattern and apply to all patterns with no affection of feature or structure of a pattern. CONSTITUTION: A position recognition method of a pattern with no affection of feature or structure of a pattern is composed of image input step(101), relative position movement step(102), pixel area extraction step(103), similarity calculation step(104), and maximum similarity calculation step(105). At image input step, a source and target image are inputted using camera or image input device. The relative position movement step moves pixels of target image by one pixel with i and C direction to get a degree of similarity between source and target image. The pixel area extraction step extracts a pixel area, in the target image, with the same size to the source image executing the relative position movement step. If a pixel area with the same size to the source image is extracted, the similarity calculation step calculates the degree of similarity between source and target image. The similarity degree is from 0 to 1. If the degree is 0, source and target image are not similar at all. If the degree is 1, the two images are same.
Abstract translation: 目的:提出了一种模式的位置识别方法来识别图案的位置,并适用于不受图案特征或结构影响的所有图案。 构成:不影响图案的特征或结构的图案的位置识别方法由图像输入步骤(101),相对位置移动步骤(102),像素区域提取步骤(103),相似度计算步骤(104) )和最大相似度计算步骤(105)。 在图像输入步骤中,使用相机或图像输入装置输入源图像和目标图像。 相对位置移动步骤通过i和C方向将目标图像的像素移动一个像素,以获得源图像和目标图像之间的相似程度。 像素区域提取步骤将目标图像中的像素区域以相同的大小提取到执行相对位置移动步骤的源图像。 如果提取与源图像具有相同大小的像素区域,则相似度计算步骤计算源图像和目标图像之间的相似度。 相似度为0到1.如果度数为0,则源图像和目标图像根本不相似。 如果度数为1,则两张图像相同。
-
公开(公告)号:KR1020000037587A
公开(公告)日:2000-07-05
申请号:KR1019980052214
申请日:1998-12-01
Applicant: 한국전자통신연구원
IPC: G01B11/16
Abstract: PURPOSE: A method for detecting protrusion by using shadow is provided to automatically and visually check an existence, position, and angle of a protrusion or concave/convex portion of an object by taking a photograph of the object put on the floor. CONSTITUTION: A method for detecting protrusion by using shadow includes the steps of radiating a light beam on an object by a lighting element and inputting a reflected image by an image input element, analyzing a shadow shape of the input image and determinating existence of a protrusion, and measuring a position and angle of the protrusion by a maximum length in an internal blank of an ellipse due to the protrusion in the shadow shape if the protrusion is exist, wherein the lighting element is a diffused light source of ring illuminator or a spot light source, a radiating angle of the lighting element is perpendicular or inclined by a predetermined angle with relation to the object, and the existence of the protrusion is determined by comparing the length of the inner blank of the protrusion and the length of the protrusion.
Abstract translation: 目的:提供通过使用阴影来检测突起的方法,通过拍摄放置在地板上的物体的照片来自动和目视地检查物体的突起或凹/凸部分的存在,位置和角度。 构成:通过使用阴影检测突起的方法包括以下步骤:通过照明元件将光束照射在物体上并通过图像输入元件输入反射图像,分析输入图像的阴影形状并确定突起的存在 并且如果存在突起,则由于阴影形状的突起而在椭圆形的内部坯件中测量突起的位置和角度的最大长度,其中照明元件是环形照明器的漫射光源或点 光源,照明元件的照射角度相对于物体垂直或倾斜预定角度,并且突起的存在通过比较突起的内部坯件的长度和突起的长度来确定。
-
73.
公开(公告)号:KR101770599B1
公开(公告)日:2017-08-23
申请号:KR1020120128758
申请日:2012-11-14
Applicant: 한국전자통신연구원
Abstract: 본발명에의한소셜미디어에서영향력있는사용자를검색하기위한장치, 시스템및 그방법이개시된다. 본발명에따른소셜미디어에서영향력있는사용자를검색하기위한장치는사용자로부터관심을가지고있는대상에상응하는키워드를입력받는입력부; 입력받은상기키워드를포함하는검색요청메시지를송신하여송신된상기검색요청메시지에상응하는검색응답메시지를수신하는통신부; 상기검색응답메시지를수신하면, 수신된상기검색응답메시지로부터상기키워드에관련된영향력있는사용자가기 설정된영향력순위에따라나열된검색리스트를추출하는제어부; 추출된상기검색리스트를기반으로상기사용자로부터입력받은키워드에관련된영향력있는사용자를기 설정된영향력순위에따라순차적으로표시하는표시부; 및추출된상기검색리스트를저장하는저장부를포함한다.
Abstract translation: 公开了根据本发明的用于在社交媒体中搜索有影响的用户的装置,系统和方法。 根据本发明的用于在社交媒体中搜索有影响力用户的装置包括:输入单元,用于从用户接收与感兴趣对象相对应的关键词; 通信单元,用于发送包括输入关键字的搜索请求消息并接收与发送的搜索请求消息相对应的搜索响应消息; 控制器,用于接收搜索响应消息并从搜索响应消息中提取根据与关键字有关的有影响力的用户设置的影响力等级排列的搜索列表; 显示单元,根据预定的影响力排名,基于提取的搜索列表顺序地显示与从用户输入的关键字相关的有影响力的用户; 以及用于存储提取的搜索列表的存储单元。
-
公开(公告)号:KR101735312B1
公开(公告)日:2017-05-16
申请号:KR1020130033232
申请日:2013-03-28
Applicant: 한국전자통신연구원
CPC classification number: G06F17/30705 , G06F17/3053 , G06Q50/00 , G06Q50/01
Abstract: 본발명에의한소셜미디어분석을기반으로복합이슈를탐지하기위한장치, 시스템및 그방법이개시된다. 본발명에따른소셜미디어분석을기반으로복합이슈를탐지하기위한시스템은사용자단말기로부터키워드를제공받아제공받은상기키워드에관련이있는유형별단일이슈들을탐지하는단일이슈탐지부; 탐지된상기유형별단일이슈들로부터유형별복합이슈들을탐지하는복합이슈탐지부; 탐지된유형별복합이슈들을분석하여그 분석한결과에따라상기유형별복합이슈들을순위화하는복합이슈순위화부; 및순위화된상기유형별복합이슈들을사용자들이마이크로트렌드를도출할수 있는기 설정된형태로구성하여그 구성된형태를사용자에게제공하는복합이슈구성부를포함한다.
-
75.
公开(公告)号:KR101695011B1
公开(公告)日:2017-01-10
申请号:KR1020110084704
申请日:2011-08-24
Applicant: 한국전자통신연구원
Inventor: 김현진
CPC classification number: G06F17/30616
Abstract: 토픽별 오피니언과소셜영향력자를기반으로토픽을탐지및 추적할수 있는장치및 방법이개시된다. 인터넷상의콘텐츠로부터토픽별오피니언을추출하여토픽-오피니언DB를생성하고, 소셜구성원을행태특성에기초하여순위화한소셜영향력자를추출하여토픽-소셜영향력자 DB를생성하는토픽오피니언분석장치와토픽-오피니언DB와토픽-소셜영향력자DB를저장하는지식데이터베이스및 지식데이터베이스를기반으로탐색이요청된대상토픽에대한오피니언을탐지하고, 대상토픽에대한소셜영향력자를검색하여검색된상기소셜영향력자에의해제공또는생성된콘텐츠를수집하여분석하는토픽탐지추적장치를포함하는토픽별오피니언과소셜영향력자를기반으로토픽을탐지하고추적하는시스템을제공한다. 또한, 인터넷상의콘텐츠로부터토픽별오피니언과소셜구성원을행태특성에기초하여순위화한소셜영향력자를추출하여토픽-오피니언 DB와토픽-소셜영향력자 DB로구성되는지식데이터베이스를생성하는단계와지식데이터베이스를기반으로탐색이요청된대상토픽에대한오피니언을탐지하고, 대상토픽에대한소셜영향력자를검색하여검색된소셜영향력자에의해제공또는생성된콘텐츠를수집하여분석하는토픽탐지추적단계를포함하는토픽별오피니언과소셜영향력자를기반으로토픽을탐지하고추적하는방법을제공한다. 따라서, 인터넷상의콘텐츠에서특정토픽에대한소셜구성원의반응을모니터링할수 있고, 특정토픽에대한소셜영향력자가어떠한영향력을보이는지추적할수 있다.
Abstract translation: 提供了能够基于每个主题的意见和社会影响者来检测和跟踪主题的系统及其方法。 基于每个主题的意见和社会影响者检测和跟踪主题的系统包括:主题意见分析装置,被配置为从因特网上的内容中提取每个主题的意见以生成主题意见数据库(DB), 并根据行为特征提取社会影响者,从而产生一个话题 - 社会影响者DB; 知识DB,被配置为存储主题意见DB和主题社会影响者DB; 以及主题检测和跟踪装置,被配置为基于所述知识DB检测所请求搜索的指定主题的意见,搜索所述指定主题的社会影响者,并且收集和分析由所搜索的社会影响者提供或生成的内容。
-
公开(公告)号:KR1020130089566A
公开(公告)日:2013-08-12
申请号:KR1020120075974
申请日:2012-07-12
Applicant: 한국전자통신연구원
IPC: G06F17/28
Abstract: PURPOSE: Interpretation method and interpretation device are provided to offer an interpretation service for multi-language multimedia by providing an automatic interpretation service in a multimedia platform. CONSTITUTION: A display unit (220) displays an interpretation option configuration menu to a source sentence as an interpretation target in which a category is designated. A user input unit (240) receives the interpretation option configuration from the user, a communication unit (230) transmits the interpretation option to an interpretation server and receives an interpretation results from the interpretation server. The interpretation option is an interpretation option for the entire data or partial data of the source sentence and the interpretation option received by the user input unit is determined according to the category of the source sentence. [Reference numerals] (210) Control unit; (220) Display unit; (230) Communication unit; (232) Message generating unit; (234) Transmitting unit; (236) Receiving unit; (240) User input unit
Abstract translation: 目的:提供解释方法和解释设备,通过在多媒体平台中提供自动翻译服务,为多语言多媒体提供口译服务。 构成:显示单元(220)向源语句显示解释选项配置菜单作为指定类别的解释对象。 用户输入单元(240)从用户接收解释选项配置,通信单元(230)将解释选项发送到解释服务器,并从解释服务器接收解释结果。 解释选项是对于源语句的整个数据或部分数据的解释选项,并且用户输入单元接收到的解释选项根据源语句的类别来确定。 (附图标记)(210)控制单元; (220)显示单元; (230)通讯单元; (232)消息生成单元; (234)发送单元; (236)接收单位; (240)用户输入单元
-
公开(公告)号:KR1020090041929A
公开(公告)日:2009-04-29
申请号:KR1020070107723
申请日:2007-10-25
Applicant: 한국전자통신연구원
CPC classification number: G06F17/30011 , G06F3/04895 , G06F9/453
Abstract: A method for offering a manual through the misoperation pattern analysis of a user equipment and a system therefor are provided to enable a user to efficient use a corresponding device through an efficient manual interface by collecting/recognizing patterns of frequent errors and offering a proper user manual announcement through the voice or display device. In case the inputted operation pattern of a user equipment is a misoperation pattern, a manual providing system searches manual information about the inputted misoperation pattern from an operation pattern sequence DB storing manuals corresponding to each maloperation pattern(300~315). In case the manual information is searched, a system extracts text information from the manual information(320), and then outputs the extracted text information through the voice or display device(325).
Abstract translation: 提供了通过用户设备及其系统的误操作模式分析提供手册的方法,以使用户能够通过收集/识别频繁错误的模式并提供适当的用户手册,通过有效的手动界面有效地使用相应的设备 通过语音或显示设备通知。 在用户设备的输入操作模式是误操作模式的情况下,手动提供系统从存储与每个错误操作模式(300〜315)相对应的手册的操作模式序列DB中搜索关于输入的误操作模式的手动信息。 在搜索手动信息的情况下,系统从手动信息提取文本信息(320),然后通过语音或显示装置输出提取的文本信息(325)。
-
公开(公告)号:KR1020090040943A
公开(公告)日:2009-04-28
申请号:KR1020070106376
申请日:2007-10-23
Applicant: 한국전자통신연구원
IPC: G06F15/00
CPC classification number: G06F21/32
Abstract: An olfactory sense base authentication system and a method thereof for performing user personal authentication by sensing olfactory information of the body of a user are provided to sense the inherent olfactory sense bio-information of the body of the user. An olfactory sensor unit(10) senses the inherent olfactory sense bio-information of the body of user according to the sensing request control of a controller(50). A sensing vector generator produces a plurality of sensing vectors from sensing values which become with the digitalization [digitalize] provided from a plurality of olfactory sensors. A learning unit(20) reads the initial studying request control of the controller, the comparative object olfactory sense organism information vector and study frequency. The storage stores the learned comparative object olfactory sense organism information vector and the comparative object olfactory sense organism information vector learned with the study frequency and authenticator(30).
Abstract translation: 提供了一种用于通过感测用户身体的嗅觉信息进行用户个人认证的嗅觉感知基础认证系统及其方法,以感测用户的身体的固有的嗅觉感知生物信息。 嗅觉传感器单元(10)根据控制器(50)的感测请求控制来感测用户身体的固有嗅觉感知生物信息。 感测矢量发生器从多个嗅觉传感器提供的数字化[数字化]中获得的感测值产生多个感测向量。 学习单元(20)读取控制器的初始学习请求控制,比较对象嗅觉有机体信息向量和学习频率。 存储存储学习的比较对象嗅觉感知生物信息向量和与学习频率和认证者学习的比较对象嗅觉生物体信息向量(30)。
-
公开(公告)号:KR1020080052382A
公开(公告)日:2008-06-11
申请号:KR1020070119262
申请日:2007-11-21
Applicant: 한국전자통신연구원
IPC: H04N21/45
CPC classification number: H04N21/45 , G06F17/2705 , G06F17/30 , H04N21/8126
Abstract: An apparatus and a method for providing interactive information are provided to analyze the request of a user on the basis of an interactive input received from the user and offer information corresponding to the analyzed result. A dialogue sentence analyzing unit(20) analyzes an input sentence received from a user. A dialogue management unit(30) analyzes the request of the user through the analyzed result of the dialogue sentence analyzing unit. When a real-time information update is requested from the dialogue management unit, an automatic knowledge constructing unit(70) extracts daily life information updated on a web in real time and stores the extracted daily life information in a daily information database. A response generating unit(40) generates a response for the request of the user analyzed in the dialogue management unit and provides the generated response to the user. When it is impossible to respond to the request of the user or an error exists in the response for the request of the user, an exception processing unit(80) recovers a system to allow the user to cancel the request of the user.
Abstract translation: 提供一种用于提供交互信息的装置和方法,用于基于从用户接收到的交互式输入来分析用户的请求,并提供与分析结果相对应的信息。 对话句分析单元(20)分析从用户接收的输入语句。 对话管理单元(30)通过对话句分析单元的分析结果分析用户的请求。 当从对话管理单元请求实时信息更新时,自动知识构建单元(70)实时地提取在web上更新的日常生活信息,并将提取的日常生活信息存储在日常信息数据库中。 响应生成单元(40)生成对话管理单元中分析的用户的请求的响应,并向用户提供生成的响应。 当不可能响应于用户的请求或在用户的请求的响应中存在错误时,异常处理单元(80)恢复系统以允许用户取消用户的请求。
-
公开(公告)号:KR100829401B1
公开(公告)日:2008-05-15
申请号:KR1020070064985
申请日:2007-06-29
Applicant: 한국전자통신연구원
IPC: G06F17/27
CPC classification number: G06F17/2755 , G06F17/30705
Abstract: A method and a device for recognizing a fine-grained named entity are provided to recognize a fine-grained named entity class without increasing time needed for recognizing and learning the fine-grained named entity largely even if the number of fine-grained named entity classes is increased. A morpheme analyzer(100) analyzes morphemes of inputted text. A named entity quality recognizer(200) recognizes a named entity quality of each morpheme by using at least one of databases(D1-D4). A candidate named entity recognizer(300) recognizes a candidate named entity by using a named entity recognition model(M1) based on a named entity quality recognition result. A large class named entity classifier(400) classifies a large class named entity by using a large class named entity classification model(M2) based on a candidate named entity recognition result. A large class named entity classification re-ranker(500) ranks again a large class named entity classification result. A fine-grained named entity classifier(600) classifies a fine-grained named entity by using a fine-grained named entity classification model(M3) based on a large class named entity classification re-ranking result.
Abstract translation: 提供了一种用于识别细粒度命名实体的方法和设备,以便在不增加用于识别和学习细粒度命名实体所需的时间的情况下,即使是细粒度的命名实体类的数量也能够识别细粒度的命名实体类 增加了。 语素分析器(100)分析输入文本的语素。 命名实体质量识别器(200)通过使用数据库(D1-D4)中的至少一个来识别每个语素的命名实体质量。 名为实体识别器(300)的候选者基于命名实体质量识别结果,通过使用命名实体识别模型(M1)来识别候选命名实体。 一个大类命名实体分类器(400)通过使用名为实体分类模型(M2)的大类,基于候选的实体识别结果对大类命名实体进行分类。 一个大类命名实体分类重新排序(500)再次排列了一个大类命名实体分类结果。 一个细粒度的命名实体分类器(600)通过使用基于大类命名实体分类重新排序结果的细粒度命名实体分类模型(M3)对细粒度命名实体进行分类。
-
-
-
-
-
-
-
-
-