公开(公告)号：US08380713B2

公开(公告)日：2013-02-19

申请号：US12814220

申请日：2010-06-11

申请人： Hyo-Jung Oh ,  Chung-Hee Lee ,  Soo-Jong Lim ,  Jeong Heo ,  Hyun-Ki Kim ,  Mi-Ran Choi ,  Yeo-Chan Yoon ,  Chang-Ki Lee ,  Yi-Gyu Hwang ,  Myung-Gil Jang

发明人： Hyo-Jung Oh ,  Chung-Hee Lee ,  Soo-Jong Lim ,  Jeong Heo ,  Hyun-Ki Kim ,  Mi-Ran Choi ,  Yeo-Chan Yoon ,  Chang-Ki Lee ,  Yi-Gyu Hwang ,  Myung-Gil Jang

IPC分类号： G06F17/30

CPC分类号： G06F17/30654

摘要： Provides is an apparatus for question answering based on answer trustworthiness including: an answer indexer that indexes documents of which document trustworthiness satisfying a threshold value among documents included in a document collection and stores it in a knowledge Bases; an answer candidate extractor that extracts answer candidate documents for a user's question from the knowledge Bases; an answer source trustworthiness measurement unit; an answer extraction strategy trustworthiness measurement unit; and a trustworthiness integrator that generates an answer candidate trustworthiness list by ranking the answer candidate documents on the basis of the document trustworthiness, the source trustworthiness, and the extraction strategy trustworthiness of the answer candidate documents.

摘要翻译： 提供是一种基于应答可信赖性的问答设备，包括：答案索引器，其对包含在文档集合中的文档中的哪个文档信任度满足阈值的文档进行索引，并将其存储在知识库中; 答案候选者提取器，从知识基础中提取用户问题的答案候选文件; 答案源可信度测量单位; 答案提取策略可信度测量单位; 以及可信度积分器，其通过基于答复候选文档的文档可信度，源可信度和提取策略的可信度来对答案候选文档进行排名来生成答复候选可信度列表。

公开(公告)号：US20100023549A1

公开(公告)日：2010-01-28

申请号：US12417232

申请日：2009-04-02

申请人： Miran CHOI ,  Jeong Heo ,  Myung Gil Jang ,  Hyunki Kim ,  Yi Gyu Hwang ,  Chung Hee Lee ,  Soojong Lim ,  Hyo-Jung Oh ,  Chang Ki Lee ,  Yeo Chan Yoon

发明人： Miran CHOI ,  Jeong Heo ,  Myung Gil Jang ,  Hyunki Kim ,  Yi Gyu Hwang ,  Chung Hee Lee ,  Soojong Lim ,  Hyo-Jung Oh ,  Chang Ki Lee ,  Yeo Chan Yoon

IPC分类号： G06F17/30

CPC分类号： G06F16/48

摘要： A method for social tagging using a property field of an ontology object includes: selecting an object in an ontology database storing therein objects in forms of classes; selecting a property field in a class corresponding to the selected object; and adding a social tag by storing user's input as a value of the selected property field. Classes stored in the ontology database may have property fields defined when instances of the classes are created, and specific values may be stored as values of the property fields also when the instances are created. The property fields defined when the instances are created are classified into data type property fields and object type property field, and the selected property field is a data type property field.

摘要翻译： 使用本体对象的属性字段进行社会标记的方法包括：以存储在对象中的对象的类的形式选择本体数据库中的对象; 选择与所选对象相对应的类中的属性字段; 并通过将用户的输入存储为所选属性字段的值来添加社交标签。 存储在本体数据库中的类可以在创建类的实例时定义属性字段，并且在实例创建时也可以将特定值存储为属性字段的值。 创建实例时定义的属性字段分为数据类型属性字段和对象类型属性字段，所选属性字段是数据类型属性字段。

公开(公告)号：US20070233673A1

公开(公告)日：2007-10-04

申请号：US11701955

申请日：2007-02-02

申请人： Hee-Cheol Seo ,  Soo-Jun Park ,  Myung-Gil Jang ,  Hyun-Ki Kim ,  Yi-Gyu Hwang ,  Soo-Jong Lim ,  Jeong Heo

发明人： Hee-Cheol Seo ,  Soo-Jun Park ,  Myung-Gil Jang ,  Hyun-Ki Kim ,  Yi-Gyu Hwang ,  Soo-Jong Lim ,  Jeong Heo

IPC分类号： G06F17/30

CPC分类号： G06F17/30023 ,  Y10S707/99933

摘要： Provided are an apparatus and method for searching multimedia data based on metadata. The apparatus for searching multimedia data includes: a mapping information storing unit for storing and managing mapping information between a Moving Picture Experts Group 7 (MPEG-7) query attribute and an MPEG-7 metadata property; and a query attribute mapping unit for acquiring the MPEG-7 metadata property to be mapped with the MPEG-7 query attribute according to a user query based on the mapping information.

摘要翻译： 提供了一种基于元数据来搜索多媒体数据的装置和方法。 用于搜索多媒体数据的装置包括：映射信息存储单元，用于在运动图像专家组7（MPEG-7）查询属性和MPEG-7元数据属性之间存储和管理映射信息; 以及查询属性映射单元，用于根据基于映射信息的用户查询获取要与MPEG-7查询属性映射的MPEG-7元数据属性。

公开(公告)号：US20110145251A1

公开(公告)日：2011-06-16

申请号：US12787946

申请日：2010-05-26

申请人： Chang Ki LEE ,  Myung Gil JANG ,  Yeo Chan YOON ,  Mi Ran CHOI ,  Hyun Ki KIM ,  Pum Mo RYU ,  Soo Jong LIM ,  Yi Gyu HWANG ,  Chung Hee LEE ,  Hyo Jung OH ,  Jeong HEO

发明人： Chang Ki LEE ,  Myung Gil JANG ,  Yeo Chan YOON ,  Mi Ran CHOI ,  Hyun Ki KIM ,  Pum Mo RYU ,  Soo Jong LIM ,  Yi Gyu HWANG ,  Chung Hee LEE ,  Hyo Jung OH ,  Jeong HEO

IPC分类号： G06F17/30

CPC分类号： G06F17/278 ,  G06F16/374 ,  G06F17/2735

摘要： A system and method for constructing a named entity dictionary are disclosed. The method includes analyzing a structure of collected Web text, extracting tabulated or listed information from the Web text, extracting a named entity from the tabulated or listed information, categorizing the extracted named entity, and registering the categorized named entity in a named entity dictionary.

摘要翻译： 公开了一种用于构建命名实体字典的系统和方法。 该方法包括分析收集的Web文本的结构，从Web文本中提取列表或列出的信息，从列表或列出的信息中提取命名实体，对提取的命名实体进行分类，并将命名实体字典中的分类命名实体注册。

公开(公告)号：US20110087656A1

公开(公告)日：2011-04-14

申请号：US12814220

申请日：2010-06-11

申请人： Hyo-Jung OH ,  Chung-Hee LEE ,  Soo-Jong LIM ,  Jeong HEO ,  Hyun-Ki KIM ,  Mi-Ran CHOI ,  Yeo-Chan YOON ,  Chang-Ki LEE ,  Yi-Gyu HWANG ,  Myung-Gil JANG

发明人： Hyo-Jung OH ,  Chung-Hee LEE ,  Soo-Jong LIM ,  Jeong HEO ,  Hyun-Ki KIM ,  Mi-Ran CHOI ,  Yeo-Chan YOON ,  Chang-Ki LEE ,  Yi-Gyu HWANG ,  Myung-Gil JANG

IPC分类号： G06F17/30

CPC分类号： G06F17/30654

摘要： Provides is an apparatus for question answering based on answer trustworthiness including: an answer indexer that indexes documents of which document trustworthiness satisfying a threshold value among documents included in a document collection and stores it in a knowledge Bases; an answer candidate extractor that extracts answer candidate documents for a user's question from the knowledge Bases; an answer source trustworthiness measurement unit; an answer extraction strategy trustworthiness measurement unit; and a trustworthiness integrator that generates an answer candidate trustworthiness list by ranking the answer candidate documents on the basis of the document trustworthiness, the source trustworthiness, and the extraction strategy trustworthiness of the answer candidate documents.

摘要翻译： 提供是一种基于应答可信赖性的问答设备，包括：答案索引器，其对包含在文档集合中的文档中的哪个文档信任度满足阈值的文档进行索引，并将其存储在知识库中; 答案候选者提取器，从知识基础中提取用户问题的答案候选文件; 答案源可信度测量单位; 答案提取策略可信度测量单位; 以及可信度积分器，其通过基于答复候选文档的文档可信度，源可信度和提取策略的可信度来对答案候选文档进行排名来生成答复候选可信度列表。

公开(公告)号：US20100153094A1

公开(公告)日：2010-06-17

申请号：US12484651

申请日：2009-06-15

申请人： Chung Hee LEE ,  Hyo-Jung Oh ,  Jeong Heo ,  Yi Gyu Hwang ,  Yeo Chan Yoon ,  Miran Choi ,  Chang Ki Lee ,  Soojong Lim ,  HyunKi Kim ,  Myung Gil Jang

发明人： Chung Hee LEE ,  Hyo-Jung Oh ,  Jeong Heo ,  Yi Gyu Hwang ,  Yeo Chan Yoon ,  Miran Choi ,  Chang Ki Lee ,  Soojong Lim ,  HyunKi Kim ,  Myung Gil Jang

IPC分类号： G06F17/27 ,  G06F17/30

CPC分类号： G06F17/30654

摘要： A topic map based indexing apparatus analyzes community Q/A lists to acquire Q/A analysis information, removes redundant answers depending on the Q/A analysis information, removes insignificant answers based on the degree of reliability, ranks answer lists, and extracts the highest ranking answer as a best answer, to thereby store, in a community Q/A topic map, index information containing the community Q/A lists and the Q/A analysis information. A topic map based searching apparatus analyzes a user question to acquire question analysis information, searches similar questions from community Q/A lists belonging to a specific topic node of a pre-stored community Q/A topic map, ranks the searched similar questions depending on the question analysis information, removes redundant answers among answers to the ranked similar questions, ranks the answers, and extracts the highest ranking answer as a best answer.

摘要翻译： 基于主题地图的索引设备分析社区Q / A列表以获取Q / A分析信息，根据Q / A分析信息删除冗余答案，根据可靠性程度删除不重要的答案，排列答案列表，并提取最高 排名答案作为最佳答案，从而在社区Q / A主题地图中存储包含社区Q / A列表和Q / A分析信息的索引信息。 基于主题图的搜索装置分析用户问题以获取问题分析信息，从属于预存的社区Q / A主题图的特定主题节点的社区Q / A列表中搜索类似的问题，根据 问题分析信息，删除排名相似的问题的答案之间的冗余答案，排列答案，并提取最高排名答案作为最佳答案。

公开(公告)号：US20090076798A1

公开(公告)日：2009-03-19

申请号：US12153896

申请日：2008-05-27

申请人： Hyo Jung Oh ,  Chung Hee Lee ,  Chang Ki Lee ,  Yi Gyu Hwang ,  Ji Hyun Wang ,  Myung Gil Jang

发明人： Hyo Jung Oh ,  Chung Hee Lee ,  Chang Ki Lee ,  Yi Gyu Hwang ,  Ji Hyun Wang ,  Myung Gil Jang

IPC分类号： G06F17/28

CPC分类号： G06F17/279 ,  G10L15/063 ,  G10L15/1815 ,  G10L15/22

摘要： Provided are an apparatus and method for post-processing a dialogue error in a speech dialogue system using multilevel verification, in which both of a user's current utterance and a whole dialogue flow are taken into account through the multilevel verification including speech recognition results analysis, linguistic analysis, discourse analysis and dialogue analysis. As a result, various errors that may occur in the speech dialogue system are detected, and error post-processing appropriate to a detected error type is performed, so that speech recognition errors may be reduced.

摘要翻译： 提供了一种使用多级验证在语音对话系统中后处理对话错误的装置和方法，其中通过包括语音识别结果分析，语言识别结果分析在内的多级验证考虑了用户的当前语音和整个对话流两者 分析，话语分析和对话分析。 结果，检测到语音对话系统中可能发生的各种错误，并且执行适合于检测到的错误类型的错误后处理，从而可以减少语音识别错误。

公开(公告)号：US07412093B2

公开(公告)日：2008-08-12

申请号：US11071446

申请日：2005-03-04

申请人： Eui Sok Chung ,  Soojung Lim ,  Yi Gyu Hwang ,  Myung Gil Jang

发明人： Eui Sok Chung ,  Soojung Lim ,  Yi Gyu Hwang ,  Myung Gil Jang

IPC分类号： G06K9/00 ,  G06F7/00

CPC分类号： G10L15/1822 ,  G10L2015/027 ,  Y10S707/99936

摘要： An apparatus and a hybrid method for recognizing answer type are disclosed. The apparatus includes: a morpheme analyzer for analyzing morphemes of an input text; a syllabic answer type recognizer for extracting a predetermined size syllable from a morpheme list and recognizing an answer type based on the extracted syllable; a vocabulary feature recognizer for allocating feature to each morpheme and recognizing the feature; a vocabulary feature disambiguation unit for disambiguating vocabulary feature ambiguity of morphemes having more than one feature; a pattern rule answer type recognizer for recognizing an answer type by comparing a consecutive sequence of the morphemes and a consecutive sequence of constitutional features connected to the morphemes with a pre-constructed pattern rules; a statistic answer type recognizer for recognizing an answer type by implementing a statistic model; and an answer type sub-category recognizer for recognizing a sub-category of the recognized answer type classified to general category.

摘要翻译： 公开了用于识别答案类型的装置和混合方法。 该装置包括：用于分析输入文本的语素的语素分析器; 用于从语素列表中提取预定大小的音节并基于所提取的音节识别答案类型的音节应答类型识别器; 用于将特征分配给每个语素并识别特征的词汇特征识别器; 用于消除具有多于一个特征的词素的词汇特征歧义的词汇特征消歧单元; 模式规则应答类型识别器，用于通过将语素的连续序列与连接到语素的连续的宪法特征序列与预先构建的模式规则进行比较来识别答案类型; 用于通过实施统计模型识别答案类型的统计答案类型识别器; 以及用于识别分类为一般类别的所识别的答复类型的子类别的应答类型子类别识别器。

公开(公告)号：US20080134038A1

公开(公告)日：2008-06-05

申请号：US11951154

申请日：2007-12-05

申请人： Hyo Jung OH ,  Chung Hee Lee ,  Hyeon Jin Kim ,  Chang Ki Lee ,  Yi Gyu Hwang ,  Ji Hyun Wang ,  Myung Gil Jang ,  Yun Keun Lee

发明人： Hyo Jung OH ,  Chung Hee Lee ,  Hyeon Jin Kim ,  Chang Ki Lee ,  Yi Gyu Hwang ,  Ji Hyun Wang ,  Myung Gil Jang ,  Yun Keun Lee

IPC分类号： G06F17/27 ,  G10L15/00

CPC分类号： G10L15/26 ,  G06F16/9535

摘要： Provided are a method and apparatus for providing information according to a user's request, and more particularly, an interactive information providing service method and apparatus for analyzing a user's request and providing information corresponding to the request on the basis of a dialog input received from the user. The apparatus includes: a conversation sentence analyzer for analyzing an input sentence received from a user; a conversation manager for analyzing the user's request using an analysis result of the conversation sentence analyzer; a real-time automatic knowledge builder for extracting in real time daily information updated on the web and storing the information in a daily information database when there is a real-time information update request from the conversation manager; a response generator for generating a response to the user's request analyzed by the conversation manager and providing the response to the user; and an exception handler for allowing the user to cancel his/her request and restoring the system when it is not possible to respond to the user's request, or when there is an error in the response to the user's request. On the basis of dialog input, the method and apparatus analyze a user's request and provide information corresponding to the request, thereby enabling the user to easily obtain needed information.

摘要翻译： 提供了一种用于根据用户请求提供信息的方法和装置，更具体地，提供一种交互式信息提供服务方法和装置，用于分析用户的请求，并且基于从用户接收到的对话输入提供与该请求相对应的信息 。 该装置包括：会话语句分析器，用于分析从用户接收的输入语句; 会话管理器，用于使用会话语句分析器的分析结果来分析用户的请求; 实时自动知识构建器，用于当存在来自会话管理器的实时信息更新请求时，实时提取在网络上更新的日常信息，并将信息存储在日常信息数据库中; 响应发生器，用于产生对话管理器分析的用户请求的响应并向用户提供响应; 以及异常处理程序，用于允许用户在不可能响应用户的请求时，或当用户的请求的响应出现错误时，取消他/她的请求并恢复系统。 在对话输入的基础上，该方法和装置分析用户的请求并提供与请求对应的信息，从而使得用户能够容易地获得所需的信息。

公开(公告)号：US08050909B2

公开(公告)日：2011-11-01

申请号：US12153896

申请日：2008-05-27

申请人： Hyo Jung Oh ,  Chung Hee Lee ,  Chang Ki Lee ,  Yi Gyu Hwang ,  Ji Hyun Wang ,  Myung Gil Jang

发明人： Hyo Jung Oh ,  Chung Hee Lee ,  Chang Ki Lee ,  Yi Gyu Hwang ,  Ji Hyun Wang ,  Myung Gil Jang

IPC分类号： G06F17/27

CPC分类号： G06F17/279 ,  G10L15/063 ,  G10L15/1815 ,  G10L15/22

摘要： Provided are an apparatus and method for post-processing a dialogue error in a speech dialogue system using multilevel verification, in which both of a user's current utterance and a whole dialogue flow are taken into account through the multilevel verification including speech recognition results analysis, linguistic analysis, discourse analysis and dialogue analysis. As a result, various errors that may occur in the speech dialogue system are detected, and error post-processing appropriate to a detected error type is performed, so that speech recognition errors may be reduced.

摘要翻译： 提供了一种使用多级验证在语音对话系统中后处理对话错误的装置和方法，其中通过包括语音识别结果分析，语言识别结果分析在内的多级验证考虑了用户的当前语音和整个对话流两者 分析，话语分析和对话分析。 结果，检测到语音对话系统中可能发生的各种错误，并且执行适合于检测到的错误类型的错误后处理，从而可以减少语音识别错误。