公开(公告)号：US20160147739A1

公开(公告)日：2016-05-26

申请号：US14932425

申请日：2015-11-04

Applicant: Electronics and Telecommunications Research Institute

Inventor： Joon Ho LIM ,  Hyun Ki KIM ,  Pum Mo RYU ,  Yong Jin BAE ,  Hyo Jung OH ,  Chung Hee LEE ,  Soo Jong LIM ,  Myung Gil JANG ,  Mi Ran CHOI ,  Jeong HEO

IPC: G06F17/28

CPC classification number: G06F17/27

Abstract: An apparatus and method for updating a language analysis result are provided. The apparatus includes a storage unit configured to store language analysis result and language analysis metadata to be used for update of the language analysis result, and an update unit configured to reanalyze the language analysis metadata based on language knowledge which is added to language knowledge resources, and update the language analysis result based on the reanalyzed result.

Abstract translation: 提供了一种用于更新语言分析结果的装置和方法。 该装置包括：存储单元，被配置为存储要用于语言分析结果更新的语言分析结果和语言分析元数据;以及更新单元，被配置为基于添加到语言知识资源的语言知识重新分析语言分析元数据， 并根据重新分析结果更新语言分析结果。

公开(公告)号：US20150199335A1

公开(公告)日：2015-07-16

申请号：US14592482

申请日：2015-01-08

Applicant: Electronics and Telecommunications Research Institute

Inventor： Mi Ran CHOI ,  Hyun Ki KIM ,  Pum Mo RYU ,  Yong Jin BAE ,  Hyo Jung OH ,  Yeo Chan YOON ,  Chung Hee LEE ,  Soo Jong LIM ,  Myung Gil JANG ,  Yo Han JO ,  Yoon Jae CHOI ,  Jeong HEO

IPC: G06F17/28

CPC classification number: H04N21/4755 ,  H04N21/4668 ,  H04N21/8543

Abstract: Disclosed is a method of representing user language characteristics in a MPEG user description (MPEG-UD) system including receiving a request for a user description (UD) of the user language characteristics from a recommendation engine, calling the UD of the user language characteristics from a UD database, and transmitting the called UD of the user language characteristics to the recommendation engine.

Abstract translation: 公开了一种在MPEG用户描述（MPEG-UD）系统中表示用户语言特性的方法，包括从推荐引擎接收对用户语言特征的用户描述（UD）的请求，从用户语言特征的UD UD数据库，并将用户语言特征的被叫UD发送到推荐引擎。

公开(公告)号：US20150178267A1

公开(公告)日：2015-06-25

申请号：US14256078

申请日：2014-04-18

Applicant: Electronics and Telecommunications Research Institute

Inventor： Jeong HEO ,  Hyun Ki KIM ,  Sang Kyu PARK ,  Soo Jong LIM ,  Yoon Jae CHOI ,  Mi Ran CHOI ,  Pum Mo RYU ,  Yong Jin BAE ,  Yeo Chan YOON ,  Myung Gil JANG ,  Chung Hee LEE ,  Yo Han JO ,  Hyo Jung OH

IPC: G06F17/27 ,  G06F17/30 ,  H04L12/18

CPC classification number: G06F17/278 ,  G06F17/2785 ,  G06F17/30654 ,  G06F17/30684 ,  H04L51/32

Abstract: The present invention relates to a social media question and answer service, and discloses a social media issue processing device and method. The method includes a question analyzing unit which analyzes a question type of an input question through a question pattern dictionary which is stored in advance; a social media analyzing unit which performs issue period recognition for the question, question type based analysis, question based summary creation, and question based reliability calculation; and a report creating unit which creates a summary in accordance with at least one of correlation between the question type and the question based summary, correlation between the issue period and the question type based analysis result, and correlation between the reliability and the question based summary.

Abstract translation: 本发明涉及社交媒体问答机构，并且公开了社交媒体问题处理装置和方法。 该方法包括：问题分析单元，其通过预先存储的问题模式字典来分析输入问题的问题类型; 对问题执行问题周期识别，基于问题类型的分析，基于问题的摘要创建和基于问题的可靠性计算的社交媒体分析单元; 以及报告创建单元，其根据问题类型和基于问题的总结之间的相关性，问题周期与基于问题类型的分析结果之间的相关性以及可靠性和基于问题的总结之间的相关性中的至少一个来创建摘要 。

公开(公告)号：US20160147737A1

公开(公告)日：2016-05-26

申请号：US14932604

申请日：2015-11-04

Applicant: Electronics and Telecommunications Research Institute

Inventor： Pum Mo RYU ,  Hyun Ki KIM ,  Yong Jin BAE ,  Hyo Jung OH ,  Chung Hee LEE ,  Soo Jong LIM ,  Joon Ho LIM ,  Myung Gil JANG ,  Mi Ran CHOI ,  Jeong HEO

IPC: G06F17/27

CPC classification number: G06F17/2785 ,  G06F17/271 ,  G06F17/2755 ,  G06F17/277 ,  G06F17/2775 ,  G06F17/30401 ,  G06F17/30976

Abstract: Disclosed are a question answering system for structured knowledgebase using deep natural language question analysis, and a method thereof, the question answering system for structured knowledgebase using deep natural language question analysis includes a deep natural language question analysis unit configured to create a structure of a semantic frame by analyzing a natural language question that is input, a question-intermediate expression creation unit configured to create a question-intermediate expression of a lexicon level based on the semantic frame, a knowledgebase-specialized query creation unit configured to create a query used to search in knowledgebase that is a subject of search, based on the question-intermediate expression, and a knowledgebase search unit configured to find a correct answer in the knowledgebase that is subject of search based on the query, to provide an accuracy of the correct answer, a confidence of the correct answer and an evidence for the correct answer.

Abstract translation: 公开了使用深层自然语言问题分析的结构化知识库的问答系统及其方法，使用深层自然语言问题分析的结构化知识库的问答系统包括深层自然语言问题分析单元，其被配置为创建语义的结构 通过分析输入的自然语言问题，构造成基于所述语义帧创建词典级的问题中间表达式的问题中间表达式创建单元，所述知识库专用查询创建单元被配置为创建用于 在基于问题中间表达的搜索主题的知识库中搜索知识库搜索单元，以及知识库搜索单元，其被配置为在基于查询的搜索对象的知识库中找到正确的答案，以提供正确答案的准确性 对正确回答的信心和正确答案的证据 呃

公开(公告)号：US20160132485A1

公开(公告)日：2016-05-12

申请号：US14939016

申请日：2015-11-12

Applicant: Electronics and Telecommunications Research Institute

Inventor： Chung Hee LEE ,  Hyun Ki KIM ,  Pum Mo RYU ,  Yong Jin BAE ,  Hyo Jung OH ,  Soo Jong LIM ,  Joon Ho LIM ,  Myung Gil JANG ,  Mi Ran CHOI ,  Jeong HEO

IPC: G06F17/27

CPC classification number: G06F17/2735 ,  G06F17/2755 ,  G06F17/277

Abstract: A system and method for constructing a morpheme dictionary based on an automatic extraction of a non-registered word is provided. A non-registered word is automatically extracted based on a language-independent non-registered word automatic extraction method, and performance of a dictionary and a morpheme analysis is verified based on an automatic estimation by constructing a morpheme dictionary based on the automatically extracted non-registered word. Since the morpheme dictionary is constructed using only a dictionary in which a final verification is passed and it is helpful to improve the performance, the morpheme analysis can be properly performed on the non-registered word of a new field or a new word which newly appears as time passes.

Abstract translation: 提供了一种基于自动提取非注册字来构建语素字典的系统和方法。 基于与语言无关的非注册字自动提取方法自动提取未注册的字，并且基于自动估计，基于自动提取的非自动提取的非自动提取的非自动提取方法来验证词典和语素分析的性能， 注册字。 由于语素字典仅使用通过最终验证的字典构建，并且有助于提高性能，因此可以对新字段的非注册字或新出现的新词适当地执行语素分析 随着时间流逝。

公开(公告)号：US20130197898A1

公开(公告)日：2013-08-01

申请号：US13713511

申请日：2012-12-13

Applicant: Electronics and Telecommunications Research Institute

Inventor： Mi Ran CHOI ,  Hyun Ki KIM ,  Jeong HEO ,  Pum Mo RYU ,  Yeo Chan YOON ,  Chang Ki LEE ,  Yoon Jae CHOI ,  Myung Gil JANG ,  Chung Hee LEE ,  Hyeon Jin KIM ,  Hyo Jung OH ,  Yo Han JO

IPC: G06F17/28

CPC classification number: G06F17/28 ,  G06F17/289

Abstract: Disclosed is an apparatus for providing an accurate automatic language translation service. A user terminal according to an exemplary embodiment of the present invention includes a display unit to display a translation option setting menu for a user with respect to a source sentence of which a category is designated and to be translated; a user input unit to receive, from the user, an input on setting of a translation option; a communication unit to transmit the translation option to a translation server, and to receive a translation result from the translation server; and a control unit to control operations of the display unit, the user input unit, and the communication unit. According to the present invention, a translation service for multilingual multimedia through a natural styled highly precise automatic translation is enabled.

Abstract translation: 公开了一种用于提供准确的自动语言翻译服务的装置。 根据本发明的示例性实施例的用户终端包括：显示单元，用于针对用户指定类别的源语句和要翻译的用户显示翻译选项设置菜单; 用户输入单元，用于从用户接收关于翻译选项的设置的输入; 通信单元，用于将翻译选项传送到翻译服务器，并且从翻译服务器接收翻译结果; 以及控制单元，用于控制显示单元，用户输入单元和通信单元的操作。 根据本发明，通过自然风格的高精度自动翻译可以实现用于多语言多媒体的翻译服务。

公开(公告)号：US20160148101A1

公开(公告)日：2016-05-26

申请号：US14932471

申请日：2015-11-04

Applicant: Electronics and Telecommunications Research Institute

Inventor： Young Jik LEE ,  Hyun Ki KIM ,  Hyo Jung OH

IPC: G06N5/04 ,  G06N99/00

CPC classification number: G06N5/022 ,  G06Q10/10

Abstract: A knowledge evaluation apparatus, method, and system are provided. The knowledge evaluation apparatus includes an extraction module configured to extract at least one of triple information which is previously set with respect to a document for each field accumulated in an Internet community site; a classification module configured to classify and digitize the triple information extracted from the document for each field by a topic and an item; and a measurement module configured to measure knowledge maturity of the Internet community site based on the knowledge classified and digitized by the classification module.

Abstract translation: 提供知识评估装置，方法和系统。 所述知识评估装置包括提取模块，所述提取模块被配置为提取对于在互联网社区站点中累积的每个场地的文档预先设置的三重信息中的至少一个; 分类模块，被配置为通过主题和项目对每个字段从文档中提取的三重信息进行数字化和数字化; 以及测量模块，其被配置为基于由分类模块分类和数字化的知识来测量互联网社区站点的知识成熟度。

公开(公告)号：US20150193428A1

公开(公告)日：2015-07-09

申请号：US14256414

申请日：2014-04-18

Applicant: Electronics and Telecommunications Research Institute

Inventor： Soo Jong LIM ,  Yeo Chan YOON ,  Yoon Jae CHOI ,  Chung Hee LEE ,  Jeong HEO ,  Hyo Jung OH ,  Yo Han JO ,  Mi Ran CHOI ,  Myung Gil JANG ,  Hyun Ki KIM ,  Pum Mo RYU

IPC: G06F17/27 ,  G06F17/28

CPC classification number: G06F17/2785

Abstract: Disclosed is semantic frame operation, and disclosed are a text big data based semantic frame operating method including: collecting a predicate to be used as a semantic frame seed; configuring a synonym set for the collected predicate; collecting one or more examples in text big data in association with predicates included in the synonym set; extracting a semantic frame candidate by attaching a semantic case to the collected examples; performing error verification for the semantic frame candidate; and storing the semantic frame candidate subjected to the error verification as an extended semantic frame for the predicate, and an electronic device supporting the same.

Abstract translation: 公开了语义帧操作，并且公开了一种基于文本大数据的语义帧操作方法，包括：收集要用作语义帧种子的谓词; 为收集的谓词配置同义词集; 在与包含在同义词集中的谓词相关联的文本大数据中收集一个或多个示例; 通过将语义情况附加到所收集的示例来提取语义帧候选; 对语义帧候选进行错误验证; 并且将经过错误验证的语义帧候选存储为用于谓词的扩展语义帧，以及支持该谓词的电子设备。

公开(公告)号：US20150142780A1

公开(公告)日：2015-05-21

申请号：US14255410

申请日：2014-04-17

Applicant: ELECTRONICS AND TELECOMMUNICATIONS RESEARCH INSTITUTE

Inventor： Hyo Jung OH ,  Yong Jin BAE ,  Hyun Ki KIM ,  Chung Hee LEE ,  Yo Han JO ,  Soo Jong LIM ,  Jeong HEO ,  Yeo Chan YOON ,  Yoon Jae CHOI ,  Myung Gil JANG ,  Pum Mo RYU ,  Mi Ran CHOI

IPC: G06F17/30

CPC classification number: G06F16/338 ,  G06F16/313 ,  G06F16/9535 ,  G06F16/9537

Abstract: Provided are an apparatus for analyzing an event time-space correlation in a social web media and an operating method thereof. The apparatus includes a collection unit configured to collect a text type of document data from the social web media, a storage unit configured to store an event keyword indicating an event and event-related information including event time-space information corresponding to the event keyword, an extraction unit configured to linguistically analyze the document data to extract the event keyword and the event-related information associated with the event keyword from the document data based on a result of the linguistic analysis, and an output unit configured to receive the event keyword and event-related information and convert the received event keyword and event-related information into visual information and output the visual information.

Abstract translation: 提供了一种用于分析社交网络媒体中的事件时空相关性的装置及其操作方法。 所述装置包括：收集单元，其被配置为从所述社交网络媒体收集文本类型的文档数据;存储单元，被配置为存储指示事件的事件关键字以及包括与所述事件关键字对应的事件时空信息的事件相关信息， 提取单元，被配置为基于所述语言分析的结果来语言分析所述文档数据以从所述文档数据中提取与所述事件关键字相关联的事件关键字和事件相关信息;以及输出单元，被配置为接收所述事件关键字，以及 事件相关信息，并将接收到的事件关键字和事件相关信息转换为视觉信息并输出视觉信息。

公开(公告)号：US20140101293A1

公开(公告)日：2014-04-10

申请号：US13837698

申请日：2013-03-15

Applicant: Electronics and Telecommunications Research Institute

Inventor： Hyo Jung OH

IPC: H04L29/08

CPC classification number: H04L67/10 ,  G06Q50/01

Abstract: Disclosed is a technology for extracting issue information having high interests to users by recognizing contents of a sentence within media (including news, Tweet, and a blog), and automatically detecting and presenting an issue subject related to the issue information. A method of providing issue information according to the present invention includes: extracting an issue by extracting issue information according to a predetermined condition or a condition received from the outside by using data expressed with a text on media or meta data defining additional information on the data; and displaying an issue history or hotness of the extracted issue information which has been issued in the media to a user.

Abstract translation: 公开了一种通过识别媒体内的句子的内容（包括新闻，Tweet和博客）来提取对用户感兴趣的问题信息的技术，并且自动检测并呈现与发行信息有关的问题主题。 根据本发明的提供问题信息的方法包括：通过使用在媒体上表达的文本或者定义关于数据的附加信息的元数据来提取根据预定条件或从外部接收的条件的问题信息来提取问题 ; 并且向用户显示已经在媒体中发布的所提取的问题信息的问题历史或热度。