公开(公告)号：US20130325468A1

公开(公告)日：2013-12-05

申请号：US13985556

申请日：2011-10-21

申请人： Geun-Bae Lee ,  Sung-Jin Lee ,  Hyung-Jong Noh ,  Kyu-Song Lee

发明人： Geun-Bae Lee ,  Sung-Jin Lee ,  Hyung-Jong Noh ,  Kyu-Song Lee

IPC分类号： G10L25/51

CPC分类号： G10L25/51 ,  G09B19/04 ,  G09B19/06

摘要： Disclosed are a conversation management method and a device for executing same are disclosed. The device includes: a calculation unit for calculating the importance of an utterance intention, the similarity between utterance intentions, and the relative distance between utterance intentions using at least one of a plurality of utterance intentions in a corpus and an utterance intention in a sequence relationship with the at least one utterance intention; a similarity calculating unit for calculating the similarity between conversation flows by comparing a conversation flow obtained from a corpus and a conversation flow obtained from a user utterance by means of the importance and similarity of an utterance intention; and an utterance intention verifying unit for calculating an evaluation score of an utterance intention by evaluating a user utterance according to the relative distance between utterance intentions. Accordingly, the present invention enables the flow-processing of various conversations which are not processed in a typical information obtaining conversation device, and also determines the ranking of appropriate utterance intentions in each conversational situation by means of a score calculated by a ranking function in order to output the ranking.

摘要翻译： 公开了一种会话管理方法及其执行装置。 该装置包括：计算单元，用于计算发音意图的重要性，发音意图之间的相似性，以及使用语料库中的多个发音意图中的至少一个和语言意图之间的序列关系中的至少一个的话语意图之间的相对距离 至少有一个话语意图; 相似度计算单元，用于通过比较从语料库获得的会话流和通过用户话语获得的会话流量，借助于话语意图的重要性和相似性来计算会话流之间的相似性; 以及话语意图验证单元，用于通过根据发音意图之间的相对距离评估用户话语来计算发音意图的评价分数。 因此，本发明能够进行在典型的信息获取对话装置中未被处理的各种会话的流程处理，并且还可以通过按顺序由排序函数计算的分数来确定每个会话情况下的适当发声意图的排序 输出排名。

公开(公告)号：US20120197894A1

公开(公告)日：2012-08-02

申请号：US13498322

申请日：2010-10-11

申请人： Hyung Jong Noh ,  Jong Hoon Lee ,  Sung Jin Lee ,  Gary Geunbae Lee

发明人： Hyung Jong Noh ,  Jong Hoon Lee ,  Sung Jin Lee ,  Gary Geunbae Lee

IPC分类号： G06F17/30

CPC分类号： G06F17/30864 ,  G06F17/2745 ,  G09B19/06

摘要： Disclosed is an apparatus and method for processing documents to extract expressions and descriptions. The apparatus for processing documents includes a document collection unit, which collects documents from websites and divides each of the collected documents into a script portion and a description portion to thus generate a script document and a description document, and an expression extraction unit, which extracts expression description sentences on the basis of the description document, and extracts expressions described by the expression description sentences from the script document. According to the invention, study material, including a pair that comprises an expression to be studied and a description thereof, can be automatically constructed.

摘要翻译： 公开了一种用于处理提取表达和描述的文档的装置和方法。 用于处理文件的装置包括：文档收集单元，其收集来自网站的文档，并将每个所收集的文档划分为脚本部分和描述部分，从而生成脚本文档和描述文档;以及表达提取单元，其提取 表达式描述句子，并从脚本文档中提取由表达式描述句子描述的表达式。 根据本发明，可以自动构建包括要研究的表达式及其描述的对的研究材料。

公开(公告)号：US08666987B2

公开(公告)日：2014-03-04

申请号：US13498322

申请日：2010-10-11

申请人： Hyung Jong Noh ,  Jong Hoon Lee ,  Sung Jin Lee ,  Gary Geunbae Lee

发明人： Hyung Jong Noh ,  Jong Hoon Lee ,  Sung Jin Lee ,  Gary Geunbae Lee

IPC分类号： G06F7/00 ,  G06F17/30

CPC分类号： G06F17/30864 ,  G06F17/2745 ,  G09B19/06

摘要： Disclosed is an apparatus and method for processing documents to extract expressions and descriptions. The apparatus for processing documents includes a document collection unit, which collects documents from websites and divides each of the collected documents into a script portion and a description portion to thus generate a script document and a description document, and an expression extraction unit, which extracts expression description sentences on the basis of the description document, and extracts expressions described by the expression description sentences from the script document. According to the invention, study material, including a pair that comprises an expression to be studied and a description thereof, can be automatically constructed.

摘要翻译： 公开了一种用于处理提取表达和描述的文档的装置和方法。 用于处理文件的装置包括：文档收集单元，其收集来自网站的文档，并将每个所收集的文档划分为脚本部分和描述部分，从而生成脚本文档和描述文档;以及表达提取单元，其提取 表达式描述句子，并从脚本文档中提取由表达式描述句子描述的表达式。 根据本发明，可以自动构建包括要研究的表达式及其描述的对的研究材料。