专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

31. 发明授权

US07587389B2 Question answering system, data search method, and computer program 失效
标题翻译：问答系统，数据搜索方法和计算机程序
公开(公告)号：US07587389B2
公开(公告)日：2009-09-08
申请号：US11298855
申请日：2005-12-12
申请人： Daigo Sugihara , Hiroshi Masuichi , Tomoko Ohkuma , Hiroki Yoshimura
发明人： Daigo Sugihara , Hiroshi Masuichi , Tomoko Ohkuma , Hiroki Yoshimura
IPC分类号： G06F17/30 , G06F17/27
CPC分类号： G06F17/30654 , Y10S707/99933
摘要： A question answering system includes a question input unit input to a question, a search unit, an anaphoric analysis unit, an information extraction unit and an answer candidate extraction unit. The search unit executes search processing based on the input question. The anaphoric analysis unit executes anaphoric analysis processing on a search result. The information extraction unit extracts sentences, which include expressions having a reference relation therebetween, as reference relation sentences, the reference relation determined by finding relation in an expressions of at least one of a noun phrase, a pronoun, and a zero pronoun between sentences in the search result on a basis of a result of the anaphoric analysis; selects a first candidate sentence from a passage obtained as the search result; and selects a second candidate sentence, which is the reference relation sentence of the first candidate sentence. The answer candidate extraction unit extracts an answer candidate.
摘要翻译：问答系统包括向问题输入的问题输入单元，搜索单元，比喻分析单元，信息提取单元和答复候选提取单元。搜索单元基于输入的问题执行搜索处理。比喻分析单元对搜索结果执行图像分析处理。信息提取单元提取句子，其包括其间具有参考关系的表达式作为参考关系句子，该参考关系通过在名词短语，代词和句子之间的零代词中的至少一个的表达中找到关系而确定基于比喻分析结果的搜索结果; 从作为搜索结果获得的段落中选择第一候选句子; 并选择作为第一候选句子的参考关系句子的第二候选句子。答案候选者提取单元提取答案候选者。

32. 发明授权

US07418443B2 Question answering system, data search method, and computer program 有权
标题翻译：问答系统，数据搜索方法和计算机程序
公开(公告)号：US07418443B2
公开(公告)日：2008-08-26
申请号：US11302226
申请日：2005-12-14
申请人： Hiroki Yoshimura , Hiroshi Masuichi , Tomoko Ohkuma , Daigo Sugihara
发明人： Hiroki Yoshimura , Hiroshi Masuichi , Tomoko Ohkuma , Daigo Sugihara
IPC分类号： G06F7/00 , G06F17/30 , G06F17/27
CPC分类号： G06F17/30654 , G06F17/30684 , Y10S707/99934
摘要： A question answering system includes a question answering unit, an analysis unit, a tree structure generation unit, a feature extraction unit, an evaluation unit and a re-ranking unit. The question answering unit executes search processing based on an input question and acquires answer candidates to the question. The analysis unit executes syntactic analysis processing or syntactic and semantic analysis processing on a passage obtained as a result of the search processing. The tree structure generation unit generates a tree structure based on an analysis result. The feature extraction unit extracts a relation between a search word applied in the search processing and each acquired answer candidate as a feature corresponding to each answer candidate from the tree structure. The evaluation unit determines an evaluation value of each answer candidate based on the feature extracted. The re-ranking unit re-ranks the answer candidates based on the evaluation values.
摘要翻译：问答系统包括问答单元，分析单元，树结构生成单元，特征提取单元，评价单元和重排单元。问答单元根据输入的问题执行搜索处理，并获得问题的答案。分析单元对作为搜索处理的结果获得的段落执行句法分析处理或句法和语义分析处理。树结构生成单元基于分析结果生成树结构。特征提取单元从树结构中提取在搜索处理中应用的搜索词与每个获取的答案候选之间的关系作为与每个答案候选相对应的特征。评估单元基于所提取的特征来确定每个候选答案的评估值。重新排名单位根据评估值重新排列候选人。

33. 发明申请

US20080016065A1 DOCUMENT SEARCH SYSTEM, DOCUMENT SEARCH PROCESSING METHOD, AND DOCUMENT SEARCH PROCESSING PROGRAM 审中-公开
标题翻译：文件搜索系统，文档搜索处理方法和文档搜索处理程序
公开(公告)号：US20080016065A1
公开(公告)日：2008-01-17
申请号：US11692252
申请日：2007-03-28
申请人： Motoyuki TAKAAI , Hiroshi Masuichi
发明人： Motoyuki TAKAAI , Hiroshi Masuichi
IPC分类号： G06F17/30
CPC分类号： G06F16/93
摘要： A document search system includes: a first acquiring portion that acquires a first medical finding; a first searching portion that searches past report information for a second medical finding similar to the first medical finding acquired by the first acquiring portion, the past report information including the second medical finding and a corresponding word of the second medical finding, which is a word defined for the second medical finding; a second searching portion that searches for document information that includes the corresponding word of the second medical finding included in the past report information searched by the first searching portion, the document information being a medical evidence of the first medical finding; and a display controller that displays on a display portion, the document information searched by the second searching portion.
摘要翻译：文件搜索系统包括：获取第一医疗结果的第一获取部分; 第一搜索部分，其搜索过去的报告信息，用于与由第一获取部分获取的第一医疗查询类似的第二医疗查找，包括第二医疗查找的过去报告信息和作为第二医疗结果的对应词，其是单词为第二次医疗结果定义; 第二搜索部分，搜索包括由第一搜索部分搜索的过去报告信息中包括的第二医疗查找的相应单词的文档信息，文档信息是第一医疗结果的医学证据; 以及显示控制器，其在显示部分上显示由第二搜索部分搜索到的文档信息。

34. 发明申请

US20060235689A1 Question answering system, data search method, and computer program 有权
标题翻译：问答系统，数据搜索方法和计算机程序
公开(公告)号：US20060235689A1
公开(公告)日：2006-10-19
申请号：US11299746
申请日：2005-12-13
申请人： Daigo Sugihara , Hiroshi Masuichi , Hiroki Yoshimura , Tomoko Ohkuma
发明人： Daigo Sugihara , Hiroshi Masuichi , Hiroki Yoshimura , Tomoko Ohkuma
IPC分类号： G10L15/18
CPC分类号： G10L15/1822 , G06F17/2785 , G06F17/30654
摘要： A question answering system includes a question input unit, a search unit, an answer candidate extraction unit, an answer candidate inspection unit and an answer output unit. The search unit executes search processing based on an input question. The answer candidate extraction unit extracts an initial answer candidate based on a result of the search processing. The answer candidate inspection unit inspects the initial answer candidate. The answer candidate inspection unit executes search processing with using a query including the initial answer candidate. The answer candidate inspection unit determines whether each word of a sentence obtained as a result of the search processing has a similar lexical meaning to that of each word of the input question. The answer candidate inspection unit selects an initial answer candidate contained in a query determined to have the similar lexical meaning, as a secondary answer candidate.
摘要翻译：问答系统包括问题输入单元，搜索单元，答案候选提取单元，答案候选检查单元和答复输出单元。搜索单元基于输入的问题执行搜索处理。应答候选提取单元基于搜索处理的结果来提取初始答案候选。答复候选人检查单位检查初始答复候选人。应答候选者检查单元使用包括初始答案候选的查询执行搜索处理。答案候选者检查单元确定作为搜索处理结果获得的句子的每个单词是否具有与输入问题的每个单词相似的词汇意义。答案候选人检查单元选择包含在确定具有相似词汇意义的查询中的初始答案候选者作为次要答案候选者。

35. 发明申请

US20060206481A1 Question answering system, data search method, and computer program 有权
公开(公告)号：US20060206481A1
公开(公告)日：2006-09-14
申请号：US11232379
申请日：2005-09-22
申请人： Tomoko Ohkuma , Hiroshi Masuichi , Hiroki Yoshimura , Daigo Sugihara
发明人： Tomoko Ohkuma , Hiroshi Masuichi , Hiroki Yoshimura , Daigo Sugihara
IPC分类号： G06F17/30
CPC分类号： G06F17/30654 , Y10S707/99933 , Y10S707/99937 , Y10S707/99938 , Y10S707/99939
摘要： A question answering system includes a question-sentence analysis unit, a search unit, an answer-candidate extraction unit, a check-expression generation unit, a check-expression search unit and an answer-candidate correction unit. The question-sentence analysis unit extracts a keyword applied to a search process from an input question sentence. The search unit executes the search process with using the extracted keyword. The answer-candidate extraction unit extracts answer candidates for the input question sentence based on a search result. The check-expression generation unit analyzes the input question sentence to generate a check expression concatenating an analysis result and the extracted answer candidates. The check-expression search unit executes a search process based on the generated check expression. The answer-candidate correction unit selects an output answer to the input question from among answer the candidates based on a search result.

36. 发明授权

US06321189B1 Cross-lingual retrieval system and method that utilizes stored pair data in a vector space model to process queries 有权
标题翻译：跨语言检索系统和方法利用向量空间模型中存储的对数据来处理查询
公开(公告)号：US06321189B1
公开(公告)日：2001-11-20
申请号：US09343543
申请日：1999-06-30
申请人： Hiroshi Masuichi , Hiroshi Umemoto , Masakazu Tateno
发明人： Hiroshi Masuichi , Hiroshi Umemoto , Masakazu Tateno
IPC分类号： G06F1728
CPC分类号： G06F17/2755 , G06F17/2827 , G06F17/30666 , G06F17/30669 , G06F17/30684 , Y10S707/99935
摘要： The cross-lingual retrieval system of the present invention retrieves second language sentences which are appropriate translations of a query written in a first language using pair data without being greatly influenced by the difference in expression between the query and sentences to be the object of retrieval, length of the query or sentences to be the object of retrieval or the like. In the system, a pair data storing unit stores multiple pairs each having a first language sentence and a second language sentence having the same meaning. As a query receiving unit receives a query written in the first language, a first retrieving unit retrieves first language sentences similar to the query from a set of first language sentences stored in the pair data storing unit. A second retrieving unit then retrieves second language sentences similar to second language sentences paired with the respective first language sentences retrieved by the first retrieving unit from a set of second language sentences stored in the pair data storing unit. That is, a first retrieval of first language sentences from the pair data is performed based on a query, and then a second retrieval of second language sentences from the pair data is performed based on the result of the first retrieval.
摘要翻译：本发明的跨语言检索系统使用对数据检索作为第一语言编写的查询的适当翻译的第二语言句子，而不受作为检索对象的查询和句子之间的表达差异的很大影响，作为检索对象的查询或句子的长度等。在该系统中，一对数据存储单元存储多个具有相同含义的第一语言句和第二语句的多对。当查询接收单元接收以第一语言编写的查询时，第一检索单元从存储在对数据存储单元中的一组第一语言句子中检索类似于查询的第一语言句子。第二检索单元然后从存储在对数据存储单元中的一组第二语言句子中检索类似于与由第一检索单元检索的相应第一语言句子配对的第二语言句子的第二语言句子。也就是说，基于查询执行从对数据中的第一语言句子的第一次检索，然后基于第一次检索的结果执行来自对数据的第二语言句子的第二次检索。

37. 发明授权

US5905980A Document processing apparatus, word extracting apparatus, word extracting method and storage medium for storing word extracting program 失效
标题翻译：文件处理装置，文字提取装置，文字提取方法以及用于存储文字提取程序的存储介质
公开(公告)号：US5905980A
公开(公告)日：1999-05-18
申请号：US933113
申请日：1997-09-18
申请人： Hiroshi Masuichi , Hiroshi Umemoto , Masakazu Tateno
发明人： Hiroshi Masuichi , Hiroshi Umemoto , Masakazu Tateno
IPC分类号： G06F17/30
CPC分类号： G06F17/30616 , Y10S707/961 , Y10S707/99931 , Y10S707/99933 , Y10S707/99935
摘要： The present invention provides a document processing apparatus, word extracting apparatus, word extracting method and storage medium for storing a word extracting program, capable of appropriately presenting effective associate words to the user. A retrieving element executes retrieval of documents based on a retrieval condition inputted through a retrieval condition inputting element. A keyword designating element designates an arbitrary word among the words included in the retrieved documents as an associate-word-searching word and designates other words as candidates for an associate word. A simultaneous appearance probability calculating element calculates a simultaneous appearance probability of the associate-word-searching word and one of the candidates for the associate word in any of the retrieved documents. A first independent appearance probability calculating element obtains an independent appearance probability of the associate-word-searching word in each of all documents. A second independent appearance probability calculating element calculates an independent appearance probability of each of the candidates for the associate word in each of all documents. A calculating element calculates the sum or product of the independent appearance probability of the associate-word-searching word and the independent appearance probability of each of the candidates for the associate word. An associate word extracting element extracts a word according to the ratio of the simultaneous appearance probability to the sum or product calculated by the calculating element.
摘要翻译：本发明提供一种用于存储字提取程序的文档处理装置，字提取装置，字提取方法和存储介质，能够向用户适当地呈现有效的关联词。检索元素基于通过检索条件输入元素输入的检索条件执行文档的检索。关键词指定元素将检索到的文档中包含的单词中的任意字指定为关联词搜索词，并将其他单词指定为关联词的候选。同时出现概率计算元件计算在任何检索到的文档中的关键词搜索词和关联词的候选之一的同时出现概率。第一独立出现概率计算元件在所有文档的每一个中获得关联词搜索词的独立出现概率。第二独立出现概率计算元件计算每个所有文档中关联词的每个候选者的独立出现概率。计算元素计算关联词搜索词的独立出现概率与关联词的每个候选者的独立出现概率的和或乘积。关联词提取元素根据同时出现概率与由计算元素计算的和或乘积的比率提取单词。

38. 发明授权

US07805303B2 Question answering system, data search method, and computer program 有权
标题翻译：问答系统，数据搜索方法和计算机程序
公开(公告)号：US07805303B2
公开(公告)日：2010-09-28
申请号：US11299746
申请日：2005-12-13
申请人： Daigo Sugihara , Hiroshi Masuichi , Hiroki Yoshimura , Tomoko Ohkuma
发明人： Daigo Sugihara , Hiroshi Masuichi , Hiroki Yoshimura , Tomoko Ohkuma
IPC分类号： G10L15/00 , G06F17/28
CPC分类号： G10L15/1822 , G06F17/2785 , G06F17/30654
摘要： A question answering system includes a question input unit, a search unit, an answer candidate extraction unit, an answer candidate inspection unit and an answer output unit. The search unit executes search processing based on an input question. The answer candidate extraction unit extracts an initial answer candidate based on a result of the search processing. The answer candidate inspection unit inspects the initial answer candidate. The answer candidate inspection unit executes search processing with using a query including the initial answer candidate. The answer candidate inspection unit determines whether each word of a sentence obtained as a result of the search processing has a similar lexical meaning to that of each word of the input question. The answer candidate inspection unit selects an initial answer candidate contained in a query determined to have the similar lexical meaning, as a secondary answer candidate.
摘要翻译：问答系统包括问题输入单元，搜索单元，答案候选提取单元，答案候选检查单元和答复输出单元。搜索单元基于输入的问题执行搜索处理。应答候选提取单元基于搜索处理的结果来提取初始答案候选。答复候选人检查单位检查初始答复候选人。应答候选者检查单元使用包括初始答案候选的查询执行搜索处理。答案候选者检查单元确定作为搜索处理结果获得的句子的每个单词是否具有与输入问题的每个单词相似的词汇意义。答案候选人检查单元选择包含在确定具有相似词汇意义的查询中的初始答案候选者作为次要答案候选者。

39. 发明申请

US20080071782A1 CONCEPTUAL NETWORK GENERATING SYSTEM, CONCEPTUAL NETWORK GENERATING METHOD, AND PROGRAM PRODUCT THEREFOR 有权
标题翻译：概念网络生成系统，概念网络生成方法及其程序产品
公开(公告)号：US20080071782A1
公开(公告)日：2008-03-20
申请号：US11688902
申请日：2007-03-21
申请人： Hiroki Yoshimura , Motoyuki Takaai , Hiroshi Masuichi
发明人： Hiroki Yoshimura , Motoyuki Takaai , Hiroshi Masuichi
IPC分类号： G06F17/30
CPC分类号： G06F17/30731
摘要： A conceptual network generating system that generates a conceptual network showing conceptual relations between words, the conceptual network generating system including: a first searching unit that searches a knowledge source storing search sentences; a first generating unit that analyzes the retrieved first search result sentence; a holding unit that stores the generated first structure information in a memory unit; a second searching unit that searches the knowledge source; a second generating unit that analyzes the retrieved second search result sentence; a calculating unit that calculates similarity between the generated second structure information and the stored first structure information; and a setting unit that generates conceptual network information.
摘要翻译：概念网络生成系统，其生成显示词之间的概念关系的概念网络，所述概念网络生成系统包括：搜索存储搜索句子的知识源的第一搜索单元; 第一生成单元，分析检索到的第一搜索结果句; 保持单元，其将所生成的第一结构信息存储在存储单元中; 搜索知识源的第二搜索单元; 第二生成单元，分析检索到的第二搜索结果句; 计算单元，其计算所生成的第二结构信息和所存储的第一结构信息之间的相似度; 以及生成概念网络信息的设置单元。

40. 发明申请

US20060206472A1 Question answering system, data search method, and computer program 有权
标题翻译：问答系统，数据搜索方法和计算机程序
公开(公告)号：US20060206472A1
公开(公告)日：2006-09-14
申请号：US11231947
申请日：2005-09-22
申请人： Hiroshi Masuichi , Daigo Sugihara , Tomoko Ohkuma , Hiroki Yoshimura
发明人： Hiroshi Masuichi , Daigo Sugihara , Tomoko Ohkuma , Hiroki Yoshimura
IPC分类号： G06F17/30
CPC分类号： G06F17/30654 , G06F17/2785 , G06F17/30672 , G06F17/30867
摘要： A question answering system includes a similar-question generation unit, a first search unit, a second search unit, and an answer selection unit. The similar-question generation unit selects a feature word from an input question to generate a transformational question in which the feature word is replaced with another word. The first search unit executes a first search process based on the transformational question. The second search unit selects a word included in a first search result acquired as an extension word and executes a second search process with using the selected extension word. The answer selection unit analyzes a correspondence relation among extension words included in a second search result, determines the feature word and a constructive part of an answer equivalent word in the second search result based on an analysis result, and selects a word determined to be an answer.
摘要翻译：问答系统包括类似问题生成单元，第一搜索单元，第二搜索单元和应答选择单元。类似问题生成单元从输入问题中选择特征词以产生其中特征词被替换为另一个词的变换问题。第一搜索单元基于转换问题执行第一搜索处理。第二搜索单元选择作为扩展字获取的第一搜索结果中包含的单词，并使用所选择的扩展字执行第二搜索处理。答案选择单元分析包括在第二搜索结果中的扩展词之间的对应关系，基于分析结果确定特征词和第二搜索结果中的答案等效词的构造部分，并且选择确定为回答。

你已经成功收藏专利！

检索式保存成功!

IPRDB

热门服务

关于我们

友情链接

联系方式