专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

1. 发明申请

US20100131534A1 INFORMATION PROVIDING SYSTEM 审中-公开
标题翻译：信息提供系统
公开(公告)号：US20100131534A1
公开(公告)日：2010-05-27
申请号：US12595334
申请日：2008-04-09
申请人： Toshio Takeda , Susumu Akamine , Satoshi Nakazawa , Kai Ishikawa
发明人： Toshio Takeda , Susumu Akamine , Satoshi Nakazawa , Kai Ishikawa
IPC分类号： G06F17/30
CPC分类号： G06F17/21 , G06F17/27
摘要： An information providing system comprises: an associated document determining unit that determines at least one piece of associated document data that includes an expression equal or similar to a cited section based on a cited section in document data; a limiting expression extraction unit that extracts an expression that corresponds to a condition for, correction for, addition to, or annotation to an expression equal or similar to the cited section from associated document data determined by the associated document determining unit; an information creation unit that creates an expression extracted by the limiting expression extraction unit or information regarding this expression as information to be displayed; and a display unit that displays information created by the information creation unit.
摘要翻译：一种信息提供系统，包括：相关联的文档确定单元，基于文献数据中引用的部分，确定包括与所引用的部分相等或类似的表达的至少一条相关联的文档数据; 限制表达提取单元，从相关联的文档确定单元确定的相关联的文档数据中提取对应于与所引用的部分相同或相似的表达的校正，添加或注释的条件的表达式; 信息创建单元，其创建由限制表达式提取单元提取的表达或关于该表达式的信息作为要显示的信息; 以及显示单元，显示由信息创建单元创建的信息。

2. 发明申请

US20100218076A1 DOCUMENT ANALYZING METHOD, DOCUMENT ANALYZING SYSTEM AND DOCUMENT ANALYZING PROGRAM 审中-公开
标题翻译：文件分析方法，文件分析系统和文件分析程序
公开(公告)号：US20100218076A1
公开(公告)日：2010-08-26
申请号：US12738592
申请日：2008-10-10
申请人： Kai Ishikawa , Susumu Akamine , Satoshi Nakazawa , Toshio Takeda
发明人： Kai Ishikawa , Susumu Akamine , Satoshi Nakazawa , Toshio Takeda
IPC分类号： G06F17/00
CPC分类号： G06F17/2785
摘要： To obtain a document group in which an assertion standpoint with respect to a proposition and a ground for the assertion are the same between documents constituting the document group without using an expression concerning opinions or grounds, etc., in a document. A document analyzing method comprising: determining whether a ground for the assertion with respect to a proposition is the same or not based on whether citation source documents in the form of an electronic document cited in electronic documents are common or not; and combining, based on the determination result, electronic documents including an assertion with respect to a given proposition, between which the assertion standpoint on whether to affirm or deny the proposition or whether to be in a neutral standpoint with respect to the proposition and a ground for the assertion standpoint are the same, into one group.
摘要翻译：在文件中获取一个文件组，其中关于提出的断言立场和断言的理由在构成文件组的文件之间是相同的，而不使用关于意见或理由的表达等。一种文件分析方法，包括：基于电子文件中引用的电子文件的引用源文件是否共同，确定关于命题的断言的理由是否相同; 并根据确定结果，结合电子文件，其中包括关于给定命题的断言，其中断言是肯定还是否认该提议，或者是否就该提案而言处于中立立场因为断言立场是一样的，分为一组。

3. 发明授权

US08521674B2 Information analysis system, information analysis method, and information analysis program 有权
标题翻译：信息分析系统，信息分析方法和信息分析程序
公开(公告)号：US08521674B2
公开(公告)日：2013-08-27
申请号：US12596209
申请日：2008-04-25
申请人： Susumu Akamine , Satoshi Nakazawa , Kai Ishikawa , Toshio Takeda
发明人： Susumu Akamine , Satoshi Nakazawa , Kai Ishikawa , Toshio Takeda
IPC分类号： G06F17/00 , G06N5/00
CPC分类号： G06K9/00536
摘要： A system includes a time-series data pattern checking means that receives time-series data from an input device and extracts a time-series pattern corresponding to the received time-series, and an effective period determination means that extracts an effective period corresponding to the time-series pattern from a time-series pattern/effective period correspondence table stored in a time-series pattern/effective period correspondence table storage means. The effective period determination means determines effective period time-series data which is a portion of the time-series data received from the input device in the effective period, according to the determined effective period and causes an output device to outputs the determined effective period and the determined effective period time-series data.
摘要翻译：系统包括时间序列数据模式检查装置，其从输入装置接收时间序列数据并提取与所接收的时间序列相对应的时间序列模式，以及有效周期确定装置，其提取对应于存储在时间序列图形/有效期间对应表存储装置中的时间序列图形/有效期间对应表的时间序列图形。有效期确定装置根据所确定的有效期间，确定在有效期间从输入装置接收到的时间序列数据的一部分的有效期间时间序列数据，并使输出装置输出所确定的有效期，确定的有效期时间序列数据。

4. 发明申请

US20100076990A1 INFORMATION ANALYSIS SYSTEM, INFORMATION ANALYSIS METHOD, AND INFORMATION ANALYSIS PROGRAM 有权
标题翻译：信息分析系统，信息分析方法和信息分析方案
公开(公告)号：US20100076990A1
公开(公告)日：2010-03-25
申请号：US12596209
申请日：2008-04-25
申请人： Susumu Akamine , Satoshi Nakazawa , Kai Ishikawa , Toshio Takeda
发明人： Susumu Akamine , Satoshi Nakazawa , Kai Ishikawa , Toshio Takeda
IPC分类号： G06F17/30
CPC分类号： G06K9/00536
摘要： A system includes a time-series data pattern checking means that receives time-series data from an input device and extracts a time-series pattern corresponding to the received time-series, and an effective period determination means that extracts an effective period corresponding to the time-series pattern from a time-series pattern/effective period correspondence table stored in a time-series pattern/effective period correspondence table storage means. The effective period determination means determines effective period time-series data which is a portion of the time-series data received from the input device in the effective period, according to the determined effective period and causes an output device to outputs the determined effective period and the determined effective period time-series data.
摘要翻译：系统包括时间序列数据模式检查装置，其从输入装置接收时间序列数据并提取与所接收的时间序列相对应的时间序列模式，以及有效周期确定装置，其提取对应于存储在时间序列图形/有效期间对应表存储装置中的时间序列图形/有效期间对应表的时间序列图形。有效期确定装置根据所确定的有效期间，确定在有效期间从输入装置接收到的时间序列数据的一部分的有效期间时间序列数据，并使输出装置输出所确定的有效期，确定的有效期时间序列数据。

5. 发明授权

US08983977B2 Question answering device, question answering method, and question answering program 有权
标题翻译：问答设备，问答方法和问答方案
公开(公告)号：US08983977B2
公开(公告)日：2015-03-17
申请号：US12281350
申请日：2007-02-20
申请人： Kai Ishikawa , Susumu Akamine
发明人： Kai Ishikawa , Susumu Akamine
IPC分类号： G06F7/00 , G06F17/30
CPC分类号： G06F17/30654 , G06F17/30401 , G06F17/30646 , G06F17/30663 , G06F17/30666
摘要： A question-answering device, a question-answering method, and a question-answering program that can obtain an answer to an inputted query with high probability are described. A score calculation element 305 determines a matching degree between the group of the style and the topic of an inputted query and the group of the style and the topic of the query of question-answer pairs. A search result presentation element 306 narrows the question-answer pairs on the basis of the matching degree.
摘要翻译：描述可以以高概率获得输入查询的答案的问答设备，问答方法和问答程序。分数计算元件305确定所输入的查询的样式组和主题的组与问答对查询的样式和主题的组之间的匹配程度。搜索结果呈现元素306基于匹配度来缩小问答对。

6. 发明授权

US08583435B2 Request content identification system, request content identification method using natural language, and program 有权
标题翻译：请求内容识别系统，使用自然语言请求内容识别方法和程序
公开(公告)号：US08583435B2
公开(公告)日：2013-11-12
申请号：US12224885
申请日：2007-03-09
申请人： Kai Ishikawa , Susumu Akamine , Shinichi Ando
发明人： Kai Ishikawa , Susumu Akamine , Shinichi Ando
IPC分类号： G10L15/18 , G06F17/27
CPC分类号： G06F17/30637 , G06F17/30663 , G10L17/00 , G10L17/22
摘要： A request content identification system performs an audio recognition process according to audio data inputted from an input device (100b) and performs a request analysis process by using a common rule stored in common rule storage means (401) and a request unique rule stored in request unique rule storage means (402). Moreover, the request content identification system performs a similar document search process between the audio recognition result and an information request sentence or a reply stored in replay request data storage means (404). Request candidate score calculation means (304c) calculates an integrated score from an audio recognition score, a request analysis score, and a similar document search score obtained by the respective processes. Request identification result generation means (302b) identifies the request content having the highest integrated score and sends it to an output device (200).
摘要翻译：请求内容识别系统根据从输入装置（100b）输入的音频数据进行音频识别处理，并通过使用存储在通用规则存储装置（401）中的公共规则和存储在请求中的请求唯一规则来执行请求分析处理唯一规则存储装置（402）。此外，请求内容识别系统执行音频识别结果与信息请求语句之间的类似的文档搜索处理或存储在重放请求数据存储装置（404）中的答复。请求候选分数计算装置（304c）根据各个处理获得的音频识别分数，请求分析分数和类似文档搜索分数来计算积分分数。请求识别结果生成装置（302b）识别具有最高积分分数的请求内容并将其发送到输出装置（200）。

7. 发明申请

US20090099840A1 Request Content Identification System, Request Content Identification Method Using Natural Language, and Program 有权
标题翻译：请求内容识别系统，使用自然语言和程序的请求内容识别方法
公开(公告)号：US20090099840A1
公开(公告)日：2009-04-16
申请号：US12224885
申请日：2007-03-09
申请人： Kai Ishikawa , Susumu Akamine , Shinichi Ando
发明人： Kai Ishikawa , Susumu Akamine , Shinichi Ando
IPC分类号： G06F17/27
CPC分类号： G06F17/30637 , G06F17/30663 , G10L17/00 , G10L17/22
摘要： A request content identification system performs an audio recognition process according to audio data inputted from an input device (100b) and performs a request analysis process by using a common rule stored in common rule storage means (401) and a request unique rule stored in request unique rule storage means (402). Moreover, the request content identification system performs a similar document search process between the audio recognition result and an information request sentence or a reply stored in replay request data storage means (404). Request candidate score calculation means (304c) calculates an integrated score from an audio recognition score, a request analysis score, and a similar document search score obtained by the respective processes. Request identification result generation means (302b) identifies the request content having the highest integrated score and sends it to an output device (200).
摘要翻译：请求内容识别系统根据从输入装置（100b）输入的音频数据进行音频识别处理，并通过使用存储在通用规则存储装置（401）中的公共规则和存储在请求中的请求唯一规则来执行请求分析处理唯一规则存储装置（402）。此外，请求内容识别系统执行音频识别结果与信息请求语句之间的类似的文档搜索处理或存储在重放请求数据存储装置（404）中的答复。请求候选分数计算装置（304c）根据各个处理获得的音频识别分数，请求分析分数和类似文档搜索分数来计算积分分数。请求识别结果生成装置（302b）识别具有最高积分分数的请求内容并将其发送到输出装置（200）。

8. 发明申请

US20090012926A1 QUESTION ANSWERING DEVICE, QUESTION ANSWERING METHOD, AND QUESTION ANSWERING PROGRAM 有权
标题翻译：问题解答设备，问题解答方法和问题解答程序
公开(公告)号：US20090012926A1
公开(公告)日：2009-01-08
申请号：US12281350
申请日：2007-02-20
申请人： Kai Ishikawa , Susumu Akamine
发明人： Kai Ishikawa , Susumu Akamine
IPC分类号： G06N5/02 , G06F7/06 , G06F17/30
CPC分类号： G06F17/30654 , G06F17/30401 , G06F17/30646 , G06F17/30663 , G06F17/30666
摘要： A question-answering device, a question-answering method, and a question-answering program that can obtain an answer to an inputted query with high probability are described. A score calculation element 305 determines a matching degree between the group of the style and the topic of an inputted query and the group of the style and the topic of the query of question-answer pairs. A search result presentation element 306 narrows the question-answer pairs on the basis of the matching degree.
摘要翻译：描述可以以高概率获得输入查询的答案的问答设备，问答方法和问答程序。分数计算元件305确定所输入的查询的样式组和主题的组与问答对查询的样式和主题的组之间的匹配程度。搜索结果呈现元素306基于匹配度来缩小问答对。

9. 发明授权

US08447589B2 Text paraphrasing method and program, conversion rule computing method and program, and text paraphrasing system 有权
标题翻译：文本改写方法和程序，转换规则计算方法和程序，以及文本翻译系统
公开(公告)号：US08447589B2
公开(公告)日：2013-05-21
申请号：US12448421
申请日：2007-12-21
申请人： Kai Ishikawa , Susumu Akamine
发明人： Kai Ishikawa , Susumu Akamine
IPC分类号： G06F17/27
CPC分类号： G06F17/2795 , G06F17/28
摘要： A paraphrase model of a question text inputted by a user is learned, and a paraphrase expression is generated in real time. When information in text set storage unit is updated, text pair extracting unit extracts a paraphrase text pair from the text set storage unit and stores it in text pair storage unit. Model learning unit learns a question text paraphrase model from the paraphrase text pair in text pair storage unit, and stores it in model storage unit. Text pair extracting unit extracts a paraphrase text pair again from the text set storage unit by using the question text paraphrase model which the model storage unit possesses, and stores it in the text pair storage unit. In case where the stored paraphrase text pair is the same as the paraphrase text pair stored in the text pair storage unit, learning of the question text paraphrase model is ended. Candidate creating unit reads the question text paraphrase model from the model storage unit and generates a paraphrase candidate of the inputted question text.
摘要翻译：学习用户输入的问题文本的释义模型，并实时地生成释义表达式。当文本集存储单元中的信息被更新时，文本对提取单元从文本集存储单元中提取释义文本对，并将其存储在文本对存储单元中。模型学习单元从文字对存储单元中的释义文本对中学习一个问题文本改写模型，并将其存储在模型存储单元中。文本对提取单元通过使用模型存储单元拥有的问题文本解释模型，从文本集存储单元再次提取释义文本对，并将其存储在文本对存储单元中。在存储的释义文本对与存储在文本对存储单元中的释义文本对相同的情况下，问题文本解释模型的学习结束。候选创建单元从模型存储单元读取问题文本替代模型，并生成输入的问题文本的释义候选。

10. 发明申请

US20100010803A1 TEXT PARAPHRASING METHOD AND PROGRAM, CONVERSION RULE COMPUTING METHOD AND PROGRAM, AND TEXT PARAPHRASING SYSTEM 有权
标题翻译：文本记录方法和程序，转换规则计算方法和程序以及文本记录系统
公开(公告)号：US20100010803A1
公开(公告)日：2010-01-14
申请号：US12448421
申请日：2007-12-21
申请人： Kai Ishikawa , Susumu Akamine
发明人： Kai Ishikawa , Susumu Akamine
IPC分类号： G06F17/27
CPC分类号： G06F17/2795 , G06F17/28
摘要： A paraphrase model of a question text inputted by a user is learned, and a paraphrase expression is generated in real time. When information in text set storage unit is updated, text pair extracting unit extracts a paraphrase text pair from the text set storage unit and stores it in text pair storage unit. Model learning unit learns a question text paraphrase model from the paraphrase text pair in text pair storage unit, and stores it in model storage unit. Text pair extracting unit extracts a paraphrase text pair again from the text set storage unit by using the question text paraphrase model which the model storage unit possesses, and stores it in the text pair storage unit. In case where the stored paraphrase text pair is the same as the paraphrase text pair stored in the text pair storage unit, learning of the question text paraphrase model is ended. Candidate creating unit reads the question text paraphrase model from the model storage unit and generates a paraphrase candidate of the inputted question text.
摘要翻译：学习用户输入的问题文本的释义模型，并实时地生成释义表达式。当文本集存储单元中的信息被更新时，文本对提取单元从文本集存储单元中提取释义文本对，并将其存储在文本对存储单元中。模型学习单元从文字对存储单元中的释义文本对中学习一个问题文本改写模型，并将其存储在模型存储单元中。文本对提取单元通过使用模型存储单元拥有的问题文本解释模型，从文本集存储单元再次提取释义文本对，并将其存储在文本对存储单元中。在存储的释义文本对与存储在文本对存储单元中的释义文本对相同的情况下，问题文本解释模型的学习结束。候选创建单元从模型存储单元读取问题文本替代模型，并生成输入的问题文本的释义候选。

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