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. 发明授权

US09015080B2 Systems and methods for semantic inference and reasoning 有权
标题翻译：语义推理与推理的系统与方法
公开(公告)号：US09015080B2
公开(公告)日：2015-04-21
申请号：US13422962
申请日：2012-03-16
申请人： Sameer Joshi , Todd Pehle , Larry Crochet
发明人： Sameer Joshi , Todd Pehle , Larry Crochet
IPC分类号： G06N5/02 , G06N99/00 , G06N5/04
CPC分类号： G06N5/04 , G06F17/30554 , G06F17/30598 , G06N99/005
摘要： A method and system for analyzing a corpus of data artifacts is disclosed. The method comprises obtaining, by a computer, a semantic representation of the data artifacts, where the semantic representation indicates (1) entities identified in the data artifacts, and (2) semantic relationships among the entities as indicated by the data artifacts. The method further comprises clustering the data artifacts into clusters of semantically related data artifacts based on the semantic representation and inferring additional semantic relationships between pairs of the entities. The inferring comprises applying, on a cluster-by-cluster basis, a multi-tiered network of inference engines to a portion of the semantic representation corresponding to the cluster, where the multi-tiered network of inference engines includes a domain-independent inference tier and a domain-specific inference tier.
摘要翻译：公开了一种用于分析数据伪影语料库的方法和系统。该方法包括由计算机获取数据工件的语义表示，其中语义表示指示（1）在数据工件中标识的实体，以及（2）由数据工件指示的实体之间的语义关系。该方法还包括基于语义表示将数据工件聚类成语义相关的数据工件簇，并推断出实体对之间的附加语义关系。推断包括将逐层的推理引擎的多层次网络应用于对应于该群集的语义表示的一部分，其中多层次的推理引擎网络包括与域无关的推理层和域特定推理层。

2. 发明申请

US20130246315A1 SYSTEMS AND METHODS FOR SEMANTIC INFERENCE AND REASONING 有权
公开(公告)号：US20130246315A1
公开(公告)日：2013-09-19
申请号：US13422962
申请日：2012-03-16
申请人： Sameer Joshi , Todd Pehle , Larry Crochet
发明人： Sameer Joshi , Todd Pehle , Larry Crochet
IPC分类号： G06N5/04 , G06F15/18
CPC分类号： G06N5/04 , G06F17/30554 , G06F17/30598 , G06N99/005
摘要： A method and system for analyzing a corpus of data artifacts is disclosed. The method comprises obtaining, by a computer, a semantic representation of the data artifacts, where the semantic representation indicates (1) entities identified in the data artifacts, and (2) semantic relationships among the entities as indicated by the data artifacts. The method further comprises clustering the data artifacts into clusters of semantically related data artifacts based on the semantic representation and inferring additional semantic relationships between pairs of the entities. The inferring comprises applying, on a cluster-by-cluster basis, a multi-tiered network of inference engines to a portion of the semantic representation corresponding to the cluster, where the multi-tiered network of inference engines includes a domain-independent inference tier and a domain-specific inference tier.

3. 发明授权

US09489350B2 Systems and methods for semantic search, content correlation and visualization 有权
标题翻译：语义搜索，内容相关和可视化的系统和方法
公开(公告)号：US09489350B2
公开(公告)日：2016-11-08
申请号：US13097746
申请日：2011-04-29
申请人： Larry Crochet , Michael Niv
发明人： Larry Crochet , Michael Niv
IPC分类号： G06F17/22
CPC分类号： G06F17/2211
摘要： Methods and systems for searching over large (i.e., Internet scale) data to discover relevant information artifacts based on similar content and/or relationships are disclosed. Improvements over simple keyword and phrase based searching over internet scale data are shown. Search engines providing accurate and contextually relevant search results are disclosed. Users are enabled to identify related documents and information artifacts and quickly, ascertain, via visualization, which of these documents are original, which are derived (or copied) from a source document or information artifact, and which subset is independently generated (i.e., an original document or information artifact).
摘要翻译：公开了用于基于类似的内容和/或关系搜索大型（即互联网规模）数据以发现相关信息工件的方法和系统。显示了通过互联网比例数据对简单关键词和基于短语的搜索进行改进。公开了提供准确和内容相关的搜索结果的搜索引擎。用户能够识别相关文档和信息工件，并通过可视化快速确定哪些文档是原始的，哪些是从源文档或信息工件导出（或复制的），哪些子集是独立生成的（即，原始文件或信息工件）。

4. 发明授权

US08725771B2 Systems and methods for semantic search, content correlation and visualization 有权
标题翻译：语义搜索，内容相关和可视化的系统和方法
公开(公告)号：US08725771B2
公开(公告)日：2014-05-13
申请号：US13097797
申请日：2011-04-29
申请人： Larry Crochet , Michael Niv
发明人： Larry Crochet , Michael Niv
IPC分类号： G06F17/30 , G06F7/00
CPC分类号： G06F17/2211
摘要： Methods and systems for searching over large (i.e., Internet scale) data to discover relevant information artifacts based on similar content and/or relationships are disclosed. Improvements over simple keyword and phrase based searching over internet scale data are shown. Search engines providing accurate and contextually relevant search results are disclosed. Users are enabled to identify related documents and information artifacts and quickly, ascertain, via visualization, which of these documents are original, which are derived (or copied) from a source document or information artifact, and which subset is independently generated (i.e., an original document or information artifact).
摘要翻译：公开了用于基于类似的内容和/或关系搜索大型（即互联网规模）数据以发现相关信息工件的方法和系统。显示了通过互联网比例数据对简单关键词和基于短语的搜索进行改进。公开了提供准确和内容相关的搜索结果的搜索引擎。用户能够识别相关文档和信息工件，并通过可视化快速确定哪些文档是原始的，哪些是从源文档或信息工件导出（或复制的），哪些子集是独立生成的（即，原始文件或信息工件）。

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