公开(公告)号：US20150302299A1

公开(公告)日：2015-10-22

申请号：US14788589

申请日：2015-06-30

申请人： Primal Fusion Inc.

发明人： Anne Jude Hunt ,  Alexander David Black ,  Peter Joseph Sweeney ,  Ihab Francis Ilyas

IPC分类号： G06N5/02 ,  G06F17/30

CPC分类号： G06N5/02 ,  G06F17/30914

摘要： Techniques for analyzing and synthesizing complex knowledge representations (KRs) may utilize an atomic knowledge representation model including both an elemental data structure and knowledge processing rules stored as machine-readable data and/or programming instructions. One or more of the knowledge processing rules may be applied to analyze an input complex KR to deconstruct its complex concepts and/or concept relationships to elemental concepts and/or concept relationships to be included in the elemental data structure. One or more of the knowledge processing rules may be applied to synthesize an output complex KR from the stored elemental data structure in accordance with an input context. Multiple input complex KRs of various types may be analyzed and deconstructed to populate the elemental data structure, and input complex KRs may be transformed through the elemental data structure to output complex KRs of different types, providing semantic interoperability to KRs of different types and/or KR models.

摘要翻译： 用于分析和合成复杂知识表示（KR）的技术可以利用原子知识表示模型，其包括存储为机器可读数据和/或编程指令的元数据结构和知识处理规则。 可以应用知识处理规则中的一个或多个来分析输入复合体KR以将其复杂概念和/或概念关系解构为要包括在基本数据结构中的元素概念和/或概念关系。 一个或多个知识处理规则可以被应用以根据输入上下文从存储的基本数据结构合成输出复合体KR。 可以对各种类型的多输入复合体KR进行分析和解构以填充元素数据结构，并且可以通过元素数据结构来转换输入复数KR，以输出不同类型的复合KR，为不同类型和/或不同类型的KR提供语义互操作性 KR型号。

公开(公告)号：US09934465B2

公开(公告)日：2018-04-03

申请号：US14788589

申请日：2015-06-30

申请人： Primal Fusion Inc.

发明人： Anne Jude Hunt ,  Alexander David Black ,  Peter Joseph Sweeney ,  Ihab Francis Ilyas

IPC分类号： G06F17/30 ,  G06N5/02

CPC分类号： G06N5/02 ,  G06F17/30914

摘要： Techniques for analyzing and synthesizing complex knowledge representations (KRs) may utilize an atomic knowledge representation model including both an elemental data structure and knowledge processing rules stored as machine-readable data and/or programming instructions. One or more of the knowledge processing rules may be applied to analyze an input complex KR to deconstruct its complex concepts and/or concept relationships to elemental concepts and/or concept relationships to be included in the elemental data structure. One or more of the knowledge processing rules may be applied to synthesize an output complex KR from the stored elemental data structure in accordance with an input context. Multiple input complex KRs of various types may be analyzed and deconstructed to populate the elemental data structure, and input complex KRs may be transformed through the elemental data structure to output complex KRs of different types, providing semantic interoperability to KRs of different types and/or KR models.