公开(公告)号：US11003671B2

公开(公告)日：2021-05-11

申请号：US14952495

申请日：2015-11-25

申请人： Vobis, Inc.

发明人： Andrew Buhrmann ,  Michael Buhrmann ,  Ali Shokoufandeh ,  Jesse Smith ,  Yakov Keselman ,  Kurtis Peter Dane

IPC分类号： G06F16/00 ,  G06F16/2457 ,  G06F16/248 ,  G06F16/28 ,  G06F16/2452 ,  G06F16/36 ,  G06F40/14 ,  G06F16/33 ,  G06Q10/10

摘要： A microprocessor executable method and system for determining the semantic relatedness and meaning between at least two natural language sources is described in a prescribed context. Portions of natural languages are vectorized and mathematically processed to express relatedness as a calculated metric. The metric is associable to the natural language sources to graphically present the level of relatedness between at least two natural language sources. The metric may be re-determined with algorithms designed to compare the natural language sources with a knowledge data bank so the calculated metric can be ascertained with a higher level of certainty.

公开(公告)号：US20160232160A1

公开(公告)日：2016-08-11

申请号：US14952495

申请日：2015-11-25

申请人： Vobis, Inc.

发明人： Andrew Buhrmann ,  Michael Buhrmann ,  Ali Shokoufandeh ,  Jesse Smith ,  Yakov Keselman ,  Kurtis Peter Dane

IPC分类号： G06F17/30 ,  G06Q10/10 ,  G06F17/22

CPC分类号： G06F16/24578 ,  G06F16/24522 ,  G06F16/248 ,  G06F16/285 ,  G06F16/367 ,  G06F17/2247 ,  G06Q10/1053

摘要： A microprocessor executable method and system for determining the semantic relatedness and meaning between at least two natural language sources is described in a prescribed context. Portions of natural languages are vectorized and mathematically processed to express relatedness as a calculated metric. The metric is associable to the natural language sources to graphically present the level of relatedness between at least two natural language sources. The metric may be re-determined with algorithms designed to compare the natural language sources with a knowledge data bank so the calculated metric can be ascertained with a higher level of certainty.

摘要翻译： 在规定的上下文中描述用于确定至少两个自然语言源之间的语义相关性和含义的微处理器可执行方法和系统。 自然语言的部分被矢量化和数学处理以表示相关性作为计算度量。 该度量与自然语言来源相关联，以图形方式呈现至少两种自然语言源之间的相关性水平。 可以用旨在将自然语言源与知识数据库进行比较的算法重新确定度量，以便可以以更高的确定性确定所计算的度量。