US 11,868,883 B1
Intelligent control with hierarchical stacked neural networks
Michael Lamport Commons, Cambridge, MA (US)
Filed by Michael Lamport Commons, Cambridge, MA (US)
Filed on Dec. 16, 2019, as Appl. No. 16/716,028.
Application 16/716,028 is a division of application No. 14/733,472, filed on Jun. 8, 2015, granted, now 10,510,000, issued on Dec. 17, 2019.
Application 14/733,472 is a division of application No. 14/322,147, filed on Jul. 2, 2014, granted, now 9,053,431, issued on Jun. 9, 2015.
Application 14/322,147 is a continuation of application No. 13/281,343, filed on Oct. 25, 2011, granted, now 8,775,341, issued on Jul. 8, 2014.
Claims priority of provisional application 61/406,777, filed on Oct. 26, 2010.
Int. Cl. G06N 3/08 (2023.01); G10L 15/16 (2006.01); G06N 3/02 (2006.01); G06F 40/253 (2020.01); G06F 40/30 (2020.01); G06F 16/33 (2019.01); G06N 3/045 (2023.01); G06Q 10/107 (2023.01)
CPC G06N 3/08 (2013.01) [G06F 16/3344 (2019.01); G06F 40/253 (2020.01); G06F 40/30 (2020.01); G06N 3/02 (2013.01); G06N 3/045 (2023.01); G10L 15/16 (2013.01); G06Q 10/107 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A method for analyzing grammar in a natural language message, comprising:
receiving a natural language message having a type a model of hierarchical complexity level of at least 6;
detecting an ordered set of words within the natural language message;
linking the set of words found within the natural language message to a corresponding set of expected words, the set of expected words having semantic attributes, the corresponding set of expected words being dependent on natural language training data;
detecting a set of grammatical structures represented in the natural language message, based on:
the type of the received natural language message,
the ordered set of words, and
the semantic attributes of the corresponding set of expected words; and
producing at least one output selectively dependent on the set of grammatical structures represented in the natural language message.