US 11,809,956 B2
Composite cognitive insights
Matthew Sanchez, Austin, TX (US); and Dilum Ranatunga, Austin, TX (US)
Assigned to Tecnotree Technologies, Inc., Lewes, DE (US)
Filed by Cognitive Scale, Inc., Austin, TX (US)
Filed on Oct. 3, 2019, as Appl. No. 16/591,808.
Application 16/591,808 is a continuation of application No. 14/729,549, filed on Jun. 3, 2015, granted, now 10,445,369, issued on Oct. 15, 2019.
Claims priority of provisional application 62/009,626, filed on Jun. 9, 2014.
Prior Publication US 2020/0034388 A1, Jan. 30, 2020
This patent is subject to a terminal disclaimer.
Int. Cl. G06F 16/28 (2019.01); G06F 16/2458 (2019.01); G06F 16/901 (2019.01); G06F 16/2455 (2019.01); G06F 16/955 (2019.01); G06F 16/958 (2019.01); G06N 5/022 (2023.01); G06N 20/00 (2019.01); G06N 5/04 (2023.01)
CPC G06N 5/022 (2013.01) [G06N 5/04 (2013.01); G06N 20/00 (2019.01); G06F 16/2465 (2019.01); G06F 16/24568 (2019.01); G06F 16/287 (2019.01); G06F 16/9024 (2019.01); G06F 16/955 (2019.01); G06F 16/972 (2019.01)] 3 Claims
OG exemplary drawing
 
1. A computer-implementable method for
providing composite cognitive insights comprising:
receiving streams of data from a plurality of data sources;
processing the streams of data from the plurality of data sources via a cognitive inference and learning system, the processing the streams of data from the plurality of data sources generating a sub-graph for incorporation into a cognitive graph, the cognitive graph being stored within a repository of cognitive graphs, the repository of cognitive graphs comprising a plurality of application cognitive graphs, each of the plurality of application cognitive graphs being associated with a predetermined cognitive application, the cognitive inference and learning system executing on a hardware processor of an information processing system, the cognitive inference and learning system providing a cognitive computing function, the cognitive inference and learning system comprising a cognitive platform, the cognitive platform comprising a cognitive engine, the cognitive engine comprising
an insight engine, the insight engine encapsulating a predetermined algorithm, the predetermined algorithm being applied to the cognitive graph to generate a result, the predetermined algorithm contributing to answering a specific question and providing additional cognitive insights, and
a graph query engine, the graph query engine being implemented to receive and process queries such that the queries are sent to the cognitive graph, the insight engine operating collaboratively with the graph query engine to generate a cognitive insight, the insight engine comprising a plurality of insight agents, the insight engine interacting with a plurality of machine learning models, the machine learning models being generated, accessed and updated by the insight engine in the process of generating the cognitive insight;
processing an application cognitive graph of the plurality of application cognitive graphs via an insight agent of the insight engine and the graph query engine, the processing the application cognitive graph providing a plurality of individual cognitive insights for a user, the application cognitive graph being associated with a cognitive application, the insight agent using the application cognitive graph as a data source to provide the plurality of individual insights to the cognitive application;
generating a composite cognitive insight, the composite cognitive insight being composed of the plurality of individual cognitive insights, the generating orchestrating a subset of the plurality of insight agents to generate the composite cognitive insight from the plurality of individual cognitive insights, the subset of the plurality of insight agents being suited to provide the composite cognitive insight to a particular user for a particular purpose, the composite cognitive insight comprising a contextually-relevant composite insight;
providing the composite cognitive insight to a user via the cognitive application;
presenting the contextually-relevant composite insight to a user;
determining whether the user provides feedback regarding the contextually-relevant composite insight; and,
generating a contextually-relevant question responsive to user provided feedback
determining whether the user provides a response to the contextually-relevant question; and,
providing additional cognitive insights responsive to the response to the contextually-relevant question; and wherein
the cognitive engine interacts with the cognitive application via an insight application program interface, the insight application program interface conveying the cognitive insight to the cognitive application.