Composite cognitive insights

• US 10,445,369 B2
• Filed: 06/03/2015
• Issued: 10/15/2019
• Est. Priority Date: 06/09/2014
• Status: Active Grant

• Current Assignee: Tecnotree Technologies Incorporated (Tecnotree Oyj)
• Original Assignee: Cognitive Scale Inc (Tecnotree Oyj)
• Inventors: Sanchez, Matthew, Ranatunga, Dilum
• Primary Examiner(s): Trujillo, James
• Assistant Examiner(s): Mina, Fatima P
• Application Number:
  US14/729,549
• Publication Number:
  US 20150356200A1
• Time in Patent Office: 1,595 Days
• CPC Class Codes: G06F 13/4208 being a system bus, e.g. VME bus, Futurebus, Multibus
• CPC Class Codes: G06F 16/24568 Data stream processing; Continuous queries
• CPC Class Codes: G06F 16/2465 Query processing support for facilitating data mining operations in structured databases
• CPC Class Codes: G06F 16/287 Visualization; Browsing
• CPC Class Codes: G06F 16/9024 Graphs; Linked lists G06F16/9027 takes precedence
• CPC Class Codes: G06F 16/955 using information identifiers, e.g. uniform resource locators [URL]
• CPC Class Codes: G06F 16/972 Access to data in other repository systems, e.g. legacy data or dynamic Web page generation
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: G06N 5/022 Knowledge engineering; Knowledge acquisition
• CPC Class Codes: G06N 5/04 Inference or reasoning models
• CPC Class Codes: G06Q 30/0241 Advertisements
• CPC Class Codes: G06Q 30/0269 based on user profile or attribute
• CPC Class Codes: G06Q 30/0277 Online advertisement
• CPC Class Codes: H04W 4/025 using location based information parameters

Abstract

A method for providing composite cognitive insights which includes receiving streams of data from a plurality of data sources; processing the streams of data from the plurality of data sources, the processing the streams of data from the plurality of data sources performing data enriching and generating a sub-graph for incorporation into a cognitive graph; processing the cognitive graph, the processing the cognitive graph providing a plurality of individual cognitive insights; and, generating a composite cognitive insight, the composite cognitive insight being composed of the plurality of individual cognitive insights.

Claims

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 performing data enriching and generating a sub-graph for incorporation into a cognitive graph, the cognitive graph comprising a machine-readable formalism for knowledge representation that provides a common framework allowing data and knowledge to be shared, the cognitive graph being stored within a repository of cognitive graphs, the repository of cognitive graphs comprising a plurality of application cognitive graphs, the cognitive inference and learning system executing on a hardware processor of an information processing system, the cognitive inference and learning system and the information processing 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 bridged into the cognitive graph, the insight engine operating collaboratively with the graph query engine to generate a cognitive insight, the insight engine comprising an insight agent;

processing an application cognitive graph of the plurality of application cognitive graphs via the 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 predetermined cognitive application, the insight agent using the application cognitive graph as a data source to provide the plurality of individual insights;

generating a composite cognitive insight, the composite cognitive insight being composed of the plurality of individual cognitive insights, the generating orchestrating the insight agent to generate the composite cognitive insight from the plurality of individual cognitive insights; and

,

providing the composite cognitive insight to a user via a cognitive application.

2. The method of claim 1, wherein:

the plurality of individual cognitive insights used when composing the composite cognitive insight are related to a particular composite cognitive insight session, the cognitive insight session comprising a plurality of queries over a period of time, the plurality of queries being stored within a cognitive session graph associated with the session.

3. The method of claim 1, wherein:

the composite cognitive insight comprises a contextually-relevant composite insight.

4. The method of claim 3, further comprising:

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.

5. The method of claim 4, further comprising:

determining whether the user provides response to the contextually-relevant question; and

,

providing additional cognitive insights responsive to the response to the contextually-relevant question.

6. The method of claim 1, wherein:

a plurality of insight agents orchestrate the processing of the cognitive graph to provide the plurality of individual cognitive insights used when composing the composite cognitive insight.