Cognitive engine for use within a cognitive environment

Patent metadata

Field	Value
Publication number	US-10325209-B2
Application number	US-201514629615-A
Country	US
Kind code	B2
Filing date	Feb 24, 2015
Priority date	Jun 9, 2014
Publication date	Jun 18, 2019
Grant date	Jun 18, 2019

Abstract

A cognitive information processing system which includes a processor; a data bus coupled to the processor; and a non-transitory, computer-readable storage medium embodying computer program code, the non-transitory, computer-readable storage medium being coupled to the data bus. The computer program code interacting with a plurality of computer operations and comprising instructions executable by the processor and configured for: 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; and, processing the cognitive graph, the processing the cognitive graph providing cognitive insights.

First claim

What is claimed is:

1. A system comprising:
a processor;
a data bus coupled to the processor; and
a non-transitory, computer-readable storage medium embodying computer program code, the non-transitory, computer-readable storage medium being coupled to the data bus, the computer program code interacting with a plurality of computer operations and comprising instructions executable by the processor and configured for:
receiving streams of data from a plurality of data sources, the plurality of data sources comprising a public data source and a private data source, the public data source comprising publicly available information, the private data source comprising privately managed, company specific information, the public data source comprising at least one of a social data source stored in a social data repository, public data source stored in a public data repository, a licensed data source stored in a licensed data repository and a proprietary data source stored in a proprietary data repository;
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 based upon the data enriching on the data from the plurality of data sources for incorporation into at least one of a cognitive graph and a private cognitive graph via a cognitive inference and learning system, the cognitive graph and the private cognitive graph each comprising a common framework for sharing data between the cognitive graph and the private cognitive graph, the cognitive graph storing publicly available information, the private cognitive graph storing privately managed, company specific information, the data enriching being performed via an enrichment agent, the cognitive graph and the private cognitive graph each comprising a respective machine-readable, declarative memory system, the cognitive graph and the private cognitive graph each comprising a collection of nodes and edges that join pairs of nodes, the cognitive graph storing and learning both episodic memory and semantic memory, the sub-graph comprising a collection of nodes and edges that join pairs of nodes that are next lower than those contained in each of the cognitive graph and the private cognitive graph, the cognitive graph being stored within a repository of 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 being coupled to and communicating with the plurality of data sources, the cognitive graph, the private cognitive graph and a cognitive application, the cognitive platform comprising a cognitive engine, the cognitive engine processing the streams of data from the plurality of data sources;
processing the cognitive graph and the private cognitive graph, the processing the cognitive graph obtaining publicly available information stored within the cognitive graph, the processing the private cognitive graph obtaining privately managed, company specific information stored within the private cognitive graph, the processing combining the publicly available information obtained from the cognitive graph and the privately managed, company specific information obtained from the private cognitive graph to provide cognitive insights, the cognitive insights comprising a visual data story highlighting user-specific insights, relationships and recommendations; and,
providing the cognitive insights to a destination, the destination comprising the cognitive application, the cognitive application used by a user to interact with the cognitive insights, the cognitive application being a network cloud-based application, interaction with the cognitive insights being in the form of a response or a query, the response or query being provided to the cognitive inference and learning system, the cognitive inference and learning system providing another cognitive insight in response to the response or query from the user.

2. The system of claim 1 , wherein the instructions executable by the processor further comprise instructions for:
generating the cognitive graph using the streams of data from the plurality of sources, the cognitive graph comprising a computer readable formalism of knowledge that provides the common framework.

3. The system of claim 1 , wherein the instructions executable by the processor for processing the cognitive graph to provide cognitive insights further comprise instructions for:
performing a perceive operation, the perceive operation performing at least one of an extract operation, a parse operation, a tag operation, an enrich multi-structured data operation, an automate feature extraction operation, an apply spatial encoding operation and a temporal encoding operation; and,
performing a relate operation, the relate operation performing at least one of a comprehend operation, an identify and infer relevant insights operation, a question list generation operation, the relate operation providing observation feedback to the perceive operation.

4. The system of claim 1 , wherein the instructions executable by the processor for processing the cognitive graph to provide cognitive insights further comprise instructions for:
performing an operate operation, the operate operation applying cognitive processes to generate evidence based hypothesis and insights, the operate operation providing decisions feedback to the perceive operation; and,
performing a process and execute operation, the process and execute operation providing insights or automatically taking action, the process and execute operation providing result feedback to the perceive operation.

5. The system of claim 1 , wherein the instructions executable by the processor further comprise instructions for:
automatically and continuously refining understanding to improve future interactions based upon the observation feedback, decisions feedback, and result feedback.

6. The system of claim 1 , wherein:
the processing the streams of data from the plurality of data sources and processing the cognitive graph interact with a cloud infrastructure when performing the processing the streams of data and the processing the cognitive graph.

7. A non-transitory, computer-readable storage medium embodying computer program code, the computer program code comprising computer executable instructions configured for:
receiving streams of data from a plurality of data sources, the plurality of data sources comprising a public data source and a private data source, the public data source comprising publicly available information, the private data source comprising privately managed, company specific information, the public data source comprising at least one of a social data source stored in a social data repository, public data source stored in a public data repository, a licensed data source stored in a licensed data repository and a proprietary data source stored in a proprietary data repository;
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 based upon the data enriching on the data from the plurality of data sources for incorporation into at least one of a cognitive graph and a private cognitive graph via a cognitive inference and learning system, the cognitive graph and the private cognitive graph each comprising a common framework for sharing data between the cognitive graph and the private cognitive graph, the data enriching being pe

Assignees

• Cognitive Scale Inc

Inventors

• Sanchez Matthew
• Ranatunga Dilum

Classifications

• G06Q50/14

  Travel agencies · CPC title

• G06N5/04 Primary

  Inference or reasoning models · CPC title