Method for cognitive information processing

• US 10,262,261 B2
• Filed: 02/24/2015
• Issued: 04/16/2019
• Est. Priority Date: 06/09/2014
• Status: Active Grant

• Current Assignee: Tecnotree Technologies Incorporated
• Original Assignee: Cognitive Scale Inc (Tecnotree Oyj)
• Inventors: Sanchez, Matthew, Saxena, Manoj, Sabhikhi, Akshay
• Primary Examiner(s): Nilsson, Eric
• Application Number:
  US14/629,608
• Publication Number:
  US 20150356404A1
• Time in Patent Office: 1,512 Days
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: G06N 5/02 Knowledge representation; Symbolic representation

Abstract

A cognitive information processing system environment which includes a plurality of data sources; a cognitive inference and learning system coupled to receive a data from the plurality of data sources, the cognitive inference and learning system processing the data from the plurality of data sources to provide cognitively processed insights, the cognitive inference and learning system further comprising performing a learning operation to iteratively improve the cognitively processed insights over time; and, a destination, the destination receiving the cognitively processed insights.

Claims

1. A method for cognitive information processing comprising:

receiving data from a plurality of data sources, the plurality of data sources comprising at least one of a social data source stored in a social data repository, public data source stored in a public data repository, licensed data source stored in a licensed data repository and proprietary data source stored in a proprietary data repository;

processing the data from the plurality of data sources to provide cognitively processed insights via a cognitive inference and learning system, 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 graph, the cognitive graph being derived from the plurality of data sources, the cognitive graph enabling the cognitive inference and learning system to render the cognitively processed insights;

performing a learning operation to iteratively improve the cognitively processed insights over time; and

,

providing the cognitively processed insights to a destination via a cognitive insight stream, the cognitive insight stream comprising a stream of visualized insights, the destination comprising a cognitive application, the cognitive application enabling a user to interact with the cognitive insights, the cognitive application being a cloud-based application that learns from user engagement and data interactions.

2. The method of claim 1, wherein:

the plurality of data sources comprise at least one of situational data sources and temporal data sources.

3. The method of claim 1, wherein:

the plurality of data sources comprise at least one of a social data source, a public data source, a private data source and a device data source.

4. The method of claim 1, further comprising:

performing analysis operations to achieve a semantic level of understanding about language by relating syntactic structures.

5. The method of claim 1, further comprising:

performing multi-criteria decision making operations to achieve a goal.

6. The method of claim 1, further comprising:

filtering for information through collaborative involvement of a plurality of entities.

7. The method of claim 1, further comprising:

enabling natural language interactions with the cognitive inference and learning system.

8. The method of claim 1, further comprising:

processing information, organizing the information, ranking the information and generating s corresponding summary of the information.

9. The method of claim 1, further comprising:

identifying elements in a set of data that refer to the same entity across different data sources.

10. The method of claim 1, wherein:

the destination comprises at least one of a mobile application, an alert, a business intelligence type application, a statistical tool, a third party custom application, a marketplace and an application program interface.

11. A method for a cognitive information processing system comprising:

receiving data from the plurality of data sources to the cognitive interface and learning system, the plurality of data sources comprising a public data source stored in a public data repository and a private data source stored in a private data repository, the private data repository being maintained within a private network environment;

processing data from a plurality of data sources to provide cognitively processed insights via a first cognitive inference and learning system and a second cognitive inference and learning system,

the first cognitive inference and learning system executing on an information processing system, the cognitive inference and learning system and the information processing system providing a cognitive computing function, the first cognitive inference and learning system comprising a hosted cognitive platform, the hosted cognitive platform comprising

a hosted cognitive engine, the hosted cognitive engine comprising hosted a dataset engine, a hosted graph query engine and a hosted insight/learning engine,

a plurality of hosted sourcing agents, the plurality of hosted sourcing agents sourcing multi-site, multi-structured data streams from the public data source,

a plurality of hosted destination agents, the plurality of hosted destination agents publishing the cognitively processed insights to a consumer of cognitive insight data;

the second cognitive inference and learning system executing on an information processing system contained within the private network environment, the second cognitive inference and learning system and the information processing system providing a second cognitive computing function, the second cognitive inference and learning system comprising a private cognitive platform, the private cognitive platform comprising

a private cognitive engine, the private cognitive engine comprising a private dataset engine, a private graph query engine and a private insight/learning engine,

a plurality of private sourcing agents, the plurality of private sourcing agents sourcing multi-site, multi-structured data streams from the private data source,

a plurality of private destination agents, the plurality of private destination agents publishing the cognitively processed insights to a consumer of cognitive insight data; and

,

performing, via the first cognitive inference and learning system and the second cognitive inference and learning system, learning operations to iteratively improve the cognitively processed insights over time; and

,

providing the cognitively processed insights to a destination via a cognitive insight stream, the cognitive insight stream comprising a stream of visualized insights, the destination comprising a cognitive application, the cognitive application enabling a user to interact with the cognitive insights, the cognitive application being a cloud-based application that learns from user engagement and data interactions.

12. The method of claim 11, further comprising:

performing analysis operations to achieve a semantic level of understanding about language by relating syntactic structures.

13. The method of claim 11, further comprising:

performing multi-criteria decision making operations to achieve a goal.

14. The method of claim 11, further comprising:

filtering for information through collaborative involvement of a plurality of entities.