Universal graph output via insight agent accessing the universal graph

• US 10,860,933 B2
• Filed: 10/11/2016
• Issued: 12/08/2020
• Est. Priority Date: 05/13/2016
• Status: Active Grant

• Current Assignee: Tecnotree Technologies Incorporated
• Original Assignee: Cognitive Scale Inc (Tecnotree Oyj)
• Inventors: Lindsley, Hannah R., Sanchez, Matthew
• Primary Examiner(s): Shmatov, Alexey
• Assistant Examiner(s): Nguyen, Tri T
• Application Number:
  US15/290,465
• Publication Number:
  US 20170330093A1
• Time in Patent Office: 1,519 Days
• CPC Class Codes: G06F 16/3329 Natural language query formulation or dialogue systems
• CPC Class Codes: G06F 16/367 Ontology
• CPC Class Codes: G06F 16/84 Mapping; Conversion
• CPC Class Codes: G06F 16/9024 Graphs; Linked lists G06F16/9027 takes precedence
• CPC Class Codes: G06F 16/90335 Query processing
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: G06N 5/01 Dynamic search techniques; Heuristics; Dynamic trees; Branch-and-bound
• CPC Class Codes: G06N 5/02 Knowledge representation; Symbolic representation
• CPC Class Codes: G06N 5/022 Knowledge engineering; Knowledge acquisition
• CPC Class Codes: G06N 5/04 Inference or reasoning models
• CPC Class Codes: G06N 5/043 Distributed expert systems; Blackboards
• CPC Class Codes: G06N 5/048 Fuzzy inferencing

Abstract

A computer-implementable method for generating an insight comprising: receiving data from a plurality of data sources; processing the data from the plurality of data sources, the processing the data from the plurality of data sources identifying a plurality of knowledge elements; and, storing the knowledge elements within the cognitive graph as a collection of knowledge elements, the storing universally representing knowledge obtained from the data; and, generating a cognitive insight based upon the collection of knowledge elements stored within the cognitive graph, the generating the cognitive insight using an insight agent to access the collection of knowledge elements.

Claims

1. A computer-implementable method for generating an insight comprising:

receiving data from a plurality of data sources;

processing the data from the plurality of data sources, the processing the data from the plurality of data sources identifying a plurality of knowledge elements, the processing being performed via a cognitive inference and learning system, the cognitive inference and learning system executing on a hardware processor of an information processing system and interacting with the plurality of data sources, 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 processing the data from the plurality of data sources; and

,

storing the knowledge elements within a cognitive graph of a universal knowledge repository as a collection of knowledge elements, the storing universally representing knowledge obtained from the data, the cognitive graph comprising integrated machine learning functionality, the integrated machine learning functionality using extracted features of newly-observed data from user feedback received during a learning phase to improve accuracy of knowledge stored within the cognitive graph;

performing mapping operations on a query to generate query related knowledge elements based upon the user feedback, the mapping operations generating a set of parse trees using a parse rule set, the mapping operations comprising mapping structural elements to resolve ambiguity, the mapping operations comprising mapping structural elements of the query around a verb of the query, the mapping of the structural elements transforming the structural elements into words higher up an inheritance chain within the cognitive graph, the parse trees being ranked by a conceptualization ranking rule set, the parse trees representing ambiguous portions of the text of the query;

performing a conceptualization operation, the conceptualization operation identifying relationships of concepts identified from ranking the set of parse trees using the conceptualization ranking rule set, the conceptualization operations generating a set of conceptualization ambiguity options, the set of conceptualization ambiguity options being ranked using the conceptualization ranking rule set, top-ranked conceptualization options being stored in the cognitive graph;

submitting an insight agent query from an insight agent to the universal knowledge repository;

providing matching results to the insight agent responsive to the insight agent query based upon a matching rule set and a plurality of answer related knowledge elements in the universal knowledge repository; and

,

generating a cognitive insight based upon the matching results, the generating the cognitive insight using an insight agent to access the collection of knowledge elements.

2. The method of claim 1, further comprising:

accessing a plurality of query related knowledge elements within the cognitive graph via the insight agent;

processing the query related insights to identify a meaning of a query from a user;

accessing the plurality of answer related knowledge elements within the cognitive graph via the insight agent.

3. The method of claim 2, further comprising:

accessing the plurality of query related knowledge elements further comprises the insight agent traversing the plurality of query related knowledge elements within the cognitive graphs.

4. The method of claim 3, wherein:

the query related knowledge elements are stored within the cognitive graph as nodes;

subsets of nodes are related via edges; and

,

the traversing the plurality of query related knowledge elements comprises the insight agent accessing nodes of interest via parent nodes and child nodes based upon nodes related via the edges.

5. The method of claim 2, further comprising:

accessing the plurality of answer related knowledge elements further comprises the insight agent traversing the plurality of answer related knowledge elements within the cognitive graphs, the traversing the plurality of answer related knowledge elements being based upon the meaning of the query inferred by the insight agent.

6. The method of claim 5, wherein:

the query related knowledge elements are stored within the cognitive graph as nodes;

subsets of nodes are related via edges; and

,

the traversing the plurality of answer related knowledge elements comprises the insight agent accessing nodes of interest via parent nodes and child nodes based upon nodes related via the edges.