Universal quantification of knowledge elements within a cognitive graph

• US 10,860,936 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.
• Primary Examiner(s): Gofman, Alex
• Assistant Examiner(s): Black, Linh
• Application Number:
  US15/290,506
• Publication Number:
  US 20170329869A1
• Time in Patent Office: 1,519 Days
• Field of Search: 707603, 707798, 707E17011, 707E17012, 707E17065, 707800, 707E1706, 707E17068, 707E17069
• 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 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 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, each knowledge element being structurally defined within the cognitive graph.

Claims

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 for managing a cognitive graph of a universal knowledge repository, 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 data from a plurality of data sources;

processing, via a cognitive inference and learning system, the data from the plurality of data sources, the processing the data from the plurality of data sources identifying a plurality of knowledge elements as complexity of modeling quantity in a universal cognitive graph of the universal knowledge repository, the cognitive inference and learning system comprising a cognitive platform, the cognitive platform comprising

the universal cognitive graph, the universal cognitive graph including one or more user profiles and an integrated machine learning functionality having cognitive functionality which uses extracted features of newly-observed data from user feedback received via an Application Program Interface during a learn phase to improve accuracy of the knowledge elements stored within the universal cognitive graph, the learn phase includes user feedback on observations generated during a relate phase, the universal cognitive graph refers to a representation of expert knowledge associated with groups over a period of time to depict relationships between entities; and

a cognitive engine, the cognitive engine comprising a dataset engine, a graph query engine and an insight/learning engine, the dataset engine being implemented to establish and maintain a dynamic data ingestion and enrichment pipeline, the graph query engine being implemented to receive and process queries such that the queries are bridged into the cognitive graph, the insight/learning engine being implemented to generate a cognitive insight from the cognitive graph; and

,

storing the knowledge elements within the cognitive graph as a collection of knowledge elements, the storing universally representing knowledge obtained from the data, each knowledge element being structurally defined within the cognitive graph, structurally defining a knowledge element being implemented with an ontology, the ontology universally representing knowledge and comprising a representation of entities along with properties and relations of the entities according to a system of categories, the ontology storing a knowledge element within a cognitive graph based upon a set of categories of the knowledge element and a set of attributes of the knowledge element;

the collection of knowledge elements being accurately and precisely modeled via a ladder entailment pattern and a diamond entailment pattern, the ladder entailment pattern comprising a pattern formed in the universal cognitive graph where rungs of the ladder entailment pattern are formed by a first set of nodes having a categorical relationship with a corresponding second set of nodes and rails of the ladder entailment pattern are formed by attributive relationships respectively associated with the first and second set of nodes;

receiving a user query that includes text of the data to generate a graph query;

performing based on a mapper rule set, mapping operations on the user query;

parsing using parsing operations or a parse rule set, the user query to identify ambiguities of the text after the performing mapping operations, wherein a parsing operation of the parsing operations comprises lossless parsing operations in which all parse variations are identified using a minimum basic structure that is known true, wherein the using of the parse rule set in the performance of the parsing operations results in generation of a set of parse trees, wherein each parse tree of the parse trees is represented as the text being parsed;

ranking based on a parse ranking rule set, the parse trees which results in determination of top-ranked parse trees to resolve the ambiguities in the text of the query, wherein the parse trees are transformed to a tree representing an interpretation of ambiguous portions of the data, the interpretation of the ambiguous portions of the data is changed based upon the user feedback, the top-ranked parse trees are stored in the universal knowledge repository;

identifying, by the computer, knowledge elements of the parse trees that are represented ambiguous portions of the text, wherein the identified knowledge elements of the parse trees are stored within the universal cognitive graph in a configuration representing relationship of concepts;

identifying knowledge elements of the parse trees that are represented ambiguous portions of the text, wherein the identified knowledge elements of the parse trees are stored within the universal cognitive graph in a configuration representing relationship of concepts;

querying the universal knowledge repository in response to the user query, the querying the universal knowledge repository using the identified knowledge elements of the parse trees and the identified a plurality of knowledge elements of the universal cognitive graph to produce composite cognitive insights as recommendations that satisfy the graph query;

ranking information in insight streams, the composite cognitive insights that are provided in a cognitive insight summary, the information being related to a location of the user, the user feedback and a device used by the user;

publishing the ranked composite cognitive insights in the cognitive insight summary to the user of cognitive insight data, the ranked composite cognitive insights being related to the one or more cognitive user profiles.

2. The system of claim 1, wherein:

a relationship between a first knowledge element and a second knowledge element comprises only one of the categorical relationship and the attributive relationship, the categorical relationship representing inheritance of an entity and the attributive relationship representing attribution of the entity.

3. The system of claim 1, wherein:

the diamond entailment pattern comprises a pattern formed in the universal cognitive graph when two parent nodes of a first node inherit from a common second node.

4. The system of claim 1, wherein:

inheritance relationships between a base node and a parent node define a particular concept within the cognitive graph.

5. The system of claim 1, wherein:

a plurality of knowledge elements representing quantity concepts are stored within the cognitive graph, the plurality of knowledge elements representing quantity concepts enabling quantity to be modeled within the cognitive graph.

6. A non-transitory, computer-readable storage medium embodying computer program code, the computer program code comprising computer executable instructions configured for:

receiving data from a plurality of data sources;

processing, via a cognitive inference and learning system, the data from the plurality of data sources, the processing the data from the plurality of data sources identifying a plurality of knowledge elements as complexity of modeling quantity in a universal cognitive graph of the universal knowledge repository, the cognitive inference and learning system comprising a cognitive platform, the cognitive platform comprising

the universal cognitive graph, the universal cognitive graph including one or more user profiles and an integrated machine learning functionality having cognitive functionality which uses extracted features of newly-observed data from user feedback received via an Application Program Interface during a learn phase to improve accuracy of the knowledge elements stored within the universal cognitive graph, the learn phase includes user feedback on observations generated during a relate phase, the universal cognitive graph refers to a representation of expert knowledge associated with groups over a period of time to depict relationships between entities and

a cognitive engine, the cognitive engine comprising a dataset engine, a graph query engine and an insight/learning engine, the dataset engine being implemented to establish and maintain a dynamic data ingestion and enrichment pipeline, the graph query engine being implemented to receive and process queries such that the queries are bridged into the cognitive graph, the insight/learning engine being implemented to generate a cognitive insight from the cognitive graph; and

,

storing the knowledge elements within the cognitive graph as a collection of knowledge elements, the storing universally representing knowledge obtained from the data, each knowledge element being structurally defined within the cognitive graph, structurally defining a knowledge element being implemented with an ontology, the ontology universally representing knowledge and comprising a representation of entities along with properties and relations of the entities according to a system of categories, the ontology storing a knowledge element within a cognitive graph based upon a set of categories of the knowledge element and a set of attributes of the knowledge element;

the collection of knowledge elements being accurately and precisely modeled via a ladder entailment pattern and a diamond entailment pattern, the ladder entailment pattern comprising a pattern formed in the universal cognitive graph where rungs of the ladder entailment pattern are formed by a first set of nodes having a categorical relationship with a corresponding second set of nodes and rails of the ladder entailment pattern are formed by attributive relationships respectively associated with the first and second set of nodes;

receiving a user query that includes text of the data to generate a graph query;

performing based on a mapper rule set, mapping operations on the user query;

parsing using parsing operations or a parse rule set, the user query to identify ambiguities of the text after the performing mapping operations, wherein a parsing operation of the parsing operations comprises lossless parsing operations in which all parse variations are identified using a minimum basic structure that is known true, wherein the using of the parse rule set in the performance of the parsing operations results in generation of a set of parse trees, wherein each parse tree of the parse trees is represented as the text being parsed;

ranking based on a parse ranking rule set, the parse trees which results in determination of top-ranked parse trees to resolve the ambiguities in the text of the query, wherein the parse trees are transformed to a tree representing an interpretation of ambiguous portions of the data, the interpretation of the ambiguous portions of the data is changed based upon the user feedback, the top-ranked parse trees are stored in the universal knowledge repository;

identifying, by the computer, knowledge elements of the parse trees that are represented ambiguous portions of the text, wherein the identified knowledge elements of the parse trees are stored within the universal cognitive graph in a configuration representing relationship of concepts;

identifying knowledge elements of the parse trees that are represented ambiguous portions of the text, wherein the identified knowledge elements of the parse trees are stored within the universal cognitive graph in a configuration representing relationship of concepts;

querying the universal knowledge repository in response to the user query, the querying the universal knowledge repository using the identified knowledge elements of the parse trees and the identified a plurality of knowledge elements of the universal cognitive graph to produce composite cognitive insights as recommendations that satisfy the graph query;

ranking information in insight streams, the composite cognitive insights that are provided in a cognitive insight summary, the information being related to a location of the user, the user feedback and a device used by the user;

publishing the ranked composite cognitive insights in the cognitive insight summary to the user of cognitive insight data, the ranked composite cognitive insights being related to the one or more cognitive user profiles.

7. The non-transitory, computer-readable storage medium of claim 6, wherein:

a relationship between a first knowledge element and a second knowledge element comprises only one of the categorical relationship and the attributive relationship, the categorical relationship representing inheritance of an entity and the attributive relationship representing attribution of the entity.

8. The non-transitory, computer-readable storage medium of claim 6, wherein:

the diamond entailment pattern comprises a pattern formed in the universal cognitive graph when two parent nodes of a first node inherit from a common second node.

9. The non-transitory, computer-readable storage medium of claim 6, wherein:

inheritance relationships between a base node and a parent node define a particular concept within the cognitive graph.

10. The non-transitory, computer-readable storage medium of claim 6, wherein

a plurality of knowledge elements representing quantity concepts are stored within the cognitive graph, the plurality of knowledge elements representing quantity concepts enabling quantity to be modeled within the cognitive graph.

11. The non-transitory, computer-readable storage medium of claim 6, wherein the computer executable instructions are deployable to a client system from a server system at a remote location.

12. The non-transitory, computer-readable storage medium of claim 6, wherein the computer executable instructions are provided by a service provider to a user on an on-demand basis.