MACHINE LEARNING TO INTEGRATE KNOWLEDGE AND NATURAL LANGUAGE PROCESSING

Title:

MACHINE LEARNING TO INTEGRATE KNOWLEDGE AND NATURAL LANGUAGE PROCESSING

Document Type and Number:

WIPO Patent Application WO/2019/138289

Kind Code:

A1

Abstract:

A system, computer program product, and method are provided to automate a framework for knowledge graph based persistence of data, and to resolve temporal changes and uncertainties in the knowledge graph. Natural language understanding, together with one or more machine learning models (MLMs), is used to extract data from unstructured information, including entities and entity relationships. The extracted data is populated into a knowledge graph. As the KG is subject to change, the KG is used to create new and retrain existing machine learning models (MLMs). Weighting is applied to the populated data in the form of veracity value. Blockchain technology is applied to the populated data to ensure reliability of the data and to provide auditability to assess changes to the data.

More Like This:

WO/2018/100700	DATA CONVERSION DEVICE AND DATA CONVERSION METHOD
WO/2011/044659	SYSTEM AND METHOD FOR PHRASE IDENTIFICATION
WO/2021/261882	ELECTRONIC DEVICE AND NEOLOGISM-BASED SENTENCE CONVERTING METHOD FOR ELECTRONIC DEVICE

Inventors:

BACARELLA DAVID (US)
BARNEBEE JAMES (US)
LAWRENCE NICHOLAS (US)
PATEL SUMIT (US)

Application Number:

PCT/IB2018/060736

Publication Date:

July 18, 2019

Filing Date:

December 31, 2018

Export Citation:

Click for automatic bibliography generation Help

Assignee:

IBM (US)
IBM UK (GB)
IBM CHINA INVESTMENT CO LTD (CN)

International Classes:

G06F40/237

Foreign References:

US20150324350A1	2015-11-12
US20170161615A1	2017-06-08
CN107015963A	2017-08-04

Attorney, Agent or Firm:

LITHERLAND, David (GB)

Download PDF:

View/Download PDF PDF Help

Previous Patent: BEAM CONSOLIDATION AND SELECTION BASED ON EXTERNAL INFORMATION

Next Patent: TRANSMISSION MEANS FOR A MOTOR VEHICLE LATCH AND A MOTOR VEHICLE LATCH