Quang Thenguyen Duong

US Patent:

20200035240, Jan 30, 2020

Filed:

Jul 27, 2018

Appl. No.:

16/047602

Inventors:

- Armonk NY, US
Quang T.N. Duong - Austin TX, US
David L. Schmidt - Cary NC, US

International Classification:

G10L 15/24
G06F 3/01
G06F 15/18
G16H 20/70
G06F 17/30

Abstract:

Mechanisms are provided for mitigating the effects of long term cognitive conditions on patient interactions by providing artificial intelligence mechanisms to assist with such interactions. The mechanisms perform a machine learning operation to learn, for a particular patient, associations between patient indicators and concepts that the patient is attempting to communicate or concepts representing actions that the patient would like to perform within a patient environment. The mechanisms receive, from a monitoring device in a patient environment, a patient input representing an attempt by the patient to communicate a concept or interact with the patient environment. The mechanisms perform a cognitive translation of one or more patient indicators in the patient input to one or more corresponding concepts based on results of the machine learning operation. The mechanisms then generate a translation output specifying the one or more corresponding concepts.

US Patent:

20150293783, Oct 15, 2015

Filed:

Apr 9, 2014

Appl. No.:

14/248540

Inventors:

- Armonk NY, US
Quang T. Duong - Austin TX, US
Nnaemeka I. Emejulu - Austin TX, US
Anil K. Levi - Round Rock TX, US
Karthikeyan Ramamoorthy - Austin TX, US
Vincent C. Willimas - Mission Viejo CA, US

Assignee:

INTERNATIONAL BUSINESS MACHINES CORPORATION - Armonk NY

International Classification:

G06F 9/48
G06F 9/50

Abstract:

Provided are techniques for the scheduling of an identity Manager reconciliation at an optimal time. The techniques include partitioning a security identity management handling task into a First sub-task and a second sub-task; assigning to the first sub-task a first priority, based upon a first projected number of accounts affected by the first sub-task, a first attribute criteria, a first expected completion time, and a corresponding first scheduler index value, based upon the first priority; and assigning to the second sub-task a second priority, based upon a second projected number of accounts affected by the second sub-task, a second attribute criteria, a second expected completion time, and a second scheduler index value, based upon the second priority; and scheduling the first sub-task prior to the second sub-task in accordance with a prioritization algorithm in which a first weighted combination of the first priority and first expected completion time is greater than a second weighted combination of the second priority and the second expected completion time.