Rana Eddine Novack

US Patent:

20180365354, Dec 20, 2018

Filed:

Dec 14, 2017

Appl. No.:

15/842672

Inventors:

- Armonk NY, US
Vincent Petrus Anthonius Lonij - Dublin, IE
Rahul Nair - Dublin, IE
Rana E. Novack - Clifton VA, US
Paulito Pedregosa Palmes - Dublin, IE

International Classification:

G06F 17/50
G06F 3/0481
G06F 3/0482
G06F 17/27

Abstract:

Techniques for employing natural language processing (NLP) to facilitate geospatial analysis are provided. In one example, a computer-implemented method comprises receiving, by a device operatively coupled to a processor, input information in a natural language format indicating a change to a state of a system comprising different nodes through which physical elements flow, wherein the system is associated with a state model that characterizes movement of the physical elements through the different nodes based on one or more flow parameters. The computer-implemented method further comprises, determining, by the device based on the input information, a subset of the one or more flow parameters associated with the change, determining, by the device based on the input information, one or more constraints to the subset that account for the change, and modifying, by the device, the state model based on the one or more constraints, resulting in a modified state model.

US Patent:

20180357564, Dec 13, 2018

Filed:

Jun 13, 2017

Appl. No.:

15/621067

Inventors:

- Armonk NY, US
Vincent LONIJ - Dublin, IE
Rahul NAIR - Dublin, IE
Rana E. NOVACK - Clifton VA, US
Paulito PALMES - Dublin, IE

Assignee:

INTERNATIONAL BUSINESS MACHINES CORPORATION - Armonk NY

International Classification:

G06N 99/00
G06N 5/04

Abstract:

Embodiments for intelligent flow prediction by a processor. One or more flows of a domain of interest between target entities may be forecasted according to one or more forecast models learned via machine learning using extracted features of one or more target variables from one or more data sources. The one or more flows may include a quantitative value, an intensity score, an intensity category, or a combination thereof between the target entities.