Mary Ann Swift

US Patent:

20220414396, Dec 29, 2022

Filed:

Jun 28, 2021

Appl. No.:

17/359959

Inventors:

- Armonk NY, US
Anne Elizabeth Gattiker - Austin TX, US
Matthew Comer - Austin TX, US
Mary D. Swift - Rochester NY, US
Ambal Balakrishnan - Austin TX, US
Florian Pinel - New York NY, US

International Classification:

G06K 9/62
G06N 3/08

Abstract:

Provided is a method, computer program product, and system for predicting image sharing decisions using machine learning. A processor may receive a set of annotated images and an associated text input from each user of a plurality of users. The processor may train, using the set of annotated images and the associated text input from each user, a neural network model to output an image sharing decision that is specific to a user.

US Patent:

20200372367, Nov 26, 2020

Filed:

May 22, 2019

Appl. No.:

16/419230

Inventors:

- Armonk NY, US
Naga KATREDDI - Wexford PA, US
Vishesh RAIMUGIA - DURHAM NC, US
Mary SWIFT - Rochester NY, US

Assignee:

INTERNATIONAL BUSINESS MACHINES CORPORATION - Armonk NY

International Classification:

G06N 3/08
G06F 17/27
G06F 16/17

Abstract:

Embodiments for responding to computing system incidents are provided. Information associated with a computing system is analyzed to generate a base system model of the computing system. The information includes at least one of system logs and metrics data of the computing system. An indication of an incident associated with the computing system is received. The base system model is utilized to analyze the incident. The analysis of the incident includes characterizing the incident as a previously detected incident or an unknown incident. A strategy for responding to the incident is identified based on the analysis of the incident.

US Patent:

20200327818, Oct 15, 2020

Filed:

Apr 11, 2019

Appl. No.:

16/382176

Inventors:

- Armonk NY, US
Mary D. Swift - Rochester NY, US
Jennifer Nolan - Toronto, CA
Elezaveta Koumpan - Stoney Creek, CA

International Classification:

G09B 5/12
G06Q 10/06
G06Q 10/10
G09B 19/00
G09B 5/04
G10L 13/04

Abstract:

An interleave module interleaves training and task support to assist a user to complete a task while simultaneously providing training to the user. The interleave module helps the user work towards a desired state using a task knowledge base while interjecting appropriate training based on need, the user's mental state and timing constraints. The interleave module may use a variety of input sensors for a subject and the agent to help determine actions to be taken to achieve the task goals and the user's mental state for training.

US Patent:

20200013091, Jan 9, 2020

Filed:

Jul 3, 2018

Appl. No.:

16/026117

Inventors:

- Armonk NY, US
EDWARD E. SEABOLT - Williamson TX, US
MARY D. SWIFT - Rochester NY, US
BRIAN HULL - Brooklyn NY, US

International Classification:

G06Q 30/02
G06F 17/27
G06K 9/00
G06Q 30/06

Abstract:

A method of configuring a widget defining a user interface includes parsing content from a corpus comprising documents describing a plurality of products, selecting a plurality of pillars from the content, wherein the pillars are descriptors describing a product space of the products, determining an affinity of each of the products to each of the pillars, receiving, via the widget, a selection of a first pillar, and displaying a given product in the widget, the given product selected from the products given the selection of the first pillar.

US Patent:

20190334979, Oct 31, 2019

Filed:

Jul 11, 2019

Appl. No.:

16/509036

Inventors:

- Armonk NY, US
Ashok Kumar - Chelmsford MA, US
Mary D. Swift - Rochester NY, US
Michael D. Whitley - Durham NC, US

International Classification:

H04L 29/08
G06F 16/34
G06Q 50/00
G06Q 10/10

Abstract:

A method, computer program product, and computer system for receiving, by a computing device, a question from a user. A first answer provided by a first subject matter expert is identified. A second answer provided by a second subject matter expert is identified. It is determined that a profile of the user matches a first profile of the first subject matter expert more than a second profile of the second subject matter expert. The first answer provided by the first subject matter expert is sent to the user with a preference over the second answer provided by the second subject matter expert based upon, at least in part, determining that the profile of the user matches the first profile of the first subject matter expert more than the second profile of the second subject matter expert.

US Patent:

20190188271, Jun 20, 2019

Filed:

Dec 15, 2017

Appl. No.:

15/844289

Inventors:

- Armonk NY, US
Eun Ha - Armonk NY, US
Chung-Wei Hang - Armonk NY, US
Kazi Hasan - Armonk NY, US
Christopher Munjal Nolan - Acton MA, US
Lin Pan - Armonk NY, US
Sai Prathyusha Peddi - Cary NC, US
Mary Diane Swift - Rochester NY, US

International Classification:

G06F 17/30

Abstract:

Systems and methods for generating answers to questions. One method includes receiving a question having question terms; identifying candidate answers to the question having answer terms; searching data sources to determine passages including either a question term or an answer term in the candidate answer; scoring the passages for candidate answers using a scoring mechanism, the scoring mechanism computing a first degree of relevance of the passage to the question terms, computing a second degree of relevance of the passage to the answer terms of one of the candidate answers, and determining a score for the passage by combining the first degree of relevance and the second degree of relevance; ranking candidate answers to the question based on the scores associated with the scoring each of the passages for each of the candidate answers; and providing an answer to the question based on ranking of the candidate answers.

US Patent:

20190026656, Jan 24, 2019

Filed:

Sep 25, 2018

Appl. No.:

16/141203

Inventors:

- Armonk NY, US
Stephan J. Roorda - Fuquay-Varina NC, US
Mary D. Swift - Rochester NY, US

International Classification:

G06N 99/00
G09B 7/00

Abstract:

A method, computer program product, and computer system, for receiving a first set of ground truth instances from a first source. A second set of ground truth instances may be received from a second source. The first and second sets of ground truth instances may be weighed differently based on a level of trust associated with each of the first and second sources. The weighted first and second sets of ground truth instances may be applied in a machine learning task executed by a computer.

US Patent:

20190019379, Jan 17, 2019

Filed:

Jul 11, 2017

Appl. No.:

15/646425

Inventors:

- ARMONK NY, US
Gregory J. Boss - Saginaw MI, US
Mary Diane Swift - Rochester NY, US
Edgar A. Zamora Duran - Heredia, CR

International Classification:

G08B 7/06
G08B 25/10
G08B 25/01

Abstract:

Embodiments of the present invention disclose a method, computer program product, and system for generating and transmitting a Personalized Emergency Evacuation Plan (PEEP). The computer receives an emergency condition real-time data from a plurality of building sensors, a tracking data of at least one user from a plurality of tracking sensors, a facility structural data from a facility database, and a stored user data from a user database for the at least one user. The computer generates a personalized emergency evacuation plan (PEEP) for the at least one user, wherein is a set of recommendations to put the user in the safest position, based on at least the emergency condition real-time data and the received stored user data. The computer transmits the PEEP to a user mobile device, wherein the user mobile device presents the PEEP to the at least one user.