Laura R Rodriguez

US Patent:

20220318510, Oct 6, 2022

Filed:

Apr 1, 2021

Appl. No.:

17/220513

Inventors:

- Armonk NY, US
Laura Janet Rodriguez - Durham NC, US
Sara Beth Weber - Arlington MA, US
Brittany Bogle - Durham NC, US
Smriti Talwar - Clonsilla, IE
Brent Alan Miller - Cary NC, US

International Classification:

G06F 40/30
G06F 9/451
G06F 16/901
G06F 40/284
G06F 40/253
G06F 40/166

Abstract:

Systems, methods, and computer programming products for alleviating ambiguity amongst the terms and language displayed by the user interface of software products and services. The disclosed solutions catalog terms displayed by the UI of software and services and identify where overlapping terms with the same or substantially similar term names are presented by the UI but have different meanings than the software most familiar to the user. Natural language processing is leveraged to derive meanings of software terms using the context of the surrounding words and text elements within the UI, as well as product documentation, error messages, sentiment and other textual clues. Ambiguity among overlapping terms is alleviated by modifying the UI, highlighting differences in term definitions from the software or services a user is most familiar with using, and updating the UI in a manner that differentiates the overlapping terms displayed by accessed products or services.

US Patent:

20210157817, May 27, 2021

Filed:

Nov 21, 2019

Appl. No.:

16/691398

Inventors:

- Armonk NY, US
Laura Janet RODRIGUEZ - Durham NC, US
Stephanie HUSTON - Durham NC, US

International Classification:

G06F 16/2457
G06F 17/28
H04L 12/58

Abstract:

Techniques for content augmentation and assist are provided. A textual conversation between a first user and a plurality of recipients is analyzed to determine a first intent of the first user. A set of relationships is determined between the first user and the plurality of recipients, and a set of historical intents corresponding to each of the plurality of recipients is evaluated to identify similar intents to the first intent. A plurality of predefined messages is identified based on one or more similar intents that overlap between two or more of the plurality of recipients. A first predefined message is selected, from the plurality of predefined messages, based on the first intent and the determined set of relationships, and suggested content is provided based on the first predefined message.

US Patent:

20200036547, Jan 30, 2020

Filed:

Jul 24, 2018

Appl. No.:

16/044060

Inventors:

- Armonk NY, US
Marshall Lamb - Raleigh NC, US
Laura Janet Rodriguez - Durham NC, US

International Classification:

H04L 12/18
G06F 17/30

Abstract:

A method, system and computer program product for storing and retrieving meeting and presentation effectiveness data. The effectiveness data for material associated with the meeting or presentation is collected, and the effectiveness data is stored as feedback metadata in a file with the material. The feedback metadata comprises an updateable and searchable record of the effectiveness data for the material, thereby allowing a user to search the material based on the effectiveness data as well as its content.

US Patent:

20190349212, Nov 14, 2019

Filed:

May 9, 2018

Appl. No.:

15/974825

Inventors:

- ARMONK NY, US
Marshall A. Lamb - Raleigh NC, US
Laura J. Rodriguez - Durham NC, US

International Classification:

H04L 12/18
G06K 9/00
H04L 29/08

Abstract:

A method, computer system, and a computer program product for evaluating an effectiveness of an electronic meeting based on real-time audience analysis is provided. The present invention may include receiving a participant data feed having at least one physical marker of a meeting participant. The present invention may include measuring the physical marker of each participant. The present invention may include deriving at least one initial audience metric associated with the participant. The present invention may include generating a baseline participant score for each participant based on the derived initial audience metric. The present invention may include evaluating the generated baseline participant score in view of at least one initial factor. The present invention may include generating a baseline meeting effectiveness score for the meeting by aggregating the evaluated baseline participant scores of a plurality of participants and displaying a graphic representation of the generated baseline meeting effectiveness score.

US Patent:

20190208370, Jul 4, 2019

Filed:

Jan 4, 2018

Appl. No.:

15/862402

Inventors:

- Armonk NY, US
Laura J. Rodriguez - Durham NC, US

International Classification:

H04W 4/08
H04L 12/58
G06Q 50/00
G06F 17/30

Abstract:

Formation of connected interest groups in communication threads is described. According to the computer-implemented method, a number of communications within a communication thread that reflect a similar sentiment related to a topic are detected. A level of connectedness of authors of a set of the number of communications is determined and a connected interest group is formed. The connected interest group includes authors with a level of connectedness greater than a predetermined threshold. An indication of the connected interest group is then provided.

US Patent:

20190035421, Jan 31, 2019

Filed:

Sep 28, 2018

Appl. No.:

16/145378

Inventors:

- Armonk NY, US
Laura J. Rodriguez - Durham NC, US

International Classification:

G10L 25/63
G06F 17/27

Abstract:

Mechanisms, in a natural language processing (NLP) system are provided. The NLP system receives a plurality of communications associated with a communication system, over a predetermined time period, from a plurality of end user devices. The NLP system identifies, for each communication in the plurality of communications, a user submitting the communication to thereby generate a set of users comprising a plurality of users associated with the plurality of communications. The NLP system retrieves a user model for each user in the set of users, which specifies at least one attribute of a corresponding user. The NLP system generates an aggregate user model that aggregates the at least one attribute of each user in the set of users together to generate an aggregate representation of the attributes of the plurality of users in the set of users. The NLP system performs a cognitive operation based on the aggregate user model.

US Patent:

20160196313, Jul 7, 2016

Filed:

Jan 2, 2015

Appl. No.:

14/588563

Inventors:

- Armonk NY, US
Laura J. Rodriguez - Durham NC, US

International Classification:

G06F 17/30

Abstract:

Mechanisms, in a Question and Answer (QA) system, are provided for performing a personalized context based search of a corpus of information. A question is received, by the QA system, from a first user via a source device. An answer and supplemental information about the answer to the question are generated based on a corpus processed by the QA system. One or more personality traits associated with the first user are identified and a subset of the supplemental information is selected to present along with the answer to the first user based on the one or more personality traits associated with the first user. The answer and the subset of supplemental information are output to the first user via the source device.

US Patent:

20160196336, Jul 7, 2016

Filed:

Jan 2, 2015

Appl. No.:

14/588547

Inventors:

- Armonk NY, US
Laura J. Rodriguez - Durham NC, US

International Classification:

G06F 17/30

Abstract:

Mechanisms, in a Question and Answer (QA) system, are provided for performing a personalized context based search of a corpus of information. A question is received, by the QA system, from a first user via a source device. A first user profile associated with the first user, which specifies a personality trait of the first user, is retrieved. First candidate answers to the original question are generated based on a search of a corpus and second users having a similar personality trait to the personality trait of the first user are identified. Similar questions to that of the original question, which were previously submitted to the QA system by the one or more second users are identified. Second candidate answers based on the one or more similar questions are generated by the QA system. A final answer based on the first candidate answers and the second candidate answers is generated and output to the user via the source device.