International Business Machines Corporation

Rachel K E Bellamy

John Thomas Richards

Calvin Bruce Swart

Peter Kenneth Malkin

Bonnie E John

Sharon Mary Trewin

John C Thomas, Jr

Jacquelyn Annette Martino

Paul Michael Matchen

Michael Desmond

Valentina Salapura

Jonathan Lenchner

Jonathan Hudson Connell, Ii

Robert G Farrell

Brian Paul Gaucher

David O S Melville

Harold Leon Ossher

Samuel Scott Adams

Padmanabhan Santhanam

Jonathan P Brezin

Myra B Cohen

Amanda M Swearngin

Sameep Mehta

Philip Shilung Yu

Biplav Srivastava

Ramya Raghavendra

Elizabeth Daly

Kalapriya Kannan

Kush Raj Varshney

Thomas David Erickson

Aleksandra Mojsilovic

Oznur Alkan

Darrell Christopher Reimer

Manish Kesarwani

Matthew R Arnold

Tracee L Wolf

Clay Edwin Williams

Kaoutar El Maghraoui

Michael James Hind

Jason Benjamin Ellis

Wendy Anne Kellogg

Matthew Scott Davis

Stephanie Houde

David John Piorkowski

Vera Liao

Margaret Myers Burnett

Jason Tsay

Mark Richard Laff

Joseph A Lawrance

Takayuki Yamaizumi

Brian Price

A method for automatically generating documentation for an artificial intelligence model includes receiving, by a computing device, an artificial intelligence model. The computing device accesses a model facts policy that indicates data to be collected for artificial intelligence models. The computing device collects artificial intelligence model facts regarding the artificial intelligence model according to the model facts policy. The computing device accesses a factsheet template. The factsheet template provides a schema for an artificial intelligence model factsheet for the artificial intelligence model. The computing device populates the artificial intelligence model factsheet using the factsheet template with the artificial intelligence model facts related to the artificial intelligence model.

Generation and management of an artificial intelligence (AI) model documentation throughout its life cycle

A processor may record a first location at an event with at least one person. The processor may monitor a plurality of actions of that at least one person at the first location. The processor may interpret at least one action of the at least one person that indicates a change of interest to a second location at the event. Based on the at least one action, the processor may determine the second location at the event. The processor may record the second location at the event.

Automatic selection of event video content

Embodiments for building domain models from dialog interactions by a processor. A domain knowledge may be elicited from one or more dialog interactions with one or more users according to one or more dialog strategies. One or more domain models may be built and/or enhanced according to the domain knowledge.

Building domain models from dialog interactions

In one embodiment, in accordance with the present invention, a method, computer program product, and system for performing actions based on captured interpersonal interactions during a meeting is provided. One or more computer processors capture the interpersonal interactions between people in a physical space during a period of time, using machine learning algorithms to detect the interpersonal interactions and a state of each person based on vision and audio sensors in the physical space. The one or more computer processors analyze and categorize the interactions and state of each person, and tag representations of each person with the respectively analyzed and categorized interactions and states of the respective person over the period of time. The one or more computer processors then take an action based on the analysis.

Detecting interaction during meetings

A computer-implemented method manages remote electronic drop-ins on local conversations. A local audio sensor transmits a captured conversation from a local cluster of persons to a remote communication device where members of the local cluster of persons are within a predefined distance of one another, and where the remote communication device is at a location that is beyond a human hearing range from the local audio sensor. One or more processors determine that the captured conversation is about a particular topic. A request from a remote user is received from the remote communication device to electronically drop in on a particular remote cluster of persons who are having a conversation about the particular topic. In response to receiving the request from the remote user, one or more processors selectively connect a local communication device proximate to the cluster of persons to the remote communication device.

Managing drop-ins on focal points of activities

Detecting user input based on multiple gestures is provided. One or more interactions are received from a user via a user interface. An inferred interaction is determined based, at least in part, on a geometric operation, wherein the geometric operation is based on the one or more interactions. The inferred interaction is presented via the user interface. Whether a confirmation has been received for the inferred interaction is determined.

Detecting input based on multiple gestures

A computer-implemented method manages drop-ins on conversations near a focal point of proximal activity in a gathering place. One or more processors receive a first set of sensor data from one or more sensors in a gathering place, and then identify a focal point of proximal activity based on the first set of received sensor data received from the one or more sensors. One or more processors characterize a conversation near the focal point based on a second set of received sensor data from the one or more sensors, and then present a characterization of the conversation to an electronic device. One or more processors enable the electronic device to allow a user to drop-in on the conversation.

Systems and methods are provided for post-hoc correction of calibration errors in eye tracking data, which take into consideration calibration errors that result from changes in user position during a user session in which the user's fixations on a display screen are captured and recorded by an eye tracking system, and which take into consideration errors that occur when the user looks away from a displayed target item before selecting the target item.

Correcting systematic calibration errors in eye tracking data

In a method for generating an audio summary of a portion of an electronic document, a user input selecting a focus position within a rendered electronic document is received. The plurality of document elements included in the rendered electronic document is identified. A plurality of audio objects corresponding to the plurality of document elements is generated. An audio signal is generated. The audio signal includes a subset of the plurality of audio objects corresponding to a subset of the plurality of document elements contained within a predetermined range from the focus position. The audio signal indicates the spatial relation between the elements of the elements subset. The audio signal is rendered to the user.

Context awareness in auditory browsing

Mechanisms are provided for generating a shape tag cloud display. A user input is received that specifies an arbitrarily hand-drawn shape tag. A set of shape tag equivalence classes is updated based on the received user input to assign the arbitrarily hand-drawn shape tag to a shape tag equivalence class having similar previously entered arbitrarily hand-drawn shape tags. Rankings of the shape tags relative to one another are generated. The shape tag cloud display is generated based on the rankings. A representation of each shape tag within the shape tag cloud display has display characteristics based on the rankings. The shape tag cloud display is then output.

Creating tag clouds based on user specified arbitrary shape tags

Methods of providing usability predictions are set forth herein. A method includes obtaining test cases for analyzing usability of a graphical user interface of a given software application. The method further includes automatically generating, using a processor, a human performance model based on the test cases. The method also includes generating the usability predictions based on the human performance model. At least some of the test cases are generated automatically from an analysis of the given software application.

Linking graphical user interface testing tools and human performance modeling to enable usability assessment

Growing community of inventors

Bedford, NY, United States of America

Rachel K E Bellamy