International Business Machines Corporation

University College Dublin

Nationaluniversity of Ireland, Maynooth

Waterford Institute of Technology

National University of Ireland

National University of Ireleand

Jonathan D Dunne

Liam S Harpur

James Patrick Galvin, Jr

Kelley Anders

Patrick Joseph O'Sullivan

Jeremy R Fox

Paul Basil French

Al Chakra

Trudy L Hewitt

Asima Silva

Paul R Bastide

Jeffrey B Sloyer

Hitham Ahmed Assem Aly Salama

Jeremiah O'Connor

Hernan A Cunico

Robert E Loredo

Ian D Stewart

Robert Huntington Grant

Andrew T Penrose

Lisa M W Bradley

David W Malone

Yi Han

Zachary A Silverstein

Gary Denner

Fang Lu

Nadiya Kochura

Amy D Travis

Jonathan Frederick Brunn

Patrick W McDonagh

Qi Cheng Li

Hua Shao

Jason Flood

Lisa Seacat DeLuca

Martin G Keen

Jeremy A Greenberger

John Rice

Shadi Eskamaei Albouyeh

Sumit Patel

Ming Jiang

Mary Swift

Matthew Francis Rutkowski

Mark E Wallace

Bo Jiang

Vijay Francis

Sarbajit Kumar Rakshit

Jana Helton Jenkins

Dana Lea Price

Yuk Lung Chan

Mark Patrick Delaney

Juan Zhang

Si Bin Fan

Lisa M Bradley

Stanley Kieran Jerrard-Dunne

Ping Xiao

Xue Fei Duan

Dong Jun Zong

Ami H Dewar

Jie Mao

Charlotte Hutchinson

Shikhar Kwatra

Matthew E Broomhall

Maharaj Mukherjee

Kuntal Dey

Peng Hui Jiang

Seema Nagar

Jonathan Lenchner

John David Wilson

David Bruce Lection

Sushain Pandit

Xiang Sean Zhou

Xiao Xiao

Mark B Stevens

Hemant Kumar Sivaswamy

Aris Gkoulalas-Divanis

Guang Han Sui

Bo Tong Liu

Steven Edward Atkin

Tiberiu (Jim) Suto

Zhi Hong Li

Ravi Krishnan Muthukrishnan

Da Li Liu

Narayana Aditya Madineni

Kaleb Dean Walton

Xue Yong Zhang

Abdolreza Salahshour

Chao Wu

Vijai Kalathur

Qin Li

Anamitra Bhattacharyya

Raphael I Arar

Qi Feng Huo

Chris Kau

Krishnamohan Dantam

Bhavna Agrawal

Xin Zheng

Muneeb Arshad

Brendan P Arthurs

Pranab Agarwal

Chen Jiang

Melissa Restrepo Conde

A method for tuning software container interdependent systems includes receiving, by a computer processor operating a prediction engine, data from one or more software containers. The data includes operations from one or more software applications in the software containers. The prediction engine identifies a plurality of dependencies in the operations. The prediction engine develops a model of interdependencies based on the identified dependencies. The prediction engine determines one or more failure candidates in the identified dependencies. The prediction engine generates a software architecture template based on the identification of failure candidates.

Rebuilding container event logic from secondary and tertiary systems

A computer implemented method processes log events. A computer system determines dependence and independence of training log events. The computer system clusters the training log events with determined dependence and independence to form clustered training log events. The computer system generates an event association model using the clustered training log events. The computer system clusters the log events using the event association model.

Artificial intelligence driven log event association

A computer-implemented method can determine a linguistic boundary condition for synthetic data generation in a multi-class classification problem. The method includes analyzing empirical labelled data using linguistic and vector representation techniques. The method further includes deriving a synthetic boundary conditional (SBC) model based on the analysis of the empirical labelled data and identifying a boundary location for performant synthetic data generation using the SBC model.

Boundary detection for synthetic data generation

According to one embodiment, a method, computer system, and computer program product for human-machine interfacing is provided. The present invention may include receiving a personality corpus associated with a personality typology comprising multiple personality types; extracting a plurality of utterances from a user; selecting, by a personality model, a personality type associated with the user based on the utterances and the personality corpus; identifying a compatible personality type of the selected personality type; constructing one or more natural language scripts from a word graph associated with the compatible personality type; and transmitting the one or more natural language scripts to the user.

Personality-enhanced chat discourse responses

The illustrative embodiments provide for signature discourse transformation. An embodiment includes detecting a signature discourse of a user by analyzing the user's discourse using corpus linguistics. The embodiment also includes generating computing a collection of words distinct to the user. The embodiment also includes sensing, using tone analysis and a natural language process model, a tone of the collection of words distinct to the user in the signature discourse utterance. The embodiment also includes mapping a cartesian value of the collection of words distinct to the user. The embodiment also includes deriving a signature discourse transformation (SDT) model from the signature discourse utterances, the collection of words, the tone, and the cartesian value. The embodiment also includes transforming, using the signature discourse transformation, an original discourse by the user into an anonymized text.

Signature discourse transformation

An approach for directing a chat agent for an online discussion is provided. A processor retrieves message data from a messaging program. A processor identifies at least one topic present in the message data. A processor, responsive to a determination that the at least one topic is a primary topic, updates the chat agent with the primary topic. A processor modifies message data based on the determined primary topic.

Primary topic identification in text data

An embodiment for determining presentation content effectiveness using attraction modeling is provided. The embodiment may include receiving presentation content from a meeting host during on online collaborative meeting. The embodiment may also include capturing one or more actions of one or more users during a display of the presentation content to the one or more users. The embodiment may further include creating an audience attention model. The embodiment may also include in response to determining at least one user is distracted from the presentation content, modifying the display of the presentation content for each distracted user in accordance with one or more characteristics associated with each distracted user. The embodiment may further include categorizing the one or more users into one or more groups. The embodiment may also include providing visual feedback to the meeting host.

Presentation content effectiveness using attraction modeling

An embodiment of a summarization application divides collected conversation data into media and text components. The application implements respective machine learning mechanisms to enhance modeling operations of the text and media components to identify key elements from the conversation. The application generates a headline banner from a group of key elements based on an analysis involving first predetermined criteria. The application also combines additional key elements to the group of key elements to form a second group of key elements. The application generates a summary from the second group of key elements based on a second analysis involving second predetermined criteria. The application presents, via a display, the headline banner according to a first output of the first key element analysis and the summary according to a second output of the second key element analysis.

Summarizing multi-modal conversations in a multi-user messaging application

At least one target in a speech of a first speaker during an electronic conference is identified. A closest vector between the identified target and a group of possible matches for the target is determined. A most similar match for the identified target is determined based on a current usage context for the identified target, a history of stored information associated with the first speaker and the identified target, and the determined closest vector. The most similar match to a set of participants of the electronic conference is displayed.

Dynamically resolving names and acronyms

Using data of a plurality of interactions within a collaborative network, a collaborative network graph is constructed. Each node in the collaborative network graph represents a participant in an interaction, and each edge in the collaborative network graph represents an interaction between participants represented by corresponding nodes. Using a plurality of stochastic simulations of changes to the collaborative network graph, integration of a new node into the collaborative network is simulated. A simulation in the plurality of stochastic simulations producing a largest score improvement between scores computed on the collaborative network graph is selected as a best simulation. Using a plurality of changes to the collaborative network graph included in the best simulation, an integration recommendation is constructed, in which a portion of the integration recommendation corresponds to a change in the plurality of changes.

Dynamically integrating nodes into a collaborate network

Participant inclusion determination can include generating a textual analysis of a draft of an electronic communication in response to a sender preparing the draft for conveyance over an electronic communications network. A word relevance score can be computed for each word of the draft based on the textual analysis. Probabilistically weighted distances between the sender, an initial recipient of the electronic communication, and more additional recipient candidates for additionally receiving the electronic communication can be determined. The probabilistically weighted distances can correspond to hierarchical distances within a hierarchical structure corresponding to an organization in which the sender, the initial recipient, and one or more additional recipient candidates are members. At least one of the additional recipient candidates can be selected for receiving the electronic communication over the electronic communications network based on the word relevance scores and the probabilistically weighted distances.

Collaboration participant inclusion

A computer-implemented method, computer program product, and computing system is provided for determining quality of experience for communication sessions. In an implementation, a method may include determining a plurality of intrusive quality of experience scores associated with a plurality of intrusive audio transmission samples. The method may also include determining a plurality of non-intrusive quality of experience scores associated with a plurality of non-intrusive audio transmission samples. The method may further include deriving a quality of experience coefficient based upon a relationship between the plurality of intrusive quality of experience scores and the plurality of non-intrusive quality of experience scores.

Determining quality of experience for communication sessions

Embodiments for intelligent mitigation of concentration conflicts by a processor. A concentration level of a user required for one or more primary activities may be determined from one or more data sources. A distraction level indicating a possible impact to the concentration level caused by one or more secondary objects may be determined. One or more actions may be provided to mitigate the possible impact to the concentration level.

Intelligent mitigation of concentration conflicts

Computer-implemented methods, computer program products, and computer systems for mitigating frequency loss may include one or more processors configured for receiving first audio data corresponding to unobstructed user utterances, receiving second audio data corresponding to first obstructed user utterances, generating a frequency loss (FL) model representing frequency loss between the first audio data and the second audio data, receiving third audio data corresponding to one or more second obstructed user utterances, processing the third audio data using the FL model to generate fourth audio data corresponding to a frequency loss mitigated version of the second obstructed user utterances, and transmitting the fourth audio data to a recipient computing device. The first obstructed user utterances are obstructed by a facemask and the one or more second obstructed user utterances is obstructed by the facemask. The FL model may be executed as an audio plugin in a web conferencing program.

Mitigating voice frequency loss

Growing community of inventors

Dungarvan, Ireland

Jonathan D Dunne