International Business Machines Corporation

Kyndryl, Inc.

Kelley Anders

Jeremy R Fox

Jonathan D Dunne

Liam S Harpur

Trudy L Hewitt

Lisa Seacat DeLuca

Robert Huntington Grant

Jeremy A Greenberger

Grant Douglas Miller

Zachary A Silverstein

Paul R Bastide

Gregory J Boss

John David Wilson

Shadi Eskamaei Albouyeh

Stacy M Cannon

Sarbajit Kumar Rakshit

Al Chakra

Kimberly Dawn McCall

Sonya Leech

Rick A Hamilton, Ii

Fang Lu

Lin Sun

Dana Lea Price

Qi Cheng Li

Nadiya Kochura

Michael C Hollinger

Geoffrey Martin Hambrick

Mary Swift

Michael Scott Thomason

Christian Compton

Meenakshi Nagarajan

Faisal Ghaffar

Paul K Bullis

Ahmad Abdul Wakeel

Irene Lizeth Manotas Gutiérrez

Michael Bender

Maharaj Mukherjee

Jonathan Lenchner

Jessica Kelley Murillo

Cesar Augusto Rodriguez Bravo

David Bruce Lection

Johnny Menh-Han Shieh

Mark B Stevens

Gary Denner

Steven Edward Atkin

Alireza Pourshahid

Ping Xiao

Logan Bailey

William Reilly

Leo Kluger

Chen Liang

Wesley A Hoffler

Robert Roy Paar

Lisa Ann Cassidy

Pauric Grant

Mark Leftwich

Anthony Whelan

Andrew Charles Whiriskey

Darrius Plantz

A computer-implemented method for document concatenation and ontological structuring. The method includes identifying a downloaded file and determining whether the downloaded file is associated with one or more saved files. Based on determining that the downloaded file is associated with the one or more saved files, developing an ontological structure storing the downloaded file and the one or more saved files.

Document concatenation and ontological structuring based on similarities

An embodiment trains a machine-learning model using a first training corpus of general items indicative of varying levels of confidence. The embodiment also prepares a second training corpus that includes domain-specific items indicative of varying levels of confidence extracted from communications from members of a project group associated with a project. The embodiment retrains the machine-learning model using the second training corpus and generates a confidence score for the project based on confidence values assigned by the machine-learning model to each of a plurality of project-related communication items from members of the project group. The embodiment also detects that the confidence score is below a predetermined threshold confidence level and, in response, initiates a communication to members of the project group conveying information regarding an automated remedial action for the project.

Assessing project quality using confidence analysis of project communications

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

A computer-implemented method includes: receiving, by a computer device and from a user device, a draft social media message; determining, by the computer device and based on the receiving, data of an Internet of Things (IoT) device that is related to the draft social media message; generating, by the computer device and based on the determining, a suggested social media message that includes the data of the IoT device; and transmitting, by the computer device, the suggested social media message to the user device.

Automatically suggesting social media messages including Internet of Things (IoT) device data

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

Computer technology for performing a download of a set of file(s) by multiple computer devices. Different computer devices respectively download different parts of the set of files and respectively encapsulate them with file wrappers to create multiple 'sealed off portions.' Each sealed off portion indicates what portion of the code of the set of file(s) is in that sealed off portion. The multiple sealed off portions are transferred (for example, over a local area network) to another computer device, which may, or may not, be one of the multiple computers that created one of the sealed off portions, and this computer device assembles the sealed off portions to re-create the set of file(s).

Computer technology for device forwarding downloads

Embodiments for managing potential customers by one or more processors are described. An identification of a potential customer for a vendor is received. A risk level associated with the potential customer is determined based on customer data from at least one data source associated with the potential customer. A signal representative of the determined risk level associated with the potential customer is generated.

Methods and systems for managing risk with respect to potential customers

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

A method, a computer system, and a computer program product for managing content relevancy is provided. Embodiments of the present invention may include collecting and analyzing a plurality of data, wherein the plurality of data includes document data, document access data and user data. Embodiments of the present invention may include retrieving topic model content based on the plurality of data. Embodiments of the present invention may include building a machine learning (ML) model to determine one or more topics contained in the topic model content. Embodiments of the present invention may include generating a heatmap based on the user data. Embodiments of the present invention may include building a content relevancy model (CRM) based on the ML model and the heatmap. Embodiments of the present invention may include determining an action state for the document data. Embodiments of the present invention may include storing the CRM.

Detecting and improving content relevancy in large content management systems

A ticket relating to a software event is received in a software development system. One or more public forums on software development is searched for the software event. Two or more topics on the software event are identified from one or more conversations from the one or more public forums that regard the software event. Two or more causes of the software event are determined by analyzing interrelations of the two or more topics.

Collaborative software event discourse decomposition

Methods, computer program products, and systems are presented. The methods include, for instance: inputs of emotion time series data of a user and environmental factor data from one or more data collection device for a user assistance service. A baseline emotion time series is generated and an environmental factor that is likely to have affected changes in state of emotion on a subject is identified by regression analysis. An emotion time series model for the identified environmental factor is produced and prediction of a path to attain a target state of emotion at a certain time in the future is made. Recommendation to achieve the target state of emotion is produced based on the predicted path.

State of emotion time series

Embodiments for providing demographic reach with anonymity by a processor. User data access may be managed via a data access agent by generating a unique user privacy profile having a selected level of anonymity for each relationship between a user and an application service.

Managing access to data for demographic reach with anonymity

A method, computer system, and a computer program product for indicating a hyperlink record is provided. The present invention may include receiving a hyperlink. The present invention may also include searching a data structure including a repository of a plurality of hyperlinks stored in at least one user system, where each hyperlink in the repository of the plurality of hyperlinks includes a hyperlink record having at least one reference to the at least one user system. The present invention may then include identifying a record of the received hyperlink in the searched data structure. The present invention may further include, in response to identifying the record of the received hyperlink within the searched data structure, modifying the received hyperlink to indicate the at least one reference to the at least one user system.

Hyperlink visual indicator

The exemplary embodiments disclose a system and method, a computer program product, and a computer system for naming a digital file. The exemplary embodiments may include detecting a user saving an unnamed digital file to a digital folder, extracting one or more first features from data collected from one or more named digital files within the digital folder, generating one or more models correlating the extracted one or more first features with one or more names of the one or more named digital files, extracting one or more second features from the unnamed digital file, and determining a name for the unnamed digital file based on applying the one or more models to the extracted one or more second features.

Cognitive digital file naming

Growing community of inventors

East New Market, MD, United States of America

Kelley Anders