International Business Machines Corporation

Airbnb, Inc.

Merative US L.p.

Paul R Bastide

Matthew E Broomhall

Robert E Loredo

Fang Lu

Alaa Abou Mahmoud

Liam S Harpur

Jonathan D Dunne

Lisa Seacat DeLuca

Lin Sun

Thomas J Evans, Iv

Dale M Schultz

Lydia Mai Do

Asima Silva

Rohit Ranchal

Aris Gkoulalas-Divanis

Sean Callanan

Andrew E Davis

Donna Karen Byron

SathyaNarayanan Srinivasan

Senthil K Bakthavachalam

Aaron J Quirk

Jana Helton Jenkins

Kelley Anders

Sandra Louise Kogan

Margo L Ezekiel

Ishwarya Rajendrababu

Shakil Manzoor Khan

Kulvir Singh Bhogal

Trudy L Hewitt

Jeffrey Robert Hoy

Sathyanarayanan Srinivasan

Ralph E LeBlanc, Jr

Fred Raguillat

Alexander Pikovsky

Arun Vishwanath

Dwarikanath Mahapatra

Aaron Michael Cohen

Vijay Francis

Eric S Portner

Piyush Madan

Vishrawas Gopalakrishnan

Susmita Saha

Mark Gargan

Xu Wang

Shunguo Yan

Lisa M W Bradley

John Michael Boyer

Stefan Von Cavallar

Pei Sun

Lorelei M McCollum

Leah A Lawrence

Jayanth Krishnan

Shu Li

Shane M Kilmon

Dan Dumont

Jodi Rajaniemi

Amanda N Savitzky

Patrick Joseph O'Sullivan

Shikhar Kwatra

Corville O Allen

Hubertus Franke

Anca Sailer

Uri Kartoun

Carl Kraenzel

Frederik Frank Flöther

Michael L Taylor

Sunil Kumar Mishra

Richard Tuthill Bassemir

Jennifer Lane Vargus

Benjamin C Wisnewski

Beth L Hoffman

Weisong Wang

Chen Tian

Mary E Miller

Na Pei

Stacy M Cannon

Yael Alkalay

Tushar Kumar Jayantilal

Chun Li Jia

Dana Lea Price

Nadiya Kochura

John Rice

Miguel A Estrada

Amy D Travis

Leho Nigul

Manish Kataria

Eric M Wilcox

Jason Flood

Grant Covell

Jaime M Stockton

Brenton P Chasse

Yun Zhi Lin

Filiz Isabell Kiral-Kornek

Mark E Elliott

Ying Mo

Thomas Hay Rogers

Matthew Stephen Rosno

King Shing K Lui

Neal Fishman

Alexandra Urman

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

A method, computer system, and a computer program product for image evaluation is provided. The present invention may include extracting one or more individual objects from an image. The present invention may include determining a general sentiment for each of the one or more individual objects. The present invention may include determining a personal sentiment score each of the one or more individual objects. The present invention may include generating an overall sentiment score for the image based on at least the general sentiment score for each of the one or more individual objects and the personal sentiment score for each of the one or more individual objects. The present invention may include determining the overall sentiment score for the image exceeds a personal threshold of a user. The present invention may include providing one or more improvement mechanisms to the user.

Emotional response evaluation for presented images

Embodiments of the invention provide a computer system that includes a processor electronically coupled to a memory. The processor is operable to perform processor operations that include determining that a user is in a virtual reality (VR) environment and accessing a multisensory state associated with the VR environment and the user. A multisensory declutter analysis is applied to the multisensory state to generate decluttered multisensory streams. The decluttered multisensory streams are used to generate a decluttered multisensory view associated with the user.

Decluttered views in a virtual environment

A system for generating of posts, the system including: a server; and a network connection for the server; the server to: maintain a database of users and corresponding user behavior when generating a post on a specific topic; match a first user generating a current post and a topic of the current post to user behavior in the database; based on the matching user behavior from the database, identify different versions during development of the current post; and dictate distribution of different versions of the post based on the matching user behavior from the database.

System for social versioning

Systems and techniques that facilitate quantum circuit valuation are provided. In various embodiments, a system can comprise an input component that can access a first quantum circuit. In various embodiments, the system can further comprise a valuation component that can appraise the first quantum circuit based on one or more factors (e.g., frequency factor, complexity factor, resource factor, similarity factor), thereby yielding a value score that characterizes the first quantum circuit. In various instances, the system can further comprise an execution component that can recommend deployment of the first quantum circuit based on determining that the value score exceeds a threshold.

Quantum circuit valuation

Dynamically moderating healthcare application data. Receive an incoming data load request comprising a plurality of referential data elements and assess a downstream query impact of the plurality of referential data elements. Determine, based on the assessing, a sensitivity level of the plurality of referential data elements, and alter, based on the sensitivity level, compilation of insights generated using the plurality of referential data elements and compilation of a plurality of referenced data elements.

Healthcare application insight compilation sensitivity

A system and method of visually displaying healthcare protocols to a user receives from the user, via an electronic communications network, search term(s) associated with a health-related condition. A corpus of document(s) stored in an electronic format is identified with a computer and, based on the search term(s), at least one of the document(s) is analyzed with the computer for a treatment protocol associated with the health-related condition. First content for presentation to the user is determined with the computer, the first content including at least a portion of the treatment protocol associated with the health-related condition. A risk value indicative of risk(s) associated with the first content is determined. In response to a determination that the risk value exceeds the risk threshold, second content for presentation is determined by reformatting the first content. A message is sent causing the second content to be visually displayed to the user.

Risk based presentation of healthcare protocols

A method, system, and computer program product to prevent misinterpretation of communications via artificial intelligence assistants. The method includes monitoring an artificial intelligence enabled communication. The method also includes analyzing messages, participants, and actions within the communication. The method also includes identifying critical data within the communication. The method also includes determining critical sequence data, where the critical sequence data is a sequence of conversation elements that contains the critical data. The method also includes predicting an uncertainty level for the critical sequence data, where the uncertainty level indicates an amount of uncertainty that the artificial intelligence correctly interprets the critical sequence data. The method also includes determining that the uncertainty level for the critical sequence data is above a threshold uncertainty value, resulting in critical sequence data that is subject to misinterpretation. The method also includes resolving any uncertainties for the critical sequence data.

Stream integrity for artificial intelligence conversations

A baseline of behavior is determined for a population of users that interact with an autonomous agent that is configured to respond to natural language prompts of users of the population using respective user profiles for each user. An element associated with a first user that deviates more than a threshold amount from the baseline is identified. In response to the element deviating more than the threshold amount, the autonomous agent is caused to engage the first user unprompted regarding the element via an engagement that is configured to verify an association between the first user and the element. A response from the first user regarding the engagement is determined to verify the association between the first user and the element. A first user profile that corresponds to the first user is updated in response to determining that the first user response verifies the association.

Autonomous communication initiation responsive to pattern detection

A method, computer system, and a computer program product for recasting repetitive messages is provided. Embodiments may include receiving, by a processor, a message. Embodiments may include determining, by the processor, whether the received message is repetitive. Embodiments may include rating, by the processor, an importance level of the received message. Embodiments may include determining a preference for recasting the received message.

Recast repetitive messages

In an approach for conversational interchange optimization, a processor monitors conversations in a communication system. A processor generates a list of topics in the conversations. A processor determines a flow for each topic based on length of time, number of participants, and sentiment associated to each topic. The flow is the progress of interactions and shifts for each topic. A processor builds a statistical model for each topic based on the flow to predict success or failure of a topic progression for an incoming conversation. A processor updates the topic progression for the incoming conversation based on the predicted success or failure.

Conversational interchange optimization

Aspects of the invention include receiving a data erasure request associated with a user and identifying, based at least in part on the data erasure request, an entity associated with the user and one or more identifiers for the user. Aspects also include identifying, based at least in part on the one or more identifiers for the user, a cohort that includes the user and comparing the one or more identifiers for the user to identifiers of a plurality of users that are not members of the cohort. Aspects further include identifying a replacement user from the plurality of users based on the comparison and replacing the entity associated with the user in the cohort with an entity associated with the replacement user.

Timing for user data erasure requests

A method, system and computer program product for managing a calendar application. A need to optimize a calendar is identified. Furthermore, a period of time to optimize the calendar is received or identified. All the scheduled events (e.g., scheduled meetings) in the calendar are then selected during that period of time. The attendees, topics and flags, if any, for each of the selected scheduled events during the period of time are extracted. Prior collaborations with the user involving the extracted attendees and/or topics of the selected scheduled events are identified. Collaboration data (e.g., participants/senders/attendees, topics) is then extracted from the identified prior collaborations. A list of actions (e.g., delegate scheduled event to another user) is generated to be performed on a selected scheduled event based on the extracted collaboration data. The generated list of actions to be performed on the selected scheduled event is then presented to the user.

Assisting user in managing a calendar application

A method, system and computer program product for improving the discoverability of messages on a social network. The creation of a proposed message that requests a response from a target audience is detected. The social network is then searched to identify search terms and posts related to the proposed message. Upon identifying the search terms, the search terms are ranked in order of usage among the identified posts. A list of identified search terms in order of rank is then presented to the user to modify the proposed message. The proposed message is modified using a search term selected by the user from the list of search terms. The modified message is then posted on the social network. In this manner, the message created by the user has been modified to improve the discoverability of the message on the social network and to increase responses from an appropriate target audience.

Modifying messages to be more discoverable on a social network

Online outreach based reward model generation is described. A set of features that are indicative of an online outreach for a user are determined, the online outreach originating from a particular online network. Based on this set of features, an online outreach for the user originating from the particular online network is determined. A reward model is derived from the online outreach for the user. The reward model indicates locations within the particular online network that are to be searched for user information.

Online outreach-based reward model generation for user information search

Growing community of inventors

Boxford, MA, United States of America

Paul R Bastide