International Business Machines Corporation

Nuance Communications, Inc.

Other

Airbnb, Inc.

Merative US L.p.

Fang Lu

Paul R Bastide

Alaa Abou Mahmoud

Nadiya Kochura

Robert E Loredo

Matthew E Broomhall

Janani Janakiraman

Jeremy R Fox

Uri Kartoun

Susan Marie Cox

Jana Helton Jenkins

Sarbajit Kumar Rakshit

Trudy L Hewitt

Su Liu

Tushar Agrawal

Azadeh Salehi

Corey S McCaffrey

Elaine I Kuo

Jonathan D Dunne

Dan Zhang

William M Quinn

Maureen Elizabeth Kraft

Piyush Madan

Stuart J Clifford

Emmet R Clifford

Craig M Trim

Zachary A Silverstein

Joseph Lam

Yoonyoung Park

Vishrawas Gopalakrishnan

Ishwarya Rajendrababu

Weisong Wang

Martin G Keen

Lenin Mehedy

Kenney Ng

Shaila Pervin

Mani Abedini

Loulwa F Salem

Jingwei Yang

Jeremy A Greenberger

Jing Lan Chen

Li Ping Wang

Clement Decrop

Shilpa N Mahatma

Xi Zhang

Nancy Ellen Kho

Jin Yan Chen

SathyaNarayanan Srinivasan

Jayanth Krishnan

Ka Lin

Lisa Seacat DeLuca

Corville O Allen

Donna Karen Byron

Kelley Anders

Robert Huntington Grant

Mark Alexander McGloin

Steven I Ross

Shi Kun Li

Thomas J Evans, Iv

Corinne M Ryan

Daniel Ramirez

Logan Bailey

Vijay Francis

Meenal Pore

Shruti Kumar

Alex Xingqi Casella

Sathyanarayanan Srinivasan

Shane M Kilmon

Hau Co

Lei Wang

James R Kozloski

Aaron K Baughman

Itzhack Goldberg

Susann Marie Keohane

Michael Muller

Chin Ngai Sze

Rasit Onur Topaloglu

Anca Sailer

Wen Jie Wang

Jing Yang

Eoin Lane

Pratyush Kumar

Thomas T Hanis

Kumar Ravi

Christian Compton

Rohit Ranchal

Stefan Von Cavallar

Arun Vishwanath

Yajuan Wang

Dwarikanath Mahapatra

Fatemeh Jalali

Grant Covell

Ye Xu

Melissa Restrepo Conde

James M Moreno

Gigi Y C Yuen-Reed

Alphonse Joseph Wojtas

Mauro Martino

Charu Pandhi

Harini Jagannathan

Embodiments detect a task keyword related to an offloaded task of a task-giver, train a machine learning (ML) model using the task keyword, determine that the task keyword is similar to a historical task by utilizing the trained ML model, record a user input in response to determining that the task keyword is similar to the historical task, freeze an action execution during a pseudo action before a finality action is executed, provide the recorded user input to the task-giver and requesting approval from the task-giver, and execute the offloaded task using robotic process automation (RPA) in response to receiving approval from the task-giver.

Ad-hoc pseudo completion task

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 digital model is generated of a debris location where the digital model includes an augmented reality overlay of the debris location. Digital data from sensors at a debris field is received at a computer, and the digital data depicts debris in the debris field. Materials in the debris field are detected and identified based on the detected materials in the debris field. Layers of materials in the debris field are identified. A digital model is generated of the materials in the debris field including in the layers. Using the computer and an augmented reality (AR) device, an augmented reality overlay is generated based on the digital model of the materials in the debris fields. The augmented reality overlay is superimposed over the digital model of the materials in the debris field to indicate the materials in the debris field and the materials in the layers of the debris field.

Augmented reality overlay of digital model of debris location to detect environmental risks

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

Taking security actions according to calculated sensitivity levels of objects. Sensitivity levels are determined according to learned security measures taken on objects having certain content. Security actions are taken upon determining that an object in view of recently added content has an actionable sensitivity level. Additional considerations apply to baseline aspects of the object as well as ongoing changes to the baseline considerations.

Content based security requirements

An embodiment for augmented reality (AR)-based visualization of an activity with collaboration amelioration is provided. The embodiment may include receiving real-time and historical data relating to an activity. The embodiment may also include identifying each step of the activity and a time to complete each step. The embodiment may further include executing a plurality of digital twin simulations of avatars of different types of workers performing each step of the activity. The embodiment may also include in response to determining a current distribution of human and robotic workers is not optimized, prompting a manager with an AR overlaid slider bar. The embodiment may further include generating a knowledge corpus including an optimized distribution. The embodiment may also include creating a visual animation of the optimized distribution. The embodiment may further include displaying the visual animation to at least one human worker via an AR device.

AR-based visualization of activity with collaboration amelioration

In an approach to improve risk assessment and management, embodiments monitor a predetermined area by collecting, by one or more sensing devices, data related to environmental conditions and spatial relationships between one or more objects in the predetermined area. Further, embodiments determine, based on a model and the monitoring, that an accidental event is likely to occur within a predetermined distance or within the predetermined area. Additionally, embodiments identify a predetermined mitigation action from a knowledge corpus to apply to the accidental event; and proactively implementing the identified mitigation action to prevent or manage the accidental event.

Computer-based risk analysis and mitigation

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

Facilitating transfer of data from a first machine and/or computing system to at least a second machine and/or computing system in instances where traditional data transfer methods (such as using a communications network) are not immediately feasible is achieved by identifying a triggering event for physical transport of data, collecting the data to be transported, and transferring the data. Secure transfer of the collected data is achieved via encryption of the collected data.

Data transfer workflow in a multi-machine ecosystem

An approach for assisting users with disabilities in an emergency situation relating to a vehicle is disclosed. The approach determines the profile of the passenger in a vehicle by noting preferences and disabilities associated with the passenger. After a vehicle accident, the approach determines the condition of the vehicle and the condition of the passenger. Based on various information received, the approach creates an action list of solutions for the passenger, wherein the action list has assigned dynamic risk scores. The approach determines the best solution based on the risk scores and selects the best solution from the action list.

Assistance from autonomous vehicle during emergencies

A method, computer system, and a computer program product for optimizing social collaboration is provided. The present invention may include identifying content within a social collaboration history with a high level of engagement. The present invention may include generating one or more groups of unique topic keywords based on the identified content. The present invention may include receiving a potential post from a user. The present invention may include identifying an overlap between the potential post and at least one of the one or more groups of unique topic keywords. The present invention may include providing one or more recommendations to the user.

Information sharing with effective attention management system

Disclosed are techniques for dynamic compression of audio-visual data, including a digital encoding method, digital compression method, and a system. One embodiment of the digital encoding method may comprise identifying a scene projected onto a sensor, wherein the scene comprises a plurality of objects. Some embodiments may further comprise analyzing the plurality of objects to determine which of the plurality objects can be redeveloped by a GAN regeneration module to a threshold quality level and which of the plurality of objects cannot be redeveloped with the GAN regeneration module to the threshold quality level. Some embodiments may further comprise generating an optimized capture plan based on the analyzing. Some embodiments may further comprise encoding the scene pursuant to the optimized capture plan to produce a digital media file.

Dynamic compression of audio-visual data

The present invention may include a computing device that receives root data, where the root data comprises a plurality of datasets. The computing device determines a context of each dataset within the plurality of datasets. The computing device identifies one or more users based on monitoring behavior of the one or more users related to each dataset. The computing device appends metadata associated with each dataset within the plurality of datasets with the determined context and the one or more identified users and setts access restrictions to each dataset in the metadata based on the context and the one or more identified users.

Contextualization of organization data and handling storage quantification

Described is a method for logistic transport monitoring of an IoT device utilizing token generation for payload data for features and peripheral functionality associated with the IoT device being shipped between an origin location and a target location. The method include generating a pre-shipment token prior to loading of the IoT device onto a logistic transporter and regenerating a token subsequent to loading of the IoT device onto the logistic transporter, where a validated pre-shipment token and a matching regenerated token indicate a faultless operational status of the IoT device. The method includes iteratively regenerating tokens during the shipment of the IoT device, where a mismatch between an iteratively generated token and the regenerated token indicate an operational fault of the IoT device indicating the IoT device was damaged during the shipment between the origin location and the target location.

Logistical transport verification of operational functionality

A method, system and computer program product for amplifying a single voice during an audio conversation. One embodiment of the method may comprise receiving, by a computing device, an audio sample of speech from a user, and generating, by the computing device, a user-specific acoustic model for enhancement of speech by the user based upon the audio sample. The method may further comprise receiving a live audiovisual stream, the live audiovisual stream including live speech by the user during an audio conversation, wherein the live audiovisual stream includes background noise, and using, by the computing device, the user-specific acoustic model to selectively amplify the live speech during the live audiovisual stream without amplifying the background noise.

Speaker-specific voice amplification

Growing community of inventors

Billerica, MA, United States of America

Fang Lu