International Business Machines Corporation

Nuance Communications, Inc.

Other

Airbnb, Inc.

Merative US L.p.

International Business Machines Coproration

Fang Lu

Paul R Bastide

Alaa Abou Mahmoud

Nadiya Kochura

Robert E Loredo

Matthew E Broomhall

Jeremy R Fox

Janani Janakiraman

Uri Kartoun

Susan Marie Cox

Jana Helton Jenkins

Sarbajit Kumar Rakshit

Trudy L Hewitt

Tushar Agrawal

Su Liu

Jonathan D Dunne

Azadeh Salehi

Corey S McCaffrey

Elaine I Kuo

Martin G Keen

Zachary A Silverstein

Dan Zhang

William M Quinn

Maureen Elizabeth Kraft

Piyush Madan

Emmet R Clifford

Stuart J Clifford

Craig M Trim

Joseph Lam

Yoonyoung Park

Vishrawas Gopalakrishnan

Ishwarya Rajendrababu

Kenney Ng

Lenin Mehedy

Shaila Pervin

Mani Abedini

Loulwa F Salem

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

Corinne M Ryan

Thomas J Evans, Iv

Logan Bailey

Daniel Ramirez

Vijay Francis

Meenal Pore

Shruti Kumar

Alex Xingqi Casella

Shane M Kilmon

Sathyanarayanan Srinivasan

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

Christian Compton

Kumar Ravi

Rohit Ranchal

Stefan Von Cavallar

Arun Vishwanath

Yajuan Wang

Chen Wang

Dwarikanath Mahapatra

Bo Wen

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

A method for providing context-aware cueing for daily interactions, navigation, and accessibility is disclosed. In one embodiment, such a method includes receiving routine data describing routine-based tasks associated with a user. The method further receives interaction data describing current interactions of the user in a particular environment. The method processes, using a neural network, the routine data and interaction data to determine a next step to be performed by the user that is consistent with the routine-based tasks and the current interactions. The method provides a cue to the user to perform the next step in the particular environment. This cue may include one or more of a visual, auditory, and haptic cue. The method may continuously refine the neural network to increase the accuracy of the cue. A corresponding system and computer program product are also disclosed.

Context-aware cueing for daily interactions, navigation, and accessibility

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

Mitigating GPS inaccuracy is provided. The method comprises identifying a required level of location accuracy for an activity of an autonomous system and determining, according to GPS coordinates, a location of the autonomous system. A determination is made, according to a knowledge base created by historical learning, whether GPS location accuracy at the location of meets the required level of location accuracy for the activity. Responsive to a determination that the GPS location accuracy at the location of the autonomous system does not meet the required level of accuracy, location determination is handed off to an installed infrastructure within proximity of the autonomous system which provides the required level of location accuracy. The autonomous system then performs the activity according to location information provided by the installed infrastructure.

Proactive mitigation of GPS accuracy errors

A system for layer-by-layer three-dimensional (3D) printing of a 3D printed object. The system includes a printing component configured to print a plurality of layers to form the 3D printed object, a surface modification component configured to be co-operable with the printing component and configured to apply an appropriate degree of surface roughness to at least one of the plurality of layers after being printed, and a controller configured to identify parameters of each of the at least one of the plurality of layers and configured to control operation of the printing component and the surface modification component, wherein the parameters include the appropriate degree of surface roughness.

Method and system of three-dimensional printing to prepare surface for gripping of subsequent layers

Methods for intelligent management of asset workflows are disclosed herein. One method includes predicting that a user is going to perform a predetermined action based on one or more user movements included in a signal received from a wearable sensing device and generating, by a processor, a warning of one or more consequences of the user performing the predetermined action. The method further includes displaying, on augmented reality glass, the warning to the user prior to the user actually performing the predetermined action. Also disclosed herein are systems and apparatus that can include, perform, and/or implement the operations of the methods.

Systems, apparatus, program products, and methods for intelligent management of asset workflows

An embodiment for improved authentication of chatbot users for chat history recovery. The embodiment may record a first chat conversation between a first chat service operator and a first user, wherein the first chat conversation includes a first-step authentication and a chat history. The embodiment may detect a request to resume the first chat conversation. The embodiment may, in response to detecting the request to resume the first chat conversation, initiate a recovery process by sending a random-generated token to the first-step authentication. The embodiment may receive verification of the random-generated token. The embodiment may generate, by a large language model, one or more authentication questions based on content of the chat history. The embodiment may authenticate the first user based on one or more correct answers to the one or more authentication questions. The embodiment may resume the first chat conversation including the chat history.

Cross-platform chatbot user authentication for chat history recovery

Aspects of the present disclosure relate to dynamic adjustment of shared content within web conferences. Web conference data associated with a web conference can be received. A determination can be made that a condition is met for adjusting shared content that is currently being shared within the web conference. An adjustment to make to the shared content that is currently being shared within the web conference can be determined. The shared content can be adjusted based on the determination to generate adjusted shared content. The adjusted shared content can be displayed within the web conference.

Dynamic adjustment of shared content within web conferences

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

Growing community of inventors

Billerica, MA, United States of America

Fang Lu