International Business Machines Corporation

Justin David Weisz

Justin Gregory Manweiler

James R Kozloski

Clifford A Pickover

Maryam Ashoori

Katherine Vogt

David M Lubensky

Yu Ma

Gregory F Boland

Peter Kenneth Malkin

Umut Topkara

Blaine H Dolph

Mal Pattiarachi

Kevin E Siemonsen

James Thomas Rayfield

Avraham Leff

Marco Pistoia

Michael S Gordon

Nitendra Rajput

Jacquelyn Annette Martino

Danny Soroker

Kristina Marie Brimijoin

Hani Talal Jamjoom

Anni Rosa Coden

Stephanie Houde

Russell G Olsen

Mahanth K Gowda

Xiying Wang

Judith O Uchidiuno

Ashish Kundu

Michael Muller

Youngja Park

Ching-Yung Lin

John Thomas Richards

Steven I Ross

Elham Khabiri

Shimei Pan

Keith C Houck

Fernando Carlos Martinez

Marcus D Roy

Saad Ismail

Wanyi Lin

Sarbajit Kumar Rakshit

Robert G Farrell

James Corvin Fletcher

Jonathan H Connell

Atul S Kumar

Kartik Talamadupula

Sal M Rosato

Arunima Chaudhary

Mayank Agarwal

Abhishek Bhandwaldar

Donald W McCleary

Benjamin Hoover

In an approach for assisting a user to remain focused on a task, a processor collects a plurality of information regarding one or more digital activities of a user. A processor tokenizes the plurality of information into one or more vectorized embeddings. Responsive to determining that the user has engaged a focus mode, a processor intercepts one or more communications. A processor synthesizes, utilizing a large language model and the one or more vectorized embeddings, one or more natural language responses to the one or more communications. A processor transmits the one or more natural language responses to one or more originating users of the one or more communications. Responsive to determining that the user has ended the focus mode, a processor displays a summary of the one or more communications and the one or more natural language responses transmitted while the user was in the focus mode.

Summarization for attention management and recall

Embodiments relate to interactive graphical display. A request is processed by a generative system to generate multiple hypotheses of an output in response to the request, a primary hypothesis of the multiple hypotheses having a highest confidence for the output, multiple secondary hypotheses of the multiple hypotheses having a lower confidence than the highest confidence. At least one region of divergence is determined from the primary hypothesis by the multiple secondary hypotheses, the at least one region of divergence having alternatives in the multiple secondary hypotheses, the alternatives in the multiple secondary hypotheses differing from the primary hypothesis. A graphical user interface displays the at least one region of divergence in the primary hypothesis and alternatives in the multiple secondary hypotheses for the at least one region of divergence, the alternatives and primary hypothesis for the at least one region of divergence being displayed as selectable options for a user.

Interactive graphical display of multiple overlapping hypotheses or document versions

An implicit bias monitoring system is provided. The system receives sensor data including video and audio that are captured during an interaction between a first individual and a second individual. The system determines a set of attributes associated with the interaction based on the received sensor data, the set of attributes comprising at least one of race and gender of the second individual. The system detects an implicit bias based on a combination of the determined set of attributes and a bias profile. The system generates an alert based on the detected implicit bias.

Detecting and notifying for potential biases in artificial intelligence applications

A method for applying GPS UAV attitude estimation to accelerate computer vision. The UAV has a plurality of GPS receivers mounted at fixed locations on the UAV. The method includes receiving GPS signals from each GPS satellite in view of the UAV, the GPS measurements comprising pseudo-range and carrier phase data representing the distance between each GPS receiver and each GPS satellite. Carrier phase and pseudo-range measurements are determined for each GPS receiver based on the pseudo-range and carrier phase data. The GPS carrier phase and pseudo-range measurements are compared pair-wise for each pair of GPS receiver and satellite. An attitude of the UAV is determined based on the relative distance measurements. A 3D camera pose rotation matrix is determined based on the attitude of the UAV. Computer vision image search computations are performed for analyzing the image data received from the UAV in real time using the 3D camera pose rotation matrix.

Acceleration of real time computer vision processing on UAVs through GPS attitude estimation

A method of using artificial intelligence to provide source code from an original programming language in a target programming language showing regions of low confidence. The method includes receiving, by a computing device, a code base in an original programming language. The computing device further provides the code base in the original programming language to a target programming language using an artificial intelligence tool. The computing device additionally displays the code base in the target programming language using a visualization tool in a visual interface. The computing device still further displays the regions of uncertainty to a human user in the visual interface. The regions of uncertainty provide low confidence regions of the code base in the target programming language for targeted user intervention. The regions of low confidence correlate with violations to provide displayed actionable insight regions.

Computer assisted programming with targeted visual feedback

A method, system, and computer program product for motion-based user interfaces are provided. The method identifies a navigation mode indication. A navigation interface is generated at a display device and configured based on the navigation mode indication to include a first graphical content. At least a portion of the navigation interface is modified based on one or more movements of the mobile computing device. A portion of the navigation interface is selected based on detecting a pressure change on at least a portion of a mobile computing device. The method presents a second graphical content on the display device based on the selected portion of the navigation interface.

Movement pattern-based mobile device user interfaces

A method includes defining a two-dimensional geographic region by two-dimensional geographic coordinates to define the bounds of the region, converting each of the two-dimensional coordinates to three dimensional coordinates by way of a lookup stored in a computer readable medium, generating a three-dimensional grid of points, each spaced in an arrangement to encompass coverage of a predetermined ground area, and applying heuristics for a shortest path planning, relative to the three-dimensional grid of points.

Method of optimized path planning for UAVs for the purpose of ground coverage

A system, method and computer program product for composing persistent object instances that link resources across multiple, disparate systems. An example method includes associating resources with namespace-URLs and object instances. One of the namespace-URLs is designated as primary namespace-URL. A web-based object API is provided through which the object instance can be accessed. The web-based object API uses the primary namespace-URL as an identifier of the object instance.

Composition of persistent object instances linking resources across multiple, disparate systems

An embodiment of the invention provides a method for sending a message from a first user to a second user where an interface receives a message from the second user. A processor connected to the interface identifying one or more keywords in the message and searches an electronic database for the keyword(s) to identify one or more scripted message for the keyword(s). The electronic database includes scripted messages for each keyword in the electronic database. A communications device connected to the processor sends the identified scripted message(s) to the second user.

Cognitive messaging with dynamically changing inputs

A video stream control method, system, and a computer program product include analyzing a video stream to identify a section of the video stream where a condition will occur, delivering a notification that the condition will occur in the section of the video stream and modifying the video stream before the section of the video stream is played, and selecting a type of delivery of the section of the video stream based on a set of rules factoring the condition and user data at a time of the notification.

System, method, and recording medium for providing notifications in video streams to control video playback

The present application relates to systems for programming devices, such as unmanned autonomous vehicles or 'drones,' with a card-based format and methods for using the same. The system and methods generally comprise a programming system that receives one or more instructional cards selected by a user. The system generates an executable program based on the instructional cards received, and transmits the program to a device for execution.

Systems and methods for programing drones

A vehicular alert system includes an autonomous aerial vehicle and a central computer. The autonomous aerial vehicle includes a processor, a display, and a detector. The processor controls a data transceiver. The detector detects one or more vehicular condition. The central computer communicates with the autonomous aerial vehicle via the data transceiver. The central computer includes a memory device. The memory device stores vehicular condition data and road condition data. The central computer communicates one of a vehicular condition or a road condition to the autonomous aerial vehicle. The processor of the autonomous aerial vehicle displays the received condition on the display.

Vehicular alert system

A method for controlling a drone includes receiving a request for information about a spatial location, generating data requests, configuring a flight plan and controlling one or more drones to fly over the spatial location to obtain data types based on the data requests, storing heterogeneous data captured by the one or more drones and creating spatio-temporal indices for identifying spatial or temporal coverage gaps in the data necessary to answer the request, controlling the one or more drones to fly over the spatial location to obtain a plurality of data types from the identified spatial or temporal coverage gaps and extracting and analyzing data to answer the request.

System and method to operate a drone

Growing community of inventors

Scarsdale, NY, United States of America

Justin David Weisz