International Business Machines Corporation

Kyndryl, Inc.

Maplebear Inc.

Martin G Keen

John Michael Ganci, Jr

Sarbajit Kumar Rakshit

James Edward Bostick

Craig M Trim

Hernan A Cunico

Jeremy R Fox

Michael Bender

Natalie Brooks Powell

Adam Smye-Rumsby

Brian M O'Connell

Evelyn R Anderson

Paul A R Frank

Kristen Conley

Zachary A Silverstein

Aaron K Baughman

Clement Decrop

Tushar Agrawal

Gandhi Sivakumar

Andrew David Humphreys

John J P McNamara

Shikhar Kwatra

Richard D Johnson

Andrew M Garratt

Kimberly Greene Starks

Paul Alexander Raphael Frank

Alexander Reznicek

Bahman Hekmatshoartabari

Fang Lu

David Bruce Lection

Gregory J Boss

Jonathan D Dunne

Mauro Marzorati

Phani Kumar V U Ayyagari

Stan Kevin Daley

Madan K Chukka

Martin J Presler-Marshall

Grant Mericle

Ravi Ranjan

David W Messina

Dean T Brown

Rhonda L Childress

John David Wilson

Abhishek Jain

Tiberiu (Jim) Suto

Mary E Rudden

Atul Mene

Thomas Jefferson Sandridge

Harry Hoots

Vignesh Harish

David W Watts

Keith R Walker

Jana Helton Jenkins

Sarvesh S Patel

Kushal S Patel

Randy Allan Rendahl

Raghuveer Prasad Nagar

Hemant Kumar Sivaswamy

Mu Qiao

Gary Francis Diamanti

Uri Kartoun

Garfield Winston Vaughn

Victor Povar

Jennifer M Hatfield

Jennifer A Mallette

Michael Boone

Todd Mark Kelsey

Michael Seth Silverstein

Robert A Richter

John Handy Bosma

Paul P Giangarra

Michael J Iantosca

Khwaja Jawahar Jahangir Shaik

Richard Johnson

Xin Wang

Anthony Stevens

Joel Garnatz

Rita Beisel

Cristina Olivia McComic

Roger Everette Sanders

Christopher John Rayns

Paul Alexander Frank

Uma Maheshwar Reddy Chamakura

Brian M Burnette

Justin S Teasley

Todd Neill

Mark A Castle

Mark N Walters

Chris Rayns

Jenny Davidse

Caroline S C McNamara

Kriti Kamra

Makenzie Manna

An embodiment for a method of using machine learning algorithms to proactively identify potential errors in code instance data for creating technical documentation. The embodiment may receive code instance data. The embodiment may generate error classifications for the received code instance data using a convolutional neural network and natural language processing techniques. The embodiment may perform a correlation analysis to derive correlations between the generated error classifications for the received code instance data and similarly occurring classifications in one or more historical code instances. The embodiment may calculate a score for each of the derived correlations, the calculated score corresponding to a likelihood that the similarly occurring classifications in the one or more other code instances represents a potential error. The embodiment may output notifications to a user for each of the derived correlations for which the calculated score exceeds a threshold value.

Proactively identifying errors in technical documentation code

A computer-implemented method, in accordance with one embodiment, includes obtaining observational data from an unmanned aerial vehicle (UAV) deployed in a working environment, the working environment including a plurality of entities carrying out tasks within the working environment. The data is analyzed to detect a disruption caused by the UAV to one or more of the entities within the working environment during the deployment. A parameter of a deployment is adjusted based on the analysis of the obtained data.

Unmanned aerial vehicle deployment parameter modification

A context aware code snippet recommendation method, system, and computer program product that includes generating comments for source code, learning semantically meaningful sentence embeddings based on the comments, and retrieving code snippets from the source code based on the learned semantically meaningful sentence embeddings.

Context aware code snippet recommendation

According to one embodiment, a method, computer system, and computer program product for selectively recording meetings is provided. The embodiment may include initiating a digital meeting. The embodiment may also include determining two or more rule sets, including one or more local rule sets, for selectively recording the digital meeting, wherein each rule set includes one or more rules. The embodiment may further include recording one or more recordings of the digital meeting according to each local rule set.

Selective recording of meeting content

A process is provided for usage-pattern-based generation of a digital model of a product. The process includes obtaining a usage pattern of a user of a product, where the usage pattern includes a set of usage pattern parameters. In addition, the process includes using a machine learning model of an artificial intelligence system to generate a 3-D virtual image of the product aligned with the usage pattern, and analyzing, by the artificial intelligence system, the 3-D virtual image of the product to facilitate identifying a requirement specification for the product based on the usage pattern. Further, the process includes generating a digital model of a new product for the user based on the identified requirement specification.

Usage-pattern-based generation of digital product model

A computer-implemented method for airflow control for agricultural pollination is disclosed. The computer-implemented method includes performing image analysis on an agricultural image to determine a type and classification of one or more plants in the agricultural image, determining one or more pollination requirements for the one or more determined plants, determining one or more current airflow parameters within a predetermined area of the one or more plants in the agricultural image, determining one or more optimal airflow parameters based on the type of plants in the agricultural image, the classification of plants in the agricultural image, the one or more pollination requirements for the plants in the agricultural image, and the one or more current airflow parameters, and generating an automatic airflow adjustment model for optimizing the airflow parameters for the plants based, at least in part, on the one or more determined optimal airflow parameters.

Airflow control for agricultural pollination

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

In an approach for monitoring a user's in-flight activity and/or a pattern of movement of a user and warning the user of an in-flight activity or a pattern of movement that could lead to a potential short-term or long-term injury, a processor monitors a body movement and a posture of a user through an application of micro-location analysis enabled by a mesh network of 5G sensors over a period of time. A processor determines whether the body movement and the posture detected can lead to an activity or a series of activities that can result in a potential injury. Responsive to determining a pre-set threshold of risk has been reached, a processor issues a real time alert to the user to warn of the potential injury.

Preventative workplace injury alerting system utilizing mmwave 5G positional localization

Embodiments of the invention are directed to a computer-implemented method that includes accessing, using a processor system, a three-dimensional (3D) model of a device-under-design (DUD). The processor system is used to receive a first design operation associated with the 3D model of the DUD. A collaboration dependency model is used to make a prediction of a dependency relationship between the first design operation and a second design operation.

Virtual reality design navigation using a temporal collaboration dependency map

An embodiment includes classifying an incoming communication message as having an instruction classification based on a natural language processing (NLP) analysis of the incoming communication message. The embodiment extracts, responsive to classifying the incoming communication message as having the instruction classification, user operations as a workflow dataset. The embodiment clusters the workflow dataset into a task cluster with other similar workflow datasets representative of previously-extracted user operations. The embodiment designates the instruction classification as a trigger event based at least in part on the NLP analysis of the incoming communication message. The embodiment generates a robotic process automation (RPA) bot script that comprises program instructions executable by a processor to cause the processor to perform operations that automate the user operations in response to the trigger event.

Automatic detection of robotic process automation trigger events

According to one embodiment, a method, computer system, and computer program product for identifying induced deformation of a 3D object is provided. The embodiment may include receiving an unaltered three-dimensional (3D) rendering of an object and attribute information of the object. The embodiment may include identifying one or more influencing factors of forecasted local deformation of one or more portions of the 3D rendering based on the attribute information. The embodiment may include creating, via a generative adversarial network (GAN), a 3D rendering of the object showing the forecasted local deformation. The embodiment may include identifying induced deformation of one or more other portions of the 3D rendering caused by the forecasted local deformation. The embodiment may include creating, via the GAN, a 3D rendering of the object showing the identified induced deformation.

Generative adversarial network based identification of induced deformation in three-dimensional object

A computer-implemented method, a computer system and a computer program product adapt a vehicle communication network range based on an awareness of vehicle speed. The method includes identifying a plurality of devices within a recommended range of a vehicle. The method also includes obtaining a current driving environment from the plurality of devices. In addition, the method includes calculating a required range for a communications network based on the current driving environment and determining required devices within the required range. Lastly, the method includes dynamically creating the communications network when the required range is greater than the recommended range, where the communications network includes the vehicle, the plurality of devices within the recommended range and the required devices.

Speed-aware adaptation of vehicle communications networks

Methods, systems, and a computer program product are disclosed. The first method includes obtaining virtual session data in real time, identifying a positional utterance in the virtual session data, and generating a positional insight for the positional utterance. The first method also includes generating a best-practices recommendation based on the positional insight. The second method includes obtaining virtual session data, identifying positional utterances in the virtual session data, and generating positional insights for each of the positional utterances. The second method also includes selecting each of the positional insights having confidence scores above a threshold score and generating best-practices recommendations based on the selected positional insights.

Contextual positioning in virtual space

A method, computer system, and computer program product for utilizing crowdsourcing of images captured by individuals to determine the status of a subject is provided. The embodiment may receive, by a processor associated with a broad beacon, an impulse. The embodiment may also transmit a request to each client device within a preconfigured distance through the broad beacon based on the received impulse. The embodiment may further, in response to an acceptance of the transmitted request by a user associated with a client device, initializing a pairing sequence between the client device and an aimable beacon. The embodiment may also transmit information to identify a subject of photographic capture from the aimable beacon to the client device. The embodiment may further receive an image captured by the user based on the received information.

Object attribution derivation via crowd-sourced optical sensors

According to one embodiment, a method, computer system, and computer program product for mitigating computer fan noise. The embodiment may include retrieving a previously generated baseline profile for a user participating in a real-time e-conference call via a computing device. The embodiment may include identifying real-time hardware and software metrics of the computing device. The embodiment may include calculating a current fan indicative noise (FIN) score for the call based on the baseline profile and the identified metrics. The embodiment may include determining whether the current FIN score is above a threshold value. In response to determining that the FIN score is above a threshold value, the embodiment may include determining whether the computing device is at risk of damage. In response to determining that the computing device is not at risk of damage, the embodiment may include limiting operation of one or more fans of the computing device.

Dynamic mitigation of fan noise during e-conference based on real-time and retroactive data

Growing community of inventors

Cary, NC, United States of America

Martin G Keen