International Business Machines Corporation

Kyndryl, Inc.

Clea Anne Zolotow

John Valentine Delaney

Anthony M Hunt

Maeve M O'Reilly

Tedrick Neal Northway

Andrew Paul Barnes

Simon J Brady

Laxmikantha Sai Nanduru

Florian Graf

Barry Hollywood

Gavin Charles O'Reilly

Daniel P Toulan

Sean Thomas Fornash

Jonas E Bryllert

Claus Schroeder-Hansen

Mihai Criveti

Jørgen Egbert Floes

Niamh Phelan

Claus Schrøder-Hansen

Petra Kopp

David O'Grady

Randy Scott Johnson

Mickey Iqbal

Marci Devorah Formato

Susheel Gooly

Pedro Soares

Julian Kopp

Maeve O'Reilly

Ana Maria Bezerra Maimoni

Thomas Spatzier

Alice-Maria Marascu

Gerhard A Widmayer

Kim Poh Wong

John F Graham

Anil Kumar Narigapalli

Francesco Mariani

Ruediger Schulze

Niambh Scullion

John Robert Davis

Saritha Route

Valerie Lampkin

Selcuk Nedim Oezmen

Russell G Conner

Johan Van Kessel

Gerhard H Widmayer

Jack Louis Cherkas

Richard M Cocchiara

Philippe H V M Spaas

Alexander J Harvilchuck

Kenneth Weber

Dmitri Lerko

Li Feng Zhang

Craig M Trim

Thomas W Bish

Bernhard Julius Klingenberg

Stephen Robert Guendert

Eric P Bouillet

Pritpal Arora

Teodora Sandra Buda

Dennis Anthony Perpetua, Jr

Calvin D Lawrence

Steven Joseph Kurtz

H William Rinckel

John Leonard

Walter E Schmidt

Venkateswarlu Basyam

Srinivasa M Raghavan

Arvind Viswanathan

Rudolph C Baron

Nikhilkumar V Shah

Zheng Xie

Ulrike Vauth

Richard J Baird

Oliver Raff

Christopher Peter Baker

Ellis Edward Bishop

Walter F Schmidt

Thomas Brackhahn

James S Bennett

Ricky L Montagna

Pawel J Wieczorek

Jan B Lillelund

Brian Rasmussen

Tomasz Gola

James Michael Kenley

Robert L Boyce, Jr

James Taggart

Jeanette Louise Livings

Shankar Balasubramanian

Arvid Van Essche

Dennis M Carden

Vladimir V Danilevich

Hasibe Göçülü

Shane Dalton

Patrick Arthur Fagan

Alan P Murphy

Anastasios Xouzafeiris

Leszek Adamiak

Sean T Fomash

A method includes training a recurrent neural network by monitoring data in a memory of a first server as the first server executes jobs and by determining an amount of computing resources used by the first server while executing the jobs and applying the recurrent neural network to data in the memory to predict an amount of computing resources that the first server will use when executing a first future job. The method also includes, in response to determining that execution of the first future job did not meet a performance criterion, making a change to the first server. The method further includes further training the recurrent neural network using a reinforcement learning technique, applying the recurrent neural network to determine that the change should be made to a second server, and in response, making the change to the second server before the second server executes a second future job.

Machine learning and optimization techniques for job scheduling

Computer systems that use artificial intelligence to predict strategies, scenarios and or game plans for sports games that are already in progress. In some embodiments a feedback loop is used so that the artificial intelligence takes into account events occurring in and/or around the game as they occur to provide updated predictions.

Artificial intelligence assisted sports strategy predictor

Application transition and transformation is provided by observing and analyzing execution of a monolithic application to provide properties of the data communication of the monolithic application, identifying, by an artificial intelligence engine, atomic application element(s) having logical functional block(s) that function independent of other atomic application element, determining, by the artificial intelligence engine, candidate atomic application element(s) for migrating out of the monolithic application and refactoring, based on automated testing and validation, refactoring at least one candidate atomic application element into a respective at least one refactored element, where the refactoring selects a platform technology for the refactored element and implements functionality of the candidate atomic application element as the refactored element of the selected platform technology, and providing the at least one refactored element to system(s) for execution thereon.

Application transition and transformation

A method, computer program product, and system includes a processor(s) utilizing the image capture device to track eye movements of a user interacting with a display communicatively coupled to the one or more processors, the image capture device continuously collecting image data. The processor(s) determines, based on analyzing the collected image data, a probability of whether a user may be experiencing a vision-related issue. Based on the probability being within a given pre-determined range, the processor(s) identifies the vision-related issue experienced by the user. The processor(s) generates, based on the vision-related issue, a two dimensional visual exercise to address the vision-related issue for performance by the user. The processor(s) deploys a graphical user interface to the display, where the graphical user interface comprises the visual exercise. The processor(s) provides the visual exercise to the user via the graphical user interface.

Vision improvement utilizing computer displays

Workload distribution is automatically optimized. Cost penalty amounts imposed on executing a database operation transaction by current and alternative processing pathway options are determined as a function of execution response times that exceed a service level agreement time limit. Respective computer processing hardware costs are determined for executing the database operation transaction via each of the current and alternative processing pathway options. Respective licensing costs are determined for migrating execution of the database operation transaction to each of the alternative processing pathway options. Accordingly, the current or alternative middleware option that has a lowest total combined cost of licensing costs, computer processing hardware costs and service level agreement penalty costs is chosen as the path for execution of the database operation transaction.

Workload distribution optimizer

In an approach for a smart reading assistant that helps users learn to read a new language, a processor detects a language of a digital book opening by a user on a computing device. A processor identifies a user reading capability level for the language of the digital book from a user profile for the user. A processor inputs at least one in context meaning of potential unknown words based on the user reading capability level. A processor detects a user action by the user on the computing device. A processor updates the user reading capability level based on the user action. A processor identifies, using collocation extraction, related words to a word involved in the user action. A processor inputs at least one in context meaning of at least one of the related words.

Smart reading assistant

Methods and systems include managing bandwidth in Fibre Channel over Internet Protocol (FCIP) communication channels. A method includes monitoring traffic demand at an FCIP communication channel and, in response to an anticipated period of throughput demand on the FCIP communication channel, reallocating physical throughput bandwidth of the FCIP communication channel by configuring bandwidth of one or more tunnels of the FCIP communication channel.

Managing bandwith in fibre channel over internet protocol communication channels

Computer implemented systems and methods for migrating datacenter data include providing a quantity of carriers having a data storage capacity, receiving, by the quantity of carriers, a quantity of data stored in a first data storage system having a first location and including erasure coded data blocks. The quantity of carriers migrates to a second data storage system having a second location; and transmits the quantity of data to the second data storage system.

Datacenter relocation utilizing storage carriers and erasure coding

Application consistent dataset recovery using a cognitive control plane is provided. Sequence and timestamp of snapshots of volumes in a consistency group across heterogenous storage components corresponding to an application are recorded to facilitate operational recovery of application consistent datasets for the application. The cognitive control plane establishes a framework to manage, monitor, analyze, and update the consistency group and metadata to facilitate application consistent data recovery. A set of snapshots needed for the operational recovery of the application consistent datasets for the application is identified by mapping the sequence and timestamp of the snapshots of the volumes in the consistency group across the heterogenous storage components corresponding to the application in response to the computer determining that the operational recovery of the application consistent datasets for the application has been requested. The operational recovery of the application consistent datasets for the application is performed using the set of snapshots.

Cognitive control plane for application consistent datasets

Data migrations are not able to be identified or traced through a switched network to their originating hub, because the corresponding TCP/IP data stream goes through a plurality of optimized differential switches and the originating IP in the packet header gets replaced at each switch. The present invention provides a mechanism to introduce a lag or a jitter into the IP to label the migrated data. The labeled data are able to be traced and identified through multiple managed hubs and/or switches.

Managing data traffic according to data stream analysis

A method includes: determining, by a computer device, affinities between components in a networked computer system; determining, by the computer device, a risk level of each of the components; determining, by the computer device, a risk level of the networked computer system; detecting, by the computer device, a threat in the networked computer system; determining, by the computer device, an action based on the threat, the risk level of ones of the components affected by the threat, and the risk level of the system; and reconfiguring, by the computer device, the networked computer system based on the determined action.

Network shutdown for cyber security

An approach for determining a veracity of a reported event is provided. In an embodiment, a set of predictor variables is retrieved from a selected use case. Each of these predictor values is a condition that indicates the veracity of the reported event. In addition, a set of hidden predictor variables is generated from a set of unstructured documents related to the reported event using a hidden Markov model that is based on the predictor variables using a cognitive system. These hidden predictor variables are combined with the set of predictor variables to generate a set of updated predictor variables. These updated predictor variables are used by the cognitive system to return a determination of the veracity of the reported event.

Cognitive systematic review (CSR) for smarter cognitive solutions

A computer directs activity within a computer storage subsystem. The computer identifies a computer operating environment including a computer, and a storage subsystem connected to a group of storage devices. The compute receives metadata representing current and historic performance metrics of said computer operating environment. The computer identifies a first device associated with a first behavior profile governed by a power law distribution, and a second device associated with a second behavior profile governed by a normal distribution. The computer trains Machine Learning (ML) models based on the behavior profiles. The computer establishes Device Performance Rules based on the ML models. The computer forecasts time-based storage system requirements based, at least in part on the Device Performance Rules. The computer prefetches data to a cache component based, at least in part on said forecasted system requirements, in accordance with a time reference available to said computer.

Analytics-driven direction for computer storage subsystem device behavior

A method for retrieving a plurality of electronic images that includes obtaining images from a plurality of electronic storage sites. A first set of images containing a main protagonist is selected from the plurality of electronic images. An intent based image selection is performed from the first set of images. The intent based image selection includes tagging the first set of images with word tags identifying content of the images, creating a word cloud from the word tags, plotting the top word tags from the word cloud in a Venn diagram, and extracting images from the overlapping are of the Venn diagram.

Artificial intelligence driven image retrieval

A method, computer system, and computer program product for optimizing a number of robots for operation of a process at a target system. The method may include providing a plurality of available robots to carry out tasks in the process at the target system. The method may monitor the target system by carrying out the process or part of the process with a varying number of robots to determine the processor utilization whilst the robots are executing a varying number of tasks. The method may balance process constraints of the execution of the process with physical system constraints of the target system by measuring a relationship between a number of tasks at a transactional level and the processor utilization. The method may output the optimized number of robots to be allocated for the process or part of the process.

Robotic management for optimizing a number of robots

Growing community of inventors

Key West, FL, United States of America

Clea Anne Zolotow