International Business Machines Corporation

Kyndryl, Inc.

Globalfoundries Inc.

Gandhi Sivakumar

Sarvesh S Patel

Kushal S Patel

Sandeep R Patil

Craig M Trim

Faried Abrahams

Matthew B Trevathan

Riyazahamad Moulasab Shiraguppi

Sri Ramanathan

Amol Ashok Dhondse

Anand Pikle

Luke Peter Macura

Geetha Adinarayan

Kerard R Hogg

Rashida A Hodge

Kimberly Greene Starks

Sreekanth Ramakrishna Iyer

Blaine H Dolph

Abhinay Ravinder Nagpal

Garfield Winston Vaughn

Raman Harishankar

Lennox Epstein Thomas

Vijayaganesh Subramanian

Sasikanth Eda

Michael Edward Alexander

Vasanthi M Gopal

Martin G Keen

Shaw-Ben Shi

Kerrie Lamont Holley

Bhushan Pradip Jain

Meng Hong Tsai

Krishnan K Ramachandran

Lynn Kwok

Lakisha R S Hall

Victor Povar

Laura Irina Rusu

Matthew Adam Terry

Abhishek Jain

John Gerard Musial

Nanjangud C Narendra

Miku K Jha

Sandeep Patil Ramesh

Jigneshkumar K Karia

Sarbajit Kumar Rakshit

Vijay Ekambaram

Ahamed Jalaldeen

Ram Viswanathan

Lalit Agarwalla

Siddharth N Purohit

Shankar S Kalyana

Michael Bender

Deepak R Ghuge

Anil Manohar Omanwar

Rizwan Dudekula

Maharaj Mukherjee

Vinod A Valecha

Rodolfo Lopez

Piyush Sarwal

Aaron K Baughman

Shikhar Kwatra

Louie Arthur Dickens

Hemant Kumar Sivaswamy

Padmanabha Venkatagiri Seshadri

Ali P Arsanjani

Prashant Sodhiya

Shah M R Islam

Karthikeyan Ponnalagu

Andrew John Bernoth

Guy Sharon

John Michael Ganci, Jr

James Edward Bostick

Dirk Pfeiffer

Hernan A Cunico

Timothy Michael Lynar

John Michael Wagner

Prasenjit Sarkar

Vibha Singhal Sinha

Michael John Brady

Duane Mark Baldwin

Seng Chai Gan

Kalapriya Kannan

Ashok Pon Kumar Sree Prakash

Jianbin Tang

Smitkumar Narotambhai Marvaniya

Chitra Dorai

Ashish Mungi

Daniel Joseph Martin

Ramamohan Chennamsetty

Gaurav Chhaunker

Wesley McMillan Devine

Suraj Pandey

Yuhong Yin

Ronald Ambrosio

Susan L Sylvia

Salil Ahuja

Anbumunee Ponniah

Rama K Akkiraju

Naeem Altaf

Shweta Shandilya

Sreenivasa Rao Pamidala

A computer-implemented method, according to one embodiment, includes receiving, from a plurality of initiators, a plurality of reservation requests for logical unit numbers (LUNs) of a storage target. Exclusive type network paths between the initiators and the LUNs requested in the reservation requests are caused to be added to a restricted path list. The method further includes determining the initiators of the plurality of initiators, that have access to at least one of the exclusive type network paths in the restricted path list. Session logout commands are caused to be sent to the determined initiators. The session logout commands instruct the determined initiators to thereafter re-log in to sessions that are logged out of as a result the determined initiators adhering to the session logout commands. The method further includes allocating a first session that a first of the determined initiators re-logs in to, to a first fiber.

Allocating sessions associated with exclusive access to different fibers of a storage target

Computer implemented method, systems, and computer program products include program code executing on a processor(s) mapping, based on analyzing two or more nodes over which tasks comprising the workflow are distributed, each node to one or more parameters utilized to evaluate efficacy of the workflow. The processor(s) determines, based on the mapping, costs associated with each node and costs associated with changes to each node. The processor(s) identifies tasks in the workflow that can be changed to counter disruptions impacting at least one parameter of the one or more parameters utilized to evaluate the efficacy of the workflow.

Determining dynamic workflows

A computer-implemented method, according to one embodiment, includes generating a temporal mapping of positions of a first satellite with respect to predetermined portions of land of Earth and predetermined bodies of water of the Earth. The method further includes determining, based on the temporal mapping, a first job for the first satellite to offload to a first target device during a first period of time that a footprint coverage region of the first satellite is within a predetermined proximity to a first of the bodies of water. In response to a determination that the footprint coverage region of the first satellite is within the predetermined proximity to the first body of water, the first satellite is caused to offload the first job to the first target device.

Workload management based on a proximity to bodies of water and land

An approach is provided in which the approach stores, in a cached recycle bin, a set of sensor data that is sent from a sensor at a transmit frequency. The approach samples at least a portion of the set of sensor data from the cached recycle bin based on a sampling frequency and training a machine learning model using the sampled data. In response to detecting that a performance of the machine learning model falls below a threshold during the training, the approach adjusts the sampling frequency and re-sampling at least a portion of the sensor data based on the adjusted sampling frequency. The approach instructs the sensor to adjust the transmit frequency in response to determining that the performance of the machine learning model reaches the threshold using the re-sampled data.

Auto sampling in internet-of-things analytics system via cached recycle BINS753634

In an approach for amplifying a mission critical workload to a low Earth orbit (LEO) satellite using a booster drone, responsive to receiving a first request to amplify a mission critical workload to a LEO satellite, a processor initiates a targeted service instance. A processor obtains a level of mission criticality of the first request by mapping the first request against a registry of applications and a respective level of mission criticality of the applications. A processor selects a booster drone from a drone delivery station. A processor determines a first geo-location from where a satellite data communication needs to be initiated. A processor determines a second geo-location of the LEO satellite to where the satellite data communication needs to be pushed. A processor generates one or more signal strength requirements. A processor amplifies the mission critical workload according to the one or more generated signal strength requirements.

Mission critical data delivery booster drones for satellite data centers

A first version of a model specified by a model execution request is executed, producing a first execution result. A second version of the model is selected according to an input data attribute specified by the model execution request. The second version of the model is executed, producing a first execution result. Using a natural language processing engine, responsive to the first execution result and the second execution result differing by more than a threshold amount, a natural language explanation of a difference between the first execution result and the second execution result is constructed.

Version based model result explainability

A telecom network monitoring method and associated computer program product and hardware device. Location and activation sight information is collected via a plurality of image retrieval devices associated with a plurality of hardware devices connected to a telecom network. Object elevation, movement, and abstraction attributes of objects within images retrieved from the plurality of image retrieval devices are collected from a metadata database. Based on the object elevation, movement, and abstraction attributes of objects within the images, obstruction characteristics associated with obstruction objects of the objects located within a coverage area of the telecom network are detected. The obstruction characteristics are mapped with login and disturbance patterns of the telecom network. Based on results of the mapping, an alternative transmission location within the telecom network is determined. The alternative transmission location includes improved transmissions characteristics with respect to the transmission location.

Telecommunication network monitoring

An approach is provided in which the approach detects a set of personal information data corresponding to a set of users in a set of training data. The approach transforms the set of training data into a set of semantically equivalent training data by replacing the set of personal information with a set of semantic equivalent data. The approach then trains a machine learning model using the set of semantically equivalent training data.

Data de-identification using semantic equivalence for machine learning

Condition-based, selective workload reduction through at least one port of a network device is provided. The process includes determining, by a network device of a computing environment, that the network device has a defined condition, and obtaining, by the network device, classifications of applications using the network device, where the classifications include multiple different application classifications. Further, the process includes reducing, by the network device, workload through at least one port of the network device based on determining that the network device has the defined condition. The reducing includes reducing workload through the at least one port of the network device of an application of a particular application classification of the multiple different application classifications, without reducing workload through a selected port of the network device of another application of a different application classification of the multiple different application classifications.

Dynamic, condition-based network device continuity optimization

A processor may receive a route request from a user. The processor may receive data associated with predicted routes of one or more nearby vehicles. The processor may select a recipient vehicle from the one or more nearby vehicles, where the recipient vehicle is selected based on recipient selection criteria. The processor may determine one or more driving change requests for the recipient vehicle. The processor may send the one or more driving change requests and a proposed token to the recipient vehicle. The processor may provide a token to the recipient vehicle in response to the recipient vehicle implementing the driving change requested.

Cooperative operation of vehicles

A method includes collecting, by one or more processors of a computer system, digestive capabilities for Input Output Queues (IOQs) of infrastructure components in a hybrid cloud infrastructure, and allocating, by the one or more processors of the computer system, nonvolatile memory express (NVMe) storage cloud resources for the hybrid cloud infrastructure based on the collected digestive capabilities for IOQs of the infrastructure components.

Adaptive hybrid cloud resource management

A method, computer program product, and computer system for using agents at a data lake to assist training, testing, and deploying a model for predicting one or more outputs from specified input to the model, using agents at the data lake. The agents identify at the data lake: hardware resources, a first portion of model input data for training and testing the model, a training language, and a first software resource. A first execution of the first software resource is triggered to split the first portion of the model input data into training input data and testing input data. A first portion of the hardware resources is identified for training and testing the model. A second software resource stored at the data lake is identified for optimizing the model in accordance with an optimization algorithm. Training the model at the data lake is triggered.

Agent assisted model development

Provided is a method, a computer program product, and a system for associating mathematical functions to numerical text in a natural language sample. The method includes inputting a natural language sample from a text dataset and identifying a numerical text within the natural language sample. The method further includes displaying a mathematical function corresponding to the numerical text to be selected. The mathematical function can be selected via graphical user interface displayed on a computing device. The method also includes receiving and inserting the mathematical function as a feature into a feature vector of the natural language sample and selecting an output label for the natural language sample. The output label relates to the mathematical function selected for the numerical text. The method further includes exporting the natural language sample into a labeled dataset which can be used to train a machine learning model.

Mathematical function defined natural language annotation

A method, apparatus and computer program for detecting natural language (NL) bias by a conversational system is described. Embodiments of the invention determine an NL bias in a set of training questions used to train a machine learning model used by the conversational system to select a user intent. Other embodiments of the invention determine an NL bias in a user question received by the conversation system as compared to the set of training questions. The NL bias causes the machine learning to preferentially associate user queries to a user intent. In respective embodiments, the system takes a corrective action to adjust the NL bias of the training questions or the user question.

Natural language bias detection in conversational system environments

Methods, computer program products, and systems are presented. The methods include, for instance: obtaining prediction data that are indicative of media use behaviors of a user; and predicting, in dependence on the prediction data, a pattern of the media use behaviors of the user.

Dynamic media use control service

Growing community of inventors

Bentleigh, Australia

Gandhi Sivakumar