International Business Machines Corporation

Kyndryl, Inc.

Shikhar Kwatra

Sarbajit Kumar Rakshit

Jeremy R Fox

Aaron K Baughman

Craig M Trim

Zachary A Silverstein

Adam Lee Griffin

Indervir Singh Banipal

Paul N Krystek

Sushain Pandit

Komminist S Weldemariam

John David Wilson

Joseph N Kozhaya

Raghuveer Prasad Nagar

Nadiya Kochura

Mauro Marzorati

Corville O Allen

Vijay Ekambaram

Andrew Ronald Freed

Hemant Kumar Sivaswamy

Tiberiu (Jim) Suto

Gray Franklin Cannon

Seng Chai Gan

Christopher J Hardee

Scott Edward Schneider

Liam S Harpur

Peeyush Jaiswal

Priyansh Jaiswal

Robert Huntington Grant

Stephen Carl Hammer

Martin G Keen

Cesar Augusto Rodriguez Bravo

James R Kozloski

Maharaj Mukherjee

Venkata Vara Prasad Karri

Michael S Gordon

Vittorio R Castelli

Florian Pinel

Vinod A Valecha

Jeronimo Irazabal

Clement Decrop

Victor Povar

Michael Bender

Diwesh Pandey

Padmanabha Venkatagiri Seshadri

Smitkumar Narotambhai Marvaniya

Spencer Thomas Reynolds

Robert E Loredo

Jun Zhu

Edgar Adolfo Zamora Duran

Hyman David Chantz

Roxana Monge Nunez

Mary E Rudden

Stefan Ravizza

Clifford A Pickover

Gregory J Boss

Paul R Bastide

Gandhi Sivakumar

Maja Vukovic

Qiqing Christine Ouyang

Shailendra Moyal

Vijay Kumar Ananthapur Bache

Petr Novotny

Saravanan Sadacharam

Gary Francis Diamanti

Steven Joroff

Natalie Brooks Powell

Michael Man Behrendt

Srinivas Babu Tummalapenta

Lisa Seacat DeLuca

Jonathan D Dunne

Al Chakra

Jeremy A Greenberger

Kuntal Dey

Trudy L Hewitt

John Edward Petri

Jonathan Lenchner

Kushal S Patel

Manish Anand Bhide

Nitin Gaur

Yu Long Cao

Charles Evan Beller

Hernan A Cunico

Todd Russell Whitman

Kimberly Greene Starks

Dulce Beatriz Ponceleon

Divyesh Jadav

Michael John Spisak

Russell Patrick Bobbitt

Prasenjit Dey

Jacob Ryan Jepperson

Arun Joseph

Munish Goyal

Franz Friedrich Liebinger Portela

Thomas J Fleischman

Manish Mahesh Modh

Anil Bindu Lingambudi

David Alonso Campos Batista

Christian Compton

Jagadesh Ramaswamy Hulugundi

By analyzing a natural language content concurrently with a presentation of the natural language content, a first language of the natural language content is detected. By analyzing the natural language content concurrently with the presentation of the natural language content, it is detected that a subset of the natural language content is expressed in a second language, wherein the second language is different from the first language, wherein a set of known languages comprises the first language, wherein the set of known languages excludes the second language. From the subset of the natural language content, a modified subset expressed in the first language is generated. The modified subset is inserted into the natural language content.

Contextual and personalized real time content modification for language assistance

A method, computer system, and a computer program product for dynamic speech modulation is provided. The present invention may include transmitting a first response to a received command. The present invention may include determining the first response is not understood by a user. The present invention may include transmitting a second response to the received command.

Dynamic virtual assistant speech modulation

A method, a structure, and a computer system for playback optimization. The exemplary embodiments may include transcribing an audio stream at normal and at high playback speed, as well as determining whether portions of the audio stream are unintelligible at the high playback speed. The exemplary embodiments may further include reducing a speed of the high playback speed for portions determined unintelligible, and transcribing the audio stream with the unintelligible portions played at the reduced high playback speed. The exemplary embodiments may further include determining whether the unintelligible portions are still unintelligible at the reduced high playback speed and, if not, identifying the reduced high playback speed as an optimal playback speed of the unintelligible portions. The exemplary embodiments may additionally include, in response to receiving a request to play the audio stream at the high playback speed, playing the unintelligible portions at the optimal playback speed.

Audio playback and captioning

Embodiments are directed to techniques for secure network connectivity. The techniques including a system having a credential server storing a Personal-Public (PP) Service Set. Identifier (SSID) profile configured according to registration information provided from a personal computing device. The system further including a Wireless Access Point (WAP) communicatively coupled to the credential server and configured to implement a PP SSID connection using the PP SSID profile to create a single-device, single-use, password-protected, unadvertised, and encrypted networking channel between the personal computing device and the Internet.

Establishing a personal-public service set identifier connection between a personal device and the internet

A method, system, and computer program product for occupant-based elevator actions are provided. The method identifies a set of subjects approaching a set of elevators to generate a set of identities for the set of subjects. A set of initial priority statuses are generated for the set of subjects. Based on the set of identities and the set of initial priority statuses, an elevator dispatch solution is determined. The method updates at least a portion of the initial priority statuses to generate a set of subsequent priority statuses in response to a subset of subjects entering at least one elevator. The method determines an isolation response for a first subject of the subset of subjects and modifies the elevator dispatch solution based on the isolation response to generate an isolation dispatch solution. The at least one elevator executes the isolation dispatch solution.

Occupant-based intelligent elevator actions

Embodiments receive a data metrics input which corresponds with a microservice issue, determine a final outcome by multiplying each metric of the data metrics input by a weight, determine a link output based on the final outcome, determine a cost function based on the link output, evaluate that a cost output of the cost function has a minimized error, output a data metrics output based on the cost output of the cost function having the minimized error, train at least one machine learning (ML) model using the data metrics output, receive a new data metrics input which corresponds with another microservice issue, and provide a recommendation corresponding to the new data metrics input using the trained at least one ML model.

Alert management

A system includes: a platform; a payload extending from a platform; an adjustable tether connecting the payload to the platform; and a sail extending from the payload. The system further includes a computer program that is executable to relocate the platform to the area of interest based on a threshold based decision which may include providing a tether and sail configuration.

Relocation based coverage area enhancement system

A computer-implemented method, a computer program product for predictive device maintenance, and system for a plurality of Internet of Things (IoT) devices. One embodiment may comprise generating a risk score as a weighted measure of input data about an Internet of Things (IoT) device and a frequency of failure of the IoT device, determining an optimal time to trigger a predictive notification pertaining to the IoT device using the risk score, and at the determined optimal time, issuing the predictive notification. The risk score in some embodiments may indicate an estimate of loss of function of the IoT device.

Predictive device maintenance

The exemplary embodiments disclose a method, a computer program product, and a computer system for determining the context of media. The exemplary embodiments may include a user consuming media, collecting data of the media, extracting one or more features from the collected data, and determining a media context based on the extracted one or more features and one or more models.

Displaying contextual information of media

A computer-implemented method includes: presenting, by a computing device, a virtual event user interface to an attendee of a virtual event; obtaining, by the computing device, data about actions performed by the attendee within the virtual event; creating, by the computing device, a tensile sphere kernel that is specific to the attendee using the obtained data; creating, by the computing device, a mixed tensile sphere kernel using the tensile sphere kernel that is specific to the attendee and another tensile sphere kernel of another attendee; determining, by the computing device, an event recommendation of the virtual event using the mixed tensile sphere kernel; and presenting, by the computing device, the event recommendation to the attendee by changing the virtual event user interface to show the event recommendation.

Event experience representation using tensile sphere mixing and merging

One or more computer processors derive a base corpus by capturing time series haptic data from an artisan performing an artisanal skill comprising a plurality of artisanal actions, wherein each artisanal action in the plurality of artisanal actions is associated with a time interval. The one or more computer processors train a multi-agent reinforcement learning (MARL) model utilizing the derived base corpus, wherein the MARL model outputs a vector representing one or more predicted artisanal actions required to complete the artisanal skill. The one or more computer processors generate a training avatar utilizing a trained generated adversarial network fed with one or more user parameters identified from a user requesting guidance for the artisanal skill and the output vector of the trained MARL model. The one or more computer processors guide the user with the generated training avatar in an execution of the artisanal skill.

Artisan learning system

Text is received from a user describing item(s) for migration to a computing environment with cloud feature(s), resulting in item description(s), the text including unstructured text that are processed separately. Text mining is performed on the unstructured text to extract item feature(s). For each listing a portion of the unstructured text is extracted, resulting in an extracted text portion for each listing from which an entity is identified. Each entity or item feature is mapped to cloud feature(s) available from solution(s) with cloud feature(s). Based on the cloud feature(s), recommendation(s) are made to the user regarding cloud feature(s) of the solution(s) for optional consideration by the user. Explanation(s) for the recommended cloud feature(s) from explainability model(s) may be provided to the user.

Computing environment provisioning

A computer captures a voice of a user. The computer determines a frequency spectrum and a voice pattern of the voice. The computer identifies one or more topics of the voice by transcribing the voice by a natural language processing. The computer identifies the user based on matching the frequency spectrum of the voice to the frequency spectrum of the conversation and the pattern of the voice to the pattern of the conversation when a conversation is intercepted and determines a trust score based on comparing the one or more topics to the one or more topics extracted from the conversation.

AI based system and method for corners of trust for a caller

A method, computer program product, and system include a processor(s) that map a physical environment by utilizing one or more image capture devices to scan aspects of the physical environment. The mapping identifies contamination levels and features associated with objects in the environment. The processor(s) utilizes unsupervised learning and supervised learning to identify activities engaged in by a user in the environment. The processor(s) determines that a trigger event has occurred. The processor(s) identify an activity engaged in by the user and determine if a user interface utilized by the program code to display results is visible to the user. If the processor(s) determines that the interface is not visible, the processor(s) selects an alert mechanism to alert the user to the trigger event and alerts the user to the trigger event with the selected alert mechanism.

Sanitized surface monitoring and smart user alerts

A route from a first physical location to a second physical location is divided into a set of segments using a route optimization engine. Using a user response analysis model, a response to a physical environment associated with a segment in the set of segments is scored, the scoring resulting in a score. Using a content generation model and the score, the physical environment is augmented, the augmenting combining the physical environment and a generated environment.

Vehicle based external environment augmentation for operator alertness

Growing community of inventors

San Jose, CA, United States of America

Shikhar Kwatra