International Business Machines Corporation

Sailion Inc.

Tyler Gross

Brandon M Kobilka

John S Werner

Arkadiy O Tsfasman

Ronald A Felice

A method and system for distributing a compute model and data to process to heterogeneous and distributed compute devices. The compute model and a portion of the data is processed on a benchmark system and the timing used to make a job execution speed estimate for each compute device. Compute devices are selected and assigned data chunks based on the estimate so distributed processing is completed within a predefined time period. The compute model and data chunks can be sent to the respective compute devices using separate processes, such as a payload manager configured to transfer compute jobs to remote devices and a messaging engine configured to transfer data messages, and where the payload manager and messaging engine communicate with corresponding software engines on the compute devices.

Method and system for distributed workload processing

A method, system and computer program product are provided. An analysis module receives a plurality of presentation source materials, including text documents, books, video files, audio files, and presentations. A transcript is generated from audio and video received from a presenter device during a live teaching session. Keywords are extracted from the plurality of presentation source materials. An integrated keyword list is created by integrating the extracted keywords with the generated transcript. Participants in an online meeting are grouped into live group breakout sessions, each of which is independent. Data from each participant is continuously recorded in the breakout session. The correlation between the integrated keyword list and the recorded participant output is periodically analyzed to output a score trendline to determine the level of comprehension by the participants of the presentation materials. The score trendline and the scores for each breakout session are displayed on a presenter dashboard.

Keyword analysis in live group breakout sessions

A method, system and computer program product are provided. For each keyword that is visible on a display device, scanning the content that is stored on a user device, or is accessed from a network connection to identify and extract keywords. Further provided is cross-referencing the extracted keywords with a corpus of scored keywords. Based on the extracted keywords being found in the corpus of scored keywords, expanding and/or abridging any of the extracted keywords based on a score in the corpus of scored keywords prior to displaying the modified content on the display device. wherein the extracted keywords match a keyword in the corpus.

Expanding or abridging content based on user device activity

Aspects receiving, by a processor, observation data about an activity. The processor identifies overlapping content between the observation data and a base electronic document. The order of the overlapping content in the observation data is compared, by the processor, to the order of the overlapping content in the base electronic document. The processor changes an order of content in the base electronic document to create a modified electronic document in response to the order of the overlapping content in the observation data being different than the order of the overlapping content in the base electronic document.

Growing community of inventors

New York, NY, United States of America

Tyler Gross