Act, Inc.

Lu Ou

Yuchi Huang

Michael Yudelson

Shi Pu

Digital learning or tutoring systems as described herein embed, by a trained machine learning knowledge tracing engine, an array for learner interactions X into a static representation ecorresponding to a prior learner interaction xand determine a contextualized interaction representation hbased on this. Digital tutoring systems described herein calculate, by a masked attention layer of the trained machine learning knowledge tracing engine, an attention weight Abased on a time gap between two learner interactions with the system, and can calculate a contextualized interaction representation h, wherein the contextualized interaction representation his proportional to the attention weight A. The systems can provide for display at the GUI a second question item based on the contextualized interaction representation h, the second question item corresponding to a recommended learner recommendation.

Growing community of inventors

Iowa City, IA, United States of America

Lu Ou