US 12,248,757 B2
Transforming content to support neurodivergent comprehension of the content
Natalia Russi-Vigoya, Round Rock, TX (US); Jennifer M. Hatfield, San Francisco, CA (US); Jill S. Dhillon, Jupiter, FL (US); Juhi Bharat, Highland Park, NJ (US); and Joshua Totte, Santa Monica, CA (US)
Assigned to INTERNATIONAL BUSINESS MACHINES CORPORATION, Armonk, NY (US)
Filed by INTERNATIONAL BUSINESS MACHINES CORPORATION, Armonk, NY (US)
Filed on Mar. 16, 2023, as Appl. No. 18/184,852.
Prior Publication US 2024/0311583 A1, Sep. 19, 2024
Int. Cl. G06F 40/166 (2020.01); G06F 40/42 (2020.01)
CPC G06F 40/42 (2020.01) [G06F 40/166 (2020.01)] 20 Claims
OG exemplary drawing
 
1. A computer-based method of supporting neurodivergent comprehension of content comprising:
retrieving responses to a questionnaire, the retrieved responses including a series of reading preferences and behaviors associated with a registered user;
receiving an activation command from the registered user;
automatically identifying, within displayed content, predicted difficult comprehension areas using a pre-trained natural language processing model based on the series of reading preferences and behaviors associated with the registered user;
marking a textual element associated with the predicted difficult comprehension areas that may be transformed to improve comprehensibility of the predicted difficult comprehension areas for the registered user;
detecting user interaction with the marked textual element;
in response to detecting user interaction with the marked textual element, transforming the marked textual element to address the predicted difficult comprehension areas based on the series of reading preferences and behaviors associated with the registered user;
in response to transforming the marked textual element, providing transformed content and an associated feedback questionnaire to the registered user; and
gathering feedback from the registered user in response to one or more prompts included in the associated feedback questionnaire, wherein the one or more prompts request a numerical rating from the registered user, and are related to the provided transformed content and features of a specific transformation applied to the marked textual element, storing the feedback, wherein the pre-trained natural language processing model is retrained based on the stored feedback to identify and transform additional difficult comprehension areas specific to the registered user.