US 12,461,978 B2
Method and system for literacy adaptive content personalization
Dan Pelleg, Haifa (IL); Ran Wolff, Geva-Carmel (IL); and Avihai Mejer, Atlit (IL)
Assigned to YAHOO ASSETS LLC, Dulles, VA (US)
Filed by YAHOO ASSETS LLC, Dulles, VA (US)
Filed on Dec. 5, 2022, as Appl. No. 18/061,625.
Application 18/061,625 is a continuation of application No. 16/726,548, filed on Dec. 24, 2019, granted, now 11,520,840.
Prior Publication US 2023/0093836 A1, Mar. 30, 2023
This patent is subject to a terminal disclaimer.
Int. Cl. G06F 16/9535 (2019.01); G06F 16/21 (2019.01); G06F 16/9538 (2019.01)
CPC G06F 16/9535 (2019.01) [G06F 16/219 (2019.01); G06F 16/9538 (2019.01)] 17 Claims
OG exemplary drawing
 
1. A method for content personalization, the method comprising:
retrieving, by a content modification engine, content items previously consumed by a first user;
retrieving, from a database based on metadata of a request from the first user, a first literacy score of the first user;
determining a social group including the first user and other users, wherein the other users have also consumed the content items;
refining, based on literacy scores of the other users and an average literacy score of content items composed by the first user, the first literacy score of the first user, wherein the average literacy score is determined based on a readability score of each of the content items composed by the first user;
modifying, in accordance with a model and based on the refined first literacy score of the first user, a first content item identified based on a request from the first user to generate multiple versions of the first content item, wherein at least some of text of each of the multiple versions is replaced by replacement text;
verifying each of the multiple versions of the first content item based on a difference between the refined first literacy score of the first user and a literacy score of the version; and
providing, in response to the request, at least one of the verified versions of the first content item to the first user by using a graphical model to embed a pop-up box including a description of the replacement text.