US 12,141,534 B2
Personalizing automated conversational system based on predicted level of knowledge
Robert John Moore, San Jose, CA (US); Eric Young Liu, Santa Clara, CA (US); Shun Jiang, San Jose, CA (US); Chung-hao Tan, San Jose, CA (US); Lei Huang, Mountain View, CA (US); Guangjie Ren, Belmont, CA (US); and Sungeun An, Lilburn, GA (US)
Assigned to International Business Machines Corporation, Armonk, NY (US)
Filed by International Business Machines Corporation, Armonk, NY (US)
Filed on Dec. 30, 2021, as Appl. No. 17/566,108.
Prior Publication US 2023/0214601 A1, Jul. 6, 2023
Int. Cl. G06F 40/35 (2020.01); G06N 5/02 (2023.01)
CPC G06F 40/35 (2020.01) [G06N 5/02 (2013.01)] 16 Claims
OG exemplary drawing
 
7. A method for personalizing an automated conversational system, the method comprising:
making predictions of a familiarity of a user with concepts needed to understand a standard output utterance based on the familiarity of an aggregate of users and a background knowledge model utilizing a conditional probability table of the concepts and related concepts, wherein the standard output utterance assumes that the concepts are known;
storing the predictions in an individual user model for the user; and
receiving, by the automated conversational system, a conversational response from the user to the output utterance;
updating the individual user model for the user based on the conversational response in relation to each of the concepts and related concepts; and
giving, by the automated conversational system, the standard output utterance to the user when it is predicted that the user is familiar with the concepts, or a nonstandard output utterance when it is it is predicted that the user is unfamiliar with at least one of the concepts.