US 12,169,697 B2
Methods and systems for expert-novice guidance
Emily Sumner, Berkeley, CA (US); Nikos Arechiga, San Mateo, CA (US); Yue Weng, San Mateo, CA (US); Shabnam Hakimi, Chapel Hill, NC (US); and Jonathan A. DeCastro, Arlington, MA (US)
Assigned to Toyota Research Institute, Inc., Los Altos, CA (US)
Filed by Toyota Research Institute, Inc., Los Altos, CA (US)
Filed on Sep. 14, 2021, as Appl. No. 17/474,652.
Prior Publication US 2023/0083838 A1, Mar. 16, 2023
Int. Cl. G06F 17/00 (2019.01); G06F 16/332 (2019.01); G06F 40/284 (2020.01); G06F 40/40 (2020.01); G06N 5/04 (2023.01); G06F 16/33 (2019.01)
CPC G06F 40/40 (2020.01) [G06F 16/3322 (2019.01); G06F 40/284 (2020.01); G06N 5/04 (2013.01); G06F 16/33 (2019.01)] 17 Claims
OG exemplary drawing
 
1. A system comprises:
a processor;
a memory module communicatively coupled to the processor;
a natural language processing (NLP) module communicatively coupled to the processor;
a set of machine-readable instructions stored in the memory module that, when executed by the processor, direct the processor to perform operations comprising:
receiving a text data;
receiving a training text data for training one or more models of the NLP module;
generating, with a novice model of the NLP module, a novice suggestion based on the text data and the training text data, the novice suggestion comprising a first idea related to the text data;
generating, with an expert model of the NLP module, an expert suggestion based on the text data and the training text data, the expert suggestion comprising a second idea elaborating on the text data, the second idea being different from the first idea, wherein generating the expert suggestion comprises:
determining, with the expert model of the NLP module, a topic of the text data based on a keyword of the text data;
identifying, with the expert model of the NLP module, a reference document based on the topic; and
extracting, with the expert model of the NLP module, reference text data from the reference document based on the keyword to generate the expert suggestion; and
outputting the novice suggestion and/or the expert suggestion.