| CPC G06F 16/90332 (2019.01) [G06F 17/18 (2013.01); G06F 18/22 (2023.01); G06N 3/04 (2013.01)] | 20 Claims |
|
1. A method, comprising:
receiving a set of question and answer (Q/A) pairs;
identifying a set of references in the set of Q/A pairs that link pairs of Q/A pairs of the set of Q/A pairs, wherein the set of references is based on at least an identifier of a first Q/A pair of the set of Q/A pairs being included in a second Q/A pair of the set of Q/A pairs;
identifying popular Q/A pairs of the set of Q/A pairs based on the set of references, wherein:
the popular Q/A pairs are referenced by a subset of the set of Q/A pairs;
identifiers of the popular Q/A pairs are included in specific Q/A pairs of the subset of the set of Q/A pairs; and
each respective Q/A pair of the subset of the set of Q/A pairs comprises a respective question of a plurality of questions; and
training a machine learning model through a supervised learning process to predict Q/A pairs of the set of Q/A pairs that are relevant to a given question, wherein the supervised learning process comprises providing a particular question of the plurality of questions to the machine learning model, receiving a prediction from the machine learning model as to whether a popular Q/A pair of the Q/A pairs is relevant to the particular question, and iteratively adjusting parameters of the machine learning model based on comparing the prediction to a label that is based on whether the set of references indicates that the popular Q/A pair is relevant to the particular question.
|