Information processing method, information processing device, and computer system

Abstract

Provided is an information processing method, an information processing device, and a computer system that improve the accuracy of a machine learning task. The information processing method of the present embodiment includes: calculating a first feature amount of a first domain of query data (S22); calculating a plurality of first similarities between the first feature amount and each of a plurality of second feature amounts within a first feature amount space of the first domain (S23); based on the first similarities, obtaining a plurality of third feature amounts of a second domain that are associated with one or more feature amounts selected from the plurality of second feature amounts from a second feature amount space of the second domain (S25); calculating one or more fourth feature amounts of the second domain for a plurality of selection items related to the query data (S27); calculating a plurality of second similarities between the third and fourth feature amounts (S28); and selecting an answer to the query data from a plurality of answer candidates corresponding to the plurality of third feature amounts based on the second similarities (S29).

Images