CPC G06N 5/022 (2013.01) [G06F 18/2148 (2023.01); G06F 18/217 (2023.01); G06N 20/00 (2019.01); G06V 10/7747 (2022.01); G06V 10/776 (2022.01)] | 9 Claims |
1. A computer-implemented entity learning recognition training method, comprising:
in the training phase:
selecting a structural element from a plurality of structural elements;
for an entity comprising a language structure in a training database:
associating the structural element with an attribute in an aspect of the entity;
generating an augmented entity based on a combination of the structural element and the attribute; and
adding the augmented entity to the training database which creates an augmented database; and
training a model based on a combination of the original entity and the augmented entity in the augmented database.
|