CPC G06F 40/30 (2020.01) | 20 Claims |
1. A computer-implemented method comprising:
a) retrieving a plurality of data sets from a plurality of electronically controllable equipment associated with an automated environment, wherein the plurality of data sets comprises a plurality of metadata;
b) creating a training set comprising (i) a plurality of data sets from a plurality of electronically controllable equipment associated with a second automated environment other than said automated environment, and (ii) a label that indicates a semantic arrangement associated with each of the plurality of electronically controllable equipment associated with the second automated environment;
c) training an ensembling machine learning model with the training set;
d) selecting one or more base classifiers from the plurality of base classifiers based at least in part on a similarity level between metadata associated with the one or more base classifiers and the plurality of metadata associated with the plurality of data sets;
e) ensembling the one or more base classifiers with the ensembling machine learning model to assign one or more weights to the one or more base classifiers based at least in part on the similarity level;
f) applying the ensembled machine learning model to the automated environment to generate a semantic map indicative of semantic arrangement of the plurality of electronically controllable equipment associated with the automated environment; and
g) displaying the semantic map.
|