| CPC G06F 16/353 (2019.01) [G06F 17/18 (2013.01); G06N 20/00 (2019.01)] | 19 Claims |

|
1. A method of identifying an objective from documents, the method comprising:
determining a correlation of each of a plurality of keywords extracted from a set of documents with respect to each class within a set of predefined classes;
determining a first set of keywords from the plurality of keywords, wherein the correlation for each of the first set of keywords is below a predefined correlation threshold;
identifying a set of data samples comprising a first plurality of sentences oriented towards a set of objectives and a second plurality of sentences disaffiliated from the set of objectives;
computing a statistical significance value of each keyword in the first set of keywords with respect to the first plurality of sentences;
generating a first set of features by discarding at least one keyword from the first set of keywords, wherein the statistical significance value for each of the at least one keyword is above a predefined statistical threshold; and
training a machine learning model to identify an objective of a document, based on the first set of features and the first plurality of sentences.
|