US 10,482,074 B2Granted

System and method for classifying data with respect to a small dataset

AssigneeWipro Limited

InventorsMohit Sharma, Raghottam Mannopantar

Life of this patent

Estimating the term…

Loading patent…

Abstract

This technology relates generally to data classification, and more particularly to system and method for classifying an input statement with respect to a small dataset. In one embodiment, a method is provided for classifying an input statement with respect to a small dataset. The method comprises receiving the input statement, extracting a plurality of input keywords from the input statement, computing a membership score for each of a plurality of category ontology trees based on the plurality of input keywords, and determining a classification of the input statement based on the membership score. The plurality of category ontology trees are derived from the small dataset and correspond to a plurality of classifications in the small dataset.

Claims15

Dependent claims

A method for classifying input statements with respect to small datasets, the method comprising:

receiving, by a classification device, an input statement;
extracting, by the classification device, a plurality of input keywords from the input statement;
for each of the plurality of input keywords, computing, by the classification device, an actual coverage in each of a plurality of category ontology trees based on a path length from a tree-root and a number of missing words from the tree-root;
computing, by the classification device, a sum of the actual coverage for the plurality of input keywords in each of the plurality of category ontology trees;
computing, by the classification device, a membership score for each of the plurality of category ontology trees based on the sum of the actual coverage and a total number of keywords in each of the plurality of category ontology trees, wherein the plurality of category ontology trees is derived from a small dataset and corresponds to a plurality of classifications in the small dataset;
and
classifying, by the classification device, the input statement with respect to the small dataset based on the membership score and the plurality of category ontology trees.

4 more elements

A classification device, comprising memory comprising programmed instructions stored in the memory and one or more processors configured to be capable of executing the programmed instructions stored in the memory to:

receive an input statement;
extract a plurality of input keywords from the input statement;
for each of the plurality of input keywords, compute an actual coverage in each of a plurality of category ontology trees based on a path length from a tree-root and a number of missing words from the tree-root;
compute a sum of the actual coverage for the plurality of input keywords in each of the plurality of category ontology trees;
and
compute a membership score for each of the plurality of category ontology trees based on the sum of the actual coverage and a total number of keywords in each of the plurality of category ontology trees, wherein the plurality of category ontology trees is derived from a small dataset and corresponds to a plurality of classifications in the small dataset;
and
classify the input statement with respect to the small dataset based on the membership score and the plurality of category ontology trees.

5 more elements

A non-transitory computer readable medium having stored thereon instructions for classifying input statements with respect to small datasets comprising executable code which when executed by one or more processors, causes the processors to:

receive an input statement;
extract a plurality of input keywords from the input statement;
for each of the plurality of input keywords, compute an actual coverage in each of a plurality of category ontology trees based on a path length from a tree-root and a number of missing words from the tree-root;
compute a sum of the actual coverage for the plurality of input keywords in each of the plurality of category ontology trees;
and
compute a membership score for each of the plurality of category ontology trees based on the sum of the actual coverage and a total number of keywords in each of the plurality of category ontology trees, wherein the plurality of category ontology trees is derived from a small dataset and corresponds to a plurality of classifications in the small dataset;
and
classify the input statement with respect to the small dataset based on the membership score and the plurality of category ontology trees.

5 more elements

Dependencies are inferred from the claim text.