US 11,941,036 B2
Methods and arrangements for similarity search based on multi-label text classification
Brian Nguyen, Chantilly, VA (US); Paul Cho, Boston, MA (US); and Ankur Ankur, Arlington, VA (US)
Assigned to Capital One Services, LLC, McLean, VA (US)
Filed by Capital One Services, LLC, McLean, VA (US)
Filed on Jun. 3, 2022, as Appl. No. 17/831,651.
Prior Publication US 2023/0394075 A1, Dec. 7, 2023
Int. Cl. G06F 16/30 (2019.01); G06F 16/33 (2019.01); G06F 16/35 (2019.01)
CPC G06F 16/35 (2019.01) [G06F 16/3347 (2019.01)] 19 Claims
OG exemplary drawing
 
1. An apparatus comprising:
memory; and
logic circuitry coupled with the memory to:
provide a hierarchical label structure for a document, the hierarchical label structure comprising a predicted set of hierarchical labels associated with the document;
access a historical label performance database, the historical label performance database comprising performance data associated with each assignee in a complete set of assignees for each label in a complete set of the hierarchical labels;
generate a first vector for the hierarchical label structure for the document;
generate a second vector for each of the assignees in an identified set of assignees, the second vector comprising each hierarchical label in the predicted set of hierarchical labels of the hierarchical label structure for the document, the identified set comprising one or more of the assignees in the complete set of assignees;
perform a similarity search to identify a predicted assignee from the identified set of assignees; and
predict a selected assignee of the identified set of assignees to associate with the document via the similarity search.