US 11,698,934 B2
Graph-embedding-based paragraph vector machine learning models
Suman Roy, Bangalore (IN); Amit Kumar, Gaya (IN); Ayan Sengupta, Noida (IN); Riccardo Mattivi, Dublin (IE); Ahmed Selim, Dublin (IE); and Shashi Kumar, Bengaluru (IN)
Assigned to Optum, Inc., Minnetonka, MN (US)
Filed by Optum, Inc., Minnetonka, MN (US)
Filed on Sep. 3, 2021, as Appl. No. 17/466,594.
Prior Publication US 2023/0079343 A1, Mar. 16, 2023
Int. Cl. G06F 7/02 (2006.01); G06F 16/00 (2019.01); G06F 16/93 (2019.01); G06F 16/901 (2019.01); G06F 16/36 (2019.01); G06N 20/00 (2019.01)
CPC G06F 16/93 (2019.01) [G06F 16/9024 (2019.01); G06F 16/36 (2019.01); G06N 20/00 (2019.01)] 21 Claims
OG exemplary drawing
 
1. A computer-implemented method comprising:
identifying, by one or more processors, a plurality of word vectors associated with a document data object characterized by an ontology graph;
identifying, by the one or more processors, one or more relationships of the document data object based at least in part on the ontology graph;
generating, by the one or more processors and using a graph-embedding-based paragraph vector machine learning model, a document representation and one or more relational representations for the one or more relationships based at least in part on the plurality of word vectors and the one or more relationships, wherein:
the graph-embedding-based paragraph vector machine learning model is configured to optimize a textual-relational optimization output that comprises a textual optimization sub-output and a relational optimization sub-output,
the textual optimization sub-output is generated based at least in part on (a) the plurality of word vectors, (b) the document representation, and (c) a weighted distance value for a secondary document data object of a plurality of document data objects other than the document data object,
the weighted distance value is determined based at least in part on (a) a distance value between the document data object and the secondary document data object and (b) a relational representation for a relationship type of the secondary document data object and the document data object, and
the relational optimization sub-output is generated based at least in part on the document representation and the one or more relational representations; and
initiating, by the one or more processors, the performance of one or more prediction-based actions based at least in part on at least one of the document representation or the one or more relational representations.