US 12,393,782 B2
System and method for determining intentions of messages
Prakash Ranganathan, Tamilnadu (IN)
Assigned to Verizon Patent and Licensing Inc., Basking Ridge, NJ (US)
Filed by Verizon Patent and Licensing Inc., Basking Ridge, NJ (US)
Filed on Jan. 10, 2022, as Appl. No. 17/571,766.
Prior Publication US 2023/0222291 A1, Jul. 13, 2023
Int. Cl. G06F 40/30 (2020.01); G06N 20/00 (2019.01); H04L 51/02 (2022.01); H04L 51/21 (2022.01); H04L 51/216 (2022.01)
CPC G06F 40/30 (2020.01) [G06N 20/00 (2019.01); H04L 51/02 (2013.01); H04L 51/21 (2022.05); H04L 51/216 (2022.05)] 19 Claims
OG exemplary drawing
 
1. A method comprising:
training a machine learning model using training information to generate a trained machine learning model;
loading the trained machine learning model into a natural language generation engine;
receiving, from a client device, a first set of text via a messaging interface;
determining, based upon the first set of text and using the natural language generation engine loaded with the trained machine learning model, one or more sets of text semantically similar to the first set of text;
determining, based upon the first set of text and the one or more sets of text, a plurality of intention predictions comprising:
a first intention prediction based upon the first set of text, wherein a first confidence score is indicative of a first probability that the first intention prediction is correct; and
one or more second intention predictions generated based upon the one or more sets of text, wherein a second intention prediction of the one or more second intention predictions is generated based upon a second set of text of the one or more sets of text, wherein a second confidence score is indicative of a second probability that the second intention prediction is correct, wherein a third intention prediction of the one or more second intention predictions is generated based upon a third set of text of the one or more sets of text, wherein a third confidence score is indicative of a third probability that the third intention prediction is correct, wherein the second intention prediction and the third intention prediction are both indicative of a common intention;
determining a first intention, of the first set of text, based upon:
the plurality of intention predictions,
the first confidence score,
the second confidence score corresponding to the second intention prediction indicative of the common intention, and
the third confidence score corresponding to the third intention prediction indicative of the common intention; and
performing one or more operations based upon the first intention.