US 11,862,157 B2
Automated ordering system
Rahul Aggarwal, Austin, TX (US); Vinay Kumar Shukla, Austin, TX (US); Pranav Nirmal Mehra, Bangalore (IN); Vrajesh Navinchandra Sejpal, Bangalore (IN); Akshay Labh Kayastha, Bangalore (IN); Yuganeshan A J, Bangalore (IN); German Kurt Grin, Buenos Aires (AR); Fernando Ezequiel Gonzalez, Caba (AR); Julia Milanese, Berlin (DE); Zubair Talib, Irvine, CA (US); and Matias Grinberg, Caba (AR)
Assigned to ConverseNow AI, Austin, TX (US)
Filed by ConverseNowAI, Austin, TX (US)
Filed on Jul. 2, 2021, as Appl. No. 17/366,941.
Application 17/366,941 is a continuation in part of application No. 17/184,207, filed on Feb. 24, 2021.
Prior Publication US 2022/0270600 A1, Aug. 25, 2022
This patent is subject to a terminal disclaimer.
Int. Cl. G10L 15/00 (2013.01); G10L 15/22 (2006.01); G10L 15/18 (2013.01); G06Q 50/12 (2012.01); G10L 15/26 (2006.01); G06Q 30/0601 (2023.01)
CPC G10L 15/22 (2013.01) [G06Q 30/0633 (2013.01); G06Q 50/12 (2013.01); G10L 15/1815 (2013.01); G10L 15/26 (2013.01); G10L 2015/225 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A method comprising:
receiving, by a software agent executing on a server, a communication comprising a first utterance from a customer;
predicting, using an intent classifier, a first intent of the first utterance;
based on determining that the first intent is order-related, predicting, using a dish classifier, a cart delta vector based at least in part on the first utterance;
modifying a cart associated with the customer based on the cart delta vector;
predicting, using a dialog model, a first dialog response based at least in part on the first utterance; and
providing the first dialog response, by the software agent, to the customer using a text-to-speech converter.