US 11,741,529 B2
System for eatery ordering with mobile interface and point-of-sale terminal
Christopher Siefken, Charlotte, NC (US); Mahesh Kommareddi, Charlotte, NC (US); William Wine, Charlotte, NC (US); Arjun Wadwalkar, Charlotte, NC (US); Santiago Lopez, Medellin (CO); David Sanchez, Medellin (CO); and Davison Anaya, Medellin (CO)
Assigned to XENIAL, INC., Charlotte, NC (US)
Filed by XENIAL, INC., Charlotte, NC (US)
Filed on Feb. 25, 2020, as Appl. No. 16/800,428.
Claims priority of provisional application 62/810,837, filed on Feb. 26, 2019.
Prior Publication US 2020/0273089 A1, Aug. 27, 2020
Int. Cl. G06Q 30/06 (2023.01); G06Q 30/0601 (2023.01); G06N 20/00 (2019.01); G06F 40/295 (2020.01); G06Q 20/20 (2012.01); G06Q 50/12 (2012.01); G10L 15/30 (2013.01); G10L 25/30 (2013.01)
CPC G06Q 30/0635 (2013.01) [G06F 40/295 (2020.01); G06N 20/00 (2019.01); G06Q 20/20 (2013.01); G06Q 30/0641 (2013.01); G06Q 50/12 (2013.01); G10L 15/30 (2013.01); G10L 25/30 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A non-transitory computer-readable medium configured to store instructions executable by one or more processors to perform operations comprising:
independently processing, by each of a first system and a second system via a voice application programming interface (API) enabling order placement by a customer, audio data relating to one or more orders by the customer for food or beverage in a menu and one or more intentions of the customer associated with the food or beverage in the menu;
determining whether the first system has supplied a first indication relating to an intention of the one or more intentions of the customer associated with performing fir st language processing of the audio data, the first system being configured to perform one or more of the first language processing, first transcription processing, or first entity recognition processing for menu items in the menu;
selecting a result of second language processing of the audio data from the second system in response to determining that the first system has not supplied the first indication, the second system being configured to perform one or more of second language processing of higher quality than the first language processing, second transcription processing of lower quality than the first transcription processing, or second entity recognition processing for menu items in the menu, and wherein the second entity recognition processing comprises recognizing at least a portion of the audio data as relating to a single entity, wherein the operations further comprise:
identifying a plurality of speakers of the audio data;
determining a speaker of authority based on, during the second language processing, linking metadata of the audio data to one of the plurality of speakers and identifying the speaker of authority based on a percentage of intent related content of the speaker of authority compared to other speakers of the plurality of speakers, wherein during the second language processing the second system amplifies the audio data of the speaker of authority;
performing combination conversion validation on the result of the second language processing of the one or more orders to create an updated result of the result of the second language processing, wherein combination conversion validation comprises determining whether the result of the second language processing of the one or more orders contain a bundle of two or more menu items offered together on the menu; and
transmitting, via an order submission API enabling order creation at a point-of-sale (POS) terminal of a store, the updated result of the one or more orders to the point-of-sale (POS) terminal to execute order processing.