US 12,340,804 B1
Systems and methods to translate a spoken command to a selection sequence
Maneesh Dewan, Sunnyvale, CA (US); Jatin Chhugani, Mountain View, CA (US); Ganesh Satish Mallya, Santa Clara, CA (US); Alan Diec, Sunnyvale, CA (US); Vamsi Reddy Chagari, Milpitas, CA (US); Sudheer Tumu, Santa Clara, CA (US); and Nithyanand Kota, Santa Clara, CA (US)
Assigned to Suki AI, Inc., Redwood City, CA (US)
Filed by Suki AI, Inc., Redwood City, CA (US)
Filed on May 3, 2024, as Appl. No. 18/655,040.
Application 18/655,040 is a continuation of application No. 17/989,449, filed on Nov. 17, 2022, granted, now 11,978,451.
Application 17/989,449 is a continuation of application No. 17/221,603, filed on Apr. 2, 2021, granted, now 11,508,373, issued on Nov. 22, 2022.
This patent is subject to a terminal disclaimer.
Int. Cl. G10L 15/22 (2006.01); G06F 3/04842 (2022.01); G10L 15/02 (2006.01); G10L 15/06 (2013.01); G10L 15/08 (2006.01)
CPC G10L 15/22 (2013.01) [G06F 3/04842 (2013.01); G10L 15/02 (2013.01); G10L 15/063 (2013.01); G10L 15/08 (2013.01); G10L 2015/221 (2013.01); G10L 2015/225 (2013.01)] 14 Claims
OG exemplary drawing
 
1. A system configured to translate a spoken command to a selection sequence, the system comprising:
electronic storage configured to store primary correlations and secondary correlations, wherein the primary correlations indicate relationships between commands and terms, wherein the commands correspond to sets of one or more executable operations to cause results, wherein the secondary correlations indicate relationships between selection sequences provided by users via client computing platforms and sets of previously spoken terms that are spoken temporally in conjunction with performances of the selection sequences, wherein the selection sequences cause particular results;
one or more processors configured by machine-readable instructions to:
obtain audio information captured by a client computing platform, the audio information conveying spoken terms;
determine whether the spoken terms include one or more of the terms included in the primary correlations or the secondary correlations;
responsive to determining that the spoken terms include one or more terms indicated in a given primary correlation with a given command, perform a set of one or more executable operations that correspond to the given command; and
responsive to determining that the spoken terms include a given set of previously spoken terms indicated in a given secondary correlation, perform a given selection sequence corresponding to the given set of previously spoken terms to cause a particular result.