US 11,854,535 B1
Personalization for speech processing applications
Sihui Zhang, Bellevue, WA (US); Amber Roy Chowdhury, Bellevue, WA (US); Hassan Haider Malik, Issaquah, WA (US); Sanjay Kumar, Kirkland, WA (US); Uday S. Sandhar, Seattle, WA (US); Pawel Matykiewicz, Bellevue, WA (US); Ming Ma, Bellevue, WA (US); and Anand Vishwanath Suvarnkar, Redmond, WA (US)
Assigned to AMAZON TECHNOLOGIES, INC., Seattle, WA (US)
Filed by Amazon Technologies, Inc., Seattle, WA (US)
Filed on Mar. 26, 2019, as Appl. No. 16/365,033.
Int. Cl. G10L 15/22 (2006.01); G10L 15/08 (2006.01); G10L 15/18 (2013.01); G10L 15/16 (2006.01)
CPC G10L 15/08 (2013.01) [G10L 15/18 (2013.01); G10L 15/1815 (2013.01); G10L 15/1822 (2013.01); G10L 15/22 (2013.01); G10L 15/16 (2013.01); G10L 2015/223 (2013.01); G10L 2015/227 (2013.01)] 20 Claims
OG exemplary drawing
 
5. A method, comprising:
receiving, from a first skill, a first request to rank content, wherein the first request comprises a list of unranked content and device data identifying a device;
determining a first machine learning model associated with the first skill;
determining a first feature definition describing a first aspect of the content;
generating first feature data according to the first feature definition;
determining a second feature definition describing interaction with the first skill;
determining first user profile data associated with the device;
generating second feature data according to the second feature definition based on the first user profile data;
generating, by the first machine learning model, a ranked list of the content based at least in part on the first feature data and the second feature data; and
sending the ranked list to the first skill.