US 11,785,299 B1
Selecting advertisements for media programs and establishing favorable conditions for advertisements
Harshal Dilip Wanjari, Issaquah, WA (US); Sanjeev Kumar, Redmond, WA (US); Ayman Mahfouz, Culver City, CA (US); Thomas Albert Faulhaber, Seattle, WA (US); Pratik GuhaRay, Kenmore, WA (US); Robert Eicher Simmering, Santa Ana, CA (US); Hsuan-Cheng Lai, Issaquah, WA (US); Ramasubramanian Balagurunathan, Redmond, WA (US); and Juan Martin Borgnino, Marina Del Rey, CA (US)
Assigned to Amazon Technologies, Inc., Seattle, WA (US)
Filed by Amazon Technologies, Inc., Seattle, WA (US)
Filed on Sep. 30, 2021, as Appl. No. 17/491,204.
This patent is subject to a terminal disclaimer.
Int. Cl. G10L 15/08 (2006.01); H04N 21/458 (2011.01); H04N 21/44 (2011.01); H04N 21/81 (2011.01); H04N 21/442 (2011.01); H04N 21/466 (2011.01)
CPC H04N 21/458 (2013.01) [G10L 15/08 (2013.01); H04N 21/44008 (2013.01); H04N 21/44204 (2013.01); H04N 21/466 (2013.01); H04N 21/812 (2013.01); G10L 2015/088 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A first computer system comprising at least a first data store and at least a first computer processor, wherein the first computer system is connected to one or more networks, and
wherein the first data store has one or more sets of instructions stored thereon that, when executed by at least the first computer processor, cause the first computer system to perform a method comprising:
identifying information regarding an advertisement;
determining a theme associated with the advertisement based at least in part on the information regarding the advertisement;
identifying first audio data transmitted to at least a plurality of computer systems,
wherein each of the plurality of computer systems is associated with at least one listener to a media program,
wherein at least a first portion of the audio data is received from a second computer system associated with a creator of the media program, and
wherein at least a second portion of the audio data was received from one of the plurality of computer systems;
providing the first audio data as a first input to a first machine learning model trained to identify at least one word expressed within audio data;
identifying a first set of words of the media program based at least in part on a first output received in response to the first input;
identifying a subject of a media program consistent with the theme associated with the advertisement;
determining that the subject is associated with the first set of words and a second set of words;
transmitting information comprising the second set of words to the second computer system;
receiving second audio data from the second computer system, wherein the second audio data represents at least a portion of the second set of words;
causing the second audio data to be transmitted to at least the plurality of computer systems;
after causing the second audio data to be transmitted to at least the plurality of computer systems,
transmitting code for causing a display of a user interface on the second computer system, wherein the user interface comprises:
a third set of words, wherein the third set of words corresponds to the theme associated with the advertisement; and
a selectable element for causing third data corresponding to the first advertisement to be transmitted to at least the second computer system;
receiving an interaction with the selectable element;
in response to receiving the interaction with the selectable element,
causing the third audio data to be transmitted to at least the plurality of computer systems.