Back to results
US 9,928,835 B1Granted
Systems and methods for determining content preferences based on vocal utterances and/or movement by a user
AssigneeAmazon Technologies, Inc.
InventorJoshua K. Tang
Life of this patent
Estimating the term…
Abstract
This disclosure relates to systems and methods for determining when a user likes a piece of content based, at least in part, on analyzing user responses to the content. In one embodiment, the user's response may be monitored by audio and motion detection devices to determine when the user's vocals or movements are emulating the content. When the user's emulation exceeds a threshold amount the content may be designated as “liked.” In certain instances, a similar piece of content may be selected to play when the current content is finished.
Claims20
A system, comprising:
- a speaker configured to generate first audio output signal corresponding to playback of a song;
- a microphone configured to receive a sound wave representative of an utterance by a user, and further configured to generate a second audio output signal corresponding to the sound wave;
- at least one memory comprising computer-executable instructions;
- at least one processor configured to execute the computer-executable instructions to:
- determine, using the first audio output signal, that the song is playing;
- determine, using the second audio output signal, that the utterance is present during the playback of the song;
- determine a number of words in the utterance that are similar to lyrics of the song;
- determine that the number of words exceeds a threshold number;
- determine that timing of words within the utterance is synchronized with a melody of the song;
- and
- generate an indication that the user likes the song.
8 more elements
A device, comprising:
- a speaker configured to generate output signal corresponding to playback of a song;
- an accelerometer configured to generate second output signal representative of movement of the device;
- at least one memory device having computer-executable instructions stored therein;
- at least one processor coupled to the at least one memory device and configured to execute the computer-executable instructions to:
- determine, using the output signal, that the song is playing;
- determine a characteristic of the movement using at least the second output signal;
- determine that the characteristic of the movement corresponds to a component of the song, wherein the component of the song comprises a tempo or a rhythm;
- rank the characteristic using a ranking criterion, resulting in a movement ranking of the characteristic, wherein the ranking criterion comprises accuracy of correspondence to the component of the song, quantity of the correspondence to component of the song, or intensity of the correspondence to the component of the song;
- and
- generate an indication that a user likes the song based at least on the movement ranking exceeding a defined threshold amount.
7 more elements
A method, comprising:
- generating, by a speaker of a device, output signal corresponding to playback of a song;
- receiving, from an accelerometer, second output signal representative of movement of a second device;
- determining, using the output signal, that the song is playing;
- determining a characteristic of the movement using at least the second output signal;
- determining that the characteristic of the movement corresponds to a component of a song, wherein the component of the song comprises a tempo or a rhythm;
- ranking the characteristic using a ranking criterion, resulting in a movement ranking of the characteristic, wherein the ranking criterion comprises accuracy of correspondence to the component of the song, quantity of the correspondence to component of the song, or intensity of the correspondence to the component of the song;
- and
- generating an indication that a user likes the song based at least on the movement ranking exceeding a defined threshold amount.
5 more elements
Dependencies are inferred from the claim text.