| CPC G06F 16/433 (2019.01) [G06F 16/24578 (2019.01); G06F 16/435 (2019.01); G06F 16/438 (2019.01); G06F 16/9535 (2019.01)] | 20 Claims |
|
1. A method comprising:
receiving a voice query;
identifying, by control circuitry, a plurality of content items based on the voice query, wherein the plurality of content items comprises:
a first content item having an associated first type and a first relevance score, wherein the first type indicates the first content item is labeled for a first group, and the first relevance score indicates a level of relevance of the first content item to members of the first group;
a second content item having an associated second type and a second relevance score, wherein the second type indicates the second content item is labeled for a second group different from the first group, and the second relevance score indicates a level of relevance of the second content item to members of the second group;
determining that the voice query is from a member of the first group or second group by classifying the voice query based on acoustic features of the voice query;
based on the determining, modifying, by the control circuitry, one or both of the first relevance score of the first content item and the second relevance score of the second content item; and
after modifying one or both of the first relevance score and the second relevance score, selecting, by the control circuitry, for a presentation the first content item or the second content item based on the first relevance score and the second relevance score.
|