| 摘要 |
A method of recommending songs to a listener. The method obtains a set of feature values for each of a plurality of songs. Whenever a playback event is generated for a song, a first reward and a Mood State Value ("MSV") based on a set of parameters are determined. Each feature value associated with the song is associated with the MSV and for each feature value, a second reward is calculated based on the first reward and is assigned to the feature value. A current MSV is determined and any songs having a feature value identical to a feature value associated with the current MSV are identified. For each song identified, a cumulative reward is calculated by totaling the second reward assigned to any feature values associated with the current MSV that are also associated with the song. Finally, one or more songs are recommended based on their cumulative rewards.
|
