System and methods for detecting temporal music trends from online services

摘要

A system and methods for automatically detecting temporal music trends by observing music consumption by users of online services, for example, social networks, and user sharing habits. In some embodiments, the system and methods gather music consumption patterns (e.g., downloading, listening, sharing or the like) of users, including music identifiers for a track, album, or playlist in a user's music library and time stamps that indicate consumption times corresponding to the music identifiers. A temporal trends detection engine determines music of interest to users by analyzing music consumption patterns of users, user interests and tastes in music, and social affinity between users. A recommendations engine automatically generates and transmits recommendations of music determined by the temporal trends detection engine to be of interest to users.

主权项

1. A computer-implemented method for detecting temporal music trends in an online community, executing on one or more computing devices, the method comprising:
identifying a type of music for a particular user based on activities of the particular user inside and outside the online community; determining, by at least one of the one or more computing devices, users of the online community that share a common interest in the type of music with the particular user; obtaining, by at least one of the one or more computing devices, music consumption data for the users that share the common interest in the type of music with the particular user, wherein the music consumption data includes a plurality of items of music having the type of music, and timestamps that indicate when and how many times each one of the plurality of items of music was consumed by the users, the plurality of items of music identified by unique music identifiers; compiling a list of the plurality of items of music consumed by the users that share the common interest in the type of music with the particular user, the list of the plurality of items of music including the time stamps that indicate when and how many times each of the plurality of items of music was consumed by the users; determining, from the list, one or more popular items of music that are popular based on the time stamps that indicate when and how many times the one or more popular items of music were consumed by the users; determining a strength of a social affinity between the users and the particular user based on interactions between the users and the particular user in the online community; generating recommendations, by at least one of the one or more computing devices, for the particular user, including transmitting the recommendations for the particular user from the users that share the common interest in the type of music with the particular user based on the strength of the social affinity between the particular user and the users, and reconfiguring the recommendations for display to the particular user by determining real-time popular items that are popular based on time stamps; and providing for display to the particular user the generated recommendations.