Systems, apparatuses, methods and computer-readable medium for automatically generating playlists based on taste profiles

A system for generating playlists, comprising:

• one or more processors configured to:
• receive activity records associated with a media content play history of a user, the activity records containing activity information based on actions of the user and context information defining a context in which each of the actions was performed;
• retrieve intent signals from the activity records, the intent signals indicating a level of intention in the actions of the user, wherein the level of intention is based, in part, on the context information;
• select a first media object from the media content play history;
• construct an N-dimensional latent factor vector based on the activity records and the intent signals associated with the first media object, wherein N is an integer and the N-dimensional latent factor vector defines attributes of the first media object,
• identify a first playlist including the first media object;
• identify, within the first playlist, a second media object that is not in the media content play history and has attributes defined by an M-dimensional latent factor vector, wherein M is an integer and the M-dimensional latent factor vector matches the N-dimensional latent factor vector based on one or more relationships between the latent factor vectors;
• generate a second playlist including the second media object;
• record feedback associated with interactions of the user with the first playlist and the second playlist;
• feed the feedback to at least one latent factor model used to construct any one of (i) the N-dimensional latent factor vector, (ii) the M-dimensional latent factor vector, or (iii) a combination of (i) and (ii);
• and
• update the second playlist using the at least one latent factor model.

A non-transitory computer readable storage medium storing one or more programs, the one or more programs comprising instructions, which, when executed by an electronic device with one or more processors, cause the electronic device to perform the steps of:

• receiving activity records associated with a media content play history of a user, the activity records containing activity information based on actions of the user and context information defining a context in which each of the actions was performed;
• retrieving intent signals from the activity records, the intent signals indicating a level of intention in the actions of the user, wherein the level of intention is based, in part, on the context information;
• selecting a first media object from the media content play history;
• constructing an N-dimensional latent factor vector based on the activity records and the intent signals associated with the first media object, wherein N is an integer and the N-dimensional latent factor vector defines attributes of the first media object,
• identifying a first playlist including the first media object;
• identifying, within the first playlist, a second media object that is not in the media content play history and has attributes defined by an M-dimensional latent factor vector, wherein M is an integer and the M-dimensional latent factor vector matches the N-dimensional latent factor vector based on one or more relationships between the latent factor vectors;
• generating a second playlist including the second media object;
• recording feedback associated with interactions of the user with the first playlist and the second playlist;
• feeding the feedback to at least one latent factor model used to construct any one of (i) the N-dimensional latent factor vector, (ii) the M-dimensional latent factor vector, or (iii) a combination of (i) and (ii);
• and
• updating the second playlist using the at least one latent factor model.