Generation and selection of actions for entities in a video delivery system

A non-transitory computer-readable storage medium containing instructions, that when executed, control a computer system to be configured for:

• generating a set of entities found on a video delivery system for a user;
• generating a set of actions for the set of entities to form a set of action/entity pairs from the one or more entities and the set of actions, wherein each action/entity pair includes an action to be performed on an entity found on the video delivery system;
• generating probabilities for the set of action/entity pairs based on a respective action and a respective entity in a respective action/entity pair, and user behavior of the user on the video delivery system, wherein a probability for an action/entity pair indicates the probability the user would select that action/entity pair when compared against other action/entity pairs;
• ranking action/entity pairs in the set of action/entity pairs based on respective probabilities for the action/entity pairs;
• selecting an action feed based on the ranking of the set of action/entity pairs, the action feed including at least a portion of the set of action/entity pairs;
• and
• outputting the action feed to the client for display on an interface, wherein an action on an entity in the action feed is performed by the video delivery system when selected by the user on the interface displayed on the client.

An apparatus comprising:

• one or more computer processors;
• and
• a non-transitory computer-readable storage medium comprising instructions, that when executed, control the one or more computer processors to be configured for:
• generating a set of entities found on a video delivery system for a user;
• generating a set of actions for the set of entities to form a set of action/entity pairs from the one or more entities and the set of actions, wherein each action/entity pair includes an action to be performed on an entity found on the video delivery system;
• generating probabilities for the set of action/entity pairs based on a respective action and a respective entity in a respective action/entity pair, and user behavior of the user on the video delivery system, wherein a probability for an action/entity pair indicates the probability the user would select that action/entity pair when compared against other action/entity pairs;
• ranking action/entity pairs in the set of action/entity pairs based on respective probabilities for the action/entity pairs;
• selecting an action feed based on the ranking of the set of action/entity pairs, the action feed including at least a portion of the set of action/entity pairs;
• and
• outputting the action feed to the client for display on an interface, wherein an action on an entity in the action feed is performed by the video delivery system when selected by the user on the interface displayed on the client.