Abstract: An artificial intelligence (AI) application uses an external machine learning component from a different computing environment to develop context data for use by the AI application. The context data includes raw data outputs from the external machine learning component. An active machine learning component is executed with the context data and provides a suggested next step to a computer to implement as an automated output. A feedback loop adds the suggested next step from the active machine learning component to the context data and forms an augmented data set for providing context to the AI application. A context component selects a rule from a rules engine that corresponds to the augmented data set. The computer implements an automated output according to the rule that was selected.

Abstract: Relationships and descriptions are inferred for entities that appear in media content, such as movies and television programs. In one embodiment, media content is analyzed to infer relationships among entities that appear in the media content over an entirety of the media content. Relationships between two or more entities may change over time in the media content. A request is received from a client device for entity information regarding one or more entities relative to a particular time in the media content. Relationships that have been inferred via this analysis are then identified based at least in part on the particular time. The entity information presenting the identified relationships is sent to the client device.