Abstract: A system capable of generating and storing program data associated with localized content, such as over-the-air television broadcasts. The system may update a knowledge base with the program data to improve natural language understanding (NLU) processing associated with the localized content. For example, a voice enabled device may receive a voice command and the system may perform NLU processing to interpret the voice command, determine content based on the program data and send an instruction to an output device to output the content. The program data may include information about localized content such as channels detected by the output device and/or content broadcast on the channels, including information about an output device, a channel number, call sign, station name, signal strength, etc. associated with a detected channel, and/or a program name, genre, actors, directors, producers, etc. associated with content broadcast on the channel or stored in a local storage device.

Abstract: The recording of broadcast media can be performed by a network storage service even where a client is unable to provide a full copy of the media file. For example, a client might want to record a television broadcast by transmitting the content to a remote storage service. For a high definition format, however, the upload limitations of the data connection may prevent the full content from being uploaded from that client. Accordingly, clients recording the same content and using the same service can upload respective segments of the content, with each segment being provided by at least one of the clients and available for subsequent download. At least some of those clients can also store some of the segments such that those clients can act as peer sources for obtaining those segments.

Abstract: A system capable of generating and storing program data associated with localized content, such as over-the-air television broadcasts. The system may update a knowledge base with the program data to improve natural language understanding (NLU) processing associated with the localized content. For example, a voice enabled device may receive a voice command and the system may perform NLU processing to interpret the voice command, determine content based on the program data and send an instruction to an output device to output the content. The program data may include information about localized content such as channels detected by the output device and/or content broadcast on the channels, including information about an output device, a channel number, call sign, station name, signal strength, etc. associated with a detected channel, and/or a program name, genre, actors, directors, producers, etc. associated with content broadcast on the channel or stored in a local storage device.

Abstract: The performance of a device can be improved by intelligently terminating (or otherwise operationally adjusting) applications, services, or processes that the user is unlikely to access on the device. Information such as system event data and hint data can be obtained from various sources and fed to one or more predictor algorithms, which can determine the likelihood that a user will access various applications over a period of time. Other determinations can be made as well, such as which applications are most likely causing degradation in performance. Various termination actions can be selected to be performed, which can in some cases adjust the applications selected for termination by an operating system of the device. Once a set of actions is selected, those termination actions can be performed for the associated application(s) at least to the extent needed to restore health of the device.