A system and method are disclosed for training a machine learning model using information pertaining to transmissions of one or more media items to user devices associated with a user account. Generating training data for the machine learning model includes generating first contextual information associated with a first user device and generating a first target output that identifies an indication of a preference of a user preference to cancel the first transmission. The method includes providing the training data to train the machine learning model.

Methods and apparatus to identify streaming sessions are disclosed. A disclosed apparatus for identifying streaming sessions includes an encoder to generate an identifier corresponding to a media file of an advertisement, a detector to determine a presence of the identifier in the advertisement presented at a media presentation device, a timing analyzer to determine a time at which the advertisement was presented, and an associator. The associator is to compare the identifier and the time to a streaming session log from a streaming service provider, identify a streaming session in which the advertisement associated with the identifier was presented at the time based on the comparison, and associate a panelist identifier corresponding to the media presentation device with a streaming session identifier corresponding to the streaming session.

The present disclosure provides a method for quick start of live video streaming. The method includes: recognizing a type of a current player and invoking a quick start policy compatible with the type of the current player; during the execution of the quick start policy, retrieving a current system time and a quick start configuration time corresponding to the current player; based on the current system time and the quick start configuration time, determining a quick start index position in a target live video stream, and based on the quick start index position, determining a key frame index position in the target live video stream; and sending video data in the target live video stream starting from the key frame index position to the current player and discarding audio data in the target live video stream between the key frame index position and the quick start index position.

The disclosed technology relates to adaptively encoding a video stream based on viewer engagement, content schedule and/or content characteristics. A system routes a video stream from a signal extractor to a first virtual encoder. The first virtual encoder is instantiated on a cloud platform and provides a first video output at a first bitrate. A second virtual encoder is instantiated on the cloud platform in response to a change in viewer count. The system routes the video stream from the signal extractor to the second virtual encoder. The second virtual encoder provides a second video output at a second bitrate. The second bitrate is different from the first bitrate.

In one aspect, a method includes determining a content-modification operation channel-change rate for a group of content-presentation devices having a common content-presentation device attribute; comparing the content-modification operation channel-change rate with a baseline channel-change rate; determining that a result of the comparing satisfies a threshold condition; and based on determining that the result of the comparing satisfies the threshold condition, preventing at least one content-presentation device of the group of content-presentation devices from carrying out a future content-modification operation.

In one example, the present disclosure describes a device, computer-readable medium, and method for improving media quality at the network edge by encoding the media into a digital stream that is carried, end-to-end, to a peer edge device. For instance, in one example, a method includes initiating, by a first computing device, a connection to a second computing device, selecting, by the first computing device, a codec for encoding data into a data stream, wherein the codec is selected such that the data stream can be decoded by the second computing device without being transcoded by an intermediary, encoding, by the first computing device, the data into the data stream using the codec, and sending, by the first computing device, the data stream to the second computing device.

In one aspect, a method includes determining a content-modification operation channel-change rate for a group of content-presentation devices having a common content-presentation device attribute; comparing the content-modification operation channel-change rate with a baseline channel-change rate; determining that a result of the comparing satisfies a threshold condition; and based on determining that the result of the comparing satisfies the threshold condition, preventing at least one content-presentation device of the group of content-presentation devices from carrying out a future content-modification operation.

In one example, the present disclosure describes a device, computer-readable medium, and method for improving media quality at the network edge by encoding the media into a digital stream that is carried, end-to-end, to a peer edge device. For instance, in one example, a method includes initiating, by a first computing device, a connection to a second computing device, selecting, by the first computing device, a codec for encoding data into a data stream, wherein the codec is selected such that the data stream can be decoded by the second computing device without being transcoded by an intermediary, encoding, by the first computing device, the data into the data stream using the codec, and sending, by the first computing device, the data stream to the second computing device.

A video-on-demand (VOD) content delivery system has a VOD Application Server which manages a database of templates for presentation of video content elements of different selected types categorized in hierarchical order. A web-based Content Management System receives content uploaded online in file formats with metadata for title and topical area, and automatically converts it into video data format compatible with the VOD content delivery system indexed by title and topical area. A User Interface for the system delivers listings data to the viewer's TV indexed by title and topical area specified by the uploaded metadata.

Disclosed are a method and an apparatus for live streaming. The method includes: collecting, by a first terminal, live streaming audio data and first live streaming image data in a live streaming process; sending, by the first terminal, the live streaming audio data and the first live streaming image data to a server, and sending, by the first terminal, a first device identifier of the first terminal to the server; sending, by the first terminal, the live streaming audio data to a second terminal; collecting, by the second terminal, second live streaming image data; and sending, by the second terminal, the second live streaming image data and the live streaming audio data to the server, and sending, by the second terminal, a second device identifier of the second terminal to the server.