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.

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.

Systems and methods are disclosed herein for storing configuration data as a set of master data and override data where one set of configuration data is defined as the master and every other set of configuration data is defined as override configuration data. A media guidance application may generate master configuration data including the most common configuration data used in the geographical region served by the media guidance application, and number of override configurations which contain only those data which differ from the master configuration data for a number of sub-regions of the geographical region. This reduces duplicative configuration data, and the media guidance application need only store one full set of configuration data, namely the master configuration data, and a number of smaller override configurations.

A method for updating an embedded device that includes a processor that receives an image file including at least one of kernel software, hardware configuration data, and application software. The embedded device parses the image file to determine portions of the image file that have been indicated by at least one flag as being modified from that currently being included on the embedded device. The embedded device installing at least portions of the image file on the embedded device and resetting portions of the embedded device based upon the at least one flag.

Embodiments provide for methods, computer program products, and systems to improve media playback comprising receiving a variant stream, identifying respective maximum segment durations for a plurality of different types of client devices that will play media content contained in the variant stream, generating, using the variant stream, a respective playlist for each of the plurality of different types of client devices, wherein the respective playlists each contain different maximum segment durations, and delivering the respective playlists to at least one of the plurality of different types of client devices via a distribution network.

This patent disclosure provides various embodiments of a client-server based digital video playback system and technique. In one aspect, a process for playing internet/online videos on a user device is disclosed. This process can begin by sending a video playback request for playing an online video to the server, wherein the video playback request includes a device type and a browser type of the user device. Next, the process receives a set of video playback addresses and a set of video playback configuration files from the server, wherein the set of video playback addresses and the set of video playback configuration files are generated based on the device type and the browser type. The process subsequently selects a video playback address from the set of video playback addresses corresponding to a transcoded version of the online video that matches a device version and a browser version of the user device. The process next obtains the transcoded version of the online video from the selected video playback address, and plays the obtained video on the user device.

Embodiments provide for methods, computer program products, and systems to improve media playback comprising receiving a variant stream, identifying respective maximum segment durations for a plurality of different types of client devices that will play media content contained in the variant stream, generating, using the variant stream, a respective playlist for each of the plurality of different types of client devices, wherein the respective playlists each contain different maximum segment durations, and delivering the respective playlists to at least one of the plurality of different types of client devices via a distribution network.

Systems and methods are disclosed herein for storing configuration data as a set of master data and override data where one set of configuration data is defined as the master and every other set of configuration data is defined as override configuration data. A media guidance application may generate master configuration data including the most common configuration data used in the geographical region served by the media guidance application, and number of override configurations which contain only those data which differ from the master configuration data for a number of sub-regions of the geographical region. This reduces duplicative configuration data, and the media guidance application need only store one full set of configuration data, namely the master configuration data, and a number of smaller override configurations.

Training data for a machine learning model is generated. Generating the training data includes generating first training input, the first training input including first contextual information associated with a first user device of multiple user devices associated with a user account. The first contextual information identifies first location information corresponding to the first user device. A first target output for the first training input is generated. The first target output identifies an indication of a preference associated with the user account to cancel a first transmission of one or more media items to the first user device. The training data is provided to train the machine learning model on (i) a set of training inputs including the first training input, and (ii) a set of target outputs including the first target output.

In an automatic, computer-implemented method, a selected television advertisement is presented automatically in association with a television program or channel, which in turn is selected based at least in part on information from an online user profile that contains information indicating a user's preference for that television program or channel. The television advertisement is selected based at least in part on additional information from the online user profile that is unrelated to the selected television program or channel. The selected television advertisement is presented on or during the selected television program or channel via a set-top box, which has a set-top box identifier associated with the online user profile.