Abstract:
Systems and methods are disclosed herein for determining user segments created by a predictive model based on user behavioral data. A data analysis application executing on a computing device receives training data and a user input defining an outcome of interest. The data analysis application trains a predictive model with the training data and the outcome of interest. The data analysis application generates input data for each of a set of conditions determined from the training data. The data analysis application receives predicted outcome from the predictive model based on the input data. The data analysis application determines the relevance of the condition based on a comparison of the predicted outcome and the outcome of interest. The data analysis application generates a user segment that comprises a condition from the set of conditions based on the relevance of the condition.
Abstract:
A computer implemented method and apparatus for avoiding license storming during an unplanned regional blackout. The method comprises generating a leaf license for each geographic region of a plurality of geographic regions in a broadcast area, wherein each leaf license includes a first content encryption key for decrypting media content associated with the leaf license, and where each leaf license is bound to a root license for each geographic region in the plurality of geographic regions; and generating, in response to a blackout event, a new leaf license for each geographic region of the plurality of geographic regions that are located outside of a blackout area, wherein each new leaf license includes a second content encryption key different from the first content encryption key for decrypting protected media content, and wherein each new leaf license remains bound to the root license for each geographic region in the plurality of geographic regions.
Abstract:
A computer implemented method and apparatus for providing fault tolerance during live streaming. The method comprises creating a global manifest comprising a plurality of first entries extracted from a first manifest, wherein the first manifest comprises one or more entries of a predetermined sequence, each entry corresponding to a media fragment to be played in the predetermined sequence on a media player; identifying a gap in the plurality of first entries; receiving a second manifest; and upon receiving a second manifest comprising at least one second entry, extending the global manifest to include the at least one second entry, wherein the at least one second entry comprises a second entry that is in sequence after a last entry in the global manifest, and the at least one second entry in sequence after the last entry in the global manifest does not include a gap.
Abstract:
Disclosed systems and methods generate user-session representation vectors from data generated by user interactions with online services. A transformation application executing on a computing device receives interaction data, which is generated by user devices interacting with an online service. The transformation application separates the interaction data into session datasets. The transformation involves normalizing the session datasets by modifying the rows within each session dataset by removing event identifiers and time stamps. The application transforms each normalized session dataset into a respective user-session representation vector. The application outputs the user-session representation vectors.
Abstract:
Recommendation control techniques using incremental matrix factorization and clustering are described. User latent factors and item latent factors are computed from data that denotes ratings associated with the users regarding respective ones of the plurality of items of digital content. Data is obtained that describes interaction of a particular one of the users with at least one respective item of the digital content. A plurality of clusters is formed using the user latent factors. The recommendations are generated using the user latent factors and the item latent factors for each of the plurality of clusters. Further, at least one of recommendations is located based on comparison of a user identifier of a subsequent user with the plurality of clusters. Interaction of the subsequent user with the digital content is controlled based on the located at least one of the recommendations.
Abstract:
Audience segmentation can be based on a viewing angle of a user viewing a video of a multi-angle viewing environment. During playback, a sequence of the user-controlled viewing angles of the video are recorded. The sequence represents the viewing angle of the user at a given point in time. Based on the sequences of several users, a predominant sequence of viewing angles of the video is determined. One or more audience segment tags are assigned to the predominant sequence of viewing angles. During subsequent playbacks of the video, the sequence(s) of user-controlled viewing angles of the video are recorded. The recorded sequence(s) of the subsequent user(s) are compared to the predominant sequence of viewing angles of the video, and the subsequent user(s) are assigned to an audience segment based on the comparison and the corresponding audience segment tags.
Abstract:
Systems and methods are disclosed for securely identifying a computing device via a web browser utilizing a customized digital font. In particular, in one or more embodiments, the disclosed systems and methods generate a customized digital font and install the customized digital font on a computing device. Moreover, the disclosed systems and methods utilize the customized digital font to identify the computing device. In particular, one or more embodiments include systems and methods that identify an element of a webpage rendered by the computing device utilizing the customized digital font and identify the client device based on the rendered element of the webpage.
Abstract:
A computer implemented method and apparatus for providing fault tolerance during live streaming. The method comprises creating a global manifest comprising a plurality of first entries extracted from a first manifest, wherein the first manifest comprises one or more entries of a predetermined sequence, each entry corresponding to a media fragment to be played in the predetermined sequence on a media player; identifying a gap in the plurality of first entries; receiving a second manifest; and upon receiving a second manifest comprising at least one second entry, extending the global manifest to include the at least one second entry, wherein the at least one second entry comprises a second entry that is in sequence after a last entry in the global manifest, and the at least one second entry in sequence after the last entry in the global manifest does not include a gap.
Abstract:
A computer implemented method and apparatus for avoiding license storming during an unplanned regional blackout. The method comprises generating a leaf license for each geographic region of a plurality of geographic regions in a broadcast area, wherein each leaf license includes a first content encryption key for decrypting media content associated with the leaf license, and where each leaf license is bound to a root license for each geographic region in the plurality of geographic regions; and generating, in response to a blackout event, a new leaf license for each geographic region of the plurality of geographic regions that are located outside of a blackout area, wherein each new leaf license includes a second content encryption key different from the first content encryption key for decrypting protected media content, and wherein each new leaf license remains bound to the root license for each geographic region in the plurality of geographic regions.