A method disclosed herein provides for receiving, at a user device, a media stream including frames of a first resolution generated by a graphics-rendering application and utilizing one or more weight matrices pre-trained in association with the graphics-rendering application to locally upscale each received frame of the media stream at the user device to a second resolution greater than the first resolution. Local upscaling of the media stream may be performed “on the fly,” such as with respect to individual content streams (e.g., a game) or segments of content streams (e.g., a scene within a game).

Disclosed are a method and a system for enhancing sound and picture quality based on scene recognition, and a display. The method includes: recognizing a real scene reflected in a current screen of the display; calculating sound and picture quality enhancement parameters matching the real scene; and controlling the display to play sound and picture corresponding to the real scene according to best sound and picture quality corresponding to the sound and picture quality enhancement parameters.

The present disclosure relates to a computer-implemented process for evaluating user activity, user preference, and/or user habit via one or more personal devices and providing precisely timed and situationally targeted content recommendations. It is an object of the present disclosure to provide a technological solution to the long felt need in small scale content recommendation systems caused by the technical problem of generating situationally targeted and user preference targeted content recommendations for users of an interactive electronic system.

Provided are an artificial intelligence (AI) system that mimics cognitive functions, such as cognition and judgment, of the human brain using a machine learning algorithm such as deep learning and applications thereof. More particularly, provided is a device including a memory storing least one program and a first video, a display, and at least one processor configured to display the first video on at least one portion of the display by executing the at least one program, wherein the at least one program includes instructions for: comparing an aspect ratio of the first video with an aspect ratio of an area in which the first video is to be displayed, generating a second video corresponding to the aspect ratio of the area by using the first video when the aspect ratio of the first video is different from the aspect ratio of the area, and displaying the second video in the area, wherein the generating of the second video is performed by inputting at least one frame of the first video to an AI neural network.

Methods, systems, and apparatuses for content recommendations based on user activity data are described herein. An analytics subsystem may receive first activity data. The first activity may be indicative of a plurality of first engagements with a first plurality of media assets. At least one machine learning model may be configured to receive an input of activity data, such as the first activity data, and to determine at least one content recommendation on that basis. The at least one content recommendation may comprise a recommendation for at least one media asset. The at least one media asset may be associated with at least one media asset classification. The analytics subsystem may send the at least one content recommendation.

A computer-implemented method of using video program viewer interaction data that has been loaded to a media measurement database as input to a measurement engine which then calculates Linear, DVR, and VOD asset viewing activity at three levels: (a) Video Program, (b) Video Program Airing, (c) Video Program Airing Segment, where each level provides summary metrics for groupings of Demographic, Geographic, and/or Device Characteristic, and also second-by-second viewing metrics, including counting advertising impressions, within the Demographic, Geographic, Device groupings. System also accounts for reduced value of ad viewing when viewer is using trick plays or when viewer delays viewing recorded content. Together these metrics provide detailed information on customer viewing behavior which can be used to drive business decisions for service providers, advertisers and content producers. Additionally, a viewing histogram analysis is produced.

A method, a set-top box, and a non-transitory computer readable medium for log based issue prediction. The method includes receiving, on a processing server, system log files from a customer-premises equipment, the system log files containing events that are logged by an operating system of the customer-premises equipment; parsing, by the processing server, the events of the system log files to processes and mapping the processes to one or more components of the customer-premises equipment; extracting, by the processing server, features from the mapped processes of the one or more components of the customer-premises equipment; classifying, by the processing server, the extracted features with a first machine learning algorithm; and predicting, by the processing server, anomalies in one or more components of the customer-premises equipment with a second machine learning algorithm using the classified features from the first machine learning algorithm.

An example apparatus includes processor circuitry to: access first input data from meters, the meters to monitor media devices associated with a plurality of panelists, the first input data including media source data and panel data; reduce a dimensionality of the first input data to generate second input data of reduced dimensionality relative to the first input data, the dimensionality of the first input data to be reduced based on a prior probability of an audience rating associated with the plurality of panelists and an approximation of a dependency of the audience rating on at least one of the media source data and the panel data; and decode the second input data of reduced dimensionality to output a probability model parameter for a multivariate probability model, the multivariate probability model having dimensions corresponding to the first input data, the multivariate probability model to label census data.

Methods, apparatus, systems, and articles of manufacture are disclosed that improve short content identification in an audio stream through channel change detection and audio block realignment. Example instructions cause one or more processors to form a first audio block from an audio stream, detect whether the first audio block contains a channel change, the first audio block being one of a plurality of audio blocks the accessed audio, determine an offset of time from a beginning of the first audio block to when the channel change occurs in response to the channel change being detected in the first audio block, and create a new audio block aligned to start at the offset of time beyond the beginning of the first audio block using audio information from the audio stream, the new audio block to include a single channel of audio stream data.

Systems and methods are described for selecting content item identifiers for display. The system may identify a set of content items that are likely to be requested in the future based on a history of content item requests. The system then selects a first plurality of content categories using a category selection neural net and selects a first set of recommended content items for the first plurality of content categories. The system increases a reward score for the first plurality of content categories based on receiving a request for a content item that is included in the first set of recommended content items. The system also decreases the reward score for the first plurality of content categories based on determining that the requested content item is included in the set of content items that are likely to be requested in the future. The neural net is trained based on the reward score of the first plurality of content categories to reinforce reward score maximization. The trained neural net is the used to select content items for display.