A system and method for dynamically training a system to determine an age rating for media content. An exemplary method includes obtaining age rating data for a plurality of territories; determining, based on the age rating data, a similarity vector relating to the target territory; determining, for the similarity vector, a territory associated with a highest prediction score; in response to determining that the territory associated with the highest prediction score is not the source territory, generating a training dataset comprising the age rating data for the target territory, the source territory, and the territory associated with the highest prediction score; and executing a machine learning model, trained by the training dataset, to output an age rating for a content item in the target territory based on an age rating for the content item in the source territory.

Disclosed herein are systems, methods, and computer-readable storage media for generating a speech recognition model for a media content retrieval system. The method causes a computing device to retrieve information describing media available in a media content retrieval system, construct a graph that models how the media are interconnected based on the retrieved information, rank the information describing the media based on the graph, and generate a speech recognition model based on the ranked information. The information can be a list of actors, directors, composers, titles, and/or locations. The graph that models how the media are interconnected can further model pieces of common information between two or more media. The method can further cause the computing device to weight the graph based on the retrieved information, wherein the weighted graph is further normalized to yield a normalized weighted graph to help with speech query searching of media content using speech recognition. The graph can further model relative popularity information in the list. The method can rank information based on a PageRank algorithm.

An example method performed by a processing system includes receiving a request from a user, wherein the request identifies a plurality of items of source content, and wherein the request indicates that the user would like to generate synthesized content from the plurality of items of source content, retrieving, by the processing system, a plurality of sets of permissions, wherein each set of permissions of the plurality of sets of permissions is associated with one item of source content of the plurality of items of source content, determining, by the processing system, whether the request can be satisfied, based on the plurality of sets of permissions, and automatically generating, by the processing system, the synthesized content using the plurality of items of source content, when the request can be satisfied based on the plurality of sets of permissions.

In various embodiments, a training application generates a perceptual video model. The training application computes a first feature value for a first feature included in a feature vector based on a first color component associated with a first reconstructed training video. The training application also computes a second feature value for a second feature included in the feature vector based on a first brightness component associated with the first reconstructed training video. Subsequently, the training application performs one or more machine learning operations based on the first feature value, the second feature value, and a first subjective quality score for the first reconstructed training video to generate a trained perceptual quality model. The trained perceptual quality model maps a feature value vector for the feature vector to a perceptual quality score.

The application relates to a video recommendation method and device, and a computer readable storage medium. The video recommendation method comprises: obtaining a user feature of a sample user and a video feature of a sample video; learning a click rate, a like rate, and a follow rate on the basis of a full-connection neural network algorithm to obtain trained user feature and video feature; performing, according to the trained user feature and video feature, combined learning on the click rate, the like rate, and the follow rate on a user side neural network and a video side neural network; and obtaining a video recommendation list according to a network parameter of a neural network algorithm obtained by means of combined learning. According to the video recommendation method, by adding a full-connection neural network algorithm training phase, the trained user feature and video feature are obtained.

A system can include a memory to store machine readable instructions. The system can also include a processing unit to access the memory and execute the machine readable instructions. The machine readable instructions can include a scheduling agent that can determine a download time for selected media content from a content provider. The download time can be based on a viewing time and a monitored network usage pattern over an extended period of time at the system.

Providing enhanced video content includes processing at least one video feed through at least one spatiotemporal pattern recognition algorithm that uses machine learning to develop an understanding of a plurality of events and to determine at least one event type for each of the plurality of events. The event type includes an entry in a relationship library detailing a relationship between two visible features. Extracting and indexing a plurality of video cuts from the video feed is performed based on the at least one event type determined by the understanding that corresponds to an event in the plurality of events detectable in the video cuts. Lastly, automatically and under computer control, an enhanced video content data structure is generated using the extracted plurality of video cuts based on the indexing of the extracted plurality of video cuts.

The present disclosure relates to limiting viewing of media content. More particularly, the present invention relates to classifying segments of content for limited viewing based on user preferences and classifications.

According to a first aspect, there is provided a method for parental control of media content for a media guidance application, the method comprising, determining user preferences comprising settings for restricting viewing of segments of media content, determining media content for user consumption on a user device, determining a classification of each of a plurality of segments of the media content using a content analyzer and classifier, and comparing the determined classifications against the user preferences. In response to the comparing, the method further comprises the steps of, determining an action associated with the determined classification for restricting viewing of one or more of the plurality of segments of the media asset and modifying the one or more of the plurality of segments based on the determined action.

Systems, methods, and non-transitory computer-readable media can detect a trigger to generate a set of media content items associated with at least one of a particular media content item or a user viewing the particular media content item. A plurality of content generators can be utilized to generate a plurality of subsets of media content items. Each of the plurality of content generators can identify a respective subset out of the plurality of subsets of media content items based on at least one of information associated with the particular media content item or information associated with the user viewing the particular media content item. At least some media content items in at least some of the plurality of subsets of media content items can be ranked based on respective information associated with each media content item.

Various embodiments describe methods, systems, and devices for delivering secondary video content are disclosed. Exemplary implementations may perform, at a processor of a computing device, an active video semantic analysis on a segment of a first video content presented on a viewing device. The active video semantic analysis may identify an active video first visible element visible within the segment. Also, a secondary video content, that is not directly related to the first video content, may be matched based on a prior semantic analysis on the secondary video content that identified a secondary-video first visible element therein that is associated with the active video first visible element from the segment. In addition, the secondary video content may be presented on the viewing device immediately after the segment.