Systems and methods for searching, identifying, scoring, and providing access to companion media assets for a primary media asset are disclosed. In response to a request for companion content, metadata within a predefined time period of a play position when the request was made, is downloaded. A dynamic search template that contains search parameters based on the downloaded metadata is generated. In response to the search conducted using the search template, a plurality of companion media assets are identified and then verified. A trust score for the companion media asset is accessed. The trust score may be analyzed and modified based on its contextual relationship to the play position of the primary media asset. If the trust score is within a rating range, then a link to access the companion media asset, or a specific segment or play position within the companion media asset, is provided.

A user of a storage system can upload files for a media asset, which can include a high quality media file and various related files. As part of the upload process, the storage system can extract metadata that describes the media asset. The user can specify one or more lifecycle policies to be applied for storage of the asset, and a rules engine can ensure the application of the one or more policies. The rules engine can also enable the use of simple media processing workflows. A filename hashing approach can be used to ensure that the segments and files for the asset are stored in a relatively random and even distribution across the partitions of the storage system. As part of the lifecycle for the asset, the high quality media file can be moved to less expensive storage once transcoding of the asset or another such action occurs.

In various embodiments, structured pages are dynamically generated based on user inputs. In response to a user input such as a query, a page generating engine ranks content items according to relevance to the user input in order to generate a list of the content items that is ordered based on the relevance. The page generating engine further maps the content items to collections of content items that can be displayed together in a page. Then, the page generating engine generates a structured page that includes a subset of the collections and associated content items that are assigned to collections within the subset of collections based on relevance and/or coherence criteria. Thereafter, the structured page is transmitted to a client device for display via user interface.

A method and apparatus for performing an integrated search is provided. An interface is provided that allows users to search and select any data related to a searchable term. Searchable terms may comprise titles of content, actors, and tags. Upon receiving results from the initial search, the user progresses through the initial search by selecting a result from the initial search and conducting a further search of that selection. The search may progress through many layers of searching in order to find information useful to the user and the user may perform actions based upon results of the search. The search implements a display with two columns, the first column displaying selectable data, and the second column displaying results to the selected data. The search is further customizable based upon a privacy level selected by the user.

A system, computer readable storage medium, and computer-implemented method presents video search results responsive to a user keyword query. The video hosting system uses a machine learning process to learn a feature-keyword model associating features of media content from a labeled training dataset with keywords descriptive of their content. The system uses the learned model to provide video search results relevant to a keyword query based on features found in the videos. Furthermore, the system determines and presents one or more thumbnail images representative of the video using the learned model.

Technologies are provided for automated quality assessment of translations. In some embodiments, quality of a translation can be assessed by generating a machine-learning (ML) model that classifies the translation as pertaining to one of three quality categories. A first quality category can include, for example, translations that are deemed satisfactory. A second quality category can include, for example, translations that are deemed subject to edition prior to being deemed satisfactory. A third quality category can include, for example, translations that are deemed unsatisfactory. The generated ML model can then be applied to the translation and a corresponding sentence in a source language in order to classify the translation as pertaining to one of the three categories.

A method and a device for viewing a conference are provided. In the method, after a wide-view video of a specific conference, related conference event data, and speech content of each participant are obtained, a highlight video of the specific conference is correspondingly generated. Accordingly, the efficiency of conference viewing is improved.

Embodiments of the present invention relate to methods, systems, and computer program products for managing a plurality of live comments. A plurality of live comments is obtained for a video, the plurality of live comments being associated with a plurality of fragments in the video, respectively. A plurality of features are extracted from the plurality of live comments, respectively. A knowledge base is generated for the plurality of live comments based on the plurality of features. With these embodiments, the live comments may be managed in an effective way. Further, the knowledge base may provide answers to a user query.

Aspects of the subject disclosure may include, for example, a device including a processing system including a processor; and a memory that stores executable instructions that, when executed by the processing system, facilitate performance of operations of identifying a user of the device; sending a record of content downloaded from a content provider by the device to a distributed virtual agent; and receiving an advertisement via the content provider, wherein the advertisement is selected by an ad fulfillment service responsive to information provided by the distributed virtual agent. Other embodiments are disclosed.

Systems and methods for generating media program keywords based on a video-hosting website are disclosed herein. Control circuitry identifies, on the video-hosting website, video content items that include at least a portion of a media program. The media program has a media program identifier and the video content items have respective titles, each including one or more terms. The control circuitry identifies a term included in more than one of the titles and identifies a group of the video content items that have the term included in their title. Based on the video-hosting website, the control circuitry determines a cumulative number of rankings of the video content items within the group and generates a relevance score for the term based on the cumulative number of rankings. The control circuitry stores the term and the relevance score in a keyword database in association with the media program identifier.