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 video tag determination method, a terminal, and a storage medium are provided, belonging to the technical field of computers. The method includes: extracting time-sequence feature information between first target frame images in a video, the time-sequence feature information being information determined based on the feature differences of the first target frame images at different time points; generating, based on to the time-sequence feature information, a dynamic event description text for describing a dynamic event corresponding to the video; and determining, based on the dynamic-event description text, a video tag of the video.

The disclosure provides a method for processing a video, an electronic device, and a computer storage medium. The method includes: determining a plurality of first identifiers related to a first object based on a plurality of frames including the first object in a target video; determining a plurality of attribute values associated with the plurality of first identifiers based on a knowledge base related to the first object; determining a set of frames from the plurality of frames, in which one or more attribute values associated with one or more first identifiers determined from each one of the set of frames are predetermined values; and splitting the target video into a plurality of video clips based on positions of the set of frames in the plurality of frames.

Technologies are provided for insertion of directed content into video assets based on analysis of audio data corresponding to the video assets. Some embodiments include a computing system that can receive audio data corresponding to a video asset. The computing system can generate, using the audio data, a time series of tags corresponding to speech conveyed by the video asset. The computing system can then generate a time-asset mapping between time and directed content using the time series and a correlation policy. The directed content can include digital media intended for a defined audience, for example. The time-asset mapping associates groups of directed content assets to respective specific times in the time series. The computing system can insert, using the mapping, a defined directed content asset from a group of directed content assets identified in the mapping.

A method of processing data, a device, and a medium are provided, which relate to a field of an artificial intelligence technology, in particular to fields of computer vision, natural language technology, speech technology, deep learning and knowledge graph. The method of processing data includes: generating a video feature, a question feature and an answer feature based on acquired video data, acquired question data and acquired candidate answer data; determining a link relationship between the video feature, the question feature and the answer feature; and determining a matching result for the video data, the question data and the candidate answer data based on the link relationship.

Techniques for using contextual information relating to content presented by a television as part of a search query for an information search are presented. A search management component, at a given moment in time during presentation of television-related content by a communication device in or associated with a television, identifies contextual information associated with a section of the television-related content and generates a content identifier timestamp associated with the contextual information and the section of television-related content. A search component augments a search query using the contextual information to facilitate customization of a subset of search results based on the contextual information. The contextual information in the search query can facilitate disambiguating the search query or promoting a search result over another search result in the subset of search results, based on the contextual information, to facilitate customization of the subset of search results.

Systems and methods are provided to record portions of media assets. User request is received to record a media asset together with a criterion for recording portions of that media asset. A content recognition algorithm is executed against segments of the media asset to determine a set of keywords associated with those segments. Separately a set of keywords associated with the criterion is generated. Sets of keywords are compared and segments that match the criterion are discovered. If it is determined that a first segment and third segment each match the criterion and a second segment does not, a delete indicator is added to the second segment and the third and first segments are compared. If those segments match the delete indicator is removed from the second segment.

Provided are a voice packet recommendation method and apparatus, a device and a storage medium. The method includes selecting at least one target display video for a user from among candidate display videos associated with voice packets and using voice packets to which the at least one target display video belongs as candidate voice packets; selecting a target voice packet for the user from among the candidate voice packets according to attribute information of the candidate voice packets and attribute information of the at least one target display video; and recommending the target voice packet to the user.

In various examples, natural language processing may be performed on text generated by a game to extract one or more in-game events from the game. The system (e.g., a client device and/or server) may receive the text in the form of one or more strings generated by a game application. The system may then extract one or more in-game events from the text using natural language processing. The game may include the text in a message it sends to the system (e.g., using an Application Programming Interface (API)) and/or in a game log entry or notification. The text may be generated based at least on the game determining one or more conditions are satisfied in the gameplay (e.g., victory, points scored, milestones, eliminations, item acquisition, etc.). The text may be mapped to event templates, which may then be used to extract parameters of events therefrom.

We describe offline links to online digital assets. The offline links can be in hardcopy text. A link can be in a format like [BBQ Ribs], where there is a starting delimiter (eg “[”) and a closing delimiter (“]”). We call this a “linket”. A user has a mobile device with a camera. She scans a linket in hardcopy she is reading. Her device converts this to digital form and sends to a server. The server maps the linket to an URL or other electronic data. The linket acts as a brand, akin to a domain name.