Abstract: Self-learning systems process incoming data from sources such broadcast, cable, or IP-driven television and can discover topics that broadly describe the incoming data in real-time. These topics can be used to gather and store metadata from various metadata sources such as social networks. Using the metadata, content delivery systems working in parallel with the self-learning systems can deliver highly contextualized supplementary content to client applications, such as mobile devices used as “second screen” devices.

Abstract: In some embodiments, a method for capturing live video content comprises capturing video signals in a video capture server connected to a video source; receiving the captured video signals from the video capture server in an initial processing server; processing the captured video signals in the initial processing server to provide at least video files for storage and text files associated with the captured video signals; receiving the associated text files in a topic extraction server in communication with the initial processing server and performing contextual topic extracting and processing to provide additional searchable contextual information; and storing the searchable contextual information and placing this information, along with the original text files in a searchable database archive, the stored information being associated with the stored video files.

Abstract: Disclosed embodiment providing for the capture of video content. The video content is segmented in real-time into clips by topic, and those clips are delivered as customized queues of video items relevant to the consumer according to their interests as aggregated from their social graph data and manual entry.

Abstract: Disclosed embodiment providing for the capture of video content. The video content is segmented in real-time into clips by topic, and those clips are delivered as customized queues of video items relevant to the consumer according to their interests as aggregated from their social graph data and manual entry.

Abstract: Disclosed embodiment providing for the capture of video content. The video content is segmented in real-time into clips by topic, and those clips are delivered as customized queues of video items relevant to the consumer according to their interests as aggregated from their social graph data and manual entry.

Abstract: Self-learning systems process incoming data from sources such broadcast, cable, or IP-driven television and can discover topics that broadly describe the incoming data in real-time. These topics can be used to gather and store metadata from various metadata sources such as social networks. Using the metadata, content delivery systems working in parallel with the self-learning systems can deliver highly contextualized supplementary content to client applications, such as mobile devices used as “second screen” devices.

Abstract: Self-learning systems process data in real-time and output the processed data to client applications in an effective manner. They comprise a capture platform that captures data and generates a stream of text, a text decoding server that extracts individual words from the stream of text, an entity extractor that identifies entities, a trending engine that outputs trending results, and a live queue broker that filters the trending results. The self-learning systems provide more efficient realization of Boxfish technologies, and provide or work in conjunction with real-time processing, storage, indexing, and delivery of segmented video. Furthermore, the self-learning systems efficiently perform entity relationing by creating entity network graphs, and are operable to identify advertisements from the data.

Abstract: Disclosed embodiment providing for the capture of video content. The video content is segmented in real-time into clips by topic, and those clips are delivered as customized queues of video items relevant to the consumer according to their interests as aggregated from their social graph data and manual entry.