scispace - formally typeset
Patent

Self-learning methods, entity relations, remote control, and other features for real-time processing, storage, indexing, and delivery of segmented video

Reads0
Chats0
TLDR
In this article, a self-learning system is used to discover topics that broadly describe the incoming data in real-time, and these topics can be used to gather and store metadata from various metadata sources such as social networks.
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.

read more

Citations
More filters
Patent

Self-learning statistical natural language processing for automatic production of virtual personal assistants

TL;DR: In this paper, a computing device has a semantic compiler to generate a semantic model based on a corpus of sample requests, and the semantic compiler may generate the semantic model by extracting contextual semantic features or processing ontologies.
Patent

Method and system for conducting an opinion search engine and a display thereof

TL;DR: In this paper, an opinion search engine serves as the backbone in complex data crunching of thousands or millions of electronic social media messages which detect, extract, compute, and correlate both unstructured textual data and structured textual data.
Patent

Clarifying audible verbal information in video content

TL;DR: In this paper, a server receives a user request to clarify audible verbal information associated with a media content item playing in proximity to a client device, where the user request includes an audio sample of the media content items and a user query, and the audio sample corresponds to a portion of the content item proximate in time to the user query.
Patent

Displaying information related to content playing on a device

TL;DR: In this article, a computer-implemented method was proposed to detect whether a user is watching media content, and after detecting that the user was watching media, presented on a user device a first affordance providing a first user-selectable election to receive information on entities relevant to the media content; in response to user selection of the election, displaying on the user device information on a respective entity relevant to media content.
Patent

Event pop-ups for video selection

TL;DR: In this paper, a computer program product for notifying a viewer of content relevant to the viewer's interests is provided, where a computer identifies an identity of a viewer, wherein the display device is displaying a first video feed.
References
More filters
Patent

Multimedia content filtering

TL;DR: In this paper, a latent semantic mapping (LSM) filter is used to classify multimedia content into two categories based on the one or more parameters of the multimedia content and then the tag is input into the LSM filter.
Patent

Time ordered indexing of audio data

TL;DR: In this paper, attributes including one or more types of accents and human languages from an audio information stream are encoded into a time ordered index, and different human language models are compared at approximately the same time to generate an integrated time-ordered index.
Patent

Method for making digital documents browseable

TL;DR: In this paper, a method for making one or more digital documents browseable was proposed, in which the digital documents were automatically, topically segmented into one-or more topical segments.
Patent

Internet search-based television

TL;DR: In this paper, the best features of both Internet video search and television-type viewing experience have been combined to enable the user to search for and view Internet video content in a television-like experience.
Patent

Methods and apparatus for conversational advertising

TL;DR: In this paper, the authors present methods and apparatus, including computer program products, implementing and using techniques for conversational advertising Relevant commentary data associated with an electronic advertisement can be identified on one or more electronic forums accessible over the data network The identified commentary data can be filtered according to one or multiple parameters including commentary content, conversation volume, a designated timeframe, a topic, a tag, a keyword, an index, a link, a classification scheme, an authonty, a relevance measure, a meme, a word, a phrase, and/or a ranking.