Methods, systems, and computer program products for categorizing/rating content uploaded to a network for broadcasting

Patent metadata

Field	Value
Publication number	US-2016234569-A1
Application number	US-201615130578-A
Country	US
Kind code	A1
Filing date	Apr 15, 2016
Priority date	Jan 5, 2007
Publication date	Aug 11, 2016
Grant date	—

Abstract

Methods, systems, and computer program products that automatically categorize and/or assign ratings to content (video and audio content) uploaded by individuals who want to broadcast the content to others via a communications network, such as an IPTV network, are provided. When an individual uploads content to a network, a network service automatically extracts an audio stream from the uploaded content. Words in the extracted audio stream are identified. For each identified word, a preexisting library of selected words is queried to determine if a match exists between words in the library and words in the extracted audio stream. The selected words in the library are associated with a particular content category or content rating. If a match exists between an identified word and a word in the library, the uploaded content is assigned a content category and/or rating associated with the matched word.

First claim

What is claimed is:

1 . A device, comprising:
a processor; and a memory that stores executable instructions that, when executed by the processor, facilitate performance of operations, comprising:
obtaining an audio stream from uploaded content to obtain an extracted audio stream;
identifying non-speech sounds in the audio stream as identified non-speech sounds;
performing pattern recognition for the identified non-speech sounds;
querying non-speech sound patterns stored within a library to detect a match between identified non-speech sounds in the extracted audio stream and non-speech sound patterns stored within the library, wherein the library stores a plurality of non-speech sounds, wherein the library is provided by a communications network, and wherein each non-speech sounds of the plurality of non-speech sounds stored in the library has a content category assigned thereto;
assigning a content category to the uploaded content in accordance with a match between the identified non-speech sounds and the non-speech sound patterns stored within the library as an assigned non-speech sound content category; and
embedding the assigned non-speech sound content category within metadata associated with the uploaded content.

2 . The device of claim 1 , wherein the operations further comprise identifying words within the extracted audio stream, wherein the library stores a plurality of words, and wherein each word of the plurality of words stored in the library has a content category assigned thereto.

3 . The device of claim 2 , wherein the operations further comprise querying words stored within the library to determine whether a match exists between identified words in the extracted audio stream and words stored within the library.

4 . The device of claim 3 , wherein the operations further comprise assigning a content category to the uploaded content in accordance with a match between the identified words and the words stored within the library as an assigned word content category.

5 . The device of claim 2 , wherein an identified word is associated with offensive material, and wherein the operations further comprise assigning a content rating that identifies that the content may contain offensive material.

6 . The device of claim 5 , wherein the identified word include musical lyrics, and wherein the audio stream comprises metadata including a digital music file encoded with the musical lyrics.

7 . The device of claim 5 , wherein the operations further comprise generating a notification that human intervention is required for assigning the content rating.

8 . The device of claim 1 , wherein the memory comprises one of an audio stream extraction application, a text conversion application, a library querying application, and a category assignment application for execution by the processor.

9 . The device of claim 1 , wherein the operations further comprise selecting an advertisement for insertion within the content.

10 . A network service, comprising:
a library of a plurality of selected words and non-speech sounds indicative of a category of content, each word being associated with a particular a content rating; at least one processor; and a memory that stores executable instructions that, when executed by the at least one processor, facilitate performance of operations, comprising:
obtaining an audio stream from content uploaded to a communications network to obtain an extracted audio stream;
identifying non-speech sounds in the extracted audio stream as identified non-speech sounds;
performing pattern recognition for the identified non-speech sounds;
detecting a match between identified non-speech sounds and non-speech sound patterns stored in the library; and
assigning a content rating to the content in accordance with a match between the identified non-speech sounds and the non-speech sounds stored in the library.

11 . The network service of claim 10 , wherein the communications network comprises an interactive television network, and wherein the content is uploaded to the network via a user device.

12 . The network service of claim 11 , wherein the operations further comprise providing a web interface accessed by the user device, and wherein the content is uploaded via the web interface.

13 . The network service of claim 10 , wherein the operations further comprise:
identifying words in the extracted audio stream as identified words, wherein the words in the extracted audio stream include musical lyrics provided in metadata of the extracted audio stream; and querying the library to determine whether a match exists between the identified words in the extracted audio stream and the plurality of selected words stored in the library.

14 . The network service of claim 13 , wherein the operations further comprise assigning a content rating to the content in accordance with a match between the identified words and the plurality of selected words stored in the library.

15 . The network service of claim 14 , wherein the operations further comprise embedding the content rating within metadata associated with the content, wherein the metadata comprises a digital music file encoded with lyrics, and wherein the content rating comprises a music rating.

16 . A method, comprising:
obtaining, by a server comprising a processor, an audio stream from content uploaded to a communications network via a web interface; identifying non-speech sounds in the audio stream as identified non-speech sounds; detecting, by the server, a match between the identified non-speech sounds and non-speech sound patterns in a library, wherein the library stores a plurality of words and a plurality of non-speech sounds, and wherein the library is provided by a network service operating on the communications network; and querying, by the server, a library indicative of a category of content and non-speech sounds, each word being associated with a particular content category, to determine whether a match exists between identified non-speech sounds in the audio stream and the non-speech sounds in the library.

17 . The method of claim 16 , further comprising identifying words in the audio stream as identified words, wherein the words in the audio stream include musical lyrics provided in metadata of the audio stream, and wherein the library further includes words.

18 . The method of claim 17 , wherein the operations further comprise:
detecting a match between the identified words and the words included in the library; and assigning, a content category to the content in accordance with a match between the identified words and the words included in the library as an assigned content category.

19 . The method of claim 18 , further comprising:
extracting words from lyrics associated with music in the audio stream; and assigning a content rating to the music based on the lyrics, wherein the content rating comprises a music rating.

20 . The method of claim 18 , further comprising embedding the assigned content category within metadata associated with the content.

Assignees

• At & T Ip I Lp

Inventors

• Yu Ke

Classifications

• G10L15/1815 Primary

  Semantic context, e.g. disambiguation of the recognition hypotheses based on word meaning · CPC title

• H04N21/233

  Processing of audio elementary streams {(monitoring, identification or recognition of audio in broadcast systems H04H60/58)} · CPC title

• H04N21/23418

  involving operations for analysing video streams, e.g. detecting features or characteristics (television picture signal circuitry for scene change detection H04N5/147; filtering for image enhancement G06T5/00; methods or arrangements for recognising scenes G06V20/00; arrangements characterised by components specially adapted for monitoring, identification or recognition of video in broadcast systems H04H60/59) · CPC title

• H04N21/26603

  for automatically generating descriptors from content, e.g. when it is not made available by its provider, using content analysis techniques · CPC title

• G06F16/60

  of audio data · CPC title