Processing segments of closed-caption text using external sources
Particular embodiments provide supplemental content that may be related to video content that a user is watching. A segment of closed-caption text from closed-captions for the video content is determined. A first set of information from the segment of closed-caption text, such as terms may be extracted. Particular embodiments use an external source that can be determined from a set of external sources. To determine the supplemental content, particular embodiments may extract a second set of information from the external source. Because the external source may be more robust and include more text than the segment of closed-caption text, the second set of information may include terms that better represent the segment of closed-caption text. Particular embodiments thus use the second set of information to determine supplemental content for the video content, and can provide the supplemental content to a user watching the video content.
1. A method comprising:
in a closed-caption processor disposed in a broadcast communication system, and communicatively coupled via the broadcast communication system to a plurality of client devices:
receiving a set of external sources;
determining terms extracted from each of the set of external sources;
storing the terms for each of the set of external sources for use when the external source is selected; and
automatically determining a segment of closed-caption text from closed-captions provided in video content available for viewing at the client devices by users;
in the closed-caption processor, automatically selecting an external source from the set of external sources, the selecting based on a first set of information comprising a first set of terms extracted from the segment of closed-caption text, the external source including text not included in the segment of closed-caption text;
in the closed-caption processor, generating a second set of information comprising a second set of terms extracted from the external source;
in the closed-caption processor, determining supplemental content, the determining based on a result of a search using the second set of information; and
via the broadcast communication system, outputting the supplemental content, from the closed-caption processor to a client device associated with a user, as being relevant to the segment of closed-caption text, the outputting based on the user viewing the segment of closed-caption text;
wherein the supplemental content is outputted to the user while the video content corresponding to the segment of closed-caption text is being delivered to the user.
2. The method of claim 1 , further comprising:
determining a restriction based on the segment of closed-caption text; and
selecting a subset of external sources from the set of external sources based on the restriction, wherein selecting the external source is from the subset of external sources.
3. The method of claim 2 , wherein the restriction comprises one of a group consisting of a time associated with the video content, a time associated with the external source, a producer of the video content, a producer of the external source, a popularity of the video content, a popularity of the external source, an owner of the video content, an identity of the user, a genre of the external source, and a genre of the video content.
4. The method of claim 1 , wherein:
the first set of information is determined by extracting the first set of terms from the segment of closed-caption text, the first set of terms being extracted by a term extraction algorithm, and
generating the second set of information comprises extracting the second set of terms from the external source, the second set of terms being extracted by the term extraction algorithm.
5. The method of claim 4 , wherein the term extraction algorithm recognizes an additional term in the external source not found in the segment of closed-caption text based on analyzing the external source.
6. The method of claim 5 , wherein the first set of terms and the second set of terms comprise key terms or named entities determined by the term extraction algorithm.
7. The method of claim 1 , wherein the first set of information comprises all terms from the segment of closed-caption text.
8. A non-transitory computer-readable storage medium containing instructions that, when executed, control a closed-caption processor disposed in a broadcast communication system, and communicatively coupled via the broadcast communication system to a plurality of client devices, to be configured for:
automatically determining a segment of closed-caption text from closed-captions provided in video content available for viewing by users;
automatically selecting an external source from a set of external sources based on a first set of information comprising a first set of terms extracted from the segment of closed-caption text, the external source including text not included in the segment of closed-caption text, wherein selecting the external source comprises:
determining terms extracted from a first external source,
determining terms extracted from a second external source, and
determining which of the terms extracted from the first external source and the second external source is to be used as the second set of information based on a similarity of the terms extracted from the first external source and the second external source to the first set of information;
generating a second set of information comprising a second set of terms extracted from the external source;
determining supplemental content, the determining based on a result of a search using the second set of information; and
outputting the supplemental content, via the broadcast communication system, to a client device associated with a user, as being relevant to the segment of closed-caption text, the outputting based on the user viewing the segment of closed-caption text;
wherein the supplemental content is outputted to the user while the video content corresponding to the segment of closed-caption text is being delivered to the user.
9. A method comprising:
in a closed-caption processor disposed in a broadcast communication system, and communicatively coupled via the broadcast communication system to a plurality of client devices, automatically determining a segment of closed-caption text from closed-captions provided in video content available for viewing at the client devices by users;
in the closed-caption processor, automatically selecting an external source from a set of external sources, the selecting based on a first set of information comprising a first set of terms extracted from the segment of closed-caption text, the external source including text not included in the segment of closed-caption text, wherein selecting the external source comprises:
determining terms extracted from a first external source,
determining terms extracted from a second external source, and
determining which of the terms extracted from the first external source and the second external source is to be used as the second set of information based on a similarity of the terms extracted from the first external source and the second external source to the first set of information;
in the closed-caption processor, generating a second set of information comprising a second set of terms extracted from the external source;
in the closed-caption processor, determining supplemental content, the determining based on a result of a search using the second set of information; and
via the broadcast communication system, outputting the supplemental content, from the closed-caption processor to a client device associated with a user, as being relevant to the segment of closed-caption text, the outputting based on the user viewing the segment of closed-caption text;
wherein the supplemental content is outputted to the user while the video content corresponding to the segment of closed-caption text is being delivered to the user.
10. The method of claim 1 , wherein the segment of closed-caption text is received while the video content is being sent to the user.
11. The method of claim 1 , wherein determining the supplemental content comprises:
submitting the second set of information to a search engine to determine search results, wherein at least a portion of the search results are output as the supplemental content.
12. The method of claim 11 , wherein at least a portion of the first set of information is submitted to the search engine to determine the search results.
13. The method of claim 1 , wherein the supplemental content comprises an identifier or link to the external source.
14. The method of claim 1 , wherein the second set of information is used for generating a subsequent second set of information for a subsequent segment of closed-caption text.
15. The method of claim 1 , wherein the second set of information includes multimedia content extracted from video content of the external source.
16. The method of claim 1 , wherein the first set of information includes information extracted from the video content associated with the closed-caption text.
17. A non-transitory computer-readable storage medium containing instructions that, when executed, control a closed-caption processor disposed in a broadcast communication system, and communicatively coupled via the broadcast communication system to a plurality of client devices, to be configured for:
receiving a set of external sources;
determining terms extracted from each of the set of external sources;
storing the terms for each of the set of external sources for use when the external source is selected;
automatically determining a segment of closed-caption text from closed-captions provided in video content available for viewing by users;
automatically selecting an external source from the set of external sources based on a first set of information comprising a first set of terms extracted from the segment of closed-caption text, the external source including text not included in the segment of closed-caption text;
generating a second set of information comprising a second set of terms extracted from the external source;
determining supplemental content, the determining based on a result of a search using the second set of information; and
outputting the supplemental content, via the broadcast communication system, to a client device associated with a user, as being relevant to the segment of closed-caption text, the outputting based on the user viewing the segment of closed-caption text;
wherein the supplemental content is outputted to the user while the video content corresponding to the segment of closed-caption text is being delivered to the user.
18. The non-transitory computer-readable storage medium of claim 17 , further configured for:
determining a restriction based on the segment of closed-caption text; and
selecting a subset of external sources from the set of external sources based on the restriction, wherein selecting the external source is from the subset of external sources.
19. An apparatus comprising:
one or more closed-caption computer processors disposed in a broadcast communication system, and communicatively coupled via the broadcast communication system to a plurality of client devices; and
a non-transitory computer-readable storage medium comprising instructions that, when executed, control the one or more closed-caption computer processors to be configured for:
receiving a set of external sources;
determining terms extracted from each of the set of external sources;
storing the terms for each of the set of external sources for use when the external source is selected;
automatically determining a segment of closed-caption text from closed-captions provided in video content available for viewing by users;
automatically selecting an external source from the set of external sources based on a first set of information comprising a first set of terms extracted from the segment of closed-caption text, the external source including text not included in the segment of closed-caption text;
generating a second set of information comprising a second set of terms extracted from the external source;
determining supplemental content, the determining based on a result of a search using the second set of information; and
outputting the supplemental content, via the broadcast communication system, to a client device associated with a user, as being relevant to the segment of closed-caption text, the outputting based on the user viewing the segment of closed-caption text;
wherein the supplemental content is outputted to the user while the video content corresponding to the segment of closed-caption text is being delivered to the user.
20. An apparatus comprising:
one or more closed-caption computer processors disposed in a broadcast communication system, and communicatively coupled via the broadcast communication system to a plurality of client devices; and
a non-transitory computer-readable storage medium comprising instructions that, when executed, control the one or more closed-caption computer processors to be configured for:
automatically determining a segment of closed-caption text from closed-captions provided in video content available for viewing by users;
automatically selecting an external source from a set of external sources based on a first set of information comprising a first set of terms extracted from the segment of closed-caption text, the external source including text not included in the segment of closed-caption text, wherein selecting the external source comprises:
determining terms extracted from a first external source,
determining terms extracted from a second external source, and
determining which of the terms extracted from the first external source and the second external source is to be used as the second set of information based on a similarity of the terms extracted from the first external source and the second external source to the first set of information;
generating a second set of information comprising a second set of terms extracted from the external source;
determining supplemental content, the determining based on a result of a search using the second set of information; and
outputting the supplemental content, via the broadcast communication system, to a client device associated with a user, as being relevant to the segment of closed-caption text, the outputting based on the user viewing the segment of closed-caption text;
wherein the supplemental content is outputted to the user while the video content corresponding to the segment of closed-caption text is being delivered to the user.