Processing content based on natural language queries
Disclosed are systems and methods for summarizing content or preparing missed portions of content based on natural language queries. A natural language query can be received. One or more portions of summarized or missed content can be determined based on the natural language query, and transmitted to a user device.
1. A method comprising:
receiving a natural language query associated with output of content by a computing device;
determining, based on the natural language query, a portion of the content responsive to the natural language query;
determining, based on metadata satisfying a threshold, a summary of the portion of the content, wherein the metadata is associated with the portion of the content; and
sending, to the computing device, the summary of the portion of the content.
2. The method of claim 1 , further comprising selecting, based on the metadata associated with the content, the summary of the portion of the content from a plurality of summaries.
3. The method of claim 1 , wherein the metadata associated with the content comprises an indicator of a significance of the summary, wherein the indicator of the significance of the summary satisfies the threshold.
4. The method of claim 1 , wherein the metadata associated with the content comprises an indicator of a relevance of the summary to the content based on the natural language query, wherein the indicator of the relevance of the summary satisfies the threshold.
5. The method of claim 1 , wherein receiving the natural language query comprises receiving the natural language query while the content is being output by the computing device.
6. The method of claim 1 , further comprising determining, based on the natural language query being indicative of a character or an event, a start time of the portion of the content.
7. The method of claim 6 , wherein sending the summary of the portion of the content comprises:
causing playback of the content on the computing device to stop;
sending, to the computing device, the summary of the portion of the content; and
causing the playback of the content on the computing device to resume.
8. The method of claim 1 , wherein the summary is based on a time code associated with the natural language query.
9. The method of claim 1 , further comprising determining, based on the natural language query, a duration for the summary of the portion of the content.
10. The method of claim 1 , wherein the natural language query is based on audio data.
11. A method comprising:
receiving a natural language query associated with output of content by a computing device;
determining, based on the natural language query and the content, a summary of at least a portion of the content; and
sending, to the computing device and based on metadata, associated with the content, indicating that the summary is significant, the summary.
12. The method of claim 11 , further comprising selecting, based on the metadata associated with the content, the summary from a plurality of summaries.
13. The method of claim 11 , wherein the metadata associated with the content is indicative of a significance of the summary and wherein the significance of the summary satisfies a threshold indicating that the summary is significant.
14. The method of claim 11 , wherein the natural language query is associated with the content being output by the computing device.
15. The method of claim 11 , further comprising determining, based on the natural language query being indicative of a character or an event, a start time of a first portion of the content.
16. An apparatus comprising:
one or more processors; and
a memory storing processor-executable instructions that, when executed by the one or more processors, cause the apparatus to:
receive a natural language query associated with output of content by a computing device;
determine, based on the natural language query, a portion of the content responsive to the natural language query;
determine, based on metadata, associated the portion of the content, satisfying a threshold, a summary of the portion of the content; and
send, to the computing device, the summary of the portion of the content.
17. The apparatus of claim 16 , wherein the processor-executable instructions, when executed by the one or more processors, further cause the apparatus to select, based on the metadata associated with the content, the summary from a plurality of summaries.
18. The apparatus of claim 16 , wherein the metadata associated with the content comprises an indicator of a significance of the summary, wherein the indicator of the significance of the summary satisfies the threshold.
19. The apparatus of claim 16 , wherein the metadata associated with the content comprises an indicator of a relevance of the summary to the content based on the natural language query, wherein the indicator of the relevance of the summary satisfies the threshold.
20. The apparatus of claim 16 , wherein the processor-executable instructions that, when executed by the one or more processors, cause the apparatus to receive the natural language query, cause the apparatus to receive the natural language query while the content is being output by the computing device.
21. The apparatus of claim 16 , wherein the processor-executable instructions, when executed by the one or more processors, further cause the apparatus to determine, based on the natural language query being indicative of a character or an event, a start time of the portion of the content.
22. The apparatus of claim 21 , wherein the processor-executable instructions that, when executed by the one or more processors, cause the apparatus to send the summary of the portion of the content, cause the apparatus to:
cause playback of the content on the computing device to stop;
send, to the computing device, the summary of the portion of the content; and
cause the playback of the content on the computing device to resume.
23. The apparatus of claim 16 , wherein the summary is based on a time code associated with the natural language query.
24. The apparatus of claim 16 , wherein the processor-executable instructions, when executed by the one or more processors, further cause the apparatus to determine, based on the natural language query, a duration for the summary of the portion of the content.
25. The apparatus of claim 16 , wherein the natural language query is based on a voice query.