Systems and methods for generating a media-based result to an ambiguous query

1. A method for providing a search result based on an ambiguous voice query, comprising:

receiving an ambiguous voice query relating to an object from a user;

parsing the ambiguous voice query to determine a term;

determine whether the term matches a trending topic in a plurality of trending topics;

in response to determining that the term does not match the trending topic, identifying a first node representing the term on a knowledge graph;

searching, starting from the first node on the knowledge graph, for a second node representing media asset related information;

determining a distance between the first node and the second node;

comparing the distance between the first node and the second node with a pre-defined threshold;

in response to determining that the distance is below the pre-defined threshold:

identifying a media asset relating to the media asset related information from the second node; and

providing, in response to the ambiguous voice query, results including the media asset.

2. The method of claim 1 , further comprising:

wherein the trending topic is used to identify results to be provided in response to the ambiguous voice query.

3. The method of 2 , further comprising:

determining whether the term corresponds to one or more previously viewed media assets in a list of assets previously viewed by the user;

wherein searching the social media network for the trending topic is performed in response to determining that the term does not correspond to the one or more previously viewed media assets.

4. The method of 3 , wherein determining whether the term corresponds to one or more previously viewed media assets in a list of assets previously viewed by the user comprises:

retrieving a viewing history of the user; and

identifying a media asset that the user has viewed based on the viewing history.

5. The method of 4 , further comprising:

generating a plurality of video frames from the identified media asset; and

determining whether one of the pluralities of video frames contains the object indicated in the ambiguous voice query.

6. The method of 5 , further comprising:

in response to determining that at least one video frame contains the object:

determining a media asset segment containing the at least one video frame from the media asset;

obtaining information relating to the object and the media asset segment based at least in part on metadata corresponding to the media asset segment; and

generating for display, the media asset segment containing the at least one video frame and information relating to the object.

7. The method of 6 , wherein determining a media asset segment containing the at least one video frame from the media asset further comprises:

searching the media asset for a first video frame that contains the object; and

determining a starting playback position corresponding to the first video frame.

8. The method of 7 , further comprising:

searching for a second video frame that is a last instance in which the object appears since the starting playback position; and

determining an ending playback position corresponding to the second video frame.

9. A system comprising:

input/output circuitry configured to generate a user input interface configured to receive a query relating to an object from a user; and

control circuitry configured to:

receive an ambiguous voice query relating to an object from a user;

parse the ambiguous voice query to determine a term;

determine whether the term matches a trending topic in a plurality of trending topics;

in response to determining that the term does not match the trending topic, identify a first node representing the term on a knowledge graph;

search, starting from the first node on the knowledge graph, for a second node representing media asset related information;

determine a distance between the first node and the second node;

compare the distance between the first node and the second node with a pre-defined threshold;

in response to determining that the distance is below the pre-defined threshold:

identify a media asset relating to the media asset related information from the second node; and

providing, in response to the ambiguous voice query, results including the media asset.

10. The system of claim 9 , wherein the control circuitry is further configured to:

wherein the trending topic is used to identify results to be provided in response to the ambiguous voice query.

11. The system of claim 10 , wherein the control circuitry is further configured to:

determine whether the term corresponds to one or more previously viewed media assets in a list of assets previously viewed by the user;

wherein searching the social media network for the trending topic is performed in response to determining that the term does not correspond to the one or more previously viewed media assets.

12. The system of claim 11 ,

wherein determining whether the term corresponds to one or more previously viewed media assets in a list of assets previously viewed by the user comprises configuring the control circuitry to:

retrieve a viewing history of the user; and

identify a media asset that the user has viewed based on the viewing history.

13. The system of claim 12 , wherein the control circuitry is further configured to:

generate a plurality of video frames from the identified media asset; and

determine whether one of the pluralities of video frames contains the object indicated in the ambiguous voice query.

14. The system of claim 13 , wherein the control circuitry is further configured to:

in response to determining that at least one video frame contains the object:

determine a media asset segment containing the at least one video frame from the media asset;

obtain information relating to the object and the media asset segment based at least in part on metadata corresponding to the media asset segment; and

generate for display, the media asset segment containing the at least one video frame and information relating to the object.

15. The system of claim 14 , wherein determining a media asset segment containing the at least one video frame from the media asset further comprises:

searching the media asset, for a first video frame that contains the object; and

determining a starting playback position corresponding to the first video frame.

16. The system of claim 15 , wherein the control circuitry is further configured to:

search, for a second video frame that is a last instance in which the object appears since the starting playback position; and

determine an ending playback position corresponding to the second video frame.

17. A non-transitory machine-readable medium comprising non-transitory machine-readable instruction encoded thereon for providing a search result based on an ambiguous voice query, the instructions comprising:

instructions for parsing the ambiguous voice query to determine a term;

instructions for determining whether the term matches a trending topic in a plurality of trending topics;

instructions for, in response to determining that the term does not match the trending topic, identifying a first node representing the term on a knowledge graph;

instructions for searching, starting from the first node on the knowledge graph, for a second node representing media asset related information;

instructions for determining a distance between the first node and the second node;

instructions for comparing the distance between the first node and the second node with a pre-defined threshold;

in response to determining that the distance is below the pre-defined threshold:

instructions for identifying a media asset relating to the media asset related information from the second node; and

instructions for providing, in response to the ambiguous voice query, results including the media asset.

18. The non-transitory machine-readable medium of claim 17 , wherein the instructions further comprise:

wherein the trending topic is used to identify results to be provided in response to the ambiguous voice query.

19. The non-transitory machine-readable medium of claim 18 , wherein the instructions further comprise:

instructions for determining whether the term corresponds to one or more previously viewed media assets in a list of assets previously viewed by the user;

wherein searching the social media network for the trending topic is performed in response to determining that the term does not correspond to the one or more previously viewed media assets.

20. The non-transitory machine-readable medium of claim 19 , wherein the instructions for determining whether the term corresponds to one or more previously viewed media assets in a list of assets previously viewed by the user comprises:

instructions for retrieving a viewing history of the user; and

instructions for identifying a media asset that the user has viewed based on the viewing history.