Augmented display from conversational monitoring

1. A method for generating for display an indication of a segment of media content relevant to a voice communication, the method comprising:

receiving a plurality of words spoken by a first user at a communication device during the voice communication with a second user;

determining, based on comparing the plurality of words with a plurality of keywords indicating that media content is being described, that the first user is describing a media content; and

in response to determining that the first user is describing the media content:

retrieving metadata for each of a plurality of media assets that the first user previously consumed;

determining, based on comparing the metadata of each media asset in the plurality of media assets that the first user has previously consumed with the plurality of words, a media asset that the first user is describing;

retrieving metadata for each of a plurality of segments of the media asset that the first user is describing;

determining, based on the metadata for each of the plurality of segments and the plurality of words, the segment of the media asset that the first user is describing; and

generating, for display to the second user, the indication of the segment.

2. The method of claim 1 , wherein comparing the plurality of words with the plurality of keywords comprises:

selecting a first word of the plurality of words;

determining, based on comparing the first word of the plurality of words with each keyword of the plurality of keywords, whether the first word matches any of the plurality of keywords; and

in response to determining that the first word matches a keyword from the plurality of keywords, updating a word matching score.

3. The method of claim 2 , wherein determining, based on comparing the plurality of words with the plurality of keywords, that the first user is describing the media content comprises:

determining whether the word matching score is greater than a threshold value; and

in response to determining that the word matching score is greater than the threshold value, determining that the first user is describing the media content.

4. The method of claim 2 , wherein updating the word matching score comprises:

retrieving a weight associated with the keyword; and

updating the word matching score with the weight associated with the keyword.

5. The method of claim 1 , wherein retrieving the metadata for each of the plurality of media assets that the first user previously consumed comprises:

transmitting, to a profile server, a request for media asset viewing history of the first user, wherein the request comprises an identifier of the first user;

receiving, in response to the request for the media asset viewing history, a plurality of media asset identifiers, wherein each of the plurality of media asset identifiers identifies a media asset the first user has previously consumed;

transmitting, to a metadata repository for each of the plurality of media asset identifiers, a request for corresponding metadata; and

receiving in response to the request for the corresponding metadata, a corresponding data structure associated with the corresponding metadata.

6. The method of claim 1 , wherein determining, based on comparing the metadata of each media asset in the plurality of media assets that the first user has previously consumed with the plurality of words, the media asset that the first user is describing comprises:

calculating, for each of the plurality of media assets, an amount of words of the plurality of words that match a corresponding media asset; and

determining the media asset that the first user is describing based on the calculated amount of words for each corresponding media asset.

7. The method of claim 1 , wherein determining, based on the metadata for each of the plurality of segments and the plurality of words, the segment of the media asset that the first user is describing comprises:

comparing text of the metadata for each of the plurality of segments with each of the plurality of words;

identifying the metadata with a largest amount of words matching the plurality of words; and

selecting the segment corresponding to the metadata with the largest amount of words matching the plurality of words.

8. The method of claim 1 , wherein generating, for display to the second user, the indication of the segment comprises:

identifying an electronic device associated with the second user; and

generating for display the indication of the segment on the electronic device.

9. The method of claim 1 , further comprising:

transmitting, to the first user, a request to confirm that the segment was correctly identified, wherein the request comprises the indication of the segment; and

receiving, in response to the request to confirm, a response from the first user.

10. The method of claim 9 , further comprising:

determining whether the response from the first user indicates that the segment was correctly identified; and

transmitting, in response to determining that the segment was not correctly identified, to the first user a request to identify the correct media asset, wherein the request comprises a plurality of indications corresponding to a plurality of media assets with a largest amount of metadata matching the plurality of words.

11. A system for generating for display an indication of a segment of media content relevant to a voice communication, the system comprising:

communication circuitry; and

control circuitry configured to:

receive a plurality of words spoken by a first user at a communication device during the voice communication with a second user;

determine, based on comparing the plurality of words with a plurality of keywords indicating that media content is being described, that the first user is describing a media content; and

in response to determining that the first user is describing the media content:

retrieve metadata for each of a plurality of media assets that the first user previously consumed;

determine, based on comparing the metadata of each media asset in the plurality of media assets that the first user has previously consumed with the plurality of words, a media asset that the first user is describing;

retrieve metadata for each of a plurality of segments of the media asset that the first user is describing;

determine, based on the metadata for each of the plurality of segments and the plurality of words, the segment of the media asset that the first user is describing; and

generate, for display to the second user, the indication of the segment.

12. The system of claim 11 , wherein the control circuitry is further configured to compare the plurality of words with the plurality of keywords by:

selecting a first word of the plurality of words;

determining, based on comparing the first word of the plurality of words with each keyword of the plurality of keywords, whether the first word matches any of the plurality of keywords; and

in response to determining that the first word matches a keyword from the plurality of keywords, updating a word matching score.

13. The system of claim 12 , wherein the control circuitry is further configured to determine, based on comparing the plurality of words with the plurality of keywords, that the first user is describing the media content by:

determining whether the word matching score is greater than a threshold value; and

in response to determining that the word matching score is greater than the threshold value, determining that the first user is describing the media content.

14. The system of claim 12 , wherein the control circuitry is further configured to update the word matching score by:

retrieving a weight associated with the keyword; and

updating the word matching score with the weight associated with the keyword.

15. The system of claim 11 , wherein the control circuitry is further configured to retrieve the metadata for each of the plurality of media assets that the first user previously consumed by:

transmitting, to a profile server, a request for media asset viewing history of the first user, wherein the request comprises an identifier of the first user;

receiving, in response to the request for the media asset viewing history, a plurality of media asset identifiers, wherein each of the plurality of media asset identifiers identifies a media asset the first user has previously consumed;

transmitting, to a metadata repository for each of the plurality of media asset identifiers, a request for corresponding metadata; and

receiving in response to the request for the corresponding metadata, a corresponding data structure associated with the corresponding metadata.

16. The system of claim 11 , wherein the control circuitry is further configured to determine, based on comparing the metadata of each media asset in the plurality of media assets that the first user has previously consumed with the plurality of words, the media asset that the first user is describing by:

calculating, for each of the plurality of media assets, an amount of words of the plurality of words that match a corresponding media asset; and

determining the media asset that the first user is describing based on the calculated amount of words for each corresponding media asset.

17. The system of claim 11 , wherein the control circuitry is further configured to determine, based on the metadata for each of the plurality of segments and the plurality of words, the segment of the media asset that the first user is describing by:

comparing text of the metadata for each of the plurality of segments with each of the plurality of words;

identifying the metadata with a largest amount of words matching the plurality of words; and

selecting the segment corresponding to the metadata with the largest amount of words matching the plurality of words.

18. The system of claim 11 , wherein the control circuitry is fur her configured to generate, for display to the second user, the indication of the segment by:

identifying an electronic device associated with the second user; and

generating for display the indication of the segment on the electronic device.

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

transmit, to the first user, a request to confirm that the segment was correctly identified, wherein the request comprises the indication of the segment; and

receive, in response to the request to confirm, a response from the first user.

20. The system of claim 19 , wherein the control circuitry is further configured to:

determine whether the response from the first user indicates that the segment was correctly identified; and

transmit, in response to determining that the segment was not correctly identified, to the first user a request to identify the correct media asset, wherein the request comprises a plurality of indications corresponding to a plurality of media assets with a largest amount of metadata matching the plurality of words.