Dynamically scheduling non-programming media items in contextually relevant programming media content

1. A system, comprising:

a memory for storing instructions; and

a processor configured to execute the instructions, and based on the executed instructions, the processor is further configured to:

store keywords or event information associated with semantics of programming media content that is received from a source device;

map contextual data of the programming media content with the stored keywords or the event information;

extract contextual keywords from the contextual data from the programming media content based on the mapping of the contextual data with the stored keywords or the event information;

determine a plurality of potential non-programming media items from a plurality of non-programming media items for a plurality of users, based on a match between a sentiment type of each of the plurality of non-programming media items and the extracted contextual keywords;

determine a candidate spot in the programming media content based on at least the contextual keywords and a sentiment type associated with a potential non-programming media item of the plurality of potential non-programming media items; and

dynamically generate, based on at least a set of constraints, a schedule for insertion of the potential non-programming media item at the candidate spot in the programming media content at run time for viewing at a consumer device.

2. The system according to claim 1 , wherein the processor is further configured to parse program-specific information associated with the programming media content based on a plurality of natural language processing techniques.

3. The system according to claim 1 , wherein the processor is further configured to:

determine an advertiser based on the contextual data; and

receive the potential non-programming media item associated with the advertiser.

4. The system according to claim 1 , wherein the processor is further configured to determine the sentiment type of the potential non-programming media item based on a match between media item metadata associated with the potential non-programming media item and a vocabulary database.

5. The system according to claim 1 , wherein the potential non-programming media item is associated with at least one of a media content source, media item information, the plurality of users, or a playback duration.

6. The system according to claim 1 , wherein the processor is further configured to dynamically generate the schedule of the potential non-programming media item at the candidate spot based on social media data associated with social media behavior of a user associated with the consumer device.

7. The system according to claim 1 , wherein the processor is further configured to analyze the contextual data based on content recognition detection of the programming media content of a channel, and

wherein the programming media content corresponds to at least one of a live feed or pre-stored video-on-demand (VOD) assets.

8. The system according to claim 1 , wherein the processor is further configured to:

detect an upcoming inbound trigger in the programming media content; and

determine the candidate spot in the programming media content based on the upcoming inbound trigger.

9. The system according to claim 1 , wherein

the set of constraints comprises at least one of a count of first non-programming media items of the potential non-programming media item for an insertion in a defined time duration of the programming media content, a minimum or maximum count of second non-programming media items of the potential non-programming media item, a media content identifier to differentiate between similar product items corresponding to different brands, break duration limits, or a time separation, and

the second non-programming media items correspond to a media content source.

10. The system according to claim 1 , wherein the processor is further configured to determine an engagement index of a user associated with the consumer device,

wherein the consumer device receives the programming media content that includes the dynamically generated schedule of the potential non-programming media item for the candidate spot,

wherein the engagement index for the user is objectively quantified to emphasize on metrics associated with audience retention and impact translation for the contextual data associated with the programming media content, and

wherein the engagement index is optimized to reflect on an increased return of investment (ROI) for the potential non-programming media item.

11. The system according to claim 1 , wherein program-specific information associated with the programming media content corresponds to closed captions associated with live feed of the programming media content of a channel.

12. The system according to claim 1 , wherein program-specific information associated with the programming media content corresponds to closed captions associated with pre-stored video-on-demand (VOD) assets.

13. The system according to claim 1 , wherein the processor is further configured to extract the contextual data from program-specific information associated with the programming media content of a channel based on a plurality of natural language processing techniques.

14. The system according to claim 13 , wherein the contextual data is extracted based on content recognition of the programming media content of the channel, and

wherein the contextual data corresponds to a plurality of topics that corresponds to one or more time intervals of the programming media content of the channel.

15. The system according to claim 13 , wherein the processor is further configured to:

extract in-stream metadata from the programming media content; and

store the in-stream metadata as live program-specific information in a cloud storage system.

16. A method, comprising:

storing, by a processor, keywords or event information associated with semantics of programming media content that is received from a source device;

mapping, by the processor, contextual data of the programming media content with the stored keywords or the event information;

extracting, by the processor, contextual keywords from the contextual data from the programming media content based on the mapping of the contextual data with the stored keywords or the event information;

determining, by the processor, a plurality of potential non-programming media items from a plurality of non-programming media items for a plurality of users, based on a match between a sentiment type of each of the plurality of non-programming media items and the extracted contextual keywords;

determining, by the processor, a candidate spot in the programming media content based on at least the contextual keywords and a sentiment type associated with a potential non-programming media item of the plurality of potential non-programming media items; and

dynamically generating, by the processor, based on at least a set of constraints, a schedule for insertion of the potential non-programming media item at the candidate spot in the programming media content at run time for viewing at a consumer device.

17. The method according to claim 16 , further comprising parsing, by the processor, program-specific information associated with the programming media content based on a plurality of natural language processing techniques.

18. The method according to claim 16 , further comprising:

determining, by the processor, an advertiser based on the contextual data; and

receiving, by the processor, the potential non-programming media item associated with the advertiser.

19. The method according to claim 16 , further comprising determining, by the processor, the sentiment type of the potential non-programming media item based on a match between media item metadata associated with the potential non-programming media item and a vocabulary database.

20. The method according to claim 16 , wherein the potential non-programming media item is associated with at least one of a media content source, media item information, the plurality of users, or a playback duration.

21. The method according to claim 16 , further comprising generating, by the processor, the schedule of the potential non-programming media item at the candidate spot based on social media data associated with social media behavior of a user associated with the consumer device.

22. The method according to claim 16 , wherein

the set of constraints comprises at least one of a count of first non-programming media items of the potential non-programming media item for an insertion in a defined time duration of the programming media content, a minimum or maximum count of second non-programming media items of the potential non-programming media item, a media content identifier to differentiate between similar product items corresponding to different brands, break duration limits, or a time separation, and

the second non-programming media items correspond to a media content source.

23. The method according to claim 16 , further comprising determining, by the processor, an engagement index of a user associated with the consumer device,

wherein the consumer device receives the programming media content that includes the dynamically generated schedule of the potential non-programming media item for the candidate spot,

wherein the engagement index for the user is objectively quantified to emphasize on metrics associated with audience retention and impact translation for the contextual data associated with the programming media content, and

wherein the engagement index is optimized to reflect on an increased return of investment (ROI) for the potential non-programming media item.

24. A non-transitory computer-readable medium having stored thereon, computer executable instruction that when executed by a computer, causes the computer to execute operations, the operation comprising:

storing keywords or event information associated with semantics of programming media content that is received from a source device;

mapping contextual data of the programming media content with the stored keywords or the event information;

extracting contextual keywords from the contextual data from the programming media content based on the mapping of the contextual data with the stored keywords or the event information;

determining a plurality of potential non-programming media items from a plurality of non-programming media items for a plurality of users, based on a match between a sentiment type of each of the plurality of non-programming media items and the extracted contextual keywords;

determining a candidate spot in the programming media content based on at least the contextual keywords and a sentiment type of a potential non-programming media item of the plurality of potential non-programming media items; and

dynamically generating, based on at least a set of constraints, a schedule for insertion of the potential non-programming media item at the candidate spot in the programming media content at run time for viewing at a consumer device.