Methods, systems, and apparatuses to respond to voice requests to play desired video clips in streamed media based on matched close caption and sub-title text
Methods, Systems, and Apparatuses are described to implement voice search in media content for requesting media content of a video clip of a scene contained in the media content streamed to the client device; for capturing the voice request for the media content of the video clip to display at the client device wherein the streamed media content is a selected video streamed from a video source; for applying a NLP solution to convert the voice request to text for matching to a set of one or more words contained in at least close caption text of the selected video; for associating matched words to close caption text with a start index and an end index of the video clip contained in the selected video; and for streaming the video clip to the client device based on the start index and the end index associated with matched closed caption text.
1. A method for searching content, comprising:
applying, by a server, natural language processing (NLP) to convert a voice request to text, wherein the voice request is captured by a local device in communication with the server;
creating a first search handler to execute a search in a media database based on the text, wherein the search identifies media content in response to contextual data associated with the media content matching the text;
tagging the media content identified by the first search handler in response to the search; and
playing a video scene at the local device in response to a selection of the video scene from the tagged media content.
2. The method of claim 1 , wherein the contextual data comprises metadata.
3. The method of claim 2 , further comprising creating a second search handler to execute a second search, wherein the second search identifies the media content in response to subtitle data matching the text.
4. The method of claim 3 , further comprising creating a third search handler to execute a third search to identify the media content in response to close caption data associated with the media content matching the text.
5. The method of claim 1 , further comprising creating a searchable index of media content based on the tagged media content.
6. The method of claim 1 , further comprising creating a presentation layer including thumbnail images of scenes identified by the first search handler.
7. The method of claim 1 , further comprising executing a script associated with the video scene in response to the selection of the video scene at the local device.
8. A system for processing voice requests for identifying media content in streaming media for display, comprising:
a local device; and
a server in communication with the local device and configured to perform operations, the operations comprising:
applying natural language processing (NLP) to convert a voice request to text, wherein the voice request is captured by the local device;
creating a first search handler to execute a search in a media database based on the text, wherein the search identifies media content in response to contextual data associated with the media content matching the text;
tagging the media content identified by the first search handler in response to the search; and
playing a video scene at the local device in response to a selection of the video scene from the tagged media content.
9. The system of claim 8 , wherein the operations further comprise creating a second search handler to execute a second search, wherein the second search identifies the media content in response to subtitle data matching the text.
10. The system of claim 9 , wherein the operations further comprise creating a third search handler to execute a third search to identify the media content in response to close caption data associated with the media content matching the text.
11. The system of claim 8 , wherein the operations further comprise creating a searchable index of media content based on the tagged media content.
12. The system of claim 8 , wherein the operations further comprise creating a presentation layer comprising thumbnail images of scenes identified by the first search handler.
13. The system of claim 8 , further comprising executing a script associated with the video scene in response to the selection of the video scene at the local device.
14. The system of claim 8 , wherein the contextual data comprises metadata.
15. A streaming system comprising a processor in communication with a non-transitory memory configured to store instructions that, when executed by the processor, cause the streaming system to perform operations, the operations comprising:
applying natural language processing (NLP) to convert a voice request to text, wherein the voice request is captured by a local device in communication with the streaming system;
creating a first search handler to execute a search in a media database based on the text, wherein the search identifies media content in response to contextual data associated with the media content matching the text;
tagging the media content identified by the first search handler in response to the search; and
playing a video scene at the local device in response to a selection of the video scene from the tagged media content.
16. The streaming system of claim 15 , wherein the contextual data comprises metadata.
17. The streaming system of claim 15 , wherein the contextual data comprises subtitles and closed caption data.
18. The streaming system of claim 15 , wherein the operations further comprise creating a second search handler to execute a second search, wherein the second search identifies the media content in response to subtitle data matching the text.
19. The streaming system of claim 15 , wherein the operations further comprise creating a second search handler to execute a second search to identify the media content in response to close caption data associated with the media content matching the text.
20. The streaming system of claim 15 , wherein the operations further comprise creating a searchable index of media content based on the tagged media content.