Video to data

• US 10,218,954 B2
• Filed: 02/07/2015
• Issued: 02/26/2019
• Est. Priority Date: 08/15/2013
• Status: Active Grant

• Current Assignee: Cellular South, Inc. (Telapex Incorporated)
• Original Assignee: Cellular South, Inc. (Telapex Incorporated)
• Inventors: Lakhani, Naeem, Smith, IV, Bartlett Wade, Talley, Allison A.
• Primary Examiner(s): Shah, Paras D
• Application Number:
  US14/910,698
• Publication Number:
  US 20160358632A1
• Time in Patent Office: 1,480 Days
• Field of Search: 704231, 704270, 7042701, 704275, 382100, 382173, 382176, 382177, 345418, 348 61
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence
• CPC Class Codes: H04N 9/80 Transformation of the television signal for recording, e.g. modulation, frequency changing; Inverse transformation for playback
• CPC Class Codes: H04N 9/802 involving processing of the sound signal H04N9/806, H04N9/835 take precedence
• CPC Class Codes: H04N 9/8715 involving the mixing of the reproduced video signal with a non-recorded signal, e.g. a text signal

Abstract

A method and system can generate video content from a video. The method and system can include generating audio files and image files from the video, distributing the audio files and the image files across a plurality of processors and processing the audio files and the image files in parallel. The audio files associated with the video to text and the image files associated with the video to video content can be converted. The text and the video content can be cross-referenced with the video.

Claims

1. A method to generate video data from a video comprising:

generating audio files and image files from the video;

distributing the audio files and the image files across a plurality of processors and processing the audio files and the image files in parallel;

converting audio files associated with the video to text;

identifying an object in the image files;

determining a contextual topic from the image files;

assigning a probability of accuracy to the identified object based on the contextual topic;

converting the image files associated with the video to video data, wherein the video data comprises the object, the probability, and the contextual topic;

cross-referencing the text and the video data with the video to determine contextual topics;

generating a contextual text, an image, or an animation based on the determined contextual topics;

generating a content-rich video based on the generated text, image, or animation.

2. The method according to claim 1, further comprising:

applying natural language processing to the text to determine context associated with the video.

3. The method according to claim 1, further comprising:

applying natural language processing to the text to extract a topic.

4. The method according to claim 1, further comprising:

processing the image files to extract additional text.

5. The method according to claim 4, wherein the additional text is generated by segmenting the image files before processing the image files in parallel.

6. The method according to claim 1, further comprising:

processing the image files to extract an object and determine a motion associated with the object.

7. The method according to claim 1, wherein the text is generated by segmenting the audio before processing the audio files in parallel.

8. The method according to claim 6, wherein the audio files and the image files are segmented at spectrum thresholds.

9. The method according to claim 1, further comprising:

generating an advertisement based on the text and the video data.

10. The method according to claim 9, further comprising:

placing the advertisement in the video at a preferred time.

11. The method according to claim 1, further comprising:

generating metadata.

12. The method according to claim 11, wherein the metadata comprises a number of frames, a range of said frames and/or timestamp references.

14. The system according to claim 11, wherein converting the audio comprises natural language processing.

15. The system according to claim 11, the computer directs the audio to be converted by at least one node of a cluster and the computer directs the images to be converted by at least one other node of the cluster in parallel.

16. The server according to claim 11, wherein the audio and the images are segmented at spectrum thresholds.

13. A system for extracting data from a video, comprising:

a computer processor; and

a non-transitory computer readable medium containing instructions directing the system to execute the steps of;

converting audio associated with the video to text;

converting images associated with the video to video data, wherein the video data comprises identified objects;

extracting topics from the text and the video data;

assigning probabilities of accuracy for each of the identified objects, wherein the probabilities are based on the extracted topics;

cross-referencing the text, the video data, and the topics with the video to determine contextual topics;

generating a contextual text, an image, or an animation based on the determined contextual topics; and

generate a content-rich video based on the generated contextual text, image, or animation.

17. The system according to claim 13, wherein the computer directs the system to generate metadata.

18. The system according to claim 13, wherein the metadata comprises a number of frames, a range of said frames and/or timestamp references.