Systems and methods for enhancing recorded or intercepted calls using information from a facial recognition engine
A video stream from a webcam or video telephone is received. The video stream can be analyzed in real-time as it is being received or can be recorded and stored for later analysis. Information within the video streams can be extracted and processed by a facial and video content recognition engine and the information derived therefrom can be stored as metadata. The metadata can be used for enriching the call content recorded by a recorder. The information derived from the video streams can be used to solve business and legal issues.
1. A method for enhancing call content of a telephone call to be recorded using information from facial and video content recognition engine comprising:
receiving a video stream with the telephone call;
receiving results from the facial and video content recognition engine, the facial and video content recognition engine extracting information from the video stream and analyzing the extracted information to supply the results as metadata associated with the telephone call;
periodically sampling the call with the facial and video content recognition engine and re-evaluating the metadata;
and
recording the telephone call in accordance with information extracted from the metadata, wherein the metadata is used to determine if the telephone call should or should not be recorded or to determine whether the telephone call should be suspended.
2. The method of claim 1 , wherein the metadata is queried for statistical information.
3. The method of claim 1 further comprising storing the metadata in a data store.
4. The method of claim 1 , wherein the analyzing of the extracted information occurs in real time as the telephone call is being received.
5. A non-transitory computer-readable storage medium comprising computer-readable instructions that when executed:
receive a video stream with an intercepted telephone call;
receive results from a facial and video content recognition module, wherein the facial and video content recognition module periodically extracts information from the video stream, analyzes the extracted information and sends results of analyzing the extracted information to a recording subsystem; and
use the received results to determine programmatically whether the intercepted telephone call should be recorded or should not be recorded or to determine programmatically whether the intercepted telephone call should be suspended.
6. The computer-readable storage medium of claim 5 , comprising further computer-readable instructions that when executed record the intercepted call in response to a programmatic determination that the intercepted call should be recorded.
7. The computer-readable storage medium of claim 5 , comprising further computer-readable instructions that when executed do not record the intercepted call in response to a programmatic determination that the intercepted call should be recorded or suspend the telephone call in response to a programmatic determination that the intercepted telephone call should be suspended.
8. The computer-readable storage medium of claim 5 , comprising further computer-readable instructions that when executed detect a speaker change programmatically.
9. The computer-readable storage medium of claim 8 , comprising further computer-readable instructions that when executed start recording the intercepted telephone call in response to detecting the speaker change programmatically.
10. The computer-readable storage medium of claim 8 , comprising further computer-readable instructions that when executed stop recording the intercepted telephone call in response to detecting the speaker change programmatically.
11. The computer-readable storage medium of claim 5 , wherein the analyzing of the extracted information occurs in real time as the telephone call is being received.
12. A system comprising:
a recording subsystem that receives information from a facial and video content recognition module, the information extracted from a video data stream of a telephone call and analyzed by the facial and video content recognition module, wherein the recording subsystem uses the received information to determine that the telephone call should or should not be recorded or to determine whether the telephone call should be suspended,
wherein the telephone call is an intercepted telephone call, and wherein the facial and video content recognition module periodically extracts information from the video data stream, and analyzes the extracted information to produce results from which a programmatic determination by the facial and video content recognition module is made to record the telephone call.
13. The system of claim 12 , further comprising a data store that stores the received information as metadata.
14. The system of claim 13 , wherein the data store is searchable.
15. The system of claim 12 , wherein the facial and video content recognition module periodically provides the results to the recording system from which the programmatic determination to record the telephone call is re-evaluated.
16. The system of claim 12 , wherein the facial and video content recognition module extracts information from the video data stream in real time, and analyzes the extracted information in real time to produce results from which a programmatic determination is made to not record the telephone call.
17. The system of claim 16 , wherein the facial and video content recognition module periodically provides the results to the recording system from which the programmatic determination to not record the telephone call is re-evaluated.
18. The system of claim 12 , further comprising a facial and video content recognition data store, wherein the received information is matched against the video content recognition data store for identification.
19. The system of claim 12 , wherein the facial and video content recognition module uses the received information to enhance call content of the recorded call.