Automatic contextual media recording and processing utilizing speech analytics
View Patent ↗Embodiments are provided for the automatic real-time recording and processing of media in a communications network based on the context of the media. In one embodiment, a media stream is received in an analysis module in a service platform in the communications network. The media stream may represent a communication session between a calling party and a call center in the network. The incoming media steam is analyzed to identify words comprising a context of the communication session. A determination is then made as to whether the context of the communication session is related to a set of business rules associated with the service platform which may automatically trigger the retention of a recording of the communication session. If the context of the communication session is related to the set of business rules, the retention of the communication session is automatically triggered in real-time at a recording module.
1. A method comprising:
receiving a media stream representing a communication session between a calling party and a called party;
storing the media stream in a cache;
analyzing, via a processor, the media stream to determine a context of the communication session;
comparing the context against a set of rules for triggering retention of the communication session, to yield a context comparison value; and
upon the context comparison value exceeding a threshold, storing an unabridged version of the communication session by transferring the media stream from the cache to a non-cache long-term storage.
2. The method of claim 1 further comprising automatically archiving the media stream based on the set of rules.
3. The method of claim 2 , wherein automatically archiving the media stream based on the set of rules further comprises:
flagging at least one segment of the communication session being recorded for retention and for performance of at least one action based on the set of rules, to yield a flagged segment of the communication session being recorded; and
performing the at least one action in response to the flagged segment of the communication session being recorded.
4. The method of claim 3 , wherein performing the at least one action on the flagged segment of the communication session being archived comprises prompting, in real-time, the performance of an action in response to an audio portion of the communication session being archived.
5. The method of claim 3 , wherein automatically archiving the media stream based on the set of rules further comprises:
prioritizing the flagged segment of the communication session being recorded for later retrieval; and
storing the flagged segment of the communication session being recorded.
6. The method of claim 1 , wherein receiving a media stream comprises receiving audio and video content representing the communication session between the calling party and the called party in the network over a mixed communications path.
7. The method of claim 1 , wherein receiving a media stream comprises receiving an audio only content stream representing the communication session between the calling party and the called party in the network.
8. The method of claim 1 , wherein analyzing the media stream to determine a context of the communication session comprises utilizing language model dependent speech recognition to identify phrases comprising the context of the communication session.
9. A system comprising:
a processor; and
a non-transitory storage device having stored therein instructions for controlling the processor to perform a method comprising:
receiving a media stream representing a communication session between a calling party and a called party;
storing the media stream temporarily in a cache;
analyzing the media stream to determine a context of the communication session; and
comparing the context against a set of rules for triggering retention of the communication session, to yield a context comparison value; and
upon the context comparison value exceeding a threshold, storing an unabridged version of the communication session by transferring the media stream from the cache to a non-cache long-term storage.
10. The system of claim 9 , wherein comparing the context of the communication session is based on language model dependent speech recognition.
11. The system of claim 9 , the non-transitory computer-readable storage medium storing additional instructions which result in the method further comprising:
flagging at least one segment of the media stream being archived for retention and for the performance of at least one action based on the set of rules, to yield a flagged segment of the media stream being archived.
12. The system of claim 11 , the non-transitory computer-readable storage medium storing further instructions which result in the method further comprising performing at least one action in response to the flagged segment of the media stream being archived.
13. The system of claim 12 , the non-transitory computer-readable storage medium storing yet additional instructions which result in the method further comprising prioritizing the flagged segment of the communication session being archived.
14. A non-transitory computer-readable storage medium having stored therein computer-executable instructions which, when executed on a computer, cause the computer to perform a method comprising:
receiving a media stream representing a communication session between a calling party and a called party;
storing the media stream temporarily in a cache;
analyzing the media stream to determine a context of the communication session;
comparing the context against a set of rules for triggering retention of the communication session, to yield a context comparison value; and
upon the context comparison value exceeding a threshold, storing an unabridged version of the communication session by transferring the media stream from the cache to a non-cache long-term storage.
15. The non-transitory computer-readable storage medium of claim 14 storing additional instructions which result in the method further comprising automatically processing the media stream being recorded based on the set of rules.
16. The non-transitory computer-readable storage medium of claim 15 , storing additional instructions which result in the method further comprising:
flagging least one segment of the media stream being recorded for retention in a storage module and for performing at least one action based on the set of rules, to yield a flagged segment of the media stream being recorded; and
performing the at least one action in response to the flagged segment of the media stream being recorded.
17. The non-transitory computer-readable storage medium of claim 16 , wherein performing the at least one action comprises prompting, in real-time, a performance of an action in response to an audio portion of the media stream being recorded.
18. The non-transitory computer-readable storage medium of claim 16 , wherein automatically processing the media stream being recorded based on the set of rules further comprises:
prioritizing the flagged segment of the media stream being recorded for later retrieval from the storage module; and
storing the flagged segment of the media stream being recorded in the storage module.
19. The non-transitory computer-readable storage medium of claim 14 , wherein analyzing the media stream to determine a context of the communication session comprises utilizing language model dependent speech recognition to identify phrases comprising the context of the communication session.