Intelligent tagging for multimedia call recording purposes using continuous metadata
View Patent ↗A method of indexing recordings of contact center communication sessions is described. The method allows for a recording to be indexed with metadata reflecting a time-varying characteristic of one or more of the parties of the communications session, e.g. the mood of a caller, the current location of a caller. The indexing of recordings with such information allows for more granular search of recordings, in order to find particular call conditions. This can be useful from the point of view of education and training of new call center operatives, and for assessment of call center performance.
1. A method for providing an indexed recording of a telephony communication session involving a participant in said session, the method comprising the steps of, using a processing device:
recording at least a portion of said telephony communication session;
obtaining, in respect of one or more periods in which said participant is recorded as actively participating, at least one time-varying characteristic associated with said participant, wherein said at least one time-varying characteristic varies over time for that particular participant and is neither the identity of the participant nor the content of the participant's speech; and
indexing said recorded data with metadata, said metadata varying in response to said at least one time-varying characteristic, wherein said at least one time-varying characteristic is neither the identity of the participant nor the content of the participant's speech, and wherein for the step of indexing, the at least one characteristic is chosen from the following: a location indicator; a bandwidth usage indicator; an activity indicator.
2. The method of claim 1 , wherein the method further comprises the steps of:
obtaining at least one time-varying characteristic associated with at least one other participant in said session, wherein said at least one time-varying characteristic varies over time for that at least one other participant and is neither the identity of the participant nor the content of the participant's speech; and
indexing said recorded data with metadata, said metadata varying in response to said at least one time-varying characteristic associated with said at least one other participant.
3. The method of claim 1 , wherein the method further comprises the step of storing the indexed recording in a storage device.
4. The method of claim 1 , wherein said metadata varies in response to said at least one time-varying characteristic by recording a time-varying value of the characteristic.
5. The method of claim 1 , wherein said metadata varies in response to said at least one time-varying characteristic by recording a rate of change of a time-varying value of the characteristic.
6. The method of claim 1 , wherein said step of indexing is performed as said communication session is being recorded.
7. The method of claim 1 , wherein the method comprises the step of presenting an indication of the at least one time-varying characteristic to at least one participant during the communication session.
8. The method of claim 1 , wherein the method comprises the step of receiving a characterization feed for the portion of the telephony communication session, the characterization feed comprising a time-varying indicator of the level of the at least one characteristic of the participant in the session.
9. The method of claim 8 , wherein said step of indexing is responsive to said characterization feed.
10. A system for indexing a recording of a telephony communication session involving a participant in said session, the system comprising:
a storage buffer for recording at least a portion of said telephony communication session;
a characterization feed receiving device operable to receive at lease one time-varying characteristic associated with said participant in respect of one or more periods in which said participant is recorded as actively participating, wherein said at least one time-varying characteristic varies over time for that particular participant and is neither the identity of the participant nor the content of the participant's speech; and
a tagging processor operable to indexing said recorded data with metadata, said metadata varying in response to said at least one time-varying characteristic, wherein said at least one time-varying characteristic is neither the identity of the participant nor the content of the participant's speech, and wherein for the step of indexing, the at least one characteristic is chosen from the following: a location indicator; a bandwidth usage indicator; an activity indicator.
11. A computer program product stored on a non-transitory computer readable medium comprising a set of instructions which, when executed on a computer, are operable to implement the steps of the method as outlined above.
12. The method of claim 1 , wherein for the step of indexing, the at least one characteristic is chosen from a mood indicator and a speech volume indicator.
13. The method of claim 12 , wherein said mood indicator is based on the content of the participant's speech.
14. The method of claim 8 , wherein the characterization feed comprises at least one of a mood indicator, a volume indicator; and a stress level indicator.