Identifying recorded call data segments of interest
A method and apparatus of processing a voice call are disclosed. One example method of operation may include recording at least a portion of a conference call and storing the portion of the conference call in memory. The method may also include processing the portion of the conference call to identify at least one segment of interest and adding the at least one segment of interest to an existing work order associated with a third party application. The method may further provide forwarding the at least one segment of interest to a third party computing device.
1. A computer automated method, comprising automatically:
receiving a “begin recording” signal during a call from a telephone used by one of one of a plurality of call participants as a call leader, by the call leader pressing a key of the telephone's dual tone modulation frequency (DTMF) numeric keypad to begin recording the call;
periodically time stamping the recording to provide indicators of call progress;
thereafter, receiving a “stop recording” signal from the telephone used by the call leader, by the call leader pressing a key of the telephone's dual tone modulation frequency (DTMF) numeric keypad during the call to stop recording the call, whereby a portion of the call is recorded;
storing the recording with corresponding time stamps in a tangible storage device;
converting audio of the recording to text, and storing the text in the tangible storage device;
retrieving at least one predetermined keyword stored in the tangible storage device, and comparing the at least one predetermined keyword to the stored text to identify occurrences of the at least one predetermined keyword in the text;
identifying at least one of:
a first number of words or seconds before the occurrence, and
a second number of words or seconds after the occurrence, as buffers, wherein a number of words or seconds in the buffers is based on a received preference from a third party computing device; and
saving each occurrence of the at least one predetermined keyword and the buffers with corresponding time stamp information as a segment of interest of the recording and sending the segment of interest to the third party computing device.
2. The method of claim 1 , wherein the number of words or seconds before and after the keyword is a predetermined default number.
3. The method of claim 1 , wherein a plurality of segments of interest based on a plurality of identified keyword instances are forwarded to a call participant, and are made available to be played in an order determined by the participant.
4. An apparatus, comprising:
a tangible computer-readable storage device containing computer readable instructions;
a processor operatively coupled to the storage device that executes the instructions to:
receive a “begin recording” signal during a call from a telephone used by one of a plurality of call participants as a call leader, by the call leader pressing a key of the telephone's dual tone modulation frequency (DTMF) numeric keypad to begin recording the call;
periodically time stamp the recording to provide indicators of call progress;
thereafter, receive a “stop recording” signal from the telephone used by the call leader, by the call leader pressing a key of the telephone's dual tone modulation frequency (DTMF) numeric keypad during the call to stop recording the call, whereby a portion of the call is recorded;
store the recording with corresponding time stamps in a tangible storage device;
convert audio of the recording to text and store the text in the tangible storage device;
retrieve at least one predetermined keyword stored in the tangible storage device, and compare the at least one predetermined keyword to the stored text to identify occurrences of the at least one predetermined keyword in the text;
identify at least one of:
a first number of words or amount of time before the occurrence, and
a second number of words or amount of time after the occurrence, as buffers, wherein a number of words or seconds in the buffers is based on a received preference from a third party computing device; and
save each occurrence of the at least one predetermined keyword and the buffers with corresponding time stamp information as a segment of interest of the recording and send the segment of interest to the third party computing device.
5. The apparatus of claim 4 , further comprising a transmitter configured to transmit the segment of interest to the third party receiver.
6. The apparatus of claim 4 , wherein the number of words or seconds before and after the keyword are selected by the third party.
7. The apparatus of claim 4 , wherein the number of words or seconds before and after the keyword is a predetermined default number.
8. The apparatus of claim 4 , wherein the processor is further configured to forward a plurality of segments of interest based on a plurality of identified keyword instances to a call participant, and are made available to be played in an order determined by the participant.
9. A non-transitory computer readable storage medium containing instructions executable by a processor to perform a method comprising:
receiving a “begin recording” signal during a call from a telephone used by one of a plurality of call participants as a call leader, by the call leader pressing a key of the telephone's dual tone modulation frequency (DTMF) numeric keypad to begin recording the call;
periodically time stamping the recording to provide indicators of call progress;
thereafter, receiving a “stop recording” signal from the telephone used by the call leader, by the call leader pressing a key of the telephone's dual tone modulation frequency (DTMF) numeric keypad during the call to stop recording the call, whereby a portion of the call is recorded;
storing the recording with corresponding time stamps in a tangible storage device;
converting audio of the recording to text, and storing the text in the tangible storage device;
retrieving at least one predetermined keyword stored in the tangible storage device, and comparing the at least one predetermined keyword to the stored text to identify occurrences of the at least one predetermined keyword in the text;
identifying at least one of:
a first number of words or seconds before the occurrence, and
a second number of words or seconds after the occurrence, as buffers, wherein a number of words or seconds in the buffers is based on a received preference from a third party computing device; and
saving each occurrence of the at least one predetermined keyword and the buffers with corresponding time stamp information as a segment of interest of the recording and sending the segment of interest to the third party computing device.
10. The non-transitory computer readable storage medium of claim 9 , wherein the first and second number of words or seconds is one of:
a predetermined default number, and
a number selected by the third party.
11. The non-transitory computer readable storage medium of claim 9 , wherein a plurality of segments of interest based on a plurality of identified keyword instances are forwarded to a call participant, and are made available to be played in an order determined by the participant.