Structured conversation enhancement

1. A method, comprising:

determining, with computer hardware, an anticipated ebb point of a current conversation taking place on a first platform, the first platform being a first type of communication platform, in response to a predetermined triggering event indicating a start of the current conversation;

monitoring, with the computer hardware, the current conversation using pattern recognition and determining a probable change in the anticipated ebb point in response to recognizing a word pattern indicating a change in the current conversation; and

responsive to the probable change in the anticipated ebb point, initiating with the computer hardware, a response action, wherein the response action comprises activating a second platform, the second platform being a second type of communication platform different than the first type of communication platform, for the current conversation and switching a plurality of participants in the current conversation to the second platform.

2. The method of claim 1 , wherein the anticipated ebb point of the current conversation is based on a plurality of prior conversations grouped according to an identified topic of the current conversation.

3. The method of claim 1 , wherein the recognizing the word pattern indicating a change in the current conversation uses a deep learning neural network or k-means clustering.

4. The method of claim 3 , wherein the change in the current conversation comprises moving from one phase of the current conversation to another or moving from one topic to another.

5. The method of claim 1 , wherein the response action further comprises notifying a current conversation participant of the change in the anticipated ebb point.

6. The method of claim 5 , wherein the notifying includes indicating a probability that the current conversation will conclude within a specified time.

7. The method of claim 1 , wherein the predetermined triggering event is a push triggered event, pull triggered event, conditionally triggered event, scheduled action or user-initiated action.

8. A system, comprising:

a processor configured to initiate operations including:

determining an anticipated ebb point of a current conversation taking place on a first platform, the first platform being a first type of communication platform, in response to a predetermined triggering event indicating a start of the current conversation;

monitoring the current conversation using pattern recognition and determining a probable change in the anticipated ebb point in response to recognizing a word pattern indicating a change in the current conversation; and

responsive to the probable change in the anticipated ebb point, initiating a response action, wherein the response action comprises activating a second platform, the second platform being a second type of communication platform different than the first type of communication platform, for the current conversation and switching a plurality of participants in the current conversation to the second platform.

9. The system of claim 8 , wherein the anticipated ebb point of the current conversation is based on a plurality of prior conversations grouped according to an identified topic of the current conversation.

10. The system of claim 8 , wherein the recognizing the word pattern indicating a change in the current conversation uses a deep learning neural network or k-means clustering.

11. The system of claim 8 , wherein the change in the current conversation comprises moving from one phase of the current conversation to another or moving from one topic to another.

12. The system of claim 8 , wherein the response action further comprises notifying a current conversation participant of the change in the anticipated ebb point.

13. The system of claim 12 , wherein the notifying includes indicating a probability that the current conversation will conclude within a specified time.

14. A computer program product comprising a computer readable storage medium having program instructions embodied therewith, wherein the computer readable storage medium is not a transitory, propagating signal per se, the program instructions executable by a processor to cause the processor to initiate operations comprising:

determining, by the processor, an anticipated ebb point of a current conversation taking place on a first platform, the first platform being a first type of communication platform, in response to a predetermined triggering event indicating a start of the current conversation;

monitoring, by the processor, the current conversation using pattern recognition and determining a probable change in the anticipated ebb point in response to recognizing a word pattern indicating a change in the current conversation; and

responsive to the probable change in the anticipated ebb point, initiating by the processor, a response action, wherein the response action comprises activating a second platform, the second platform being a second type of communication platform different than the first type of communication platform, for the current conversation and switching a plurality of participants in the current conversation to the second platform.

15. The computer program product of claim 14 , wherein the anticipated ebb point of the current conversation is based on a plurality of prior conversations grouped according to an identified topic of the current conversation.

16. The computer program product of claim 14 , wherein the recognizing the word pattern indicating a change in the current conversation uses a deep learning neural network or k-means clustering.

17. The computer program product of claim 14 , wherein the change in the current conversation comprises moving from one phase of the current conversation to another or moving from one topic to another.

18. The computer program product of claim 14 , wherein the response action further comprises notifying a current conversation participant of the change in the anticipated ebb point.

19. The computer program product of claim 18 , wherein the notifying includes indicating a probability that the current conversation will conclude within a specified time.

20. The computer program product of claim 14 , wherein the predetermined triggering event is a push triggered event, pull triggered event, conditionally triggered event, or user-initiated action.