Moderating artificial intelligence (AI) agent interlocution in group dialog environments
Provided are techniques for moderating Artificial Intelligence (AI) agent interlocution in group dialog environments. Under control of an interlocution module that has been trained with dialog content and dialog turns, an indication that interlocution is to be determined for a group dialog is received. Under control of the interlocution module, it is determined whether an AI agent is to participate in the group dialog based on a current dialog context and a dialog response. Under control of the interlocution module, in response to determining that the AI agent is to participate in the group dialog, the AI agent is triggered to post the dialog response to the group dialog.
1. A computer-implemented method, comprising operations for:
during a group dialog with an Artificial Intelligence (AI) agent and at least two users,
under control of an interlocution module that has been trained with dialog content and dialog turns,
receiving an indication that an interlocution point is to be determined for the group dialog;
determining the interlocution point at which the AI agent is to participate in the group dialog based on a current dialog context and a dialog response; and
triggering the AI agent to post the dialog response to the group dialog at the interlocution point;
receiving feedback comprising a positive emote or a negative emote for the dialog response; and
further training the interlocution module based on the received feedback.
2. The computer-implemented method of claim 1 , further comprising operations for:
receiving another indication that interlocution is to be determined for the group dialog;
determining that the AI agent is to participate in the group dialog based on a new current dialog context; and
generating a new dialog response.
3. The computer-implemented method of claim 1 , wherein the dialog content and the dialog turns are annotated with persona data and temporal data, and wherein the temporal data comprises a duration, a time since a last response, and an average response time.
4. The computer-implemented method of claim 1 , wherein the dialog content is annotated with one or more positive interlocution points and one or more negative interlocution points.
5. The computer-implemented method of claim 1 , wherein the indication that the interlocution point is to be determined is generated at each dialog turn in the group dialog.
6. The computer-implemented method of claim 1 , wherein the indication that that the interlocution point is to be determined is generated periodically.
7. A computer program product, the computer program product comprising a computer readable storage medium having program instructions embodied therewith, the program instructions executable by a processor to cause the processor to perform operations for:
during a group dialog with an Artificial Intelligence (AI) agent and at least two users,
under control of an interlocution module that has been trained with dialog content and dialog turns,
receiving an indication that an interlocution point is to be determined for the group dialog;
determining the interlocution point at which the AI agent is to participate in the group dialog based on a current dialog context and a dialog response; and
triggering the AI agent to post the dialog response to the group dialog at the interlocution point;
receiving feedback comprising a positive emote or a negative emote for the dialog response; and
further training the interlocution module based on the received feedback.
8. The computer program product of claim 7 , wherein the program instructions are executable by the processor to cause the processor to perform further operations for:
receiving another indication that interlocution is to be determined for the group dialog;
determining that the AI agent is to participate in the group dialog based on a new current dialog context; and
generating a new dialog response.
9. The computer program product of claim 8 , wherein the dialog content and the dialog turns are annotated with persona data and temporal data, and wherein the temporal data comprises a duration, a time since a last response, and an average response time.
10. The computer program product of claim 7 , wherein the dialog content is annotated with one or more positive interlocution points and one or more negative interlocution points.
11. The computer program product of claim 7 , wherein the indication that the interlocution point is to be determined is generated at each dialog turn in the group dialog.
12. The computer program product of claim 7 , wherein the indication that that the interlocution point is to be determined is generated periodically.
13. A computer system, comprising:
one or more processors, one or more computer-readable memories and one or more computer-readable, tangible storage devices; and
program instructions, stored on at least one of the one or more computer-readable, tangible storage devices for execution by at least one of the one or more processors via at least one of the one or more computer-readable memories, to perform operations comprising:
during a group dialog with an Artificial Intelligence (AI) agent and at least two users,
under control of an interlocution module that has been trained with dialog content and dialog turns,
receiving an indication that an interlocution point is to be determined for the group dialog;
determining the interlocution point at which the AI agent is to participate in the group dialog based on a current dialog context and a dialog response; and
triggering the AI agent to post the dialog response to the group dialog at the interlocution point;
receiving feedback comprising a positive emote or a negative emote for the dialog response; and
further training the interlocution module based on the received feedback.
14. The computer system of claim 13 , wherein the operations further comprise:
receiving another indication that interlocution is to be determined for the group dialog;
determining that the AI agent is to participate in the group dialog based on a new current dialog context; and
generating a new dialog response.
15. The computer system of claim 14 , wherein the dialog content and the dialog turns are annotated with persona data and temporal data, and wherein the temporal data comprises a duration, a time since a last response, and an average response time.
16. The computer system of claim 13 , wherein the dialog content is annotated with one or more positive interlocution points and one or more negative interlocution points.
17. The computer system of claim 13 , wherein the indication that the interlocution point is to be determined is generated at each dialog turn in the group dialog.
18. The computer system of claim 13 , wherein the indication that that the interlocution point is to be determined is generated periodically.