Progressively extending conversation scope in multi-user messaging platform

1. A method, in a data processing system comprising at least one processor and at least one memory, the at least one memory comprising instructions which are executed by the at least one processor and configure the processor to implement a conversation scope system, comprising a conversation scope controller and a conversation scope extractor, for extending conversation scope in a multi-user messaging platform, the method comprising:

capturing, by the conversation scope controller executing on the at least one processor of the data processing system, an utterance input by a user into a chat platform;

performing a search of a chat history data structure using enhanced information retrieval (IR), at least one knowledge graph, and machine learning (ML) to find an answer to the utterance;

responsive to determining that a high confidence answer is not found for the utterance, searching, by the conversation scope controller, a bot registry data structure for a bot that performs a task requested by the utterance;

responsive to determining that a bot is not found to perform a task requested by the utterance, searching, by the conversation scope controller, for an active communication in messaging chat rooms the user is subscribed to and extracting, by the conversation scope extractor, conversation scope related to the utterance;

responsive to determining that a conversation scope is not found in an active communication in messaging chat rooms, searching, by the conversation scope controller, for human expert users who can answer the utterance; and

responsive to determining that human expert users are not found to answer the utterance, searching, by the conversation scope controller, messaging chat rooms and proposing, by the conversation scope controller, a target messaging chat room for the utterance.

2. The method of claim 1 , further comprising:

responsive to finding a high confidence answer to the utterance presenting the high confidence answer to the user.

3. The method of claim 1 , wherein performing the search of the chat history data structure comprises:

generating one or more candidate answers based on entities extracted from the utterance, at least one knowledge graph, and a set of features;

generating a confidence score for each of the one or more candidate answers; and

comparing each confidence score to a threshold value.

4. The method of claim 1 , further comprising:

responsive to finding a given bot that performs the task requested by the utterance, opening a chat room with the given bot and the user.

5. The method of claim 1 , further comprising:

responsive to extracting conversation scope, opening a chat room with the extracted conversation scope for the user.

6. The method of claim 1 , further comprising:

responsive to finding one or more human expert users who can answer the utterance, suggesting a direct message or user list including the one or more human expert users to the user.

7. The method of claim 1 , wherein searching for an active communication in messaging chat rooms the user is subscribed to comprises using a classifier to classify the utterance into a class that matches a chat room name.

8. A computer program product comprising a non-transitory computer readable storage medium having a computer readable program stored therein, wherein the computer readable program comprises instructions, which when executed on a processor of a computing device causes the computing device to implement a conversation scope system, comprising a conversation scope controller and a conversation scope extractor, for extending conversation scope in a multi-user messaging platform, wherein the computer readable program causes the computing device to:

capture, by the conversation scope controller executing on the at least one processor of the data processing system, an utterance input by a user into a chat platform;

perform a search of a chat history data structure using enhanced information retrieval (IR), at least one knowledge graph, and machine learning (ML) to find an answer to the utterance;

responsive to determining that a high confidence answer is not found for the utterance, search, by the conversation scope controller, a bot registry data structure for a bot that performs a task requested by the utterance;

responsive to determining that a bot is not found to perform a task requested by the utterance, search, by the conversation scope controller, for an active communication in messaging chat rooms the user is subscribed to and extracting conversation scope to the user;

responsive to determining that a conversation scope is not found in an active communication in messaging chat rooms, search, by the conversation scope controller, for human expert users who can answer the utterance; and

responsive to determining that human expert users are not found to answer the utterance, search, by the conversation scope controller, messaging chat rooms and propose, by the conversation scope controller, a target messaging chat room for the utterance.

9. The computer program product of claim 8 , wherein computer readable program further causes the computing device to:

responsive to finding a high confidence answer to the utterance, present the high confidence answer to the user.

10. The computer program product of claim 8 , wherein performing the search of the chat history data structure comprises:

generating one or more candidate answers based on entities extracted from the utterance, at least one knowledge graph, and a set of features;

generating a confidence score for each of the one or more candidate answers; and

comparing each confidence score to a threshold value.

11. The computer program product of claim 8 , wherein the computer readable program further causes the computing device to:

responsive to finding a given bot that performs the task requested by the utterance, opening a chat room with the given bot and the user.

12. The computer program product of claim 8 , wherein the computer readable program further causes the computing device to:

responsive to extracting conversation scope, opening a chat room with the extracted conversation scope for the user.

13. The computer program product of claim 8 , wherein the computer readable program further causes the computing device to:

responsive to finding one or more human expert users who can answer the utterance, suggesting a direct message or user list including the one or more human expert users to the user.

14. The computer program product of claim 8 , wherein searching for an active communication in messaging chat rooms the user is subscribed to comprises using a classifier to classify the utterance into a class that matches a chat room name.

15. An apparatus comprising:

at least one processor; and

a memory coupled to the at least one processor, wherein the memory comprises instructions which, when executed by the at least one processor, cause the processor to implement a conversation scope system, comprising a conversation scope controller and a conversation scope extractor, for extending conversation scope in a multi-user messaging platform, wherein the instructions cause the at least one processor to:

capture, by the conversation scope controller executing on the at least one processor of the data processing system, an utterance input by a user into a chat platform;

perform a search of a chat history data structure using enhanced information retrieval (IR), at least one knowledge graph, and machine learning (ML) to find an answer to the utterance;

responsive to determining that a high confidence answer is not found for the utterance, search, by the conversation scope controller, a bot registry data structure for a bot that performs a task requested by the utterance;

responsive to determining that a bot is not found to perform a task requested by the utterance, search, by the conversation scope controller, for an active communication in messaging chat rooms the user is subscribed to and extracting conversation scope to the user;

responsive to determining that a conversation scope is not found in an active communication in messaging chat rooms, searching, by the conversation scope controller, for human exert users who can answer the utterance; and

responsive to determining that human exert users are not found to answer utterance, search, by the conversation scope controller, messaging chat rooms and propose, by the conversation scope controller, a target messaging chat room for the utterance.

16. The apparatus of claim 15 ,

wherein performing the search of the chat history data structure comprises:

generating one or more candidate answers based on entities extracted from the utterance, at least one knowledge graph, and a set of features;

generating a confidence score for each of the one or more candidate answers; and

comparing each confidence score to a threshold value.

17. The apparatus of claim 15 , wherein the instructions further cause the at least one processor to:

responsive to finding a given bot that performs the task requested by the utterance, opening a chat room with the given bot and the user.

18. The apparatus of claim 15 , wherein the instructions further cause the at least one processor to:

responsive to extracting conversation scope, opening a chat room with the extract conversation scope for the user.

19. The apparatus of claim 15 , wherein the instructions further cause the at least one processor to:

responsive to finding one or more human expert users who can answer the utterance, suggesting a direct message or user list including the one or more human expert users to the user.

20. The apparatus of claim 15 , wherein searching for an active communication in messaging chat rooms the user is subscribed to comprises using a classifier to classify the utterance into a class that matches a chat room name.