System and method for answering natural language questions posed by a user

1. A computer-implemented method for answering natural language medical information questions posed by a user of a medical conversational interface of a cognitive artificial intelligence system, the method comprising:

inferring a therapeutic intent of the user from internal medical concepts and medical data entities;

generating a therapeutic paradigm logical framework for interpreting of a medical question, wherein

the therapeutic paradigm logical framework comprises a catalog of medical logical progression paths from the medical question to respective therapeutic answers,

each of the medical logical progression paths comprises one or more medical logical linkages from the medical question to a therapeutic path-specific answer, and

the medical logical linkages comprise the internal medical concepts and external therapeutic paradigm concepts derived from a store of medical subject matter ontology data;

selecting a likely medical information path from among the medical logical progression paths to a likely path-dependent medical information answer based upon the therapeutic intent of the user; and

answering the medical question by following the likely medical information path to the likely path-dependent medical information answer.

2. The computer-implemented method for answering natural language medical information questions posed by a user of a medical conversational interface of a cognitive artificial intelligence system of claim 1 , further comprising relating medical inference groups of the internal medical concepts.

3. The computer-implemented method for answering natural language medical information questions posed by a user of a medical conversational interface of a cognitive artificial intelligence system of claim 2 , wherein the relating medical inference groups of the internal medical concepts further comprises relating groups of the internal medical concepts based at least in part on shared medical data entities for which each internal medical concept of a medical inference group of internal medical concepts describes a respective medical data attribute.

4. The computer-implemented method for answering natural language medical information questions posed by a user of a medical conversational interface of a cognitive artificial intelligence system of claim 1 , wherein selecting a likely medical information path from among the medical logical progression paths to a likely path-dependent medical information answer based upon the intent further comprises selecting a likely medical information path from among the medical logical progression paths to a likely path-dependent medical information answer based in part upon the therapeutic intent of the user and in part upon sufficiency of medical diagnostic data to complete the medical logical linkages.

5. The computer-implemented method for answering natural language medical information questions posed by a user of a medical conversational interface of a cognitive artificial intelligence system of claim 1 , wherein selecting a likely medical information path from among the medical logical progression paths to a likely path-dependent medical information answer based upon the intent further comprises selecting a likely medical information path from among the medical logical progression paths to a likely path-dependent medical information answer after requesting additional medical diagnostic data from the user.

6. The computer-implemented method for answering natural language medical information questions posed by a user of a medical conversational interface of a cognitive artificial intelligence system of claim 1 , wherein selecting a likely medical information path from among the medical logical progression paths to a likely path-dependent medical information answer based upon the intent further comprises selecting a likely medical information path from among the medical logical progression paths to a likely path-dependent medical information answer based in part upon treatment sub-intents comprising tactical constituents related to the therapeutic intent of the user by the store of medical subject matter ontology data.

7. The computer-implemented method for answering natural language medical information questions posed by a user of a medical conversational interface of a cognitive artificial intelligence system of claim 1 , wherein selecting a likely medical information path from among the medical logical progression paths to a likely path-dependent medical information answer based upon the intent further comprises selecting a likely medical information path from among the medical logical progression paths to a likely path-dependent medical information answer based in part upon the therapeutic intent of the user and in part upon sufficiency of medical diagnostic data to complete the medical logical linkages, wherein the medical diagnostic data to complete the medical logical linkages includes user-specific medical diagnostic data.

8. A cognitive intelligence platform for answering natural language questions posed by a user of a conversational interface of an artificial intelligence system, the cognitive intelligence platform comprising:

a cognitive agent configured for receiving from a user interface a user-generated natural language query, wherein the cognitive agent is an artificial intelligence-based conversation agent;

a knowledge cloud containing a store of subject matter ontology data;

a critical thinking engine configured for:

inferring an intent of the user from internal concepts and entities,

generating a logical framework for interpreting of a question, wherein

a logical framework comprises a catalog of paths from the question to respective answers,

each of the paths comprises one or more linkages from the question to a path-specific answer, and

the linkages comprise the internal concepts and external concepts derived from the store of subject matter ontology data,

selecting a likely path from among the paths to a likely path-dependent answer based upon the intent, and

answering the question by following the likely path to the likely path-dependent answer.

9. The cognitive intelligence platform for answering natural language questions posed by a user of a conversational interface of an artificial intelligence system of claim 8 , wherein the critical thinking engine is further configured for relating groups of the internal concepts.

10. The cognitive intelligence platform for answering natural language questions posed by a user of a conversational interface of an artificial intelligence system of claim 8 , wherein the critical thinking engine is further configured for relating groups of the internal concepts by relating groups of the internal concepts based at least in part on shared entities for which each internal concept of a group of internal concepts describes a respective attribute.

11. The cognitive intelligence platform for answering natural language questions posed by a user of a conversational interface of an artificial intelligence system of claim 8 , wherein the critical thinking engine is further configured for selecting a likely path from among the paths to a likely path-dependent answer based upon the intent further comprises selecting a likely path from among the paths to a likely path-dependent answer based in part upon the intent and in part upon sufficiency of data to complete the linkages.

12. The cognitive intelligence platform for answering natural language questions posed by a user of a conversational interface of an artificial intelligence system of claim 8 , wherein the critical thinking engine is further configured for selecting a likely path from among the paths to a likely path-dependent answer based upon the intent further comprises selecting a likely path from among the paths to a likely path-dependent answer after requesting additional data from the user.

13. The cognitive intelligence platform for answering natural language questions posed by a user of a conversational interface of an artificial intelligence system of claim 8 , wherein the critical thinking engine is further configured for selecting a likely path from among the paths to a likely path-dependent answer based upon the intent further comprises selecting a likely path from among the paths to a likely path-dependent answer based in part upon sub-intents comprising tactical constituents related to the intent by the store of subject matter ontology data.

14. The cognitive intelligence platform for answering natural language questions posed by a user of a conversational interface of an artificial intelligence system of claim 8 , wherein the critical thinking engine is further configured for selecting a likely path from among the paths to a likely path-dependent answer based upon the intent further comprises selecting a likely path from among the paths to a likely path-dependent answer based in part upon the intent and in part upon sufficiency of data to complete the linkages, wherein the data to complete the linkages includes user-specific data.

15. A computer program product in a non-transitory computer-readable medium for answering natural language questions posed by a user of a conversational interface of an artificial intelligence system, the computer program product in a computer-readable medium comprising instructions, which, when executed, cause a processor of a computer to perform:

inferring an intent of the user from internal concepts and entities;

generating a logical framework for interpreting of the question, wherein

a logical framework comprises a catalog of paths from the question to respective answers,

each of the paths comprises one or more linkages from the question to a path-specific answer, and

the linkages comprise the internal concepts and external concepts derived from a store of subject matter ontology data;

selecting a likely path from among the paths to a likely path-dependent answer based upon the intent; and

answering the question by following the likely path to the likely path-dependent answer.

16. The computer program product in a non-transitory computer-readable medium for answering natural language questions posed by a user of a conversational interface of an artificial intelligence system of claim 15 , further comprising instructions, which, when executed, cause the processor of the computer to perform relating groups of the internal concepts.

17. The computer program product in a non-transitory computer-readable medium for answering natural language questions posed by a user of a conversational interface of an artificial intelligence system of claim 16 , wherein the instructions, which, when executed, cause the processor of the computer to perform relating groups of the internal concepts further comprise instructions, which, when executed, cause the processor of the computer to perform relating groups of the internal concepts based at least in part on shared entities for which each internal concept of a group of internal concepts describes a respective attribute.

18. The computer program product in a computer-readable medium for answering natural language questions posed by a user of a conversational interface of an artificial intelligence system of claim 15 , wherein the instructions, which, when executed, cause the processor of the computer to perform selecting a likely path from among the paths to a likely path-dependent answer based upon the intent further comprise instructions, which, when executed, cause the processor of the computer to perform selecting a likely path from among the paths to a likely path-dependent answer based in part upon the intent and in part upon sufficiency of data to complete the linkages.

19. The computer program product in a non-transitory computer-readable medium for answering natural language questions posed by a user of a conversational interface of an artificial intelligence system of claim 15 , wherein instructions, which, when executed, cause the processor of the computer to perform selecting a likely path from among the paths to a likely path-dependent answer based upon the intent further comprise instructions, which, when executed, cause the processor of the computer to perform selecting a likely path from among the paths to a likely path-dependent answer after requesting additional data from the user.

20. The computer program product in a non-transitory computer-readable medium for answering natural language questions posed by a user of a conversational interface of an artificial intelligence system of claim 15 , wherein the instructions, which, when executed, cause the processor of the computer to perform selecting a likely path from among the paths to a likely path-dependent answer based upon the intent further comprise instructions, which, when executed, cause the processor of the computer to perform selecting a likely path from among the paths to a likely path-dependent answer based in part upon sub-intents comprising tactical constituents related to the intent by the store of subject matter ontology data.