Identifying and processing poly-process natural language queries

1. A computer-based method of identifying and processing poly-process natural language queries, the method comprising:

receiving a natural language query;

automatically identifying a bridge entity in the received natural language query;

automatically determining whether the received natural language query is a poly-process query based on one or more query tokens in the received natural language query having matches in at least a first ontology, and at least one or more additional query tokens in the received natural language query having matches in at least a second ontology;

in response to determining that the received natural language query is the poly-process query, automatically generating sub-queries for each process in the poly-process query and generating results for each sub-query;

automatically combining the results of each sub-query using the bridge entity to output a combined result;

automatically generating a modified sub-query for post-processing of the combined result; and

automatically processing the modified sub-query to generate a final query result for the received natural language query.

2. The computer-based method of claim 1 , wherein automatically identifying the bridge entity in the received natural language query further comprises:

comparing the first ontology to the second ontology to identify one or more common concepts in the received natural language query.

3. The computer-based method of claim 1 , wherein automatically generating the sub-queries for each process in the poly-process query further comprises:

generating a first sub-query including language from the received natural language query based on the first ontology and a corresponding a first process; and

generating a second sub-query including language from the received natural language query based on the second ontology and a corresponding to a second process.

4. The computer-based method of claim 1 , wherein automatically identifying the bridge entity in the received natural language query further comprises:

identifying the bridge entity in the received natural query based on a score-based probability extracted from machine learning.

5. The computer-based method of claim 1 , wherein automatically generating the sub-queries for each process in the poly-process query further comprises:

identifying one or more joint operations that apply to each of the sub-queries and delaying the processing of the one or more joint operation until post-processing of the modified sub-query.

6. The computer-based method of claim 5 , wherein automatically generating the modified sub-query for post-processing of the combined result further comprises:

processing the one or more joint operations in the modified sub-query.

7. A computer system, the computer system comprising:

one or more processors, one or more computer-readable memories, one or more computer-readable tangible storage medium, and program instructions stored on at least one of the one or more computer-readable tangible storage medium for execution by at least one of the one or more processors via at least one of the one or more computer-readable memories, wherein the computer system is capable of performing a method comprising:

receiving a natural language query;

automatically identifying a bridge entity in the received natural language query;

automatically determining whether the received natural language query is a poly-process query based on one or more query tokens in the received natural language query having matches in at least a first ontology, and at least one or more additional query tokens in the received natural language query having matches in at least a second ontology;

in response to determining that the received natural language query is the poly-process query, automatically generating sub-queries for each process in the poly-process query and generating results for each sub-query;

automatically combining the results of each sub-query using the bridge entity to output a combined result;

automatically generating a modified sub-query for post-processing of the combined result; and

automatically processing the modified sub-query to generate a final query result for the received natural language query.

8. The computer system of claim 7 , wherein automatically identifying the bridge entity in the received natural language query further comprises:

comparing the first ontology to the second ontology to identify one or more common concepts in the received natural language query.

9. The computer system of claim 7 , wherein automatically generating the sub-queries for each process in the poly-process query further comprises:

generating a first sub-query including language from the received natural language query based on the first ontology and a corresponding first process; and

generating a second sub-query including language from the received natural language query based on the second ontology and corresponding second process.

10. The computer system of claim 7 , wherein automatically identifying the bridge entity in the received natural language query further comprises:

identifying the bridge entity in the received natural query based on a score-based probability extracted from machine learning.

11. The computer system of claim 7 , wherein automatically generating the sub-queries for each process in the poly-process query further comprises:

identifying one or more joint operations that apply to each of the sub-queries and delaying the processing of the one or more joint operations until post-processing of the modified sub-query.

12. The computer system of claim 11 , wherein automatically generating the modified sub-query for post-processing of the combined result further comprises:

processing the one or more joint operations in the modified sub-query.

13. A computer program product, the computer program product comprising:

one or more computer-readable tangible storage medium and program instructions stored on at least one of the one or more computer-readable tangible storage medium, the program instructions executable by a processor capable of performing a method, the method comprising:

receiving a natural language query;

automatically identifying a bridge entity in the received natural language query;

automatically determining whether the received natural language query is a poly-process query based on one or more query tokens in the received natural language query having matches in at least a first ontology, and at least one or more additional query tokens in the received natural language query having matches in at least a second ontology;

in response to determining that the received natural language query is the poly-process query, automatically generating sub-queries for each process in the poly-process query and generating results for each sub-query;

automatically combining the results of each sub-query using the bridge entity to output a combined result;

automatically generating a modified sub-query for post-processing of the combined result; and

automatically processing the modified sub-query to generate a final query result for the received natural language query.

14. The computer program product of claim 13 , wherein automatically identifying the bridge entity in the received natural language query further comprises:

comparing the first ontology to the second ontology to identify one or more common concepts in the received natural language query.

15. The computer program product of claim 14 , wherein automatically generating the sub-queries for each process in the poly-process query further comprises:

generating a first sub-query including language from the received natural language query based on the first ontology and a corresponding to a first process; and

generating a second sub-query including language from the received natural language query based on the second ontology and a corresponding second process.

16. The computer program product of claim 13 , wherein automatically identifying the bridge entity in the received natural language query further comprises:

identifying the bridge entity in the received natural query based on a score-based probability extracted from machine learning.

17. The computer program product of claim 13 , wherein automatically generating the sub-queries for each process in the poly-process query further comprises:

identifying one or more joint operations that apply to each of the sub-queries and delaying the processing of the one or more joint operations until post-processing of the modified sub-query.