Cognitive computing using a plurality of model structures

1. A method of populating a data set, the method comprising:

generating a plurality of models that model the behavior of an agent process, wherein the plurality of models comprises:

a first model;

a second model; and

a third model;

using the plurality of models to generate one or more requests for one or more external data sources, wherein the one or more requests request information that is missing from the data set that is associated with a first user;

using the plurality of models to select a plurality of queries from a data store of predefined queries, wherein the plurality of queries are selected by the plurality of models to request information from the first user that is missing from the data set;

populating at least a portion of the data set using information received in response to:

the one or more requests for the one or more external data sources; and

the plurality of queries.

2. The method of claim 1 , further comprising:

storing a history of queries and information received in response to the queries for users other than the first user;

identifying one or more patterns from the history of queries and information received in response to the queries; and

using the one or more patterns to select the plurality of queries from the data store of predefined queries.

3. The method of claim 2 , further comprising:

altering a decision logic layer of the plurality of models based on the one or more patterns.

4. The method of claim 2 , further comprising:

clustering users based on whether the information received in response to the queries was accurate.

5. The method of claim 1 , wherein the plurality of queries are selected based on a role of a second user.

6. The method of claim 1 , further comprising:

determining, by the plurality of models, whether information received in response to the plurality of queries should replace information received in response to the one or more requests for the one or more external data sources in the data set.

7. The method of claim 1 , wherein the plurality of queries are selected based on an objective received from the first user.

8. The method of claim 1 , wherein the first model comprises a Business Process Modeling Notation (BPMN) model.

9. The method of claim 1 , wherein the second model comprises a Case Management Model and Notation (CMMN) model.

10. The method of claim 1 , wherein the third model comprises a Decision Model and Notation (DMN) model.

11. A system comprising:

one or more processors; and

one or more memory devices comprising instructions that, when executed by the one or more processors, cause the one or more processors to perform operations comprising:

generating a plurality of models that model the behavior of an agent process, wherein the plurality of models comprises:

a first model;

a second model; and

a third model;

using the plurality of models to generate one or more requests for one or more external data sources, wherein the one or more requests request information that is missing from the data set that is associated with a first user;

using the plurality of models to select a plurality of queries from a data store of predefined queries, wherein the plurality of queries are selected by the plurality of models to request information from the first user that is missing from the data set;

populating at least a portion of the data set using information received in response to:

the one or more requests for the one or more external data sources; and

the plurality of queries.

12. The system of claim 11 , further comprising a conversational API that is configured to manage a history of query sets and corresponding responses in one or more linked communication sessions.

13. The system of claim 11 , further comprising a content API that is configured to receive topic codes and return query sets corresponding to each of the topic codes.

14. The system of claim 11 , the operations further comprising:

clustering users based on whether the information received in response to the queries was accurate.

15. The system of claim 11 , wherein the plurality of queries are selected based on a role of a second user.

16. The system of claim 11 , the operations further comprising:

determining, by the plurality of models, whether information received in response to the plurality of queries should replace information received in response to the one or more requests for the one or more external data sources in the data set.

17. The system of claim 11 , wherein the plurality of queries are selected based on an objective received from the first user.

18. A non-transitory, computer-readable medium comprising instructions that, when executed by one or more processors, cause the one or more processors to perform operations comprising:

generating a plurality of models that model the behavior of an agent process, wherein the plurality of models comprises:

a first model;

a second model; and

a third model;

using the plurality of models to generate one or more requests for one or more external data sources, wherein the one or more requests request information that is missing from the data set that is associated with a first user;

using the plurality of models to select a plurality of queries from a data store of predefined queries, wherein the plurality of queries are selected by the plurality of models to request information from the first user that is missing from the data set;

populating at least a portion of the data set using information received in response to:

the one or more requests for the one or more external data sources; and

the plurality of queries.

19. The non-transitory, computer-readable medium of claim 18 , the operations further comprising:

storing a history of queries and information received in response to the queries for users other than the first user;

identifying one or more patterns from the history of queries and information received in response to the queries; and

using the one or more patterns to select the plurality of queries from the data store of predefined queries.

20. The non-transitory, computer-readable medium of claim 18 , the operations further comprising:

determining, by the plurality of models, whether information received in response to the plurality of queries should replace information received in response to the one or more requests for the one or more external data sources in the data set.