AI-based data virtualization

1. A computer-implemented method, comprising:

determining a context of a data access request for a data virtualization engine;

determining a plurality of data sources that are relevant to the data access request by using a governance machine learning model, wherein the governance machine learning model is trained to predict the data sources based on the data access request and the context;

determining, before performing the data access request, a plurality of data governance rules-policies that are relevant to the data access request, by using the governance machine learning model, wherein the governance machine learning model is further trained to predict the plurality of data governance rules-policies based on the data sources and the context, and wherein the plurality of data governance rules-policies defines a corresponding plurality of data regulations based on a plurality of legal jurisdictions associated with a plurality of legal responsibilities; and

generating, by using a query machine learning model, a data access command executable by the data virtualization engine that is configured to retrieve data from the data sources and apply the plurality of determined data governance rules-policies, wherein generating the data access command comprises automatically translating the determined data governance rules-policies into QUERY understandable format, and wherein automatically translating the determined data governance rules comprises:

using semantic analytics on the determined data governance rules-policies; and

applying machine learning techniques.

2. The method of claim 1 , wherein the machine learning techniques comprise one selected from a group consisting of:

supervised learning; and

unsupervised learning.

3. The method of claim 1 , further comprising generating a visualization of a result generated by the data virtualization engine, wherein the result comprises an actual data result and a masked result.

4. The method of claim 3 , wherein the visualization comprises a multi-dimensional visualization.

5. The method of claim 1 , wherein the governance machine learning model learns to generate an exception data governance rule-policy based on training data comprising one or more historical data access requests that are related to the data access request, and one or more associated historical data governance rule-policies.

6. The method of claim 1 , further comprising generating a result for the data access request using the data virtualization engine and the data access command.

7. The method of claim 1 , wherein the governance machine learning model is trained to determine a context for the data access request using historical changes to the determined data governance rules-policies.

8. The method of claim 1 , wherein the determined data governance rules-policies comprise one selected from a group consisting of:

text documents;

video recordings;

images; and

email.

9. The method of claim 1 , wherein the data access command comprises a structured query language command.

10. The method of claim 1 , further comprising:

aggregating a plurality of results generated by the data sources; and

providing the aggregated results for a client that provides the data access request.

11. A computer program product comprising one or more computer readable storage media, and program instructions collectively stored on the one or more computer readable storage media, the program instructions comprising instructions configured to cause one or more processors to perform a method comprising:

determining a context of a data access request for a data virtualization engine;

determining, before performing the data access request, a plurality of data governance rules-policies that are relevant to the data access request, by using a governance machine learning model, wherein the governance machine learning model is further trained to predict the data governance rules-policies based on the data sources and the context, and wherein the plurality of data governance rules-policies defines a corresponding plurality of data regulations based on a plurality of legal jurisdictions associated with a plurality of legal responsibilities; and

generating, by using a query machine learning model, a data access command executable by the data virtualization engine that is configured to retrieve data from the data sources and apply the plurality of determined data governance rules-policies, wherein generating the data access command comprises automatically translating the determined data governance rules-policies into QUERY understandable format, and wherein automatically translating the determined data governance rules comprises:

using semantic analytics on the determined data governance rules-policies; and

applying machine learning techniques.

12. The computer program product of claim 11 , wherein automatically translating the determined data governance rules comprises:

using semantic analytics on the determined data governance rules-policies; and

applying machine learning techniques.

13. The computer program product of claim 11 , further comprising generating a visualization of a result generated by the data virtualization engine, wherein the result comprises an actual data result and a masked result.

14. The computer program product of claim 13 , wherein the visualization comprises a multi-dimensional visualization.

15. The computer program product of claim 11 , wherein the governance machine learning model learns to generate an exception data governance rule-policy based on training data comprising one or more historical data access requests that are related to the data access request, and one or more associated historical data governance rule-policies.

16. The computer program product of claim 11 , wherein the data determined governance rules-policies comprise one selected from a group consisting of:

text documents;

video recordings;

images; and

email.

17. A system comprising:

one or more computer processing circuits; and

one or more computer-readable storage media storing program instructions which, when executed by the one or more computer processing circuits, are configured to cause the one or more computer processing circuits to perform a method comprising:

determining a context of a data access request for a data virtualization engine;

determining a plurality of data sources that are relevant to the data access request by using a governance machine learning model, wherein the governance machine learning model is trained to predict the data sources based on the data access request and the context;

determining, before performing the data access request, a plurality of data governance rules-policies that are relevant to the data access request, by using the governance machine learning model, wherein the governance machine learning model is further trained to predict the data governance rules-policies based on the data sources and the context, and wherein the plurality of data governance rules-policies defines a corresponding plurality of data regulations based on a plurality of legal jurisdictions associated with a plurality of legal responsibilities; and

generating, by using a query machine learning model, a data access command executable by the data virtualization engine that is configured to retrieve data from the data sources and apply the determined data governance rules-policies, wherein generating the data access command comprises automatically translating the determined data governance rules-policies into QUERY understandable format, and wherein automatically translating the determined data governance rules comprises:

using semantic analytics on the determined data governance rules-policies; and

applying machine learning techniques.

18. The system of claim 17 , wherein the governance machine learning model learns to generate an exception data governance rule-policy based on training data comprising one or more historical data access requests that are related to the data access request, and one or more associated historical data governance rule-policies.