Interactive and dynamic mapping engine (IDME)
Methods, systems, and apparatuses, among other things, may provide for an interactive dynamic mapping engine (IDME) for business intelligence, which may interactively obtain information for user devices from sources and schema unknown to the user devices.
1. A method comprising:
at a learning phase, building, by an adaptive machine learning model based on a pattern of inputs from a user device, a user query profile, wherein the user query profile comprises learned patterns of queries included in the pattern of inputs;
returning, by the adaptive machine learning model, a result of the queries;
at a grow phase, integrating, by the adaptive machine learning model, the learned patterns in the user query profile with a first base model of the adaptive machine learning model responsive to a positive evaluation of the result of the queries;
staging, by the adaptive machine learning model, based on the first base model and the queries, a self-learning model of the adaptive machine learning model;
at a mature phase, discerning, by the adaptive machine learning model, based on the first base model and the self-learning model, a mature usage pattern;
at an evolution phase, integrating, by the adaptive machine learning model, the mature usage pattern with the first base model to form a matured model; and
activating, by the adaptive machine learning model, the matured model as a second base model for future evolutions of the adaptive machine learning model.
2. The method of claim 1 , further comprising:
identifying, by the adaptive machine learning model based on the self-learning model, a query that was abandoned; and
adjusting, by the adaptive machine learning model, the self-learning model to deemphasize the learned patterns of the queries or a result associated with the abandoned query.
3. The method of claim 1 , wherein the first base model includes a starting knowledge base for novice users.
4. The method of claim 3 , wherein the discerning the mature usage pattern is based on determining a number of user inputs satisfies a pattern threshold.
5. The method of claim 3 , wherein the discerning the mature usage pattern is based on determining a number of user inputs fail to satisfy a pattern threshold.
6. The method of claim 3 , wherein the discerning the mature usage pattern includes determining a number of matured patterns reaches a matured pattern threshold value.
7. The method of claim 6 , wherein the discerning the mature usage pattern includes adapting the mature usage pattern based on a satisfaction comparison.
8. The method of claim 3 , further comprising evaluating, by the adaptive machine learning model, the result of the queries, wherein the discerning the mature usage pattern is based on the positive evaluation of the result of the queries.
9. A system comprising:
a processor; and
a memory including instructions that, when executed by the processor, cause the system to:
at a learning phase, build, by a machine learning model based on a pattern of inputs from a user device, a user query profile, wherein the user query profile comprises learned patterns of queries included in the pattern of inputs;
return, by the machine learning model, a result of the queries;
at a grow phase, integrate, by the machine learning model, the learned patterns of queries in the user query profile with a first base model of the machine learning model responsive to a positive evaluation of the result of the queries;
stage, by the machine learning model, based on the first base model and the queries, a self-learning model of the machine learning model;
at a mature phase, discern, by the machine learning model based on the first base model and the self-learning model, a mature usage pattern;
at an evolution phase, integrate, by the machine learning model, the mature usage pattern with the first base model to form a matured model; and
activate, by the machine learning model, the matured model as a second base model for future evolutions of the machine learning model.
10. The system of claim 9 , wherein the instructions are further configured to cause the system to:
identify, by the machine learning model based on the self-learning model, a query replaced by a new query without selecting of results of the query; and
adjusting, by the machine learning model, the self-learning model to deemphasize the learned patterns or a result associated with the query.
11. The system of claim 9 , wherein the first base model includes a starting knowledge base for novice users.
12. The system of claim 9 , wherein the discerning the mature usage pattern is based on determining a number of user inputs satisfies a pattern threshold.
13. The system of claim 9 , wherein the discerning the mature usage pattern is based on determining a number of user inputs fail to satisfy a pattern threshold.
14. The system of claim 9 , wherein the discerning the mature usage pattern includes determining a number of matured patterns reaches a matured pattern threshold value.
15. The system of claim 9 , wherein the instructions are further configured to cause the system to evaluate, by the machine learning model the result of the queries, wherein the discerning the mature usage pattern is based on the positive evaluation of the result of the queries.
16. The system of claim 15 , wherein the discerning the mature usage pattern includes adapting the mature usage pattern based on a satisfaction comparison.
17. A computer program product comprising:
a non-transitory computer-readable storage medium; and
instructions stored on the non-transitory computer-readable storage medium that, when executed by a processor, causes the processor to:
at a learning phase, build, by a machine learning model based on a pattern of inputs from a user device, a user query profile, wherein the user query profile comprises learned patterns of queries included in the pattern of inputs;
return, by the machine learning model, a result of the queries;
at a grow phase, integrate, by the machine learning model, the learned patterns in the user query profile with a first base model of the machine learning model responsive to a positive evaluation of the result of the queries;
stage, by the machine learning model, based on the first base model and the queries, a self-learning model of the machine learning model;
at a mature phase, discern, by the machine learning model, based on the first base model and the self-learning model, a mature usage pattern;
at an evolution phase, integrate, by the machine learning model, the mature usage pattern with the first base model to form a matured model; and
activate, by the machine learning model, the matured model as a second base model for future evolutions of the machine learning model.
18. The computer program product of claim 17 wherein the instructions are further configured to cause the processor to:
identify, by the machine learning model, based on the self-learning model, a query replaced by a new query without selecting of results of the query; and
adjusting, by the machine learning model, the self-learning model to deemphasize the learned patterns or a result associated with the query.
19. The computer program product of claim 17 , wherein the first base model includes a starting knowledge base for novice users.
20. The computer program product of claim 17 , wherein the discerning the mature usage pattern is based on determining a number of user inputs satisfies a pattern threshold.