CPC G06F 16/24542 (2019.01) [G06F 16/2455 (2019.01); G06F 16/287 (2019.01)] | 20 Claims |
1. A method, comprising:
receiving, via a processor, a plurality of queries from a client device;
receiving, via the processor, execution statistics for each of the plurality of queries;
determining, via the processor, one or more topics based on one or more characteristics of the plurality of queries;
grouping, via the processor, the plurality of queries into the one or more topics;
calculating, via the processor, execution statistics for each topic of the one or more topics, based upon the execution statistics of queries of a corresponding topic;
applying, via the processor, the plurality of queries and the execution statistics associated with each of the plurality of queries to a machine learning model to identify potentially relevant characteristics of the plurality of queries that result in a threshold level of divergent execution between two or more of the plurality of queries;
providing, to a downstream system, an indication of the execution statistics and the potentially relevant characteristics for each topic of the one or more topics;
performing, based on the execution statistics, an efficiency simulation;
identifying, based on the efficiency simulation, an optimized scheduling for the plurality of queries; and
providing an electronic indication of the identified optimized scheduling of the plurality of queries, wherein the electronic indication comprises an electronic instruction to render a graphical user interface (GUI), the GUI comprising a scheduling recommendation, a recommended time of query execution, one or more recommended topics, and one or more recommended cloud computing resources available for purchase from a cloud service provider by which to execute the queries.
|