US 11,921,720 B1
Systems and methods for decoupling search processing language and machine learning analytics from storage of accessed data
Chinmay Madhav Kulkarni, Sunnyvale, CA (US); Lin Ma, Burnaby (CA); Amir Malekpour, Vancouver (CA); Mohan Rajagopalan, Mountain View, CA (US); John C. Reed, Saratoga, CA (US); and Ram Sriharsha, Oakland, CA (US)
Assigned to Splunk Inc., San Francisco, CA (US)
Filed by SPLUNK Inc., San Francisco, CA (US)
Filed on Nov. 1, 2022, as Appl. No. 17/978,684.
Application 17/978,684 is a continuation of application No. 17/074,100, filed on Oct. 19, 2020.
Int. Cl. G06F 16/2453 (2019.01); G06F 16/2455 (2019.01); G06N 20/00 (2019.01)
CPC G06F 16/24549 (2019.01) [G06F 16/2455 (2019.01); G06N 20/00 (2019.01)] 20 Claims
OG exemplary drawing
 
1. A computer-implemented method, comprising:
receiving a query comprised of a sequence of operators;
parsing the query to detect each operator of the sequence of operators, wherein the sequence of operators includes a machine learning (ML) operator that represents a trained ML model;
retrieving metadata of the ML operator indicating a schema of the ML operator;
generating either a filter or a projection configured to reduce an amount of data retrieved upon application of the filter or projection to an operator of the sequence of operators comprising the query, wherein generating of the filter or the projection is based at least in part on the schema of the ML operator; and
executing the query on data of a first data source including application of the filter or the projection and processing by the ML operator thereby obtaining a query result.