US 12,229,150 B2
Intelligent compute request scoring and routing
Matthew Lynch, Brooklyn, NY (US); Brandon Krieger, New York, NY (US); Giulio Mecocci, Brooklyn, NY (US); Kyle Patron, Philadelphia, PA (US); Kevin Pyc, New York, NY (US); and Sander Kromwijk, New York, NY (US)
Assigned to Palantir Technologies Inc., Denver, CO (US)
Filed by Palantir Technologies Inc., Palo Alto, CA (US)
Filed on Feb. 18, 2020, as Appl. No. 16/793,881.
Application 16/793,881 is a continuation of application No. 16/175,371, filed on Oct. 30, 2018, granted, now 10,606,851.
Claims priority of provisional application 62/729,204, filed on Sep. 10, 2018.
Prior Publication US 2020/0183945 A1, Jun. 11, 2020
This patent is subject to a terminal disclaimer.
Int. Cl. G06F 16/2457 (2019.01); G06F 9/50 (2006.01)
CPC G06F 16/24578 (2019.01) [G06F 9/5027 (2013.01)] 21 Claims
OG exemplary drawing
 
1. A system comprising:
one or more computer processors configured to execute computer-executable instructions to cause the system to at least:
receive, via a user input, a query indicating a request to perform a processing operation on a portion of one or more data sets;
determine that the query includes user defined code for running by a back-end computer resource, the user defined code including a custom script to perform specific operations;
determine one or more scores associated with the query, including at least:
a first score based at least in part on the query including the user defined code, wherein the first score indicates a level of risk of executing the user defined code; and
a second score based at least in part on a scope of the processing operation including one or more of a type of processing being performed or a size of the one or more data sets being processed;
in response to determining that the query includes user defined code, filter a set of back-end resources to exclude back-end resources not configured to execute the user defined code;
determine, based on the received query, the determined one or more scores, and historical information of prior processing outcomes, a back-end resource of the filtered set of back-end resources to execute the query;
determine a stop parameter based on the user defined code, the stop parameter indicating one or more of a run-time limit, a memory usage limit, or a post-processing action configured to stop the determined back-end computer resource;
generate a compute request including the query and the stop parameter; and
provide the compute request to the determined back-end computer resource.