US 11,836,032 B2
Error monitoring and prevention in computing systems based on determined trends and routing a data stream over a second network having less latency
Michael Shawn Jacob, LeRoy, IL (US); Benjamin D. Schappaugh, Bloomington, IL (US); William Guthrie, Mesa, AZ (US); Frank Matthew McCully, Hudson, IL (US); Timothy J. Nickel, Bloomington, IL (US); Brian W. Batronis, Gilbert, AZ (US); and Robert D. Rariden, Bloomington, IL (US)
Assigned to State Farm Mutual Automobile Insurance Company, Bloomington, IL (US)
Filed by State Farm Mutual Automobile Insurance Company, Bloomington, IL (US)
Filed on Oct. 14, 2021, as Appl. No. 17/501,231.
Claims priority of provisional application 63/092,119, filed on Oct. 15, 2020.
Prior Publication US 2022/0121509 A1, Apr. 21, 2022
Int. Cl. G06F 11/07 (2006.01); G06F 11/00 (2006.01); G06N 20/00 (2019.01)
CPC G06F 11/004 (2013.01) [G06F 11/0754 (2013.01); G06N 20/00 (2019.01)] 20 Claims
OG exemplary drawing
 
1. A computing system associated with a first organization, comprising:
one or more processors; and
one or more computer-readable media storing instructions which, when executed by the one or more processors, cause the one or more processors to:
receive a plurality of data streams from a plurality of computing devices via one or more networks, wherein a first computing device of the plurality of computing devices is associated with the first organization and a second computing device of the plurality of computing devices is associated with a second organization that is different from the first organization;
determine a current value of a characteristic associated with a first data stream of the plurality of data streams, the first data stream being received from the first computing device via a first network of the one or more networks, the first network characterized by a first latency;
access historical data associated with the first data stream, wherein the historical data includes values of the characteristic over a first period of time;
identify a trend associated with the first data stream based at least in part on the current value of the characteristic and the historical data;
predict, based at least in part on the trend, that a future value of the characteristic will be greater than or equal to a threshold value after a second period of time;
determine, based on predicting that the future value will be greater than or equal to the threshold value, a potential future fault associated with the first network or the first computing device;
based at least in part on the potential future fault, identify a second network of the one or more networks having a second latency that is less than the first latency;
identify an action to perform based at least in part on the potential future fault. wherein the action includes routing the first data stream over the second network; and
cause the action to be performed, wherein performing the action prevents the potential future fault from occurring.