US 11,860,756 B2
Automated system alert based on logs sentiment analysis
Dinesh Babu Yeddu, Guntur (IN); Sundaravelu Shanmugam, Bangalore (IN); and Raju Karuppiah, Bangalore (IN)
Assigned to KYNDRYL, INC., New York, NY (US)
Filed by KYNDRYL, INC., New York, NY (US)
Filed on Oct. 1, 2021, as Appl. No. 17/492,040.
Prior Publication US 2023/0103840 A1, Apr. 6, 2023
Int. Cl. G06F 11/00 (2006.01); G06F 11/32 (2006.01); G06F 11/34 (2006.01); G06F 40/30 (2020.01); G06F 40/237 (2020.01)
CPC G06F 11/327 (2013.01) [G06F 11/3428 (2013.01); G06F 11/3476 (2013.01); G06F 40/237 (2020.01); G06F 40/30 (2020.01)] 20 Claims
OG exemplary drawing
 
1. A computer implemented method comprising:
creating, by one or more processors, a log data specific lexicon based on log data samples, each word in the log data specific lexicon corresponding to a weighted sentiment score with a binary polarity;
obtaining, by the one or more processors, a log message from a computing platform;
assigning, by the one or more processors, a sentiment value to the log message based on respective weighted sentiment scores by the log data specific lexicon corresponding to words appearing in the log message;
classifying, by the one or more processors, the log message for a class indicating an issue the log message addresses;
determining, by the one or more processors, an alert type for the log message based on the sentiment value, the class, and a priority of the log message, wherein the alert type is preconfigured with a set of alert type values of varying risk levels; and
producing, by the one or more processors, a system alert to a user according to the alert type for the log message, wherein the system alert comprises a predefined set of key performance indicators corresponding to the alert type to thereby inform the user on the issue addressed by the log message.