US 11,755,402 B1
Self-healing information technology (IT) testing computer system leveraging predictive method of root cause analysis
Raju Chavan, Overland Park, KS (US); and Aaron R. Haehn, Olathe, KS (US)
Assigned to T-MOBILE INNOVATIONS LLC, Overland Park, KS (US)
Filed by Sprint Communications Company L.P., Overland Park, KS (US)
Filed on Feb. 1, 2021, as Appl. No. 17/164,806.
Int. Cl. G06F 11/00 (2006.01); G06F 11/07 (2006.01); G06F 11/36 (2006.01); G06N 20/00 (2019.01)
CPC G06F 11/079 (2013.01) [G06F 11/3664 (2013.01); G06F 11/3684 (2013.01); G06F 11/3688 (2013.01); G06N 20/00 (2019.01)] 20 Claims
OG exemplary drawing
 
1. A method of performing root cause analysis of communication system testing results, submitting communication system defect tickets along with associated previously resolved communication system defect tickets that provide insights for repairing the communication system defects, and analyzing previously resolved communication system defect tickets to update a machine learning test error categorization engine, comprising:
receiving logs from communication system applications undergoing test by a machine learning test error categorization engine executing on a computer system;
categorizing a plurality of error messages in the logs received from the communication system applications by the machine learning test error categorization engine based on a plurality of pre-defined categorization rules, wherein each of the plurality of error messages is categorized as a test data error, a test environment error, a test case error, or a valid error;
for each error message categorized as a test data error by the machine learning test error categorization engine, automatically remediating the test data error and rerunning a test case that generated the error message by a test data error handling script executing on the computer system;
for each error message categorized as a test environment error by the machine learning test error categorization engine, accessing a test environment monitoring system by a test environment error handling script executing on the computer system to determine if a test environment outage associated with the error message categorized as a test environment error has been reported;
if a test environment outage associated with the error message categorized as a test environment error by the machine learning test error categorization engine has not been reported, sending a notification about the outage associated with the test environment by the test environment error handling script;
if a test environment outage associated with the error message categorized as a test environment error by the machine learning test error categorization engine has been reported, sending a notification to a tester about the reported test environment outage by the test environment error handling script;
for each error message categorized as a test case error by the machine learning test error categorization engine, searching a communication system defect ticket data store by a test case error handling script executing on the computer system to identify previously resolved communication system defect tickets that match the test case error;
for each error message categorized as a test case error by the machine learning test error categorization engine, sending a notification to a tester by the test case error handling script indicating the error message was categorized as a test case error and identifying the previously resolved communication system defect tickets found to match the test case error;
for each error message categorized as a valid error by the machine learning test error categorization engine, searching the communication system defect ticket data store by a valid error handling script executing on the computer system to identify previously resolved communication system defect tickets that match the valid error;
for each error message categorized as a valid error by the machine learning test error categorization engine, generating a communication system defect ticket by the valid error handling script that describes the error message categorized as a valid error and identifies at least some of the previously resolved communication system defect tickets that match the valid error;
analyzing the previously resolved communication system defects by the machine learning test error categorization engine;
synthesizing new categorization rules by the machine learning test error categorization engine based on analyzing the previously resolved communication system defects; and
training the machine learning test error categorization engine according to the new categorization rules to enable the machine learning test error categorization engine to categorize subsequent error messages according to the new categorization rules.