Microsoft Technology Licensing, LLC

Rakesh Namineni

Udayan Kumar

Mohit Verma

Qingwei Lin

Si Qin

Kamaljit S Bath

Bo Qiao

Ramanathan Muthiah

Jian Zhang

Yingnong Dang

Yu Kang

Suneel Suresh

Ananth Geethanath

Chitra Mandyam

Cole Robert Fornia

Michael David Helm

Manoj Kumar

Nishant R Bhatt

Julien Hoachuck

Namrata Jain

Jeffrey Ding He

Pooja Rani

Jimmy Wong

The present disclosure relates to methods, systems, and computer readable media for analyzing log files for a wide variety of services (e.g., cloud computing services or microservices) to determine whether the services are operating as designed over some period of time associated with the log file(s). The present disclosure includes features and functionality for training or otherwise generating a model being configured to predict whether portions of an input log file include data reflective of normal operations of a corresponding service used to generate the input log file. The present disclosure provides a domain-agnostic approach to training an outlier detection model to analyze log files for a wide variety of services.

Training and implementing a steady state log analyzer

Methods and systems for detecting systemwide service issues by using anomaly localization. In an example, a method includes receiving time-series monitoring data for multiple services, the time-series monitoring data including multiple dimensions and an error metric; for the monitoring data from each service, evaluating scopes within the monitoring data based on an objective function for a time-series of the error metric to identify at least one anomalous scope, each scope including at least one dimension and a value for the dimension; based on evaluating the scopes, generating a ranked list of scopes for each service based on objective function scores for the scopes; correlating the ranked lists of scopes across the multiple services to identify a cross-service anomaly; and generating an alert for the services based on the cross-service anomaly, the alert indicating at least one scope as a potential root cause for the cross-service anomaly.

Detecting systemwide service issues by using anomaly localization

Techniques for managing support computing services in computing systems are disclosed. One example technique includes analyzing data representing a service ticket having data representing multiple messages exchanged between the user and a support entity of a support tier in the computing system. Based on the analysis, an interaction pattern in the multiple messages can be identified. The interaction pattern includes a sequence of words or phrases arranged in a chronological order. The method can further include determining whether the identified interaction pattern matches one or more interaction patterns corresponding to previously escalated service tickets and triggering a notification of the immediate escalation of the service ticket to another support entity in another support tier in response to determining that the interaction pattern matches one of the one or more interaction patterns corresponding to previously escalated service tickets.

Service ticket escalation based on interaction patterns

A system may include a processing unit; a storage device comprising instructions, which when executed by the processing unit, configure the processing unit to perform operations comprising: retrieving a meeting count of meetings scheduled during a future time period; generating a predicted usage level of a service during the future time period based on the meeting count; determining a resource modification for the service based on the predicted usage level; and implementing the resource modification prior to the future time period.

Predictive system resource allocation

A system may include a processing unit; a storage device comprising instructions, which when executed by the processing unit, configure the processing unit to perform operations comprising: receiving a service outage alert for a service used by an entity; retrieving a current count of non-recurring meetings for the entity; determining that the service outage alert is a false positive based on a current service load for the service and the current count; and based on the determining, suppressing the service outage alert.

System for suppressing false service outage alerts

Growing community of inventors

Sammamish, WA, United States of America

Rakesh Namineni