View source for 18227877. MACHINE LEARNING AIDED DIAGNOSIS AND PROGNOSIS OF LARGE SCALE DISTRIBUTED SYSTEMS simplified abstract (Microsoft Technology Licensing, LLC)

=MACHINE LEARNING AIDED DIAGNOSIS AND PROGNOSIS OF LARGE SCALE DISTRIBUTED SYSTEMS=


==Organization Name==

[[:Category:Microsoft Technology Licensing, LLC|Microsoft Technology Licensing, LLC]]


[[Category:Microsoft Technology Licensing, LLC]]

==Inventor(s)==

[[:Category:Ravi Teja Bellam of Redmond WA (US)|Ravi Teja Bellam of Redmond WA (US)]][[Category:Ravi Teja Bellam of Redmond WA (US)]]

[[:Category:Rohith Reddy Gundreddy of Redmond WA (US)|Rohith Reddy Gundreddy of Redmond WA (US)]][[Category:Rohith Reddy Gundreddy of Redmond WA (US)]]

[[:Category:Woo Sik Kim of Redmond WA (US)|Woo Sik Kim of Redmond WA (US)]][[Category:Woo Sik Kim of Redmond WA (US)]]

[[:Category:Vineeth Thayanithi of Naperville IL (US)|Vineeth Thayanithi of Naperville IL (US)]][[Category:Vineeth Thayanithi of Naperville IL (US)]]

[[:Category:Neil Patrick Gompf of Redmond WA (US)|Neil Patrick Gompf of Redmond WA (US)]][[Category:Neil Patrick Gompf of Redmond WA (US)]]

[[:Category:Arup Arcalgud of Redmond WA (US)|Arup Arcalgud of Redmond WA (US)]][[Category:Arup Arcalgud of Redmond WA (US)]]

[[:Category:Gurpreet Sohal of Seattle WA (US)|Gurpreet Sohal of Seattle WA (US)]][[Category:Gurpreet Sohal of Seattle WA (US)]]

==MACHINE LEARNING AIDED DIAGNOSIS AND PROGNOSIS OF LARGE SCALE DISTRIBUTED SYSTEMS - A simplified explanation of the abstract==


This abstract first appeared for US patent application 18227877 titled 'MACHINE LEARNING AIDED DIAGNOSIS AND PROGNOSIS OF LARGE SCALE DISTRIBUTED SYSTEMS

The abstract describes a system for providing machine learning aided diagnostics and prognostics for large distributed systems. The system includes a diagnostics module that applies two-tiered analysis to detect anomalous behavior in the system, as well as a prognostics module that maps identified issues to resolution plans.

* Multivariate telemetry and event data is collected and analyzed to identify anomalies in the large distributed system.
* Univariate analysis is then applied to the identified anomalies to rank the results and generate a diagnostics incident report.
* The prognostics module reviews the incident report and maps each issue to a resolution plan.
* If the resolution plan is unsuccessful, the issue is escalated to a support team.
* The system aims to predict and prevent issues, as well as reduce resolution time.

Potential Applications:
- Monitoring and maintenance of large distributed systems
- Predictive maintenance in industrial settings
- Fault detection in complex networks

Problems Solved:
- Early detection of anomalies in large distributed systems
- Efficient resolution of issues through machine learning aided diagnostics
- Reduction of downtime and maintenance costs

Benefits:
- Improved system reliability and performance
- Cost savings through proactive maintenance
- Enhanced operational efficiency

Commercial Applications:
Title: Machine Learning Aided Diagnostics and Prognostics System for Large Distributed Systems
This technology can be utilized in various industries such as telecommunications, manufacturing, and cloud computing to enhance system reliability and reduce maintenance costs.

Questions about Machine Learning Aided Diagnostics and Prognostics System for Large Distributed Systems:
1. How does the system detect anomalies in large distributed systems?
The system detects anomalies by collecting and analyzing multivariate telemetry and event data.
2. What are the potential benefits of using machine learning aided diagnostics in large distributed systems?
The benefits include improved system reliability, cost savings, and enhanced operational efficiency.


==Original Abstract Submitted==

Disclosed is a system for providing machine learning aided diagnostics and prognostics for large distributed systems. A diagnostics module applies two-tiered analysis to detect anomalous behavior of the large scale distributed system. First, multivariate telemetry and event data emitted from the large scale distributed systems is collected by a diagnostics component, which applies multivariate analysis to identify of set of N-anomalies. Second, univariate telemetry and event data is obtained by the diagnostics component, which applies univariate analysis to the N-anomalies previously identified, ranks the results, and provides them to an AI to generate a diagnostics incident report. A prognostics module reviews the diagnostics incident report and maps each identified issue to a resolution plan. If execution of the resolution plan does not succeed in resolving the identified issue, the issue is escalated to a support team. The disclosed techniques may predict and prevent issues, or drastically reduce resolution time.



[[Category:G06F11/07]]
[[Category:G06N20/00]]
[[Category:CPC_G06F11/079]]