18327400. REAL TIME DETECTION OF METRIC BASELINE BEHAVIOR CHANGE simplified abstract (Microsoft Technology Licensing, LLC)

From WikiPatents
Jump to navigation Jump to search

REAL TIME DETECTION OF METRIC BASELINE BEHAVIOR CHANGE

Organization Name

Microsoft Technology Licensing, LLC

Inventor(s)

Raphael Fettaya of Herzliya (IL)

Rachel Lemberg of Herzliya (IL)

Yaniv Lavi of Herzliya (IL)

REAL TIME DETECTION OF METRIC BASELINE BEHAVIOR CHANGE - A simplified explanation of the abstract

This abstract first appeared for US patent application 18327400 titled 'REAL TIME DETECTION OF METRIC BASELINE BEHAVIOR CHANGE

Simplified Explanation

The patent application describes techniques for real-time detection of changes in metric baseline behavior. These techniques involve comparing historic and sample time series information for a component metric to determine if there is a significant difference. If a significant difference is detected, an alert notification is generated to identify the period of time when the baseline change occurred.

  • Techniques for real-time detection of changes in metric baseline behavior
  • Generating reference and sample distance signatures based on historic and sample time series information
  • Comparing the reference and sample distance signatures to determine a signature difference
  • Determining if the second period of time is a baseline change candidate based on the signature difference being greater than a distance threshold
  • Presenting an alert notification to identify the second period of time as the baseline change candidate

Potential Applications

  • Monitoring and detecting changes in performance metrics for software systems
  • Identifying anomalies in network traffic patterns
  • Detecting changes in sensor data for industrial equipment

Problems Solved

  • Provides a method for real-time detection of changes in metric baseline behavior
  • Allows for proactive identification of baseline changes, which can help prevent system failures or performance issues
  • Reduces the need for manual monitoring and analysis of metric data

Benefits

  • Enables early detection of baseline changes, leading to faster response times and improved system reliability
  • Reduces the risk of system failures or performance degradation
  • Automates the process of monitoring and analyzing metric data, saving time and resources


Original Abstract Submitted

Example aspects include techniques for real-time detection of metric baseline behavior change. These techniques may include generating a reference distance signature based on historic time series information for a component metric, the historic time series information corresponding to a first period of time, generating a sample distance signature based on sample time series information for the component metric, the sample time series information corresponding to a second period of time, and comparing the reference distance signature to the sample distance signature to determine a signature difference. In addition, the techniques may include determining that the second period of time is a baseline change candidate based on the signature difference being greater than a distance threshold, and presenting, based at least in part on the signature difference, an alert notification identifying the second period of time as the baseline change candidate.