Hierarchical Metric Tree for Live Traffic Analysis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Software engineers face difficulties in quickly identifying significantly impacted categories of traffic and metrics during live traffic experiments, as customary systems require manual data aggregation and analysis, taking several hours to several days to determine significant changes in user traffic metrics.
Innovation Solution
A system and method that summarize changes between two sets of metrics using a hierarchical metric tree data structure, allowing users to select and drill down into significant metrics, employing statistical processes like z-scores to identify deviations and organize data into a user-friendly interface for quick analysis.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual data aggregation and analysis methods are used, then detailed statistics about application properties and user traffic can be generated, but the analysis time increases to several hours to several days
Solution Approach 1:
The patent segments the large volume of traffic metrics into hierarchical categories (parent metrics and child submetrics). This segmentation allows the system to organize thousands of metrics into manageable groups, enabling rapid identification of significant changes without analyzing every individual metric manually.
Solution Approach 2:
The patent introduces an intermediary automated analysis system that acts as a mediator between raw traffic data and human analysts. This system automatically aggregates data, computes statistics, and identifies significant metric changes, eliminating the need for manual spreadsheet creation and data aggregation while preserving detailed statistical analysis capabilities.
2Measurement precision
If thousands of metrics across several thousand categories are monitored, then comprehensive coverage of application performance is achieved, but the difficulty of determining impact increases
Solution Approach 1:
The patent organizes thousands of metrics into a hierarchical structure with parent metrics and child submetrics. This segmentation reduces the cognitive load on analysts by presenting data in organized groups rather than as a flat list of thousands of individual metrics, making impact determination more manageable.
Solution Approach 2:
The patent applies local quality by allowing analysts to focus on specific categories or submetrics that are relevant to particular experiments or concerns. The system enables drilling down into specific metric categories while maintaining the ability to view comprehensive coverage, allowing targeted analysis without sacrificing overall visibility.
3Measurement precision
If detailed manual analysis procedures are used, then accurate metric interpretation is achieved, but productivity decreases due to time-consuming processes
Solution Approach 1:
The patent implements self-service by enabling the system to automatically perform data aggregation, statistical computation, and significant change identification. The automated system serves itself by processing and analyzing traffic data without requiring manual intervention for routine analytical tasks, thereby increasing productivity while maintaining accuracy through systematic automated procedures.
Solution Approach 2:
The patent replaces manual mechanical analysis processes with automated computational systems. Instead of analysts manually creating spreadsheets and computing statistics, the system automatically performs these operations, substituting human manual labor with automated computational mechanisms that maintain accuracy while dramatically increasing analysis throughput.
Data Source
AI summary
A system and method for summarizing changes between a first set of metrics and a second set of metrics are disclosed. An example method includes obtaining and categorizing a first set of metrics for an application. A second set of metrics for the application may be obtained and categorized. A statistical process may be used to determine metrics that should be displayed. Metrics may be organized into a metric tree data structure that is hierarchical including parent metrics and child submetrics. Metrics that have been determined to be displayed may be displayed in the tree data structure so that the metrics are selectable with a single user input. In response to receiving a selection of a metric via the single user input, traffic categories and submetrics may be displayed that are children of the metric within the tree data structure may be displayed.