Graph Embedding for User Activity Structural Analysis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for analyzing user activity data in cloud computing platforms rely on metric averages that fail to capture the complexity of interdependent user actions and structural relationships, leading to inadequate insights and ineffective interventions.
Innovation Solution
The method involves collecting and processing data to generate graph data representing actors and objects, using graph embedding to convert this data into metric space, allowing for the modeling of relationships and extraction of actionable insights.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If attribute-based aggregations (sums, counts, averages) are used to analyze collected data, then the analysis process is simple and fast, but the interdependence of users' actions and structural relationships are lost
Solution Approach 1:
The patent transforms flat attribute-based data into multi-dimensional graph structures where nodes represent users/actions and edges represent relationships. This dimensional transformation preserves structural information while enabling new types of analysis that capture interdependence, resolving the contradiction between simplicity and information retention.
Solution Approach 2:
The patent introduces graph embeddings as an intermediary representation that bridges raw event data and high-level metrics. These embeddings capture structural relationships in a compressed form that can be efficiently processed, maintaining both analytical depth and computational efficiency.
2Measurement precision
If graph embedding is used to convert graph data into metric space data, then deeper insights into user activity structure are obtained, but additional processing time and computational resources are required
Solution Approach 1:
The patent performs graph embedding operations in advance to pre-compute metric space representations of users and actions. These pre-computed embeddings can then be queried efficiently without repeating the full embedding process, reducing real-time processing time while maintaining insight accuracy.
Solution Approach 2:
The patent adjusts embedding dimensionality and complexity parameters based on specific analysis needs. By changing these parameters, the system can balance between obtaining deep structural insights and maintaining acceptable processing times for different use cases.
Data Source
AI summary
Systems and methods for graph embedding already-collected but not yet connected data are disclosed. A method includes extracting a first set of actor-related data, a second set of object-related data, and a third set of temporal data from a set of the already-collected but not yet connected data representative of a unit-level contribution to the target activity. The method further includes generating graph data for at least one graph having a plurality of nodes and a plurality of edges using the set of the already-collected but not yet connected data, where each of the plurality of nodes corresponds to the actor or the object, and where an attribute associated with each of the plurality of edges corresponds to a measurement associated with the target activity during a temporal dimension of interest. The method further includes converting the graph data into metric space data using a graph embedding process.