Analytics Entity Resolution via Higher-Order Node Combinations
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional analytics systems are inefficient and inaccurate in attributing data sources, leading to fragmented sessions and missed insights due to their inability to accurately resolve source interactions across different devices and sessions.
Innovation Solution
The implementation of analytics system entity resolution techniques that leverage connectivity patterns and typed higher-order node combinations to accurately associate user interactions across different devices and sessions, using a heterogeneous network representation and filtering systems to generate predicted links between source IDs.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional techniques assign separate source IDs to different devices and sessions, then device-specific data tracking is simple, but source resolution accuracy deteriorates
Solution Approach 1:
The patent transitions from conventional pairwise node comparisons to higher-order subgraph patterns involving multiple nodes and edges. By analyzing connectivity patterns across multiple devices, sessions, and interactions simultaneously, the system resolves source identity ambiguities that cannot be solved by examining individual device-sessions in isolation.
Solution Approach 2:
The system changes the parameters of analysis from simple node attributes to complex subgraph structural properties. By examining the topology, connectivity patterns, and relational structures within higher-order subgraphs, the system achieves more accurate source resolution than conventional methods that rely on basic node comparisons.
2Productivity
If conventional analytics systems maintain sessions separately, then data processing is simpler, but insights generation deteriorates
Solution Approach 1:
The patent segments the complex task of source resolution into identifiable higher-order subgraph patterns. By defining specific structural patterns (such as device-session-interaction sequences) as discrete units of analysis, the system can efficiently process and match these patterns across large datasets without requiring exhaustive pairwise comparisons of all nodes.
Solution Approach 2:
The system performs preliminary action by pre-identifying and indexing higher-order subgraph patterns within the data. This allows the analytics system to quickly retrieve and compare pre-processed pattern structures rather than computing connections from scratch, significantly reducing computational time while maintaining insight generation capability.
3Measurement precision
If conventional techniques use lower-order node analysis, then computational efficiency is maintained, but resolution accuracy deteriorates
Solution Approach 1:
The patent creates simplified copies or representations of complex higher-order subgraph patterns that can be efficiently processed. By extracting key structural features and connectivity characteristics of subgraphs into standardized pattern templates, the system maintains processing efficiency while capturing the essential information needed for accurate source attribution.
Data Source
AI summary
Techniques and systems are described for analytics system entity resolution. Typed higher-order node combinations are determined within a dataset, and an amount of similarity between two arbitrary nodes within the dataset is determined based on the typed higher-order node combinations. The amount of similarity enables the digital analytics to accurately perform source resolution of portions of the dataset to a respective source, and may be utilized to control output of digital content to a client device.