Identity Graph Confidence Scoring for Context-Aware User Resolution
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing identity management systems lack flexibility in managing user accounts, often treating them as a single user only after sufficient linking information is known, limiting their management and context-dependent usage.
Innovation Solution
A user identity management platform using a graph database maintains identity graphs with flexible management and selection of user account information based on context, allowing for the creation of new user clusters and edges between nodes, and calculating confidence levels for associations.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If user accounts are aggregated into a single user identity once sufficient linking information is known, then identity certainty is improved, but flexibility in managing user accounts across different contexts is worsened
Solution Approach 1:
The patent segments user identity into multiple independent user profile nodes, each representing a specific user account or persona. These nodes are connected through a graph structure with confidence edges, allowing flexible combination of different user profiles based on context requirements rather than forcing a single aggregated identity.
Solution Approach 2:
The system dynamically determines which user profile nodes to combine based on the specific context and confidence threshold requirements. The graph structure allows the system to adaptively select and combine different user profiles (e.g., combining payment card profiles with loyalty program profiles) rather than using a fixed aggregated identity.
2Adaptability or versatility
If user accounts are treated as separate independent users until linked, then flexibility in context-dependent management is improved, but computational complexity and processing time are worsened
Solution Approach 1:
The system uses confidence thresholds as feedback mechanisms to automatically determine when and how to combine user profiles. When the confidence level between user profiles exceeds the threshold, the system combines them; when below, they remain separate. This automated feedback-based decision process reduces manual intervention and computational overhead.
Solution Approach 2:
The patent changes the parameter of confidence threshold to control the balance between flexibility and computational complexity. By adjusting this parameter, the system can optimize the number of user profiles to process and combine, reducing computational load while maintaining appropriate flexibility for different business contexts.
3Quantity of substance
If all user account information is considered regardless of confidence level, then inclusivity of user data is improved, but accuracy of user identity determination is worsened
Solution Approach 1:
The patent applies different quality standards (confidence thresholds) to different user profile nodes and their connections. Not all user data is treated equally - only profiles connected with sufficient confidence are combined for a given query, while maintaining the option to include additional profiles if needed based on specific context requirements.
Data Source
AI summary
A user identity management platform is provided that manages user identity for an enterprise, such as a retail enterprise. In particular, a specific identity graph structure is provided that allows for flexible management and selection of user account information depending on the context in which that user account information is to be used. Confidence scores may be maintained for nodes and edges and probabilistic techniques associated with account activity may be used to improve confidence of association among nodes within a cluster representing a unique user.