User Correlation Database for Imperfect Identity Matching
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Large businesses face challenges in managing and analyzing user records spread across multiple geographic locations, often with imperfect identifying information, leading to inefficiencies in data aggregation and user association, which hinders insights into user behavior and service recommendations.
Innovation Solution
A system utilizing machine learning models to identify unique users across disparate databases, associate user records, and generate interactive user interfaces that provide insights into user behavior, service connections, and propensity for disassociation or association with specific items, enabling improved data aggregation and presentation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If user records are manually entered and maintained across multiple geographic locations, then each location can maintain local records of user interactions, but data aggregation and user association become inefficient and inaccurate due to imperfect identifying information
Solution Approach 1:
The patent introduces a centralized user correlation database and machine learning model as an intermediary between distributed location databases. This intermediary automatically matches user records across locations using imperfect identifying information (name, address, phone, email), resolving the contradiction by providing reliable user association without manual intervention.
Solution Approach 2:
The patent replaces the manual mechanical process of coordinate data entry and user matching with an automated machine learning system. The ML model analyzes identifying information from multiple databases and automatically correlates user records, dramatically improving both accuracy and efficiency compared to manual methods.
2Quantity of substance
If tens or hundreds of employees manually record user interactions using fillable forms, then detailed user information can be captured at each location, but the complexity and time required to coordinate and aggregate this data across multitudes of employees becomes prohibitive
Solution Approach 1:
The system enables self-service data aggregation where the machine learning model automatically processes and correlates user records without requiring employee coordination. Each location independently maintains its records, and the centralized system automatically integrates them, eliminating the need for complex inter-employee coordination while handling large volumes of user data.
3Ease of operation
If user records are stored in distributed databases across geographic regions, then local data maintenance is simplified, but obtaining a holistic view of individual users across all locations becomes difficult without significant processing overhead
Solution Approach 1:
The patent implements preliminary action by pre-correlating user records across all locations in the user correlation database before queries are made. The machine learning model continuously processes and links user records, so when a holistic user view is needed, the information is already prepared and immediately available, eliminating retrieval delays while maintaining local data independence.
Data Source
AI summary
Methods, systems, and apparatus, including computer programs encoded on computer storage media, for a feature clustering of users, user correlation database access, and user interface generation system. The system can obtain information stored in different databases located across geographic regions, and determine unique users from the different information. The information can be included in unique records in the databases, with each record describing a particular user, and with each user described with imperfect identifying information. The system can analyze the different information utilizing machine learning models, and can associate each record with a particular unique user. The system can obtain identifications of items associated with each user, and determine the propensity of the user to disassociate with one or more items, or determine likelihoods of future association with different items not presently associated with the user.