Entity Resolution and Relevance Scoring for Buyer Matching
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The real-estate domain faces inefficiencies due to manual labor in locating potential buyers, inaccurate entity identification across different databases, and redundant property recommendations, leading to wasted time and damaged relationships.
Innovation Solution
A method and system for resolving entities across databases using resolution rules and machine learning to determine relevance scores, enabling accurate identification and enrichment of transaction data for potential participating entities.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If manual methods are used to locate potential buyers across multiple databases, then flexibility and adaptability are maintained, but productivity is low and time consumption is high
Solution Approach 1:
The patent replaces manual mechanical search processes with an automated computerized system that uses machine learning models and algorithms to identify potential buyers across multiple databases, thereby increasing productivity and reducing time loss
Solution Approach 2:
The system enables automatic entity resolution and relevance scoring without human intervention, allowing the database system to self-service by automatically matching properties with potential buyers based on learned patterns from transaction data
2Measurement precision
If entity data from different databases are compared using simple matching, then processing speed is fast, but measurement precision of entity identity is low
Solution Approach 1:
The system transforms entity identification from simple string matching to a multi-parameter analysis using machine learning models that evaluate multiple features and characteristics simultaneously, improving measurement precision despite increased complexity
Solution Approach 2:
The patent introduces machine learning models as intermediaries between raw database records and entity identification decisions, allowing complex comparisons to be mediated through learned representations that improve accuracy
3Productivity
If relevant potential buyers are identified using automated systems, then productivity increases, but reliability of buyer-property matching may decrease due to inaccurate entity resolution
Solution Approach 1:
The system incorporates feedback mechanisms where the machine learning model learns from actual transaction outcomes and adjusts its entity resolution and relevance scoring to improve reliability while maintaining high productivity
Solution Approach 2:
The patent performs preliminary entity resolution and validation steps before making final buyer-property matches, ensuring that the foundation for matching is accurate and reliable before automated productivity benefits are realized
Data Source
AI summary
A method and system for detecting relevant potential participating entities across different databases. A method includes retrieving transaction data related to potential participating entities by resolving each of the plurality of potential participating entities between a dataset including transaction data and a dataset indicating the plurality of potential participating entities, wherein resolving the plurality of potential participating entities further includes applying resolution rules requiring matching a plurality of features between respective instances of the potential participating entity in the transaction data and in the dataset indicating the plurality of potential participating entities; determining a plurality of relevance scores based on the retrieved transaction data and entity characteristics of a subject entity, wherein each relevance score represents a relevance of the subject entity with respect to a respective potential participating entity; and identifying, based on the plurality of relevance scores, at least one relevant potential participating entity.