Merchant Matching Model for Multi-Source Data Identification
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing systems face challenges in identifying and retrieving merchant data from multiple disparate data structures, leading to inefficiencies in data access and resource utilization due to varying storage formats, identifiers, and incomplete data.
Innovation Solution
A merchant data device utilizing machine learning to generate a merchant matching model that identifies a unique core merchant identifier, enabling access to merchant data across multiple data sources by mapping core identifiers to separate merchant identifiers and structures, thereby facilitating efficient data retrieval and conservation of resources.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of information
If merchant data is stored in multiple disparate data structures with different formats and identifiers, then data coverage and completeness are improved, but data retrieval time and computational resources increase
Solution Approach 1:
The patent combines multiple disparate merchant data structures into a unified view by training a machine learning model to recognize equivalencies between merchants represented by different identifiers across various data structures. This merging approach maintains comprehensive data coverage while enabling efficient retrieval through a single coordinated query system rather than requiring separate searches across multiple independent structures.
Solution Approach 2:
The trained model serves as a universal translator that can map between any combination of merchant identifiers from different data structures (e.g., mapping a first data structure's merchant ID to a second data structure's merchant ID). This multi-functional capability allows the system to handle diverse data formats and identifier schemes while providing consistent efficient access through a single interface.
2Loss of information
If merchant data is stored in multiple disparate data structures with different formats and identifiers, then data coverage and completeness are improved, but system complexity increases
Solution Approach 1:
The patent introduces a trained machine learning model as an intermediary layer between the application layer and multiple disparate data structures. This mediator handles all the complexity of mapping between different merchant identifiers and data formats, while presenting a simplified unified interface to users. The model acts as a buffer that absorbs the system complexity without propagating it to the user interface or requiring complex coordination between data structures.
Solution Approach 2:
The system creates a virtual copy or representation of merchant data that can be accessed through multiple identifier types without physically duplicating the actual data storage. The trained model generates mapped identifiers that reference the same underlying merchant records across different data structures, providing a lightweight virtual representation that simplifies access patterns without requiring complex physical data replication.
3Loss of information
If traditional methods are used to query merchant data across multiple data structures, then comprehensive data retrieval is achieved, but computational resources and network bandwidth are consumed
Solution Approach 1:
The patent performs preliminary action by training the machine learning model in advance to learn the mapping relationships between different merchant identifiers across multiple data structures. This pre-training phase captures the complex relationships between identifiers so that during actual query operations, the system can quickly apply the learned mappings without performing computationally intensive analysis or coordination across multiple data structures in real-time, significantly reducing operational computational resources and network bandwidth.
Data Source
AI summary
A device may receive a merchant query including first merchant data associated with a first merchant. The first merchant data may be provided, as input, to a merchant matching model associated with a merchant data structure, the merchant matching model having been trained to determine a measure of confidence that input merchant data corresponds to an existing merchant in the merchant data structure. The device may receive, as output from the merchant matching model, a measure of confidence that the first merchant data corresponds to a second merchant, the second merchant being associated with second merchant data stored in the merchant data structure. The device may also determine, based on the measure of confidence, that the first merchant corresponds to the second merchant. Based on the determination, the device may obtain the second merchant data from the merchant data structure and perform an action based on the second merchant data.