ML Product Catalog Management Automating Data Ingestion

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Current product catalog management systems are inefficient and prone to errors due to manual data ingestion processes, which result in biased and limited product data, making it difficult to maintain comprehensive and navigable catalogs across multiple channels.

Innovation Solution

The use of machine learning techniques to access, analyze, and refine product data, creating and updating data records, and organizing them hierarchically within a product catalog, thereby automating the ingestion and enrichment of product information.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Quantity of substance

If manual data ingestion processes are used to build product catalogs, then product data can be collected from multiple sources, but the process is time-consuming and results in biased and limited product data

Engineering Contradiction:

Improvecompleteness of product dataVSAvoidtime required for data ingestion

Core Design Contradiction:

Quantity of substanceVSLoss of time

Solution Approach 1:

The patent replaces manual mechanical data ingestion processes with automated machine learning systems. ML models automatically scrape, extract, and structure product data from multiple sources including the web, replacing the manual effort of data collection and processing while significantly increasing both speed and data completeness.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The system enables self-service data ingestion where the ML-powered platform automatically discovers, collects, and processes product information without requiring manual intervention. The system serves itself by continuously scraping and updating product catalogs autonomously.

Inventive Principle:

Principle #25Self-service

2Reliability

If manual processes are used to maintain and update product catalogs, then coordination across multiple teams can be achieved, but the catalog is not kept current and accurate

Engineering Contradiction:

Improveaccuracy of product dataVSAvoidspeed of catalog updates

Core Design Contradiction:

ReliabilityVSProductivity

Solution Approach 1:

Manual coordination processes are replaced with automated ML systems that continuously monitor and update product catalogs. The system automatically detects product changes, updates pricing and availability information, and maintains data accuracy without requiring human coordination across teams.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The patent implements continuous automated updating of product catalogs through ML models that run continuously to scrape and process product information. This ensures the catalog is constantly kept current and accurate, replacing discontinuous manual update cycles.

Inventive Principle:

Principle #20Continuity of useful action

3Ease of manufacture

If third party data providers are used to supply product records, then data collection is simplified, but product details and meaningful transaction data are ignored

Engineering Contradiction:

Improveease of data collectionVSAvoidproduct details and transaction data

Core Design Contradiction:

Ease of manufactureVSLoss of information

Solution Approach 1:

The patent replaces reliance on third-party data providers with direct automated web scraping and data extraction using ML models. This allows the system to collect comprehensive product details and transaction data directly from source websites, eliminating information loss that occurs with third-party intermediaries.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

4Quantity of substance

If comprehensive product catalogs are created with many products across multiple categories, then catalog coverage is improved, but navigation and search become difficult

Engineering Contradiction:

Improvecomprehensiveness of catalogVSAvoidease of navigation and search

Core Design Contradiction:

Quantity of substanceVSEase of operation

Solution Approach 1:

The patent implements automated hierarchical category structuring using ML models that organize products into logical categories and subcategories. This segmentation of the comprehensive product catalog into structured groups makes navigation and search easier while maintaining complete product coverage.

Inventive Principle:

Principle #1Segmentation

Data Source

PatentUS20250190942A1Technologies for using machine learning to manage product catalogs

Publication Date: 2025.06.12 FETCH REWARDS INC

AI summary

Systems and methods for using machine learning to dynamically manage product catalogs are disclosed. According to certain aspects, a set of machine learning models may analyze a set of data identifying a product to create or update a data record associated with the product, where the set of machine learning models may include a brand assignment model, a category assignment model, and a tag assignment model. Further, an entity resolution model may refine the data record, which may be organized according to a set of hierarchical data for the product. Additionally, a product catalog may be updated to identify the product according to the set of hierarchical data for the product.