Cloud-Based TV Viewership Data for E-Commerce Recommendations
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing e-commerce product recommendation systems are limited in scope, relying solely on user inputs, previously viewed products, and browsing history, missing opportunities to suggest relevant products that may not be captured by these methods.
Innovation Solution
A cloud-based system that collects and stores TV viewership data using automated content recognition (ACR) to recommend products based on commercials viewed by users, providing a broader range of potential recommendations.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If product recommendations are based solely on user inputs, previously viewed products, and browsing history, then the recommendation system is simple to implement, but the scope and relevance of recommendations are narrow
Solution Approach 1:
The patent merges multiple data sources including TV viewership data, radio listenership data, search queries, and browsing history into a unified recommendation system. This combination broadens the scope of recommendations beyond what any single source could provide, while the integrated approach manages complexity through centralized data processing.
Solution Approach 2:
The recommendation system is designed to process and analyze multiple types of user interaction data across different platforms and media channels. This multi-functional capability allows the system to generate recommendations based on diverse data inputs, enhancing versatility while maintaining a unified system architecture.
2Measurement precision
If TV viewership data is collected using automated content recognition, then product recommendation relevance is enhanced through demographics and ad campaign reinforcement, but system complexity and data processing requirements increase
Solution Approach 1:
The patent introduces automated content recognition (ACR) technology as an intermediary to bridge TV/radio content and user viewing/listening data. This mediator automatically identifies and captures commercial content, enabling precise tracking of ad exposure without manual intervention, thereby enhancing recommendation accuracy while managing complexity through automated processing.
Solution Approach 2:
The system replaces manual data collection and analysis methods with automated content recognition technology. This substitution uses algorithmic processing to identify and extract product information from TV and radio content, improving measurement precision while reducing the need for manual data processing infrastructure.
3Adaptability or versatility
If multiple data sources are integrated for product recommendations, then the pool of potential recommendations is broadened, but data processing and storage requirements increase
Solution Approach 1:
The patent extracts only the essential and relevant features from multiple data sources, such as product identifiers, user interaction patterns, and demographic information. This selective extraction reduces the volume of data that needs to be stored and processed while maintaining the versatility of recommendations based on the most important data elements.
Solution Approach 2:
The system segments data from different sources into distinct categories and processing streams, allowing for efficient management and analysis of large volumes of data. By organizing data into manageable segments, the system can process information from multiple sources without being overwhelmed by the total data volume.
Data Source
AI summary
Recommendations are made to an e-shopper based on commercials that the e-shopper may have recently viewed on TV or heard on radio. In one preferred embodiment, a cloud-based server collects and stores TV viewership data through mobile devices, using automated content recognition (ACR).