Shoppable Video URL Extraction From Generic Video Metadata
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing video corpuses are created in non-scalable ways, limiting the number of shoppable videos and frustrating users who may not discover products they are interested in.
Innovation Solution
Generating shoppable uniform resource locators (URLs) from generic video corpuses by extracting, combining, and normalizing URLs, applying filters for noise reduction and quality control, and presenting personalized product recommendations.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If generic video corpuses are used without shoppable video implementation, then video creation is simpler and more scalable, but users cannot discover or purchase products while watching videos
Solution Approach 1:
The system extracts URLs from video metadata to create shoppable video corpuses. By extracting relevant URL information from existing video metadata without fundamentally changing the video creation process, the system enables product discovery while maintaining scalability of video production.
Solution Approach 2:
The system introduces an intermediary processing layer that converts generic video corpuses into shoppable video corpuses by extracting and processing URLs from metadata. This intermediary process bridges the gap between simple video creation and enhanced product discovery capabilities.
2Productivity
If shoppable videos are created manually with full implementation, then users can shop seamlessly within videos, but the production process becomes time-consuming and non-scalable
Solution Approach 1:
The system performs preliminary extraction of URLs from video metadata during video processing, preparing shoppable video corpuses in advance. This preliminary action enables seamless user shopping experience while maintaining efficient production through automated preprocessing.
Solution Approach 2:
The system uses automated URL extraction and processing from video metadata, allowing the system to serve itself in creating shoppable video corpuses without manual intervention. This self-service approach maintains ease of operation while improving productivity.
3Loss of information
If URLs are extracted and processed from video metadata, then personalized product recommendations can be provided, but data processing complexity and noise reduction requirements increase
Solution Approach 1:
The system extracts only the necessary URL information from video metadata that is relevant for product discovery, rather than processing all metadata. This partial action approach maintains product information completeness while reducing unnecessary processing complexity.
Solution Approach 2:
The system applies targeted processing to specific portions of video metadata where URLs are likely to be found, rather than uniformly processing all metadata. This local quality approach preserves important product information while minimizing overall processing complexity.
Data Source
AI summary
Aspects of the present disclosure relate to providing a shoppable video corpus by generating a shoppable URL. A URL is extracted from a video corpus, in which the extracted URL may be a long URL or a short URL. Extracted URLs are then combined and normalized. From the normalized URL, noise is removed and quality control is performed. As a result, shoppable URL may be presented at the user’s computing device as personal recommendation. The video and metadata of the cleaned URL is also ingested and stored in a database for future reference.