Live Sports Thumbnail Filtering via Deep Learning Extraction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Users of electronic devices cannot easily verify information about live sports from advertisement thumbnails displayed on the screen, as these thumbnails are often insignificant and mixed with game thumbnails.
Innovation Solution
An electronic device method and system that uses a pre-trained deep learning model to classify and remove advertisement thumbnails from the display, allowing only game thumbnails to be shown, enabling users to quickly access information about live sports.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Quantity of substance
If advertisement thumbnails are displayed on the display screen along with game thumbnails, then the display screen shows more content (higher quantity of information), but the user cannot easily verify information about live sports (lower information quality)
Solution Approach 1:
The patent extracts and removes advertisement thumbnails from the display screen, separating them from game thumbnails. The processor identifies advertisement thumbnails using a deep learning model and excludes them from display, allowing only game thumbnails to be shown. This resolves the contradiction by maintaining the quantity of relevant thumbnails while eliminating irrelevant advertisement content that degrades information quality.
2Adaptability or versatility
If advertisement thumbnails are displayed on the display screen, then the content variety increases, but the user experience deteriorates due to insignificant advertisement content
Solution Approach 1:
The system extracts advertisement thumbnails from the mixed thumbnail stream and removes them from display. The processor uses image recognition to identify advertisement content and filters it out, preserving only game-related thumbnails. This maintains content variety through diverse game thumbnails while eliminating advertisement content that degrades user experience.
Solution Approach 2:
The deep learning model acts as an intermediary between the thumbnail stream and the display screen. It processes thumbnails to identify and filter advertisement content before display, serving as a mediator that separates relevant game thumbnails from irrelevant advertisement thumbnails, thereby improving user experience without losing content variety.
3Area of stationary object
If all thumbnails (game and advertisement) are displayed, then the display screen utilizes full space, but the relevant information about live sports becomes harder to verify
Solution Approach 1:
The patent removes advertisement thumbnails from the display, extracting only game thumbnails for presentation. This reduces the total number of displayed thumbnails slightly but eliminates confusion caused by advertisement content, thereby improving the accuracy of sport information verification while maintaining efficient use of display space through game-relevant content.
Data Source
AI summary
Provided are an electronic device for removing an advertisement thumbnail from a display screen for providing a list of sports and an operating method of the electronic device that may retrieve an image thumbnail extracted from a game video being broadcast live, determine whether the image thumbnail is a game thumbnail or an advertisement thumbnail using a pre-trained deep learning model, and display the game thumbnail on a display screen when the image thumbnail is the game thumbnail and remove the advertisement thumbnail on the display screen when the image thumbnail is the advertisement thumbnail.