Highlight Replay Generation Using User Interaction Metrics
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing techniques for generating highlight replays of live media events rely on static metrics and manual selection, failing to include segments of interest to users and requiring significant human resources.
Innovation Solution
Dynamically determining highlights based on user interaction metrics and social media metrics, using machine learning algorithms to generate highlight replays that include segments of greatest interest to users, reducing the need for human resources.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Extent of automation
If static metrics and manual selection are used to generate highlight replays, then the selection process is simple to implement, but the relevance of highlights to user interest is poor and human resources are heavily required
Solution Approach 1:
The system uses user interaction data and social media metrics to automatically identify and select highlight segments without human intervention. The algorithm processes engagement metrics, detects significant events, and generates highlight reels autonomously, allowing the system to serve itself in the highlight selection process
Solution Approach 2:
The patent replaces manual human selection (mechanical process) with an automated algorithmic system that analyzes engagement metrics and social media data. This substitution eliminates the need for human operators to manually review and select highlight segments, significantly reducing labor requirements while improving accuracy
2Productivity
If manual selection of highlight segments is performed, then the quality of segment selection can be controlled by human expertise, but the processing time and human resources required are significantly increased
Solution Approach 1:
The system pre-processes and analyzes user interaction data and social media metrics during the media content delivery period. By preparing engagement metrics and identifying potential highlight candidates in advance, the system enables rapid generation of highlight reels without requiring time-consuming manual review when the highlights are needed
Solution Approach 2:
The automated algorithm processes and analyzes engagement metrics at high speed, replacing the slow manual review process. The system can evaluate numerous segments simultaneously based on quantitative metrics, dramatically increasing processing speed and reducing the time required to generate highlight replays
3Measurement precision
If static metrics are used to determine highlight segments, then the generation process is straightforward, but the ability to capture segments of genuine user interest is limited
Solution Approach 1:
The system introduces engagement metrics and social media data as intermediary indicators to measure user interest. Rather than directly observing user preferences, the system uses these intermediary metrics (rewinds, pauses, social media mentions) as proxies to accurately infer which segments capture genuine user interest
Solution Approach 2:
The patent adds new dimensions to the measurement system by incorporating social media metrics and detailed user interaction data beyond traditional static metrics. This multi-dimensional approach includes analyzing rewinds, pauses, social media mentions, and engagement patterns across multiple platforms, providing a more comprehensive and accurate measurement of user interest
Data Source
AI summary
Systems, methods, and computer-readable media are disclosed for dynamically determining highlights of media content based on user interaction metrics and/or social media metrics. In one embodiment, an example method may include determining media content streamed to user devices over a time period and corresponding to a live event, determining user interaction data associated with the media content and indicative of user interactions with the user devices, determining, using the user interaction data, a quality score for a time interval during the time period, the quality score indicative of user engagement in a segment of the media content, determining, using the time interval and segment-by-segment metadata, a stream start time and a stream end time for the segment, generating, using the stream start time and the stream end time, a clip of the segment, and determining, using the quality score, that the clip is to be included in a highlight.