Hot User Generated Content Determination via Quality and Correlation Thresholds
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing UGC website systems struggle to accurately identify high-quality user-generated content (UGC) that is relevant to users and categories, leading to poor relevance and real-time performance, causing inconvenience to users who must navigate through numerous interactions to find needed content.
Innovation Solution
A method and apparatus that analyze historical UGC to determine quality scores and correlation degrees with categories, identifying hot accounts and subsequently evaluating newly posted content based on predefined thresholds to determine if it is a hot UGC, ensuring relevance and timeliness.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If the system analyzes all UGC to identify high-quality content, then the relevance and quality of recommended content improves, but the system complexity and processing time increase
Solution Approach 1:
The patent segments the UGC evaluation process into two distinct phases: (1) analyzing historical UGC to identify hot accounts with quality thresholds, and (2) evaluating new UGC from these identified hot accounts. This segmentation reduces system complexity by focusing computational resources on promising content sources rather than processing all UGC equally.
Solution Approach 2:
The system performs preliminary analysis on historical UGC to pre-identify hot accounts before evaluating new content. By establishing quality benchmarks and identifying reliable content sources in advance, the system reduces real-time processing complexity while maintaining high identification accuracy for new UGC.
2Speed
If the system processes and evaluates all newly posted UGC in real-time, then the timeliness of content recommendation improves, but the resource consumption and processing load increase
Solution Approach 1:
The patent applies local quality assessment by evaluating only specific attributes of UGC from hot accounts (quality score and correlation degree) rather than comprehensive analysis. This selective evaluation reduces resource consumption while maintaining timely recommendation capability for high-quality content.
Solution Approach 2:
The system performs partial evaluation on new UGC by checking only critical thresholds (quality score threshold and correlation degree threshold) rather than exhaustive analysis. This partial action approach enables fast processing with reduced resource consumption while identifying high-quality content effectively.
3Productivity
If the system uses simple filtering criteria for UGC, then the processing speed increases, but the quality and relevance of recommended content decreases
Solution Approach 1:
The patent changes the evaluation parameters from basic metrics to sophisticated measures including quality scores (based on text length, word count, punctuation analysis) and correlation degrees (using TF-IDF and cosine similarity). These parameter transformations enable accurate quality assessment while maintaining processing efficiency through structured computation.
Solution Approach 2:
The system replaces simple mechanical filtering with intelligent evaluation mechanisms including text quality analysis, category correlation computation, and threshold-based decision making. This substitution maintains high processing speed while significantly improving content quality assessment accuracy through algorithmic evaluation.
4Ease of operation
If the system requires multiple user interactions to find relevant content, then user navigation flexibility increases, but user experience and time efficiency deteriorates
Solution Approach 1:
The system provides self-service by automatically identifying and recommending high-quality UGC from hot accounts without requiring extensive user navigation. The automated quality assessment and recommendation mechanism reduces user effort and search time while maintaining ease of access to relevant content through the recommendation interface.
Data Source
AI summary
According to an example, at least one hot account is determined for each category according to quality scores and correlation degrees of history user generated content (UGCs); after a UGC newly posted by the hot account is received, if a quality score of the newly posted UGC is higher than a predefined quality score threshold and a correlation degree between the newly posted UGC and the category that the hot account belongs to is higher than a predefined correlation degree threshold, the newly posted UGC is determined as a hot UGC.