Live Streaming Tagging via Intermediate Rule-Based Mediation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional methods for categorizing live streaming data rely on machine learning models, producing outputs that are more understandable by machines than humans and lack precision due to inherent algorithmic limitations, resulting in low granularity and imprecision in tagging live content.
Innovation Solution
A system and method that generate intermediate tags using multiple machine learning models and determine final tags based on predefined criteria, allowing for human-understandable and precise categorization of live streaming programs by combining outputs from different models in a structured manner, enhancing granularity and precision.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If machine learning models are used to categorize live streaming data, then automation and processing speed are improved, but measurement precision and manufacturing precision deteriorate due to algorithmic limitations and machine-unfriendly outputs
Solution Approach 1:
The patent introduces an intermediary processing layer that translates machine learning model outputs into human-understandable tags. The system generates intermediate tags from multiple ML models, then uses rule-based processing to combine these into final precise tags, serving as a mediator between machine processing and human interpretation
Solution Approach 2:
The tagging process is divided into distinct segments: multiple parallel ML models generate intermediate tags independently, then a rule-based system combines these segments into a final precise tag. This segmentation allows each component to specialize while achieving overall high precision
2Device complexity
If single machine learning model output is used directly, then device complexity is reduced, but manufacturing precision and measurement precision worsen due to low granularity
Solution Approach 1:
The patent merges outputs from multiple machine learning models by generating intermediate tags from each model and then combining them through rule-based processing. This merging of multiple model outputs achieves high granularity and precision without requiring any single complex model
3Ease of operation
If machine learning model outputs are used directly, then ease of operation is maintained, but loss of information occurs because outputs are more understandable by machines than humans
Solution Approach 1:
The rule-based processing system acts as an intermediary that converts machine-oriented model outputs into human-oriented final tags. This intermediary layer preserves the automated processing benefits while eliminating the loss of human understandability
Solution Approach 2:
The patent replaces the purely machine-learning-based tagging system with a hybrid system that incorporates rule-based processing. This substitution transforms the output format from machine-optimized to human-optimized while maintaining automation
Data Source
AI summary
The present disclosure relates to a system, a method and a computer-readable medium for tagging live streaming data. The method includes generating a first intermediate tag for the live streaming program, generating a second intermediate tag for the live streaming program, and determining a final tag for the live streaming program according to the first intermediate tag and the second intermediate tag. The present disclosure can categorize contents in a more granular and precise way.