Media Sentiment Analysis via Segmented Portion Feedback

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current media interaction technologies do not allow users to effectively provide sentiment-based feedback on specific portions or objects within media content, such as videos or audio files, limiting the ability to analyze and generate reports on user preferences and reactions.

Innovation Solution

A system and method for receiving user input data that includes sentimental identifiers and pressure or time indicators, allowing users to associate sentiments with specific portions of media, which are then aggregated and analyzed to determine average sentiment values, enabling the creation of reports and personalized media experiences.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If users provide sentiment feedback on entire media pieces only, then data collection is simple, but the precision of sentiment analysis is insufficient for specific portions or objects

Engineering Contradiction:
Improvesentiment analysis precisionVSAvoidsystem complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent segments media content into distinct portions and identifies objects within those portions, allowing sentiment feedback to be associated with specific segments rather than the entire media piece. This enables precise sentiment analysis for particular objects or time periods while maintaining a manageable system structure through hierarchical organization of media segments and their associated sentiments.

Inventive Principle:
Principle #1Segmentation

2Reliability

If the system collects detailed sentimental information including pressure and time data, then the quality of sentiment data improves, but the amount of data to be processed increases

Engineering Contradiction:
Improvesentiment data qualityVSAvoiddata processing efficiency
Core Design Contradiction:
ReliabilityVSProductivity

Solution Approach 1:

The patent extracts only the essential sentiment-related features (sentiment identifier, pressure amount, time duration) from user interactions, storing and processing only these critical data points rather than capturing all possible interaction details. This extraction approach maintains high data quality for sentiment analysis while minimizing the overall data volume that requires processing and storage.

Inventive Principle:
Principle #2Taking out (Extraction)

3Adaptability or versatility

If users can select from multiple sentimental identifiers, then the versatility of sentiment expression improves, but the complexity of input interface increases

Engineering Contradiction:
Improvesentiment expression versatilityVSAvoidinput interface ease
Core Design Contradiction:
Adaptability or versatilityVSEase of operation

Solution Approach 1:

The patent implements a dynamic interface where the available sentimental identifiers and their arrangements can adapt based on context, such as the type of media being viewed or the user's interaction history. This dynamic adaptation allows the system to provide versatile sentiment expression options while maintaining ease of operation by presenting only the most relevant identifiers in a user-friendly manner at any given moment.

Inventive Principle:
Principle #15Dynamics

Data Source

PatentUS11947587B2Methods, systems, and media for generating sentimental information associated with media content
Publication Date: 2024.04.02 GOOGLE LLC
  • US11947587B2 patent drawing
  • US11947587B2 patent drawing
  • US11947587B2 patent drawing

AI summary

In accordance with some embodiments, a method for generating sentimental information associated with media content is provided, the method comprising: receiving user input data corresponding to a user; identifying a portion of the media content item based on the user input data; determining a sentiment based on the user input data, wherein the sentiment is one of a positive sentiment which indicates that the media content item was liked by the user or a negative sentiment which indicates that the media content item was disliked by the user; determining an amount of the sentiment based on the user input data; associating the amount of the sentiment with the portion of the media content item; and generating, for the media content item, sentimental information that indicates the amount of the sentiment associated with at least one portion of the media content item.