Media Event Segmentation via Short Message Context Analysis

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing systems fail to effectively identify and annotate segments of interest within lengthy media events, such as live media events, as users may only be interested in specific portions and lack knowledge about their interest.

Innovation Solution

A method and system that utilize short message sampling from multiple users to identify segments and context within media events by analyzing short message activity, including follower counts and conversational patterns, to segment and annotate media events in real-time.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Loss of information

If the entire media event content is provided to users, then users can access all available content, but users cannot efficiently locate segments of interest within lengthy content

Engineering Contradiction:

Improveinformation accessibilityVSAvoidtime to locate interest

Core Design Contradiction:

Loss of informationVSLoss of time

Solution Approach 1:

The patent divides lengthy media event content into smaller, manageable segments based on temporal boundaries and content characteristics. Each segment is independently analyzed and annotated with metadata, allowing users to efficiently navigate to specific portions of interest without reviewing entire lengthy content.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The system performs preliminary analysis of media event content before user access, pre-segmenting content and generating annotations in advance. This preliminary processing creates an indexed structure that enables rapid retrieval of segments of interest, eliminating the need for users to manually search through lengthy content.

Inventive Principle:

Principle #10Preliminary action

2Productivity

If automated segment identification is implemented, then segment identification efficiency is improved, but measurement precision of segment boundaries may deteriorate

Engineering Contradiction:

Improvesegment identification efficiencyVSAvoidsegment boundary accuracy

Core Design Contradiction:

ProductivityVSMeasurement precision

Solution Approach 1:

The system employs feedback mechanisms where initial automated segment identification results are evaluated and refined. Annotations generated from short message sampling provide feedback signals that adjust and improve subsequent segment boundary detection, progressively enhancing precision while maintaining high identification efficiency.

Inventive Principle:

Principle #23Feedback

Solution Approach 2:

Segment boundaries are not fixed but dynamically adjusted based on multiple analysis criteria including short message activity patterns, content transitions, and temporal characteristics. This dynamic approach allows the system to adapt boundary positions for optimal accuracy while maintaining efficient automated processing.

Inventive Principle:

Principle #15Dynamics

Data Source

PatentUS10325019B2Media event structure and context identification using short messages

Publication Date: 2019.06.18 PINTEREST INC

AI summary

The present disclosure is descriptive of discovering structure, content, and context of a media event, e.g., a live media event, using real-time discussions that unfold through short messaging services. Generally, a sampling of short messages of a plurality of users is obtained. The sampling of short messages corresponds to a media event. A segment in the media event is identified using the sampling of short messages, and at least one term taken from the sampling of short messages is identified. The at least one term is indicative of a context of the identified segment.