Conversational Media Segment Detection From Viewing History

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Conventional media sharing systems fail to efficiently identify and share relevant segments of media content during conversations, as users often face overwhelming content choices and confusing interfaces, leading to subpar experiences.

Innovation Solution

A media guidance application that monitors voice communications between users, extracts keywords, and uses viewing history to identify and generate an indication of relevant media content segments for sharing, without requiring complex user interactions.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of operation

If conventional interfaces are used to select media content segments, then users can share specific content, but the interface becomes confusing and difficult to use during conversations

Engineering Contradiction:
Improveease of sharing media contentVSAvoidinterface complexity
Core Design Contradiction:
Ease of operationVSDevice complexity

Solution Approach 1:

The system automatically monitors voice communications, extracts keywords, and identifies relevant media segments without requiring manual interface interaction. The media sharing system serves itself by autonomously selecting and sharing content based on conversation analysis, eliminating the need for complex user navigation through media libraries and selection interfaces.

Inventive Principle:
Principle #25Self-service

Solution Approach 2:

The patent replaces manual mechanical interaction with conventional interfaces (clicking, scrolling, selecting) with an automated voice-based system. Voice monitoring and keyword extraction algorithms substitute for manual interface manipulation, allowing users to share media content naturally during conversation without focusing on controlling their device.

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

2Loss of information

If users manually navigate through media content to find desired segments, then specific content can be shared, but users lose the moment and excitement of the conversation

Engineering Contradiction:
Improveloss of conversation contextVSAvoidtime to locate content
Core Design Contradiction:
Loss of informationVSLoss of time

Solution Approach 1:

The system performs preliminary actions by continuously monitoring and analyzing voice communications in real-time. Keywords are extracted and media segments are pre-identified during the conversation flow, so when a user expresses interest in sharing content, the relevant segments are already prepared and can be immediately shared without interrupting the conversation's momentum.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The system provides continuous feedback by monitoring conversation content and automatically identifying relevant media segments. This real-time feedback loop allows the system to understand user intent and provide appropriate media suggestions or automatic sharing based on the ongoing conversation, maintaining the natural flow and excitement of the interaction.

Inventive Principle:
Principle #23Feedback

3Adaptability or versatility

If comprehensive media content is made available for sharing, then users can find relevant segments, but the overwhelming amount of content makes selection difficult

Engineering Contradiction:
Improvemedia content availabilityVSAvoiddifficulty in finding content
Core Design Contradiction:
Adaptability or versatilityVSEase of operation

Solution Approach 1:

The system extracts only the relevant portions of media content that are directly related to the conversation topics. By using keyword extraction and conversation analysis, the system filters out unnecessary content and presents only the specific segments that match the discussion context, making content selection intuitive and effortless during conversations.

Inventive Principle:
Principle #2Taking out (Extraction)

Data Source

PatentUS12621530B2Augmented display from conversational monitoring
Publication Date: 2026.05.05 ADEIA GUIDES INC
  • US12621530B2 patent drawing
  • US12621530B2 patent drawing
  • US12621530B2 patent drawing

AI summary

Systems and methods are provided for generating for display an indication of a segment of media content relevant to a voice communication. This may be accomplished by a media guidance application that monitors a voice communication between users. The media guidance application determines that a first user is describing media content. In response to determining that the first user is describing the media content, the media guidance application retrieves media asset viewing history of the first user. The media guidance application determines, based on metadata of each media asset in the media asset viewing history of the first user and the voice communication, a media asset that the first user is describing. The media guidance application determines, based on metadata of the media asset, a segment of the media asset that the first user is describing. The media guidance application generates, for display, an indication of the segment.