Conversation Relevance Filtering for Messaging Interfaces

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Messaging applications face challenges in effectively presenting relevant posts within conversations, often overwhelming users with multiple author accounts, making it difficult to identify the most relevant contributors and providing insufficient information about authors.

Innovation Solution

A computing device determines the most relevant accounts in a conversation and presents only their associated posts, while allowing users to select and view additional information about authors, such as profile cards, to enhance user engagement and understanding.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Loss of information

If all posts from multiple accounts are presented in a conversation, then the completeness of information is improved, but the complexity of the interface and difficulty of identifying relevant content increases

Engineering Contradiction:
Improvecompleteness of conversation informationVSAvoidinterface complexity
Core Design Contradiction:
Loss of informationVSDevice complexity

Solution Approach 1:

The patent segments the conversation display by identifying and separating posts from different accounts, then selectively presenting only posts from the most relevant account. This segmentation allows the system to maintain information completeness for relevant participants while filtering out content from less relevant accounts, thereby reducing interface complexity without losing important conversation context.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The system extracts and identifies the most relevant account from multiple participants in a conversation based on analysis of post associations and conversation patterns. By extracting only the relevant account's posts for display while maintaining access to all posts in the background, the system reduces the visible information complexity while preserving the essential conversation flow and context.

Inventive Principle:
Principle #2Taking out (Extraction)

2Quantity of substance

If posts from multiple accounts are displayed, then the quantity of information is improved, but the ease of operation and user focus deteriorates

Engineering Contradiction:
Improvequantity of posts displayedVSAvoidease of identifying relevant content
Core Design Contradiction:
Quantity of substanceVSEase of operation

Solution Approach 1:

The system extracts and identifies the most relevant account from multiple participants in a conversation based on analysis of post associations and conversation patterns. By extracting only the relevant account's posts for display while maintaining access to all posts in the background, the system reduces the visible information complexity while preserving the essential conversation flow and context.

Inventive Principle:
Principle #2Taking out (Extraction)

Solution Approach 2:

The system dynamically adjusts the displayed posts based on the identified relevant account, automatically filtering content to show only posts from that account while maintaining the ability to access other posts on demand. This dynamic adaptation simplifies the user interface and improves ease of operation by presenting information in a context-relevant manner without permanently losing access to the complete conversation data.

Inventive Principle:
Principle #15Dynamics

3Loss of information

If detailed information about all authors is provided, then the depth of information is improved, but the complexity of the interface increases

Engineering Contradiction:
Improvedepth of author informationVSAvoidinterface complexity
Core Design Contradiction:
Loss of informationVSDevice complexity

Solution Approach 1:

The patent applies local quality by providing detailed author information specifically for the most relevant account while maintaining a simplified view for other accounts. The system enhances the display with comprehensive profile details, post history, and contextual information for the identified relevant account, while keeping the interface clean and simple for less relevant participants, thereby optimizing information depth where it matters most without overwhelming the overall interface complexity.

Inventive Principle:
Principle #3Local quality

Data Source

PatentUS11301115B2Determining most relevant accounts in a conversation
Publication Date: 2022.04.12 X CORP
  • US11301115B2 patent drawing
  • US11301115B2 patent drawing
  • US11301115B2 patent drawing

AI summary

A computing device can receive at least a first post in association with a first account, a second post in association with the first account, the second post being associated with the first post, a third post in association with a second account, the third post being associated with the first post, a fourth post in association with the second account, the fourth post being associated with the first post, and a fifth post in association with a third account, the fifth post being associated with the first post, determine that the first account and the second account are most relevant to a conversation, and based on determining that the first account and the second account are most relevant to the conversation, present the first post, the second post, the third post, and the fourth post without presenting the fifth post.