Chat Suggestion System Using Usage-Based Content Pair Ranking

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Conventional chat systems face challenges in generating and maintaining chat suggestions for unconventional message content, such as pictograms and ideograms, due to their abstract nature and changing contextual meaning, requiring significant frontend work and regular database updates.

Innovation Solution

A content suggestion system that tracks and ranks message content pairs based on usage metrics, displaying suggestions in a chat interface, including text, images, audio, and video, to provide relevant and dynamic chat suggestions.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If conventional chat systems use explicit inputs and dictionaries to generate chat suggestions, then the system can provide basic text suggestions, but it fails to handle unconventional message content like pictograms and ideograms due to their abstract nature and changing contextual meaning

Engineering Contradiction:
Improvecapability to handle unconventional message contentVSAvoidfrontend work and database maintenance
Core Design Contradiction:
Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The system automatically learns from user interactions and ranks content pairs based on actual usage patterns. The ranking module continuously updates suggestions based on what users actually select, eliminating the need for manual frontend work and database maintenance while adapting to changing contextual meanings of unconventional content

Inventive Principle:
Principle #25Self-service

Solution Approach 2:

The system implements a feedback loop where user selections of content pairs are tracked and used to update the ranking. This feedback mechanism allows the system to learn from real usage patterns and continuously improve its suggestions without requiring manual reconfiguration of databases or frontend code

Inventive Principle:
Principle #23Feedback

2Reliability

If the system tracks and stores content pairs with usage metrics, then it can dynamically rank and display relevant chat suggestions, but it requires ongoing data collection and processing operations

Engineering Contradiction:
Improverelevance of chat suggestionsVSAvoidtime for data collection and processing
Core Design Contradiction:
ReliabilityVSLoss of time

Solution Approach 1:

The system pre-ranks content pairs based on historical usage data and presents the top-ranked suggestions immediately. This preliminary ranking based on accumulated usage metrics eliminates the need for real-time complex processing, reducing time delays while maintaining high relevance of suggestions

Inventive Principle:
Principle #10Preliminary action

Data Source

PatentUS20240430219A1Content suggestion system
Publication Date: 2024.12.26 SNAP INC
  • US20240430219A1 patent drawing
  • US20240430219A1 patent drawing
  • US20240430219A1 patent drawing

AI summary

A content suggestion system to generate and cause display of a set of chat suggestions based on messages received at a client device. The content suggestions system is configured to display messages that include message content at a client device, and identify content selected by a user of the client device to be included in a response to the messages received at the client device. The content suggestion system tracks and stores a number of times in which a particular pair of content appear in succession in a chat context, and calculates a ranking of the content among a set of available content. When subsequent messages that include the content of the content pair are displayed at the client device, the content suggestion system retrieves and presents a set of content as suggestions, based on the corresponding ranks.