Semantic Emoji Input via Emotion Classification Model

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Traditional emoji input methods are time-consuming and inefficient, requiring users to search through numerous emoji libraries and packages, limiting the diversity and timeliness of emoji usage in chat applications, and often necessitating multiple downloads and updates across different platforms.

Innovation Solution

A semantic understanding based emoji input method that analyzes user input text to determine emotion labels and matches them with corresponding emojis from a vast resource database, providing users with relevant and diverse emoji options directly in the input interface, eliminating the need for manual package management and updates.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If users manually search through multiple emoji libraries and packages to find desired emojis, then emoji diversity and customization are improved, but input time and operational complexity increase significantly

Engineering Contradiction:
Improveemoji diversityVSAvoidinput time
Core Design Contradiction:
Adaptability or versatilityVSLoss of time

Solution Approach 1:

The system pre-establishes a comprehensive emoji resource database that aggregates emojis from multiple third-party packages and platforms before user input. This preliminary organization of emoji resources enables instant retrieval based on semantic analysis, eliminating the need for users to manually search through multiple packages during actual input operations.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The patent introduces an emotion classification model as an intermediary between user text input and emoji selection. The model performs semantic analysis on input text to determine emotion labels, which then automatically map to corresponding emojis from the pre-established database. This intermediary process replaces manual searching with automated, context-aware emoji recommendation.

Inventive Principle:
Principle #24Intermediary (Mediator)

2Adaptability or versatility

If users download and install multiple third-party emoji packages to access diverse emoji themes, then emoji variety is improved, but device storage requirements and operation complexity increase

Engineering Contradiction:
Improveemoji varietyVSAvoidpackage management complexity
Core Design Contradiction:
Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The system creates a universal emoji resource database that consolidates functionality across multiple third-party packages and platforms. Instead of requiring separate package installations for different emoji themes, the database provides unified access to diverse emoji collections, making the system multi-functional without increasing user-side complexity.

Inventive Principle:
Principle #6Universality (Multi-functionality)

Solution Approach 2:

The patent implements a centralized emoji resource database that stores copies of emoji resources from multiple sources. Users access emojis through this central database rather than installing multiple packages, effectively copying the essential emoji data into a manageable, unified structure that eliminates package management overhead.

Inventive Principle:
Principle #26Copying

3Reliability

If emoji packages are updated across different platforms to maintain current content, then emoji relevance is improved, but frequency of downloads and network resource consumption increase

Engineering Contradiction:
Improveemoji relevanceVSAvoidupdate frequency
Core Design Contradiction:
ReliabilityVSDuration of action of moving object

Solution Approach 1:

The system pre-establishes a comprehensive emoji resource database that aggregates emojis from multiple third-party packages and platforms before user input. This preliminary organization of emoji resources enables instant retrieval based on semantic analysis, eliminating the need for users to manually search through multiple packages during actual input operations.

Inventive Principle:
Principle #10Preliminary action

4Ease of operation

If simple emoticons are provided with basic input methods, then ease of input is improved, but emoji richness and user engagement decrease

Engineering Contradiction:
Improveinput simplicityVSAvoidemoji richness
Core Design Contradiction:
Ease of operationVSAdaptability or versatility

Solution Approach 1:

The patent introduces an emotion classification model as an intermediary between user text input and emoji selection. The model performs semantic analysis on input text to determine emotion labels, which then automatically map to corresponding emojis from the pre-established database. This intermediary process replaces manual searching with automated, context-aware emoji recommendation.

Inventive Principle:
Principle #24Intermediary (Mediator)

Data Source

PatentUS10685186B2Semantic understanding based emoji input method and device
Publication Date: 2020.06.16 BEIJING SOGOU TECHNOLOGY DEVELOPMENT CO LTD
  • US10685186B2 patent drawing
  • US10685186B2 patent drawing
  • US10685186B2 patent drawing

AI summary

The present disclosure provides a semantic understanding based emoji input method and device, and relates to the input method technology field. The method includes: obtaining a text content according to an input sequence; performing word segmentation on the text content, and extracting text features based on the word segmentation result; constructing an input vector using the text features, performing classification using an emotion classification model to determine an emotion label of the text content; based on a correspondence relationship between the emotion label and emojis of various themes, respectively obtaining an emoji corresponding to the emotion label from each of the various themes; sorting the obtained emojis of the various themes, and displaying the sorted emojis as candidate options in a client. The disclosed invention facilitates users to input an emoji, enhances emoji input efficiency, and provides users with rich and wide scope of emoji resources.