Emotion-Driven Image Selection and Merging in Electronic Devices

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing technologies lack the ability to efficiently select or edit images that represent a user's emotional state among multiple candidates, and there is no method to merge images corresponding to multiple users into a single image.

Innovation Solution

An electronic device and method that allow for the selection and/or editing of images based on the type and degree of a user's emotion, and the ability to merge images from multiple users into a single image.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If multiple candidate images are provided to represent user emotions, then the expressiveness of communication is improved, but the time required to select the desired image increases

Engineering Contradiction:
ImproveexpressivenessVSAvoidimage selection time
Core Design Contradiction:
Adaptability or versatilityVSLoss of time

Solution Approach 1:

The system automatically performs image selection based on user input text without requiring manual browsing through candidate images. The image selection unit selects an appropriate image automatically by analyzing the user's input text and matching it with suitable images from the database, enabling the system to serve itself in the selection process.

Inventive Principle:
Principle #25Self-service

Solution Approach 2:

The manual mechanical process of browsing and selecting images is replaced with an automated information processing system. The image selection unit uses text analysis and matching algorithms to automatically determine the most appropriate image, substituting the manual selection mechanism with an intelligent automated system.

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

2Adaptability or versatility

If images from multiple users are merged into a single image, then the representation of group emotions is improved, but the complexity of image processing increases

Engineering Contradiction:
Improvegroup emotion representationVSAvoidimage processing complexity
Core Design Contradiction:
Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The image merging process is segmented into distinct functional units: an image merging unit that receives individual user images, analyzes their emotional content, and combines them into a composite image representing group emotion. This segmentation allows complex processing to be broken down into manageable, specialized operations.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The image merging unit is designed to handle multiple types of input images from different users and produce a universal output that represents collective emotion. The system can process various image formats and emotional expressions from multiple users through a single multi-functional merging mechanism.

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

Data Source

PatentEP3669537B1Electronic device providing text-related image and method for operating the same
Publication Date: 2025.06.04 SAMSUNG ELECTRONICS CO LTD
  • EP3669537B1 patent drawingFigure 1A~1B
  • EP3669537B1 patent drawingFigure 2A
  • EP3669537B1 patent drawingFigure 2B

AI summary

An electronic device comprises an input device comprising input circuitry, a display device, a communication circuit, and at least one processor configured to control the electronic device to: receive a text through the input device, transmit first information about the text to a server, control the communication circuit to receive second information associated with an image identified based on an emotional state of a first user, the emotional state of the first user being identified as a result of analysis of the text by a learning model trained using a database for a plurality of texts and a plurality of types of emotion and degrees of emotion and an emotional state of a second user conversing with the first user, and display the image based on the second information associated with the image.