Electronic Apparatus Emotion Recognition via Text-Gated Camera Activation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing electronic apparatuses face challenges in reliably identifying user emotions while minimizing power consumption and processing load, as they often require constant camera or microphone usage, leading to increased power consumption and reduced real-time processing efficiency.
Innovation Solution
An electronic apparatus that uses a processor to identify user emotions from input text, selectively turning on a camera or microphone only when emotion-related information is detected, and combines information from text, images, and audio using trained AI models to improve reliability and reduce power usage.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If a camera or microphone is always turned on to identify user emotion with high reliability, then emotion recognition reliability is improved, but power consumption increases
Solution Approach 1:
The system performs preliminary text analysis before activating the camera or microphone. By first processing the input text through an AI model to detect emotion-related keywords, the system determines whether camera/microphone activation is necessary, thereby avoiding unnecessary power consumption while maintaining reliability when needed
Solution Approach 2:
The system dynamically adjusts the operating state of the camera and microphone based on real-time text analysis results. When emotion-related information is detected in the text, the camera or microphone is activated; otherwise, they remain inactive. This dynamic adaptation resolves the contradiction between maintaining reliability and reducing power consumption
2Reliability
If user image or audio is processed in real-time using AI technology, then emotion recognition reliability is improved, but processing load increases
Solution Approach 1:
The emotion recognition process is segmented into multiple stages: first, text is analyzed for emotion-related keywords; second, based on text analysis results, image or audio processing is selectively performed. This segmentation reduces the overall processing load by avoiding unnecessary real-time image/audio analysis while maintaining reliability through multi-modal verification when needed
Solution Approach 2:
The system performs partial processing by analyzing only the text component first, and conditionally processes image or audio data based on text analysis outcomes. This partial action approach reduces processing load compared to always processing all data types, while still achieving reliable emotion recognition when the text indicates emotional content
3Use of energy by moving object
If only text input is used to identify user emotion, then power consumption is reduced, but emotion recognition reliability decreases
Solution Approach 1:
Text analysis is performed as a preliminary step to determine whether camera or microphone activation is necessary. This preliminary text processing consumes minimal power and serves as a gatekeeper to decide when more power-intensive image/audio processing should be activated, thereby maintaining low power consumption while ensuring reliability when needed
Solution Approach 2:
The system dynamically switches between text-only mode and multi-modal mode based on the content analysis. When text contains emotion-related information, the system activates camera or microphone for enhanced reliability; when text lacks emotional content, the system remains in low-power text-only mode. This dynamic switching resolves the contradiction between power consumption and reliability
Data Source
Figure 1~3
Figure 4~5b
Figure 5c~6b
AI summary
An electronic apparatus is provided. The electronic apparatus includes a user interface, a camera, a memory configured to store a first artificial intelligence model trained to obtain information on an emotion based on an input image, and a processor, connected to the user interface, the camera, and the memory, configured to control the electronic apparatus. The processor is configured to, based on text being input through the user interface, identify whether the text includes first information on a user's emotion, based on the text including the first information, obtain second information for the emotion by inputting the image obtained through the camera to the first artificial intelligence model, and identify a type of the user's emotion based on the first information obtained from the text and the second information obtained from the image.