Character Communication Device With Contextual Facial Expression Variation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing communication devices lack variation in facial expressions for the same voice input, leading to user disinterest.
Innovation Solution
A communication device that generates varied facial expressions based on user emotions and internal states, using a combination of sensors to estimate emotions and a database to select appropriate responses, allowing for rich facial expression variations.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If the communication device uses the same response sentence and facial expression for the same voice input, then the device operation is simple and reliable, but the user loses interest due to lack of variation
Solution Approach 1:
The patent applies dynamics by making the facial expression selection variable and adaptive rather than fixed. The system dynamically selects from multiple facial expressions based on detected user emotions and internal device states, allowing the same voice input to trigger different expressions in different contexts. This resolves the contradiction by introducing variability without requiring complete system redesign.
Solution Approach 2:
The patent changes the parameter of facial expression selection based on multiple input parameters including user emotions detected by sensors and internal device states. By varying the output parameter (facial expression) according to changing input conditions, the system achieves diversity in response while maintaining a relatively simple underlying architecture that processes these parameters through standardized pathways.
2Measurement precision
If the communication device uses multiple sensors to detect user emotions and internal states, then the facial expression variation is enhanced, but the device complexity increases
Solution Approach 1:
The patent segments the emotion detection function across multiple specialized sensors, each responsible for detecting specific emotional cues (facial expressions, voice tone, body language). This segmentation allows the system to achieve comprehensive emotion detection accuracy while keeping each individual sensor relatively simple and manageable, resolving the contradiction between measurement precision and device complexity.
Solution Approach 2:
The patent implements multi-functionality by using a centralized control unit that processes inputs from multiple different sensor types and integrates them into a unified emotion assessment. This universal processing approach allows the system to achieve high measurement precision through multiple sensors while avoiding the complexity of having separate processing systems for each sensor type.
3Reliability
If the communication device selects facial expressions based on combination of user emotions and internal states, then the communication effectiveness is improved, but the control complexity increases
Solution Approach 1:
The patent applies local quality by assigning specific roles and weights to different input factors (user emotions versus internal device states) in the facial expression selection process. Rather than treating all inputs uniformly, the system gives appropriate emphasis to each type of input based on its relevance, achieving effective communication through nuanced control while managing complexity through differentiated processing strategies.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
A communication device including: an utterance acquisition part (101, 201) configured to acquire an utterance of a user to a character; an information acquisition part (102, 202) configured to acquire information different from the utterance; a voice generation part (209, 210) configured to generate a response voice to be emitted by the character based on a content of the utterance acquired by the utterance acquisition part (101, 201); and an expression generation part (205, 207) configured to generate a response expression to be expressed by a face portion of the character based on the content of the utterance acquired by the utterance acquisition part (101, 201), wherein when the information is acquired from the information acquisition part (102, 202), the expression generation part (205, 207) generates the response expression using the information together with the content of the utterance, the response expression generated when the information is acquired being different from a response expression generated when the information is not acquired.