Conversation Frame Extraction for Emotional State Control
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current automatic response systems from agents do not consider how users feel during conversations, leading to ineffective engagement.
Innovation Solution
A communication system that analyzes actual user conversations to generate a conversation structure that can lead users to a predetermined feeling by accumulating and extracting conversation frames based on feeling parameters.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of manufacture
If voice of an automatic response from the agent is based on conversation data generated in advance on assumption of questions and answers with the user, then the system can provide structured responses, but how the user feels through the conversation is not taken into consideration
Solution Approach 1:
The system performs preliminary analysis of user conversations to extract feeling parameters and generate conversation frames in advance. These frames are structured data that capture emotional contexts and patterns, which are then reused during actual agent interactions to quickly adapt responses without real-time analysis overhead
Solution Approach 2:
The system creates simplified copies of actual user conversations in the form of conversation frames that capture essential emotional patterns. These frames are standardized templates that replicate the structure and emotional context of real conversations, enabling the agent to respond appropriately without processing entire conversation histories
2Adaptability or versatility
If the system accumulates and analyzes actual user conversations to generate conversation structures, then it can lead users to predetermined feelings, but the complexity of data processing increases
Solution Approach 1:
The system segments conversation data into discrete feeling parameters and conversation frames. Each conversation is broken down into structured components representing different emotional states and transitions, making the complex data manageable and reusable for guiding users to predetermined feelings
Solution Approach 2:
The system transforms unstructured conversation data into structured parameters representing user feelings. By converting qualitative emotional states into quantifiable feeling parameters, the system enables computational processing and systematic manipulation of conversation structures to guide emotional outcomes
3Measurement precision
If feeling parameters are extracted from each collected conversation unit, then the system can understand user emotions, but the processing time and computational resources increase
Solution Approach 1:
The system extracts feeling parameters and generates conversation frames in advance during offline processing. This preliminary analysis creates a reusable database of emotional patterns that can be quickly matched during real-time interactions, avoiding the need for time-consuming analysis during actual agent-user conversations
Data Source
AI summary
The communication system includes a communication unit that receives a conversation of a user, an accumulation unit that accumulates a conversation frame that describes a structure of a conversation generated on a basis of the conversation of the user collected via the communication unit, and a control unit that obtains a feeling parameter related to a feeling of the user who sends the conversation in units of the collected conversation. The control unit further extracts the conversation frame from the conversation on a basis of the feeling parameter, and accumulates the conversation frame in the accumulation unit.