Conversation System Using User History for Agent Utterance Generation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing conversation systems with intelligent agents lack the ability to consider past conversation content, requiring users to repeatedly provide personal information and correct agent utterances, leading to user inconvenience.
Innovation Solution
A conversation provision method and system that utilize a user's history information to enable an agent to lead a conversation appropriate to the user's state or situation, by storing and summarizing user utterances from previous sessions and using this information to generate relevant agent utterances in subsequent sessions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If the agent only considers current conversation content, then the conversation processing is simple, but the user convenience deteriorates due to repeated information provision
Solution Approach 1:
The system performs preliminary actions by storing user information and past conversation content in a database before new conversations occur. When a user initiates a conversation, the system automatically retrieves and utilizes this pre-stored information, eliminating the need for users to repeatedly provide the same information and improving convenience without proportionally increasing processing complexity.
Solution Approach 2:
A database serves as an intermediary between the user and the agent, storing and managing user information and conversation history. This intermediary component enables the agent to access relevant past information without directly complicating the conversation processing logic, as the database handles the complexity of information retrieval and management.
2Productivity
If the agent does not consider past conversation content, then the processing speed is fast, but the conversation relevance deteriorates
Solution Approach 1:
The system extracts only the necessary past conversation content and user information from the database that are relevant to the current conversation context. By selectively taking out only the needed information rather than processing entire conversation histories, the system maintains fast processing speed while preventing loss of relevant contextual information.
Solution Approach 2:
The system applies partial action by utilizing only the portion of past conversation content that is relevant to the current interaction, rather than processing all historical data. This selective approach maintains processing speed while ensuring that sufficient contextual information is available for relevant conversations.
3Adaptability or versatility
If the system stores and processes user history information, then the conversation customization improves, but the system complexity increases
Solution Approach 1:
The database serves as a universal component that handles multiple functions: storing user information, saving conversation history, retrieving relevant data, and managing information across different conversation sessions. This multi-functional approach enables conversation customization without requiring separate complex systems for each function, thereby limiting the increase in overall system complexity.
Data Source
AI summary
A conversation provision method includes forming a conversation session between an agent and a user; generating an utterance of the agent by using the user's history related to a previous conversation session having been formed before the conversation session; and performing a conversation with the user by providing the utterance of the agent to the user.