AI Dialog System Reducing Turn Frequency via Task Association
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional dialog systems in electronic apparatuses provide only a response to user inquiries, leading to unnecessary dialog turns and increased user effort, as they do not offer additional related responses based on user preference and dialog history.
Innovation Solution
An electronic apparatus equipped with an artificial intelligence model that identifies tasks, determines the degree of association between them, sets response patterns, and provides additional responses, reducing unnecessary dialog turns by learning from user interactions and preferences.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Device complexity
If the dialog system provides only a response to user inquiries, then the system complexity is low, but the user has to perform multiple inquiries and the dialog time becomes long
Solution Approach 1:
The system performs preliminary analysis of user preferences and dialog history before providing responses. By pre-processing user data and identifying association relationships between tasks in advance, the system can proactively provide additional relevant information without waiting for multiple user inquiries, thereby reducing dialog time while maintaining manageable system complexity through structured data preparation.
2Productivity
If the electronic apparatus provides additional responses based on user preference and dialog history, then the user interaction efficiency is improved, but the device complexity increases
Solution Approach 1:
The system implements feedback mechanisms by continuously analyzing user preferences and dialog history to dynamically adjust and provide additional relevant responses. This feedback loop enables the system to learn from user interactions and improve user interaction efficiency over time. The complexity is managed by focusing feedback processing on specific user preference data and dialog history rather than comprehensive system analysis.
Solution Approach 2:
The system performs self-service by automatically analyzing user preferences and dialog history to generate additional relevant responses without requiring explicit user requests for each piece of information. The electronic apparatus serves itself by autonomously determining what additional information would be useful based on the identified association relationships between tasks, thereby improving user interaction efficiency while keeping the interface simple.
3Loss of information
If the system identifies tasks and determines degree of association between them, then additional relevant responses can be provided, but the processing complexity increases
Solution Approach 1:
The system segments the dialog processing into distinct task identification stages, where each user inquiry is broken down into specific tasks that can be independently analyzed for association relationships. By dividing the complex processing into manageable task segments, the system can identify relevant information and provide complete responses without overwhelming processing complexity, as each segment can be handled separately using established association rules.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
An electronic apparatus and a control method thereof are provided. A method of controlling an electronic apparatus according to an embodiment of the disclosure includes: receiving input of a first utterance, identifying a first task for the first utterance based on the first utterance, providing a response to the first task based on a predetermined response pattern, receiving input of a second utterance, identifying a second task for the second utterance based on the second utterance, determining the degree of association between the first task and the second task, and setting a response pattern for the first task based on the second task based on the determined degree of association satisfying a predetermined condition. The control method of an electronic apparatus may use an artificial intelligence model trained according to at least one of machine learning, a neural network, or a deep learning algorithm.