Hierarchical Dialog Task Library for Spoken Systems
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing spoken dialog systems face challenges in reusing dialog knowledge across domain tasks, requiring significant construction time and effort, and lack a method to package knowledge for subtasks, leading to inefficient dialog management and increased system-user interaction.
Innovation Solution
A spoken dialog system utilizing a hierarchical dialog task library that packages and manages dialog knowledge for subtasks, allowing for the reuse of existing knowledge and enabling effective dialog flow management by estimating subsequent user interactions, thereby reducing design complexity and construction time.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If dialog knowledge is constructed for each domain task using existing methods, then the dialog service can be provided, but a large amount of time and effort is required and dialog knowledge cannot be reused
Solution Approach 1:
The patent segments dialog knowledge into hierarchical task units (domain tasks divided into subtasks, which are further divided into smaller task units). This segmentation allows reusable dialog knowledge to be packaged at the subtask level, enabling efficient reuse across different domain tasks without reconstructing entire dialog knowledge bases, thereby reducing construction time and improving productivity.
Solution Approach 2:
The patent creates a dialog knowledge library that stores reusable dialog knowledge templates and patterns. These packaged knowledge units can be copied and adapted for different domain tasks, eliminating the need to construct dialog knowledge from scratch for each new application, thus significantly reducing construction time and effort.
2Ease of operation
If traditional dialog management is used, then system response can be processed, but user side dialog progress information is lost causing unnecessary dialog interactions
Solution Approach 1:
The patent implements dual dialog management that incorporates feedback mechanisms to track and maintain user side dialog progress information. By monitoring user dialog state and providing appropriate feedback, the system can anticipate user needs and guide the dialog flow, reducing unnecessary interactions and improving ease of operation without significantly increasing complexity.
3Adaptability or versatility
If dialog knowledge is not packaged for subtasks, then existing systems can operate, but new application domains cannot be efficiently created by combining subtasks
Solution Approach 1:
The patent segments dialog knowledge into reusable subtask units that can be independently packaged and combined. This segmentation enables flexible creation of new application domains by selecting and combining appropriate subtasks from the library, greatly improving adaptability and ease of creating new domains without rebuilding entire dialog systems.
Data Source
AI summary
The present invention relates to a spoken dialog system and method based on dual dialog management using a hierarchical dialog task library that may increase reutilization of dialog knowledge by constructing and packaging the dialog knowledge based on a task unit having a hierarchical structure, and may construct and process the dialog knowledge using a dialog plan scheme about relationship therebetween by classifying the dialog knowledge based on a task unit to make design of a dialog service convenient, which is different from an existing spoken dialog system in which it is difficult to reuse dialog knowledge since a large amount of construction costs and time is required.