Modular Spoken Dialog System Context Shift Management
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Developing complex spoken dialog systems is costly and time-consuming due to the difficulty in handling context shifts and requiring highly skilled developers, especially with the increased complexity from advanced large vocabulary speech recognition and natural language understanding.
Innovation Solution
A method and system that utilize modular subdialogs and flow controllers to manage context shifts within spoken dialog systems, allowing for reusable components and efficient handling of user input changes, enabling simpler development and deployment of spoken dialog services.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If traditional dialog manager development methods are used with advanced speech recognition and natural language understanding, then the system can handle more complex speech applications, but the development process becomes more costly and time-consuming
Solution Approach 1:
The dialog manager is divided into multiple flow controllers, each responsible for specific dialog contexts. This segmentation allows the system to handle complex speech applications by distributing dialog management across specialized components rather than requiring a single complex dialog manager, thereby reducing overall system complexity while maintaining versatility.
Solution Approach 2:
Flow controllers are designed as universal components that can be reused across different dialog contexts and speech applications. This multi-functionality allows the same flow controller architecture to serve multiple purposes, reducing development costs and time while maintaining the capability to handle complex speech applications through configuration rather than custom development.
2Reliability
If traditional development processes are used for dialog managers, then highly-skilled developers are required, but this increases development costs and time
Solution Approach 1:
The flow controller architecture enables less-skilled developers to create and maintain dialog managers by providing a standardized, self-service framework. Developers can configure flow controllers for specific dialog contexts using predefined patterns and interfaces, reducing the need for highly-skilled developers while maintaining dialog manager accuracy through the structured approach.
3Adaptability or versatility
If context shifts are handled in traditional spoken dialog services, then the system can respond to user input changes, but encoding these transitions becomes tedious and difficult
Solution Approach 1:
Context shifts are handled by transitioning between different flow controllers, each specialized for specific dialog contexts. This segmentation makes encoding context shifts easier by defining clear boundaries and transition points between contexts, rather than requiring complex encoding within a single dialog manager. The system maintains adaptability to user input changes by allowing smooth transitions between flow controllers based on user input.
Data Source
AI summary
A system and method are disclosed for switching contexts within a spoken dialog between a user and a spoken dialog system. The spoken dialog system utilizes modular subdialogs that are invoked by at least one flow controller that is a finite state model and that associated with a dialog manager. The spoken dialog system includes a dialog manager with a flow controller and a reusable subdialog module. The method includes, while the spoken dialog is being controlled by the subdialog module that was invoked by the flow controller, receiving context-changing input associated with speech from a user that changes a dialog context and comparing the context-changing input to at least one context shift. And, if any of the context shifts are activated by the comparing step, then passing control of the spoken dialog to the flow controller with context shift message and destination state.