Prebuilt Conversational Items for Building CU Systems
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Building conversational understanding systems requires significant expertise, time, and resources, as developers need to create fully-labeled data and configure complex components like ASR, NLU, and NLG systems, which is resource-intensive and prohibitive for third-party developers.
Innovation Solution
A system that provides prebuilt conversational items with preconfigured parameters, constraints, and structures, allowing builders to select and implement these items without further input to form a conversational understanding system, reducing the need for domain expertise and resources.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If developers build conversational understanding systems from scratch using traditional methods, then the system can be fully customized to specific needs, but the process requires significant expertise, time, and resources
Solution Approach 1:
The patent applies preliminary action by pre-configuring conversational items with parameters, constraints, and structures before deployment. Developers can select from pre-built templates and items that have already been configured with common settings, eliminating the need to build everything from scratch while maintaining customization capability through selective modification.
Solution Approach 2:
The patent uses copying by providing reusable conversational item templates that can be selected and instantiated multiple times. These templates represent proven configurations that can be copied and adapted for different use cases, reducing the need to create unique configurations for each application.
2Reliability
If developers configure all components manually including ASR, NLU, and NLG systems, then the system achieves optimal performance for specific applications, but the process is resource-intensive and prohibitive for third-party developers
Solution Approach 1:
The patent applies partial action by allowing developers to configure only the specific parameters and constraints relevant to their application needs, rather than requiring complete configuration of all ASR, NLU, and NLG components. The system provides default configurations for non-critical parameters, enabling faster deployment while maintaining performance for application-specific requirements.
Solution Approach 2:
The patent implements universality by creating conversational item templates that can serve multiple functions across different applications. A single pre-configured template can be adapted for various use cases by modifying only application-specific parameters, reducing the need for separate configuration processes for each application.
3Productivity
If the system provides prebuilt conversational items with preconfigured parameters and constraints, then the building process becomes faster and requires less expertise, but the system may lack flexibility for highly customized applications
Solution Approach 1:
The patent applies dynamics by making the pre-configured conversational items modifiable and adaptable. While items start with pre-configured parameters and constraints for quick deployment, the system allows developers to modify these configurations dynamically based on specific application requirements, balancing speed with flexibility.
Solution Approach 2:
The patent uses segmentation by dividing the conversational system into discrete, selectable items and parameters. Each conversational item can be independently configured and modified, allowing developers to make targeted changes to specific parameters without affecting the entire system, thus maintaining both speed and flexibility.
Data Source
AI summary
Systems and methods for building conversational understanding systems are provided. More specifically, the systems and methods utilize prebuilt conversational items that can form a CU system upon selection by a builder without requiring any further input from the builder. Accordingly, the systems and methods for building a conversational understanding system reduce the expertise, time, and resources necessary to build a conversational understanding system for an application when compared to systems and methods that utilize conversational items that require further input from the builder.