Speech Routing System Using Feedback-Driven Conditional Nodes
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing speech processing systems face challenges in efficiently routing user requests through conditional routing scenarios, requiring additional user input and interrupting the workflow with intermediate actions like authentication, which can complicate the user experience.
Innovation Solution
A speech processing routing system that dynamically determines routing destinations using machine learning models trained on user feedback and contextual data, generating routing plan data that includes conditional nodes and destination nodes, allowing for seamless execution of user requests without repeated input.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If traditional speech processing systems route user requests through conditional routing scenarios, then authentication and intermediate actions can be performed, but the user experience is interrupted and additional user input is required
Solution Approach 1:
The system performs authentication and determines routing destinations in advance by generating routing plan data that includes conditional nodes and destination nodes. This preliminary action allows the system to prepare the complete routing path before the user completes their request, eliminating the need for interrupting the user during authentication.
Solution Approach 2:
The system introduces routing plan data as an intermediary structure that mediates between the user's spoken request and the final execution. This routing plan data contains conditional nodes and destination nodes that enable the system to handle authentication and routing logic without requiring additional user input or interrupting the workflow.
2Reliability
If speech processing systems require additional user input for conditional routing, then authentication can be verified, but the workflow is complicated and time is lost
Solution Approach 1:
The system determines routing destinations and prepares routing plan data in advance, including conditional nodes for authentication. This allows authentication verification to be performed as part of the pre-computed routing plan rather than as an interrupting step during user interaction, reducing workflow completion time.
Solution Approach 2:
The system uses machine learning models trained on user feedback to predict routing destinations and generate routing plan data. This feedback mechanism enables the system to learn from past interactions and optimize routing decisions, reducing the need for additional user input and minimizing workflow disruption.
3Productivity
If speech processing systems use simple routing, then user requests are processed quickly, but conditional actions like authentication cannot be properly handled
Solution Approach 1:
The system segments the routing process into distinct components represented in the routing plan data: conditional nodes for authentication and other intermediate actions, and destination nodes for final request handling. This segmentation allows the system to manage complex conditional logic while maintaining efficient processing by pre-computing the entire routing path.
Solution Approach 2:
The system performs preliminary analysis to generate routing plan data that includes all necessary conditional nodes and destination nodes before executing the user request. This preliminary action enables the system to handle complex conditional actions efficiently by having the complete routing strategy prepared in advance, rather than making decisions during request processing.
Data Source
AI summary
Devices and techniques are generally described for using user feedback to determine routing decisions in a speech processing system. In various examples, first data representing a first utterance may be received. Second data representing a first semantic interpretation of the first utterance may be determined. A first intent data processing application may be selected for processing the second data. Feedback data may be determined related to the first intent data processing application processing the second data. Third data representing a semantic interpretation of a second utterance may be received, wherein the first semantic interpretation is the same as the second semantic interpretation. A second intent data processing application may be determined for processing the third data based at least in part on the feedback data.