Implicit Routing for Modular Conversational Handlers
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current human-machine interaction systems face complexity in managing interactive dialog flows, particularly in speech conversations, as they require analyzing verbal inputs in a single workspace, leading to inefficiencies and inaccuracies in intent estimation and action management.
Innovation Solution
The implementation of a method that routes verbal inputs to multiple handlers using implicit routing based on content and context, where verbal content identifiers extract features like intent and entity from the inputs, compute match confidence values, and select the most appropriate handler to manage the input, reducing ambiguity and complexity.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Device complexity
If a single workspace is used to analyze verbal inputs, then the system structure is simple, but the complexity of analyzing dialog flow increases and accuracy of intent estimation decreases
Solution Approach 1:
The patent divides the single workspace into multiple specialized handlers, each responsible for specific intents or tasks. This segmentation allows each handler to focus on particular aspects of verbal input analysis, improving accuracy while maintaining manageable complexity through modular organization.
2Manufacturing precision
If multiple handlers are introduced to improve intent estimation accuracy, then accuracy increases, but the complexity of routing and managing handlers increases
Solution Approach 1:
The patent introduces a router as an intermediary component that receives verbal inputs and automatically directs them to the appropriate handler based on content analysis. This mediator eliminates the need for users to manually manage or specify handlers, reducing routing complexity while enabling multiple specialized handlers to work together efficiently.
3Manufacturing precision
If explicit handler specification is required from users, then routing accuracy may improve, but user ease of operation decreases
Solution Approach 1:
The system performs self-service by automatically analyzing the content of verbal inputs and routing them to appropriate handlers without requiring user intervention. The router examines the input itself to determine the correct handler, eliminating the burden of explicit handler specification from the user while maintaining accurate routing through intelligent content-based decisions.
4Reliability
If comprehensive analysis of all verbal inputs is performed in one workspace, then completeness of analysis is achieved, but computation resources and latency increase
Solution Approach 1:
The patent segments the comprehensive analysis task across multiple specialized handlers, each optimized for specific types of verbal inputs. This distribution prevents any single component from bearing the full computational burden, reducing overall latency and resource consumption while maintaining completeness through the collective coverage of all handlers.
Solution Approach 2:
The router acts as an efficient intermediary that quickly directs verbal inputs to the most appropriate handler, avoiding unnecessary processing by all handlers. This selective routing mechanism preserves completeness of analysis by ensuring the right handler processes each input, while significantly improving computation efficiency by eliminating redundant analysis across the entire system.
Data Source
AI summary
A computer implemented method of routing a verbal input to one of a plurality of handlers, comprising using one or more processors adapted to execute a code, the code is adapted for receiving a verbal input from a user, applying a plurality of verbal content identifiers to the verbal input, each of the verbal content identifiers is adapted to evaluate an association of the verbal input with a respective one of a plurality of handlers by computing a match confidence value for one or more features, such as an intent expressed by the user and/or an entity indicated by the user, extracted from the verbal input and routing the verbal input to a selected one of the handlers based on the matching confidence value computed by the plurality of verbal content identifiers. The selected handler is adapted to initiate one or more actions in response to the verbal input.