Speechlet Orchestration for Accurate Context-Based Command Routing
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing speech processing systems face challenges in accurately routing user inputs to the most appropriate speechlet due to ambiguity and disproportionate prioritization, leading to inefficient and sometimes inaccurate execution of user commands.
Innovation Solution
A system architecture with a system orchestration component and an aggregator that incorporates knowledge of speechlet functionality and routing rules, along with a conflict resolution mechanism, to determine the best speechlet for user inputs based on context and conditions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If speech processing systems use simple routing based on basic keyword matching, then the system complexity is low, but the routing accuracy deteriorates due to ambiguity and disproportionate prioritization
Solution Approach 1:
The patent introduces a system orchestration component as an intermediary between the speechlet invocation and the execution environment. This mediator analyzes routing rules, resolves conflicts between multiple speechlets, and determines the most appropriate speechlet based on contextual factors, thereby improving routing accuracy without requiring fundamental changes to the underlying speech processing architecture
Solution Approach 2:
The system implements feedback mechanisms where the system orchestration component continuously evaluates routing outcomes and adjusts speechlet selection based on performance metrics and contextual information. This feedback loop enables the system to learn from past routing decisions and improve accuracy over time while maintaining manageable complexity through iterative optimization
2Measurement precision
If the system queries multiple speechlets to determine the best match, then the routing accuracy improves, but the processing time increases
Solution Approach 1:
The patent applies preliminary action by pre-configuring routing rules and speechlet priorities before runtime. The system orchestration component prepares routing decisions in advance based on available contextual information, allowing it to quickly determine the most appropriate speechlet without querying all possible speechlets during actual command processing, thus reducing processing time while maintaining accuracy
Solution Approach 2:
The system segments the speechlet selection process into distinct phases: initial filtering based on routing rules, conflict resolution for overlapping speechlets, and final selection. This segmentation allows the system to efficiently narrow down candidates through hierarchical decision-making rather than evaluating all speechlets equally, reducing processing time while preserving routing accuracy
3Reliability
If the system uses a comprehensive routing rule evaluation mechanism, then the command execution accuracy improves, but the computational resources required increase
Solution Approach 1:
The system implements partial action by evaluating only the necessary subset of routing rules and speechlets based on the specific command context. The system orchestration component selectively applies routing rule evaluation depth - using comprehensive evaluation only when needed and simpler evaluation for routine commands - thereby maintaining high execution accuracy while optimizing computational resource utilization through adaptive evaluation intensity
Data Source
AI summary
Techniques for routing a user command to a speechlet and resolving conflicts between potential speechlets are described. A system determines an intent of an input command. The system also receives context information associated with the input command. The system determines speechlets (e.g., speechlets and/or skills) that may execute with respect to the input command given the intent and the context data. The system then determines whether conditions of routing rules, associated with the speechlets, are satisfied given the context data. If the conditions of only one routing rule are satisfied, the system causes the speechlet associated with the routing rule to execute with respect to the input command. If the conditions of more than one routing rule are satisfied, the system may determine a speechlet to execute with respect to the input command based on the speechlets' priorities in a list of speechlets and/or based on potential output data provided by the speechlets.