Hybrid Voice Intent Processing for Low-Latency Accurate Requests
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing information handling systems struggle to efficiently process voice requests and accommodate multiple gaming environments with varying AV systems and network availability, leading to inconsistent user experiences across different locations in a home.
Innovation Solution
A hybrid local and global intent engine system is employed, where a local intent engine processes voice requests on a computing device, and if confidence thresholds are not met, a global intent engine on another device is utilized, with a hub device managing game sessions and AV configurations across multiple environments.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Speed
If a local intent engine is used to process voice requests, then processing speed and responsiveness are improved, but accuracy and reliability deteriorate when confidence thresholds are not met
Solution Approach 1:
The system divides intent prediction into two segments: local intent prediction (fast, first-level processing) and global intent prediction (accurate, second-level processing). The local intent engine processes requests immediately for speed, while the global intent engine provides backup accuracy when needed, resolving the contradiction between speed and reliability.
Solution Approach 2:
The hub device acts as an intermediary between the local computing device and the global intent engine. It receives voice requests locally, evaluates confidence measures, and selectively forwards requests to the global intent engine when local confidence is insufficient, enabling seamless transition between fast local processing and accurate global processing.
2Reliability
If a global intent engine is used to ensure accurate intent prediction, then reliability is improved, but processing speed and responsiveness deteriorate due to network dependency
Solution Approach 1:
The system performs preliminary local intent prediction before involving the global intent engine. By pre-processing requests locally and only escalating when confidence is insufficient, the system minimizes network dependency and maintains fast response times while ensuring accuracy when needed.
Solution Approach 2:
The system dynamically adjusts processing mode based on confidence measures. When local confidence is high, it uses fast local processing; when confidence is low, it transitions to accurate global processing. This dynamic adaptation resolves the contradiction between speed and reliability.
3Adaptability or versatility
If AV systems are configured for each environment, then user experience consistency is improved, but device complexity and configuration overhead increase
Solution Approach 1:
The hub device provides universal AV configuration management that works across multiple environments. It automatically detects the current environment, selects appropriate AV settings, and configures devices accordingly, enabling the system to adapt to different environments without requiring separate manual configurations for each location.
Solution Approach 2:
The system performs self-service environmental adaptation by automatically detecting which environment the user is in and configuring AV settings without user intervention. The hub device autonomously manages the complexity of multi-environment configuration, reducing the burden on users while maintaining adaptability.
4Stability of the object's composition
If session migration is implemented across environments, then user experience continuity is improved, but system coordination complexity increases
Solution Approach 1:
The hub device serves as an intermediary for session management across environments. It coordinates session state, manages migration between devices, and maintains continuity seamlessly, abstracting the complexity of multi-device coordination from users and enabling stable session composition across different environments.
Data Source
AI summary
Systems and methods described herein may provide a system that enables hybrid local and global processing of voice requests from a user. A computing device may receive audio data containing a voice request from a user and may determine, using a local intent engine, a local intent prediction based on the voice request. The computing device may determine that the local intent prediction has a confidence measure that is less than a predetermined threshold and may, in response, transmit data containing the voice request to a global intent engine. The computing device may receive a global intent prediction from the global intent engine and may determine a corresponding computing process based on the global intent prediction.


