User Utterance Routing by QoS Scoring Across Electronic Devices
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for determining which electronic device to process a user utterance do not consider the service quality of the application, leading to suboptimal user experience and inefficient intent classification.
Innovation Solution
An intelligent server and electronic device system that calculates a quality of service score for combinations of electronic devices and domains based on context information, determining the best device and domain to process the utterance, considering service quality.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If the server determines which electronic device to process user utterance based on predefined policy, then the device selection is simple and fast, but the service quality and user experience may be compromised
Solution Approach 1:
The patent changes the parameter for device selection from simple predefined policies to quality of service scores that incorporate multiple factors including device capabilities, application performance, and user context. This allows the system to maintain speed while improving service quality by dynamically adjusting selection criteria.
Solution Approach 2:
The patent replaces the mechanical predefined policy system with an intelligent scoring system that automatically evaluates multiple devices and applications based on contextual information. This substitution enables more reliable service quality determination while maintaining processing efficiency through automated decision-making.
2Device complexity
If the server only considers whether the application supports the utterance for determining which application to process, then the determination process is simple, but the service quality and user experience are not optimized
Solution Approach 1:
The patent changes the determination parameters from simple application support checks to comprehensive quality of service scores that include application performance metrics, device capabilities, and user context. This enables the system to maintain simplicity in the determination process while significantly improving service quality through multi-factor evaluation.
Solution Approach 2:
The patent introduces quality of service scores as an intermediary mechanism between the simple application support check and the final application selection. This intermediary layer aggregates multiple factors including application performance, device capabilities, and user context into a single scoring metric, enabling both simplicity and high service quality.
3Productivity
If the server processes each electronic device's intent classification separately, then the processing is straightforward, but the configuration complexity and processing time increase
Solution Approach 1:
The patent merges the intent classification process into a unified approach where the server simultaneously determines both the target electronic device and the target application through a single quality of service scoring process. This consolidation eliminates the need for separate processing steps, thereby improving efficiency while reducing configuration complexity.
Solution Approach 2:
The patent creates a universal intent classification system that handles both device selection and application determination within a single framework. The quality of service scoring mechanism serves multiple functions: evaluating device capabilities, assessing application performance, and making final selection decisions, thereby reducing overall system complexity and processing time.
Data Source
AI summary
An intelligent server for processing a user utterance is provided. The intelligent server includes a memory configured to store context information including information on electronic devices and information on domains corresponding to the electronic devices, and a processor configured to, based on a target utterance received from any one of the one or more electronic device and the context information, generate combinations of electronic device information and domain information capable of processing the target utterance, determine reference information for processing the target utterance among the context information, and calculate a quality of service score for each combination referring to the reference information, determine a target combination of a target electronic device and a target domain corresponding to the target electronic device based on the quality of service score, and transmit a command to process the target utterance with the target domain, to the target electronic device.


