Speech Input Profile Context for Multi-User Session Handling
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing speech processing systems struggle to differentiate between multiple users interacting with communal devices, leading to inconsistent and less personalized user experiences, while personal devices often rely on session contexts that may not accurately reflect user identities.
Innovation Solution
A system that determines user profiles based on biometric signals, presence detection, and explicitly selected profiles, allowing it to handle inputs from personal devices using a selected profile and communal devices using recognized profiles, while maintaining session contexts when appropriate.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Stability of the object's composition
If speech processing systems use session contexts to handle user inputs, then continuity of interaction is maintained, but user identity differentiation becomes inaccurate especially on personal devices
Solution Approach 1:
The system segments user identification into two independent pathways: biometric-based recognition for communal devices and session context-based identification for personal devices. This segmentation allows each pathway to be optimized for its specific use case, resolving the contradiction between maintaining session continuity and accurately identifying users.
Solution Approach 2:
The system dynamically selects between biometric recognition and session context approaches based on device type (communal vs. personal). This dynamic adaptation allows the system to maintain session continuity on personal devices while using more accurate biometric methods on communal devices, resolving the accuracy-stability contradiction.
2Device complexity
If speech processing systems treat all devices uniformly, then system complexity is reduced, but user experience personalization deteriorates
Solution Approach 1:
The system implements a universal framework that handles both communal and personal devices through a single architecture, while providing multi-functional user identification methods (biometric and session context). This allows the system to maintain simplicity at the architectural level while delivering personalized experiences through appropriate method selection.
Solution Approach 2:
The system applies different identification qualities to different device types: biometric recognition for communal devices and session context for personal devices. This local differentiation enables personalized user experiences without requiring complex customizations across the entire system architecture.
3Measurement precision
If biometric recognition is used for all devices, then user identity accuracy is improved, but system resource consumption and processing time increase
Solution Approach 1:
The system applies biometric recognition only partially - specifically for communal devices where user differentiation is critical. For personal devices, it uses the lighter session context approach, avoiding excessive resource consumption while maintaining sufficient accuracy for each device type.
Solution Approach 2:
The system changes the identification parameter based on device type: using biometric data for communal devices and session context identifiers for personal devices. This parameter adaptation reduces processing resource consumption on personal devices while maintaining accurate user identification where needed.
Data Source
AI summary
A speech-processing system may be configured to provide certain endpoints (e.g., skills and/or applications) with data reflecting an explicitly selected user profile. When handling requests from a device configured to support a session context (e.g., a personal device), the skill may handle multiple requests in an interaction (e.g., a “session”) using the selected profile as the session context, even if the system recognizes a different user for one or more of the requests. Thus, if the system recognizes more than one user using a personal device during an interaction with the skill (e.g., playing a game or requesting songs), the skill may handle each request of the interaction according to the selected profile. For a device not configured to support a session person, however, (e.g., a communal device) the skill may handle each request according to the recognized profile regardless of an explicitly selected profile.