Digital Assistant Voiceprint Authorization for Public Safety
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Public safety digital assistants, such as those used by police officers, face challenges in distinguishing between authorized and unauthorized users, leading to potential disruptions and misuse when responding to wake words and queries in public safety contexts.
Innovation Solution
Implementing a system that builds voiceprints of unauthorized secondary users and only accepts intent input from authorized users, ensuring that only the primary user can issue query intents and secondary users can provide additional input only when explicitly allowed.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If the digital assistant responds to wake words from any user, then the device remains responsive and useful to the primary user, but unauthorized secondary users can disrupt operations by issuing false queries or commands
Solution Approach 1:
The system segments user authorization into two distinct levels: primary users who can issue complete query intents, and secondary users who can only provide intent input when explicitly allowed. This segmentation resolves the contradiction by maintaining responsiveness for authorized users while blocking unauthorized disruption from secondary users.
Solution Approach 2:
The patent introduces an intermediary authorization mechanism that mediates between wake word detection and query processing. The system uses voiceprint analysis and authorization checks as an intermediary step to verify user credentials before allowing query intent submission, thus preventing unauthorized access while maintaining responsiveness for legitimate users.
2Adaptability or versatility
If the digital assistant accepts input from multiple speakers in a household, then the device serves multiple users, but it cannot distinguish between authorized and unauthorized users
Solution Approach 1:
The system performs preliminary actions by building and storing voiceprints of authorized users in advance. Before processing any query, the system compares the wake word speaker's voice against stored voiceprints to verify authorization. This preliminary verification enables multi-user support while maintaining precise user identification and authorization control.
3Productivity
If the digital assistant responds to all wake words regardless of speaker, then the device remains highly responsive, but it becomes vulnerable to misuse and disruption by non-owners
Solution Approach 1:
The system applies preliminary anti-action by implementing preemptive authorization checks and voiceprint verification before processing query intents. This prevents unauthorized users from misusing the system while maintaining rapid response for authorized users, thus eliminating harmful factors without sacrificing productivity.
Data Source
AI summary
Techniques for a digital assistant to receive intent input from a secondary user are provided. A digital assistant receives a query intent from a primary user, wherein the primary user is authorized to provide query intents. It is determined, based on the query intent, that intent input will be provided by a secondary user, wherein the secondary user is not authorized to provide query intents. Intent input provided by the secondary user is received. The digital assistant processes the query intent using the intent input. The results of the query intent are provided to the primary user.