Voice Query Fingerprinting for Illegitimate Request Suppression
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing voice-based client systems struggle to differentiate between legitimate and illegitimate voice queries, particularly in environments where malicious actors or media content may trigger unintended processing of voice queries.
Innovation Solution
The system employs a method to detect illegitimate voice queries by clustering similar queries received from multiple client devices over time, generating electronic fingerprints for common queries, and blacklisting queries that meet specific suppression criteria to prevent unwanted processing.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If the system processes all voice queries received from client devices, then the system responds to all user requests, but malicious or illegitimate queries consume system resources and may cause denial of service
Solution Approach 1:
The system performs preliminary actions by generating electronic fingerprints of voice queries and maintaining a blacklist of illegitimate queries before processing requests. When a voice query is received, the system first checks if its fingerprint exists in the blacklist, preventing illegitimate queries from consuming processing resources while allowing legitimate queries to proceed normally
Solution Approach 2:
The patent introduces electronic fingerprints as an intermediary mechanism between the voice query and the processing system. The fingerprint serves as a mediator that identifies and filters illegitimate queries without requiring the system to analyze the full content of each query, thus maintaining high processing throughput while blocking harmful requests
2Reliability
If the system implements voice query filtering and blacklisting mechanisms, then illegitimate queries are suppressed, but the device complexity increases due to additional processing requirements
Solution Approach 1:
The system creates simplified copies of voice queries in the form of electronic fingerprints, which are compact representations that can be quickly compared against the blacklist. This copying approach maintains high reliability in identifying illegitimate queries while minimizing the computational complexity of the filtering process, as fingerprint comparison is much simpler than full query analysis
Data Source
AI summary
A computing system receives requests from client devices to process voice queries that have been detected in local environments of the client devices. The system identifies that a value that is based on a number of requests to process voice queries received by the system during a specified time interval satisfies one or more criteria. In response, the system triggers analysis of at least some of the requests received during the specified time interval to trigger analysis of at least some received requests to determine a set of requests that each identify a common voice query. The system can generate an electronic fingerprint that indicates a distinctive model of the common voice query. The fingerprint can then be used to detect an illegitimate voice query identified in a request from a client device at a later time.