Voice-Based User Identification for Personalized Query Access
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing speech recognition systems require users to manually input account information for multiple services, leading to inconvenience and security risks, especially when multiple users share a device.
Innovation Solution
An electronic device and system that utilize speech recognition to register and identify users based on voice, providing optimized queries tailored to the user's account history, either locally or through a server, enabling secure and convenient access.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If users manually input account information for each service, then service access is achieved, but user convenience deteriorates and time is lost
Solution Approach 1:
The system performs preliminary actions by storing account information in advance and automatically retrieving it when needed. The voice recognition system pre-processes user identity verification and automatically fills account credentials, eliminating the need for users to manually input information during service access.
Solution Approach 2:
The system enables self-service by automatically managing account information retrieval and service access based on voice commands. The electronic device independently handles authentication and account management tasks without requiring manual user intervention for each service access.
2Ease of operation
If users remain logged in to avoid repeated input, then convenience is improved, but security deteriorates due to potential unauthorized access
Solution Approach 1:
The system implements dynamic authentication where login status is not static but continuously verified through voice recognition. The authentication state adapts in real-time based on voice biometric verification, allowing the system to maintain security while providing seamless access for authorized users.
Solution Approach 2:
The system replaces traditional mechanical authentication methods (passwords, physical logins) with voice biometric recognition. This substitution maintains security through unique vocal characteristics while improving convenience by eliminating manual authentication steps.
3Adaptability or versatility
If multiple users share one electronic device, then device utilization is improved, but ease of operation deteriorates as each user must input their account information
Solution Approach 1:
The voice recognition system provides universal functionality for multiple users through a single interface. The system can identify and authenticate different users based on their voice characteristics, enabling one device to serve multiple users without requiring separate authentication mechanisms for each user.
Solution Approach 2:
The voice recognition system acts as an intermediary between multiple users and the device's account management system. It translates voice inputs into authenticated user identities, mediating the interaction between diverse users and the standardized authentication protocol.
4Ease of operation
If speech recognition is used to identify users, then manual input is eliminated and convenience is improved, but system complexity increases
Solution Approach 1:
The patent introduces a server as an intermediary that handles the complex speech recognition and voice biometric analysis. The electronic device itself remains relatively simple, delegating the computationally intensive voice processing tasks to the external server, thus reducing local system complexity while maintaining advanced functionality.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
An electronic device and a system including the same are disclosed. The electronic device according to one embodiment of the present disclosure comprises a display; a memory that stores a usage history; a user input interface that transmits signals corresponding to user inputs; and a controller, wherein the controller checks the user account corresponding to a voice signal when the voice signal is received through the user input interface, determines whether the usage history for the user account is stored in the memory, outputs a preset first recommended query through the display when the user account does not exist or the usage history for the user account does not exists in the memory, and outputs a second recommended query corresponding to the usage history for the user account through the display when the usage history for the user account is stored in the memory.