Dynamic Storage Security for Voice Assistant Conversations
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current systems fail to effectively analyze and adapt to user conversation data from voice-enabled personal assistants, leading to inadequate storage and security settings, which can result in insecure storage and retrieval of sensitive information.
Innovation Solution
A method that processes conversation data from voice-enabled personal assistants to derive sentiment and topic parameters, using natural language processing to update functional settings for storage and security, ensuring appropriate encryption and redundancy levels based on the analysis.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If static storage and security settings are used for all conversation data, then system complexity is reduced and ease of operation is improved, but security reliability deteriorates because sensitive information cannot be adequately protected
Solution Approach 1:
The patent implements dynamic storage and security settings that automatically adjust based on conversation analysis. The system transitions from static configuration to dynamic adaptation by monitoring conversation sentiment and topic parameters, then modifying storage priority, security levels, and retention policies in real-time. This resolves the contradiction by making the system complex only when needed for security while maintaining simplicity for ordinary operations.
Solution Approach 2:
The system changes multiple parameters including storage priority, security level, encryption intensity, and data retention duration based on analyzed conversation characteristics. By dynamically adjusting these parameters according to sentiment scores and topic sensitivity, the system achieves high security reliability for sensitive data while maintaining operational simplicity through automated parameter modification.
2Reliability
If high security settings and encryption are applied to all conversation data, then security reliability is improved, but processing time increases and productivity deteriorates
Solution Approach 1:
The patent applies differential security measures based on local conversation characteristics. Instead of uniform high-security processing for all data, the system analyzes each conversation's sentiment and topic to determine appropriate security levels. Sensitive conversations receive enhanced encryption and security protocols, while ordinary conversations use standard processing, thereby maintaining security reliability without universally sacrificing processing speed.
3Reliability
If conversation data is stored with high priority and redundancy for all interactions, then data reliability is improved, but storage resource consumption increases and loss of substance worsens
Solution Approach 1:
The system dynamically adjusts storage priority and redundancy levels based on conversation analysis results. Conversations identified as sensitive through sentiment and topic analysis receive high-priority storage with multiple redundancy copies, while ordinary conversations are stored with lower priority and minimal redundancy. This dynamic allocation ensures data reliability for important information while conserving storage resources.
4Reliability
If detailed analysis of conversation data is performed to determine security settings, then security reliability is improved, but processing time increases and loss of time worsens
Solution Approach 1:
The system performs preliminary analysis of conversation data using natural language processing to extract sentiment and topic parameters before determining security settings. By conducting this analysis upfront and using pre-defined classification rules, the system achieves reliable security determination without requiring extensive real-time processing, thus minimizing time loss while maintaining security accuracy.
Data Source
AI summary
Methods, computer program products, and systems are presented. The method computer program products, and systems can include, for instance: receiving conversation data of a user from a data source, the data source being provided be a voice enabled personal assistant (VEPA); processing the conversation data to return a sentiment parameter value and a topic parameter value for the conversation data; updating one or more functional setting of a computing environment in dependence on the sentiment parameter value and the topic parameter value; receiving subsequent conversation data from the data source; and processing the subsequent conversation data in accordance with the updated one or more functional setting.