Curiosity-Based IVA Activation via Speech Wavelength Analysis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Intelligent virtual assistants (IVAs) often require explicit activation words or phrases, which may not accurately reflect user curiosity, leading to inefficient search processes and inappropriate responses.
Innovation Solution
A system that determines user curiosity based on audible speech wavelengths, facial expressions, and historical patterns, allowing for the activation of IVAs without explicit commands and adjusting search depth and knowledge base utilization accordingly.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If explicit activation words or phrases are required for IVA, then the system can distinguish between intentional commands and casual speech, but it fails to accurately detect user curiosity and responds inefficiently
Solution Approach 1:
The patent replaces the mechanical activation word system with an acoustic analysis system that detects curiosity through speech wavelength characteristics. The system analyzes the acoustic properties of speech signals to identify curiosity states, substituting the need for explicit activation words with automated acoustic pattern recognition.
Solution Approach 2:
The system changes the parameter for detecting user intent from discrete activation words to continuous acoustic wavelength parameters. By monitoring speech wavelength characteristics and their variations, the system can detect curiosity states and adjust search depth dynamically based on these parameter changes.
2Productivity
If the IVA performs deep searches for all user queries, then it provides comprehensive information, but it wastes computational resources on non-curious queries
Solution Approach 1:
The patent applies partial action by adjusting search depth based on detected curiosity levels. When curiosity is detected through speech wavelength analysis, the system performs deeper searches; when curiosity is not detected, it performs shallower searches, avoiding excessive computational effort on queries that don't require comprehensive answers.
Solution Approach 2:
The system dynamically adjusts search depth based on real-time detection of curiosity through speech analysis. The search parameters are not fixed but change dynamically according to the user's expressed curiosity level, allowing the system to optimize resource allocation adaptively.
3Measurement precision
If the system monitors multiple user parameters (speech wavelength, facial expressions), then it can accurately detect curiosity, but it increases data processing complexity
Solution Approach 1:
The patent segments the curiosity detection process into distinct components: speech wavelength analysis, facial expression recognition, and historical pattern matching. Each component processes specific data types independently, and their results are integrated to form the overall curiosity assessment, making the complex system more manageable and efficient.
Data Source
AI summary
Embodiments of the present invention determine a curiosity of a user based on data received from an electronic device associated with the user, where the data includes audible speech captured from user and one or more facial expressions of the user. Embodiments of the present invention identify a first wavelength for audible speech from the user to initiate a command detection mode based on a plurality of wavelengths associated with a user profile for the user. Embodiments of the present invention identify a topic for the audible speech from the user and responsive to determining an intelligent virtual assistant is an intended recipient based on the topic, suspend an activation word for the intelligent virtual assistant.