Voice Personality Profiles for Natural Media Guidance Dialog
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Traditional media guidance systems employ a rigid, turn-based approach that can appear robotic, lacking the intelligence and human-like interaction desired by users.
Innovation Solution
Implementing a media guidance application that interacts through a voice interface, allowing for interruptions and changes of subjects based on user hesitation or keywords, using a Knowledge Graph to relate topics and user preferences, and adjusting interaction frequency based on personalized voice personality profiles.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If a turn-based approach is used for voice interactions, then the system structure is simple and easy to implement, but the interaction appears rigid and robotic
Solution Approach 1:
The patent implements dynamic conversation management by allowing the system to interrupt user speech and change topics based on detected hesitation or keywords. The conversation flow is no longer rigidly turn-based but adapts dynamically to user responses, making interactions appear more natural and human-like while managing complexity through structured dialogue states
2Productivity
If the system provides frequent recommendations, then user engagement increases, but user annoyance increases due to excessive interruptions
Solution Approach 1:
The patent implements feedback mechanisms by monitoring user responses to recommendations and adjusting future recommendation frequency accordingly. The system detects user hesitation and annoyance signals, then modulates the frequency and timing of interruptions to maintain optimal engagement while minimizing user frustration
Solution Approach 2:
The system dynamically changes parameters such as recommendation frequency, interruption timing, and topic transition probability based on conversation state and user response patterns. This allows the system to optimize engagement levels while adapting to individual user preferences and tolerance thresholds
3Adaptability or versatility
If the system changes topics frequently, then conversation appears more intelligent and human-like, but coherence of conversation decreases
Solution Approach 1:
The patent introduces topic models and semantic relationships as intermediaries between the current conversation state and potential topic transitions. These intermediaries ensure that topic changes are contextually relevant and coherent by selecting new topics that are semantically connected to the current discussion, maintaining conversation flow while allowing flexibility
Data Source
AI summary
Systems and methods are described herein for providing media guidance. Control circuitry may receive a first voice input and access a database of topics to identify a first topic associated with the first voice input. A user interface may generate a first response to the first voice input, and subsequent to generating the first response, the control circuitry may receive a second voice input. The control circuitry may determine a match between the second voice input and an interruption input such as a period of silence or a keyword or a phrase, such as “Ahh,”, “Umm,”, or “Hmm.” The user interface may generate a second response that is associated with a second topic related to the first topic. By interrupting the conversation and changing the subject from time to time, media guidance systems can appear to be more intelligent and human.