Persona-Adaptive Assistant Output With Dynamic Visual Cues
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current automated assistants lack visual richness in their dialog sessions, with visual content often mirroring only the audible content and failing to convey a wide range of human expressions and animations.
Innovation Solution
Implementations enable automated assistants to dynamically adapt their outputs based on a given persona, incorporating personalized textual content and visual cues, such as animated gestures and display animations, through the use of large language models (LLMs) tailored to the user's assigned persona.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If automated assistants use static visual content that mirrors audible content, then the system complexity is low and ease of manufacture is high, but the visual richness and user engagement are insufficient
Solution Approach 1:
The patent applies dynamics by transforming static visual content into dynamic visual content that adapts in real-time based on dialog context and persona. The visual content now changes according to the automated assistant's emotional state, dialog flow, and assigned persona characteristics, making the system visually adaptive rather than fixed.
Solution Approach 2:
The patent changes visual parameters dynamically by adjusting visual cues based on persona attributes, dialog context, and emotional states. Different personas trigger different visual parameter configurations (colors, animations, gestures), allowing the same underlying system to produce diverse visual outputs through parameter variation.
2Reliability
If automated assistants incorporate personalized visual cues and animations for different personas, then user engagement improves and visual richness increases, but the device complexity and processing requirements increase
Solution Approach 1:
The patent applies preliminary action by pre-defining persona characteristics, visual cue templates, and animation patterns before dialog sessions begin. When a persona is assigned, the corresponding visual configurations are pre-loaded and ready for rapid deployment, reducing real-time processing complexity while maintaining rich visual output.
Solution Approach 2:
The patent uses copying by creating template-based visual representations that can be reused across different dialog contexts. Instead of generating unique visual content from scratch for each interaction, the system copies and adapts pre-defined visual patterns associated with different personas, reducing processing complexity while maintaining visual richness.
3Adaptability or versatility
If the automated assistant uses hard-coded rules for visual representations, then the implementation is simple and device complexity is low, but the range of visual expressions is limited
Solution Approach 1:
The patent applies universality by creating a multi-functional visual representation system that serves multiple personas and dialog contexts through a single unified framework. The same visual engine handles different personas by selecting from shared visual cue templates, making the system universally applicable across diverse scenarios without requiring separate hard-coded rules for each persona.
Solution Approach 2:
The patent adds another dimension to visual expressions by introducing persona-based visual cues as a new layer of expression. Instead of relying solely on basic hard-coded gestures, the system adds dimensional complexity through persona-specific visual parameters, emotional state indicators, and context-aware animations that operate alongside the base visual representation layer.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
Implementations relate to dynamically adapting a given assistant output based on a given persona, from among a plurality of disparate personas, assigned to an automated assistant. In some implementations, the given assistant output can be generated and subsequently adapted based on the given persona assigned to the automated assistant. In other implementations, the given assistant output can be generated specific to the given persona and without having to subsequently adapt the given assistant output to the given persona. Notably, the given assistant output can include a stream of textual content to be synthesized for audible presentation to the user, and a stream of visual cues utilized in controlling a display of a client device and/or in controlling a visualized representation of the automated assistant. Various implementations utilize large language models (LLMs), or output previously generated utilizing LLMs, to reflect the given persona in the given assistant output.