Multimodal Personality Establishment via Matching Vocal and Visual Demeanors

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current multimodal applications lack personality and dynamism, with static user interfaces and voice responses, failing to provide a engaging user experience due to limited interaction modalities and vocabulary constraints in small devices.

Innovation Solution

A method for establishing a multimodal personality by selecting and incorporating matching vocal and visual demeanors into multimodal applications, using a combination of speech and visual elements to create a dynamic user interface that adapts to user preferences and interaction history.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of operation

If speaker independent voice recognition is used to enhance user experience, then interaction capability is improved, but vocabulary is limited to predefined commands only

Engineering Contradiction:
Improveuser interaction capabilityVSAvoidvocabulary flexibility
Core Design Contradiction:
Ease of operationVSAdaptability or versatility

Solution Approach 1:

The patent implements dynamic personality selection where the system adapts its vocal demeanor (voice characteristics, tone, speaking rate) based on detected user characteristics and interaction context. This allows the system to dynamically adjust its communication style beyond fixed predefined responses, resolving the contradiction between ease of operation and vocabulary flexibility.

Inventive Principle:
Principle #15Dynamics

Solution Approach 2:

The system changes multiple parameters simultaneously including voice pitch, speaking rate, volume, and tonal characteristics to create different vocal personalities. These parameter changes enable the system to express a broader range of meanings and adapt to different user preferences without requiring an expanded vocabulary of predefined commands.

Inventive Principle:
Principle #35Parameter changes

2Adaptability or versatility

If multiple vocal demeanors are provided to enhance personality expression, then user engagement is improved, but system complexity increases

Engineering Contradiction:
Improvepersonality expression capabilityVSAvoidsystem architecture complexity
Core Design Contradiction:
Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The patent segments the vocal demeanor control into separate independent modules: voice synthesis parameters, speaking rate control, pitch modulation, and tone adjustment. Each module can be independently configured and selected based on detected user characteristics, reducing overall system complexity while maintaining rich personality expression capabilities.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The system implements a universal personality selection mechanism that uses the same detection and selection architecture across different interaction contexts. The same core modules handle both simple command recognition and complex conversational scenarios, reducing redundancy and simplifying the overall system architecture while providing versatile personality expression.

Inventive Principle:
Principle #6Universality (Multi-functionality)

3Ease of operation

If visual and vocal demeanors are synchronized to create consistent personality, then user experience is enhanced, but processing requirements increase

Engineering Contradiction:
Improveuser experience qualityVSAvoidprocessing energy consumption
Core Design Contradiction:
Ease of operationVSUse of energy by moving object

Solution Approach 1:

The patent implements preliminary selection of matched visual and vocal demeanor pairs based on detected user characteristics before actual interaction begins. By pre-establishing these pairings and caching the selection results, the system avoids real-time complex processing during interaction, reducing energy consumption while maintaining synchronized personality expression.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The system creates simplified representations or profiles of user characteristics from initial detection phases and uses these copies for subsequent demeanor selections. Instead of continuously analyzing full user profiles during interaction, the system references pre-processed characteristic copies, significantly reducing processing energy requirements while maintaining accurate personality synchronization.

Inventive Principle:
Principle #26Copying

Data Source

PatentUS8706500B2Establishing a multimodal personality for a multimodal application
Publication Date: 2014.04.22 MICROSOFT TECHNOLOGY LICENSING LLC
  • US8706500B2 patent drawing
  • US8706500B2 patent drawing
  • US8706500B2 patent drawing

AI summary

Methods, apparatus, and computer program products are described for establishing a multimodal personality for a multimodal application that include selecting, by the multimodal application, matching vocal and visual demeanors and incorporating, by the multimodal application, the matching vocal and visual demeanors as a multimodal personality into the multimodal application.