Digital Human Persona Adaptation for Natural Interaction

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current AI systems lack the ability to provide human-like interactions, as they struggle with recognizing complex human speech during spontaneous conversations and often come across as robotic and emotionally detached, failing to offer flexibility in personality styles.

Innovation Solution

A system that includes a processor and memory with instructions to receive user input, identify parameters such as context and emotion, and generate personalized responses using a knowledge database and repository, combining audio and visual attributes to create a human-like interaction by selecting from various personas.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of operation

If traditional AI systems are used for natural language processing, then machine translation and question answering capabilities are achieved, but the interaction remains robotic and emotionally detached

Engineering Contradiction:
ImproveInteraction qualityVSAvoidPersonality flexibility
Core Design Contradiction:
Ease of operationVSAdaptability or versatility

Solution Approach 1:

The system dynamically adjusts the digital human's personality attributes, emotional responses, and behavioral characteristics based on the selected persona and conversation context. The persona selection mechanism allows switching between different personality profiles (e.g., friendly, professional, humorous), making the interaction adaptable and versatile while maintaining human-like qualities throughout the conversation.

Inventive Principle:
Principle #15Dynamics

Solution Approach 2:

The system changes multiple parameters simultaneously including tone of voice, facial expressions, body language, and response style to match the selected persona. By adjusting these parameters dynamically, the system transforms from a static robotic interface to a flexible, emotionally expressive digital human that can adapt to different interaction scenarios.

Inventive Principle:
Principle #35Parameter changes

2Measurement precision

If AI systems attempt to recognize complex human speech during spontaneous conversation, then understanding capability is improved, but the system becomes less responsive and more robotic

Engineering Contradiction:
ImproveSpeech recognition accuracyVSAvoidConversation naturalness
Core Design Contradiction:
Measurement precisionVSEase of operation

Solution Approach 1:

The system uses pre-recorded human speech patterns, facial expressions, and body language from the selected persona as templates. Instead of generating responses robotically, the digital human copies and reproduces authentic human communication behaviors stored in the persona database, making spontaneous conversations feel natural and responsive while maintaining high recognition accuracy through pattern matching.

Inventive Principle:
Principle #26Copying

3Stability of the object's composition

If virtual agent systems provide standardized responses, then consistency is maintained, but flexibility in personality styles is lost

Engineering Contradiction:
ImproveResponse consistencyVSAvoidPersonality style variety
Core Design Contradiction:
Stability of the object's compositionVSAdaptability or versatility

Solution Approach 1:

The system implements a universal persona framework where a single digital human platform can perform multiple personality roles. The persona selection mechanism allows the same system to consistently deliver different personality styles (professional, casual, authoritative, empathetic) based on user choice, maintaining response consistency within each persona while providing versatility across multiple personas.

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

Data Source

PatentUS20240320519A1Systems and methods for providing a digital human in a virtual environment
Publication Date: 2024.09.26 ACCENTURE GLOBAL SOLUTIONS LTD
  • US20240320519A1 patent drawing
  • US20240320519A1 patent drawing
  • US20240320519A1 patent drawing

AI summary

Systems and methods for providing a digital human in a virtual space are disclosed herein. A system receives, from a user via a digital platform, a selection of a persona, for a digital human, from a plurality of personas. Further, the system receives, in real-time, an input from the user via the digital platform, and identifies a set of parameters associated with the input. Furthermore, the system determines, from a knowledge database, a response information based on the context of the input, and generates, using a repository, a set of attributes for the response information based at least on the set of parameters associated with the input and the persona selected by the user. Additionally, the system aggregates the set of attributes and the response information to generate a personalized response to the input, and renders the personalized response by the digital human on the digital platform.