Virtual Agent Intent Response Generation With LLM Knowledgebase Analysis

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing virtual agents rely on pre-defined responses and scripted dialogues, which often lack contextuality and fail to deliver human-like interactions.

Innovation Solution

A method and system utilizing a Large Language Model (LLM) to analyze a knowledgebase and user intent, generating responses through natural language processing and machine learning techniques to provide accurate, contextually relevant, and human-like interactions.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Device complexity

If pre-defined responses and scripted dialogues are used, then device complexity is reduced, but response contextuality and human-like interaction quality deteriorate

Engineering Contradiction:

Improvesystem complexityVSAvoidresponse contextuality

Core Design Contradiction:

Device complexityVSReliability

Solution Approach 1:

The patent replaces the mechanical rule-based system (pre-defined responses and scripted dialogues) with an AI-based semantic understanding system. The virtual agent now uses natural language processing and machine learning to comprehend user intent and generate contextually appropriate responses, eliminating the need for manual scripting while improving response quality and adaptability.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

2Ease of operation

If pre-defined responses are used, then ease of operation is improved, but adaptability to different user intents deteriorates

Engineering Contradiction:

Improveoperation simplicityVSAvoidintent handling flexibility

Core Design Contradiction:

Ease of operationVSAdaptability or versatility

Solution Approach 1:

The patent changes the fundamental parameter of response generation from static pre-defined templates to dynamic AI-generated responses. The system adjusts its behavior based on analyzed user intent, allowing it to adapt to various query types and contexts while maintaining ease of operation through automated processing.

Inventive Principle:

Principle #35Parameter changes

3Productivity

If BERT-based methods are used for response generation, then processing efficiency is improved, but response naturalness and human-like quality deteriorate

Engineering Contradiction:

Improveresponse generation speedVSAvoidresponse naturalness

Core Design Contradiction:

ProductivityVSReliability

Solution Approach 1:

The patent substitutes BERT-based response generation methods with Large Language Model (LLM) based generation. While LLMs require more computational resources, they produce significantly more natural and human-like responses by leveraging their pre-trained language understanding and generation capabilities, thereby improving response quality without sacrificing acceptable processing efficiency.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Data Source

PatentUS12541541B2Method and system for generating intent responses through virtual agents

Publication Date: 2026.02.03 QUANTIPHI INC

AI summary

A method and system for generating a response through a virtual agent is provided herein. The method comprises receiving information associated with a plurality of themes and topics. The method further comprises creating a knowledgebase based on the information received. The method further comprises analyzing the knowledgebase based on an intent identified, using an Artificial Intelligence (AI) model. Further, the method comprises generating a response corresponding to the intent through the virtual agent based on analyzation.