Virtual Assistant Knowledge Base Scaling via Automated Learning

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing virtual assistance systems face challenges in automatically scaling their knowledge base and providing effective multi-step guidance solutions without manual intervention, especially when dealing with new technologies and application areas, due to the lack of readily available training data and complex architecture.

Innovation Solution

A method and system that classify interaction data between users and real agents using a predefined domain model to identify mandatory and supplementary information, which is then clustered based on user parameters and historical data to provide automated knowledge scaling and multi-step guidance.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If manual intervention is used to add new use cases and knowledge to the virtual agent database, then the knowledge base can be extended, but the process becomes cumbersome, complex, and time-consuming

Engineering Contradiction:

Improveknowledge base extension capabilityVSAvoidmanual curation complexity

Core Design Contradiction:

Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The virtual agent system automatically learns and extends its own knowledge base by interacting with external resources and users, without requiring manual curation. The system self-updates its database with new use cases and knowledge through automated learning processes, eliminating the need for manual intervention while maintaining knowledge base adaptability

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The patent replaces the manual mechanical process of knowledge curation and database updates with an automated learning system that uses machine learning algorithms to automatically acquire, process, and integrate new knowledge from external sources, thereby substituting human effort with an automated computational system

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

2Adaptability or versatility

If training data and corpus for new technologies are created manually, then the virtual agent can learn new domains, but it requires a lot of time and effort for curation and integration

Engineering Contradiction:

Improvenew domain learning capabilityVSAvoidtraining data curation time

Core Design Contradiction:

Adaptability or versatilityVSLoss of time

Solution Approach 1:

The system pre-loads and processes general knowledge corpora and training data in advance, organizing them into structured formats that can be quickly accessed and utilized when new domain learning is required, thereby reducing the time needed for data curation and preparation when encountering new technologies

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The patent replaces the manual process of creating and curating training data with an automated system that uses web scraping, API integrations, and machine learning to automatically collect, clean, and structure training data from external sources, eliminating the time-consuming manual curation process

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

3Extent of automation

If existing virtual intelligent agent services are used to extend knowledge through external resources, then automatic knowledge extension is provided, but the architecture becomes complex and the process is time-consuming

Engineering Contradiction:

Improveautomatic knowledge extensionVSAvoidsystem architecture complexity

Core Design Contradiction:

Extent of automationVSDevice complexity

Solution Approach 1:

The patent combines multiple knowledge extension functions into a single integrated learning module that handles data collection, processing, validation, and integration in one unified system, thereby reducing architectural complexity while maintaining automatic knowledge extension capabilities through a consolidated approach

Inventive Principle:

Principle #5Merging (Combining)

4Productivity

If existing systems are used without automated learning mechanisms, then the virtual assistant can operate with current knowledge, but it cannot automatically scale up its knowledge base

Engineering Contradiction:

Improveknowledge base scaling capabilityVSAvoidautomated learning mechanism

Core Design Contradiction:

ProductivityVSExtent of automation

Solution Approach 1:

The virtual agent system automatically learns and extends its own knowledge base by interacting with external resources and users, without requiring manual curation. The system self-updates its database with new use cases and knowledge through automated learning processes, enabling knowledge base scaling through self-service automation

Inventive Principle:

Principle #25Self-service

Data Source

PatentUS11687825B2Method and system for determining response to queries in virtual assistance system

Publication Date: 2023.06.27 WIPRO LTD

AI summary

The present invention discloses method and virtual assistance system for determining response to user queries. The virtual assistance system receives data comprising plurality of interaction between one or more users and one or more real agents for resolving query, where data is classified into user and real agent data. Entities and intent identified from each of the classified user data and real agent data are classified using predefined domain model. The entities and intent are combined to identify plurality of sequence of resolution data. Based on classification of entities and intent, virtual assistance system determines first set of resolution data and second set of resolution data. Thereafter, each of plurality of sequence of resolution data is clustered into one or more category associated with type of users, based on first set and second set of resolution data, parameters associated with users and historical resolution data used for responding to query.