Conversational Web Interface via Automated Knowledge Extraction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Developing artificial intelligence applications that support natural language-based interactions for users to access web content is challenging, particularly in generating dialog flows, which are often costly and limited to predefined responses in specific subject areas.
Innovation Solution
A method that extracts knowledge from web applications, associates it with organizational structures using deep learning, and creates a semantic matcher to provide accurate responses to user queries, enabling a conversational interface that adapts to user interactions and learns from user data.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If human-authored dialog flows are used, then the conversational interface can provide structured responses, but the development cost and time increase significantly
Solution Approach 1:
The system automatically extracts knowledge from web content and generates dialog flows without human intervention. The knowledge extraction module parses web pages to identify entities, relationships, and concepts, then automatically constructs dialog flows and knowledge graphs, eliminating the need for manual dialog flow authoring while maintaining response accuracy.
Solution Approach 2:
The patent replaces the mechanical process of manual dialog flow authoring with an automated knowledge extraction and processing system. Natural language processing algorithms and machine learning models substitute for human experts in analyzing web content and generating structured dialog flows, significantly reducing development time.
2Measurement precision
If retrieval-based models with predefined responses are used, then the system can answer questions in narrow subject areas, but the adaptability to different topics and user queries is limited
Solution Approach 1:
The system creates a universal knowledge graph that can handle multiple topics and domains by extracting knowledge from diverse web sources. The knowledge graph structure allows the same system to adapt to different subject areas without requiring separate predefined response repositories for each topic, enhancing versatility while maintaining answer accuracy through structured knowledge representation.
Solution Approach 2:
The dialog flow is dynamically generated based on the knowledge extracted from web content rather than being static and predefined. The system adapts to different user queries and topics by dynamically selecting and constructing appropriate dialog paths from the knowledge graph, enabling versatility across multiple domains while maintaining precision in responses.
3Reliability
If manual knowledge curation is performed, then the quality of domain knowledge improves, but the complexity and cost of system development increases
Solution Approach 1:
The system replaces manual knowledge curation with automated knowledge extraction using natural language processing and machine learning. Algorithms automatically parse web content, extract entities and relationships, and structure knowledge into graphs, eliminating the need for manual knowledge engineering while maintaining high knowledge quality through systematic processing.
Solution Approach 2:
The system performs self-service knowledge extraction and validation by automatically analyzing web content quality, filtering relevant information, and structuring knowledge without human intervention. The automated processes include entity recognition, relationship extraction, and knowledge graph construction, reducing system complexity compared to manual curation workflows.
Data Source
AI summary
A method, apparatus and computer program product for creating a dialog system for web content is described. Knowledge is extracted from a target web application for the dialog system. The knowledge includes an organizational structure of the target web application and domain knowledge pertinent to the target web application. A deep learning process associates the domain knowledge with the organization structure of the target application. A plurality of knowledge sources of different respective types are created from the domain knowledge and the organizational structure. Each of the knowledge sources is used for providing answers to user queries to the dialog system. As part of the invention, a semantic matcher is provided to select among the answers provided by the plurality of knowledge sources for a best answer to a user query.