Document-Based Requirements Extraction Using Knowledge Graphs
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Analyzing complex requirements in construction, industrial machinery, and specialty packaging industries is knowledge-intensive and time-consuming, requiring long expertise development and differing domain knowledge across various sectors.
Innovation Solution
A computer-implemented method and system using a component model and attribute model to identify requirements in documents, enabling automatic extraction and merging of component and attribute information to produce products that meet specified requirements.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If knowledge-intensive manual analysis is used to analyze complex requirements, then analysis accuracy is improved, but time consumption and expertise requirement increase
Solution Approach 1:
The patent introduces a domain knowledge graph as an intermediary between the requirement document and the analysis process. The knowledge graph contains pre-stored component information, attribute information, and their relationships, serving as a mediator that enables automated extraction and matching of requirements without requiring manual expert analysis, thus reducing time consumption while maintaining accuracy
Solution Approach 2:
The patent performs preliminary action by pre-building the domain knowledge graph with component information, attribute information, and relationship data before the actual requirement analysis. This preparation work includes collecting domain knowledge, constructing the knowledge graph structure, and storing it for efficient querying, which eliminates the need for real-time expert knowledge retrieval during analysis
2Measurement precision
If domain experts manually analyze requirements, then domain-specific accuracy is improved, but the complexity of setup and updating domain knowledge increases
Solution Approach 1:
The patent segments the domain knowledge into distinct modules: component information, attribute information, and relationship information. Each segment is stored separately in the knowledge graph, allowing independent construction and updating of different domain components without affecting the entire knowledge base, thus reducing setup complexity
Solution Approach 2:
The patent creates a universal domain knowledge graph structure that can be applied across multiple domains (construction, industrial machinery, specialty materials, specialty packaging). The standardized schema and relationship types enable the same knowledge graph framework to serve different domains, reducing the effort needed to set up and update domain-specific knowledge bases
3Productivity
If automated methods are used to analyze requirements, then time efficiency is improved, but understanding of complex domain knowledge deteriorates
Solution Approach 1:
The domain knowledge graph acts as a mediator that encodes expert domain knowledge in a structured form, enabling automated systems to access and utilize complex domain knowledge without requiring actual expert understanding. The knowledge graph captures relationships, constraints, and domain rules that guide the automated extraction process
Solution Approach 2:
The patent implements feedback mechanisms where the automated extraction process queries the knowledge graph, matches extracted information against known domain patterns, and refines its analysis based on the results. This feedback loop ensures that automated extraction maintains domain knowledge accuracy by continuously validating against the structured knowledge base
Data Source
AI summary
A computer-implemented method, system, and computer program product for identifying requirements in a document. A document including requirements is received. Attribute related information in the document is identified using an attribute model. Component information in the document is identified using a component model. The attribute related information and the component information identified in the document are merged. Requirements in the document are identified from the merged attribute related information and component information. The requirements identified in the document are used to develop a product.