Natural Language Rule Extraction via Grammatical Parsing and SWRL
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Enterprise systems face challenges in efficiently extracting and verifying business rules from large pools of unstructured natural language documents, which is time-consuming and prone to human error.
Innovation Solution
A method and system for rule creation from natural language text using grammatical parsing, ontological representation, and semantic web rules language (SWRL) to automatically extract and verify operational rules by parsing sentences into noun and verb phrase sub-trees, splitting into 3-grams, comparing with predefined classes and data properties, and assigning subscripts to create formal rules.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If manual interpretation and verification of rules from unstructured documents is performed, then human understanding and context awareness are improved, but time consumption and error rates increase significantly
Solution Approach 1:
The system performs self-service by automatically extracting rules from unstructured documents using grammatical parsing and SWRL generation, eliminating the need for manual human verification while maintaining high accuracy through automated reasoning engines
Solution Approach 2:
The patent replaces the mechanical human verification process with an automated computational system that uses grammatical parsing, ontological matching, and SWRL rule generation to extract and verify business rules from documents, significantly reducing time while maintaining reliability
2Loss of information
If manual verification of a large pool of documents is performed, then comprehensive rule extraction is achieved, but effort and time requirements become unmanageable
Solution Approach 1:
The system segments the complex task of rule extraction into distinct phases: grammatical parsing of sentences, extraction of noun and verb phrases, conversion to SWRL rules, and verification by reasoning engines. This segmentation enables automated processing of large document pools while maintaining completeness of rule extraction
Solution Approach 2:
The patent introduces SWRL (Semantic Web Rules Language) as an intermediary formal representation between unstructured natural language documents and structured business rules. This intermediary enables automated processing and verification while preserving the complete meaning and intent of the original documents
3Productivity
If automated rule extraction from natural language text is implemented, then processing speed and consistency are improved, but complexity of the extraction system increases
Solution Approach 1:
The system performs preliminary grammatical parsing and identification of noun/verb phrases before rule generation. This preliminary action simplifies the subsequent SWRL conversion process by pre-structuring the extracted information in a standardized format, reducing overall system complexity despite the automated processing
Data Source
AI summary
Techniques for rule creation from natural language text (NLT) are disclosed. In an embodiment, a rule statement in the NLT is grammatically parsed to obtain a parse tree. Further, each of noun phrase (NP) core sub-tree and verb phrase (VP) core sub-tree, in the parse tree, is partitioned into at least one sub-tree. Furthermore, one or more operators are extracted using at least one sub-tree of NP or VP core sub-trees. The rule statement is substantially simultaneously splitted into groups of 3 adjacent words (3-grams). Each of the 3-grams is then compared with a predefined list to extract data properties and class concepts associated with the rule statement. Moreover, subscripts are assigned to the data properties, class concepts and operators. A rule head is then created based on the data properties and operators. Also, a rule is created using the data properties, operators, class concepts, associated subscripts and rule head.