Configurable Pattern Trees for Automated Purposive Model Authoring
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional model extractors for Natural Language documents are specific to a purpose and do not account for document structure, style, and semi-structured forms, making it challenging to create generic model extractors for various types of documents.
Innovation Solution
A method and system for automated authoring of purposive models from NL documents using a metamodel, pattern trees, and a configurable domain dictionary, which generates document information and models by interpreting document styles and patterns.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If conventional model extractors are used for Natural Language documents, then model extraction can be performed for specific purposes, but the system lacks versatility to handle different types of documents and purposes
Solution Approach 1:
The patent implements a universal model extractor that can handle multiple document types and purposes through a configurable framework. The system uses a metamodel and pattern tree architecture that can be adapted to different domains and purposes without requiring separate extractors for each case. This allows a single system to perform model extraction for requirements documents, design documents, policy documents, and other NL documents across various purposes.
Solution Approach 2:
The system enables versatility through parameter configuration rather than structural changes. By modifying the metamodel, pattern trees, and domain dictionary parameters, the same extractor infrastructure can be adapted to different document types and purposes. This parameter-based adaptation avoids the complexity of creating multiple specialized extractors while maintaining high versatility.
2Productivity
If manual model creation from documents is performed, then accuracy can be maintained, but productivity and automation are reduced
Solution Approach 1:
The patent introduces an intermediary layer consisting of pattern trees and metamodels that bridge natural language documents and target models. This intermediary framework enables automated extraction while maintaining accuracy by providing structured patterns that guide the extraction process. The pattern trees act as mediators that translate document content into model elements systematically, combining automation with reliability.
Solution Approach 2:
The system performs preliminary action by pre-defining pattern trees and metamodels that capture the structure and semantics of target models. These pre-configured patterns prepare the extraction framework in advance, enabling accurate automated extraction without manual intervention during the actual model creation process. The preliminary configuration ensures both automation and accuracy.
3Ease of operation
If document-centric approaches are used, then document maintenance is straightforward, but search capability and analysis are limited
Solution Approach 1:
The patent creates model copies or representations from natural language documents. Instead of working directly with unstructured documents, the system generates structured model copies that preserve the essential information while enabling advanced search and analysis capabilities. These model copies maintain the semantic meaning of the original documents while providing machine-readable structures for efficient information retrieval and processing.
Data Source
AI summary
The present disclosure is of a method for automated authoring of purposive models from Natural Language (NL) documents. Conventional model extractors to automatically extract models from NL documents are specific to a metamodel, do not consider document structure and are not configurable. Initially, the system receives a plurality of Natural Language (NL) documents, a metamodel, a plurality of pattern trees corresponding to the metamodel, and a configurable domain dictionary. Each of the plurality of pattern trees includes a plurality of pattern elements. Further, a document information is generated from each of the plurality of NL documents using a document information reading technique. Finally, a plurality of purposive models are generated for each of the plurality of NL documents by interpreting a corresponding document information based on the plurality of pattern trees and the metamodel using a pattern interpretation technique.