Decision Model Templates From Policy Text Ambiguity
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current technologies lack effective methods for automating the generation of decision models from complex policy documents, leading to tedious, expensive, and time-consuming processes that require domain experts and often result in inaccuracies due to ambiguity and interpretation challenges.
Innovation Solution
A method involving machine learning-based sentence similarity and co-reference identification, followed by discourse and sentence-level semantic parsing, is used to generate a decision model template from text corpora, transforming it into an automated decision model.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual decision model generation is used, then accuracy and domain expertise are improved, but time consumption and cost increase
Solution Approach 1:
The system enables self-service by allowing the decision model to generate itself from policy documents through automated semantic parsing and template transformation, eliminating the need for manual expert intervention in the model generation process while maintaining accuracy through structured extraction of decision logic
Solution Approach 2:
The patent replaces the mechanical manual process of expert analysts creating decision models with an automated computational system that uses semantic parsing algorithms, machine learning models, and template transformations to generate models automatically from text corpora
2Loss of time
If automated decision model generation is implemented, then time consumption is reduced, but reliability and accuracy may deteriorate due to text ambiguity
Solution Approach 1:
The system segments the complex policy document into discrete sentences and then into atomic decision elements through semantic parsing, allowing each segment to be processed independently and mapped to standardized decision model components, which improves both speed and reliability through systematic decomposition
Solution Approach 2:
The patent introduces an intermediary layer of decision model templates that mediate between the ambiguous source text and the final decision model. These templates provide structured intermediaries that transform ambiguous natural language into precise, executable decision logic, ensuring reliability while maintaining automation
3Adaptability or versatility
If complex policy documents are processed, then comprehensive decision coverage is improved, but processing complexity and difficulty increase
Solution Approach 1:
The system achieves universality by using a single automated pipeline that can process diverse policy documents across different domains. The semantic parsing model and template system are designed to handle various policy types uniformly, extracting decision logic regardless of specific domain complexity, thereby improving coverage without proportionally increasing processing complexity
Data Source
AI summary
The present inventive concept provides for a method for automated decision modelling from text including obtaining a text corpus including a policy. Terms and syntax are identified within the text corpus related to the policy. Sentence similarities and co-references based on the terms and syntax are identified. Discourse and sentence level semantic parsing is performed based on the terms and the sentence similarities and the co-references using machine learning. A decision model template is generated based on the discourse and semantic parsing, and the decision model template is transformed into an automated decision model.