Procedural Text to Actionable Knowledge Conversion
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The manual transformation of procedural knowledge from run books into executable forms is tedious and impractical due to the large volume of documents, low availability of domain experts, and inconsistent formats, limiting the potential for reuse and automation of infrastructure support services.
Innovation Solution
A method and system that structure text from documents like run books into actionable knowledge form by merging, grouping, or removing statements, marking them into categories, mapping action segments with predicates, and linking standard operators to generate predicate-action pairs, enabling automatic conversion without human intervention.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual transformation of procedural knowledge from run books into executable forms is performed, then accuracy of knowledge conversion is improved, but productivity and time consumption deteriorate due to large volume of documents and low availability of domain experts
Solution Approach 1:
The patent introduces an intermediary system comprising a parser, structured text generator, and script generator that acts as a mediator between the unstructured run book text and the executable scripts. This intermediary processing chain automatically transforms procedural knowledge without requiring domain experts to manually write scripts, thereby maintaining accuracy while dramatically improving productivity.
Solution Approach 2:
The patent replaces the mechanical manual process of domain experts writing executable scripts with an automated computational system. The system uses parsing algorithms, structured text generation, and script generation mechanisms to automatically convert run book text into executable formats, eliminating the need for manual mechanical work by experts.
2Reliability
If manual transformation of procedural knowledge is performed, then quality of executable knowledge is improved, but loss of time and human resource availability worsen
Solution Approach 1:
The patent implements preliminary action by pre-defining templates and structures for executable knowledge representation. The system prepares parsing rules, structured text formats, and script templates in advance, allowing rapid transformation of run books without requiring time-consuming manual analysis and script writing for each document.
Solution Approach 2:
The patent replaces the time-consuming manual mechanical process of expert analysis and script writing with automated computational processing. The parsing and script generation system processes multiple run books simultaneously, dramatically reducing the time required while maintaining quality through systematic automated transformation.
3Extent of automation
If standard parsers are used to extract knowledge from run books, then automation potential is improved, but measurement precision deteriorates due to grammatical errors, code scripts, and domain jargons in natural language artifacts
Solution Approach 1:
The patent applies segmentation by dividing the complex task of knowledge extraction into distinct stages: parsing the natural language text, generating structured text with identified actions and conditions, and then generating executable scripts. This segmented approach allows each stage to handle specific challenges (like grammatical errors or domain jargon) independently, improving overall precision while maintaining automation.
Solution Approach 2:
The patent introduces structured text as an intermediary representation between the raw run book text and the final executable scripts. This intermediate structured format serves as a buffer that captures the semantic meaning while filtering out noise from grammatical errors and domain jargon, thereby improving extraction precision while maintaining automation potential.
Data Source
AI summary
Disclosed is method and system for converting text used to perform an operation to reusable actionable knowledge form. Procedural knowledge available in run books is converted into reusable actionable knowledge form. The method comprises structuring the text by performing merging, grouping, editing, removing statements and marking statements present in structured text into action segments, predicates, and comments, by parsing technique and rule based reasoning. Predicate comprise conditions, action segment comprise actionable statements executed upon fulfilling conditions. Actionable statement is used to perform a task of the operation. Action segments are mapped with predicates to generate predicate-action pairs, standard operators relevant to each of conditions of predicate and actionable statements of action segment are selected, and score for standard operators is determined, and a standard operator having highest score is linked with conditions and actionable statements of the predicate-action pair, thereby converting predicate-action pair in reusable actionable knowledge form.