Analytical Platform for Structuring Unstructured Fabrication Knowledge
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Material engineers and design engineers face challenges in finding relevant knowledge for fabricating new devices due to the unstructured nature of existing knowledge in literature, requiring excessive time and effort to extract relevant information for device fabrication processes such as solar cells and lithium ion batteries.
Innovation Solution
An analytical platform is built using AI and machine learning models to transform unstructured fabrication knowledge into a structured format, enabling a graph search platform, knowledge query engine, and question-answer platform that identifies fabrication procedures, entities, and relations, thereby facilitating device fabrication.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of information
If unstructured knowledge from literature is used for device fabrication, then comprehensive information is available, but excessive time and effort are required to find relevant knowledge
Solution Approach 1:
The patent introduces an analytical platform as an intermediary system between unstructured literature knowledge and engineers. This platform includes NLP models, knowledge graphs, and search engines that automatically process, structure, and retrieve fabrication knowledge, eliminating the need for engineers to manually search through unstructured documents while preserving comprehensive information availability
Solution Approach 2:
The patent replaces the manual mechanical process of searching and extracting knowledge from unstructured literature with automated computational systems. NLP models automatically parse documents, extract entities and relations, and build structured knowledge representations, substituting human effort with algorithmic processing that maintains information completeness while dramatically reducing time requirements
2Quantity of substance
If unstructured knowledge is used, then all existing literature can be utilized, but the knowledge cannot be efficiently processed and retrieved
Solution Approach 1:
The patent segments unstructured knowledge into discrete structured components including entities (materials, devices, operations), relations (fabrication steps, properties, conditions), and hierarchical categories. This segmentation transforms voluminous unstructured text into organized knowledge units that can be efficiently stored in knowledge graphs and rapidly retrieved based on specific fabrication needs
Solution Approach 2:
The patent changes the structural parameters of knowledge from unstructured text format to structured data format with defined schemas, ontologies, and relationships. This parameter transformation enables efficient indexing, searching, and querying while preserving the complete volume of knowledge from literature through systematic extraction and organization
3Measurement precision
If manual extraction of fabrication knowledge is performed, then accurate information can be obtained, but the process requires excessive human effort and time
Solution Approach 1:
The patent implements self-service automated systems that perform knowledge extraction without requiring human intervention. NLP models automatically read, understand, and extract fabrication knowledge from literature with high accuracy, eliminating manual effort while maintaining precision through trained algorithms that specialize in scientific text processing and entity recognition
4Productivity
If structured knowledge representation is implemented, then knowledge retrieval efficiency is improved, but the initial processing complexity increases
Solution Approach 1:
The patent performs preliminary structuring of knowledge during the data collection and ingestion phase, building knowledge graphs and establishing ontologies before retrieval operations begin. This preliminary action organizes knowledge into efficient structures upfront, enabling rapid retrieval later while concentrating processing complexity in the initial setup phase rather than during repeated query operations
Data Source
AI summary
This disclosure relates generally to methods and systems for building an intelligent analytical platform to enable a device fabrication in material science. Material engineers and design engineers may face various challenges with existing knowledge, as more time and efforts are required in finding a relevant knowledge from the existing knowledge, mainly due to the unstructured form, for fabricating new devices. The present disclosure solves the technical problem of finding the relevant knowledge out of the existing knowledge, in a structured form by building an analytical platform. The unstructured format of the existing knowledge of the fabrication process is transformed into a structured format in terms of operation sequence knowledge graphs, using a set of artificial intelligence (AI) and machine learning models, and a knowledge representation model of the fabrication process. The structured format of the existing knowledge is hierarchically arranged to build the analytical platform.