Knowledge Management Framework and Model for Hardware Systems Data

Design and develop a hardware systems knowledge management software framework using Machine Learning (ML) and Artificial Intelligence (AI) techniques in Natural Language Processing (NLP) that will allow structured data components like part numbers, drawing numbers, etc to semantically analyze and link underutilized unstructured data enabling proactive mode use of data, this will also significantly increase the intrinsic value of hardware systems unstructured data in the decision-making process of designing and building reusable hardware architecture systems. This CIF will architect data for speed and integration instead of efficiency. Using an NLP framework like Stanford NLPCore, we will design a hardware system entity recognition model that can be repurposed to multiple hardware systems. The model should not only be able to recognize hardware system entities but also capture the context associated with the entities in the data and relationships to other entities. For NLP model generation, EVA spacesuit hardware system data (around 3TB) can be used for training and testing the model. Using the generated NLP model, a graph database can be used to capture knowledge from both structured and unstructured data. We would employ DGraph, an open-source, scalable, distributed fast graph database designed to be run in production, which is an ideal technology to store and manage knowledge graphs.

Traditionally, data has been architected for efficiency and informed decisions made by key stakeholders based on structured data and/or time-series data. Because of the vast amounts of unstructured data being generated, the challenge to use it for informed decision-making processes is not being addressed.

This is a mature technology (TRL 7+) — the realistic path in is usually NASA's Technology Transfer Program: licensing an existing NASA patent, or a Space Act Agreement to use NASA facilities/expertise directly. NASA also runs a startup licensing program with no upfront fee for companies formed to commercialize a specific NASA technology.

None of these are guaranteed paths for this specific project — TechPort itself doesn't have an "apply" button. Reaching out to the contact(s) above with a specific question is usually the fastest way to find out what's actually open.