Next Generation AI-Based Assisted Document Authoring, Recommendation and Understanding

This proposal presents an innovation in Focus Area 23: “Digital Transformation for Aerospace”, in subarea “T11.04: Digital Assistants for Science and Engineering”. We propose creating a set of related artificial intelligence (AI), machine learning (ML) and natural language processing (NLP) technologies that operates on collections of documents, and extracts the necessary information to assist in the creation of new similar documents as well as verify the compliance of the documents that were created. We propose to do so in a domain-independent way, not being limited to a particular domain and class of document. The innovation could be later used to create digital assistants that address many of the priority tasks already pointed out by NASA experts as being of top priority. For example, it could identify current or past work related to an idea; serve as a digital assistant that can highlight lessons learned, suggest reusable assets, highlight past solutions or suggest collaborators based on the content; or serve as a base for a digital assistant that can create one or more component or system designs from a concept of operations, a set of high-level requirements, or a performance specification.

The proposal is aligned with NASA priorities on the 2020 SBIR/STTR research topics. In particular, digital assistants that: -use engineering artifacts (e.g., requirements, design, verification) to automate traces among the artifacts and to assess completeness and consistency of traced content, -identify current or past work related to an idea by providing a list of related documents, publications, etc. -recommend an action in realtime to operators of a facility, vehicle, or other physical assets.

Docugami aims at changing how we use and relate to documents. With that objective, the innovation proposed here is intended to be incorporated into our general-use product. Application domains that are very document-focused that would be natural use cases of this innovation. For example, law, medicine, and real state, back-end databases, check for regulatory compliance, analyze trends, etc.

This is early/mid-stage (TRL 4) — the most realistic path in is NASA SBIR/STTR, which funds small businesses and research institutions to develop technology aligned with NASA's needs (equity-free, phased funding). Check whether a current SBIR/STTR solicitation topic overlaps with this project's technology area, or contact the project directly (above) to ask.

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.