Awards & Nominations
AI Prognosis has received the following awards and nominations. Way to go!

AI Prognosis has received the following awards and nominations. Way to go!
Our project not only aims to summarize CDMS pdfs but also enhances searching pdfs using Auto AI Search. We have created a web-app to preserve science legacy using AI. The prominent algorithms used are text-rank in python for PDF summarization and txtai Embeddings library in python Auto AI search. For analysis of the pdfs we have also used wordclouds as well as bigrams to understand the most frequent words used in the summary. We have integrated all of these functionalities in our solution.
Our solution is build completely on pyhton.
Software used. Python libraries like txtai for Auto Ai generation and text rank for summary generation.
Web framework: Flask
Our proposed solution has the following steps involved
1) API call to the NTRS server via NTRS openapi using python requests.
2) Download the CDMS relevant pdfs and storing their id and download link for further reference.
3) Summarizing the text of the pdfs in three following ways
a) Summarizing the complete pdf
b) Summarizing the initial 20 pages: to extarct the preface and abstract
c) Summarizing the last 20 pages: to extract the conclusion for better search
4) The search is done on the amalgamation of the following summaries used txtai embeddings
5) After the search is done the results are displayed with and after clicking on the results the respective word clouds, bigrams and AI summary is rendered.
1) NTRS CDMS PDFS
2) NTRS OpenAPi
It's been a pleasure to be a part of this exuberant global event. Hackathons always help us to transcend our limitations.
AI prognosis have given their best to come up with a convincing solution.
1) https://ntrs.nasa.gov/
2) https://ntrs.nasa.gov/api/openapi/
3) https://www.analyticsvidhya.com/blog/2018/11/introduction-text-summarization-textrank-python/
4) Youtube for AI searching
#ai#aiprognosis
The NASA Technical Report Server (NTRS) includes hundreds of thousands of items containing scientific and technical information (STI) created or funded by NASA. Imagine how difficult it can be to locate desired information in such a large repository! Your challenge is to develop a technique using Artificial Intelligence (AI) to improve the accessibility and discoverability of records in the public NTRS.
