Monash University is piloting graph database technology to track relationships between researchers, publications and equipment with the aim of improving return on research investment.<\/p>\n
<\/p>\n
\n Monash University’s Clayton campus
\n
\n iStockPhoto
\n <\/p>\n
The Melbourne-based university has developed a centralised platform on Amazon Web Services to help users more easily find information across its research ecosystem, using multi-modal generative AI.<\/p>\n
Known as the Research and Publications Pattern Analysis (RAPPA), the platform combines graph database capabilities from Amazon Neptune with generative AI services from Amazon Bedrock.<\/p>\n
Speaking at the AWS Public Sector Symposium in Canberra, Mahyar Nasabi, Monash program manager for systems and analytics, said the platform aims to provide a \u201cmissing link\u201d between the university\u2019s investments and publications, which he described as a kind of \u201ccurrency\u201d for universities.<\/p>\n
\u201cYou can find all the research, income and also the publications, but they’re not linked together,\u201d he said.<\/p>\n
“These are sitting in siloed datasets, which creates an unclear return on investment.\u201d<\/p>\n
Nasabi said the fragmentation also affects students who are searching for specific information about researchers, published papers, or scientific services.<\/p>\n
\u201cAs a research student, you want to quickly access and find specific [information],\u201d he said.<\/p>\n
\u201cThat is currently not really possible because you have to go to fragmented, siloed data.\u201d<\/p>\n
Highlighting the scale of the challenge, Nasabi noted that Monash currently has 112,000 researchers across its eight campuses, contributing to 54,000 peer-reviewed publications and in receipt of $7.6 billion in research awards.<\/p>\n
\u201cRAPPA essentially unifies the research ecosystem,\u201d he said. \u201cIt brings researchers to research capabilities, research income to research output.<\/p>\n
“Everything is in a single platform and available to query.\u201d<\/p>\n
Three core user personas<\/p>\n
Before developing RAPPA, Monash University first established three key personas who would benefit from the system, each accessing it through a natural language-enabled chatbot.<\/p>\n
A key persona is Monash\u2019s research performance team, which reviews published papers to determine which facilities and equipment were used in the research.<\/p>\n
Philippe Gabert, AWS solutions architect, said the team usually relies on cues in abstracts and acknowledgements to determine equipment used, due to the complexity and length of academic papers.<\/p>\n
To assist, one of RAPPA\u2019s key functions for the research performance team is to automatically generate a plain-language summary of each paper, making the content easier to understand.<\/p>\n
It then uses a multi-modal AI model to extract text, images and charts from the paper to \u201cinfer\u201d which equipment may have been used in the research.<\/p>\n
The research performance team will still be required to validate equipment usage before any conclusions are finalised.<\/p>\n
Meanwhile, students and researchers also benefit from RAPPA\u2019s improved access and discoverability when searching for relevant publications, experts, and research services.<\/p>\n
Monash\u2019s senior leadership and executives, who require data and insights for decision-making and governance reporting, can also gain a clearer view of equipment usage, research output, and active industry collaboration across the university.<\/p>\n
\u201cRAPPA is harnessing the power of AI and embedding itself in the workflow, Nasabi said. \u201cIt empowers them to do things that they were not able to do in the past.\u201d<\/p>\n
![\"\"\/](\"https:\/\/i.nextmedia.com.au\/News\/Monash_RAPPA_architecture.jpg\")
<\/a><\/p>\n