Victoria's Stonnington Libraries together with Civica have developed an artificial intelligence-based proof-of-concept solution to remove the manual work involved with cataloguing and searching through library archive databases.
Civica developed the prototype solution using Azure Blob Storage to store the files, Azure Cognitive Services to create meta information of each file, and Microsoft AI to create a searchable catalogue.
Initially, digital images such as photos, maps, scans, and sketches, as well as PDF-format text style documents, including minutes of meetings, flyers, newspapers, articles, and community group newsletters have been fed into the prototype digital archive.
Prior to building this platform for the last 20 years, the library had been manually cataloguing its archive database.
"You cannot underestimate the value of local community information – but creating the access to it has always presented challenges as each item has to be manually indexed, described and categorised," Natasha Tsui-Po, Stonnington Library senior team leader of System and Resources, Library, and Information Services.
"With Civica's new approach to automate that initial task, these resources can now be accessible much faster and without the burden on already time-pressed library personnel."
Read also: AI is key for business success, but lack of skilled staff remains a barrier (TechRepublic)
Stonnington Libraries said it plans to also eventually archive audio files and contemporary video content in the database.
The development of this platform is based off similar technology that Microsoft created when it built a library search and management platform to search and interpret all documents associated with the death of US President John F. Kennedy.
"Libraries are increasingly taking on the responsibility of being a community information repository – a home for all manner of information, documents, letters, photographs, video and audio files that make up our oral history. The challenge is to make this rich data set available for further use," Civica ANZ managing director of Libraries and Education Simon Jones.
"However, libraries are already busy places – they don't have the time or staff resources to manually catalogue, index and manage all of these data resources. Using Microsoft Azure Cognitive Services we have been able to automate the task – and in the process also enhance the quality of meta information making these data collections more accessible, and hence more valuable."
Updated at 3.37pm (AEST), 30 August 2019: Correction that the JFK search and management platform tool was created by Microsoft, not Civica, as originally reported.
Jetson Industries has combined electronics and online gaming with traditional sports to collect movement data and provide insights to players, coaches, and fans.
In one of the biggest AI events in the world, over 3,000 experts from research and industry showcased and discussed their latest work. Advances in machine learning are happening across the board, and integrating knowledge-based systems with graph-based deep learning promises breakthroughs.
Three experimental automation projects tell the tale of a future piloted by robots.
It uses algorithms to detect abnormal behaviour in water levels to deliver near real-time reports to farmers.