Deep Search

IBM Deep Search uses AI to collect, convert, curate, and ultimately search large document collections like public documents, such as patents and research papers. It makes information accessible that is too specific for common search tools to handle. It collects data from public, private, structured, and unstructured sources and leverages state-of-the-art AI methods to convert PDF documents into easily decipherable JSON format with a uniform schema that is ideal for today’s data scientists. It then applies dedicated natural language processing and computer vision machine-learning algorithms on these documents and ultimately creates searchable knowledge graphs.

IBM Deep Search has already allowed scientists and businesses to search mountains of unstructured data for a while. In 2022, our team made deep search even more versatile and accessible with the release of IBM Deep Search for Scientific Discovery (DS4SD), an open-source toolkit for scientific research and businesses.

You can try our demo here or find out more about IBM's research in accelerated discovery.