AI, Crowdsourcing Combine To Close "Analogy Gap" - News - Carnegie Mellon University

Searching and repurposing ideas could inspire innovation. Researchers at Carnegie Mellon University and the Hebrew University of Jerusalem devised a method enabling computers to mine databases of patents, inventions and research papers, identifying ideas that can be repurposed to solve new problems or create products. Specifically, they developed a way for computers to find analogies - comparisons between sometimes disparate methods and problems that highlight underlying similarities. As anyone who enjoyed watching TV's MacGyver disarm a missile with a paperclip or staunch a sulfuric acid leak with a chocolate bar could tell you, analogies can provide critical insights and inspiration for problem-solving. Tapping huge databases of inventions could spur innovation, but doing so without the help of analogies is, well, like finding a needle in a haystack. Computer scientists at Carnegie Mellon and at Hebrew University solved the analogy problem by combining crowdsourcing and a type of artificial intelligence known as deep learning. By observing how people found analogies, they obtained insights they used to train computer software to find even more analogies.