Worldwide Intelligent Semantic Patent Extraction & Retrieval

The next generation Internet requires a semantic expansion of digital content to fulfil the needs of intelligent retrieval systems. Content needs to be annotated with semantic information so that it can be processed by multiple agents and re-used in different contexts.

This project will examine patent structured content, with the aim of demonstrating that flexible tools can be developed for automated mark-up. WISPER is a new multilingual portal for intelligent access to large patent databases. It encodes and visualizes semantic content of patents by using advanced Text Mining, Intelligent Image Analysis and User Profiling and thereby encourages SME participation in patenting. SMEs will be able to search both text and images for the first time by using natural language.