I recall this idea brought up often in the enterprise. A person, or an enterprise, already knows many things. The problem is that 'it' does not know what it knows. If I start a search I might first want to understand what I personally know, then I might want to know what my work group knows, then what by department knows, then my enterprise, then my professional group .... Is there an accuracy, and an efficiency by thinking about this progression as a self-similar process? In the simplest test you could have an automated search that would search topics as you typed paper and establish a personal ontology of searching for you. And lead to better results. In TechnologyReview:
" ... A revamped search engine might return different results depending on whether you've researched a subject before. Google seems to have developed almost an almost preternatural ability to divine what users are really looking for when they enter a search term. Its engine often returns useful results for even the most egregiously misspelled queries. But Google's user experience team hopes to give search an additional layer of intelligence—the power to grow with users over time, returning different results depending on whether users are just beginning to investigate a subject or have become old hands ... "