Patent Law

Mark Johns, President of Littlearth, Inc. wrote to me last week about his company that has "recently developed a technology for finding related/similar documents in large document collections, e.g. patents, wikis, law cases."  The following is excerpted from an article that will appear in the Oct/Nov issue of Research Information:

This article begins with the premise that searching for information in some collection of unstructured documents is extremely valuable and it is therefore worth improving upon the efficiency of the process and the accuracy of the results. An unstructured document is defined as a cohesive body of text that is electronically accessible, e.g. patent document, news article, legal case, medical journal article.

Within some document collection, searching for relevant documents via keywords is the most common and accepted method. ... The advent of the ?search engine? is a cornerstone in the evolution of information research. In its simplest form, a search engine is used to find documents that contain some specific words.

So, what is the best way to build the appropriate search criteria? ... It is the case that in many document collections, the highest quality search criteria is actually the entire text of one of the documents in the database. A real document in the collection (or a new one that the researcher types in full) contains so much more information than what a researcher typically types as keywords. The natural language of the document and all of its inherent properties tend to shine through, if analyzed with appropriate algorithms. The effect is that the result of the search criteria is the set of documents that are most similar to or related to the original document. In ?complexity theory?, such a phenomenon is known as ?emergence?. This emergence is the key to a natural stepping-stone in the evolution of information research - a ?discovery engine?.

At Littlearth, Inc., located outside of Washington D.C., a technology called DocumentDiscovery has recently been developed.

I have briefly tried Littlearth's PatentSurf and Case-Law. I found immediate value in searching for related patents for a current business strategy project in the medical device field.  I was able to quickly find relevant patents and then use the text of the most relevant patent to find more directly relevant patents.  The Case-Law site is still "very beta" and I had less luck finding what I was seeking.  I also believe this tool could have great value applied to e-Discovery where you are trying to search through a massive volume of documents to locate all those discussing the same issue.  Using the full text of a memo or a report to locate other documents rather than crafting the "just right" keyword search.

I have added both sites to the Tools list on the left hand margin of this blog.  Take both for a spin and provide your comments on the experience at this post.  Thanks!