Multivariate Patent Similarity Detection

As patent filings and litigations increase, there is an increasing demand for more effective detection of similarities among patents, leading to better prior art search, market gap analysis, infringement detection, legal discovery, and litigation support. Ample patent data is readily available, but detection of similarities among patents is difficult, generally resulting in high false-positive and false-negative errors. A multivariate approach to detection of similarities among patents´ benefits from the advantages offered by several different techniques. In particular, leveraging text mining, the patent classification system, and patent citations can each improve accuracy. Further, visualization of the multiple variables can further assist the patent searchers.