Completing keyword patent search with semantic patent search: introducing a semiautomatic iterative method for patent near search based on semantic similarities

Patent search is a substantial basis for many operational questions and scientometric evaluations. We consider it as a sequence of distinct stages. The “patent wide search” involves a definition of system boundaries by means of classifications and a keyword search producing a patent set with a high recall level (see Schmitz in Patentinformetrie: Analyse und Verdichtung von technischen Schutzrechtsinformationen, DGI, Frankfurt (Main), 2010 with an overview of searchable patent meta data). In this set of patents a “patent near search” takes place, producing a patent set with high(er) precision. Hence, the question arises how the researcher has to operate within this patent set to efficiently identify patents that contain paraphrased descriptions of the sought inventive elements in contextual information and whether this produces different results compared to a conventional search. We present a semiautomatic iterative method for the identification of such patents, based on semantic similarity. In order to test our method we generate an initial dataset in the course of a patent wide search. This dataset is then analyzed by means of the semiautomatic iterative method as well as by an alternative method emulating the conventional process of keyword refinement. It thus becomes obvious that both methods have their particular “raison d’être”, and that the semiautomatic iterative method seems to be able to support a conventional patent search very effectively.