Tasks performed by intellectual property specialists are often ad hoc, and continuously require new approaches to search a collection of documents. We therefore investigate the bene ts of a visual `search strategy builder' to allow IP search experts to express their approach to searching the patent collection, without requiring IR or database expertise. These search strategies are executed on our probabilistic relational database framework. Search by strategy design can be very e ective. We re ned our search strategies after our initial submission to the CLEF-IP track, and with minor e ort we could include techniques shown to be bene cial for other CLEF-IP participants.
Springer
Lecture Notes in Computer Science
Human-Centered Data Analytics

Alink, W., Cornacchia, R., & de Vries, A. (2010). Searching CLEF-IP by Strategy. In Multilingual Information Access Evaluation I. Text Retrieval Experiments (pp. 468–475). Springer.