Back to blog's index

Semantics in Patent Information

HTML5 Icon

Image copyright: IntelliSemantic

The term "semantics", a specific branch of Natural Language Processing, means to add meanings to text; in fact, a word can have different meanings, depending on the context. The world “semantics” entered in patent information circles about ten years ago, mainly as “semantic searches”, denoting new kind of searches whose query is expressed as a text.

Indeed, this is only one of possible uses of semantics in patent information, which will be covered by a three parts overview paper by IntelliSemantic. The part 1 of this overview will focus on "semantic searches" only, which in any case still attract some concerns, as expressed in recent events, as CEPIUG 2018 and EPOPIC 2018.

Some of these concerns are due to the fact that semantic searches are perceived as "black box" solutions. The table here tries to "open the box" of semantic searchers by identifying the main features of today and coming semantic searchers. From this table, we can infer that the term "semantic searchers" covers today two different generations of products, while a third product generation is likely to appear to fulfill some alternatives not yet covered by today searchers: these alternatives, as the multilanguage support, are in italics in the table.

More details on semantic searches, including why to use them are available in the full paper, which can be accessed by clicking here or also here and how to assess them will be in the march issue of the IntelliSemantic newsletter (to subscribe, fill the form here).

updated on: 8/4/2019

published: @intellisemantic

Copyright © 2006-2023 by IntelliSemantic S.r.l.

Società registrata al registro delle Imprese di Torino con Numero REA TO - 1026789

Sede legale: Corso Susa 299/A -10098, Rivoli (To) - Italy

Capitale sociale 30.000 Euro

Partita IVA 09124770018