Previous Issues:
 
34
July - August
2007
33
May - June
2007
32
March - April
2007
31
January - February
2007
30
November - December
2006
29
September - October
2006
28
July - August
2006
27
May - June
2006
26
March - April
2006
25
January - February
2006
24
November - December
2005
23
September - October
2005
22
July - August
2005
21
May - June
2005
20
March - April
2005
19
January - February
2005
IPR-Helpdesk Bulletin
2002 - 2004
 
 
  N. 35, September - October 2007 

IP in practice 
IP eModules 
 

A new generation of patent and scientific information search tools


The Semantic Web

The semantic Web will make searching much easier. Today, good searches still involve Boolean operators and classification schemes. In a near future, it is likely that natural language searching will make it easier for laymen to retrieve relevant information or even allow automated searching. The machine will understand patent claims and be able to translate these claims into successful search operations. This new generation of tools is often referred to as Web 3.0, in which complex human search requests will be easily conducted using new types of search engines. Today, some initial attempts are made both in the patent and academic fields. The examples presented below show that the quest for new tools has started and is very promising.


Some examples to follow-up

IP Century tool provides automatic results for prior art, invalidity, freedom to operate searches. The results are not yet up to what humans can achieve. However, one cannot exclude that in a near future better results will be possible with new search technologies and more powerful computers.

It is in the academic field that most of those new engines can be found. Medline data are used in both following examples.

GoPubMed developed by the University of Dresden is an Ontology-based Literature search tool for biomedical research articles. The search is submitted to PubMed and the resulting abstracts are classified using Gene Ontology and Medical Subject Headings (MeSH). Additional graphic tools offer all possible statistical information display.

MEDIE developed by a Japanese University is an intelligent search engine built to retrieve biomedical correlations from MEDLINE. You can find abstracts/sentences in MEDLINE by specifying semantics of correlations, for example, "What activates p53" and "What causes colon cancer". This is one of the most impressive semantic scientific search tools.

These 3 tools represent only a small section of the efforts made to develop easier to use search tools. Killing search applications may appear sooner than expected.