Semantic solutions include in their architecture knowledge data bases.
These knowledge data base connect the form of the words with their meanings and to relate different words and different meanings with different kind of relationships, as for example subset and superset.
These knowledge data are called in general ontologies; thesauri and taxonomies are specific instantiations of them. These knowledge data in general code the domain knowledge; in the patents they can also code the document structure, since patents follow a specific document structure.
The use of the meanings of words besides the form of words allows to deal with synonyms (i.e. different words with similar meanings), omographs (i.e. words having the same form but different meanings) and more in general to deal with the multilinguality issue.
Since the wide diversity of semantic solutions, it is appropriate to further differentiate them by the technology used and by the specific function.
Examples of patent information functions which can benefit from semantics are:
a) Semantic Search improvement. This is due to the fact that by using the meanings the Recall increases, since it can be possible to capture other words having the same meaning and the Precision increases as well, since it can be possible to disambiguate identical words with different meanings
b) Semantic faceted refinement between a long list of collected documents. In this sequential approach a high recall query is first applied, which can include also garbage document, then in order to achieve precision as well, downloaded documents are suitably refined by local semantic faceted refinement.
c) Semantic support for Analysis. In this case semantics is used for supporting the user in analysing a specific patent from a specific point of view, IP or technically related.
Of course different kind of functions require different kind of technologies as well, since for example the semantic search improvement benefit from the “shallow” semantics, whilst the semantic support for analysis can include also “deep” semantics, i.e. some form of reasoning.
Some more details and some specific adoption examples are cited in the full presentation, which can accessed from http://www.intellipatent.eu/Documents/PatentInformatics2.pdf
