Elute Patent Reader includes several distinctive features in the area of patent searching, not least the complete absence of a need for keyword/boolean searching. Traditional searching is done with keywords, in combination or proximity; semantic searching is done by expanding to related concepts which occur in similar contexts. In contrast, the key concept behind Patent Reader is very simple. It reads the full content of the search document and compares the terms it finds with all the content of each patent or other document in the dataset. This is the system underlying our long-established plagiarism detection programs.
This means a user does not need to design a suitable search query; the program builds its own collection of terminology from the text. By searching on everything, tangentially related material is automatically relegated to the lower end of any report, and unrelated material does not appear at all. It also means that the search is guaranteed to be comprehensive and the report is complete within the dataset used for comparison. In addition, we provide an ability to directly compare the relevant claims with full markup of the terms matched by the program, so there is no requirement for reading the full patent and finding the relevant sections yourself.
We default to searching the claims, as this is the primary source of problems or opportunity for FTO and Invalidity searching in particular, we will be expanding our search out to other text in the patents shortly. This methodology is guaranteed to find either the primary search terms and/or the context terms of the search document.
Another contrast with national search engines in particular is that the results are always ranked by the level of similarity to the starting query, and full information on the terms found is shown.
We use the high quality ST.36 Lighthouse IP dataset. The program actually runs from the claim section collected for the full set, but in addition we can collect any of the metadata or full text for reporting purposes.