Report:Google Patent Search/Viewing Results/Weighting and Ranking Features
|Report||Patent Coverage Map||Ratings||Comments|
|This search system report was created by the Intellogist Team and is available for viewing only. If you'd like to share your knowledge on Intellogist, please visit the Best Practices, Glossary, or Community Reports pages. If you are a registered user and would like to be notified of any substantial changes to this report, you may place a "watch" on the Revisions page, which is the last page listed on the table of contents. To learn more about using the Intellogist "watchlist," see the Watchlist Help page.|
Weighting and Ranking Features
Google Patent Search automatically ranks search hits by order of perceived relevance when it constructs the hit list. In their web search engine, Google ranks results on the basis of both 1) appropriate content, determined by “sophisticated text-matching techniques” and 2) the number of quality hyperlinks pointing to that page on the web. This algorithm appears to be described in some of Google’s own patents (see US 6,285,999 and related documents, including US 6,754,873).
Google Patent Search does not explicitly describe the ranking methods used by its search engine, giving only the following paragraph in its program FAQ page:
- "As with Google Web Search, we rank patent results according to their relevance to a given search query. We use a number of signals to evaluate how relevant each patent is to a user's query, and we determine our results algorithmically."
Because it is developed by the company behind Google Web Search (and also because it was a side project as opposed to a major new initiative), it seems fair to assume that some of the same logic is at work in Google Patent Search’s ranking algorithm.
Finally, it is well known the Google Web Search engine tracks search query history to tailor the results it shows to individual users. Such tailoring would be inappropriate for prior art search purposes, and it is unknown whether the Google Patents search engine is in fact keeping track of search activity over time and allowing past searches to influence present ones. Users should be aware of this possibility. One way to get around this search "tailoring" would be to clear browser cookies before any new project begins.