Google Talks Search Technology
Google has published the second part of a blog series explaining the methods behind its search systems.
Last week, we saw some broad Q&A about the processes and the philosophies of Google search — including discussions on things such as whether search results are ever manually edited — but no major revelations about algorithms or other closely guarded Google mysteries.
This week’s edition, which was billed to be a more in-depth look at the technology driving the search process, doesn’t bring about any jaw-dropping “ahah” moments either. Google Fellow Amit Singhal discusses basic concepts of the process and the general goals on which it focuses. It’s certainly nothing earth-shattering — the post seems to be more PR-oriented than anything — but there are a couple of mildly interesting points worth a glance.
Here are the highlights, condensed down into a manageable 196 words for quick and easy digestion:
“It uses statistical signals of word salience, like word frequency, to rank pages.”
“One of the key technologies we have developed to understand pages is associating important concepts to a page even when they are not obvious on the page.”
“Other technologies we have developed include distinctions between important and less important words in the page and the freshness of the information on the page.”
“It is critical that we understand what our users are looking for (beyond just the few words in their query). We have made several notable advances in this area including a best-in-class spelling suggestion system, an advanced synonyms system, and a very strong concept analysis system.”
“The same query typed in multiple countries may deserve completely different results. A user looking for [bank] in the US should get American banks, whereas a user in the UK is either looking for the Bank Fashion line or for British financial institutions.”
“Personalization is another strong feature in our search system which tailors search results to individual users. Users who are logged-in while searching and have signed up for Web History get results that are more relevant for them than the general Google results.”