Google has let us in on the inner working of its search engine in a recent blog post.
Understandably, Google has to be quite secretive about the “Google crown jewels” – the ranking algorithms. This is due to not wanting competitors stealing or copying it and also Google doesn’t want web sites cheating the system. But, Google now plans to share a little more with us all.
Udi Manber, Vice President Engineering, Search Quality explains further:
“Being completely secretive isn’t ideal, and this blog post is part of a renewed effort to open up a bit more than we have in the past. We will try to periodically tell you about new things, explain old things, give advice, spread news, and engage in conversations.”
Manber also explains that ranking is much harder than most people realize. This is due to languages being ambiguous and there being no standards of how to convey information. So the Search Quality team needs to be able to understand all web pages, which could be written by anyone.
“The most famous part of our ranking algorithm is PageRank, an algorithm developed by Larry Page and Sergey Brin, who founded Google. PageRank is still in use today, but it is now a part of a much larger system. Other parts include language models (the ability to handle phrases, synonyms, diacritics, spelling mistakes, and so on), query models (it’s not just the language, it’s how people use it today), time models (some queries are best answered with a 30-minutes old page, and some are better answered with a page that stood the test of time), and personalized models (not all people want the same thing).”
This is only the first in a string of blog posts that Manber plans to provide to keep us informed of updates in Google search quality. To read the whole post, click here.
So what’s Google’s main focus? Manber explains that the key thing about search is that the expectation of users is growing rapidly and Google’s overall main focus is to ensure that they continue to come up with new ideas to exceed user expectations and remain the number one search engine.