Intology - Intelligent Technology News
Computers Technology Internet Arts Business Science Sports

For the first time Google has opened up a little and explained how its search engine works. Although the they didn’t reveal every thing for obvious reasons at least it gives an insight as to how things work at back end.

Google has pledged to adopt a more open approach with the formula for its search algorithms.

This was announced on Google blog by Udi Manber, Google’s vice president of engineering as part of a “renewed effort” to open up the company’s secrets.

He said:

Search Quality is the name of the team responsible for the ranking of Google search results. For something that is used so often by so many people, surprisingly little is known about ranking at Google. This is entirely our fault, and it is by design because of two reasons: competition and abuse. But 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.

The heart of the group is the team that works on core ranking. Ranking is hard, much harder than most people realize. One reason for this is that languages are inherently ambiguous, and documents do not follow any set of rules.

Another team in their group is responsible for evaluating how well they are doing.

One team is dedicated to new features and new user interfaces.

To fight spam and other abuse they have a separate team which works on variety of issues from hidden text to off-topic pages stuffed with gibberish keywords, plus many other schemes that people use in an attempt to rank higher in our search results.

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 components are:

• Language models: The ability to handle phrases, synonyms, diacritics, spelling mistakes and so on
• Query models: How people use queries
• 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
• Personalized models: To personalize results for each person depending on his/her needs

According to Manber:

Tomorrow’s queries will be much harder than today’s queries. Just as Moore’s Law governs the doubling of computing speed every 18 months, there is a hidden unwritten law that
doubles the complexity of our most difficult queries in a short time.

You can read full post here.