Monday, July 28, 2008

Google ranking Technologies

Tej Kohli using Google on daily basis and find it’s very amazing and to get desired results about queries whiten in the search box . According to Tej Kohli knowing Google and its very technologies is very difficult and moreover Google officials and Techniques also unable to define and said that its be machine work to fetch out results we are just implementing algorithms.
May 2008 , Udi Manber making an search quality group for checking the search results quality as well checking ‘Core Rankings ‘ and international searches quality . Basically according to Google officials, Google rakings is a collection of Algorithms which is used for returning most relevant documents for a user query. Each day Google have to serve near about hundreds of million quires for billion of Billion pages and algorithms runs for each query . Same algorithms also used in other Google services and images , News , YouTube , Maps , Product , Book Search and many other services .But Google official asked that , Google algorithms are nothing but try to find out locally relevant search results searched globally, keeping simple and no manual intervention in these process . We are working on ‘no query left behind “principal for proving most relevant results to the query. While we return lass than ideals results for any query in any languages in any country and then it’s used as base for further improvements. Google system architecture work upon making this process very simple. Also when user had quarried in various languages. Also Google concentrate its mind over making the process simple without compromising quality. This is an ongoing process and making changes every week with some big consideration in launching every change. But engineer approach for understanding why page get ranked and its appropriateness for query.
But sometimes situation arises when user came up with "Does Google manually edit its results?". But Google official denied for any manual listing and said it’s just be Google algorithms that gives us desired results according to query but its be true that we are analyzing websites structure , linking as well as other human work on various websites to make new algorithms . Google strictly working upon subjective listing and against manual listing adjustment. While we are making and underlying algorithms we are concentrating our mind over all aspects like languages and other issue and then make changes in entire class. Google official added “I should add, however, that there are clear written policies for websites recommended by Google, and we do take action on sites that are in violation of our policies or for a small number of other reasons (e.g. legal requirements, child porn, viruses/malware, etc).”The core technology come from academic filed of Information retrieval (IR). IR community searched studied that topic over 50 years. . It uses statistical signals of word salience, like word frequency, to rank pages , its give solid foundation for making tremendous system by using links , page structure and other such innovation .Internet searches rapidly growing as well as search results are also increasing proportionally. User expectations and search domain also increased . Google work hard to fetch desired results from the huge data which are available on Internet. Google change its algorithms because of new technologies and new components came which must be searchable and readable by search engine crawler. We have to know some before goings into depth we have to know some terms
• Pages: Google official told that they invested much pages for crawling and indexing. Google preferred size and freshness of pages and make algorithm according to that. Google is very keen to understand page association and important concept page contain. Example Google noticed official homepage for Sprovieri Gallery in London for the Italian query [galleria sprovieri londra], even though the official page does not have either London or Londra on it. In the U.S., a user searching for [cool tech pc vancouver, wa] finds the homepage even though the page does not mention anywhere that they are in Vancouver, WA. Gooogle Google developed include distinctions between important and less important words in the page and the freshness of the information on the page.
• Queries: Google said the its seems decisive to understand what users are looking for (beyond just the few words in their query). Google 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.
While user search something , he uses spelling suggestion system . Some times user searching for [kofee annan] is really searching for Mr. Kofi Annan, and is prompted: Did you mean: kofi annan; but sometimes user searching for [kofee beans] is actually looking for coffee beans. Its hard to make this internationally with very high accuracy but Google do well.
Google also using Synonyms for understanding user query which seems hard but Google had solved it . For manually its be possible but for computer processing its needs time and algorithms .When user doesn’t know exact words or even Synonyms wchih Google used in Synonyms for this case Google can do sophisticated query modifications. Like 'Dr' in the query [Dr Zhivago] stands for Doctor whereas in [Rodeo Dr] it means Drive. A user looking for [back bumper repair] gets results about rear bumper repair. For [Ramstein ab], we automatically look for Ramstein Air Base; for the query query [b&b ab] we search for Bed and Breakfasts in Alberta, Canada. Google had developed such system for near about hundred different languages. Identification is also best practice which Google often used which returns with some relevant results .Like that in the query [new york times square church] the user is looking for the well-known church in Times Square and not for articles from the New York Times. Google further enhance the query with the right concepts when, for illustration, someone looking for [PC and its impact on people] is in fact looking for impact of computers on society, or someone who searches for [rainforest instructional activities for vocabulary] is really looking for rain forest lesson plans. Google query analysis algorithms have many such state-of-the-art techniques built into them, to meet internationally in almost every language .
• Users Perspective: Google work hard to know what user want and return relevant results which starts from world class localization system with some advanced personalization technology and other great great strides for getting user intent for making universal search .
Google work on ideology “best locally relevant results served globally" which can be reflected in Google work on localization. User get different results according to different geographical location for same query .Like for US user ‘Bank’ query returns American banks where is UK its returns Bank Fashion line or for British financial institutions while in other countries its retunes financial institutions in other English speaking countries like Australia, Canada, New Zealand, South Africa. Other example is [Côte d'Or] is a geographic region in France - but it is a large chocolate manufacturer in neighboring French-speaking Belgium; and yes.
Another most important factor which Google consider Personalization which makes some results for some individuals . Like user logging make some difference into search results according to user profile and user preference. Like one user profile get results football related results and other will get baseball results for same ‘Sports Events’ query according to personalized results .Such that if you prefer particular website for purchasing you will get same site while you are searching products .An example the query [chevrolet magnum]. Magnum is actually made by Dodge and not Chevrolet. So we present the results for Dodge Magnum with the prompt See results for: dodge magnum in our result set.

Google work on Universal Search is best example to know user intent before making search results. Google also made Cross Language Information Retrieval (CLIR) . which first search information in other languages and then Google translation technology make it accessible to user who fired query .That know as “ give me what I want in any language” like some one looking for Tony Blair's biography in Russia who types the query in Russian [Тони Блэр биография] is prompted at the bottom of our results to search the English web with like that Disney movie songs in Egypt with the query [أغاني أفلام ديزني] is prompted to search the English web. Google very excited about CLIR as it truly brings us closer to our mission to organize the world's information and make it universally accessible and useful.
That be Google state-of-the-art technology which also used for making rankings systems for making “problem had solved “.But on the other hand Google also realize that some queries don’t give desired results and work further for making its possible user get every word to be return back with results. Many other technology and algorithm still under construction for making Google to be get back with relevant results

No comments: