Google hummingbird algorithm ppt
Download as PPTX, PDF11 likes12,755 views
Google introduced the Hummingbird algorithm in 2013 to improve search results. Hummingbird analyzes longer, more complex questions to provide more direct answers compared to previous algorithms like Panda and Penguin. It uses information like user location and interests to personalize results. The algorithm also leverages Google's Knowledge Graph to understand context and relationships to better answer follow-up questions. Hummingbird aims to have a more human-like conversation with users through its semantic search capabilities.
Google hummingbird algorithm ppt
- 1. GOOGLE HUMMINGBIRD ALGORITHM By Priyodarshini Dhar CSE, 2010-1041, UIT BU Seminar on
- 2. INTRODUCTION Google Hummingbird, named for the “fast and precise” results it is intended to deliver, was announced at the company’s 15th anniversary conference on September 26, 2013. Hummingbird’s strength is the ability to quickly analyze longer, more complex questions and provide the best answer to the searcher with the fewest possible clicks. "Hummingbird" algorithm is a more human way to interact with users and provide a more direct answer unlike its previous versions Panda and Penguin.
- 3. DIFFERENCE BETWEEN OLD AND NEW SEARCH TECHNIQUES : Previous Search Techniques Google Hummingbird Search 1) Keyword based search 1) Question-based, conversational, semantic search(takes into account why, when,who…) 2)The same search yields same result for different users. 2) The same search may yield different results to each user, based on current circumstances 3)Search technique does not use user information for searching 3)It uses user information like previous downloads, geographical location, social shares etc. 4)It cannot handle complex search strings. 4) It can handle long complex search strings. It uses Google’s knowledge graph. 5) Provides users many possible options to continue with search 5)It starts with answering the question. This is called “conversational search”.
- 4. KNOWLEDGE GRAPH: The Knowledge Graph is a knowledge base used by Google to enhance its search engine's search results with semantic- search information gathered from a wide variety of sources
- 5. PAGE RANK ALGORITHM A webpage’s ranking is determined by analyzing the ranking of all the other webpages that link to the webpage in question.It is calculated as, ‘n’ = the number of pages in the web. C(Tn) = the PageRank of each page by the number of outgoing links on that page d= damping factor decrease the influence of all of the pages in relation to the page in question Example : PageRank(p1) = (1- 0.5) + 0.5{ PR(p3)/3 + PR(p4)/2 + ….}
- 7. HUMMINGBIRD UPDATE It has updated the Page Rank Algorithm. It uses intelligent ranking of webpages. It takes into account question based queries like “why”, “who”, “when", "what” etc. The motivation for the ‘Hummingbird’ update, was the advent voice-recognition searching.
- 8. o Indexing faster and put a higher premium on pages that are more recent. o Relationally links search queries and Web documents o Pays more attention to each word in a query, ensuring that the whole query - the whole sentence or conversation or meaning - is taken into account, rather than particular words.
- 9. FEATURES OF HUMMINGBIRD ALGORITHM Hummingbird expands the use of the Knowledge Graph , so that Google answers more complex search queries and also improves the follow-up search process. For example, if we first search “picture of Washington Monument” and then do a second search for “how tall is it?” Google will understand the context of your second query. how tall is it
- 10. Comparisons The knowledge graph enables more comparisons between search objects (ex: “compare butter vs olive oil”, “compare Earth vs Jupiter” etc.). Geo-location enhancement If someone asks “What’s the best place to buy an iPhone 5s?” then Google will likely bring a result near to his current location. Improved mobile search design and functionality Voice search and Android/iPhone synchronization are improved and will likely continue to improve quickly.
- 11. A SIMPLE WORKING MODEL OF GOOGLE HUMMING BIRD ALGORITHM Complicated queryUser Google search engine Pages sorted according to page rank inputs Page request Response Sort into pages according to the query – taking into consideration “ why”,”who”… Most appropriate html pages
- 12. IMPORTANT THINGS TO OPTIMIZE WEBSITE FOR NEW ALGORITHM For getting high Google rank of our website/blog: A Professional Website With Good Content Good Backlinks from Related Sites Content of your website should original and must related to the topic/website Limitations: The knowledge graph still does not incorporate many languages. The Algorithm result is not applicable to all countries.
- 13. REFERENCE http://thenextweb.com/google/2013/09/26/google- unveils-search-updates-for-mobile-new-page-rank- algorithm-and-knowledge-graph-comparisons http://www.cs.duke.edu/courses/spring08/cps049s/ Slides/bryan.ppt http://googleblog.blogspot.com/2010/06/our-new- search-index-caffeine.html http://www- scf.usc.edu/~csci571/2013Fall/extras/GooglesNew SearchAlgorithm.pptx
- 14. Thank You