Not sure if ever come across this search engine called www.wolframalpha.com this is not a replacement for google or any normal search engines we use for doing searches, this is basically a answer engine that answers factual queries directly by computing the answer from structured data, rather than providing a list of documents or web pages that might contain the answer as a search engine would.
How this works?
Users submit queries and computation requests via a text field. Wolfram Alpha then computes and provides answers and relevant visualizations from a core knowledge base of curated, structured data. Wolfram Alpha thus differs from semantic search engines, which index a large number of answers and then try to match the question to one. In this way it has many parallels with Cyc, a project aimed since the 1980s at developing a common-sense inference engine.
Wolfram Alpha is built on Wolfram's earlier flagship product, Mathematica, a complete functional-programming package which encompasses computer algebra, symbolic and numerical computation, visualization, and statistics capabilities. With Mathematica running in the background, it is suited to answer mathematical questions. The answer usually presents a human-readable solution. Alpha also incorporates elements of webMathematica in delivering its content.
What this service can do for you?
The following are examples of queries using Wolfram Alpha. They are accompanied by links to the results of each search to illustrate the variety of answers that Wolfram Alpha provides to non-specific queries.
- mortgage 6%, 25 year, $140000 displays, among other things, repayment rates and graphs that represent capital vs. interest over time.
- life expectancy france 25 year old male which gives a survival analysis for a person of the given demographic.
- boiling point of water at 6 atm which returns a phase diagram alongside the result of 432.6 Kelvins.
- lim(x->0) x/sin x yields the expected result, 1, a plot, and the series expansion. The button "show steps" provides a possible derivation of the result using L'Hôpital's rule.
Wolfram Alpha is also capable of responding to increasingly complex, natural-language fact-based questions such as:
- "Where was Mary Robinson born?"
- "How old was Queen Elizabeth II in 1974?"
- "What is the forty-eighth smallest country by GDP per capita?" yields Senegal, $1090 per year.
- "What is the speed of a swallow?" yields the assumption, "Assuming estimated average cruising airspeed of an unladen African swallow", and the result, "there is unfortunately insufficient data to estimate the velocity of an African swallow (even if you specified which of the 47 species of swallow found in Africa you meant)." This is a reference to a joke from the movie Monty Python and the Holy Grail.
- When asked "What is the meaning of life?", it replies 42. This is a reference to The Hitchhiker's Guide to the Galaxy novel, in which a supercomputer is told to calculate the answer to the Ultimate Question of Life, and it finds the answer to be 42. These and all other "humorous" queries are individually written by programmers and not "understood" by the software on a deeper cognitive level.
Also, one can input the name of a website, and it will return relevant information about the site, including its hosting location, site rank, number of visitors and more.
The database currently includes hundreds of datasets, including current and historical weather, drug data, star charts, currency conversion, and many others. The datasets have been accumulated over approximately two years, and are expected to continue to grow. The range of questions that can be answered is also expected to grow with the expansion of the datasets.
How it works?
Wolfram Alpha is written in about five million lines of Mathematica (using webMathematica and gridMathematica) code and runs on 10,000 CPUs (though the number was upgraded for the launch).
As well as being a web site, Wolfram Alpha provides an API(for a fee) that delivers computational answers to other applications. One such application is the Bing search engine.
Try this and I am sure you will not be disappointed.
No comments:
Post a Comment