Google will be rolling out a search that really understands what you are searching for. Users in India will get the richer search experience — called Knowledge Graph — in the next few days.

What exactly is Knowledge Graph? If you are searching for ‘Indians’ what do you expect? People in India may expect results about ‘people residing in India’ or NRIs or PIOs. But the query may have a different meaning in the US. It could mean the indigenous community there, or even the Cleveland Indians team.

Talking about Knowledge Graph, Amit Singhal, Google Fellow and SVP, Engineering, says the new search tries to understand what you really want to search.

In his blog post on Knowledge Graph, Amit Singhal says, “Take a query like (Taj Mahal). For more than four decades, search has essentially been about matching keywords to queries. To a search engine, the words (Taj mahal) have been just that - two words.

“But we all know that [taj mahal] has a much richer meaning. You might think of one of the world’s most beautiful monuments, or a Grammy Award-winning musician, or possibly even a casino in Atlantic City, NJ. Or, depending on when you last ate, the nearest Indian restaurant. It’s why we’ve been working on an intelligent model — in geek-speak, a “graph” — that understands real-world entities and their relationships to one another: things, not strings.”

The search will enable users to get the results that will also have the context in which they are making the query. It won’t just throw up a random list of sites from where you may or may not get the information you seek.

When Google bought Freebase, it got instant access to over 12 million entities. According to Freebase, it “has information about approximately 20 million Topics or Entities at the time of writing. Each one has a unique Id, which can help distinguish multiple entities which have similar names, such as Henry Ford the industrialist vs Henry Ford the footballer.”

Amit Singal says Google’s Knowledge graph “currently contains more than 500 million objects, as well as more than 3.5 billion facts about and relationships between these different objects.”

This type of distinction is one of the main characteristics of Knowledge Graph. Google will try to understand what you are searching and will try to give the exact information you are looking for. If we take the ‘Indians’ example, the results you get (in the auto-complete list as you search) will be related to the area from where you are searching for it. There will be different results if the search is from India, Sri Lanka and the US.

It will also give additional information on the right from its database, apart from the usual search results. If you are searching for ‘Rabindranath Tagore’, you will get the usual search results, and on the right, the information about his birth, Shantiniketan, the Nobel Prize and his photographs.

Says Amit Singhal in his blog, “In fact, some of the most serendipitous discoveries I've made using the Knowledge Graph are through the magical “People also search for” feature. One of my favourite books is The White Tiger, the debut novel by Aravind Adiga, which won the prestigious Man Booker Prize. Using the Knowledge Graph, I discovered three other books that had won the same prize and one that won the Pulitzer.”

Apart from Knowledge Graph, Google is also rolling out a ‘limited trial’ of search results from Gmail account. If you are searching for “Mumbai train tickets”, the search will include any email you have written or received that has “Mumbai train tickets”. In another blog post, Amit Singal says: “We’re working on some even more useful features. For example, if you search for [my flights] we will organise flight confirmation emails for any upcoming trips in a beautifully easy-to-read way right on the search results page.”

Google’s voice search on Android phones has taken a big leap forward in the Jelly Bean (Android 4.1) version. It will soon be available on iPhone and iPad.

The Knowledge Graph itself will look great in mobiles and tablets, says Amit Singhal. “It is a beauty. Just try it out,” he says about the design.

What is making Google move towards a more intelligent search? Now, when you search for something, Google, or any other search engine just displays results based on Web sites’ keywords and other info. It really does not understand what you want.

Amit Singhal says he wants to develop a machine something similar to the one in the Star Trek serial. Why? It is because he was so fascinated by the way the machine responds to queries by Captain Kirk and others, that his aim is to build a similar computer that would understand what we ask and give the correct response. For Amit Singhal, Knowledge Graph is just a step towards that computer.

>dinakaran.rengachary@thehindu.co.in

Related Topics
comment COMMENT NOW