Google has introduced a new function to its search offering designed to boost results speeds and make it "more human".

The 'knowledge graph' will be available first to US-based users, but will be rolled out globally.

According to the BBC, Google's senior vice-president of engineering Amit Singhal said that, until now, the search engine had been able only to match keywords, rather than understand context.

As an example, Singhal said the words Taj Mahal could mean different things to different people.

"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. Or, depending on when you last ate, the nearest Indian restaurant," he said.

Google said the knowledge graph has been programmed to use around 3.5 billion different attributes to organise results, meaning it could now group results according to various alternative interpretations.

For some searches, such as on prominent people, Google will automatically pull up a summary box with key information on that topic.

The next step, Singhal said, is to look at how the site can answer more complex questions, such as 'what are the 10 deepest lakes in Africa?'

In doing so the search engine would need to draw on multiple sources and factor in many different criteria.

The knowledge graph will also work on tablets and smartphones.

* Learn more at the Google blog.