Guest Column

Semantic Search can revolutionize the travel industry

By Carsten Kraus

Although the rise of online search engines have made finding the ideal holiday easier, it is still far from being an exact science. But what if the online search process was more intelligent? What if you could ask specific questions when searching for the perfect destination to get results that more accurately reflect what you want?

Well, soon you will be able to do just that. Probably the biggest driver in this change will be Google, which will shortly be implementing ‘semantic search’ technology, widely viewed as the "next big step" in search engine functionality. Until relatively recently, this technology has been out of reach of the average internet user, but within the next few months, if we are to believe the press, the bulk of search activity going through Google will be based on semantics. This means that Google searches will no longer simply throw up a list of blue links. Instead, the top of the results page will be dotted with information that "answers questions" posed in searches.

This will enable you to make more detailed and sophisticated searches, because instead of simply trying to match the words that you have typed in, Google will analyse its own vast knowledge repository to try to understand the words and draw its own conclusions.

For example, if you were looking for ‘a hotel close to a beach in November’, a true semantic search engine would use inference technology to deduce that the destination you were looking for should be warm.  This would be a major improvement over the current keyword searches that might produce results of any venue mentioning a beach, regardless of the climate.

While Google may be the most high profile mover in this area the technology has been about for some time, and although an improvement over keyword search, standard inference semantic search  – similar to what Google is likely to be using – does have its limitations. For example, if you were looking for a venue in Scotland in November, and wanted to go for walks on a nearby beach, you might search: ‘Scotland in November with beach’. While this is a valid request, if you asked a normal inference engine, it would reject it, because it would associate the term ‘beach’ with someone looking for somewhere warm – and it is never going to be ‘warm’ in Scotland in November.

We have solved this problem by creating a ‘probabilistic’ inference engine that scores rather than judge’s information, combining semantics with fuzzy logic – which we’ve been employing in our search systems since the mid-1990s. Essentially, this probabilistic approach helps deal with real life ambiguities. We have already implemented this kind of search technology in the travel sector for German travel site weg.de, and http://urlaubswelt.neckermann.de/, a Thomas Cook travel site, with huge success.

What’s more, by using probabilistic inference search on their websites, travel companies can make it easier for people to find what they want, increasing both service levels and, even more importantly, revenues.

I believe the ability to type a query in your own words and have the search engine understand the inferences of the language is a huge step in search technology and has major implications for the travel sector. In fact, research has shown that, on the travel websites we currently work with, that as soon as people understand how the technology works and that they can really type in what they want, it takes them one third of the time to find the right product compared to conventional search.

To take full advantage of semantic search, our searching habits will have to change; moving from typing keyword queries, as we have all become conditioned, to entering free-form queries in our own words. This is where the power of semantic search lies and the technology for intelligent searching is now well within our grasp for the benefit of meetings planners… and their suppliers.

Carsten Kraus is chief executive of European online search and navigation specialist FACT-Finder Travel http://www.fact-finder.com/semantic-travel-search.html.