SemTechBiz SF SemTechBiz UK SemTechBiz NYC more TVNewser TVSpy GalleyCat AppNewser UnBeige AgencySpy PRNewser 10,000 Words FishbowlNY FishbowlLA FishbowlDC MediaJobsDaily SocialTimes AllFacebook AllTwitter

Trippin’ It On The Web

Jennifer Zaino
SemanticWeb.com Contributor

One oft-quoted example of how the Semantic Web will be realized for consumers is in helping them plan a trip – the idea that your computer can scan data around the web and coordinate options for your perfect trip, from the non-stop flight that fits your budget to the hotel that’s on the block you want to stay on to kid-friendly restaurants in the area.

That’s not the reality today, of course. But some baby steps are being taken to remove some of the hassles from travel, as evidenced by the new web service dubbed Tripit. Launched just three months ago, the company was founded by Gregg Brockway, an online travel veteran who co-founded HotWire.

The service is more lower-case than upper-case semantic web, as it isn’t built on standards such as RDF or OWL. But it is semantic in the sense that it extracts meaning from e-mails about travel plans to build a master itinerary. And it’s social in that it enables users to easily collaborate on trip-building and share their travel plans with others.

“The way most people travel today is their information is spread across the Web. You book your flight with Southewest, your hotel from hotels.com, your rental car from Dollar, maybe you have a couple of OpenTable reservations,” he says.

“Everyone has a little bit of your travel information,” which they’re none too eager to share directly. So Tripit uses proprietary technology, which it calls the “Itinerator,” to capture the unstructured information in email confirmations users forward to it from travel parties such as airlines, hotels, travel sites, restaurant reservation systems, and so on. From this information Tripit creates a comprehensive itinerary, along with value-add information around that data, such as daily weather reports, driving directions, and so on.

It was no simple task to build the foundation to understand and extract the meaningful data out of noisy e-mail that comes in multiple formats from multiple parties, says Brockway.

“Today e-mail is a very messy technology. Different e-mail clients change the structure of e-mail in subtle but important ways,” he says. “All of the people who are generating these e-mails all have their own way of talking about flights, rental cars, or trains, or what have you. We try to standardize that and put everything into the same structured format. That was definitely a little bit of a bigger challenge than we anticipated.”

Baby Step to Semantic Web

The challenge might have been more easily met were more travel-related organizations already supporting Semantic Web formats, he says.

“I find the discussions that happen around what the Semantic Web will bring to the Internet very fascinating and empowering, and it will turbo-charge our service when it happens,” he says.

But being a technology pragmatist who wanted to build a business today, Brockway couldn’t wait for those technologies to get widely distributed.

“I like to think of what we do as maybe a baby step to the Semantic Web in the sense that we’re using a proprietary approach around a very specific vertical to extract meaning, but we’re also trying to publish that information in a variety of formats,” Brockway says. “Will our job get easier when Semantic Web technologies are widely deployed? Absolutely. And in the meantime we are trying to do a variety of things to extract meaning and publish meaning, so other applications and services can access that information.”

Tripit has plans to build on its foundation, adding additional features which may include flight alerts, reminders and other “fun, interesting and helpful things” in the form of new services so that ultimately Tripit becomes a full-blown personal travel assistant that understands your preferences and can help you plan a great trip.

As Brockway notes, “We want to be a service that helps people shop and buy wherever they want, collect that information and sort through all the noise. It’s in line with the intelligent agent vision of the Semantic Web.”

The service is in beta now but fully operational, even as the company adds new features. It will formally launch sometime in the middle of next year.

SemTechBiz is Less Than 2 Weeks Away

The Semantic Tech & Business Conference (SemTechBiz) is coming to San Francisco on June 3-7! Join us for case studies, innovative panels, tutorials, and keynotes that will provide you with practical advice, hands-on guidance, and breakthrough approaches to solving business problems with semantic technology. Passes go up $200 at the door. Sign up now and save !