Search engine spawned from antiterrorism efforts finds place in business

Artificial-intelligence-based search technology originally developed to help U.S. military and government agencies gather intelligence information from the so-called deep Web is now is finding a place in businesses looking for tool that can scour the Internet beyond the Web-crawling capabilities of Google or Yahoo.

An emerging group of companies, such as Fetch Technologies Inc., are focusing on building technologies that can harvest deep Web information ensconced in databases and behind forms that obscure it from traditional general search engines.

The Defense Advanced Research Projects Agency, the U.S. Air Force, the National Science Foundation and other agencies funded development of the Fetch technology by researchers at the University of Southern California's Information Sciences Institute during the 1990s. A group of computer science professors who developed the core AI algorithms behind the Fetch Agent Platform founded the company in 1999 to build a commercial product.

The hosted Fetch Agent Platform search engine from El Segundo, Calif.-based Fetch is still commonly used by government agencies seeking to rapidly import and integrate data from multiple Web sites and databases for emergency response, location intelligence and antiterrorism efforts. However, over the past two years, said Fetch CEO Robert Landes, use of the technology has been extended to businesses in several different vertical markets looking to better target specific data sources on the Web.

"We can go to places and extract information where Google and Yahoo can't," Landes said. "The idea of how to cast this net, how to extract and aggregate information that [companies] can find useful from a commercial standpoint is where the company has really exploded."

For example, travel industry data aggregator Farelogix Inc. is using Fetch's technology to integrate fares, scheduling and related information from airlines, hotels and other travel destination sites, Landes said. Fetch on Thursday plans to announce a technology partnership with event search company Zvents Inc. to integrate Fetch's search technology into a local event search platform used by media companies and Internet service providers, he said.

Retail sites are using Fetch to aggregate content quickly, and consumer product manufacturers use the technology to develop automatic proof of delivery systems, Landes added.

Landes noted that while a Google user could perform a general search for data about Toyota Camrys, a Fetch client could use the same search to compile the VIN number, color, description and style number for all Camrys in the U.S. To do that, Fetch builds an artificial intelligence agent to extract that particular data, not just to look for Web sites that may contain that data, he said.

The strength of the system, added Fetch Chairman and CTO Steve Minton, emanates from the machine learning focus of the search engine's agent-based tools. The system can recognize types of data based on a pattern and can apply what is learned about that pattern to future searches, Minton said.