Silobreaker: When Intelligence Officers Solve Their Own Info Problems
May 20, 2008
“The Holy Grail”, one former intelligence officer told me, “is to walk in my office and have what I need on my desk, on the computer monitor, and on the screen of my secure telephone.” (You can recognize these whizzy mobile phones because some have an extra light and other features to make it hard for the bad guy to listen in on the call.)
I forget that most people in the online business don’t have experience working in intelligence, the military and law enforcement. When I see an allegedly “hot new semantic search system”, I often take a cursory look and then walk on by. The reason is that the idea of searching is not where the action is for serious intelligence.
If you do a search on Mother Google, you will find more than 300,000 references to the company. To give you a benchmark, if you search for this Web log, you get about 230,000 references with most of them to a search engine optimization company with the same name. The point is that certain services or resources, no matter how useful, are tough to find unless you know exactly what to enter in the search box.
Let me illustrate. Here’s a screen shot of a system that has been available for several years.
The query “semantic search” returned a main story, secondary items in smaller “newspaper” style boxes, an embedded live video from CeBIT, a bar chart about term frequency, and an “In Focus” section that provides the names of people and things the Silobreaker system identified as important. (If you look at the people in the “In Focus” box, you’ll see me (Stephen Arnold) identified despite my <230,000 Web log references in Google.)
Notice that Silobreaker’s default display is a report. The system delivers a synthesis of what’s important. There’s no result list. No single graphic gizmo floating in the browser without meaningful context. Silobreaker looks great but it contains a significant amount of go juice. Navigate here to explore the system yourself.
Silobreaker doesn’t do plain vanilla laundry lists. You can see a list of documents, but you see them in context; that is, a specific knowledge setting. You don’t have to ask, “What the heck does that mean?” Silobreaker presents the meaning of each item in a display.
Most of the search systems I see or get asked to review don’t do what I need done. I want to comment on a basic Silobreaker output and point out a few facts about the system. Once that housekeeping is done, I will make several observations in an effort to spark discussion about the sorry state of enterprise search and commercial business intelligence systems. For a reader who finds my criticism of the best that Silicon Valley has to offer offensive, stop reading now. If you want to see where the rubber meets the race track in the intelligence community, keep reading.
A Representative Silobreaker Display
Now let’s look at a Silobreaker “geo map” display. You can see this demonstration here.
This is a Silobreaker “geo map” display. Notice that you can launch another search, click on the hot spots shown on the map, examine related documents, or follow the “See Also” references. If you are interested in a topic, Silobreaker can put this display on your computer as your window on what’s happening now. No searching needed unless you want to type a query.
You can navigate here and see what Silobreaker calls a “Trends” display. These are mash ups that do the work a person in the line of fire–whether at a broker’s trading desk or sitting in a command and control center needs. The idea is processed, priority-ranked, “at a glance” information. In the early days of dial up modems and frame relay lines that worked at a snail’s pace, PointCast pushed information to the user’s desktop. The PointCast team understood that busy people don’t have time to go on an Easter egg hunt when information is needed. PointCast’s technology choked a user’s network connection and then strangled the wimpy desktop computers in the late 1980s. BackWeb tried to resolve some of PointCast’s problems, but the bandwidth and the computing horsepower wasn’t available. (Note: I wrote an article in 1997 about push here which contains some other early players in real time information delivery to a business user here.)
Search ignored “push”. Today, you can get a free “push” or alert service from Google. Just navigate to the Google News page. Run a query. Scroll to the bottom of the results page, and you will be able to sign up for alerts. You can get alerts from Yahoo as well. Stick with Google. My tests show Yahoo delivering more false drops each week than Google does in a month.
The point is that you have to hunt to get a useful service. The notion of push has evolved into RSS or really simple syndication.
But Silobreaker’s engineers understand that for financial, intelligence, and police, typing key words is not what wins loyal users. Not surprisingly, when a “real” interface like Silobreaker’s is shown at a trade show, a crowd gathers. The problem is that users can’t get their hands on “real” information services. It’s a Eureka moment that is very difficult to convert into an information addiction.
Believe me, once you use a system like Silobreaker, typing key words is not the way to search. Now, here’s the kicker. The relationship or geo map displays are just two of dozens the Silobreaker system supports. You can get “hot spot” maps with information plotted geographically. You can get charts and graphs. You can get relationship charts, bubble graphs, and just about any display of data that speaks to you. You can get the key quotes from the most important sources displayed for you, so you know what key thinkers say about a specific person, topic, or event.
Under the Hood
Silobreaker’s founder is a former McKinsey wizard and a decorated military officer. No, I wont reveal his name, nor will I tell you where he lives with two really friendly dogs. These lovable canines are able to part a crowd without showing their bright white fangs.
The Silobreaker SWAT team was assembled by this McKinsey wizard and a retired investment banker. They and group of tack-sharp programmers used key word indexing as a baseline. Key word search is available on any Silobreaker display, but the business end of Silobreaker puts intelligence in the system so users get actionable reports out. No messy key words required–unless you want to use them.
Over a period of years, the team created proprietary technology to chop up and understand content from Web sites, news sources, and documents like those residing on an organization’s in-house servers. The team added support for rich media. The team has technology that can ingest structured data and generate easily-customized reports. These can be embedded in a Web “heads up” display or provided as a stand-alone deliverable.
The McKinsey wizard and the banker dipped into tjeir own pockets to get Silobreaker underway. However, their contacts provided access to other resources. As Silobreaker stands today, the company licenses its system and its capabilities to commercial and governmental entities. Individuals can use the Silobreaker system as a no-charge service. The company also offers individual subscriptions. The types of licenses available can change. If you are interested, you will need to contact the company to explain your requirements.
To sum up, instead of having one new technology and an eager beaver PR person, Silobreaker has:
- Linguistic technology
- Semantic technology
- Computational intelligence technology
- Entity extraction technology
- Clustering technology
- Rendering technology
There’s more, but you get the point. Silobreaker is a system with an interface that can be designed for an investor or for a person who is shot at.
What the Company Told Me
Actually not much. Silobreaker strikes me as a low-profile, top-drawer outfit. Chatting up a stranger from Kentucky is not what these innovators do. Silobreaker’s team sticks close to the verbiage on its Web site. But I did pull out some interesting nuggets. To wit:
- The system is more than six years old with significant investment in information retrieval research and productization
- The purpose of the system is to go beyond traditional search and aggregation engines with what is called “relational analysis”.
- The indexing is able to generate “contextual insight”. If you opt to use the results list, these are relevant and filtered with more data available with a mouse click. No visit to the search box is required.
- The system recognizes people, companies, topics, places and keywords; understands how they relate to each other in the news flow, and puts them in context for the user.
- The system can handle a range of content; for example, public content and a licensee’s own information.
The company, despite its reluctance to talk with me, has a Web log here.
With the media drooling over Twine, Powerset, and Hakia, you probably will find these comments surprising. So be it.
- Silobreaker is what end users like me want. It presents meaningful, actionable information in a form that suits my particular information needs. I can have a default general display of what’s important now, or I can specify in a Trends option. No handcuffs.
- The system does work for me. When I am looking for information on a topic like Google Forms, I want the names of the people at Google who are associated with this concept. Silobreaker delivers. Period. Most of the hot new systems demonstrated to me don’t at this time do this work for me.
- The system shows me what I need to know. This may not be the Holy Grail for you, but it’s darn close for me.
In closing, keep in mind that the dismal state of enterprise search is a reflection of the dissatisfaction two-thirds of the users of these systems have for search. The quicker Silobreaker and companies like it put pressure on the Big Names in enterprise search, the happier the users will be and the more quickly I can get out of the business of trying to make a wounded duck fly like an eagle.
Check out Silobreaker. Better yet, license the system and start using information instead of the search system using you to do the work.
Stephen Arnold, May 21, 2008