Autonomy and Bayesian Theory – Put on your thinking cap

I think at this year’s LegalTech show in NYC I’m learning more about algebra than I ever wanted to know.  I should have paid better attention in school.  The reason for this is the search engine methods now being employed by several companies one of which is Autonomy.  Autonomy is the London behemoth that recently swallowed up Interwoven, which I had the impression was big in its own right.

One of the representatives from Autonomy handed me a very heavy book entitled Meaning Based Computing. I have to admit that I flipped through it rather than reading it from cover-to-cover, but the gist of it is this. Throw your old search engines away because they ain’t gonna work no more.  Especially not over the rich media that is voice mail messages, video conferences, video and audio depositions, etc and unstructured data.

Maybe it’s not fair to say throw away your old search engines because Autonomy still uses those, like keyword searching, and federated searching and also employs concept searching.  This is where the theory of Thomas Bayes comes in.  Bayes was a mathematician (OK, he probably has a more elaborate title – and he was an English cleric to boot) who came up with a theory of modern statistical probability.  According to the Autonomy book (I’m waiting for the movie to come out), “Bayes efforts centered on calculating the probabilistic relationships between multiple variables and determining the extent to which these relationships are affected when new information is obtained.”

Let’s cut to the chase – concept searching employs this Bayesian method and is able to draw correlations among words and phrases in various types of media and relates them.  Let’s simplify this by saying it’s artificial intelligence that has learning capabilities to make it more effective.  And its kinda scary.

So the Autonomy folks, using their search technology over multiple platforms and almost every byte of data can find stuff for discovery and other purposes that other  search engines and software can’t.  Their product can be proactively used for document management, policy management, compliance, daily workflow, etc. in addition to ediscovery purposes.


~ by CDLB on February 3, 2009.

Leave a Reply

Fill in your details below or click an icon to log in: Logo

You are commenting using your account. Log Out /  Change )

Google+ photo

You are commenting using your Google+ account. Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )

Connecting to %s

%d bloggers like this: