in reply to Re: Developing an Expert System/Intelligent Agent for PM?
in thread Developing an Expert System/Intelligent Agent for PM?

Assuming that the docs for infobot are correct, this isn't quite what I had in mind. Stripping away the parts that have to do with interacting with the bot, what you are mostly left with is a hash lookup (that is, given a term X, the bot returns the value of the hash key X); the expert system is only as smart as what people put into it (the factpacks for example), and doesn't 'learn' from when it returns information incorrectly or correctly.


Dr. Michael K. Neylon - mneylon-pm@masemware.com || "You've left the lens cap of your mind on again, Pinky" - The Brain
  • Comment on Re: Re: Developing an Expert System/Intelligent Agent for PM?

Replies are listed 'Best First'.
Re: Re: Re: Developing an Expert System/Intelligent Agent for PM?
by clemburg (Curate) on Jun 20, 2001 at 12:27 UTC

    But infobot works and you can implement a solution based on it very fast. Sure, the "Knowledge Base" is not too intelligent, but the language interface is very well suited to an environment like the CB. Why not start with it and then build a more complex backend?

    My main argument here is that I think the language part is much more difficult than the knowledge part, at least for the "help desk" type of application we have here.

    "the expert system is only as smart as what people put into it (the factpacks for example), and doesn't 'learn' from when it returns information incorrectly or correctly"

    As far as I understand it, the first part of the argument is true for all expert systems, and the second part is mainly about the "elegance" of the feedback mechanism. Infobot learns when people tell it to forget and to learn a new fact instead. This is a simple feedback mechanism, admitted, but given the track record of infobot, it seems to work very well.

    Christian Lemburg
    Brainbench MVP for Perl
    http://www.brainbench.com

      Again, I can only deduce this from the information on that page, and from my past experiences with IRC bots that do similar functions, is that the input is pretty much limited to variations in the way you ask for "What is X?" where X is a term, phrase, or whatever. Sure, this can be easily modified into the CB, but what I'm looking for is a way for people to be able to ask "What is X (some relation to) Y?", which, unless you fully exhaust in the factpacks every relation between X and Y, the bot might fail to answer. In addition, going back to my example of hash slices, there are times when the term may be unknown and to get at the answer, you'd have to know that term. I'm hoping that my system will be smart enough after time that if the user inputs 3 keywords normally associated with a obscure but important keyword, it will deduce that the obscure keyword is what was intended (eg, "merge" "array" and "hash" should lead to "slice").


      Dr. Michael K. Neylon - mneylon-pm@masemware.com || "You've left the lens cap of your mind on again, Pinky" - The Brain