[ba-unrev-talk] Automated Email-based CHAT-FAQ Expert System
This message encasulates a recent email exchange in which
I thought out more of the concepts involved in an automated,
interactive FAQ system: (01)
Doug wrote: (02)
> I'm always happy to answer questions directly, if it will save people
time.
> I'm glad you asked. (03)
Yeah. It is amazing how what's on the top of your head for one person is (04)
miles away for someone else. Like Eric Raymond wrote on the subject of
open source software: "With enough eyes, all bugs are shallow." (05)
I would absolutely LOVE to work on a system that monitored email
traffic, storing responses to questions, and which made it possible for
people to discover answers through automated queries. (06)
I figure that such a system would make a best try at finding an answer,
but that people would always be involved to interpret the question,
answer it, and make the system smarter. (07)
There is some ontology work using topic maps and the like that would
be spectacularly useful for such an undertaking. My dream job. Good
for a year or two, at least. (08)
Doug wrote: (09)
> Sounds great. (010)
It would be a great project to work on. I'd set it up as a filter
on the company mailing list, with a companion screen that
people could use to modify the ontological underpinnings of the
system. (011)
That way, the automated system could take a stab at replying
whenever it could, saving people from having to repeat themselves
too often. (That would be the idea, at least.) (012)
Clearly, the system has a lot of potential benefit. Who do we know
that would want to fund such a thing? (013)
Doug wrote: (014)
> Nobody else has attempted to solve this problem already?
> I'd love to dump my tips into a system that everyone could
> update/contribute to. (015)
That would be a great place to start building a database of
automatically-
answerable questions. (016)
This is a problem that is poised on the cusp of becoming solvable. There (017)
have been some attempts at intelligent customer service systems, but so
far they have fallen rather flat. (018)
The tack I recommend -- an integrated email conversation with an
answerbot sitting in and being educated, has never really been tried.
It is an approach I have been recommending for most of my professional
career -- that an integrated man/machine systems will always outperform
either one by itself. (019)
Then, too, the recent work on ontologies has a tremendous capability
for expediting such a system. For example, if a user asks: (020)
"I put floppy #2 in the drive, but I need to back up and put in #1
first,
How do I do that?" (021)
With a keyword-driven system, the machine sees "floppy" and
"back up", and gives the user instructions for copying files. Not very
helpful! (022)
But an ontology-based system potentially has the capacity to recognize
the context as "floppy in drive" and the "back up" as meaning "go back
to previous step". It can then deduce that the instructions are: (023)
* put the computer where you can see it
* turn on the lights
* find the slot where you put the floppy in
* press the button on the slot to eject the floppy
* find the floppy labeled "#1"
* insert it (024)
Doug Lenat's cyc system, for example, has enough "common sense" to
know that "back up" means eject, in this case. Even so, capturing the
ontology-information necessary to recognize and successfully answer
a query like that is no easy task. And trying to anticipate every
possible question in advance is both prohibitively expensive and
impractical. (025)
The system I propose would have 4 components:
* Users
who make queries via email (026)
* The AnswerBot
which listens to queries, and which attempts to answer
when it can (027)
* Experts
who answer them when the AnswerBot can't,
or who correct the AnswerBot's misguided attempts
(and who act as users in other areas) (028)
* Ontology Librarians
who add ontology-information that make it possible for the
system to find information it already has, but didn't know
how to relate to the specific query. (029)
One way to do that is by importing the topic map versions of
the stuff Lenat has released. (Some material is free. More
can be purchased.) Another way is by adding additional
ontological structure: For example the fact that "back up"
can mean "go back a step" as well as "copy files", depending
on context. (030)
Note:
Ideally, Experts will answer with pointers into an indexed FAQ,
which will make it easy for the ontology librarians to recognize
that the information already exists. Otherwise, they can capture
the information as a new nugget for the FAQ.
[Purple numbers, anyone?] (031)
In addition to maintaining the ontology library, these folks use
their human intelligence to recognize which reponses were
helpful, and create new info tidbits (nuggets/tips) for the system. (032)
So in a way they are documentation / customer support /
expert-system-administration gurus. (033)