Enclosed find Chapter I & II (upto p.242) from this book.
Since we have decided to diversify into "Webservices", it is important that we learn as much as we can about
Shall we try the bold experiment which I have described on p.5 (Fig. 1.1)?
Self-learning Software
Our goal is to make ResuMine / ResuSearch self-learn & improve with usage.
One way is for them to capture the “Knowledge” of hundreds of Expert-Users.
One opportunity (for self-learning) is to study the “Editing” of structured database by subscribers.
When subscribers find a value missing in any field, they would (hopefully) try to go thru the entire text of email resume to find that missing value.
And, if it does exist (but ResuMine somehow missed it), there is a good chance that the subscriber would find it if he has the patience – and NEED – to capture that value.
Having found the value, he would “insert” it in the appropriate field, then drag & drop or highlight & click or thru whatever method we specify.
Here is our opportunity to learn.
When any subscriber carries out any such “editing”, we must capture:
And we must “aggregate” all such “editing” instances. If we do, following type of scenario might emerge:
Say, “Edu. (Level – Branch – degree shortform)” was found missing in 10,000 resume extractions.
When subscribers search for “Edu” value in resumes, they may find the missing value in 8000 cases & enter it.
Now, if our software tracks these 8000 cases, it may discover that in 6000 (out of 8000) cases, subscriber located/picked-up the value in “PERSONAL DETAIL” block!
Whereas, the logic we have used, looks for “Edu” in “Edu Qualification” block!
Such “discoveries” add to our learning & improving our extraction logic.
In any case, we must offer “Edit” feature FREE to all subscribers (–since we cannot guarantee 100% extraction accuracy) – and encourage them to edit.
Of course, since ResuMine is not a neural network based software, a human developer would be still required to write the “code”, after studying the “patterns” (of locating missing values) that emerge thru aggregation of edits.
WALK THE TALK
We are planning to offer ResuMine/ResuSearch as Web-Service – to be followed by:
-
Ad-Compose
-
OES
-
etc.
Before we start “offering” these (as Webservice), we must ourselves use these for 3 months as WEBSERVICE! It is no good to tell our potential clients that although we do use these systems, we use these OFFLINE!
This would be like Bill Gates asking everyone to use “MS-Office” but Microsoft itself using “StarOffice”!
Or a Heart Specialist asking all his patients to quit smoking & eat vegetarian diet & exercise vigorously, but himself continuing to smoke & eat lots of hamburgers & never getting out of his chair!
What do we need to do to upload on our Webserver:
-
Module 1
-
Search Engine
-
OES
-
etc.?
What are “Cost” implications? What happens to our OFFLINE hardware (Servers/routers?)
No comments:
Post a Comment