1/12/1996
ARDIS = Automatic Resume Deciphering Intelligence Software
ARGIS = Automatic Resume
Generating Intelligence Software
What are these Softwares ?
What will they do ?
How will they help us ?
How will they help our Client /
Candidates ?
ARDIS
-
This software will breakup / dissect a Resume
into its different Constituents, such as
a.
Physical information (data) about a candidate
(Executive)
b.
Academic information (data) about a candidate
(Executive)
c.
Employment Record (Industry-Function – Products/Services
wise)
d.
Salary
e.
Achievements / Contributions
f.
Attitudes / Attributes / Skills / Knowledge
g.
His preferences w.r.t Industry/Function/Location
In fact, if every candidate was to
fill-in our EDS, the info would automatically fall into “proper” slots/fields
since our EDS forces a candidate to “dissect” himself into various
compartments.
But,
Getting every applicant/executive
to fill-in our standardised EDS is next to impossible – and may not be even
necessary. Executives (who have already spent a lot of time and energy
preparing/typing their biodatas) are most reluctant to Sit-down once more and
spend a lot of time once again to furnish us the SAME information/data
in our neatly arranged block of EDS. For them, this duplication is a WASTE OF
TIME ! EDS is designed for our (information – handling / processing /
retrieving ) convenience and that is the way he perceives it ! Even if he is
vaguely conscious that this (filling in of EDS) would help him in the
long-run, he does not see any immediate benefit form filling this –
hence reluctant to do so.
We too have a problem – a “Cost /
Time / Effort”
If we are receiving 100 biodatas
each day (this should happen soon), whom to send our EDS and whom NOT to ?
This can be decided only by a
Senior Executive/Consultants who goes thru each & every biodata daily and
reaches a Conclusion as to
-
Which resumes are of “interest” & need
sending an EDS
-
Which resumes are margined or not-of-immediate
interest, where we need not spend time/money / energy of sending an EDS.
We may not be able to employ a
number of Senior/Competent Consultants who can scrutinise all incoming
bio-datas and take this decision on a DAILY basis ! This, itself would be a
costly proposition.
SO,
On ONE HAND
-
We have time/cost/energy/effort of sending EDS
to everyone
On OTHER HAND
-
We have time/cost of Several Senior Consultants
to Separate out “chaffe” from “wheat”.
NEITHER IS
DESIRABLE.
But
From each biodata received daily,
we still need to decipher and drop into relevant slots/fields, relevant
data/information
OUR REQUIREMENT
NEEDS
-
Match a candidate’s profile with “Client
Requirement Profile” against specific request
-
Match a candidate’s profile against hundreds of
recruitment advertisements appearing daily in media (Job BBS.)
-
Match a candidate’s profile against “specific
vacancies” that any corporation (client or not) may “post” on our vacancy
bulletin-board (unadvertised vacancies).
-
Match a candidate’s profile against “Most likely
Companies who are likely to hire/need such an executive”, using our CORPORATE
DATA BASE, which will contain info such as
PRODUCTS
/ SERVICES of each & every Company
-
Convert each biodata received into a
RECONSTITUTED BIO-DATA (converted bio-data), to enable us to Send it out to any
client/Non-client organisation at the click of a mouse.
-
Generate (for commercial/profitable
exploitation) Such bye-product Services as
·
Compensation Trends
·
Organisation Charts
·
Job Descriptions etc. etc.
-
Permit a candidate to log-into our database and
remotely modify/alter his bio-data
-
Permit a client (or a non-client) to log into
our database and remotely conduct a SEARCH.
ARDIS is required on the assumption that far a long
time to come, “typed” bio-datas would form a major source of our database.
Other Sources, such as
-
Duly filled-in EDS. (hard-copy)
-
EDS on a floppy
-
Downloading EDS over internet (or Dial-up phone
lines) & uploading after filling-in (like Intellimatch)
Will continue to play a minor
role in foreseeable future.
HOW WILL ARDIS
WORK?
KEY-WORDS
TO recapitulate
ARDIS will,
-
Recognise “characters”
-
Convert to “WORDS”
-
Compare with 6258 Key-w which we have
found in 3500 converted bio-datas (using ISYS). If a “word” has not already
appeared (< 10 times) in these 3500 bio-datas, then its chance (probability)
of occurring in the next biodata is very very small indeed.
BUT even then,
Ardis Software will store in memory, e ach “occurrence” of
each word (old or new, first time or a thousand time)
And
will continuously calculate its “probability of occurrence”
as
P= No. of occurrence of the
given word sofar
Total no. of
occurrence of all the words in the entire population sofar
So that,
-
By the time we have SCANNED, 10,000 bio-datas,
we would have literally covered all words that have, even a small PROBABILITY
of OCCURRENCE !
So with each new bio-data “Scanned” the probability of
occurrence of each “word” is getting more & more accurate !
Same logic will hold far
-
KEY PHRASES
-
KEY SENTENCES
The “name of the game” is
-
PROBABILITY OF OCCURRENCE
AS Someone once said,
If you allow 1000 monkeys to keep on hammering keys of 1000 typewriters
for 1000 years, you will at the end, find that between them, they have
reproduced’ the entire literary-works of Shakespeare!
But to-day, if you store into a Super-Computer,
-
All the words appearing in English language
(incl.-verbs/adverbs/adj. etc.)
-
The “logic” behind construction of English
language
Then,
I am sure
the Super-Computer could reproduce the entire works of Shakespeare in 3 months
!
And, as you would have noticed, ARDIS is a Self-learning
type of software. The more it reads (Scans), the more it learns (memorises,
words, phrases & even sentences).
Because of its SELF_LEARNING / SELF-CORRECTING/
SELF-IMPROVING Capability,
ARDIS gets better & better equipped, to detect, in a
scanned biodata
-
Spelling mistakes (Wrong Word)
-
Context “ (Wrong
prefix or Suffix) – wrong PHRASE
-
Preposition “ (Wrong Phrase)
-
Adverb/Verb “ - Wrong Sentence
With minor variations,
All thoughts, words (written), Speech (Spoken) and actions,
keep on repeating again and again and again.
It is this REPETITIVENESS of words, phrases & Sentences
in Resume’s that we plan to exploit.
In fact,
By examining & memorising the several hundred (or
thousand) “Sequences” in which the words appear, it should be possible to
“Construct” the “grammar” i.e. the logic behind the Sequences. I Suppose, this
is the manner in which the experts were able to unravel the “meaning” of
hierographic inscriptions on Egyption
How to build directions of “phrases” ?
From 6252 words, let us pick any word, Say
|
Now we ask the Software to scan the directory containing
3500 converted bio-datas, with instruction that every time the word
“Achievement” is spotted, the software will immediately spot/record the prefix,
The software will record all the words that appeared before “Achievement” as
also the “number of times” each of this prefix appeared.
 |
|||
 |
|||
e.g.
1. Major 10 10/55 =
2.
Minor 9 9/55/ =
3.
Significant 8 8/55/ =
4. Relevant 7 7/55 =
5. True 6
6. Factual 5
7. My 4
8. Typical 3
9. Collective 2
10. Approximate 1
Total
no. of = 55 = 1.0000
Occurrence
As more & more bio-datas are
Scanned”
-
The number of “prefixes” will go on increasing
-
The number of “occurrences” of each prefix will
also go on increasing
-
The overall “population-size” will also go on
increasing
-
The “probability of occurrence” of each prefix
will go on getting more & more accurate i.e. more & more
representative.
This process can go on & on (as long as we keep on
scanning bio-datas). But “accuracy-improvements” will decline/taper-off, once a
sufficiently large number of prefixes (to the word “ACHIEVEMENT”, have been
accumulated. Saturation takes place.
The whole process can be repeated with the words that appear
as SUFFIXES” to the word ACHIEVEMENT, and the probability of occurrence of each
Suffix also determined.
1.
Attained 20 20/54 =
2.
Reached 15 15/54 =
3.
Planned 10 10/54 =
4.
Targetted 5
5.
Arrived 3
6.
Recorded 1
54 1.000
(population-size of all the occurrences)
Having figured – out the
“probabilities of occurrences” of each of the prefixes and each of Suffixes (
to a given word – in this case “ACHIEVEMENT”), we could next tackle the issue
of “a given combination of prefix & suffix”
e.g. What is the probability of
-
“major” ACHIEVEMENT
“attained” -------
Prefix suffix.
What is all of this statistical exercise
required ?
It we wish to stop at merely deciphering
a resume, then I don’t think we need to go thru this.
For mere “deciphering”, all we
need is to create a
KNOWLEDGE-BASE
of
-
Skills - Functions
-
Knowledge - Edu-Qualifications
-
Attitudes - Products / Services
-
Attributes - Names
-
Industries
-
Companies
etc.
etc.
Having created the knowledge-base,
simply scan a bio-data, recognise words, compare with the words contained in
the knowledge-base, find CORRESPONDENCE / EQUIVALENCE and allot/file each
scanned word into respective “fields” against each PEN (Permanent Executive
No.)
PRESTO !
You have dissected & stored
the MAN in appropriate boxes.
Our EDS has these “boxes”. Problem
is manual data-entry The D/E operator,
-
Searches appropriate “word” from appropriate
“EDS Box” and transfers to appropriate Screen.
To eliminate this
manual (time-Consuming operation) we need ARDIS.
We already have a DATA-BASE of
6500 words.
All we need to do, is to write
down against each word, whether it is a
-
Skill
-
Attribute
-
Knowledge - Location
-
Edu. -
Industry
-
Product - Function
-
Company etc. etc.
The moment we do this, what was a
mere “data-base” becomes a “KNOWLEDGE-BASE”, ready to serve as a “COMPARATOR”.
And as each new bio-data is
scanned, it will throw-up words for which there is no “Clue”. Each such new
word will have to be manually “categorised” and added to the Knowledge-base.
Then what is the advantage of calculating
for - each word
- each prefix
-
each suffix
-
each phrase
-
each sentence
Its probability of occurrence?
The advantages are:
# 1 – Detect “unlikely” prefix/suffix
Suppose ARDIS detects
“Manor Achievement”
ARDIS detects that the probability
of
-
“Manor” as prefix to “Achievement” is NIL
-
“Manor” as prefix to “Achievement” is 0.00009 (Say
nil)
Hence the correct prefix has to be
-
“Major” (and not “Manor”) for which the
probability is say, 0.4056.
# 2
ARDIS
detects
MR. HANOVAR
It recognises this as a spelling
mistake and corrects automatically to
Mr. HONAVAR
OR
It reads.
Place of Birth: KOLHAPUR
It recognises it as “KOLHAPUR” or vice
versa, if it says my name is: KOLHAPUR
# 3
Today, while scanning (using OCR),
When a mistake is detected, it gets highlighted on the screen or an asterisk
/underline starts blinking.
This draws the attention of the
operator who manually corrects the “mistake” after consulting a dictionary or
his own knowledge-base.
Once ARDIS has calculated the
probabilities of Lakhs of words and even the probabilities of their “most
likely sequence of occurrences”, then, hopefully the OCR can Self-Correct any word
or phrase without operator intervention.
So, the Scanning accuracy of OCR
should eventually become 100% - and not 75% - 85% as at present.
# 4
Eventually, we want that
-
a bio-data is
Scanned
and automatically
-
reconstitutes itself into our converted BIO DATA
FORMAT.
This is the concept of ARGIS
(automatic resume generating intelligence Software)
Here again the idea is to
eliminate the manual data-entry of the entire biodata – our ultimate goal.
But ARGIS is not possible without
first installing ARDIS and that too with the calculation of the “probability of
occurrence” as the main feature of the Software.
By studying & memorising &
calculating the “probabilities of occurrences of Lakhs of words/phrase/
sentences, ARDIS actually learns English grammar thru “frequency of
usage”.
And it is this KNOWLEDGE-BASE
which enable ARGIS to reconstitute a bio-data (in our format) in a
GRAMMATICALLY CORRECT WAY.
1/12/1996
