Yesterday , I attended a seminar on CHAT BOTS , conducted by Beerud Sheth ( www.GupShup.io )
Leaving aside the technical part ( which was beyond me ) , I realized that the time has come for some of my ideas , which I jotted down , way back in Jan 2007 , in the margins of the book :
ARTIFICIAL INTELLIGENCE APPLICATION PROGRAMMING ( M. Tim Jones )
I believe , someday soon , either some start up in the Online Recruitment space or one of the major Job Portal ( Naukri / MonsterIndia / TimesJobs / LinkedIn ), will implement these ideas
I have no doubt , Beerud ( email@example.com ) would be able to create appropriate BOTs for each of these ideas ( and , even make these BOTs talk to each other ) , for a few thousand dollars !
I wonder why people are worrying about ROBOTS replacing humans in distant future
To me , the issue is : How many human jobs, will BOTS take away in near future ?
For Recruiters / Headhunters , that answer lies on Pages 142 / 300 /388 !
· We are planning that “ weights “ of each keyword gets automatically adjusted / updated dynamically , with arrival of each new resume in our database . We only provide the “ seeds “ – the starting weights . Inputs are “ Keywords “ / Outputs are “ Raw Scores “
· This would be of interest to us . Job Advts posted ( on any job site ) are nothing but expressions of a Company’s “ staffing requirements “ .
If we have 5,000 job advts for a given Company ( over past 3 years ), we should be able to find a time-series / trend and should be able to predict its “ future “ requirements . Simplest is extrapolation of past trends !
· We have talked of a concept like Rubik’s Cube , to place ( ie; bring together ) on each “ Face “ , keywords belonging to a given “ Skill “ or “ Function “
· Goal = Getting all “ same coloured “ keywords ( squares ) onto the same face of the cube
· Path = Time taken ( shortest )
· Each “ face “ of our Virtual Rubik Cube , would have same colour , if someone succeeds in virtually “ rotating “ the layers along the 2 AXIS of freedom , until all squares are of SAME COLOUR – meaning that all squares contain Keywords belonging to SAME SKILL
· We can “ time “ the game , to see which visitor ( WHO ) , manages to get ALL keywords ( squares ) on the SAME face in the shortest possible time ; then give him recognition / credit by publishing his name on our web site
· This could be a lot of FUN – and could, possibly draw a lot of young kids to our web site !
There will be no login / registration for playing the game . Just walk in and play . Then upload the COMPLETED / SUCCESSFUL image ( with time taken ) and email to all friends to prove your cleverness ! [ 06 JAN 2007 ]
· Particles = Keywords
· Space = Text Resume
· Best found solution = Resume with highest score
· Better one = Addition / deletion of “ which “ & “ how many “ keywords , would result in a Raw Score better than the “ best found “ solution / resume ?
· What keywords ( elements ) are always found “ together “ ?
· Is one resume , a “ solution space “ in which particles ( ie; Keywords ) are swarming around ?
· Set of data = Master set of 5,000 keywords
· Smaller set = Function-wise sets of 100 keywords
· Classification = “ Skills “ & “ Functions “ are Classifications
· Read my notes on “ Expert Systems “ / eg: finding keywords which have NEVER occurred before in ANY resume .
How will software “ Know “ that it is a NEW keyword ?
– and then know “ to which new Skill / Function “ does it belong to ?
· Clusters are , Functions / Skills / Cities / Designation Levels / Edu Qualifications / Experience etc
· Customer Set : Obviously , WIPRO / Infosys / TCS / Satyam , belong to a well-defined “ customer set “
. They all have “ Common Attributes “ , ie : similar / identical job advts posted / similar / identical , resumes searched
· Each “ sub set “ can be ,
# same SKILL / same FUNCTION / same CITY / same EDU etc
· Corporates are “ purchasing “ resumes from job portals and we will have exhaustive data on their “ purchases “ , ie : Number / Type of resumes transferred to folders / opened / viewed
· We are planning a “ Recommendation System “ – which would recommend job advts to jobseekers and resumes to Recruiters
· If Wipro HR manager shortlisted / interviewed such and such candidates , same could also be of interest to Infosys HR manager
· A learning component to identify new rules = I have written some rules
· This is what we are interested in. Starting with ( may be ) 50 rules on recruitment ( getting selected / getting appointed ) , we want the algorithm to discover 500 “ NEW RULES “
· Can we develop an “ AGENT “ ( ant ) for each corporate subscriber’s each job advt., which travels to “ distant places “ ( different job sites ) , and safely bring back “ food “ ( resumes ) to its own “ nest “ ( folder ) ?
· Millions of “ ants “ ( software agents ) , let loose on Web Network, each programmed to find a “ specific “ type of resume – then , when it finds , passing on this data to the next ( adjoining ant / agent ), ie; communicating
Then becoming free again to search for next resume for which it is programmed
A resume may pass from one agent to another ( may be several hundred / thousand ) , till it finally gets received by the ANT / AGENT , who is “ programmed “ to find it in the first place !
So , it is not necessary that an AGENT ANT finds only that resume for which it is programmed , as long as it finds any ONE resume , from ANYWHERE & communicates ( passes onto the next / adjacent Ant )
Like Packet Switched Network ?
All packets getting assembled by the DESTINATION ANT
Parameters stored getting matched with arriving resume’s parameters
· In GURU-JEM ( improved version of HARVESTER ) , we are trying to find web records containing Company Name / Designation,
But from a single source ( viz: Google )
Our software agent travels to Google , finds and brings back the results ( food )
But , could we possibly design / devise , millions of software agents , each programmed to roam the Web ( or , predetermined URLs ) and find,
# One of the thousands of “ designations “ , OR
# One of the thousands of “ Company Names , OR
# One of the lakhs of “ Executive Names “ , OR
# Any combination of the above ,
Then bring back the results ?
· Since most job sites permit access to “ Job Advt Database “ to any visitor without need for a Password, it may be much easier for ANT AGENTS to roam job sites ( like Search Engine Spiders ? ) and bring home suitable Job Advts ( what we do in a limited manner )
· Game = Online Recruitment / Searching for Employers / Searching for Candidates
· Characters = Recruiters / Jobseekers
· Agents = Job Advts / Resumes
· Environment = Virtual Job Fair / Virtual Employment Portal
· I believe Cyril used such an algorithm, to read a plain text resume . The software did manage to accurately “ find “ the “ Address “ ( from anywhere in the resume ), after about 72 hours of continuous “ exploring / processing / learning “
This was nearly 8 years ago . I am sure by now , far more powerful neural-net “ Shells “ can be freely downloaded , which would “ parse “ a plain text resume to find accurately, ALL the “ fields / values “ which we need to create a “ Structured Database “
It is simply a question of experimenting and now , we have no shortage of hardware [ 07 JAN 2007 ]
· Someday ( when we have a million resumes on our web site ), we will have many sub-sets of candidates who started their careers ( first job ) ,
# at the same AGE , and with
# the same EDU QUALIFICATION
Question is : How did their careers “ Evolve “ ?
What Salary / Designation , did each of them reach / achieve , after 5 years / 10
years / 15 years ?
Was there a “ pattern “ ?
Did their “ career paths “ run “ parallel “ or did they diverge ?
What other “ factors “ ( eg: Employer Companies ), influenced such divergence ?
Did some “ plateau out “ after a time whereas others continued to climb the
Designation / Salary ladder ? ( Graph drawn to illustrate the concept )
· With an ever-expanding set of “ Rules “ , it will be possible for a “ Rule-based “ system to detect fake / fudged resumes , where a candidate is telling a lie re: some facts
· I have listed several such rules . See my notes in “ Expert System “ . Also my handwritten notes in the margin of book , “ EXPERT SYSTEMS “
· In each resume , each & every field-value is a “ FACT “ .
Therefore , facts are , Age / Experience / Designation Level / Edu Quali / City / “ Skill Keywords “ found / Salary / Employer Name etc
· One can start with simple rules such as
# Experience ( years ) cannot exceed Age
# Age cannot be less than 16
# Edu Quali cannot be less than 10th Std / SSC
# MD ( Managing Director ) cannot be less than GM ( General Manager )
# Post-Grad cannot be less than Graduate
# Salary cannot be less than Rs 1000 pm
· In developing Function Profile grphs, we are simply depending on “ presence “ or “ absence “ of any given Keyword ( Binary Status ) .
Then assigning a “ weightage “ ( of a given amount of weightage of ZERO ) , depending upon present or absent
But in real world, it may turn out that the Candidate with a lower Raw Score ( because of many “ absent “ keywords ) , turns out to be a better choice ( higher interview-score in Interactive Interview Tool ) , than a candidate with a higher Raw Score ( where most Keywords were present )
In such a scenario , should we try out “ Fuzzy Logic Algorithm “?
· Author’s note : Consider an email program that monitors the behaviour of the user. When e-mail message arrives, the model observes what the user does with the e-mail message and uses this information to learn how to automatically deal with subsequent e mail message
My comments : Beysian spam filter ? – based on a starting database of “ unwanted “ keywords in the e mail message
· We must experiment with Kurzweil’s Paraphrasing Software
· Could Kurzweil’s “ Paraphrasing Software “ be based on this ? See web site of Kurzweil .
Using this can we “ re-write “ a resume ( lilke creating a step brother ), from a given “ Sample Resume “ ?
If such “ paraphrasing / re-writing “ of resumes can be done online ( automatically ) on our web site , then we could add one more element of FUN – even if the re-written resume contains some absurd text ! In fact , such “ absurdity “ may lend an element of FUN ! [ 07 JAN 2007
· If we succeed in paraphrasing / re-writing a text resume online, we could also generate / develop a “ Subliminal / Subconscious “ function profile graph ! ( - since keywords would have got changed ) . This could be fantastic !
· Eg : Agents of Jobseekers negotiating Salary / Terms etc with Agents of Recruiters
· Virtual Job Fair will be / can be a “ Negotiating Platform “ for
# Buyers’ Agents ( Recruiters )
# Sellers’ Agents ( Jobseekers )
· Only yesterday we discussed that in “ Post Jobs “ form ,recruiter will add,
# Put in my folder, all future/incoming resumes having percentile score of > xyz
Now he has created an AGENT which checks incoming resumes daily & puts into folder “ Resumes of Interest “ – also an email will go out to the recruiter concerned ( alert )
24 June 2017
www.hemenparekh.in / blogs