Intelligent Software Agents (II)

Nick Morakitis wrote a nice paper in the heydays of the  Intelligent Software Agents: “Intelligent Software Agents Application and Classification“. And what is better it comes under the section “Where Can Intelligent Agents be Used in Travel Reservation Systems?” of the Surprise 97 conferences in the Imperial College of Science Technology, (May-June 1997).

Nick Morakitis starts saying : The evolution of modern software agent technology has given rise to an extensive overuse of the term agent. The result of this abusive usage of the word agent and the terminology that relates to it, is a great confusion as to what an agent is, what types of agents can be identified, and what are the properties and characteristics with respect to which the aforementioned identifications can be achieved.

Nick makes a summary of the up to date notions of Software Agents, describing the weak and strong definitions of Agents, the classification by their application. The explosive growth of the field was creating endless applications and uses for any subject: Personal Assistants/Organizers, Preferential Information Systems, Financial Decisions, Entertainment, Military, Transport ..

According to his classification, Zentric’s aim of making the Internet more reachable to Users saving much of their time falls into the category of  Interface+Information Agents.  They would be … “Agents focused in autonomy and learning and whose goal is to perform tasks for their owner are called interface agents. Typically, such agents observe the actions of the user, interact with him/her and attempt to learn by imitation, or direct feedback. Their abilities in negotiation are limited and most of their interactions with other agents (if any) relate to receiving advisory information. Interface agents are seemingly smart software pieces that help their owner automate and perform tasks…  and … Information agents are tools that coordinate the retrieval, management, selection and manipulation of information.”

In most of the literature related to IA (Intelligent Agents) I notice the influence of AI (Artificial Intelligence) and its highly aspirational academic style. Great theories about intelligent software , self learning, adaptive to the user, etc. etc. These are deep waters when it comes to creating software that must work and succeed beyond university labs. 

I would drop the idea of building intelligent software. Considering that nobody knows what intelligence is, we’ll have to admit that the term Intelligent Agents is more an aspirational/motivational term, it’s some way of saying that we’re are trying to build something smart, something that would make the User more efficient and his interaction with the software more satisfactory, something that as the relationship advances the efficiency and satisfaction increases thanks to the adaptation of the software to the User.

The next question is whether it would be preferable to build the Zentric Software using the principle of Intelligent Agents. To answer this question I need to find out if there are SDK or platforms that would fit me. So I’ll have to check JADE from FIPA, COUGAAR and the framework of  Carnegie Mellon University.

Intelligent Agents. Nice. Where are they ? (I)

Oh! I’m very late, this quest it’s an old aspiration. I hit the “Intelligent Agents” (IA). Plenty of stuff on Google.

Goal driven, task oriented, smart, mobile, intercomunicated processes, self learners, Agents working for me, exactly. We need lots of them to create the UCI, an intelligent agent to find jobs, another one to find trip deals and so on.

Reading papers mainly of the 90′s  it looked like Intelligent Agents were going to take the Internet in the near future. Beautiful concept and even more beautiful software architecture to implement them, a dream system for programers. They were very exciting years for development of theories and software. I think it was a general enthusiasm in all fields around Internet, many of them were ahead of their time and maybe IA was one of them. By what I see in their websites most of them are discontinued, strangely enough most of them were shading off around 1998. 

So far I have found out three relevant currently active efforts on the field, 1. The Foundation of Physical Agent (FIPA),  2. COUGAAR an Open Source Architecture for large scale distributed multi-agent systems and 3. the impressive work of Katia Sycara at the The Intelligent Software Agents Lab of the Carnegie Mellon University.

Three of them are working for a long time now and have solutions for creating intelligent distributed agent systems. They have many answers to my questions, specially Katia Sycara and her team, have analized , proposed and developed software that could be considered the ground of the User Centric Internet (UCI). 

In the paper  “A Taxonomy of Middle-agents for the Internet,” Katia Sycara and Chi Wong propose the model for the Users or “Requesters” and Providers (let’s say current websites) to communicate through the Middle Agent (MA). This model fits with my view of the UCI.

In another paper called LARKS for short, Katia Sycara and colleges go much further to define a key issue: How to describe an Agent Capability for agents to understand each other of what they offer and therefore other agents know what they and how can they ask for it. 

COUGAAR is extremely interesting for the solutions they offer and the understanding the show of large scale systems as it would be our case in the UCI. We can see their knowledge and experience when talking about the Yellow Pages implementation techniques for the listing of providers.

Three of the case studies I’m talking have their open source to implement multi-agent solutions.

Who is going build the UCI ?

Me. Not. The UCI Paradigm is a major endeavor. It is not a few programmers work, nor a single  company’s.

The User side of the UCI architecture is all to be done, the Service Providers part could be put up to work with less effort if the current WebSite owners would want to open channels to the UCI. It would not be very costly to a current employment of travel website to add the necessary software to connect to the UCI and operate though it.

The User Pod and the Engines have a major work to start to work. An User Pod would have an access from cellulars, computer , TVs .. each of them requiring a different development effort. Different code for the different type of cellulars, a website for the computer .. And then the software for each specialized task, a development for the Job Search Interface, another one for the Travel Deal Search Interface and so on.

It seems to be a work open to the programmers community and open source mega project.

It would be an ever ongoing development to add and improve subjects, languages and efficiency. That’s what Internet is all about anyway.

Architecture of the User Centric Internet

The UCI could be achieved with software, no specific hardware requirements, it would work on whatever hardware technologies the Internet would be working on at any given time. It would only require the definition of the protocols to be used by all the software parts involved. 

The UCI goal is to connect in the most efficient way “requests” with their “answers”, or “demand” with “provider”. The requests can be as broad as life is, and can be done by individuals, groups, companies. Therefore it seems obvious that for every “subject” a specialized software should be built, within the protocols and communication standards defined in the UCI. 

The User Pod

First thing we need are the interfaces for the users to post his requests and get the answers. A “user” being any individual person on his behalf or for a group or company. There should be one single login to all his possibilities in the UCI, a central account to his UCI Pod. The access to the Pod should be possible from any device, cellular, computer, TV .. i.e any device hooked to the Internet. The Pod would contain different specialized interfaces for different purposes as well as a message center, let’s say the Job Search Interface and Travel Deal Search Interface. I described the way to work in the Pod in a previous post “One day in the UCI“.

Service Providers

We need the architecture to answer to the needs of the User, let’s call them Service Providers. They are the ones that would have the answers to the requests of the user are are interested in getting to the User. There would be no limitation in the number of Service Providers in total or for any specific subject, these would usually be the ones that currently have a website in the Web Centric Internet, often with a business model behind their service. They could be  passive or active in their behavior, i.e. they could wait for user requests to come or they could in the search of users.

Users & Providers Directory

The key to connect Users and Providers would be the Directories, where a list of who, and what it requests or offers would be listed. Some kind of Yellow Pages for services and White Pages for Users. 

Engines Connecting it All

And finally the software engines that would connect it all, Users with Users, Users with Providers, Providers with Users. Thanks to the Yellow and White pages the engines would know who, where and how to contact.

What about changing the Internet upside down ?

Hundreds of sites for job search, thousands to find the best trip deal, endless news sites, millions of blogs, countless for shopping …

Is the number going to grow ? Am I missing the best deals because I don’t know the right site ? Am I up to date in ticket fares ? If I disconnect for 6 months will I have to catchup with the new oportunities, technologies, fares, sites , news sources ? 

If I move to another country, another language, do I have to sit for a week to find out what is the site for shopping, car renting, apartment renting, job searching, do I have to adapt not only to a new location but as well to a new cyberlocation ?

I feel like I’m not ready for this game, I run out of usernames and passwords, and if you ask me to change the password every few months then just forget about me.

But still I do feel uncomfortable with the idea of not knowing who is selling the cheapest flights, or not getting informed about that job positions I’m waiting for.

How about changing this Site Centric Internet to an User Centric Internet ? In other words : I don’t want to go to your web site, you come to me. orThis is what I want, anyone ?

This would be a paradigm shift in the use of internet, what I call Zentric Paradigm, where the user becomes the center and not the wanderer around cyberspace.

Now, how could this be done , can it cover all the internet ? Certainly not, I see it as an improvement to a certain type of operations we perform on the internet usually during a medium to large period of time or even indefinite, that could be arduous and time consuming, apartment search, job search, trips, shopping for best deals. Browsing for news, googling, youtubing, chatting .. are like game playing, no automation is wanted.

We need software that would allow us to say what we want, that would go to cyberspace to notify, search, retrieve what we want and come back to us with what we asked for.

Do WebSites Disappear in a User Centric Internet ?

No.

Could some service/goods provider (website) decide to become “hidden” to the Web and use only UCI interfaces to operate ? Maybe.

Could some users live without visiting websites ? Probably yes.

In other words, some websites could decide to be only present through the standard interfaces of the UCI and save the the website UI costs. In the theory of the UCI the standarization for communication between users and providers is necessary, the way an user communicates the needs and the way a providers communicates the services must follow a predefined language. The major part if not all of the search process of the users
could be eliminated in a UCI and that is one of the major roles of the web interfaces; to visually offer the ways to get to the products.

However the provider would be as important as ever, it could as well make more room for more providers where the quality and the price could make the difference instead of the website power or an adverstising campaign. More users could reach to more providers and more pragmatic reasons in the interest of the user can make the difference.

In the same way it is difficult to imagine the end of paper due to the internet, it is not easy to imagine the end of websites. Usually new technologies push old ones to the place it corresponds to them according to the response of the user.

An interesting point is to analize what would happend to adverstising due to a lower user flow to websites. If adverstising efficiencey lowers, it seems a logical consequence that the income will lower. Would a website be interested in opening a channel to the UCI interface which would cause a lower users traffic, lower clicks, lower income ?

Well, it seems to me at this point that the right question is not whether the websites will disapear, but instead, is there any chance for the UCI ?

If it’s true that “in the long run what is best for the user wins” I’m not going to close the blog yet.

One day in the User Centric Internet (UCI)

Let’s try to imagine some examples of use of the UCI. Let’s say we need a new job and as well some vacation in our dream place, both very common needs nowadays. Using our favorite interface (cellular, computer, TV ..) we would log into our Zentric Pod. There we would choose the Job Search interface and create a task defining the job we are searching for, as detailed as possible and finally we would activate the task. We could load one or more CVs as well as standard templates for answering to positions offers.

Same for the trip task, in the Trip Deal Search Interface we would define the destination prefered dates and price range. We could define a task for an inmediate purchase of a flight ticket or a much more heavier task such as finding the best trip somewhere in 4 months from now, without precise dates and with a length from 7 to 10 days.

These two tasks would be active and working 24 h to search and listen the offers available on the internet.  When matches of our request would be found we would get notified in the ways we choose : email, sms, Zentric Pod messsage box, etc.

From the job offer finds we would decide whether we need to refine our search parameters to filter those offers that involve Fortran programming (!) for instance, or to filter the offers coming from a certain fishy employment company. For the positions we are interested in we could ask to send the CV plus a few words, and we could set the “automatic send” of CV to all positions with those characteristics. Eventually when an employer would interested on us it would send us an email or call us.

We could have setup up our ZentricPod with the data to perform purchases. If the Interfaces in ZentricPod would have history record of tasks performed it could help to make much faster the next tasks based on the preferences that we already used in a previoud succesful operation. Say the monthly flight to NY, we know and the ZentricPod could now our prefered ours, airlines and stop by conditions.

All these theories are not new and most of them already implemented in the SCI in different websites where one can find efficiently job positions of trip deals. Remember this journey  to find out if the UCI is possible what involves and its consequences.

The User Centric Internet (UCI)

The fun of wandering around internet, choosing what to watch or read could be much fun, to me better than watching TV. A different thing could be to look for things that we really need, maybe inmediately or during a long period of time requiring tedious search day after day, such as searching for a job or looking for the best trip deal.

The already vast offer of websites for any subject makes it impossible to know all of them and therefore to know if we are using the one that suites us better.  We use the most popular site or the one it worked once for us so stay loyal for convenience, or the one that got all the hype and the snowball makes them number one by far, sometimes out of sheer luck for them.

Many of the lucky ones often become so big that either you are in or you are out of the living. If you’re not in MySpace or Facebook, if you are not Tweeting there is something wrong with you, you’re loosing opportunities, even worst, you are transparent, no one.

I understand the need of exhibitionism in teenagers, but is people in their forties having fun in MySpace, Facebook, Tweeting ? Do you enjoy being in LinkedIn, do you feel better with those recommendations saying you’re an mazing worker and colleague ?  

Next year will be another website to be in, and so on. More bookmarks, more usernames, more passwords.

Getting back to the useful websites, couldn’t I say somewhere what I need, what I’m looking for, what I’m up to and it would be notified into Cyberspace and and all relevant information would come to me ? Instead of signing in to 20 job search websites, and me adapting to them, can’t they get to me ?

This would be a considerable change that could save much of my time, I could reach more while doing less, eventually I could cover everything, doing less. It would be an User Centered Internet, where my requests would become a node that would attract providers and would inform me of what they can offer me.

The Internet is too big already. How is it going to be like in 20 years ?

In the article “How big is the Internet ?” in softpedia.com we can extract that according to Eric Schmidt, Google CEO, the Internet is made up of 5 million terabytes and that Google has succeeded to index only 170 terabytes up until now. The article continues saying tha Google has been indexing information for 7 years and that it would need 300 years to index all there is. Not counting the content that would be generated those 300 years of course.  

So I’m not going to find estimations of what would it be like the Internet in 20 years. There is a pretty tough job there for the future of indexing companies, lots of relevant and rubbish to index, I hope hard disks will get cheaper and cheaper. 

I’m not so interested in the archiving thing though, I’m  mostly interested in the recent data on the disk of the websites we use daily ,  those that hold the  information we need to be up to date, work, buy, travel, communicate, live.

How many websites are there ? According to the same article only from 2005, 17 million have been created. Who would say, I live only with a handful of them, some that I have discovered and some that I have been forced to by media snowballs that have converted them in monster sites. 

Well I’m sure I must be missing some interesting content/ opportunities/ fun in such a large universe of data, but then again who cares, there is too much of too many things in our media consumer brain cells, too many hours on the computer already.

This changed a while ago though, I started to look for a job, through the internet. Suddenly I wanted to know all websites, all job offers in the country, and maybe abroad. When I thought I had all of them a would find another promising website, and another one .. search, sign-in, username, password, set up profiles .. all of them looked like the ones could hold the job for me.

While a broad offer of services is very important and healthy for any economic system something wasn’t working for me there, too much work to find work.

Then I saw that to find the perfect flight or trip could be even worse if I want to make sure I’m getting the best deal, there are countless travel sites, complex to use, highly time consuming, can I go through several sites for hours to  find the best trip ? Too much work, I don’t have the time. 

To how many other areas can we extend this experiences ? Apartment finding, match making, shopping, news .. 

As wonderful as it is to have such variety something seems to me not efficient in the system, there is some disconnection between me and the the ones that make a living of giving me what I want. I would really want to meet them as much as as they want to reach to me, but I’m not sure we’re using the most effective connection.