Intelligence is an ability of a system or an individual to adapt, learn and evolve. The new generation of software solutions are no more JUST task executors but are expected to comprehend large scale dynamically generated information and make intelligent decisions. Such a system would be highly responsive to the changes in its surrounding ecosystem.
The core motivation behind realization of FIKS was to develop a modularized, flexible, self-learning and intelligent analytical framework which can be easily integrated into any software solution. FIKS is a multilayer, multidimensional framework with rich set of sophisticated features. The framework can be applied to build analytical models in wide range of domains including ecommerce, bioinformatics, life sciences, litigation, entertainment, finance, logistics and social media.
Following are the some of the salient FIKS feature:
Social Media Connectors: Social media has defined new horizons to connect people across global leading to extensive ease of information sharing and along with it bringing a new set of challenges and exciting opportunities. FIKS provide a wide range of connectors to consume data from various social media web services like Facebook, LinkedIn, Twitter, Google Buzz etc. But not just limited to these, as FIKS provide easy means to plug in any new media service depending upon application domain. For instance for Life science there are customized media connectors such as PDB and BLAST.
Information Collector: Web provides abundance information which plays a crucial rule in enriching the user experience if integrated in custom software solution. It as well assists in making smart, informed decision making. FIKS allow crawling the web using the web linkage graph and download vast amount of data of varying media formats. FIKS has aggregation capability for external information sources as well.
Distributed Computing: Ease of access to information and ability to conveniently share the same has resulted in exponential rise in data which needs to stored, processed and retrieved within a constrained time limit. At the same time the generation and inflow of data continues to grow at a significant high rate. Under such circumstances, we desire a system which is easily and effectively scalable in real time. Scalable solutions need to take under consideration concerns not only related to managing large data but as well as to have distributed computing grid in place that is effective in delivering. The computational grid is made of low end cost effective hardware which scale and adapt linearly to any change in the system.
Natural Language Processor: The large amount of information publicly available over web is in multilingual natural language form. This demands a deepening need for digital devices such as computers and mobiles to understand human languages. The application of the same may vary from sentiment analysis, language translation, document summarization, Named Entity such as Person/Place/Company name identification, Key concept generation etc. Sophisticated graphical language models Conditional Random Fields (CRFs), Maximum Entropy Markov Models (MEMMs) are used for Part-of-Speech (POS) tagging, Noun-Verb phrase identification and text context analysis.
Text/Data Mining and Statistical Machine Learning: At root of all intelligence lies an ability to learn from past experience and use the same to make decisions. In machine learning the fundamental philosophy is to provide machines with historical data to learn from and train them to make sophisticated decision similar to that of human capability. Though human brain can make intelligent circumstantial decision, it does fail to scale when number of parameters needed are large in number. Machine learning algorithms provide ability to build statistical model over sufficiently large data set that can assist human in decision making. Machine learning can be broadly classified in supervised and unsupervised learning models.
Ontology Engine and Semantic Analytic: Ontology is a representation of knowledge though concepts and relationship shared between the concepts. Ontology endeavours to represent a system or a domain to its completeness. A system which is enlightened with domain knowledge through ontology can be used to derive complex inferences which are impossible to deliver otherwise. There are several ontologies which are being developed by various research institutes and companies in the areas of medical science, patent classification, life sciences, retails marketing, word-net, concept-net that can be integrated in solution in accordance with the domain requirement.
Recommendation Engine: It’s quite interesting to observe that human interaction on various topics such as movies, music, or for the matter job profile or research paper is heavily influenced and prominently motivated by similarity and recommendations. Fascinating intelligent systems can be developed that can smartly recommend books, movies, music, tools, jobs, research papers or gifts online by capturing user’s virtual behavioural pattern, historical information and their similarity with other users across online community.. Recommendation engine lies at the core of several domain, applications and technology which inherently desires intelligent decision making capability.
Profile Processor and Log Analyzer: Recommendations are highly personalized for individual preferences and tastes. The prominent pointers to infer preference is to analyze the user profiles and derive features which are indicators of user likings and dislikes. Alternately, tracking the user behavioral pattern thorough log analysis over substantially long period of time provides with enough information to predict and identify user preference.
Inference Engine: FIKS has built in inference engine. Inference allows discovering knowledge which may not be explicitly available. Inference engine can be effectively integrated with ontologies and can be chained in forward or backward directions to derive complex conclusive decisions. Inference is many a times rule based, functioning over complex graph networks and continuously pumps new relations.
Query Processor: An incoming query can require the information to be extracted and retrieved from the various layers of the FIKS stack. The query can itself go through layers of pre-processing before being used for data retrieval. FIKS allow to query through analytical results and reports.