Machine learning is the science of getting computers to act without being explicitly programmed. In the past decade, machine learning has given us self-driving cars, practical speech recognition, effective web search, and a vastly improved understanding of the human genome. Machine learning is so pervasive today that you probably use it dozens of times a day without knowing it. Many researchers also think it is the best way to make progress towards human-level AI.

Smart Ticket Routing - A Machine Learning model which predicts correct assignment group for the tickets by using their ticket descriptions.

The usecase is that to predict the correct assignment group using machine learning algorithms. So, it is a classification problem. We used Python Scikit-Learn's LinearSVC algorithm for this prediction.

• Input - Ticket Description (Text)
• Machine Learning Model - Python Scikit-Learn - Classification problem - Support Vector Machine (SVM)
• Output - Assignment Group (Category)
• Potential savings per year - ~$385K
• Client - Netherland based Pharmaceutical company
• Service - Predictive System

NLP is a way for computers to analyze, understand, and derive meaning from human language in a smart and useful way. By utilizing NLP, developers can organize and structure knowledge to perform tasks such as automatic summarization, translation, named entity recognition, relationship extraction, sentiment analysis, speech recognition, and topic segmentation.

Entity identification - Identifying the entities like person name, date, phone numbers and so on from the user's query.

The usecase is that to find the user's context and do actions what user's requested.

• Input - User query (Text)
• NLP Engine - Python NLTK - Stanford NLP - Regex
• Output - Entities (Values)
• Service - NLP Engine

Python is a great and friendly language to use and learn. It fun, and can be adapted to both small and large projects. Python will cut your development time greatly and overall, its much faster to write Python than other languages.

Web Application - Using Python Flask Framework - A web microframework written in python.

The usecase is that to create a web application (chatbot from scratch) using web technologies like HTML, CSS, JS, Jquery, AJAX (Client Interaction) and also with Python Flask (Server Interaction).

• Machine Learning - Classification - Support Vector Machine (SVM) - Intent Classification
• Service - Chatbot as web application

A chatbot is a service or tool that you can communicate with via text messages. The chatbot understands what you are trying to say and replies with a coherent, relevant message or directly completes the desired task for you.

FAQ Bot's - A bot which will help users for their questions learned from pre-built knowledge base.

Self-Heal Bot's - A bot which will help users for updating or checking data in database.Mainly data related actions

All these bots are integrated and tested with ticketing tools like ServiceNow, JIRA and BMC Remedy. It has the capability to create tickets if anything is in out of scope.

• Input - User Query (Text)
• Machine Learning Model - Python Scikit-Learn - Classification problem - Intent identification
• NLP - Python NLTK - Entity identification
• Output - Relevant response (Text/Speech)
• Potential savings per year - 30% Cost Reduction
• Client - US based Engineering company
• Service - AI - Chatbot Support

Text analysis is about parsing texts in order to extract machine-readable facts from them. The purpose of text analysis is to create sets of structured data out of heaps of unstructured, heterogeneous documents.The process can be thought of as slicing and dicing documents into easy-to-manage and integrate data pieces.

Did N-gram text analysis for different clients to find any automation opportunities from their ticket descriptions.

Normally generates wordcloud graphs and n-gram words to find any patterns and relations in data.

Tools used - IBM Watson Analytics, Custom build application for generating graphs, N-grams and wordclouds

• Input - User Query (Text)
• Machine Learning Model - Python Scikit-Learn - Clustering problem - Birch Algorithm
• Output - Cluster words - N-gram words - Wordclouds
• Potential savings per year - ~5 New Automation Ideas
• Service - Automation Assessment

Beyond the human brain. Humans have long sought ways to expand the capabilities of the human brain. By bringing together a variety of artificial intelligence (AI), robotics process automation, and emerging capabilities, cognitive automation enables organizations to emulate and enhance the strength of the human mind.

Our system will go through automation assessments for finding any automation opportunities in workflows. If any process to automate, using RPA tools, Machine Learning we will automate and reduce the process costs

Mostly happens using basic python scripts like generating text analysis graph PPT's and also doing Volumetric analysis for huge data.

Tools used - Python and enterprise RPA tools.

• Output - Automation Usecases
• Service - Automation Assessment

OpenALPR is an open source Automatic License Plate Recognition library written in C++ with bindings in C#, Java, Node.js, Go, and Python. The library analyzes images and video streams to identify license plates. The output is the text representation of any license plate characters.

Developed the customized version of opensource OPENALPR, which will recognize vehicle plate number, vehicle color, vehicle make and model year.

Plate infos added in Beanstalk queue are fetched to mysql db. Physical plate images generated from openalpr are added directly to s3 buckets for showing in UI dashboard developed dedicately for tracking purpose.

Increased plate recognition accuracy by retraining OCR and Detector using huge high resolution plate images.

Tools used - Opensource OPENALPR, Python, Mysql Db, S3 bucket.

• Output - Automated Vehicle Tracking System
• Service - Customised Opensource OPENALPR