2.1 Introduction

Knowledge Discovery in Databases is the organized procedure of recognizing valid, useful, and understandable patterns from huge and complex data sets. Data Mining is the root of the KDD procedure, including the inferring of algorithms that investigate the data, develop the model, and find previously unknown patterns. This microservice is used for extracting the knowledge from the data, so that it could further be analyzed for generating predictive models. It is currently supported for text data

QpiAI Pro KDD Microservice offers a wide range of text data mining pipeline for processing and extracting the information hidden between large document repositories or text corpuses. Extracting the information like named entities mentioned in the documents, classify the entities to common topics for better understanding, learning the relationship between any two entities which will be further used for developing more insights. Summarization pipeline envisions the extraction of important insights from the document or text data and returns the short abstract of the documents. Document clustering allows to automatically bring out the indent between the documents and categorize into different clusters based on the spatial representations of the model. OCR is a powerful document conversion tool which supports extraction of digital information like text and tabular data from the scanned image or pdf documents.