top of page

AI Use Case

Recognise unstructured text, e.g. handwriting, in documents to extract information to streamline processes like account creation, loan and insurance origination and documentation

Recognise documents (eg handwriting) to extract information to streamline functions like account creation, loan and insurance origination and documentation. This is especially useful with high volume consumer products.

Function

Operations

General Operations

Benefits

Revenue - Sales effectiveness improvement,Data - Text mapping,Operational - Process speed up

Case Studies

Metlife~Metlife reduces document processing time by 40% by automating data capture from manual documents,US Food and Drug Administration (FDA)~US Food and Drug Administration (FDA) automates conversion of manually submitted forms to digital format with 91% accuracy using deep neural networks,Dropbox~Dropbox's in-house OCR system for document scanning outperforms commercial libraries by using neural networks ,Amazon~Amazon announces its Comprehend Medical platform to analyse unstructured medical texts,New York Times~The New York Times automates historic photo content identification and detail extraction with Google computer vision,King's College London~King's College London researchers automate real-time triage of X-ray radiograph reports with high accuracy,Roma Tre~Researchers at Roma Tre to analyse and transcribe historical documents from the Vatican Secret Archives using deep learning

Potential Vendors

Captricity,Captricity,Amazon,Google Cloud

Industry

Financial Services

Banking

Data Sets

Text,Images

AI Technologies

Product - Optical Character Recognition (OCR),Machine Learning (ML),ML Task - Prediction - Annotation,Model Architecture - Convolutional Neural Network (CNN),Algorithm - Support Vector Machine (SVM),Model Architecture - Deep Neural Networks,ML Task - Prediction - Multi-class Classification

bottom of page