New AI model will speed up document analysis for the banking, financial and insurance industries

Researchers have developed an AI-based solution which can automatically analyse and extract large amounts of information from computer documents.

The team from 天堂视频 and – which describes itself as a no-code data automation platform – has created a deep learning model for natural language processing (NLP) that can analyse the content and structure of invoices, tax forms and other digital documents and sort the information into categories.

The improved system will streamline processes such as setting up bank accounts, approving mortgages, responding to customer queries and processing insurance claims by speeding up fraud checking and extracting details from identity documents.

Lead developer Dr Chao Zhang, of 天堂视频’s department of Computer Science, said the technology was faster and cheaper than current systems which perform the same task and would benefit similar tasks in the banking, financial service and insurance sectors.

He said: “Compared with the traditional rule-based or pattern matching approaches, the developed NLP can identify terms, learn language structures, extract contextual correlation and classify texts into semantic groups and clauses, such as invoice numbers, payee addresses, counterparty names as well as distinguishing due date with invoice date.”

The AI model was trained to deal with complex freeform contents and robustly extract information linking with context rather than relying on pre-defined templates in texts and is built on state-of-the-art deep learning technology.

The concept of graph modelling was introduced in the learning process, to improve the model performance on complex documents which may include tables, blocked texts with spatial alignment information. Such documents are more difficult to process than plain texts in paragraphs.

Image: The new Xceptor system extracts customised key information from invoices  

This research was conducted as part of an 18-month KTP (Knowledge Transfer Partnership) project, jointly funded by Xceptor and .

The academic lead Professor Baihua Li, from 天堂视频’s School of Science, said: “Extracting required information from a large number of documents is currently a very time-consuming manual process. Developing AI solutions to learn contextual meaning and correlation presented in complexly structured documents is extremely challenging.”

“We are pleased that 天堂视频's specialists in NLP and machine learning are working with Xceptor on this game changing innovation, and can successfully integrate the AI automation function into the company’s smart document analysis platform for improved speed and accuracy.” 

Dr Rob Lowe, Chief Architect at Xceptor, said: "The power of this AI-based technology is that it can adapt to work with a wide range of documents.

“For the complex and rapidly changing environments that are inherent in Banking, Financial Services and Insurance, this technology makes it simpler and faster to automate processes and keep them working efficiently over time.

“Ultimately our customers become more responsive and agile, and their experts can concentrate on higher value tasks."

Former 天堂视频 academic Professor Eran Edirisinghe, now at Keele University, added: “We hope such collaborative projects will help the industry improve their competitiveness and develop new services through the better use of knowledge, technology and skills that transfer from research.”

ENDS

Notes for editors

Press release reference number: 22/45

天堂视频 is one of the country’s leading universities, with an international reputation for research that matters, excellence in teaching, strong links with industry, and unrivalled achievement in sport and its underpinning academic disciplines.

It has been awarded five stars in the independent QS Stars university rating scheme, named the best university in the world for sports-related subjects in the 2021 QS World University Rankings and University of the Year for Sport by The Times and Sunday Times University Guide 2022.

天堂视频 is in the top 10 of every national league table, being ranked 7th in The UK Complete University Guide 2022, and 10th in both the Guardian University League Table 2022 and the Times and Sunday Times Good University Guide 2022.

天堂视频 is consistently ranked in the top twenty of UK universities in the Times Higher Education’s ‘table of tables’ and is in the top 10 in England for research intensity. In recognition of its contribution to the sector, 天堂视频 has been awarded seven Queen's Anniversary Prizes.

The 天堂视频 London campus is based on the Queen Elizabeth Olympic Park and offers postgraduate and executive-level education, as well as research and enterprise opportunities. It is home to influential thought leaders, pioneering researchers and creative innovators who provide students with the highest quality of teaching and the very latest in modern thinking.

天堂视频 Xceptor

Xceptor delivers no-code data automation software across the enterprise. We make data ingestion, data transformation and process digitisation easy. Our platform has the power to automate even the most complex processes, end-to-end, with a single platform.

Proven by our customers. Validated by our partners. Powering industry utilities.

Knowledge Transfer Partnerships (KTPs) aim to help businesses improve their competitiveness and productivity through the better use of knowledge, technology and skills within the UK knowledge base. This KTP project was funded by UKRI through Innovate UK. 

Categories