Data Guardians: A collaborative journey of Infotel UK and NICD to safeguard sensitive information

Infotel UK has partnered with the National Innovation Centre for Data (NICD) to embark on a project dedicated to data management and data privacy in large organisations. This partnership highlights a significant milestone in our commitment to harness the huge potential of Data Science, Artificial Intelligence (AI), and Machine Learning (ML). The kick-off event, held in June this year, served as a platform for our teams to engage in productive brainstorming sessions, focusing on the development of projects for our in-house data management solution Deepeo. This innovative venture is set to cultivate expertise in the fields of ML, with a special emphasis on addressing real-world challenges that will leave a lasting impact on our region.

Our vision at Infotel UK has always been geared toward expanding our technological horizons, and this collaboration with NICD is a testament to that vision. Together, we aim to foster innovation while nurturing the talents of young professionals locally. Through skills projects and pair programming initiatives, in partnership with NICD, we are dedicated to equipping individuals with the tools and knowledge needed to thrive in the AI-driven era.

The crux of the project revolves around the protection of Personally Identifiable Information (PII). As the digital landscape continues to evolve, organisations are faced with the daunting task of safeguarding sensitive information in free-text data. This complex yet essential endeavour plays a pivotal role in data privacy and security.

PII encompasses a wide range of sensitive data, including but not limited to names, addresses and locations, postcodes and ZIP codes, phone numbers, credit card numbers, bank account details, National Insurance (NI) numbers, National Health Service (NHS) numbers, driving license numbers, passport numbers. Furthermore, PII detection often extends to multiple languages to cater to the diverse global landscape.

Detecting PII leads on to a number of use cases, including:

Database Searches: PII detection can be used to search databases for tables and columns that may contain sensitive information, enhancing data security through proactive measures.

Anonymisation: Anonymising free text is crucial for data modelling and ML projects like fraud detection, enabling organisations to use data without compromising individual privacy.

Redaction: Redaction involves concealing sensitive information within free text, ensuring that only authorised personnel can access complete data, a vital consideration when sharing documents or reports containing PII.

The project involves the development of advanced techniques for PII detection in free text, including:

Part of Speech Recognition (PoSR): PoSR involves analysing the grammatical structure of sentences to identify words and phrases that could potentially contain PII. It can recognize patterns associated with names, addresses, or phone numbers.

Named Entity Recognition (NER): NER is a sophisticated method that focuses on recognizing and categorizing entities within text. It can identify names, locations, dates, and other PII-related information.

In today’s interconnected world, data is shared across borders and languages. Hence, PII detection must be multilingual. Advanced PII detection systems are being developed to support multiple languages, making them versatile and effective in this global landscape.

Detecting PII in free text is a critical component of modern data security. Employing advanced techniques such as PoSR, NER, and other innovative methods, organisations can safeguard sensitive data effectively. Whether it’s searching databases, anonymising data for analysis, or redacting documents, PII detection plays a pivotal role in ensuring data privacy and security in an increasingly digital and multilingual world.

Our lab in Newcastle will serve as a dynamic hub, attracting technical experts, clients seeking innovative solutions, and a diverse range of stakeholders. This vibrant ecosystem will harness cutting-edge technologies and top talent to tackle projects that push the boundaries of innovation and drive digital transformation. We welcome our clients to propose lab projects, enabling us to unlock the potential within their data and deliver transformative solutions.

The collaboration between Infotel UK and NICD will pave the way for innovative solutions, not only for our software Deepeo but also for future client projects, bolstering expertise within the region. By leveraging the expertise of technology partners, academia, and community stakeholders, we aim to foster an ecosystem at the forefront of technological advancements and digital delivery mechanisms. We are excited to embark on this journey with NICD and believe that this collaboration will change the tech landscape, inspire future leaders, and boost the North East’s tech landscape.

Arailym O’Shaughnessy

Read more posts

CGI Young Dreamers Programme 2024…


CGI Young Dreamers Programme 2024 kicks off in Newcastle to encourage STEM careers for students   CGI, one of the largest IT and business consulting services firms in the world,…

Read more

Seventh Wave Joins Dynamo North…


Dynamo North East welcomes a new member into its fold: Seventh Wave. This addition brings a fresh wave of expertise in leadership training and team development, enhancing the diverse tapestry…

Read more

New post: Northumbria students launch green awareness campaign for Metro operator…

Join our
mailing list