At Cobuilder, the strive to make the most of Machine Learning (ML) and Artificial Intelligence (AI) started in 2017. As a forward-thinking company that aims to bring the benefits of modern technology to one of the least digitised sectors – construction, it is our role to explore new ways of creating value for our clients. This is why, in many cases new process and services at Cobuilder are the result of our intrapreneurial approach. In fact, an internal hackathon initiated the set-up of the ML/AI team at Cobuilder.
The start of a hackathon tradition
The first Hackathon at Cobuilder aimed to solve problems directly related to some of our core services: the transformation of unstructured information into machine-readable data.
To this day, much of the knowledge transfer in the construction sector still relies mainly on paper to manage processes and deliverables. Even where a certain level of digitisation occurs, due to the lack of consistent data structures, information is not machine-readable. This makes information sharing an inconsistent, labour-intensive process with a great room for error.
The aim of the hackathon was to find a way to speed up those processes of extracting unstructured data from PDF files into structured data models by reducing repetitive, manual work and increasing efficiency in the organisation.
The results were more than promising: in under 48 hours we were able to prove that a complex problem we had been struggling with for years could be solved by using AI. The essential reason for that: we boiled the complex problem down to a classification problem – a technique that categorizes data into distinct and desired number of classes where we can assign label to each class – that was something quite suitable for AI to solve.
During the hackathon our teams analysed the problem and the relevant data, developed a proposed solution and tested its performance. Not only were the results promising but the two teams participating in the hackathon achieved success using dissimilar approaches.
Todor Popov, Pavel Pavlov and Valentin Zmiycharov – the members of the AI and ML Team at Cobuilder from left to right
The beginning of the Machine Learning team at Cobuilder
After validating the idea within the hackathon, the company management decided on dedicating resources for ML/AI projects within the company. Nowadays, the Machine Learning team has 3 members, ‘head-hunted' from internal departments thus coupling core company knowledge with the power of ML and AI.
The first project of the new team that officially made the roadmap was related to interpreting Safety Data Sheets (SDS) and turning them from PDF files to machine-readable data – a task that Cobuilder experts were executing manually for more than a decade. SDS's are an integral part of the construction industry. They provide information on the hazards of working with construction materials in an occupational setting. Being able to process these documents digitally enables users to be automatically notified of the hazards and take the appropriate course of action related to working with some building materials.Through digital means this can be done as early as the design stage, so hazardous materials can be avoided in the purchasing process.
"…Artificial Intelligence (AI) has helped Cobuilder provide higher quality services due to improved workflows, and we can now produce features that have been unfeasible without using AI"
The Automated Loading and Interpreting of SDS's or ALIS was designed to aid our colleagues in digitising SDS's. The approach of ALIS is to extract the information for the more common cases, leaving for the experts to confirm, append and if necessary, change the extracted data. ALIS has more than 70% accuracy in extracting the correct data from the unstructured PDF and populating it in the right digital template. This process efficiency reduces manual labour by up to 60%.
How it works – the technical stuff
Our experience and knowledge in handling SDS's combined with the sufficient amount of available data gathered in our databases made the necessary conditions and stepping-stones for ALIS to emerge and fulfil its purpose. Furthermore, Natural Language Processing (NLP), image processing and deep neural networks are used to extract and transform the required data from PDF files. The whole algorithm bundle is put nicely in a Python package. However, providing a package solution is only a part of a data science engineer's day. Another major part is deployment and integration within the company's systems.
Our plans for the future?
So far, Machine Learning (ML) and Artificial Intelligence (AI) have helped Cobuilder provide higher quality services due to improved workflows, and we can now produce features that have been unfeasible without using AI. This really brings on a competitive advantage which, of course, extends to our customers.
"…people who create value in our business AND in our customers' businesses will be focused on innovating, creating and delivering value, while computers are doing all the manual and repetitive work"
There are many opportunities that lie ahead. Through leveraging the power of Machine Learning (ML) and Artificial Intelligence our customers will take advantage of faster, more reliable services. Making data machine-readable is something of a credo at Cobuilder. This means that people who create value in our business AND in our customers' businesses will be focused on innovating, creating and delivering value, while computers are doing all the manual and repetitive work.
The bottom line is that through digitisation we can contribute to the modernisation of the construction sector and consequently to creating a better, safer built environment.
Cobuilder International LTD is the Bulgarian subsidiary of Cobuilder AS – an international IT company based in Oslo, Norway. Cobuilder offers software solutions that enhance information and documentation management for construction products and hazardous chemicals complying with both European legal requirements and international building standards.