How We Automated Project Requirements Management with AI and ML

We are a team of the development department within a state corporation. Our department develops software for project management in the creation and design of complex engineering objects.

In this article, we would like to share the story of how we developed a product using modern AI, ML, NLP technologies and applied this product to optimize our own processes. The main problem is compliance with requirements: there are always a lot of them! Especially in the case of designing and operating complex aggregated composite systems produced by various subcontractors. In the process of work, it is necessary to take into account many small and significant conditions of requirements, each of which can affect the final result. Therefore, great importance is attached to tracking, updating and checking all requirements at each stage of the project. This is especially important in projects where it is necessary to precisely match the result to the technical task. Having studied the problem, we found that the task of compliance with and tracking technical requirements is also acute for technical personnel (project offices, engineers), lawyers, economists and company management.

All participants must:

• reduce the risks of non-fulfillment of contractual obligations;

• link the requirements of one contract with the requirements of another (trace requirements) to improve the manageability of requirements and reduce the risks of “unaccounted for” or forgotten requirements in the contract;

• reduction of time for analysis of project contracts and financial events;

• accounting for the relationships between financial events, claims and obligations;

• reducing the time for high-quality digitization and import of technical documents into requirements management systems;

• take into account financial risks and defaults.

We are integrators in business and interact with our customers, and accordingly operate with their set of design documentation, and this is, at a minimum, regulatory legal documentation and EPC contract and ITT, we also develop our own TOR for systems on the basis of these documents, and use on the basis of our TOR composite subsystems of our subcontractors, who also have their own TOR and TU. We will decipher everything below.

General hierarchy of technical design documents:

• Regulatory and legal documentation (State Standards, Laws)

• EPC contract (E-engineering, P-procurement, C-construction) and ITT (initial technical requirements)

• TOR (technical assignment)

• ChTZ (private technical assignment)

• TU (technical specifications)

And if we follow, as more precisely used in the terms of GOST 59194-2020 “Requirements Management Basic Provisions”, then there is a need to track all the connections of requirements between objects and all their components.

Can you imagine how labor-intensive the volume of engineering and technical analysis will be? 🙂

At that time, our customers from the project office had a “burning” task – to iteratively perform full traceability (tracing) for all technical requirements for a large number of project objects, starting from high-level documents and in descending order of priority:

• ITT \ TZ

• TZ \ ChTZ

• ChTZ \TU

Our team came up with the idea of ​​creating an intelligent assistant that could automate the process of requirements management in terms of establishing traceability (connection) to be able to control all requirements presented to the system, reducing the workload of employees and minimizing the risk of human error. Such products exist on the foreign market, but there are not many analogues on the Russian market. This is due to the complexity of developing such products. But our team had enough expertise to solve such a problem.

We had a task for automation: to compare the design technical requirements for the system with the technical requirements for the subsystem and establish a connection.

We have proposed a product that assists the expert in analyzing the requirements of these documents. The product, first in automatic and then in manual (finishing/controlling) mode with the ability to use the “Smart Assistant”, helps the user – the project expert – establish all the connections of the requirements contained in these documents.

We used a stack of AI NLP technologies and ML, starting from the “Classical” approaches to text comparison according to the Jaccard similarity measure based on the N-shingle method, strengthening the comparison mechanisms by applying text vectorization algorithms, semantic search, as well as machine learning for deeper adaptation to project data.

The result of our work was a product that helped our customers meet all traceability requirements. 6 times faster than planned!.

In addition, the time for checking and updating requirements in the event of changes or versioning of the project is significantly reduced, which ultimately speeds up the entire process of development and implementation of large projects.

We received feedback, conducted problem interviews, held product presentations and identified additional necessary functionality for the intelligent tracing tool. This is automatic parameterizable text atomization and classification of document entities in order to identify requirements, financial events and obligations, and their specific interrelation. Active work is currently underway to refine such functionality, including the implementation of AI methods in these processes.

Thus, the use of advanced AI, ML and NLP technologies and our internal expertise helped not only to facilitate our work, but also significantly increased the quality and efficiency of project activities of other departments of the company. We are confident that our experience can be useful to other organizations facing similar challenges in requirements management and are currently conducting pilot implementations of the system.

If you are interested or have any questions, please write to denis_solovyev888@mail.ru.