LLM-Assisted Querying and Manipulation of Analytical Resources in Supply-Chain Management

In supply-chain management, organizations rely on a wide variety of structured and semi-structured analytical resources such as task flows and key performance indicators (KPIs) to plan, monitor, and adapt to changes. These resources undergo frequent review and adaptation, often necessitating queries and manipulations in numerous ways. Utilizing Large Language Models (LLMs), this project aims to develop a chatbot that enhances user experience and operational efficiency while querying and manipulating analytical resources in supply-chain management. The project will be conducted in close collaboration with Kinaxis, a world-leading provider of supply-chain management solutions. An important observation underlying the project is that analytical resources in supply-chain management are domain-specific models. Consequently, conversational AI solutions must consider the model-oriented nature of these resources to be able to properly interpret them. Central to the project is the exploration of the interaction between model-based design in supply-chain management and chatbot functions, as a way to enable prompt-driven creation, querying, and manipulation of supply-chain management resources. The results of the project hold the potential for substantial improvements for supply-chain businesses by enhancing their interaction with analytical resources, thus facilitating informed decision-making. By integrating the outcomes into Kinaxis’ solutions, the collaboration aims to provide even more intelligent..

Faculty Supervisor:

Mehrdad Sabetzadeh;Shiva Nejati

Student:

Partner:

Kinaxis Inc.

Discipline:

Computer science

Sector:

Information and cultural industries

University:

University of Ottawa

Program: