Master Thesis - Transforming Project Documentation with AI -

Company Description

Welcome to a world, where your ideas lead to something big. Welcome to Bosch.
At Bosch, we shape the future by inventing high-quality technologies and services that spark enthusiasm and enrich people’s lives. Our promise to our associates is rock-solid: we grow together, we enjoy our work, and we inspire each other. Join in and feel the difference.

Bosch R&D Center Lund stands for modern development in cutting edge technology in the areas of connectivity, security, mobility solutions and AI. We are growing rapidly and looking for people to join us on our mission to become the Bosch Group’s 1st address for secure connected mobility solutions. We are working on a range of interesting projects, with a particular focus on software development for the automotive industry, electrical bicycles and Internet of Things.

Job Description

Problem statement

Despite the availability of documentation management tools, manually searching for the right information or troubleshooting steps is inefficient. Existing chatbots can provide support for open-source projects, but when it comes to private or enterprise-level projects, no comprehensive solution addresses this need effectively. Current systems are often fragmented, requiring users to switch between multiple platforms or repositories, resulting in delays, errors, and missed opportunities for streamlined communication. As projects grow in scale and complexity, the demand for an intelligent, automated solution that can navigate this information landscape becomes more urgent.​

The following bullet points outline the questions to be tackled along the way to meet the goal;

• What NLP and machine learning techniques are most effective in interpreting and responding to project documentation queries?
• How can the chatbot integrate with multiple documentation sources to ensure accurate and up-to-date information retrieval?
• How can the chatbot provide relevant, real-time problem-solving suggestions based on retrieved documentation?
• To what extent does an AI chatbot improve the efficiency of project management by reducing the time spent searching for documentation and troubleshooting?
• Will this solution be easily applied to big enterprise-level projects that are already established (i.e internal Bosch projects, will be trialled by Bosch Associates)?

Proposed solution

This research focuses on designing and implementing a customizable AI-powered chatbot that is automatically trained on retrieved project-related documentation and assists users with problem-solving in real-time. The chatbot will understand user queries in natural language, extract relevant information, and offer intelligent responses, thereby improving the efficiency of project documentation access and usage.​

Goal is to implement an AI-powered chatbot solution that can be effectively customized to be trained automatically on any enterprise project documentation and assist users with problem-solving in real-time.

A pre-trained model like BERT or similar shall be used. The model needs to be retrained based on the project specific data base.

You will of course have the opportunity to shape the thesis based on your knowledge, skills and discoveries during the project.

Your profile

In order to be successful in the project with think you are:

• A student in Information Technology, Computer Science, Math or Physics.
• Required knowledge / courses on data science and AI
• Front-end framework knowledge
• Interested in algorithm development and have some signal processing experience with machine learning knowledge.
• Experienced with or have at least some knowledge of programming in Python
• Self-driven, able to challenge yourself, and gain the experience needed to move the project forward.
• A person with team spirit, social skills and a curiosity for exploring new technology areas.

Qualifications

Your profile

In order to be successful in the project with think you:

• Are a student in Information Technology, Computer Science, Maths, or Physics.
• Have required knowledge / courses on data science and AI.
• Have front-end framework knowledge.
• Are interested in algorithm development and have some signal processing experience with machine learning knowledge.
• Are experienced with, or have at least some knowledge of, programming in Python.
• Are self-driven, able to challenge yourself, and gain the experience needed to move the project forward.
• Are a person with team spirit, social skills, and a curiosity for exploring new technology areas.

Additional Information

Scope of master thesis project

1-2 students completing 30 credits each (20 weeks) onsite at the Lund office

How to apply

Please specify which project you are interested in. Please note: Only applications from students at a Swedish University are accepted.