A serious game to assist students in computer science modules post-learning

Post-learning CS concept reinforcement: Students need support reinforcing their understanding of fundamental computer science concepts after learning.

In-game puzzle assistance: Players struggling with educational game puzzles need relevant and timely assistance.

Static hint limitations: Traditional hint systems provide static hints rather than dynamic hints adapted to the current game state.

Knowledge-graph hint system: The project develops and integrates a knowledge graph-based hint system into an existing serious game for computer science learning reinforcement.

Game-state adaptive hint retrieval: The system uses a structured knowledge graph of game states and traverses it to retrieve appropriate hints based on the current game state and detected error type.

Client-server inferential hint logic: Hint retrieval logic runs in Unity and a Python Flask API, dynamically analyzing player input to classify errors and select hints.

Scaffolded hint delivery: The system guides students with hints without directly revealing the answer.

Improved learning experience and confidence:

Reinforced conceptual understanding:

Further research value: