AI System for Reviewing Timetable and Room Conflicts

The problem

When course, room, time, capacity and accessibility requirement data are held in different sources, staff must match the fields manually before preparing conflicts and room alternatives.

The academic planning specialist must compare every suggested conflict and room alternative with the source record; missing or conflicting evidence must not replace the final decision.

If a shared course or specific access requirement is not routed for separate review, an unsuitable room could be assigned; the record must not proceed without a human decision.

What we set out to improve

• Time taken for draft conflicts and room alternatives with their supporting evidence to reach the academic planning specialist for review
• Resolution outcomes for records routed to human review because of a shared course or specific access requirement
• Number of suggestions corrected after identifying the risk of assigning an unsuitable room

How the system works

1. 01 Retrieve course, room, time, capacity and accessibility requirement data from authorised sources
2. 02 Verify field and document versions
3. 03 Prepare conflicts and room alternatives with their supporting evidence
4. 04 Check the exception: a shared course or specific access requirement
5. 05 Have the academic planning specialist accept, correct or reject the output
6. 06 Decision gate: course and room timetable decision
7. 07 Record the decision and source separately

Methods we used

• A source-identified data schema for course, room, time, capacity and accessibility requirement data
• A structure that separates deterministic rules from AI suggestions
• A screen showing conflicts and room alternatives alongside their supporting evidence
• A human review queue for a shared course or specific access requirement
• A record identifier that prevents duplicate processing

Where people stay involved

Data and security

Only the necessary course, room, time, capacity and accessibility requirement data should be processed. Role-based access must be applied, and unnecessary identity, health, financial and internal institutional data must not be sent to the model. Source retrieval, AI suggestions and the academic planning specialist's decision must be logged separately.

Who this suits

Frequently asked questions