UK Government: “Local plan consultations can generate thousands of responses from members of the public, the development industry and statutory consultees. For local planning authority (LPA) teams, that means weeks of reading, categorising and summarising before the real work of analysis can begin.
With the government committed to faster local plan preparation, we’re exploring whether artificial intelligence (AI) can help reduce the time spent on some of the administrative tasks without compromising the quality of the consultation analysis while continuing to support greater citizen engagement.
Where this started
Through support from our PropTech Innovation Fund, we funded Greater Cambridge Shared Planning (GCSP) – the shared planning service for Cambridge City and South Cambridgeshire District Councils – to explore how AI could transform the consultation summarisation process. GCSP partnered with the University of Liverpool to develop a tool.
Working with the planning team, the University built a bespoke large language model (LLM) trained on 15 years of Cambridge’s consultation data and key planning terminology.
In a trial last year, the tool, called PlanAI, successfully summarised 3 planning consultations, on supplementary guidance documents, in 16 minutes – a task which took 18.5 hours to do manually. As well as the significant time difference, the quality of the summaries was also compared, with the AI-generated reports providing clear breakdowns of the themes, patterns and insights from the responses. ..(More)”.
