Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Automating Document Intelligence in Statutory City Planning

Lars Malmqvist, Robin Barber

Abstract

UK planning authorities face a legislative conflict between the Planning Act, which mandates public access to application documents, and the Data Protection Act, which requires protection of personal information. This situation creates a manually intensive workload for processing large document volumes, diverting planning officers to administrative tasks and creating legal compliance risks. This paper presents an integrated AI system designed to address these challenges. The system automates the identification and redaction of personal information, extracts key metadata from planning documents, and analyzes architectural drawings for specified features. It operates with an AI-in-the-Loop (AI2L) design, presenting all suggestions for review and confirmation by planning officers directly within their existing software; no action is committed without explicit human approval. The system is designed to improve its performance over time by learning from this human oversight through active learning prioritization rather than autoapproval. The system is currently being piloted at four diverse UK local authorities. The paper details the system design, the AI2L workflow, and the evaluation framework used in the pilot. Additionally, it describes a preliminary Return on Investment (ROI) model developed to quantify potential savings and secure partner participation. This work provides a case study on deploying AI to reduce administrative burden and manage compliance risk in a public sector environment.

Automating Document Intelligence in Statutory City Planning

Abstract

UK planning authorities face a legislative conflict between the Planning Act, which mandates public access to application documents, and the Data Protection Act, which requires protection of personal information. This situation creates a manually intensive workload for processing large document volumes, diverting planning officers to administrative tasks and creating legal compliance risks. This paper presents an integrated AI system designed to address these challenges. The system automates the identification and redaction of personal information, extracts key metadata from planning documents, and analyzes architectural drawings for specified features. It operates with an AI-in-the-Loop (AI2L) design, presenting all suggestions for review and confirmation by planning officers directly within their existing software; no action is committed without explicit human approval. The system is designed to improve its performance over time by learning from this human oversight through active learning prioritization rather than autoapproval. The system is currently being piloted at four diverse UK local authorities. The paper details the system design, the AI2L workflow, and the evaluation framework used in the pilot. Additionally, it describes a preliminary Return on Investment (ROI) model developed to quantify potential savings and secure partner participation. This work provides a case study on deploying AI to reduce administrative burden and manage compliance risk in a public sector environment.
Paper Structure (28 sections, 4 figures, 6 tables)

This paper contains 28 sections, 4 figures, 6 tables.

Table of Contents

  1. Introduction
  2. Related Work
  3. Intelligent Document Processing
  4. Digitisation in UK Planning
  5. Legal and Information Governance
  6. Human-AI Collaboration Frameworks
  7. System Architecture and Implementation
  8. Phase 1: Proof of Concept
  9. Phase 2: Integrated Pilot System
  10. Enterprise Integration and Security
  11. Configurable Hybrid Processing Framework
  12. Division of Responsibilities and Scope.
  13. The AI-in-the-Loop Workflow
  14. Data Extraction and Verification
  15. Review of Detected Personal Information
  16. ...and 13 more sections

Figures (4)

  • Figure 1: The pilot system architecture, highlighting the integration of the system backend with the existing enterprise application and its secure, auditable interaction with VLM services.
  • Figure 2: The data extraction workflow. The system populates fields on the right-hand panel based on its analysis of the document shown on the left. The human operator verifies and confirms this data.
  • Figure 3: The PII detection workflow. The system presents a list of detected PII items with confidence scores. The operator reviews the list and confirms which items to redact.
  • Figure 4: The visual check workflow. The operator selects the checks to perform (left panel), and the system returns a document preview with the detected visual elements overlaid with bounding boxes (right panel).