Skip to main content

Introduction

Places are woven into our conversations effortlessly. Every day, we talk about places, whether it’s the city where we grew up, a historic monument, or a natural landmark. When it comes to capturing and storing spatial data, however, the simplicity of our daily language fades into a web of complexity. The structure of our spatial datasets often makes it difficult to craft compelling or dramatic narratives, which are central to story-based media such as games, animations, and documentaries. UrbanLinguist provides a solution to bridge this gap, enabling more seamless and effective storytelling with spatial data.

Challenges

“I want to tell the community how well we did as a local authority, how nicer our neighbourhoods are compared to others, but all I have are maps, charts and reports that no one reads”, said one of the planning officers. Telling compelling stories, building tension, and evoking emotions require different forms of information strategy than what is achievable by the medium of maps and charts.

This gap in infrastructure for spatial storytelling affects not only urban planners but also creative professionals, game designers, animators, interactive experience creators, and documentary makers, who struggle to access and use the vast urban and environmental data available. While AI platforms make data insights more accessible, they often exclude raw data itself. Similarly, open-source 3D models and game engines can visualise cities but integrating meaningful spatial data into them demands significant expertise in spatial data management.

Solutions

To address these challenges and make spatial data storytelling more dynamic and intuitive. We have developed UrbanLinguist, using natural language processing and spatial analysis tools. UrbanLinguist consists of two key components:

1. API for Natural Language Processing: This API links the technical coding and categories of ONS spatial data with natural language, enabling easy identification of spatial elements within text-based narratives. It is designed for users who wish to build custom services using spatial data. Combined with LLM-powered visualization tools, the API offers new ways to interact with spatial data.

2. Urban Planner-Focused Platform: This platform demonstrates the API’s capabilities in real-world applications. It allows users to render multiple entities (e.g., pubs, supermarkets, and parks near schools) across areas in a single textual or voice request, visualize entities and spatial relationships within custom boundaries, and display the chronological sequence of spatial elements within a given text.

Results

The API component contains core ONS geographical boundaries and Open Street Map data. The platform, however, was developed as part of the Open Geospatial Consortium’s code sprint event and is experimental in nature. While the basic version of the platform is open-source, advanced features, such as the ability to query custom datasets and define bespoke spatial terminologies, are available only in the paid version. The pricing is determined based on the specific requirements and scope of your project, ensuring that the solution is tailored to meet your unique needs effectively.

More case studies from Seal on the Beach

Europe
Company Logo - Seal on the Beach
Seal on the Beach

Supporting Creative Minds in Urban Planning (SEMINAL)

Artificial intelligence (AI) and software solutions

An innovation-led social enterprise

The directory is brought to you by the Digital Task Force for Planning, a not-for-profit organisation. Our ambition is to promote digital integration and advancement in Spatial Planning to tackle the grand challenges in the 21st Century.
Brought to you by:
Seed funded by: