The urbanixm Knowledge Discovery Engine is a collection of AI powered tools to curate knowledge of our built environment and make it easier to access information about the impact of urban interventions.
The engine collects content from the Web (local authority websites, news sites, urbanism blogs, research reports, etc.) and runs it through an information curation pipeline to extract nuggets of knowledge about urban policy, infrastructure implementations, the impact of urban interventions and statistical characteristics of places.
The resulting information is stored in our urban knowledge repository and used to power an urban knowledge search engine that we use for writing our series of urban impact/milieu stories as well as case-study research services.
Web crawler
The urbanixm web crawler traverses the World Wide Web in search of content that is relevant to urbanism. We collect various types of web-pages, including local authority websites, news sites, urbanism blogs, scientific articles, project reports and press releases.
Urban knowledge curator
The urbanixm knowledge curator is an artificial intelligence powered toolbox for content annotation. It includes content classifiers for determining whether a web-page is related to urbanism in general, whether it is a good quotable source, and whether it discusses a particular urbanism topic or is referring to a particular place.
Our classifiers also work at the level of smaller text chunks, or knowledge snippets, where we can determine the urbanism topic discussed, the places referenced as well as the narration type, e.g. whether the sentence discusses infrastructure implementation, policy, impact or statistical characteristics of a place.
Urban knowledge repository
The annotated knowledge nuggets generated by the urbanixm content curation pipeline are stored in an urban knowledge repository and are used to power downstream services, such as our internal search engine, case-study research services and stories.
