Council Insights Heidelberg - Data Analytics on Council Work using LLM

[#1]

PITCH VIDEO

JURY VIDEO

TEAM PCITURE

Team Name	Council Insights Heidelberg
Track	Public Sector
Use Case	Implementing Lage Language Models LLM for a strong Democracy
Technology	SAS Viya Model Manager, Intelligent Decisioning, Visual Text Analytics, Visual Analytics, Python, LLM, NLP, SAS Viya
Region	Heidelberg, Germany
Team lead	Benjamin Gärtner @benj_gaertner
Team members	Stephan Frenzel,   Ahsan Ali, Maria Shcheglova, Christoph Blattgerste (Student), Harsh Patel (Student) , Silvio Martin (Scientific Staff, KIT), Lutz Berger,  Ian Doig, Slava Kuliger, Stephan Verclas, Patrik Bannholzer,  Andreas Koch,   Sebastian Warkentin, Maik Röder Sundaresh Sankaran (Mentor), Ulrich Reincke (Mentor)
Social media handles	See the team's  LinkedIn Page specific for the #SASHackathon: https://www.linkedin.com/company/hack-team-heidelberg/posts/?feedView=all
Is your team interested in participating in an interview?	yes
Optional: Expand on your technology expertise
==============
Plan	Create automated scripts to regularly retrieve and download relevant documents from the local council website (https://www.gemeinderat.heidelberg.de/info.asp).  Indexation and vectorization of the scraped data  Data Analytics on the vectorized data using NLP, LLM and SAS Viya
Motivation	Our aim is to improve the transparency and accessibility of the work of Heidelberg Municipal Council. We want to enable citizens, the press and other interested parties to find out quickly and easily about the resolutions and activities of the local council. By visualizing and better presenting the work of the committees, we can strengthen citizens' commitment and trust in local government.  Analysis of strategies  We would like to compare the strategic objectives of the city of Heidelberg with the activities and resolutions of the municipal council in order to identify specific resolutions that contribute to the implementation of strategic objectives.  Relevant strategies can be strategies developed by the city of Heidelberg, such as the Heidelberg Biodiversity Strategy, as well as strategies that are valid nationwide, such as the practical guide ‘Climate Protection in Municipalities’ from the German Institute of Urban Studies.  Possible outputs  Analytics on stringency, consistency or legality of council work   Location of resolutions on a map (e.g. by districts, streets, etc.) where possible  Filter function according to districts, topics, committees, time reference (last 6 months or similar)  Search functions (full text, language, locations/regions/environment)  Summary of resolutions in understandable language  Create a chatbot or integration of an intelligent search  Possibly other types of visualizations – Mindmaps, Knowledge Graphs or similar according to keywords or districts (e.g. which topics have been discussed most frequently in the last 6 months)

[SnowTiger]

Link to the Team Page on LinkedIn with the making of the videos: https://www.linkedin.com/company/hack-team-heidelberg/posts/?feedView=all

[SnowTiger]

[ThomasKeil]

Fantastic work, great team effort - and so nice videos! I am impressed - and as a citizen of Heidelberg proud of those ambitions!!

[pazfer]

Great job ! you did something very useful for citizen as well 

[CarlosBarrera]

Congratulations team, great use case, applicable to every state, municipality and country. Also, great approach to solve it using LLMs, AI, analytics and SAS capabilities.

[LGroves]

Very cool project, great use of text analytics, and overall excellent team effort.  Well done!