Please note: The algorithm descriptions in English have been automatically translated. Errors may have been introduced in this process. For the original descriptions, go to the Dutch version of the Algorithm Register.
Loki
How does a chatbot help make information from cadastral data sources accessible to citizens? That's what we investigated with Loki.
Last change on 4th of June 2024, at 11:19 (CET) | Publication Standard 1.0
- Publication category
- Other algorithms
- Impact assessment
- Field not filled in.
- Status
- In development
General information
Theme
- Space and Infrastructure
- Work
- Living
Begin date
Field not filled in.
Contact information
https://formulieren.kadaster.nl/contact_kadaster_algoritmeregister
Link to publication website
https://labs.kadaster.nl/cases/loki
Responsible use
Goal and impact
With Loki, we want to show the demonstrated value of a chatbot in retrieving information from our data.
Considerations
Virtual assistants such as Siri, Alexa and the Google Assistant are becoming increasingly popular. In these, the user speaks a question or the question is not typed in. We are also developing the Kadaster Knowledge Graph. This creates all kinds of new insights about how we should present data in the future. We want to investigate how best to present data.
Human intervention
Field not filled in.
Risk management
minimal risk
Legal basis
Section 2a subsection c of the Land Registry Act states: 'an efficient provision of information to the government for the proper performance of public law duties and the fulfilment of statutory obligations by administrative bodies'. In short, we want to make our information available to the widest possible audience. So also to citizens.
Operations
Data
Loki uses public data in the BAG, BRK (Cadastral Map), BRT and WOZ.
Technical design
- chatbot framework Rasa
- Microsoft Azure's speech-to-text API
- Knowledge graph for connecting data from different registries and SPARQL endpoints.
Similar algorithm descriptions
- A chatbot that answers general questions from citizens 24/7 on Gennep municipality's website. The chatbot should help reduce waiting times and provide instant answers.Last change on 23rd of April 2025, at 13:38 (CET) | Publication Standard 1.0
- Publication category
- Impactful algorithms
- Impact assessment
- DPIA
- Status
- In use
- Someone asks Chatbot a question. Chatbot responds with an answer generated by Ai. Municipality of Veere feeds the chatbot with information (links to sites/knowledge base) and monitors/analyses chatbot usage.Last change on 18th of April 2024, at 14:14 (CET) | Publication Standard 1.0
- Publication category
- Other algorithms
- Impact assessment
- Field not filled in.
- Status
- In development
- The municipality has a chatbot, it is called Robin. Someone asks the chatbot a question. The bot sends the question to OpenAI for analysis. OpenAI creates an answer and sends it back to the bot. The answer is created with sources provided by the bot. In this case, the URLs of the website www.wijchen.nl.Last change on 4th of February 2025, at 9:50 (CET) | Publication Standard 1.0
- Publication category
- Other algorithms
- Impact assessment
- Field not filled in.
- Status
- In use
- KCC chatbot Zeister information assistantLast change on 17th of February 2026, at 8:16 (CET) | Publication Standard 1.0
- Publication category
- Impactful algorithms
- Impact assessment
- DPIA
- Status
- In use
- The municipality has a chatbot, it is called Robin. Someone asks the chatbot a question. The bot sends the question to OpenAI for analysis. OpenAI creates an answer and sends it back to the bot. The answer is created with sources provided by the bot. In this case, the URLs of the website www.druten.nl.Last change on 4th of February 2025, at 8:30 (CET) | Publication Standard 1.0
- Publication category
- Other algorithms
- Impact assessment
- Field not filled in.
- Status
- In use