Anonymise

Province of Utrecht

Identifying and anonymising privacy-sensitive information in information objects. It usually involves documents.

Last change on 8th of April 2026, at 13:19 (CET) | Publication Standard 1.0

• Publication category: Other algorithms
• Impact assessment: Field not filled in.
• Status: In use

General information

Theme

Organisation and business operations

Begin date

Field not filled in.

Contact information

[e-mail]

Responsible use

Goal and impact

The purpose of the algorithm is to anonymise privacy-sensitive information in information objects. This protects personal information and preserves the privacy of individuals.

Considerations

The algorithm is trained to recognise privacy-sensitive information, but is limited to classification and will therefore never reveal substantive information. Moreover, the technology helps improve the quality of anonymisation.

Human intervention

The algorithm results only act as a tool, with human intervention always needed for final anonymisation.

Risk management

To safeguard the algorithm's privacy risks, it undergoes constant evaluation and updates to address new threats and privacy challenges. Human oversight and intervention are embedded to correct errors. Moreover, there is continuous dialogue with stakeholders.

Legal basis

1. Open Government Act
2. Electronic Publications Act

Links to legal bases

• Open Government Act (WOO): https://wetten.overheid.nl/BWBR0045754/
• Electronic Publications Act (WEP): https://wetten.overheid.nl/BWBR0043961/

Operations

Data

Spatial plans and internal documents.

Links to data sources

Spatial plans and internal documents: https://www.ruimtelijkeplannen.nl/home

Technical design

Deep learning models that determine in both visual and textual ways what information is considered privacy-sensitive.

External provider

eData B.V.