Eu FLag
This project has received funding from the European Union’s Horizon 2020 research and innovation programme under grant agreement No101022004

Knowledge Graphs and the advantage of crowd knowledge in criminal investigations

In today’s information-driven society, data is generated and consumed at an unprecedented rate. However, this data is often siloed in different systems and formats, making it difficult to extract insights or understand it comprehensively. Knowledge Graphs (KGs) are an emerging technology that can help law enforcement agencies (LEAs) unlock the value of their data.

Knowledge Graph is a type of database that stores information as a network of nodes and edges, representing relationships between different entities. These entities could be anything from individuals, companies, places, products, or bank accounts to events or concepts. By using a KG, the TRACE tool can create a connected view of LEAs’ data, allowing them to better understand the relationships and dependencies between different entities.

One of the key benefits of using a KG is the ability to search and retrieve information in a speedy and efficient way. Moreover, a KG can provide a better overview of a criminal investigation, linking case data, structuring it automatically, and thus making it easier to understand the context and significance. It can support the identification of patterns, trends, and connections that may not be immediately apparent, leading to new insights and discoveries. By visualizing data in a clear and concise way, a KG should enable law enforcement personnel to make informed decisions.

A very important type of Knowledge Graph is a Crowd Knowledge Graph (CKG). The main difference between a traditional KG and a CKG is the way in which the information is curated and maintained. In the first case, the data is typically curated by subject matter experts or automated systems, whereas in the latter case, the data is curated by a distributed group of individuals who may have different levels of expertise and perspectives on the data. In the context of criminal investigations, a CKG present several advantages over traditional KGs:

  • Access to diverse perspectives and expertise: As a CKG is created by a diverse group of contributors (from partner agencies to prosecutors and others), it provides access to a wide range of perspectives and expertise. This enables investigators to obtain valuable insights and establish connections that may not be evident at first glance.
  • Increased accuracy and completeness: A CKG is curated and reviewed by multiple contributors, helping to ensure its accuracy and completeness. This can help investigators to identify and correct errors or omissions in the data (like issues with character recognition or simple misspellings), and to gather a more comprehensive and reliable picture of the subject of their investigation.
  • Efficient information gathering and analysis: A CKG can help investigators quickly identify and prioritize the most relevant information for their investigation, streamlining the data gathering and analysis process. By leveraging the crowd’s collective intelligence, investigators can identify key relationships, patterns, and insights that may be critical to the investigation.
  • Collaboration and Knowledge Sharing: A CKG provides a collaborative platform that facilitates the exchange of information, promotes teamwork, and enhances the collective intelligence of the investigative team.

Using Knowledge Graphs in our TRACE tool has many benefits. By connecting and interlinking information, and integrating additional knowledge and expertise – the “crowd knowledge”,  LEAs can gain a better and faster overview of their data, enabling them to make more informed decisions, gain new insights, and ultimately track illicit money flows more effectively. 

Author: Adriane RöckeleinProflow