Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

A Logical Approach to Criminal Case Investigation

Takanori Ugai, Yusuke Koyanagi, Fumihito Nishino

TL;DR

This paper tackles the challenge of applying explainable AI to forensic investigations by combining a knowledge-graph representation of crime-scene data with rule-based, ontology-driven inference. It builds motive and means ontologies and a killing-method ontology, integrates them into a Sherlock Holmes knowledge graph, and uses SPARQL and SHACL to infer motive, opportunity, and method for potential suspects. The study demonstrates the approach on The Adventure of the Speckled Band, showing how three characters can be inferred as potential perpetrators and explaining why and how each could have acted. The work highlights the value of semantic, interpretable reasoning for assisting investigations, while acknowledging ontology gaps and the need for automation in final judgments.

Abstract

XAI (eXplanable AI) techniques that have the property of explaining the reasons for their conclusions, i.e. explainability or interpretability, are attracting attention. XAI is expected to be used in the development of forensic science and the justice system. In today's forensic and criminal investigation environment, experts face many challenges due to large amounts of data, small pieces of evidence in a chaotic and complex environment, traditional laboratory structures and sometimes inadequate knowledge. All these can lead to failed investigations and miscarriages of justice. In this paper, we describe the application of one logical approach to crime scene investigation. The subject of the application is ``The Adventure of the Speckled Band'' from the Sherlock Holmes short stories. The applied data is the knowledge graph created for the Knowledge Graph Reasoning Challenge. We tried to find the murderer by inferring each person with the motive, opportunity, and method. We created an ontology of motives and methods of murder from dictionaries and dictionaries, added it to the knowledge graph of ``The Adventure of the Speckled Band'', and applied scripts to determine motives, opportunities, and methods.

A Logical Approach to Criminal Case Investigation

TL;DR

This paper tackles the challenge of applying explainable AI to forensic investigations by combining a knowledge-graph representation of crime-scene data with rule-based, ontology-driven inference. It builds motive and means ontologies and a killing-method ontology, integrates them into a Sherlock Holmes knowledge graph, and uses SPARQL and SHACL to infer motive, opportunity, and method for potential suspects. The study demonstrates the approach on The Adventure of the Speckled Band, showing how three characters can be inferred as potential perpetrators and explaining why and how each could have acted. The work highlights the value of semantic, interpretable reasoning for assisting investigations, while acknowledging ontology gaps and the need for automation in final judgments.

Abstract

XAI (eXplanable AI) techniques that have the property of explaining the reasons for their conclusions, i.e. explainability or interpretability, are attracting attention. XAI is expected to be used in the development of forensic science and the justice system. In today's forensic and criminal investigation environment, experts face many challenges due to large amounts of data, small pieces of evidence in a chaotic and complex environment, traditional laboratory structures and sometimes inadequate knowledge. All these can lead to failed investigations and miscarriages of justice. In this paper, we describe the application of one logical approach to crime scene investigation. The subject of the application is ``The Adventure of the Speckled Band'' from the Sherlock Holmes short stories. The applied data is the knowledge graph created for the Knowledge Graph Reasoning Challenge. We tried to find the murderer by inferring each person with the motive, opportunity, and method. We created an ontology of motives and methods of murder from dictionaries and dictionaries, added it to the knowledge graph of ``The Adventure of the Speckled Band'', and applied scripts to determine motives, opportunities, and methods.
Paper Structure (12 sections, 11 figures)

This paper contains 12 sections, 11 figures.

Table of Contents

  1. Introduction
  2. Related Works
  3. Crime Scene Knowledge Graph
  4. Knowledge Graph Schema
  5. The Adventure of the Speckled Band
  6. Investigation Process
  7. Created Ontologies
  8. Motivation
  9. Opportunities
  10. Method
  11. Comprehensive assessment
  12. Future work and Summary

Figures (11)

  • Figure 1: Architecture of the knowledge graph
  • Figure 2: Example of a scene graph
  • Figure 3: Overall structure of the reasoning system
  • Figure 4: An ontology of motives for murder
  • Figure 5: Rules for inferring who has a grudge motive
  • ...and 6 more figures