Resources

Videos, Slides, Case Studies and other GraphAware related resources

Webinar - Leveraging LLMs for Intelligence Analysis

Leveraging LLMs for Intelligence Analysis

17 Jan 2024 webinars

In this webinar session, we will unveil how Hume leverages GPT and LLMs to expedite intelligence analysis on extensive unstructured datasets, with a specific focus on law enforcement.

Our live demonstration will centre on the public judicial reports detailing a vast web of state corruption in South Africa, commonly known as the "state capture" or the Gupta Leaks. By employing OpenAI’s GPT (Generative Pre-trained Transformers), we will showcase how the model facilitates Named Entity Recognition (NER) and Relation Extraction (RE) to extract pertinent knowledge from these texts.

You will learn:

  • Prompt Engineering Excellence
    Use GPT to identify key elements crucial for Knowledge Graph creation, including entities and the relationships between them.
  • LLMs in Action
    Explore the use of Large Language Models (LLMs) for building Knowledge Graphs, including data cleaning and normalization processes
  • Results Analysis
    Investigate the central questions surrounding the Gupta Leaks:
    1. How did the Guptas sustain corruption on this scale for an extended period without arousing suspicion?
    2. What were the complicit organizations linked to the Guptas?

Fill out the short form below to watch the webinar!

Webinar - Graphs in Criminal Intelligence

Graphs in Criminal Intelligence

02 Jan 2024 webinars

In this webinar, Dan Newland, General Manager of ANZ, GraphAware, showcases the truly transformational power of Graphs for law enforcement agencies. Dan presented how a cutting-edge graph solution can eliminate obstacles in the criminal intelligence process and increase its efficiency.

You will learn how graphs solve the challenges of modern intelligence:

  • Siloed data sources: There is no central store of data or curated views that have been collected.
  • Siloed analytical tooling: There is no single tool used by everyone for everything, making collaboration burdensome.
  • Relational stores for network analysis: With relational stores, in-depth analysis is difficult.
  • Ad-hoc data collection: Law Enforcement is unique in that any given case may require new data to be loaded and analysed.
  • Manual analysis: Throughout the entire process there are manual, time-consuming steps.
  • Enormous data volumes and variety: The sheer volume and variety of data make the intelligence process problematic

Fill the short form below to watch the webinar!

Three Steps to Intelligence-Led Policing

19 Dec 2023 ebooks hume intelligence

Crafted by our experience, this e-book propose a three-step process to leverage knowledge graph for criminal intelligence. Understand how intelligence agencies organise, compile and query vast amounts of varied data rapidly, opening up a realm of limitless possibilities for further analysis and applications such as intelligence automation or pattern recognition.

Webinar - Unveiling the digital net of extremism

Unveiling the Digital Web of Extremism with Graph-Based Analytics

23 Nov 2023 webinars

In this webinar, Petr Matuska, alongside an expert guest with firsthand experience in counter-terrorism investigations, will use the Hume intelligence analytics solution to unveil terrorist sleeper cell from OSINT, phone forensics, and government data.

The live demonstration illustrates how graph-based analytics tools assist intelligence analysts to automatically create and maintain a continuously available Common Intelligence Picture, uncover hidden patterns, unknown unknowns, and automate alerts on new potential threats.

You will learn how the graph-based approach enables:

  • Fast data integration into a single view of intelligence
  • Real-time monitoring of emerging complex patterns
  • Deep analysis of connected data

Fill the short form below to watch the webinar!

NODES 2023 - Relation Extraction: Dependency Graphs vs. Large Language Models

31 Oct 2023 videos Solutions Hume Relation extraction Large Language Models graph theory intelligence analysis

Entity Resolution (ER) draws connections between scattered, incomplete, and inconsistent records to resolve unique entities. ER is relevant in intelligence analysis, in which organized, complete, and consistent information is crucial for empowering investigations in different areas. This session shows with practical examples the role of the graph as a powerful tool for improving traditional ER. We expose its multiple capabilities: the flexibility of data representation, the application of predictive analysis and machine learning algorithms, and the opportunity to explore the data using network-based visualizations. We show end-to-end pipelines, from data ingestion to downstream analysis, discussing good practices and challenges.

NODES 2023 - Graph-based Entity Resolution for Intelligence Analysis

31 Oct 2023 videos Solutions Hume Entity resolution graph theory intelligence analysis

Entity Resolution (ER) draws connections between scattered, incomplete, and inconsistent records to resolve unique entities. ER is relevant in intelligence analysis, in which organized, complete, and consistent information is crucial for empowering investigations in different areas. This session shows with practical examples the role of the graph as a powerful tool for improving traditional ER. We expose its multiple capabilities: the flexibility of data representation, the application of predictive analysis and machine learning algorithms, and the opportunity to explore the data using network-based visualizations. We show end-to-end pipelines, from data ingestion to downstream analysis, discussing good practices and challenges.

Hume & Knowledge Graphs Streamline Tax Office Investigation

02 Aug 2023 videos Solutions Hume Financial Fraud

In this video, we will present how Knowledge Graphs and Hume streamline Tax Office investigations. In particular, we are assuming the position of an investigator examining Businesses with potential Fraudulent claims for VAT Returns. The right tool enables investigators to understand and interpret relevant data much deeper and quicker, including proactively detecting complex patterns. This way, we help Tax Departments save millions of Euros from false refunds.

Harness connected data to safeguard your community

10 May 2023 solutions Hume law Enforcement

Hume provides a single view of intelligence enabling analysts to quickly identify links and patterns of interest in the vast amounts of information they have access to. On a single canvas, analysts quickly find connections between entities, understand geographical and temporal context, and perform advanced network analysis.

Learn more about how Law enforcement agencies are already using Hume to power their intelligence analysis and achieve success.

Download the Leaflet

Hume Features - Orchestra

03 Apr 2023 videos Hume Law Enforcement

Easily converting multiple distributed data sources into a single, connected source of truth, is the start of a great graph-native intelligence analysis.

Hume Orchestra is used for data ingestion from a wide range of systems and formats into Neo4j graph database, but it is not limited to ingestion only. Amongst others, Orchestra is capable of applying Machine Learning to your data, enriching it from external sources through API calls or performing advanced Graph Data Science algorithms. And in the end, it combines and connects all data in 1 source of truth, the Knowledge Graph.

Read more about the benefits of Enterprise Data Orchestration and unlock the full potential of your data.

*The data used in the video are entirely fictitious.

REQUEST A DEMO or learn more about Hume.