What is Document Processing?
In the context of an investigation, document processing is the process of extracting useful information from text, documents and other unstructured data sources. Typically this is achieved through a combination of manual input and software-based tools.
In-combination with i2 Analyst’s Notebook, investigators and analysts use document processing to help them:
- Get the complete picture of an investigation
- Identify & explore the relationships between suspects, places and other entities
- Search across the content of case files
- Generate and analyse complex criminal networks
- Investigate individuals and their connections
- Discover hidden connections
What is entity extraction?
Entity extraction is the process of extracting useful information from text. More specifically, entity extraction refers to the process of grouping text that share a common characteristic.
See an example below:
What is an entity in i2 analyst notebook?
Entities in i2 analyst notebook
Entities in i2 Analyst Notebook are used to represent the real things that are parts of your investigation.
Examples of common entities include:
Processing Documents in i2 – the manual way
Transferring entities from documents to i2
During an investigation you will inevitably have documents and other forms of unstructured data amongst your case files. To transfer entities from your digital (or physical) documents to your i2 analyst notebook project, you normally have to manually create them by clicking “insert from palette”. You then need to also add an entity label, id and other attributes to complete the entity.
This manual approach above may suffice when creating a handful of entities, but it becomes unviable when you need to import entities from hundreds of thousands of documents!
Processing Documents in i2 – the automated way
Using the Sintelix plugin, you can drag and drop all your documents directly into i2 Analysts Notebook and have all your entities created for you automatically.
Not only does this save you a tremendous amount of time, but it also increases accuracy when creating entities.
Customising automated document processing in i2
Whilst Sintelix automatically extracts many important entities from documents out-of-the-box, it also allows you to supply your own list of entities (keywords or phrases) for extraction.
You can also customise the extraction process via easily adjustable extraction rulesets.
Try a Demo
Click below for instant access to a free trial of the Sintelix i2 plugin and start automatically creating entities from your documents today.