TeXtraction Menu

TeXtraction extracts data from free-text narratives and places the data into designated database fields for analysis

Entity Extraction

Extract all IP, website, email and mailing addresses, monetary amounts, social security numbers and quoted phrases from a document.

• Extract phrases to identify similarities in statements made by suspects, witnesses, or victims.
• Extract all the names from a document to find relationships between people. Identify how many times a person is contacted or mentioned in your data. Check those names against an exhaustive database of all known last names to uncover uniqueness or frequency.
• Extract phone numbers (regardless of inconsistencies in formatting) for telephone toll analysis.
• Extract email addresses, websites and IP addresses to identify and analyze patterns of suspicious activity.
• Extract mailing addresses for geocoding or frequency analysis. How many times has a particular address been mentioned even though you’ve never responded to a call at that location?

Information Extraction

Identify critical data elements in documents using powerful analytical methods. Extract and populate database fields with: point of entry, method of entry, suspect’s actions, weapon and property taken. TeXtraction doesn’t just look for the word, but analyzes the word in context of other words for more accurate information extraction.

Content Analysis

In addition to item and information extraction, TeXtraction performs analysis against your documents. Ever wonder how many times the word “break” was within proximity of the word “window”?

When a robbery occurs, how many times were words such as security, alarm, or guard mentioned?

Textraction informs you of your data. Discover which words are being used to describe others and how often words appear with other words.

TeXtraction creates analytical databases from any unstructured data, including police narratives