Data extraction

Continuous Engine Updates

After your Dedicated AI Engine is trained for the first time, you may enjoy improved data extraction accuracy. As you continue using Rossum in production, all the data that you reviewed using Rossum’s Validation Screen can be used to retrain the engine and increase its accuracy. With Continuous Engine Updates, your engine is retrained on […]

Configuring fields for data extraction

Every Queue defines the structure of data fields that should be extracted. When editing this structure you have two options: Using Rossum pre-trained data fields (Rossum Generic AI engine has been pre-trained on certain Data fields and allows you to start extracting data without any additional training) Defining your custom fields (You can also define your custom fields and train […]

Editing Extraction Schema

Preparing an Extraction Schema is one of the most important tasks you need to do when configuring Rossum. You have a lot to define, including the names and formats of data fields you want to extract, necessary value constraints, and, if you’re using them, enum options. To configure your account, you can either use API, […]

What is Rossum AI engine?

An AI Engine is the brain behind the Rossum application. It is responsible for reading and extracting data from each document that is sent to Rossum. The AI Engine learns to identify and recognize information on documents holistically. It allows the engine to make generalized decisions based on hundreds of thousands of data that it […]

Do you need Generic or Dedicated AI Engine?

There are two types of the AI Engine – Generic AI Engine and Dedicated AI Engine. Generic AI Engine is an engine pre-trained by Rossum to process a specific document type. Currently, Rossum supports only one type of Generic AI Engine focused on invoice processing. This engine has been trained on many invoices of various […]

How Dedicated AI Engine training works

Note: If you want to use a Dedicated AI Engine make sure you have purchased the feature before you start the training process. After the purchase, the training process consists of the following steps: Extraction Schema set up. Dedicated AI Engine training requires a special schema set up. Rossum Solution Engineers will assist you with it. […]

Preparing Documents for training the Dedicated AI Engine

All documents that should be used for the Dedicated AI Engine training have to pass through a verification process. The verification process is done by using a Rossum Validation Screen. After an uploaded document is processed within Rossum, a data entry operator opens the Validation Screen and reviews the extracted data. If some data is wrong, […]

Training Dedicated AI Engine: Annotation best practices

If you have purchased Dedicated AI Engine functionality, Rossum will automatically train its AI to fit your specific needs (custom fields, specific document types, etc.). The training process runs in the background while you are using the Validation interface, however, it’s important to follow the best practices that are mentioned below to ensure that your Dedicated AI Engine achieves the […]

Annotations Guide, Part 1: Basic Rules

During the whole training process, it is important to follow the rules of the Annotation Process. Below are some basic rules that will help you to increase the accuracy of your Dedicated AI Engine: provide at least 500 documents. This is usually the minimum to achieve satisfactory accuracy. However, you may need more documents if […]

Automate data extraction from your documents with Artificial Intelligence.
Free trial