Classify Method

Defines the base for all classification mechanisms used to analyze and assign document types within a Content Model.

Remarks

The Classify Method is the core component responsible for determining the type of a document or folder by analyzing its content, structure, or other features. It is configured on a Content Model and invoked during classification activities to assign the most appropriate Content Type to each Batch Folder or Batch Page.

Overview

• A Classify Method implements the logic for document classification, supporting a variety of approaches such as rules-based, feature-based, or machine learning.
• It is used by the Classify activity and related commands to automate the assignment of document types.
• The method can be trained (if supported) using sample documents to improve accuracy.

Usage and Configuration

• Assign a Classify Method to the 'Classification Method' property of a Content Model to enable automated classification.
• Configure the method's settings and provide training samples as needed for your document set.
• Use the Train As and Train From commands to add training data, and Rebuild Training to retrain the model.
• The method can be extended by inheriting from this class to implement custom classification logic.

Related Concepts

• Content Model: The root object that organizes document types and classification logic.
• Content Type: The document type or category assigned by classification.
• Batch Folder, Batch Page: The items being classified.
• Train As, Train From, Rebuild Training: Commands for managing training data and retraining.

For more information, see the documentation for Content Model, Classify activity, and related training commands.

Derived Types

There are 6 implementations of Classify Method.

Labelset-Based	Classifies documents using Label Sets to determine the best matching document type.
Lexical	Provides a classification method that assigns document types based on text and/or image features, supporting both training-based and rules-based approaches.
LLM Classifier	Classifies a document by asking an AI to select the document type from a list.
Rules-Based	Classifies documents using rules defined on Document Type objects, enabling immediate and deterministic type assignment based on content extractors.
Search Classifier	Classifies documents by searching for similar items in a vector-based index.
Visual	Classifies documents or pages based on their visual appearance using image-based features, without requiring OCR.

Used By

Content Model