Classify Method - Revision history

Dgreenwood: /* About */

2026-02-02T14:52:49Z

About

← Older revision		Revision as of 09:52, 2 February 2026
Line 5:		Line 5:
	== About ==		== About ==

	There are currently 5 Classify Methods in Grooper:		There are currently 6 Classify Methods in Grooper:
	* [[Rules-Based]] - Classifies documents using simple "rules" defined by each '''Document Type's''' Positive Extractor and Negative Extractor properties.		* [[Rules-Based]] - Classifies documents using simple "rules" defined by each '''Document Type's''' Positive Extractor and Negative Extractor properties.
	* [[Lexical]] - Classifies documents based on text-based features on trained examples of each '''Document Type''' in the '''Content Model'''.		* [[Lexical]] - Classifies documents based on text-based features on trained examples of each '''Document Type''' in the '''Content Model'''.
	:<li class="fyi-bullet"> The Lexical method can be used to classify already separated, unclassified '''Batch Folders''' during the Classify activity. It also can be used with [[ESP Auto Separation]] to separate loose pages into classified '''Batch Folders''' during the Separate activity.		:<li class="fyi-bullet"> The Lexical method can be used to classify already separated, unclassified '''Batch Folders''' during the Classify activity. It also can be used with [[ESP Auto Separation]] to separate loose pages into classified '''Batch Folders''' during the Separate activity.
	* [[Labeling_Behavior_(Behavior)#About_Labelset-Based_Classification\|Labelset-Based]] - Classifies documents based on the presence of text-based labels defined in each '''Document Type's''' "[[Labeling Behavior\|label set]]"		* [[Labeling_Behavior_(Behavior)#About_Labelset-Based_Classification\|Labelset-Based]] - Classifies documents based on the presence of text-based labels defined in each '''Document Type's''' "[[Labeling Behavior\|label set]]"
			* [[LLM Classifier]] - Classifies documents by sending the document to a large language model (LLM) to select a Document Type from a list of the Content Model's Document Types.
	* [[Search Classifier]] - Classifies documents by finding similar documents in a [[AI Search\|search index]]. The Search Classifier method compares large language model (LLM) embeddings on unclassified documents to embeddings already collected for documents in the search index.		* [[Search Classifier]] - Classifies documents by finding similar documents in a [[AI Search\|search index]]. The Search Classifier method compares large language model (LLM) embeddings on unclassified documents to embeddings already collected for documents in the search index.
			**<li class="attn-bullet"> The '''Search Classifier''' method should be considered in-development and experimental. This feature has not been implemented in a production-ready environment.
	* [[Visual]] - Classifies documents with computer vision, using visual features on trained examples of each '''Document Type''' in the '''Content Model'''.		* [[Visual]] - Classifies documents with computer vision, using visual features on trained examples of each '''Document Type''' in the '''Content Model'''.
	:<li class="fyi-bullet"> This is a less common Classify Method. It is suitable only for highly-structured documents like forms whose general visual appearance does not change from document to document.		:<li class="fyi-bullet"> This is a less common Classify Method. It is suitable only for highly-structured documents like forms whose general visual appearance does not change from document to document.
	:<li class="fyi-bullet"> This is the only Classify Method that does not rely on text data. It can be used at scan-time when combined with "[[Event-Based Separation]]" using the "Content Type" event.		:<li class="fyi-bullet"> This is the only Classify Method that does not rely on text data. It can be used at scan-time when combined with "[[Event-Based Separation]]" using the "Content Type" event.

Dgreenwood at 21:41, 12 May 2025

2025-05-12T21:41:58Z

← Older revision		Revision as of 16:41, 12 May 2025
Line 2:		Line 2:

	<blockquote>{{#lst:Glossary\|Classify Method}}</blockquote>		<blockquote>{{#lst:Glossary\|Classify Method}}</blockquote>

			== About ==

	There are currently 5 Classify Methods in Grooper:		There are currently 5 Classify Methods in Grooper:

Dgreenwood at 21:40, 12 May 2025

2025-05-12T21:40:06Z

← Older revision		Revision as of 16:40, 12 May 2025
Line 1:		Line 1:
	{{stubs}}		{{stubs}}

	<blockquote>{{#lst:Glossary\|~~Classification~~ Method}}</blockquote>		<blockquote>{{#lst:Glossary\|Classify Method}}</blockquote>

	There are currently 5 Classify Methods in Grooper:		There are currently 5 Classify Methods in Grooper:
	* [[~~Rules-Based (Classification Method)\|~~Rules-Based]] - Classifies documents using simple "rules" defined by each '''Document Type's''' Positive Extractor and Negative Extractor properties.		* [[Rules-Based]] - Classifies documents using simple "rules" defined by each '''Document Type's''' Positive Extractor and Negative Extractor properties.
	* [[~~Lexical (Classification Method)\|~~Lexical]] - Classifies documents based on text-based features on trained examples of each '''Document Type''' in the '''Content Model'''.		* [[Lexical]] - Classifies documents based on text-based features on trained examples of each '''Document Type''' in the '''Content Model'''.
	:<li class="fyi-bullet"> The Lexical method can be used to classify already separated, unclassified '''Batch Folders''' during the Classify activity. It also can be used with [[ESP Auto Separation]] to separate loose pages into classified '''Batch Folders''' during the Separate activity.		:<li class="fyi-bullet"> The Lexical method can be used to classify already separated, unclassified '''Batch Folders''' during the Classify activity. It also can be used with [[ESP Auto Separation]] to separate loose pages into classified '''Batch Folders''' during the Separate activity.
	* [[Labeling_Behavior_(Behavior)#About_Labelset-Based_Classification\|Labelset-Based]] - Classifies documents based on the presence of text-based labels defined in each '''Document Type's''' "[[Labeling Behavior\|label set]]"		* [[Labeling_Behavior_(Behavior)#About_Labelset-Based_Classification\|Labelset-Based]] - Classifies documents based on the presence of text-based labels defined in each '''Document Type's''' "[[Labeling Behavior\|label set]]"
	* [[Search Classifier]] - Classifies documents by finding similar documents in a [[AI Search\|search index]]. The Search Classifier method compares large language model (LLM) embeddings on unclassified documents to embeddings already collected for documents in the search index.		* [[Search Classifier]] - Classifies documents by finding similar documents in a [[AI Search\|search index]]. The Search Classifier method compares large language model (LLM) embeddings on unclassified documents to embeddings already collected for documents in the search index.
	* [[~~Visual (Classification Method)\|~~Visual]] - Classifies documents with computer vision, using visual features on trained examples of each '''Document Type''' in the '''Content Model'''.		* [[Visual]] - Classifies documents with computer vision, using visual features on trained examples of each '''Document Type''' in the '''Content Model'''.
	:<li class="fyi-bullet"> This is a less common Classify Method. It is suitable only for highly-structured documents like forms whose general visual appearance does not change from document to document.		:<li class="fyi-bullet"> This is a less common Classify Method. It is suitable only for highly-structured documents like forms whose general visual appearance does not change from document to document.
	:<li class="fyi-bullet"> This is the only Classify Method that does not rely on text data. It can be used at scan-time when combined with "[[Event-Based Separation]]" using the "Content Type" event.		:<li class="fyi-bullet"> This is the only Classify Method that does not rely on text data. It can be used at scan-time when combined with "[[Event-Based Separation]]" using the "Content Type" event.

Dgreenwood: Dgreenwood moved page Classification Method (Property) to Classify Method

2025-05-12T21:12:22Z

Dgreenwood moved page Classification Method (Property) to Classify Method

← Older revision	Revision as of 16:12, 12 May 2025
(No difference)

Dgreenwood at 21:11, 12 May 2025

2025-05-12T21:11:29Z

← Older revision		Revision as of 16:11, 12 May 2025
Line 3:		Line 3:
	<blockquote>{{#lst:Glossary\|Classification Method}}</blockquote>		<blockquote>{{#lst:Glossary\|Classification Method}}</blockquote>

	~~Please see the following articles for more information~~:		There are currently 5 Classify Methods in Grooper:
	* [[Classification (~~Concept~~)\|~~Classification~~]]		* [[Rules-Based (Classification Method)\|Rules-Based]] - Classifies documents using simple "rules" defined by each '''Document Type's''' Positive Extractor and Negative Extractor properties.
	* [[Labeling_Behavior_(Behavior)#About_Labelset-Based_Classification\|Labelset-Based]]		* [[Lexical (Classification Method)\|Lexical]] - Classifies documents based on text-based features on trained examples of each '''Document Type''' in the '''Content Model'''.
	* [[~~Lexical (Classification Method)~~\|~~Lexical~~]]		:<li class="fyi-bullet"> The Lexical method can be used to classify already separated, unclassified '''Batch Folders''' during the Classify activity. It also can be used with [[ESP Auto Separation]] to separate loose pages into classified '''Batch Folders''' during the Separate activity.
	* [[~~Rules~~-~~Based (Classification Method)~~\|~~Rules-Based~~]]		* [[Labeling_Behavior_(Behavior)#About_Labelset-Based_Classification\|Labelset-Based]] - Classifies documents based on the presence of text-based labels defined in each '''Document Type's''' "[[Labeling Behavior\|label set]]"
	* [[Visual (Classification Method)\|Visual]]		* [[Search Classifier]] - Classifies documents by finding similar documents in a [[AI Search\|search index]]. The Search Classifier method compares large language model (LLM) embeddings on unclassified documents to embeddings already collected for documents in the search index.
			* [[Visual (Classification Method)\|Visual]] - Classifies documents with computer vision, using visual features on trained examples of each '''Document Type''' in the '''Content Model'''.
			:<li class="fyi-bullet"> This is a less common Classify Method. It is suitable only for highly-structured documents like forms whose general visual appearance does not change from document to document.
			:<li class="fyi-bullet"> This is the only Classify Method that does not rely on text data. It can be used at scan-time when combined with "[[Event-Based Separation]]" using the "Content Type" event.

Randallkinard at 17:47, 21 November 2024

2024-11-21T17:47:34Z

← Older revision		Revision as of 12:47, 21 November 2024
Line 9:		Line 9:
	* [[Rules-Based (Classification Method)\|Rules-Based]]		* [[Rules-Based (Classification Method)\|Rules-Based]]
	* [[Visual (Classification Method)\|Visual]]		* [[Visual (Classification Method)\|Visual]]

	~~== Glossary ==~~
	~~<u><big>'''Batch Folder'''</big></u>: {{#lst:Glossary\|Batch Folder}}~~

	~~<u><big>'''Classification Method'''</big></u>: {{#lst:Glossary\|Classification Method}}~~

	~~<u><big>'''Classification'''</big></u>: {{#lst:Glossary\|Classification}}~~

	~~<u><big>'''Content Model'''</big></u>: {{#lst:Glossary\|Content Model}}~~

	~~<u><big>'''Labelset-Based'''</big></u>: {{#lst:Glossary\|Labelset-Based}}~~

	~~<u><big>'''Lexical'''</big></u>: {{#lst:Glossary\|Lexical}}~~

	~~<u><big>'''Rules-Based'''</big></u>: {{#lst:Glossary\|Rules-Based}}~~

	~~<u><big>'''Visual'''</big></u>: {{#lst:Glossary\|Visual}}~~

Randallkinard at 13:27, 28 August 2024

2024-08-28T13:27:36Z

← Older revision		Revision as of 08:27, 28 August 2024
Line 1:		Line 1:
	~~{{AutoVersion}}~~

	{{stubs}}		{{stubs}}

Randallkinard at 15:30, 3 May 2024

2024-05-03T15:30:10Z

← Older revision		Revision as of 10:30, 3 May 2024
Line 11:		Line 11:
	* [[Rules-Based (Classification Method)\|Rules-Based]]		* [[Rules-Based (Classification Method)\|Rules-Based]]
	* [[Visual (Classification Method)\|Visual]]		* [[Visual (Classification Method)\|Visual]]

			== Glossary ==
			<u><big>'''Batch Folder'''</big></u>: {{#lst:Glossary\|Batch Folder}}

			<u><big>'''Classification Method'''</big></u>: {{#lst:Glossary\|Classification Method}}

			<u><big>'''Classification'''</big></u>: {{#lst:Glossary\|Classification}}

			<u><big>'''Content Model'''</big></u>: {{#lst:Glossary\|Content Model}}

			<u><big>'''Labelset-Based'''</big></u>: {{#lst:Glossary\|Labelset-Based}}

			<u><big>'''Lexical'''</big></u>: {{#lst:Glossary\|Lexical}}

			<u><big>'''Rules-Based'''</big></u>: {{#lst:Glossary\|Rules-Based}}

			<u><big>'''Visual'''</big></u>: {{#lst:Glossary\|Visual}}

Randallkinard: Created page with "{{AutoVersion}} {{stubs}}
{{#lst:Glossary|Classification Method}}
Please see the following articles for more information: * Classification * Labelset-Based * Lexical * Rules-Based * Visual"

2024-04-30T14:23:57Z

Created page with "{{AutoVersion}} {{stubs}} <blockquote>{{#lst:Glossary|Classification Method}}</blockquote> Please see the following articles for more information: * Classification * Labelset-Based * Lexical * Rules-Based * Visual"

New page

{{AutoVersion}}

{{stubs}}

<blockquote>{{#lst:Glossary|Classification Method}}</blockquote>

Please see the following articles for more information:
* [[Classification (Concept)|Classification]]
* [[Labeling_Behavior_(Behavior)#About_Labelset-Based_Classification|Labelset-Based]]
* [[Lexical (Classification Method)|Lexical]]
* [[Rules-Based (Classification Method)|Rules-Based]]
* [[Visual (Classification Method)|Visual]]

← Older revision		Revision as of 16:40, 12 May 2025
Line 1:		Line 1:
	{{stubs}}		{{stubs}}

	<blockquote>{{#lst:Glossary\|~~Classification~~ Method}}</blockquote>		<blockquote>{{#lst:Glossary\|Classify Method}}</blockquote>

	There are currently 5 Classify Methods in Grooper:		There are currently 5 Classify Methods in Grooper:
	* [[~~Rules-Based (Classification Method)\|~~Rules-Based]] - Classifies documents using simple "rules" defined by each '''Document Type's''' Positive Extractor and Negative Extractor properties.		* [[Rules-Based]] - Classifies documents using simple "rules" defined by each '''Document Type's''' Positive Extractor and Negative Extractor properties.
	* [[~~Lexical (Classification Method)\|~~Lexical]] - Classifies documents based on text-based features on trained examples of each '''Document Type''' in the '''Content Model'''.		* [[Lexical]] - Classifies documents based on text-based features on trained examples of each '''Document Type''' in the '''Content Model'''.
	:<li class="fyi-bullet"> The Lexical method can be used to classify already separated, unclassified '''Batch Folders''' during the Classify activity. It also can be used with [[ESP Auto Separation]] to separate loose pages into classified '''Batch Folders''' during the Separate activity.		:<li class="fyi-bullet"> The Lexical method can be used to classify already separated, unclassified '''Batch Folders''' during the Classify activity. It also can be used with [[ESP Auto Separation]] to separate loose pages into classified '''Batch Folders''' during the Separate activity.
	* [[Labeling_Behavior_(Behavior)#About_Labelset-Based_Classification\|Labelset-Based]] - Classifies documents based on the presence of text-based labels defined in each '''Document Type's''' "[[Labeling Behavior\|label set]]"		* [[Labeling_Behavior_(Behavior)#About_Labelset-Based_Classification\|Labelset-Based]] - Classifies documents based on the presence of text-based labels defined in each '''Document Type's''' "[[Labeling Behavior\|label set]]"
	* [[Search Classifier]] - Classifies documents by finding similar documents in a [[AI Search\|search index]]. The Search Classifier method compares large language model (LLM) embeddings on unclassified documents to embeddings already collected for documents in the search index.		* [[Search Classifier]] - Classifies documents by finding similar documents in a [[AI Search\|search index]]. The Search Classifier method compares large language model (LLM) embeddings on unclassified documents to embeddings already collected for documents in the search index.
	* [[~~Visual (Classification Method)\|~~Visual]] - Classifies documents with computer vision, using visual features on trained examples of each '''Document Type''' in the '''Content Model'''.		* [[Visual]] - Classifies documents with computer vision, using visual features on trained examples of each '''Document Type''' in the '''Content Model'''.
	:<li class="fyi-bullet"> This is a less common Classify Method. It is suitable only for highly-structured documents like forms whose general visual appearance does not change from document to document.		:<li class="fyi-bullet"> This is a less common Classify Method. It is suitable only for highly-structured documents like forms whose general visual appearance does not change from document to document.
	:<li class="fyi-bullet"> This is the only Classify Method that does not rely on text data. It can be used at scan-time when combined with "[[Event-Based Separation]]" using the "Content Type" event.		:<li class="fyi-bullet"> This is the only Classify Method that does not rely on text data. It can be used at scan-time when combined with "[[Event-Based Separation]]" using the "Content Type" event.

← Older revision		Revision as of 16:11, 12 May 2025
Line 3:		Line 3:
	<blockquote>{{#lst:Glossary\|Classification Method}}</blockquote>		<blockquote>{{#lst:Glossary\|Classification Method}}</blockquote>

	~~Please see the following articles for more information~~:		There are currently 5 Classify Methods in Grooper:
	* [[Classification (~~Concept~~)\|~~Classification~~]]		* [[Rules-Based (Classification Method)\|Rules-Based]] - Classifies documents using simple "rules" defined by each '''Document Type's''' Positive Extractor and Negative Extractor properties.
	* [[Labeling_Behavior_(Behavior)#About_Labelset-Based_Classification\|Labelset-Based]]		* [[Lexical (Classification Method)\|Lexical]] - Classifies documents based on text-based features on trained examples of each '''Document Type''' in the '''Content Model'''.
	* [[~~Lexical (Classification Method)~~\|~~Lexical~~]]		:<li class="fyi-bullet"> The Lexical method can be used to classify already separated, unclassified '''Batch Folders''' during the Classify activity. It also can be used with [[ESP Auto Separation]] to separate loose pages into classified '''Batch Folders''' during the Separate activity.
	* [[~~Rules~~-~~Based (Classification Method)~~\|~~Rules-Based~~]]		* [[Labeling_Behavior_(Behavior)#About_Labelset-Based_Classification\|Labelset-Based]] - Classifies documents based on the presence of text-based labels defined in each '''Document Type's''' "[[Labeling Behavior\|label set]]"
	* [[Visual (Classification Method)\|Visual]]		* [[Search Classifier]] - Classifies documents by finding similar documents in a [[AI Search\|search index]]. The Search Classifier method compares large language model (LLM) embeddings on unclassified documents to embeddings already collected for documents in the search index.
			* [[Visual (Classification Method)\|Visual]] - Classifies documents with computer vision, using visual features on trained examples of each '''Document Type''' in the '''Content Model'''.
			:<li class="fyi-bullet"> This is a less common Classify Method. It is suitable only for highly-structured documents like forms whose general visual appearance does not change from document to document.
			:<li class="fyi-bullet"> This is the only Classify Method that does not rely on text data. It can be used at scan-time when combined with "[[Event-Based Separation]]" using the "Content Type" event.