2023:Rules-Based (Classify Method) - Revision history

Dgreenwood: Dgreenwood moved page 2023:Rules-Based (Classification Method) to 2023:Rules-Based (Classify Method)

2025-06-25T15:34:25Z

Dgreenwood moved page 2023:Rules-Based (Classification Method) to 2023:Rules-Based (Classify Method)

← Older revision	Revision as of 10:34, 25 June 2025
(No difference)

Dgreenwood at 21:17, 12 May 2025

2025-05-12T21:17:49Z

← Older revision		Revision as of 16:17, 12 May 2025
Line 157:		Line 157:
	=== Mixed Classification: Combining Training-Based and Rules-Based Approaches ===		=== Mixed Classification: Combining Training-Based and Rules-Based Approaches ===

	Furthermore, a rules-based approach can be combined with a training-based approach when using the ''[[Lexical]]'' ~~'''''Classification Method'''''~~. The ''Lexical'' method uses trained examples '''Document Types''' to classify documents. It uses a [[TF-IDF]] algorithm to weight the importance text features (such as words and phrases) based on this trained examples. However, even when choosing ''Lexical'' for the '''''Classification Method''''', the '''''Positive Extractor'''''' and '''''Negative Extractor''''' properties are still present on '''Document Types'''.		Furthermore, a rules-based approach can be combined with a training-based approach when using the ''[[Lexical]]'' method. The ''Lexical'' method uses trained examples '''Document Types''' to classify documents. It uses a [[TF-IDF]] algorithm to weight the importance text features (such as words and phrases) based on this trained examples. However, even when choosing ''Lexical'' for the '''''Classification Method''''', the '''''Positive Extractor'''''' and '''''Negative Extractor''''' properties are still present on '''Document Types'''.

	Generally, the '''''Positive Extractor's''''' result will "win out" over training based classification results, because the '''''Positive Extractor's''''' confidence result (as a percentage value) will be higher than the document's similarity to the trained examples (as a percentage value) for a '''Document Type'''. This way, if you have a value which can be extracted that you know is going to be on a '''Document Type''', you can take advantage of setting a '''''Positive Extractor''''' on the '''Document Type''' to classify them. For example, document titles are often used as "rules". If you can extract text to match a title to a corresponding '''Document Type''', this is often a quick and easy way to classify a document. But, if that extractor fails for whatever reason (because of bad OCR or a new title not matching the extractor's regex), you have training data which can act as a backup classification method.		Generally, the '''''Positive Extractor's''''' result will "win out" over training based classification results, because the '''''Positive Extractor's''''' confidence result (as a percentage value) will be higher than the document's similarity to the trained examples (as a percentage value) for a '''Document Type'''. This way, if you have a value which can be extracted that you know is going to be on a '''Document Type''', you can take advantage of setting a '''''Positive Extractor''''' on the '''Document Type''' to classify them. For example, document titles are often used as "rules". If you can extract text to match a title to a corresponding '''Document Type''', this is often a quick and easy way to classify a document. But, if that extractor fails for whatever reason (because of bad OCR or a new title not matching the extractor's regex), you have training data which can act as a backup classification method.

Randallkinard at 15:15, 22 November 2024

2024-11-22T15:15:38Z

← Older revision		Revision as of 10:15, 22 November 2024
Line 163:		Line 163:
	Many of the best classification strategies involve combining the training-based ''Lexical'' method with a rules-based approach.		Many of the best classification strategies involve combining the training-based ''Lexical'' method with a rules-based approach.
	<!--#endregion-->		<!--#endregion-->

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

Randallkinard at 15:17, 27 August 2024

2024-08-27T15:17:21Z

@@ Line 8: / Line 8: @@
 Classification is then performed using the '''[[Classify]]''' activity, using the extraction rules established by the '''''Positive''''' and '''''Negative Extractor''''' properties of '''Document Types''' in a '''Content Model'''.
 == About ==
@@ Line 202: / Line 163: @@
 Many of the best classification strategies involve combining the training-based ''Lexical'' method with a rules-based approach.
 <!--#endregion-->

Randallkinard at 17:43, 10 May 2024

2024-05-10T17:43:15Z

← Older revision		Revision as of 12:43, 10 May 2024
Line 8:		Line 8:

	Classification is then performed using the '''[[Classify]]''' activity, using the extraction rules established by the '''''Positive''''' and '''''Negative Extractor''''' properties of '''Document Types''' in a '''Content Model'''.		Classification is then performed using the '''[[Classify]]''' activity, using the extraction rules established by the '''''Positive''''' and '''''Negative Extractor''''' properties of '''Document Types''' in a '''Content Model'''.

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

			<u><big>'''TF-IDF'''</big></u>: {{#lst:Glossary\|TF-IDF}}

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

	== About ==		== About ==

Randallkinard at 14:48, 22 April 2024

2024-04-22T14:48:31Z

← Older revision		Revision as of 09:48, 22 April 2024
Line 1:		Line 1:
	~~<!--#region Intro-->~~
	{{AutoVersion}}		{{AutoVersion}}
	~~<section begin="glossary" />~~
	<blockquote>		<blockquote>{{#lst:Glossary\|Rules-Based}}</blockquote>
	~~The ''~~Rules-Based'' '''''[[Classification Method]]''''' is one of three methods of classifying documents available to Grooper. This approach uses [[Data Extractor]]s to find key words, phrases, or other text-based information in order to identify and classify a document (assigning a '''[[Document Type]]''' to the '''[[Batch Folder\|Document Folder]]''').
	</blockquote>
	~~<section end="glossary" />~~
	The ''Rules-Based'' method classifies documents according to "rules" using the '''''Positive Extractor''''' and '''''Negative Extractor''''' properties of '''Document Type''' objects in a '''[[Content Model]]'''.		The ''Rules-Based'' method classifies documents according to "rules" using the '''''Positive Extractor''''' and '''''Negative Extractor''''' properties of '''Document Type''' objects in a '''[[Content Model]]'''.

Line 11:		Line 8:

	Classification is then performed using the '''[[Classify]]''' activity, using the extraction rules established by the '''''Positive''''' and '''''Negative Extractor''''' properties of '''Document Types''' in a '''Content Model'''.		Classification is then performed using the '''[[Classify]]''' activity, using the extraction rules established by the '''''Positive''''' and '''''Negative Extractor''''' properties of '''Document Types''' in a '''Content Model'''.
	~~<!--#endregion-->~~

	== About ==		== About ==

	''Rules-Based'' classification can be enabled and configured on any '''Content Model''' object. To do so, select the '''''Classification Method''''' property and select ''Rules-Based''.		''Rules-Based'' classification can be enabled and configured on any '''Content Model''' object. To do so, select the '''''Classification Method''''' property and select ''Rules-Based''.


	[[File:2023 Rules Based (Classification Method) - 2023 01 About 01.png\|center\|1000px]]		[[File:2023 Rules Based (Classification Method) - 2023 01 About 01.png\|center\|1000px]]

Dsmith at 14:25, 5 February 2024

2024-02-05T14:25:48Z

← Older revision		Revision as of 09:25, 5 February 2024
Line 160:		Line 160:
	<!--#region Mixed Classification-->		<!--#region Mixed Classification-->

	~~==== AND Collation ====~~

	=== Mixed Classification: Combining Training-Based and Rules-Based Approaches ===		=== Mixed Classification: Combining Training-Based and Rules-Based Approaches ===

Dsmith at 20:23, 2 February 2024

2024-02-02T20:23:17Z

← Older revision		Revision as of 15:23, 2 February 2024
Line 159:		Line 159:
	<!--#endregion-->		<!--#endregion-->
	<!--#region Mixed Classification-->		<!--#region Mixed Classification-->

			==== AND Collation ====

	=== Mixed Classification: Combining Training-Based and Rules-Based Approaches ===		=== Mixed Classification: Combining Training-Based and Rules-Based Approaches ===

Dgreenwood at 15:22, 12 January 2024

2024-01-12T15:22:02Z

← Older revision		Revision as of 10:22, 12 January 2024
Line 77:		Line 77:
	If we create a '''Data Type''' returning this title, we can then assign it to the '''''Positive Extractor''''' property of the "Data Information Sheet" '''Document Type'''.		If we create a '''Data Type''' returning this title, we can then assign it to the '''''Positive Extractor''''' property of the "Data Information Sheet" '''Document Type'''.

	{\|~~cellpadding~~="~~10" cellspacing="5~~"		{\|class="fyi-box"
	\|~~-style="background-color:#36b0a7; color:white"~~		\|
	~~\|style="font-size:14pt"\|~~'''FYI'''\|\|The '''''Positive Extractor''''' can be set to a variety of extraction options, including ''Reference'', ''Text Pattern'', ''Read Zone'', ''Find Barcode'', ''Read Barcode'', ''Labeled OMR'', ''Ordered OMR'', and ''Zonal OMR''.		'''FYI'''
			\|
			The '''''Positive Extractor''''' can be set to a variety of extraction options, including ''Reference'', ''Text Pattern'', ''Read Zone'', ''Find Barcode'', ''Read Barcode'', ''Labeled OMR'', ''Ordered OMR'', and ''Zonal OMR''.

	While using the ''Reference'' option, pointing to a '''Data Type''' in the Node Tree, is the most common configuration, any extractor returning a result will positively classify the document.		While using the ''Reference'' option, pointing to a '''Data Type''' in the Node Tree, is the most common configuration, any extractor returning a result will positively classify the document.
Line 135:		Line 137:
	Even if the '''''Positive Extractor''''' produces a result, if the '''''Negative Extractor''''' ''also'' produces a result, it will override classification. The document will be ''prevented'' from being classified as a "Federal W-4" '''Document Type'''.		Even if the '''''Positive Extractor''''' produces a result, if the '''''Negative Extractor''''' ''also'' produces a result, it will override classification. The document will be ''prevented'' from being classified as a "Federal W-4" '''Document Type'''.

	{\|~~cellpadding~~="~~10" cellspacing="5~~"		{\|class="fyi-box"
	\|~~-style="background-color:#36b0a7; color:white"~~		\|
	~~\|style="font-size:14pt"\|~~'''FYI'''\|\|The '''''Positive Extractor''''' can be set to a variety of extraction options, including ''Reference'', ''Text Pattern'', ''Read Zone'', ''Find Barcode'', ''Read Barcode'', ''Labeled OMR'', ''Ordered OMR'', and ''Zonal OMR''.		'''FYI'''
			\|
			The '''''Positive Extractor''''' can be set to a variety of extraction options, including ''Reference'', ''Text Pattern'', ''Read Zone'', ''Find Barcode'', ''Read Barcode'', ''Labeled OMR'', ''Ordered OMR'', and ''Zonal OMR''.

	While using the ''Reference'' option, pointing to a '''Data Type''' in the Node Tree, is the most common configuration, any extractor returning a result will positively classify the document.		While using the ''Reference'' option, pointing to a '''Data Type''' in the Node Tree, is the most common configuration, any extractor returning a result will positively classify the document.

Dgreenwood at 22:16, 8 January 2024

2024-01-08T22:16:59Z

← Older revision		Revision as of 17:16, 8 January 2024
Line 1:		Line 1:
	<!--#region Intro-->		<!--#region Intro-->
	{{AutoVersion}}		{{AutoVersion}}
	<~~blockquote style~~="~~font-size:14pt~~">		<section begin="glossary" />
			<blockquote>
	The ''Rules-Based'' '''''[[Classification Method]]''''' is one of three methods of classifying documents available to Grooper. This approach uses [[Data Extractor]]s to find key words, phrases, or other text-based information in order to identify and classify a document (assigning a '''[[Document Type]]''' to the '''[[Batch Folder\|Document Folder]]''').		The ''Rules-Based'' '''''[[Classification Method]]''''' is one of three methods of classifying documents available to Grooper. This approach uses [[Data Extractor]]s to find key words, phrases, or other text-based information in order to identify and classify a document (assigning a '''[[Document Type]]''' to the '''[[Batch Folder\|Document Folder]]''').
	</blockquote>		</blockquote>
			<section end="glossary" />
	The ''Rules-Based'' method classifies documents according to "rules" using the '''''Positive Extractor''''' and '''''Negative Extractor''''' properties of '''Document Type''' objects in a '''[[Content Model]]'''.		The ''Rules-Based'' method classifies documents according to "rules" using the '''''Positive Extractor''''' and '''''Negative Extractor''''' properties of '''Document Type''' objects in a '''[[Content Model]]'''.

← Older revision		Revision as of 10:15, 22 November 2024
Line 163:		Line 163:
	Many of the best classification strategies involve combining the training-based ''Lexical'' method with a rules-based approach.		Many of the best classification strategies involve combining the training-based ''Lexical'' method with a rules-based approach.
	<!--#endregion-->		<!--#endregion-->

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

← Older revision		Revision as of 12:43, 10 May 2024
Line 8:		Line 8:

	Classification is then performed using the '''[[Classify]]''' activity, using the extraction rules established by the '''''Positive''''' and '''''Negative Extractor''''' properties of '''Document Types''' in a '''Content Model'''.		Classification is then performed using the '''[[Classify]]''' activity, using the extraction rules established by the '''''Positive''''' and '''''Negative Extractor''''' properties of '''Document Types''' in a '''Content Model'''.

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

			<u><big>'''TF-IDF'''</big></u>: {{#lst:Glossary\|TF-IDF}}

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

	== About ==		== About ==