一键分类

Use the One Click Classification feature to easily train document classifiers straight from the Document Understanding^TM interface. This feature allows bypassing the need for manually creating Datasets, Pipelines, and ML Skills in AI Center with the help of a new user experience within Document Understanding.

Make sure that your Document Understanding project is linked to AI Center before using this functionality.

分类选项

You can use One Click Classification with Document Manager and/or Forms AI and can identify it by the Classify button.

To use One Click Classification, upload your documents in a Document Type session. Click on the New button and select one of the following options: Using Forms AI (fixed layout forms) or Using Semi-structured AI. Both options open a session where you can upload your documents. Once documents have been uploaded in their respective Document type session, you can use the New Classifier button to open the One Click Classification dialog.

The Classify button opens a dropdown with two options: Automated Training and Manual Training. Before using any of these options, make sure you have at least two Document Understanding sessions created with at least ten samples each. Not complying results in an error as the one below.

自动化训练

Use the Automated Training option to train a classification dataset straight in Document Understanding. Once you choose this option, you have to add a Classifier Name, select the preferred Document Types, and select the version of the DocumentClassifier model. When finished, click the Train button.

此功能会自动在 AI Center 中使用您之前在“训练分类数据集”弹出窗口的“分类器名称”字段中指定的名称创建一个新的数据集。

详细信息

You can see more details about the created Automated Training action by clicking on the name of the classifier from the Classifiers page, or by clicking the actions menu, and selecting the Details option.

Here's a list with all the information provided by the Details option:

• Training set - Specifies the number of documents and number of pages processed.
• Documents classified - Specifies the number of classified documents.
• F1 Score - Provides an accuracy score percentage for the dataset.
• Status - Provides the status of the classification action.
• Document types - Provides the list of Document types used for the action.
• Package Name - Provides the name of the used ML Package.
• Package Version - Provides the used version of the DocumentClassifier model.
• ML Skill details - Provides the URL of the ML Skill created for the dataset. You can copy it and use it in your workflow.
• Dataset link - Provides the public endpoint URL of the created (public) dataset.
• Pipeline details - Provides the URL of the pipeline created for the dataset.
• Score details - Specifies the accuracy score of the dataset.
• View/Hide Logs - Provides a list with all the logs of the created dataset. You can copy it and use it when needed.
  备注：

  Score details and Score percentage options are available for datasets running with DocumentClassifier version 23.1 or higher.

手动训练

Use the Manual Training option to export a classification dataset to AI Center and then train it in AI Center. Once you choose this option, you have to add a Dataset Name and select the preferred Document Types. When finished, click the Export button.

详细信息

You can see more details about the created Manual Training action by selecting the Classifiers tab from your project page, clicking on the actions menu, and selecting the Details option.

Here's a list with all the information provided by the Details option:

• Training set - Specifies the number of documents and number of pages processed.
• Documents classified - Specifies the number of classified documents.
• F1 Score - Provides an accuracy score percentage for the dataset.
• Status - Provides the status of the classification action.
• Document types - Provides the list of Document types used for the action.
• Package Name - Provides the name of the used ML Package.
• Package Version - Provides the used version of the DocumentClassifier model.
• ML Skill details - Provides the URL of the ML Skill created for the dataset. You can copy it and use it in your workflow.
• Dataset link - Provides the public endpoint URL of the created (public) dataset.
• Pipeline details - Provides the URL of the pipeline created for the dataset.
• Score details - Specifies the accuracy score of the dataset.
• View/Hide Logs - Provides a list with all the logs of the created dataset. You can copy it and use it when needed.

分类器状态

You can check the status of all your classification actions by using the Classifiers tab from your project page.

概述

选择“分类器”选项卡后，您可以看到四个不同的列，每个列都显示有关已创建的分类操作的信息。您可以按字母顺序升序或降序对它们单独排序，也可以将它们保留为默认状态，按创建日期整理，让最新的在顶部：

• Name - Displays the name of the classification actions.
• Type - Displays the type of classification action (export or train).
• Creation date - Displays the creation date.
• Status - Displays the status of the action. There are multiple available statuses for each action. Check the table below for more details.
• Refresh - Refreshes the statuses for all actions, displaying the most recent ones.

状态	描述	分类选项
可用	操作已成功执行。	自动化训练
正在进行	该操作仍在执行中。	自动化训练
导出已完成	操作已成功执行。	手动训练
正在导出	该操作仍在执行中。	手动训练
未启动	尚未开始执行操作。	Automated Training Manual Training
不同步	Document Understanding 中的状态与 AI Center 中的状态不同步。	Automated Training Manual Training
已暂停	操作已暂停。	Automated Training Manual Training

操作菜单

操作菜单位于右侧，打开后提供以下选项：

• Copy URL - Allows you to copy the URL of the public endpoint created with the Automated Training action.
• Details - Provides information about the created action.
• Delete - Deletes the created action from both Document Understanding and AI Center.
• Stop ML Skill - Stops the ML Skill for the Automated Training action.