ワークフローを構築して使用する

Once you have published your model version, you can build an IXP Unstructured and complex documents workflow in Studio and consume it in Validation Station, Action Center, or Apps.

概要

Building an IXP Unstructured and complex documents workflow involves the following main steps:

1. Package installation
2. Taxonomy definition
3. Document digitization
4. ドキュメント分類
5. Document extraction
6. ドキュメント検証

Note: The taxonomy definition step only applies to Windows projects, not Cross-platform. To find out the differences between project types, check the sections that follow.

前提条件

When you start to build your Studio workflow, you must choose the type of project you want to run: Windows or Cross-platform. Each project type requires different packages.

Make sure you install the following package versions or newer, based on the project type:

Windows

• UiPath.DocumentUnderstanding.ML.Activities 1.31.1
• UiPath.Excel.Activities 2.24.3
• UiPath.IntelligentOCR.Activities 6.22.0
• UiPath.System.Activities 24.10.6
• UiPath.Testing.Activities 24.10.3
• UiPath.UIAutomation.Activities 24.10.7

クロスプラットフォーム

• UiPath.DocumentUnderstanding.Activities 2.12.0
• UiPath.System.Activities 24.10.6
• UiPath.UIAutomation.Activities 24.10.7

Note: Studio only supports IntelligentOCR in Windows projects and is not compatible with Cross-platform projects.

Regardless of the project type you choose, you can install the packages manually or automatically. To automatically install the packages, use the Document Understanding Process template. For more details on how to search and install templates in Studio, check Project templates.

Building an IXP workflow for Windows projects

To build an IXP workflow for Windows projects, proceed as follows:

1. In Studio Desktop, create a basic process.
2. When configuring your process, in the Compatibility field, select what type of workflow you want to build: Windows or Cross-platform. For more details, check About automation projects.
3. Set up your table fields in the Taxonomy Manager option in the Design tab.
   注:

   Taxonomy Manager:

   • supports creating tables instead of fields. If you use multiple documents, use table fields that map to IXP field groups in Taxonomy Manager.
   • is available only when the IntelligentOCR package is installed. This means that it is only available on Windows projects, not Cross-platform.
4. In the Sequence, add an Assign activity to specify where you want to read documents from.
5. Add a Load taxonomy activity to display the fields you previously configured.
6. Add a For Each activity to go through each document.
7. Drag and drop the following activities within For Each:
   • Digitize document to read the documents you provided, and obtain the Document Object Model output.
   • Classify Document Scope to configure classification models if you use multiple models and document types.
   • Generative Classifier to classify documents using generative models.
   Note: The classification step is optional if you already have a document type ID.
8. Add another For Each activity to go through each classification result.
9. Drag and drop the following activities within For Each:
   • Data Extraction Scope to configure extractor activities.
   • Generative Extractor to extract documents using generative models.
10. Optionally, you can set up custom business rules or a custom post-processing logic. For example, you can set an extraction confidence threshold in Load Taxonomy to decide if the document should reach human validation or not. For more details on how to set up validation rules, check the Validation settings section in Establishing the structure.
11. Add one of the following activities:
    • Present Validation Station to validate in Validation Station.
    • Create Validation Task to validate in Action Center.
    • Create Document Validation Artifacts to validate in Apps.

    In this validation step, you can also use other activities than the ones presented. For more details, check the following resources:

    検証ステーション

    • 検証ステーション
    • クラシック検証ステーション
    • コンパクト検証ステーション
    • ドキュメントのデジタル化の手動検証

    Action Center

    • ドキュメント検証アクションを作成
    • ドキュメント検証アクション完了まで待機し再開

    Apps (アプリ)

    • アプリ アクションを使用してドキュメントを検証する

Building an IXP workflow for Cross-platform projects

To build an IXP Unstructured and complex documents workflow for Cross-platform projects, proceed as follows:

Interpreting Validation Station results from IXP models

When using workflows that leverage models for IXP Unstructured and complex documents, the Validation Station serves as a crucial interface for reviewing, confirming, and refining the extracted data. Validation Station shows how the model interpreted the document, allowing you to understand the extraction accuracy, identify uncertain areas, and make corrections where needed.

In Validation Station, each document type and its corresponding fields are displayed alongside their extracted values and confidence indicators. These confidence levels, which are derived from both the OCR engine and the extraction model, allow you to verify the reliability of the extracted data.

For more details on the validation process, check the following resources:

• クラシック検証ステーション
• コンパクト検証ステーション

Comparing Windows and Cross-platform project workflows

The following table shows a comparison between the IXP workflows for Windows and Cross-platform projects:

	Windows	クロスプラットフォーム
Packages required	IntelligentOCR Document Understanding ML	Document Understanding
タクソノミーを定義する	The Taxonomy Manager option allows you to manually edit the table fields. 注: Taxonomy Manager is available only when the Intelligent OCR package is installed.	The Document Understanding package automatically displays the taxonomy fields from the IXP model in the Extract Document Data activity.
Studio type	Recommended to use with Studio Desktop.	Recommended to use with Studio Web.