--- title: "Structured Document Classification" slug: "structured-document-classification" updated: 2026-01-21T20:08:19Z published: 2026-01-21T20:08:19Z canonical: "help.hyperscience.ai/structured-document-classification" --- > ## Documentation Index > Fetch the complete documentation index at: https://help.hyperscience.ai/llms.txt > Use this file to discover all available pages before exploring further. # Structured Document Classification ## Classification models in Hyperscience Classification models are a crucial part of document processing as they help the system determine which layout should be used to process each page you upload. In Hyperscience, we have two types of document classification: - **Structured Document Classification** - Automatically classifies documents that follow a consistent layout pattern (e.g., tax forms, standardized applications) by assigning them to the correct layout in Hyperscience. Once classified, the documents can proceed to the next step - **Field Identification Task**, **Transcription Task,** or **Flexible Extraction,** depending on your business logic. - **Semi-structured Document Classification -** Automatically classifies documents that don’t follow a consistent layout pattern (e.g., invoices, bank statements, etc.). To learn more, see [Semi-structured Document Classification](/v42/docs/clone-v42-draft-semi-structured-document-classification) and [TDM for Classification Models](/v42/docs/tdm-for-classification-models). In this article, you’ll learn how to work with Structured Document Classification. Learn more about Identification in [TDM for Identification Models](/v42/docs/v42-tdm-for-identification-models). To learn about Transcription and Flexible Extraction, see our [Transcription](/v42/docs/transcription1) and [Flexible Extraction](/v42/docs/flexible-extraction) articles. ## Structured Document Classification ### How it works When a document is submitted to the system, it is first split into individual pages. Structured Document Classification then runs through the following steps: 1. **Visual Page Classifier (Visual Page Classifier (VPC)):** - The system runs VPC, which returns layout page-level candidates for each submission page. At this stage, only candidates are proposed, not full documents. - For every page, the VPC produces a list of possible layout matches, ranked by confidence. To learn more about Structured layouts, see [Creating Structured Layouts](/v42/docs/creating-structured-layouts). - **Example**: Submission page 1 may match layout page 1 of Layout A; submission page 2 may match layout page 2 of Layout A, etc. 2. **Distribute to Forms:** - Using the list of candidates generated from the VPC, the system attempts to group pages into complete documents. - The goal is to minimize the number of documents while maximizing confidence scores across all pages. - Pages that fail to align with any layout at this stage are passed to Semi-structured classification (Non-Structured Layout Classifier (NLC)). To learn more, see [Semi-structured Document Classification](/v42/docs/clone-v42-draft-semi-structured-document-classification). 3. **Registration:** - For each proposed distribution, the system runs a Registration step to validate the page-to-layout matches. - If confidence for all candidates is above the acceptance threshold (e.g., >0.6), the document is accepted. - If one or more candidates are rejected, the system re-runs Distribute to Forms with alternative matches. 4. **Re-distribution & Finalization:** - The Distribution - Registration cycle runs up to three times: - **First attempt:** Initial grouping of candidates. - **Second attempt**: Re-distribution if a candidate is rejected. - **Third attempt:** Final re-distribution. - If all candidates are successfully registered, the current distribution is finalized and used. - If some candidates are rejected, the system generates a new distribution and retries registration. - If none of the attempts result in a fully valid distribution, the system returns the best-scoring distribution from the three tries. - This process repeats up to 3 times. 5. **Manual Review:** - Any pages that fail to classify after these steps are marked as **No Layout Found** and routed to Semi-structured Classification. Depending on your flows settings and your use case, these can be handled via Document Classification Supervision Task.To learn more, see [Semi-structured Document Classification](/v42/docs/clone-v42-draft-semi-structured-document-classification). > [!NOTE] > Blank Pages > > If a page contains very little text, VPC may match it as blank and will not attempt to classify it to a layout. #### Structured Layout Match Threshold The Structured Layout Match Threshold defines the minimum confidence score required for a page to be automatically matched to a Structured layout. - The default threshold is 0.6, but it can be adjusted to fit your use case. - Lowering the threshold may increase the risk of incorrect matches. > [!NOTE] > Layout Matching Confidence > > Confidence in layout matching directly affects the accuracy. The more confident the system is in its layout match, the more reliable the extracted data will be. To learn more, see our [Accuracy](/v42/docs/accuracy) article. > > Contact your Hyperscience representative to determine the best threshold for your use case. Expand the sections below to learn more about the Structured document classification settings and layout identifiers. ### Structured Document Classification Settings Before you start, configure **Structured** document classification behavior in your flow. - Enable **Manual Classification Supervision** to use the **Document Classification** task, as described in [Document Processing Subflow Settings](/v42/docs/document-processing-subflow-settings). - **Structured Layout Match Threshold** - This threshold controls whether a **Structured** page is matched to a layout. - Pages with confidence **below** the threshold are sent to **Document Classification** or marked as **No Layout Variation Found**. - Pages with a confidence score **above** the threshold are automatically assigned to a layout. - **Validate Classification Using Layout ID** - Enabling this setting allows Structured documents to be matched using a layout identifier. When this setting is enabled, the system checks for a matching layout identifier in the document. - **Bypass Validation if Layout ID is Missing** - This setting should be enabled when certain layouts do not contain a layout identifier. Learn more about these settings in the Classification section of our [Document Processing Subflow Settings](/v42/docs/document-processing-subflow-settings) article. ### Layout Identifiers #### Classifying Variations Some layouts can look almost identical, with only minor visual differences. To avoid misclassification in these cases, you can create layout variations. Each variation represents a small difference in the layout’s pattern, while still belonging to the same overall layout group. Learn more in [Adding a Variation to a Layout](/v42/docs/adding-a-variation-to-a-layout). #### Layout Identifiers Even with variations, the system may sometimes classify incorrectly. To improve accuracy, Hyperscience can use Layout identifiers to force the correct match. - If the identifier in the document matches the expected ID in a layout variation, the system will classify the document to that variation, regardless of the confidence score. - If the identifier does not match, the document is routed either to **Document Classification Task** or to **Document Drift Management (Layout Triage)**, depending on your flow settings: - With **Manual Classification** off, the document goes directly to **Document Drift Management**. To learn more, see [Document Drift Management (Layout Triage)](/v42/docs/document-drift-management-layout-triage) - With **Manual Classification** on, the document is reviewed further by a keyer. To learn more, see [Document Classification Task](/v42/docs/v42-draft-document-classification#document-classification-task) section of this article. #### Using Layout Identifiers 1. Go to **Library** > **Layouts**. 2. Find the layout to which you want to add a layout ID, and click on its name. 3. Find the variation to which you want to add a Layout ID, and click on its name. 4. Click **Fields** in the toolbar, and then click **Layout IDs**. ![](https://cdn.us.document360.io/87894cef-4958-4f3f-be6f-b75a78c82548/Images/Documentation/identifiers.jpg) 5. Click and drag to draw bounding boxes around each layout ID. - Once you draw a box, the machine will read and transcribe the value inside it. - Any incorrect transcriptions can be edited in the field list. 6. When you’re finished making changes to the variation, do one of the following: - If you’re ready to apply your changes to the variation, click **Commit Changes** and save it as a new version. Learn more in [Editing and Finalizing a Layout Version](/v42/docs/editing-and-finalizing-a-layout-version). - If you’re not ready to apply your changes, click the **X** button in the upper-right corner of the page. #### Layout Identifiers Best Practices The following best practices for using layout identifiers will ensure the highest levels of accuracy for the classification of Structured documents. - Use unique text at the top or the bottom of the page as a layout identifier. - The ideal layout identifier is a piece of unique text placed at the top or bottom of a page. Many documents include layout-specific versions, dates, or other identifiers in these areas. Using such identifiers helps reduce errors and improve the accuracy of matching pages to Structured layouts. - If no unique text appears at the top or bottom of the page, use another piece of variation-specific text elsewhere. - If no identifier is available at the top or bottom of the page, look for unique text within the document that appears only in a specific variation. For example, a clause included in just one variation can serve as a distinguishing factor. Using this text as a layout identifier helps the system correctly classify that variation. - Add only the layout identifiers required to tell similar layouts apart. - Each layout page should have only one identifier. In rare cases where multiple layouts share the same identifier, you can add a second one to distinguish between them. Avoid adding extra identifiers, as they reduce matching accuracy. - Structured layouts are limited to two identifiers. If you try to add more, the system displays a warning message. - Keep the number of layout identifiers consistent across all variations of the same layout. - If a layout has multiple variations, use the same number of identifiers across all of them. Otherwise, variations with more identifiers will receive a higher confidence boost, which may cause the wrong layout to be matched. ## Document Classification task Document Classification is a Supervision task used to group pages into documents and assign the correct layout. These tasks are created when automatic classification isn’t possible (e.g., when no model is available or the model’s confidence is low). ![](https://cdn.us.document360.io/87894cef-4958-4f3f-be6f-b75a78c82548/Images/Documentation/image(176).png) Expand the section below to learn how to navigate the interface and complete a Document Classification task. ### Document Classification Interface To open a Document Classification task, go to the **Tasks** section and click **Perform Tasks** under the **Supervision task type** table. ![](https://cdn.us.document360.io/87894cef-4958-4f3f-be6f-b75a78c82548/Images/Documentation/doc_class.jpg) Document Classification allows you to: - Add uncategorized pages to grouped documents. - Reorder pages in grouped documents. - Remove pages from grouped documents. - Classify (apply layouts to) manually grouped documents. - Reclassify (apply different layouts to) machine-misclassified documents. ![](https://cdn.us.document360.io/87894cef-4958-4f3f-be6f-b75a78c82548/Images/Documentation/doc_class_ui(1).jpg) #### Left Panel - Uncategorized ![](https://cdn.us.document360.io/87894cef-4958-4f3f-be6f-b75a78c82548/Images/Documentation/uncategorized.jpg) The left panel displays all uncategorized pages - pages that haven’t yet been grouped into a document. > [!NOTE] > Order of Uncategorized pages > > Pages in this panel appear in the order they were submitted to the system, with a thumbnail preview for quick scanning. - Select pages using your mouse or keyboard shortcuts. - For a full shortcut list, click the![](https://cdn.us.document360.io/87894cef-4958-4f3f-be6f-b75a78c82548/Images/Documentation/image(179).png)button. - You can also select all uncategorized pages by clicking the **Select All** button. - Click the **Create New Doc (OPTION+N)** button to group the selected pages into a new document. - To submit the Document Classification task, all pages from the left panel must be categorized. ![](https://cdn.us.document360.io/87894cef-4958-4f3f-be6f-b75a78c82548/Images/Documentation/classification_variations_change(1).gif) #### Middle Panel - Grouped Documents ![](https://cdn.us.document360.io/87894cef-4958-4f3f-be6f-b75a78c82548/Images/Documentation/middle.jpg) The middle panel shows all documents you’ve grouped. In this panel, you can: - Select a layout from the drop-down. - If a page doesn’t match any of the available layouts, you can use one of the categories below: - **Additional Form Page (No Layout Found) -** Sends the page to the **No Layout Found** workflow for review. These pages can be reviewed later and may help define a new layout. To learn more, see [Document Drift Management (Layout Triage)](/v42/docs/document-drift-management-layout-triage) and [Creating Additional Layouts](/v42/docs/creating-additional-layouts). - **Blank Page -** Marks the page as blank. It’s excluded from processing. - **Excluded** (formerly **“***Other****”***) *-* pages used as counter-examples for Semi-structured classification. To learn more, see [TDM for Classification Models](/v42/docs/tdm-for-classification-models) > [!NOTE] > Searching for a specific layout > > You can search for a specific layout using the **Layout Group** drop-down list. - Select a layout variation from the drop-down list. > [!NOTE] > Searching for layout variations > > You can search for and select a layout variation directly from the **Layout Variation** drop-down list. In v42.2 and later, selecting a layout variation automatically assigns the corresponding layout group. - Create a new document using the selected pages. - Reclassify documents that were incorrectly grouped. > [!NOTE] > Page Numbers > > All pages in the left and middle panels show their submission page number based on the order in which they were uploaded. > > - Grouped documents are sorted by the submission number of their first page. > - When you create a new document manually, the pages are automatically ordered by submission number. ![](https://cdn.us.document360.io/87894cef-4958-4f3f-be6f-b75a78c82548/Images/Documentation/classification_variations_change.gif) - Add, remove, and reorder pages within a document. ![](https://cdn.us.document360.io/87894cef-4958-4f3f-be6f-b75a78c82548/Images/Documentation/add_to_doc_append.gif) ![](https://cdn.us.document360.io/87894cef-4958-4f3f-be6f-b75a78c82548/Images/Documentation/reorder.gif) - Add a page from one document to another, using the **Add to Doc** button. Note that this will be treated as a manual match, and the content on the page will require manual extraction. - To move a page between documents, make sure both documents use the same layout variation. - To move a page to the last position in the document, click the **Append page** button. Note that if you choose to append it, the machine’s confidence will drop, and it will be sent for manual extraction. - Remove a page by clicking the ![](https://cdn.us.document360.io/87894cef-4958-4f3f-be6f-b75a78c82548/Images/Documentation/image(181).png) button or pressing **DEL** on your keyboard. - Reorder pages using the shortcuts or - Select the page you want to reorder and drag it to the desired position. - In v42.2 and later, when a page is appended or manually matched, it is highlighted with an orange border. Hovering over the page displays a tooltip indicating that the page was manually classified. This border is shown in both Manual Classification and Flexible Extraction tasks. ![](https://cdn.us.document360.io/87894cef-4958-4f3f-be6f-b75a78c82548/Images/Documentation/append_page_orange.jpg) #### Right Panel - Document Preview ![](https://cdn.us.document360.io/87894cef-4958-4f3f-be6f-b75a78c82548/Images/Documentation/page_preview(1).jpg) The right panel shows a zoomable full-page view of the selected page. - Rotate the page by clicking the ![](https://cdn.us.document360.io/87894cef-4958-4f3f-be6f-b75a78c82548/Images/Documentation/image(182).png) button or using your keyboard. > [!NOTE] > Machine-classified grouped documents rotation > > Pages in machine-classified grouped documents can not be modified in place. You need to remove the page from the document and once it falls under Uncategorized, you can rotate it. > > - You can rotate all selected Uncategorized pages 90° clockwise. > - During Machine Classification, the page image may be adjusted in order to obtain a match. Deselect **Machine Adjusted Image** by clicking the ![](https://cdn.us.document360.io/87894cef-4958-4f3f-be6f-b75a78c82548/Images/Documentation/image(183).png) button on the page’s preview in the left or right panel to reset the image to its submission state. > > ![](https://cdn.us.document360.io/87894cef-4958-4f3f-be6f-b75a78c82548/Images/Documentation/image(184).png) - To complete the task, click **Submit (CMD+Enter).** ### Reprocessing Misclassified documents If a document is marked as **Layout Incorrect** during **Flexible Extraction**, **Identification**, or **Transcription Supervision**, you can reprocess it and send it back to **Document Classification** for rework. Instead of being marked as **Complete**, the submission remains in progress until all documents are properly classified. #### Using Reprocessing You can trigger reprocessing from any **Identification or Transcription Supervision** or **Flexible Extraction** task. To learn more, see [Supervision and QA Introduction](/v42/docs/supervision-and-qa-introduction). 1. Go to **Submissions**. 2. Find the mismatched submission by its ID. 3. Click on the **Perform Tasks** link in the **Tasks** column for the submission. 4. In the right sidebar of the task, expand the document information and click **Mark Layout Variation Incorrect.** - Doing so removes the layout from all pages of the current document and creates a Document Classification task. ![](https://cdn.us.document360.io/87894cef-4958-4f3f-be6f-b75a78c82548/Images/Documentation/layout incorrect.jpg) 1. Click **Continue** on the warning message. - The document status changes to **Reprocessing** and is sent back to **Document Classification**. - On the Document Classification task, you’ll see the following message: ![](https://cdn.us.document360.io/87894cef-4958-4f3f-be6f-b75a78c82548/Images/Documentation/reclassify.png) - If multiple documents are affected, all must be completed before the submission status updates. 1. Reclassify your documents by following the guidance in [Document Classification Interface](/v42/docs/v42-draft-document-classification#document-classification-task) section. After you’ve classified your Structured documents, the next step is to extract the data you need. Learn how to work with Flexible Extraction by reading our [Flexible Extraction](/v42/docs/flexible-extraction) article. A manual task in Hyperscience where you confirm or correct the location of fields in Semi-structured documents. You can adjust or draw bounding boxes around field values to help your model learn where to look for the data you want to extract. You may need to perform a Field ID task when the machine is not confident enough in its prediction for a field, based on the target accuracy. A Supervision task that allows you to review or enter text the system couldn’t confidently read from a document. This task enables you to ensure accurate final data when the system’s confidence is low. A task in Hyperscience that involves human intervention to validate or correct data extraction for Structured documents. This task is used when automatic extraction isn’t fully reliable, allowing you to transcribe or adjust specific fields to ensure accuracy. An automated component that matches submission pages to the correct layouts from the Layout Library. It ensures accurate and efficient processing of Structured documents. Finds the correct Semi-structured or Additional layout for a given set of submission pages based on the words in the submitted documents. Note that NLC works on a page level. The confidence limit used to decide if a machine prediction should be sent for human review to ensure accuracy. A string of characters that appears on a specific location on a page in a Structured layout. It allows the machine to distinguish among similar layouts that a submission matches to. It can contain letters, numbers, or a combination of both. Layout identifiers help the machine achieve the best match for submitted pages. A manual task that is created when the system’s confidence in a prediction is below the confidence threshold. Supervision allows a human to review and correct the output, ensuring data accuracy through human-in-the-loop input.