Table Identification QA tasks are specific to Semi-structured documents with tables. Table Identification QA tasks are part of the Identification QA task queue in Tasks > Perform Tasks .  Note that Field Identification QA tasks are also loaded into the Identification QA task queue. To learn more about Field Identification QA tasks, see Field Identification Quality Assurance . To enable Table Identification QA, you need to: Go to Flows . Click on a flow. Enable Table Identification Quality Assurance in the left-hand sidebar. Click Save . Table Identification QA Sampling Rate Documents that are matched to Semi-structured layouts with tables are eligible for QA sampling. The QA sampling rate can be configured separately for each flow by following the below steps: Go to Flows . Click on a flow. Edit the value for Transcription QA Sample Rate . Click Save . Note that Table Identification QA samples on a document level. For example, if you …

an error, the callback will be called with message_type === MessageType.ERROR and info will be an Error object. Completed tasks - when all tasks are complete, the callback will be called with message_type === MessageType.COMPLETE , and info is an object with Purpose types as keys and the corresponding number of completed tasks as values. One of the following parameters: submission_id: string | number To complete tasks for a given submission ID. document_id: string | number To complete tasks for a given document ID. case_id: string | number To complete tasks for a given case ID. task_uuid: string To complete a specific task. purposes: Array To complete tasks for specific task purposes. You can find an example of the init function below: const hyperscienceCallback = (message_type, info) => { if (message_type === HyperscienceWidget.MessageType.ERROR) { console.error(info.message); } else if (message_type === HyperscienceWidget.MessageType.COMPLETE) { console.log('Tasks Completed …

In the Layout Editor for both Structured and Semi-structured layouts, there are several functions available to assist in creating and editing layouts.  The sections below list the Layout Editor functions that can be accessed via the toolbar above the layout page image, as well as keyboard shortcuts you can use.  For layout drafts that were created using the “Copy to new layout variation” feature, you can see the name of the source layout or layout variation by clicking on the information icon ( ). Note that the layout source information only appears for draft layouts or uncommitted layout variations, not for locked layouts or committed layout variations. Toolbar functions Semi-structured layout editor From left to right on the toolbar: Filter  – search for a field or field group within the layout. Undo  and  Redo  – allows recent changes to fields (resizing or moving bounding boxes, or defining metadata) to be undone or …

Overview If you create a new Semi-structured layout version, there will be no models immediately available. For optimal layout performance, train a model on the newest layout version. Recall that identification models are trained at the layout level. Increase Field ID model performance (accuracy and automation) by retraining with additional Field ID Supervision and QA documents.  Increase Table ID model performance (accuracy and automation) by retraining with additional documents that have gone through Table ID Supervision and Table ID QA.  The application can be trained on-premise and  deployed to a distinct machine in order to separate model training resources from document processing resources. For more information about this, see  What is the Trainer? Training requirements The document requirements for training Field ID and Table ID models are the same. Field ID uses Field ID Supervision and Field ID QA data, while Table ID uses Table ID Supervision and …

Custom Supervision task. Keyers can use this additional context on the Custom Supervision task’s page as they work on a task. Apply custom decisions To apply custom decisions to fields, table cells, pages, documents, or cases, you can configure custom drop-down menus on the Custom Supervision task. For example, a Custom Code Block can use business logic to approve documents. If the block fails to approve a document, a Routing Block can send this document to Custom Supervision where a keyer can manually review the unapproved document and apply a custom decision to it. Custom decisions for fields, pages, documents, and cases are displayed in the right panel, while custom decisions for table cells are displayed at the bottom of the middle panel inside the table editor. To reveal the decision drop-down menu for a given cell in the middle panel, you need to select the cell …

2. Create a bounding box for the field’s occurrence. To remove a field’s occurrence, click the Remove occurrence button ( ) next to the occurrence’s name in the right-hand sidebar. To capture additional text segments for a given field, you can add additional bounding boxes. To add an additional bounding box, follow the steps below: a. Click Add another text segment . b. Draw a bounding box for the additional text segment. Note that you can repeat steps 1 and 2 until you identify all text segments of a field. To remove a field’s bounding box, select the bounding box and click its X button. Click Save Changes . To view annotations for specific fields only: Expand the Show Fields drop-down menu at the top of the page. In the drop-down list that appears, select the fields whose bounding boxes you would like to review. View …

User Experience Tooltips when moving the pointer from one text box to another – When a user hovers over a text box, a tooltip is shown, but when the user hovers over another text box, a tooltip for that text box is not shown. This issue affects various portions of the application, but it primarily affects the Layout Editor for Structured layouts. Using calendars in date filters – Using the drop-down menus in calendars to select different months sometimes causes the calendars to automatically close. Workaround: To select different months, use the Previous ( ) and Next ( ) buttons that are located next to the drop-down menus. Layouts and Layout Variations Multiple live versions of a layout variation – The system allows you to deploy multiple versions of a layout variation across different flows, as it does not perform any validation in this area when assigning a release to a flow. However, since we …

When you click the Document ID for a submission in the Documents table, you will be taken to the Document Output page. The Document Output page contains the original page image, the machine and manual transcriptions, and some additional details that may assist in debugging and performance investigation. This page has three main sections: the document summary, the field list, and the image viewer. Document summary This section is at the top of the Document Output page and contains the aggregate stats of all pages in that document. This section is hidden by default, so to view this section click on the blue downward arrow next to the document name. Status If there are outstanding Supervision tasks for the document, a link will appear that allows you to complete those tasks. Upon completing the task, you will be redirected back to the Document Output page. If there are no available …

Annotations link. For nested tables, the Table-level Automation table separates the parent and child columns into two subtables. Viewing a table column’s training data If you are interested in reviewing the ground-truth, or training, data for a particular table column, you can do so by following the steps below. Troubleshooting table columns with low automation rates If the Table-level Automation table shows that a particular table column has a low rate of automation, you can troubleshoot it by following these steps. To view a table column’s annotations: In the Automation table, click View Annotations in the table column’s row. View the table column’s bounding boxes in the given document and make any necessary edits, as described in View and edit table column annotations . Click → at the top of the page to see the table column’s bounding boxes on the next available document.

Field Identification QA tasks are specific to Semi-structured documents. All fields’ occurrences and bounding boxes are eligible for Field Identification QA sampling. If the Continuous Field Locator model improvement setting is enabled in the "Identification" section of Administration > System Settings , Model Validation Tasks will also be loaded into this queue. These tasks look identical to Field ID QA tasks. For more information about these tasks, see Model Validation Tasks . To start a Field Identification QA task, follow these steps: Go to  Tasks > Perform Tasks . In the  Quality Assurance Tasks  card, click  Perform Tasks  for  Identification QA. In order to improve performance, it is imperative to perform QA tasks using the best practices. For more information on these, see  Best Practices for Field ID Supervision and QA . Field Identification QA tasks During Field Identification QA, you need to review all fields that are sampled for QA within a document and …

Overview If you create a new Semi-structured layout version, there will be no models immediately available. For optimal layout performance, train a model on the newest layout version. Recall that identification models are trained at the layout-level. Increase Field ID model performance (accuracy and automation) by retraining with additional Field ID Supervision and QA documents.  Increase Table ID model performance (accuracy and automation) by retraining with additional documents that have gone through Table ID Supervision and Table ID QA.  The application can be trained on-premise and  deployed to a distinct machine in order to separate model training resources from document processing resources. For more information about this, see  What is the Trainer? Training requirements The document requirements for training Field ID and Table ID models are the same. Field ID uses Field ID Supervision and Field ID QA data, while Table ID uses Table ID Supervision and …

Overview To map groups from your identity provider to Hyperscience permission groups, you must first add an authentication group . If an external user tries to log in without appropriate mapping, they will receive the following error: “This user account does not have permission to log in. Please contact your system administrator.” Adding an authentication group Go to Users > Authentication Groups. Click the Add Authentication Group button. Set a name for the group. For LDAP, the name of the authentication group should be the full LDAP Group DN (e.g., CN=DATA_CLERK,OU=HSCORP,DC=corp,DC=hyperscience,DC=com ). For SAML configured outside of Azure Active Directory (Azure AD) and for OIDC, the name of the authentication group should be the full OIDC Group name (e.g., data_clerk ). If you've configured SAML in Azure AD, the name should be the group's Object ID, not the full …

The Transcription Sampled Errors table reports errors made by human users during Transcription Supervision. The Transcription Sampled Errors table includes both field and table cell transcriptions. To adjust the number of rows shown, use the drop-down at the bottom right of the table. You can view 10, 25, 50, or 100 rows per page. The table displays each error for the selected time period and data type (Name, Address, All Data Types, etc). By clicking on the arrow ( > ) at the left side of any row, the row will expand to show two columns for each error alongside the cropped field image as it appeared on the submitted page. If a field has multiple bounding boxes, all bounding boxes will be visualized. In the left column, you will find the Data Type, the Field Name, and the Layout in which the field information was sourced. In the right column, you …

The methods you use to add and deactivate users depend on what kind of Hyperscience instance you’re using. On-premise / private cloud instances You can add and deactivate users by following the processes below. Adding new users There are two ways to add users to Hyperscience, neither of which can be done through the main user interface: Directly in Hyperscience :  Native, or local, users can be added in /admin/auth/user/add/ . Additionally, users can be added in bulk via CSV upload in /admin/auth/user/import-csv/ . The CSV file must be in the following format: username,password user1,password1 user2,password2 ... Through an external authentication provider : New users will be created in Hyperscience the first time they log in after being authenticated by your provider. External authentication methods and API users If you are using an external authentication method, you have the option of periodically revalidating API …

Overview With the Message Queue Notifier Output Block, you can configure connections to the following message queue types: ActiveMQ Amazon SQS IBM MQ RabbitMQ To select the message queue type you want to use for a Message Queue Notifier connection, click on its name in the Message Queue Type drop-down list at the top of the block’s settings. If you would like to use a Message Queue Notifier connection in a SaaS instance and your MQ service is not public, you should create a firewall pinhole for the connection. Contact your Hyperscience representative for more information. Sample use cases I have extracted content from insurance forms and want to send the JSON downstream to my IBM MQ in order to populate other systems. I have transformed submission data and want to send it to my RabbitMQ, where it will be picked up by internal software to be further …

the subflow connected to the Manual Identification Block, a copy of Submission State Notifications V37 that contains your changes is created and connected to the Manual Identification Block. By default, this new subflow is called “Submission State Notifications V37 (Copy).” The subflow connected to the Manual Transcription Block remains unchanged. If Submission State Notifications V37 is a subflow for other top-level flows or is connected to other blocks in the group you’re currently editing, those Submission State Notifications V37 subflows remain unchanged. Click Save everywhere this subflow is used in this parent flow to create a copy of the subflow that is specific to the flow containing the subflow’s connected block (i.e., this subflow’s parent flow).  This option is only available if the subflow is connected to multiple blocks in the parent flow. For example, if the Submission State Notifications V37 subflow is connected to …

Overview With our Box Listener Input Block, you can process content stored in Box. This content can then be mapped back to Box content as metadata or can be sent to other downstream systems. The Box Listener Input Block is available in both SaaS and on-premise versions of the Hyperscience application. Sample use cases Users can take extracted metadata from Box’s content and map it to the metadata fields on the content itself. Users can take extracted data from Box’s content and send it downstream for further processing via an HTTP Notifier Block or another Output Block. Block settings table In addition to the settings outlined below, you can also configure the settings described in Universal Integration Block Settings .  Name Required? Description Folder To Scan For Submissions Yes The ID of the Box folder the connector scans for image files.  Folder to Move Completed Files Yes The …