Contracts OCR

To access the Contracts Image Viewer and functions such as search and navigation, you must run Contracts OCR. Contracts OCR (Optical Character Recognition) translates images of text, such as scanned and redacted documents, into actual text characters. Contracts must have information about the location of words in the extracted text so that it can map text to image and highlight the image accurately.

Prerequisites

Before running Contracts OCR:

  • You must run Relativity Imaging and successfully generate images for the document. If no images are present, there is nothing for Contracts to OCR.
    For more information on how to run imaging in Relativity see Imaging.
  • The Contracts Extracted Text field must be empty. Contracts does not run OCR on documents that have this field already populated.

Running Contracts OCR

To run Contracts OCR:

  1. Go to the Contracts OCR Sets tab.
  2. Click New Contracts OCR Set.
  3. Enter a Name for your Contracts OCR Set.
  4. For Data Source, select a saved search to run OCR on.
  5. Select the Language you want the OCR engine to recognize. You can select more than one language.
    For a list of languages supported by Contracts OCR see Supported languages matrix.
  6. Optionally enter Users to email when OCR completes under OCR Set Notification.
  7. Click Save.
    An image of the Contracts OCR Sets page
  8. Click Run OCR in the right console.
  9. If there are errors, you can click the Download Errors link in the right console to download and review them.
    An image of the Management Console with the Download errors button selected.

Fields auto-populated by Contracts

Below is a list of all fields that Contracts will auto-populate when you run imaging and OCR.

Field name Field type Field auto population
Contracts Extracted Text Long-text Auto-populated with the full extracted text of the document.

Note: If you run imaging and OCR and later edit the values of the fields, running imaging and OCR again will replace your manual edits.

Rerunning Contracts OCR

To rerun Contracts OCR:

  1. Navigate to your Contracts OCR set and select Edit.
  2. Select Yes for Overwrite Contracts Extracted Text.

    Note: The Overwrite Contracts Extracted Text setting is set to No by default. When set to No, Contracts OCR will skip documents containing a value in the Contracts Extracted Text field. When set to Yes, Contracts OCR will overwrite the Contracts Extracted Text field for documents containing a value. If the documents in your saved search do not have values in the Contracts Extracted Text field, this setting does not affect the job as there is nothing to overwrite.
  3. Click Save.
  4. Click Run OCR in the right console.

Rerunning Contracts OCR requires the following steps to ensure data gets repopulated correctly.

Begin by creating a new tab for Contracts Image Results:

  1. Navigate to the Tabs tab.
  2. Confirm that you have not already created a Contracts Image Results tab by filtering for Object Type > is > Contract Image Results.
  3. If the tab already exists, note its name and move on To rerun Contracts OCR:. If not, continue here.
  4. Click New Tab and enter the following details for the tab: 
    • Name— Contract Image Results
      You can name this tab whatever you’d like, but these steps assume that you named the tab Contract Image Results.
    • Tab Type — Object
    • Object Type— Contract Image Results
    • Order— 9999 or any order you want to use
  5. Click Save.

To rerun Contracts OCR:

  1. Navigate to the Contracts Image Results tab you created.
  2. Use the Document field to filter for the identifier of the documents for which you want to rerun OCR.
  3. Delete all rows associated with the applicable document.
  4. Clear out the existing data in the Contracts Extracted Text field for the applicable documents.
  5. Rerun the Contracts OCR set.