Document Automation data extraction using Generative AI

Document Automation for Cloud provides Generative AI capability to extract data seamlessly from unstructured and semi-structured documents. Create learning instance with generative AI capability to process documents in English, using a Large Language Model (LLM). Note: This capability is available only in Cloud deployments with the Automation 360 v.30 release.

Note: This feature will be available with the Cloud rollout for Automation 360 v.30 release.

Benefits

Enhance extraction accuracy in a learning instance by using the Search query for Generative AI model feature when defining form fields. Document Automation offers a default customizable query based on your selected field. Transmitting your query to generative AI enhances and enables data extraction from different document types without prior training. Leverage this innovation to enhance your document processing capability.

<span>Video showing the data extraction using Generative AI feature</span>

How Generative AI improves extraction

When you create a learning instance for unstructured documents (such as: Contracts, Agreements, Reports, Letters, and Emails), the generative AI-driven data extraction capability is automatically selected. While defining the Form fields for your learning instance, you can leverage the Search query for Generative AI model option to customize your data extraction request.

For an address field, the generative AI query provides a default query such as: ‘What is the Property Address?’. You can customize this query for more focused extraction to say: ‘What is the full Property Address with city, state and zip code?' See image below for reference.

Document Automation with GenAI capability feature

On processing a document, using this learning instance, the generative AI capability will extract the complete address, instead of just the street name and number. All you need to do is define the search query in the model just once, and then for every document processed using this model, the data gets extracted with high accuracy with no additional configuration.

When creating a learning instance for semi-structured or supply-chain documents (such as: Waybill, Bill of Lading, Arrival Notice, and Packing Lists), you can leverage the generative AI-driven data extraction capability in addition to the native extraction capability based on user-provided updates in the Validator.

These are available use cases for this feature:

Create learning instance models for unstructured documents such as: Contracts, Agreements, Reports, Letters, and Emails.
- Google Vision OCR support only
- PDF and image extraction capability
- English language availability only
- Form field capability only
- Document Automation Cloud version support only
Create learning instance models for semi-structured documents such as: Waybill, Bill of Lading, Arrival Notice, and Packing Lists.

Important: Privacy Notice: When the generative AI capability is selected, the query is sent to a third-party service. Currently, the data is sent to Microsoft Azure OpenAI service, which is located in the US and EU regions. If you do not want your data sent to a third-party service, we recommend not using the generative AI feature.