Document Automation high-level data flow
- 최종 업데이트2025/07/15
Document Automation high-level data flow
Document Automation uses different data flows for different features available in the Control Room. Review the high-level data flow to understand how data traverses for each feature through different components.
Data extraction using generative AI providers
The following image shows the end-to-end data flow through different components for generative AI providers:| On-Premises |
|---|
|
| Cloud |
|---|
|
The following sections represent different stages of data flow through different components when using generative AI providers:
- Stage 1: Uploading files to the Control Room
-
On-Premises 
Cloud 
The user uploads files to the Control Room or a scheduler bot uploads the file from a shared location. The files are temporarily uploaded to the Control Room storage services.
- Stage 2: Document extraction process using
-
On-Premises 
Cloud 
The first step involved in document extraction is processing documents for OCR. Documents are processed using ABBYY OCR on the Bot Runner device or using Google Vision OCR via the Automation Anywhere proxy gateway.
On-Premises 
Cloud 
The Bot Runner device initiates the data extraction process using either the Automation Anywhere pre-trained models or third-party Cloud extraction services.
- Automation Anywhere pre-trained models: Data extraction is processed on the Bot Runner device.
- Third-party Cloud extraction:
- Document Automation subscriptions: Data extraction requests are sent and received from the third-party Cloud extraction services via the Automation Anywhere proxy gateway.
- Bring your own key (BYOK): Data extraction requests are sent and received directly from the third-party Cloud extraction services without using the Automation Anywhere proxy gateway.
- Stage 3: Downloading output
-
On-Premises 
Cloud 
The data extraction results are downloaded on the network path defined by the user as CSV or JSON. Customers typically create bots to upload this information to downstream applications or system of records.
Data extraction using Microsoft Azure AI Document Intelligence
The following image shows the end-to-end data flow through different components for Microsoft Azure AI Document Intelligence:| On-Premises |
|---|
|
| Cloud |
|---|
|
- Stage 1: Uploading files and fetching configuration details
-
On-Premises 
Cloud 
The user uploads files to the Control Room or a scheduler bot uploads the file from a shared location. The files are temporarily uploaded to the Control Room storage services.
- Stage 2: Data extraction process
-
On-Premises 
Cloud 
The Bot Runner device initiates the OCR and data extraction process using Microsoft Azure AI Document Intelligence services. Data extraction requests are sent and received directly from Microsoft Azure AI Document Intelligence services for both Document Automation subscriptions and BYOK.
- Stage 3: Downloading output
-
On-Premises 
Cloud 
The data extraction results are downloaded on the network path defined by the user as CSV or JSON. Customers typically create bots to upload this information to downstream applications or system of records.
Video: Document Automation architecture
- On-Premises deployments using generative AI providers
-
The following video shows how the data flows in the On-Premises deployment when using generative AI providers:
- Cloud deployments using generative AI providers
-
The following video shows how the data flows in the Cloud deployment when using generative AI providers: