The First Steps to Integrate with DocDigitizer PowerCapture

First steps to Integrate with DocDigitizer PowerCapture

To get started with the full-service offer by DocDigitizer PowerCapture, you will first need to create an account according to your organizational requirements.

To do this, we have specified the following set of requirements:

  • Identification
    • Name - The name of the organization
    • Email - The email of owner/responsible for the project (customer)
  • Context
    • Documents type - The type of documents to be submitted (invoice, pay slips, etc.)
    • Fields - Those to be extracted from each type of document (Fiscal number, Document number, etc.)
  • Queue
    • Has Machine Learning/AI - Those that allow automatic extraction
    • Has Human Revision - Those with human-in-the-loop (reviewers)
  • SLA
    • SLA - Determine a deadline to deliver the data
    • Max Docs Per Minute - The number of documents admitted per minute
    • Time Zone - The time zone associate with your organization
    • Calendar - Work time

Note: there is also a Free Trial Account, where users only have to supply identification.
Go to this page and fill out the request form:
Free Trial Account

Afterward, you will receive an email with some information to help get started and on the Postman collection.
The Postman Collection sent is already configured with API_KEY that authorizes access to the DocDigitizer PowerCapture API and also identifies the organization.

Glossary

Nomenclature and synonyms that are used in this guideline

  • Feature: name used when configuring or referencing document type in DocDigitizer PowerCapture platform
  • Field: name used to reference data to be captured/extracted from the document

Organization Identification

We call your DocDigitizer PowerCapture Account an Organization, where multiple individual user accounts may have access.
You will want to add a user account for every individual accessing your organization, whether to review data or other permitted actions.

Organization Context

The documents submitted to DocDigitizer PowerCapture follow the flow described in DocDigitizer PowerCapture Document Workflow.
For each organization, it is possible to configure the data that is captured from each type of document.

For instance, one organization is not interested in capturing the value of the "health number" field from document type "citizen card," while, for another organization, this field is relevant. This type of requirement can be configured.

It is possible to configure which types of documents (feature) are in the scope for each organization and define fields that are captured.
It is also possible to add new document types and fields, with previous analysis of the requirements in scope.

Organization Queue

The documents submitted can be processed in multiple streams, with parallelization at Automatic Extraction (Machine Learning/Artificial Intelligence) and Human Revision.
It is possible to opt-out of Human Revision through configuration (only Automatic Extraction).

You can also have a private queue, where reviewers from the organization are added to the process queue for reviewing the documents submitted by their organization.

Organization SLA

Associated with each organization, there is an SLA that corresponds to the maximum time that it should take for the data to be available after the document has been submitted.
This calculation has to take into account the Calendar (working hours) and Time Zone agreed on at the onset of the project.

For instance, if you have:
SLA: 480 minutes
Calendar: Weekdays from 09h to 18h
Time Zone: UTC/GMT+00:00 (Lisbon, London)

If you submit a document on Friday at 18:01, the deadline for this document will be the following Monday at 17:01.