Skip to content

Correspondence Automation#

The natif.ai Correspondence Automation extracts all major entities from any incoming document and classifies it for you:

  • Data such as the document's subject, receiver, sender, or payment information
  • A classification of the document's content into generic classes
  • A classification of the document's sender into generic classes

The workflow provides ocr, extractions, and classification results that can be used for automatic processing.

It is used with the workflow identifier correspondence_automation, at the processing endpoint i.e. POST /processing/correspondence_automation.

Supported return values#

As automatically included in the response JSON, unless otherwise specified via include query parameters.

Credit cost#

A Freemium account allows for up to 100 pages per month, where the cost is 65 credits per page, and 98 credits per document.

Note

A document is usually a bundle of 10 pages.

Extractions formats#

The value of the extractions key for this workflow may have one of the following forms, depending on the detected document_type.

For document_type = correspondence

All supported fields
  • schema_version: integer (possible values: [1])
  • document_type: string (possible values: ['correspondence'])
  • receiver: Receiver
    • company_name: StringExtraction
    • title: StringExtraction
    • first_name: StringExtraction
    • last_name: StringExtraction
    • address: Address
      • address_line_1: StringExtraction
      • address_line_2: StringExtraction
      • city: StringExtraction
      • zip: StringExtraction
      • country: CountryExtraction
  • sender: Sender
    • name: StringExtraction
    • address: Address
      • address_line_1: StringExtraction
      • address_line_2: StringExtraction
      • city: StringExtraction
      • zip: StringExtraction
      • country: CountryExtraction
    • phone: StringExtraction
    • fax: StringExtraction
    • url: StringExtraction
    • e_mail: StringExtraction
    • category: SenderCategoryExtraction
  • date: DateExtraction
  • payment_information: PaymentInformation
    • receiver: StringExtraction
    • banking_information: array of BankingInformation
      • validation_problem: boolean (deprecated)
      • note: string (deprecated)
      • confidence: number (deprecated)
      • bbox_refs: array of Reference
        • page_num: integer
        • bbox_id: integer
      • iban: StringExtraction
      • bic: StringExtraction
    • reference: StringExtraction
    • amount: FloatExtraction
  • subject: StringExtraction
  • doc_category: DocCategoryExtraction

Note

For a reference of the structure of each of the extractions objects see Extracted Values. Also, for accessing individual processing results or artifacts, have a look at Fetch Processing Results and Artifacts.

Important

The structure of extractions might contain optional paths. See this and this part of the documentation.