Documents — Send Bundle to Classification

Type: documents-classify-bundle  ·  Package: Documents Activities v1.4.5  ·  Output: object

Since: v1.3.0

Uploads a file with several documents (a bundle) whose split can’t be trusted to the classification station, together with the segments IDP — Classify proposed. Instead of extracting blindly, a person confirms where each document starts and what type it is.

Use it when IDP — Classify returns splitNeedsReview = true.

Documents — Send Bundle to Classification   path      = file
                                            reference = file
                                            segments  = doc["segments"]
                                            document  = doc
                                            pages     = doc["pages"]
                                            dpi       = 200

When to use it

A split is uncertain when there are unrecognised pages, or when the file was split into several documents with no printed mark at all to back it (only the model’s judgement). IDP — Classify flags it with splitNeedsReview. The typical pattern:

If   condition = doc["splitNeedsReview"] == true
     then:
       Documents — Send Bundle to Classification   path = file, reference = file,
                                                    segments = doc["segments"], document = doc,
                                                    pages = doc["pages"], dpi = 200
       Continue

How it works

Uploads the file to Zoan Cloud with its reference, the proposed segments, the page dimensions, the dpi and the retention. If you pass document, its reading travels with it as an OCR cache. The bundle lands in the environment’s classification station inbox; the log confirms it was sent. It needs the Zoan Cloud runtime context.

Required parameters

Parameter	Type	Default	Description
path	string	—	Path to the bundle file (PDF, PNG, JPEG or TIFF).
reference	string	—	Stable key for the bundle (for example, the file name).
segments	List	—	The segments IDP — Classify proposed: doc["segments"], each one { pageStart, pageEnd, type, recognized }.

Optional parameters

Parameter	Type	Default	Description
document	Dictionary	—	The whole object IDP — Classify returned. Its reading is stored as an OCR cache: extracting the confirmed segments later will not pay Azure again. Since 1.4.0.
pages	List	—	The per-page dimensions from IDP — Classify (doc["pages"]), so the station can render the pages.
dpi	int	—	The dpi the pages were read at (the same one you used in IDP — Classify).
retentionDays	int	—	How many days to keep the bundle. Empty = the environment’s default.

The OCR cache

Also pass it document (the whole object IDP — Classify returned) and the reading —words, pages, text— is stored with the bundle as an OCR cache. When a person confirms the split and Documents — Take Confirmed Bundles picks the bundle up, that reading comes back with it and each segment is extracted without re-reading the file or paying Azure again. Without document, everything works the same — the extraction just re-reads.

Output

Returns an object with id (the bundle’s id in Zoan Cloud) and reference (the key it was uploaded with).

What happens next

The bundle shows up in the environment’s classification station (opened from Centro › IDP, Center › IDP). A person adjusts the boundaries and types and confirms. From there, Documents — Take Confirmed Bundles picks it up to extract each segment.

Example

Send only the doubtful files to review and extract the rest directly:

IDP — Classify   path = file   projects = ["supplier-invoice", "purchase-order"]   dpi = 200
                 → output: doc
If   condition = doc["splitNeedsReview"] == true
     then:
       Documents — Send Bundle to Classification   path = file   reference = file
                                                    segments = doc["segments"]   document = doc
                                                    pages = doc["pages"]   dpi = 200
                                                    → output: sent
       Log   message = "Bundle " + sent["id"] + " sent to the classification station"
       Continue
For Each   items = doc["segments"]   itemVariable = segment
  IDP — Extract   document = doc   project = segment["type"]
                  pages = segment["pageStart"] + "-" + segment["pageEnd"]

Common errors

Message	Cause and fix
'path' is required. / 'reference' is required.	A required parameter is missing.
File not found (system error when reading path)	The path does not exist on the robot’s machine. Check it first with File Exists.
Document activities need a Zoan Cloud runtime context, which the Runner provides when it launches the playbook. Missing: …. …	The run has no Zoan Cloud. Run it from Zoan Cloud or from the Designer with a session.
Zoan Cloud rejected the upload (…): …	Zoan Cloud did not accept the bundle. The detail carries the code; retry.

Related activities

• IDP — Classify — classifies per page and proposes the segments.
• Documents — Take Confirmed Bundles — picks up the bundles already confirmed.