Vault RIM users may upload a large number of documents frequently. The RIM Document Classification Bot (RIM Bot) can automatically classify new documents, saving your organization time and effort. Auto-classification with the RIM Bot can increase compliance by reducing the number of classification errors and surfacing potential issues sooner.
When trained to use RIM Bot for auto-classification, Vault analyzes documents added to the Document Inbox and populates their Document Type, Subtype, and Classification fields, with the current status of each document listed in the RIM Auto-Classification column. This column is empty when RIM Bot is not in use.
Once this auto-classification is complete, you can review it before marking it as complete within the Document Inbox.
Note: This feature is available in all RIM Vaults when an Admin deploys a trained model.
How to Use Auto-Classification
Once an Admin deploys a Trained Model, no additional action is needed on your part.
The following document upload methods result in RIM Bot auto-classification:
- Uploading a document normally and selecting Classify documents later
- Dragging and dropping documents into the Document Inbox
- Uploading documents via the Veeva Snap mobile application.
- Uploading via Vault API
- Uploading via Vault Loader
- Uploading via FTP
- Uploading via Vault Mobile
- Documents created via Email Processing
How the RIM Bot Auto-Classifies Documents
RIM Bot queues and auto-classifies documents according to the following logic:
- Vault checks the origin of each file and assigns it to a classification queue:
- Documents uploaded via API, Vault Loader, FTP, or email are placed in a bulk processing queue, ensuring that large imports do not slow down typical auto-classification processes.
- All other documents, including those uploaded via Veeva Snap and Vault Mobile, are placed in an express processing queue.
- The RIM Bot automatically scans each added document. In the Document Inbox, you can see the progress for each document in the RIM Auto Classification field. Each document lists one of the following statuses:
- Express Queued…: The RIM Bot is waiting to process the document from the express queue.
- Bulk Queued…: The RIM Bot is waiting to process the document from the bulk queue.
- Done: The file has finished processing.
- If the RIM Bot can auto-classify the document, Vault populates the Type, Subtype, and/or Classification accordingly. Vault also adds the RIM Auto-classified document tag.
Note: If you cannot see the RIM Auto Classification or Tags fields, add them as columns in your Document Inbox. If either field is not selectable, contact your Admin to update the field configuration.
While the time to process each document can vary, Vault aims to have each file processed in five (5) seconds once the queued item is started.
Accepting Auto-Classifications
Once Vault sets the RIM Auto-Classification document field to Done, use the checkboxes to select auto-classified documents, then click Complete to enter any necessary document fields. You can only complete documents with the same classification in bulk.
Once complete, the uploaded documents are available for additional processing. Vault also tags documents as RIM Auto-classified.
Rejecting an Auto-Classification
If you find that RIM Bot applied an incorrect classification, navigate to the document and select Reclassify as normal.
Auto-Classification Limitations
- The below RIM document types (and their subtypes and classifications) are not available for auto-classification. Other document classifications may also not be available to the RIM Bot if there are not enough documents to train the RIM Bot on that classification.
- IDMP (
idmp__v) - Submission Ready (
submission_ready__v) - Archive (
archive__v) - UDI (
udi__v)
- IDMP (
- The RIM Bot only auto-classifies documents if it is confident in its selection. Documents typically have low confidence when the document could easily be classified as two or more different document types.
- Some categories of documents cannot be auto-classified. These include:
- Audio or video files
- Non-text files, such a ZIP files, statistical files, or database files
- Non-English files
- Files where Vault cannot extract text, for example, if the text is too blurry