3.5
Canopy has made significant improvements to the overall Processing experience, delivering faster performance, higher accuracy, and greater reliability. Key enhancements include:
- Faster Processing Speed: We’ve optimized processing for several key file types, including Excel, CSV, PDF, Word, and SQL, enabling noticeably quicker processing times.
- Improved OCR Performance: We’ve enhanced OCR (Optical Character Recognition) performance and quality, resulting in faster, more accurate results with fewer failed jobs.
- Fewer Files Reported as Corrupted: We’ve upgraded our processing engine to correctly handle situations where certain file types (
.doc,.xls,.xlsx,.bak,.tiff,.gif,.csv,.png, and.xpt) could be reported as corrupted but were not. - More Files Skipped Automatically: We’ve enhanced our system to automatically skip Microsoft temporary files. This means fewer irrelevant files for you to assess and review, streamlining your workflow. These files include:
| Media/MIME Types/Signature | Non Exhaustive Extension List | Kind of Document |
|---|---|---|
| Files starting with a tilde (~) that is followed by a dollar sign ($) and of one of these MIME Types: application/msword, application/vnd.openxmlformats-officedocument.wordprocessingml.document, application/vnd.openxmlformats-officedocument.spreadsheetml.sheet, application/msexcel, application/vnd.ms-powerpoint, application/vnd.openxmlformats-officedocument.presentationml.presentation, application/pdf |
.doc, .docx, .xls, .xlsx, .ppt, .pptx, .pdf | Window Temporary Files, also known as “owner file” |
| Exactly “Thumbs.db” in OLE Compound File Format | Thumbs.db | Hidden Temporary Windows Folder/Directory File |
These improvements mean fewer errors, fewer file to review, and less need for users to contact Support to reprocess files.
We’ve refactored our email-inclusiveness algorithm to significantly improve the speed of email threading. This enhancement means users can quickly and efficiently process large volumes of emails, with threading completed much quicker during post-processing.
We’ve added sorting to the Audio Duration field in the Document Page. This enhancement makes it easier to quickly locate and manage audio files by their duration, streamlining workflows that involve audio data.
Users can now play all transcribed audio and video files directly within the Document View, regardless of their original file type. This enhancement streamlines the review process by enabling seamless playback alongside the transcribed text, making the review process faster and more efficient.
We’ve resolved an issue where random numbers were being incorrectly detected as Social Security Numbers (SSNs). This fix ensures that only actual SSNs are detected, improving the accuracy of PII detection and reducing false positives.
We’ve fixed an issue where Canopy was detecting PII within hyperlinks, even when the linked content was not visible in the Document View. To prevent this, Canopy will no longer open and detect PII within hyperlinks during document processing and assessment. Additionally, users cannot redirect any hyperlinks from the Document View.