Primary personas: Digital Forensic Expert, Processing Analyst
Supporting personas: Case Manager, Data Analyst
View persona matrix
Workshop Scenario: "Data is imported — how do I ensure quality and prepare it for review?"
| Feature | Description | Key User Action |
|---|---|---|
| QA Tab | Dedicated pages: Encrypted, Corrupted, OCR, Unsupported, User Assigned, Flagrant, Logos, Noisy Text, Containers | Triage import issues by category |
| QA Status Error Messages | 18+ categorized error types with recommended resolution steps | Diagnose and resolve problems |
| QA Tab Actions | Audit Log, Download, Edit Placeholder, Move to Folder, OCR, Quarantine, Remove from QA, Show Import Messages, Suppress/Unsuppress, Tag, Try Passwords, Upload Replacement File | Per-record remediation |
| QA Reports | Generate from Import tab or any tab; Excel export; detailed logs | Track issue resolution |
| Duplicate Detection | 4 strategies: no exclusion, per-custodian, case-wide, custodian-ranked; family-level; EDRM_MIH support | Manage duplicate records |
| Duplicates View | MD5-based display with context grouping, Original indicator, Inactive Reason | Investigate duplicates |
| OCR | During import or post-import; configurable queue routing; PDF character threshold; OCR images in PDFs | Make image-based documents searchable |
| Noisy Text Detection | Identify repeated email footers/disclaimers; validate in Noisy Text view; suppress from search index | Clean up search results |
| Logo Detection | ML-based identification of logo images in emails; mark as Irrelevant | Suppress non-substantive images |
| Spam Detection | AI algorithm combining Pattern Recognition + Irrelevant field | Identify junk emails |
| Alias Detection (Name Normalisation) | NLP-powered grouping of name variants; auto-create aliases; verify/merge/reject entities | Improve people-based search accuracy |
| Language Detection | 80+ languages; primary and secondary language identification; n-gram classification | Route foreign language documents |
| PII Detection | Regex + word proximity + probability analytics; pre-configured patterns (phone, credit card, SSN, TFN, passport, etc.); custom Regex | Identify personal information |
| Named Entity Recognition (NER) | Detect people, places, SSNs, passport numbers, credit cards via NLP | Facilitate rapid entity investigation |
| Pattern Recognition | Regex library with pre-prepared and custom patterns; Validation Rules (e.g., Luhn); Supportive Words for context | Detect text patterns across documents |
| Flagrant Image Detection | AI-based detection of violent/prohibited/offensive content; confidence scoring | Protect reviewers; isolate sensitive images |
| Object Detection in Images | ML-based object recognition; updates Object Image Labels field | Classify image content |
| Container Management | Expansion tracked; containers suppressed from exports by default | Handle nested file structures |
| Suppression | Remove immaterial files from all workflows without deletion; reversible via Unsuppress | Reduce noise while preserving evidence |
| Move to Folder | Family-level move with propagation options | Segregate records by status |