Email attachments analysis introduction
When customers send emails, key information is often embedded in attachments rather than in the email body. Without a way to read those files, an email triage system processes only part of the message, which can result in incorrect routing of Cases or missed critical details. Pega Email Bot™ addresses this challenge by automatically analyzing the content of email attachments during the triage process, so that the full context of every message is available for accurate routing and Case Management.
Email attachments analysis overview
Pega Email Bot uses natural language processing (NLP) and machine learning models to detect entities in supported attachment types. Entities are data points (for example, names, dates, amounts, or policy numbers) that help the system understand the intent and context of an email. After detection, these entities, combined with the text analysis of the email body, support intelligent routing decisions, such as opening a Case or sending an automated reply.
Supported file types for email attachments analysis
Pega Platform™ uses machine learning models to detect entities in the following file types:
- Microsoft Word (DOC, DOCX)
- Open Document Format (ODT)
- Portable Document Format (PDF)
- Rich Text Format (RTF)
- Plain Text (TXT)
Optical Character Recognition
Not all attachments contain machine-readable text. Scanned documents and image-based files require an additional processing step before entity detection can occur. The Optical Character Recognition (OCR) feature converts image-based content into electronic text, making it available for analysis as if it were part of the email body.
The OCR feature supports the following file formats:
- Portable Document Format (PDF)
- Joint Photographic Experts Group (JPG)
- Portable Network Graphics (PNG)
- Tagged Image File Format (TIFF)
In addition to converting image content, the OCR feature highlights detected entities specifically in PDF attachments, which helps email Case workers review results. In on-premises environments, install the Pega OCR component from the Pega Marketplace to enable this analysis.
Benefits of analyzing email attachments
By reading both the email body and its attachments, Pega Email Bot builds a more complete picture of each incoming message. This approach results in the following outcomes:
- More accurate email routing, because the system interprets the full content of a submission rather than the subject line or email body alone.
- Improved Case Management, because relevant entities from attachments are automatically detected and associated with the correct Case.
- Reduced manual review time, because email Case workers spend less time opening and reading individual files to determine next steps.
This Topic is available in the following Module:
¿Quiere ayudarnos a mejorar este contenido?