Document Processing

The document processing services work together to extract and classify structured information from documents stored in IBM Cloud Object Storage (COS). A CONNECTION_ID and BUCKET_NAME are required in addition to the standard credentials - see Setup & Prerequisites.

Services

Service	What it does
Create Schema	Generate a key-value extraction schema from sample documents
Improve Schema	Refine an existing schema using additional examples
Merge Schema	Consolidate multiple schemas into one
Text Extraction	Extract structured key-value pairs from documents in COS
Text Classification	Classify documents stored in COS

Typical workflow

1. Create a schema from sample documents using CreateSchemaService. Optionally refine it with ImproveSchemaService or combine multiple schemas with MergeSchemaService.
2. Extract structured key-value pairs from documents using TextExtractionService with the generated schema.
3. Classify documents by type using TextClassificationService with the same schema.