Classification And Extraction
The "Classification and Extraction" settings in your document processing system provide options for configuring how documents are automatically handled upon input:
Document Splitting: This setting allows you to choose whether to split documents based on specific criteria or keep them as a single document. This can be useful when processing documents that have multiple distinct sections but are uploaded as a single file.
Amount Formatting: Here, you can enable options like rounding the total amounts in orders. This ensures that extracted data aligns with expected financial formats and rules, reducing errors in financial processing.
Table Extraction: This feature enables automated extraction of data from tables within documents. You can specify whether to extract all tables, just those relevant for costing purposes, or to automatically identify and extract tax codes. This greatly enhances the accuracy and efficiency of data extraction from structured formats within documents.
Configure Classification Rule: This option allows you to define specific patterns and criteria that help the system automatically classify and categorize documents as they are processed. This could be based on text patterns, document types, or other metadata associated with the documents.
![](https://docs.docbits.com/~gitbook/image?url=https%3A%2F%2F578966019-files.gitbook.io%2F%7E%2Ffiles%2Fv0%2Fb%2Fgitbook-x-prod.appspot.com%2Fo%2Fspaces%252FT2n2w4uDCJvv7CJ5zrdk%252Fuploads%252FooKPwGieh5JEa04NmxV7%252FBildschirmfoto%25202024-05-08%2520um%252011.11.10.png%3Falt%3Dmedia%26token%3D26e9d595-043b-4a16-80ef-fd92ac3406d1&width=768&dpr=4&quality=100&sign=38da92d9&sv=1)
Last updated