Document Classifier - Usage Guide
Document Classifier checks content of input PDF,JPG,PNG or TIFF using
pdf/classifer endpoint. Then uses AI to automatically determine class of this document (for example,
invoice etc) and returns to user. Can also use custom defined rules for classification rules.
Use Document Classifier to quickly build workflow of sorting out input documents and pdf files.
How to use built-in AI rules
pdf/classifier endpoint with your input document in
Upload Files if you need to upload local file first).
How to Create and test custom classification rules
Classification rules are storred in CSV format with one line per class in the following format:
className, logicType, keyword1, keyword2, keyword3 ..
className- a name of a class. It will be returned if rules from this class matched the document
logicType- (optional) the logic to use for keywords. Can be
ORmeans that to identify the class it should match 1 or more keywords from the list).
ANDmeans that all keywords must be found. If logic column is not set then the app uses
ORlogic be default (i.e. one of keywords listed should be found to determine a class)
keyword3etc) - is the keyword or a phrase to check. Can use regular expression, for example
/Medical Report|Med Report/i
Invoice,OR,Invoice Number,Invoice #,Invoice No,Tax Invoice,, Purchase Order,OR,PO Number,Order Number,Order No,,, Bill,OR,Bill Date,Billing Period,Bill Number,,, Bank Statement,OR,/Account Statement/i,/Statement of Account/i,Business Checking,Accounts Payable,/Statement No/i, Income Statement,OR,/Income Statement/i,,,,, Has US Number,OR,"/\b-?(\d+,?)+(\.\d\d)\b/",,,,, Medical Report,AND,/Medical Report|Med Report/i
Classifier Testing Tool
Testing and composing rules manually may be tiresome. That is why we’ve created
PDF Classifier Testing Tool that you can use to compose, test and update rules. You can also generate ready-to-use JSON request that you can use with PDF.co or API Server API calls.
How to Use
Classifier Testing Tool in
- Download ByteScout PDF Multitool app from this page (requires Windows 7 or higher)
ByteScout PDF Multitool.
PDF Multitool. Then run
Classifier Testing Toolfrom the side panel at the left from
Document Parser - Classifier Test Tool.
Classifier Test Toolwill run. Select PDF/jpg/png document or a folder with documents at the left panel with list of files.
- Click on the
Test Rulesbutton to test rules. Review results and adjust results.
You can save rules as CSV. Or click on
Copy JSON to generate JSON request for use with PDF.co (cloud) or API Server (on-prem).