Author: Philip Godfrey
What is Document Understanding in OCI?
- OCI Document Understanding is an AI service that lets developers extract text, tables, and other key data from document files through APIs and CLI tools.¹
Of all the AI services offered by Oracle, Document Understanding is one of the most intuitive and easy to use – and offers a wide range of functionality including data extraction, classification of documents and key-value extraction.
Under the hood, OCI Document Understanding allows you to take advantage of several pre-trained models to detect and classify objects within your document, including:
- Optical Character Recognition (OCR)
- Text Extraction
- Key-Value Extraction
- Table Extraction
- Document Classification
We have created the below table to help explain what each feature of the service broadly does as well as providing some common applications or use cases.
|
Feature
|
Description
|
Common Applications / Examples
|
|---|---|---|
|
Optical Character Recognition (OCR) & Text Extraction
|
Extract textual features from documents, such as printed and handwritten documents
|
• Business reports in PDF form • Receipts and invoices • Insurance or other application forms
|
|
Table Extraction
|
Extract text in tabular format with row/column information per cell.
|
• Item-level details in receipts • Invoices • Purchase orders
|
|
Key-Value Extraction
|
Extracts key-value information based on a pre-trained model of common document types
|
• Invoices • Receipts • Passports / Driver Licence
|
|
Document Classification
|
Classifies documents into different types based on high-level features and extracted keywords.
|
• Receipt • Resume •Driver Licence
|
Document Understanding in action through Oracle Analytics: ²
An excellent example provided by Benjamin Arnulf and Barry Mostert of example passport images used in Oracle Analytics to recognize text and expiration dates based on a pre-trained OCI AI model.
What are the benefits of using OCI Document Understanding?³
• Advanced AI possibilities
OCI Document Understanding utilizes Oracle’s computer vision and natural language processing technologies, tailored for essential enterprise functions like handling accounts payable, managing expenses, and overseeing content.
• Customisable models
Upload, label, and train custom models with your Oracle data through an intuitive user interface in the OCI console. This capability has limited availability.
• Cost-effectiveness
OCI Document Understanding is competitively priced so all users can take advantage of AI. Pay as you go structure.
With Document Understanding, you can automate tedious business processing tasks with prebuilt AI models and customise document extraction to fit your industry-specific needs.
What are some use cases for Document Understanding?
Below are just some examples but demonstrate the practical applications of OCI Document Understanding in your business but can be applied to a wide range of industries and sectors.
- Invoice and expense processing using invoice and receipt key-value extraction.
- Validation of personal identification documents such as employment verification, customer identification, shipping and passport key-value extraction.
- Forms processing for applications – like travel and immigration applications and membership programs using text extraction and key-value extraction.
- Extracting content from banking transaction documents like account numbers, bank codes, and line-item details using key-value and table extraction
- Expense analysis by extracting line-item details from complex utility bills.
How does Document Understanding work?
As mentioned earlier in the blog, it can be as straightforward as ingesting data from your object source, using Document Understanding to perform an action (e.g., text extraction and document classification) to then query the results and output them elsewhere such as Oracle APEX or OAC.
Interested to know more?
We’d be more than happy to discuss your requirements or questions, please get in touch here.
[1] https://www.oracle.com/uk/artificial-intelligence/document-understanding/
[2] https://blogs.oracle.com/analytics/post/innovate-with-oracle-analytics-and-ai-document-understanding
[3] https://docs.oracle.com/en-us/iaas/Content/document-understanding/using/overview.htm#overview
[4] https://www.oracle.com/uk/artificial-intelligence/document-understanding/
[5] https://www.oracle.com/uk/artificial-intelligence/document-understanding/#document-analytics
Contact us today to arrange an assessment or email:
Philip Godfrey
Principal Data Analytics & AI Consultant at Vertice
