Document Processing

From PDF to JSON in minutes. Meet BotCity Docs.

Discover now a new approach that mimics the way human vision addresses document reading

Enterprise applications and services have the constant need to read, parse and ingest information from a huge variety of documents such as invoices, pay stubs, tax documents and others.

When dealing with structured formats such as CSV or spreadsheets the task at hand is trivial but when it comes to text-based or scanned PDF documents and images this becomes a struggle.

To address this issue, developers often make use of regex rules or convert the document to a structured format like XML to parse it. This process is not only very laborious depending on the number of fields in the document but it is also highly sensitive to changes in the document or missing fields.

Cloud-based pay-per-page services offering a combination of pre-made templates and AI-based document parser generators are on trend  but most of the time those services are niched and outside of the predefined scope of templates available they can only deal with some structured tabular data from text-based PDFs. Moreover, it takes a considerable effort and a large dataset of files to train the AI model which will parse the files with an acceptable level of confidence.

We humans are more resilient to change on documents when it comes to changes on positions or fields since our vision and brain are always looking for a relationship between labels and values.

Let’s talk about BotCity Documents

BotCity Documents is a framework which allows you to easily create parsers and read documents using Python or Java programming language, in the same way as you naturally would read a document, by establishing a relation between labels and fields.

Using BotCity Studio intuitive interface and automatic code generation alongside the BotCity Documents framework for document parsing, code to parse a given field in the document is generated pretty simply:

Step 1 – Select the field in the document

Step 3 – Code is generated automatically

This process is repeated for each field in the document you need to read and your custom parser is built in minutes.

By leveraging the BotCity plugins to seamlessly integrate with your favorite OCR provider, such as Google Cloud Vision, Azure Cognitive Services or even the open-source project Tesseract, BotCity Documents can be extended to transparently deal with not only text-based PDFs but also scanned PDFs and image files using the same codebase.

All this means less headache creating multiple readers, parsers and integration with third-party services.

Take a look into BotCity Documents in action and see how you can boost your team’s productivity by constructing parsers not only faster but in a maintainable and more reliable way.

Head of Developer Experience @ BotCity.

Leave a Reply

%d bloggers like this: