Here is a quick project to convert Unstructured data to Structured data.
We will extract Unstructured data from Purchase orders in PDF format into CSV files. The overview video below shows what we will look to accomplish in this project.
The Digitization of documents in A2019 involves two steps:
- Creating a Learning Instance: We provide a few sample Purchase Order documents so that AI can learn. We then review and confirm or correct the mappings so that the AI learns the fields correctly. Here is a video showing that:
2. Once we have the learning instance, we will use bots to upload the Purchase orders that we like to process to the Learning instance. The Instance processes the PDF documents and provides structured data in CSV format. We will use another bot to download those CSV files. Here is a video showing that:
That was a walkthrough of how we can Digitize information using AI (A2019 IQ Bot) to a format that we can use for future processing. For e.g. We can take this PO data in CSV files and enter the information in an ERP system automating the Purchase order process. We will explore that in a future post.